@article{HuttererHattingenPalmetal., author = {Hutterer, Markus and Hattingen, Elke and Palm, Christoph and Proescholdt, Martin Andreas and Hau, Peter}, title = {Current standards and new concepts in MRI and PET response assessment of antiangiogenic therapies in high-grade glioma patients}, series = {Neuro-Oncology}, volume = {17}, journal = {Neuro-Oncology}, number = {6}, doi = {10.1093/neuonc/nou322}, pages = {784 -- 800}, abstract = {Despite multimodal treatment, the prognosis of high-grade gliomas is grim. As tumor growth is critically dependent on new blood vessel formation, antiangiogenic treatment approaches offer an innovative treatment strategy. Bevacizumab, a humanized monoclonal antibody, has been in the spotlight of antiangiogenic approaches for several years. Currently, MRI including contrast-enhanced T1-weighted and T2/fluid-attenuated inversion recovery (FLAIR) images is routinely used to evaluate antiangiogenic treatment response (Response Assessment in Neuro-Oncology criteria). However, by restoring the blood-brain barrier, bevacizumab may reduce T1 contrast enhancement and T2/FLAIR hyperintensity, thereby obscuring the imaging-based detection of progression. The aim of this review is to highlight the recent role of imaging biomarkers from MR and PET imaging on measurement of disease progression and treatment effectiveness in antiangiogenic therapies. Based on the reviewed studies, multimodal imaging combining standard MRI with new physiological MRI techniques and metabolic PET imaging, in particular amino acid tracers, may have the ability to detect antiangiogenic drug susceptibility or resistance prior to morphological changes. As advances occur in the development of therapies that target specific biochemical or molecular pathways and alter tumor physiology in potentially predictable ways, the validation of physiological and metabolic imaging biomarkers will become increasingly important in the near future.}, subject = {Gliom}, language = {en} } @inproceedings{MendelRauberPalm, author = {Mendel, Robert and Rauber, David and Palm, Christoph}, title = {Exploring the Effects of Contrastive Learning on Homogeneous Medical Image Data}, series = {Bildverarbeitung f{\"u}r die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, July 2- 4, 2023, Braunschweig}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, July 2- 4, 2023, Braunschweig}, publisher = {Springer Vieweg}, address = {Wiesbaden}, doi = {10.1007/978-3-658-41657-7}, pages = {128 -- 13}, abstract = {We investigate contrastive learning in a multi-task learning setting classifying and segmenting early Barrett's cancer. How can contrastive learning be applied in a domain with few classes and low inter-class and inter-sample variance, potentially enabling image retrieval or image attribution? We introduce a data sampling strategy that mines per-lesion data for positive samples and keeps a queue of the recent projections as negative samples. We propose a masking strategy for the NT-Xent loss that keeps the negative set pure and removes samples from the same lesion. We show cohesion and uniqueness improvements of the proposed method in feature space. The introduction of the auxiliary objective does not affect the performance but adds the ability to indicate similarity between lesions. Therefore, the approach could enable downstream auto-documentation tasks on homogeneous medical image data.}, language = {en} } @misc{MendelSouzaJrRauberetal., author = {Mendel, Robert and Souza Jr., Luis Antonio de and Rauber, David and Papa, Jo{\~a}o Paulo and Palm, Christoph}, title = {Abstract: Semi-supervised Segmentation Based on Error-correcting Supervision}, series = {Bildverarbeitung f{\"u}r die Medizin 2021. Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, journal = {Bildverarbeitung f{\"u}r die Medizin 2021. Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-33197-9}, doi = {10.1007/978-3-658-33198-6_43}, pages = {178}, abstract = {Pixel-level classification is an essential part of computer vision. For learning from labeled data, many powerful deep learning models have been developed recently. In this work, we augment such supervised segmentation models by allowing them to learn from unlabeled data. Our semi-supervised approach, termed Error-Correcting Supervision, leverages a collaborative strategy. Apart from the supervised training on the labeled data, the segmentation network is judged by an additional network.}, subject = {Deep Learning}, language = {en} } @article{EbigboPalmMessmann, author = {Ebigbo, Alanna and Palm, Christoph and Messmann, Helmut}, title = {Barrett esophagus: What to expect from Artificial Intelligence?}, series = {Best Practice \& Research Clinical Gastroenterology}, volume = {52-53}, journal = {Best Practice \& Research Clinical Gastroenterology}, number = {June-August}, publisher = {Elsevier}, issn = {1521-6918}, doi = {10.1016/j.bpg.2021.101726}, abstract = {The evaluation and assessment of Barrett's esophagus is challenging for both expert and nonexpert endoscopists. However, the early diagnosis of cancer in Barrett's esophagus is crucial for its prognosis, and could save costs. Pre-clinical and clinical studies on the application of Artificial Intelligence (AI) in Barrett's esophagus have shown promising results. In this review, we focus on the current challenges and future perspectives of implementing AI systems in the management of patients with Barrett's esophagus.}, subject = {Deep Learning}, language = {en} } @article{MaierDesernoHandelsetal., author = {Maier, Andreas and Deserno, Thomas M. and Handels, Heinz and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, title = {Guest editorial of the IJCARS - BVM 2018 special issue}, series = {International Journal of Computer Assisted Radiology and Surgery}, volume = {14}, journal = {International Journal of Computer Assisted Radiology and Surgery}, publisher = {Springer}, doi = {10.1007/s11548-018-01902-0}, pages = {1 -- 2}, language = {en} } @article{PassosSouzaJrMendeletal., author = {Passos, Leandro A. and Souza Jr., Luis Antonio de and Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {Barrett's esophagus analysis using infinity Restricted Boltzmann Machines}, series = {Journal of Visual Communication and Image Representation}, volume = {59}, journal = {Journal of Visual Communication and Image Representation}, publisher = {Elsevier}, doi = {10.1016/j.jvcir.2019.01.043}, pages = {475 -- 485}, abstract = {The number of patients with Barret's esophagus (BE) has increased in the last decades. Considering the dangerousness of the disease and its evolution to adenocarcinoma, an early diagnosis of BE may provide a high probability of cancer remission. However, limitations regarding traditional methods of detection and management of BE demand alternative solutions. As such, computer-aided tools have been recently used to assist in this problem, but the challenge still persists. To manage the problem, we introduce the infinity Restricted Boltzmann Machines (iRBMs) to the task of automatic identification of Barrett's esophagus from endoscopic images of the lower esophagus. Moreover, since iRBM requires a proper selection of its meta-parameters, we also present a discriminative iRBM fine-tuning using six meta-heuristic optimization techniques. We showed that iRBMs are suitable for the context since it provides competitive results, as well as the meta-heuristic techniques showed to be appropriate for such task.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @inproceedings{SouzaJrAfonsoPalmetal., author = {Souza Jr., Luis Antonio de and Afonso, Luis Claudio Sugi and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {Barrett's Esophagus Identification Using Optimum-Path Forest}, series = {Proceedings of the 30th Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T 2017), Niter{\´o}i, Rio de Janeiro, Brazil, 2017, 17-20 October}, booktitle = {Proceedings of the 30th Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T 2017), Niter{\´o}i, Rio de Janeiro, Brazil, 2017, 17-20 October}, doi = {10.1109/SIBGRAPI.2017.47}, pages = {308 -- 314}, abstract = {Computer-assisted analysis of endoscopic images can be helpful to the automatic diagnosis and classification of neoplastic lesions. Barrett's esophagus (BE) is a common type of reflux that is not straight forward to be detected by endoscopic surveillance, thus being way susceptible to erroneous diagnosis, which can cause cancer when not treated properly. In this work, we introduce the Optimum-Path Forest (OPF) classifier to the task of automatic identification of Barrett'sesophagus, with promising results and outperforming the well known Support Vector Machines (SVM) in the aforementioned context. We consider describing endoscopic images by means of feature extractors based on key point information, such as the Speeded up Robust Features (SURF) and Scale-Invariant Feature Transform (SIFT), for further designing a bag-of-visual-wordsthat is used to feed both OPF and SVM classifiers. The best results were obtained by means of the OPF classifier for both feature extractors, with values lying on 0.732 (SURF) - 0.735(SIFT) for sensitivity, 0.782 (SURF) - 0.806 (SIFT) for specificity, and 0.738 (SURF) - 0.732 (SIFT) for the accuracy.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @inproceedings{ZehnerSzaloPalm, author = {Zehner, Alexander and Szalo, Alexander Eduard and Palm, Christoph}, title = {GraphMIC: Easy Prototyping of Medical Image Computing Applications}, series = {Interactive Medical Image Computing (IMIC), Workshop at the Medical Image Computing and Computer Assisted Interventions (MICCAI 2015), 2015, Munich}, booktitle = {Interactive Medical Image Computing (IMIC), Workshop at the Medical Image Computing and Computer Assisted Interventions (MICCAI 2015), 2015, Munich}, doi = {10.13140/RG.2.1.3718.4725}, pages = {395 -- 400}, abstract = {GraphMIC is a cross-platform image processing application utilizing the libraries ITK and OpenCV. The abstract structure of image processing pipelines is visually represented by user interface components based on modern QtQuick technology and allows users to focus on arrangement and parameterization of operations rather than implementing the equivalent functionality natively in C++. The application's central goal is to improve and simplify the typical workflow by providing various high level features and functions like multi threading, image sequence processing and advanced error handling. A built-in python interpreter allows the creation of custom nodes, where user defined algorithms can be integrated to extend basic functionality. An embedded 2d/3d visual-izer gives feedback of the resulting image of an operation or the whole pipeline. User inputs like seed points, contours or regions are forwarded to the processing pipeline as parameters to offer semi-automatic image computing. We report the main concept of the application and introduce several features and their implementation. Finally, the current state of development as well as future perspectives of GraphMIC are discussed}, subject = {Bildverarbeitung}, language = {en} } @inproceedings{WeberDoenitzBrawanskietal., author = {Weber, Joachim and Doenitz, Christian and Brawanski, Alexander and Palm, Christoph}, title = {Data-Parallel MRI Brain Segmentation in Clinicial Use}, series = {Bildverarbeitung f{\"u}r die Medizin 2015; Algorithmen - Systeme - Anwendungen; Proceedings des Workshops vom 15. bis 17. M{\"a}rz 2015 in L{\"u}beck}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2015; Algorithmen - Systeme - Anwendungen; Proceedings des Workshops vom 15. bis 17. M{\"a}rz 2015 in L{\"u}beck}, publisher = {Springer}, address = {Berlin}, doi = {10.1007/978-3-662-46224-9_67}, pages = {389 -- 394}, abstract = {Structural MRI brain analysis and segmentation is a crucial part in the daily routine in neurosurgery for intervention planning. Exemplarily, the free software FSL-FAST (FMRIB's Segmentation Library - FMRIB's Automated Segmentation Tool) in version 4 is used for segmentation of brain tissue types. To speed up the segmentation procedure by parallel execution, we transferred FSL-FAST to a General Purpose Graphics Processing Unit (GPGPU) using Open Computing Language (OpenCL) [1]. The necessary steps for parallelization resulted in substantially different and less useful results. Therefore, the underlying methods were revised and adapted yielding computational overhead. Nevertheless, we achieved a speed-up factor of 3.59 from CPU to GPGPU execution, as well providing similar useful or even better results.}, subject = {Kernspintomografie}, language = {en} } @misc{MaierWeihererHuberetal., author = {Maier, Johannes and Weiherer, Maximilian and Huber, Michaela and Palm, Christoph}, title = {Abstract: Imitating Human Soft Tissue with Dual-Material 3D Printing}, series = {Bildverarbeitung f{\"u}r die Medizin 2019, Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 17. bis 19. M{\"a}rz 2019 in L{\"u}beck}, journal = {Bildverarbeitung f{\"u}r die Medizin 2019, Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 17. bis 19. M{\"a}rz 2019 in L{\"u}beck}, editor = {Handels, Heinz and Deserno, Thomas M. and Maier, Andreas and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-25325-7}, doi = {10.1007/978-3-658-25326-4_48}, pages = {218}, abstract = {Currently, it is common practice to use three-dimensional (3D) printers not only for rapid prototyping in the industry, but also in the medical area to create medical applications for training inexperienced surgeons. In a clinical training simulator for minimally invasive bone drilling to fix hand fractures with Kirschner-wires (K-wires), a 3D printed hand phantom must not only be geometrically but also haptically correct. Due to a limited view during an operation, surgeons need to perfectly localize underlying risk structures only by feeling of specific bony protrusions of the human hand.}, subject = {Handchirurgie}, language = {en} } @misc{RueckertRiederRauberetal., author = {R{\"u}ckert, Tobias and Rieder, Maximilian and Rauber, David and Xiao, Michel and Humolli, Eg and Feussner, Hubertus and Wilhelm, Dirk and Palm, Christoph}, title = {Augmenting instrument segmentation in video sequences of minimally invasive surgery by synthetic smoky frames}, series = {International Journal of Computer Assisted Radiology and Surgery}, volume = {18}, journal = {International Journal of Computer Assisted Radiology and Surgery}, number = {Suppl 1}, publisher = {Springer Nature}, doi = {10.1007/s11548-023-02878-2}, pages = {S54 -- S56}, language = {en} } @article{MaerklRueckertRauberetal., author = {Maerkl, Raphaela and Rueckert, Tobias and Rauber, David and Gutbrod, Max and Weber Nunes, Danilo and Palm, Christoph}, title = {Enhancing generalization in zero-shot multi-label endoscopic instrument classification}, series = {International Journal of Computer Assisted Radiology and Surgery}, volume = {20}, journal = {International Journal of Computer Assisted Radiology and Surgery}, publisher = {Springer Nature}, doi = {10.1007/s11548-025-03439-5}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-85674}, pages = {1577 -- 1587}, abstract = {Purpose Recognizing previously unseen classes with neural networks is a significant challenge due to their limited generalization capabilities. This issue is particularly critical in safety-critical domains such as medical applications, where accurate classification is essential for reliability and patient safety. Zero-shot learning methods address this challenge by utilizing additional semantic data, with their performance relying heavily on the quality of the generated embeddings. Methods This work investigates the use of full descriptive sentences, generated by a Sentence-BERT model, as class representations, compared to simpler category-based word embeddings derived from a BERT model. Additionally, the impact of z-score normalization as a post-processing step on these embeddings is explored. The proposed approach is evaluated on a multi-label generalized zero-shot learning task, focusing on the recognition of surgical instruments in endoscopic images from minimally invasive cholecystectomies. Results The results demonstrate that combining sentence embeddings and z-score normalization significantly improves model performance. For unseen classes, the AUROC improves from 43.9\% to 64.9\%, and the multi-label accuracy from 26.1\% to 79.5\%. Overall performance measured across both seen and unseen classes improves from 49.3\% to 64.9\% in AUROC and from 37.3\% to 65.1\% in multi-label accuracy, highlighting the effectiveness of our approach. Conclusion These findings demonstrate that sentence embeddings and z-score normalization can substantially enhance the generalization performance of zero-shot learning models. However, as the study is based on a single dataset, future work should validate the method across diverse datasets and application domains to establish its robustness and broader applicability.}, language = {en} } @inproceedings{KlausmannRueckertRauberetal., author = {Klausmann, Leonard and Rueckert, Tobias and Rauber, David and Maerkl, Raphaela and Yildiran, Suemeyye R. and Gutbrod, Max and Palm, Christoph}, title = {DIY challenge blueprint: from organization to technical realization in biomedical image analysis}, series = {Medical Image Computing and Computer Assisted Intervention - MICCAI 2025 ; Proceedings Part XI}, booktitle = {Medical Image Computing and Computer Assisted Intervention - MICCAI 2025 ; Proceedings Part XI}, publisher = {Springer}, address = {Cham}, isbn = {978-3-032-05141-7}, doi = {10.1007/978-3-032-05141-7_9}, pages = {85 -- 95}, abstract = {Biomedical image analysis challenges have become the de facto standard for publishing new datasets and benchmarking different state-of-the-art algorithms. Most challenges use commercial cloud-based platforms, which can limit custom options and involve disadvantages such as reduced data control and increased costs for extended functionalities. In contrast, Do-It-Yourself (DIY) approaches have the capability to emphasize reliability, compliance, and custom features, providing a solid basis for low-cost, custom designs in self-hosted systems. Our approach emphasizes cost efficiency, improved data sovereignty, and strong compliance with regulatory frameworks, such as the GDPR. This paper presents a blueprint for DIY biomedical imaging challenges, designed to provide institutions with greater autonomy over their challenge infrastructure. Our approach comprehensively addresses both organizational and technical dimensions, including key user roles, data management strategies, and secure, efficient workflows. Key technical contributions include a modular, containerized infrastructure based on Docker, integration of open-source identity management, and automated solution evaluation workflows. Practical deployment guidelines are provided to facilitate implementation and operational stability. The feasibility and adaptability of the proposed framework are demonstrated through the MICCAI 2024 PhaKIR challenge with multiple international teams submitting and validating their solutions through our self-hosted platform. This work can be used as a baseline for future self-hosted DIY implementations and our results encourage further studies in the area of biomedical image analysis challenges.}, language = {en} } @unpublished{GutbrodRauberWeberNunesetal., author = {Gutbrod, Max and Rauber, David and Weber Nunes, Danilo and Palm, Christoph}, title = {OpenMIBOOD: Open Medical Imaging Benchmarks for Out-Of-Distribution Detection}, doi = {10.48550/arXiv.2503.16247}, pages = {18}, abstract = {The growing reliance on Artificial Intelligence (AI) in critical domains such as healthcare demands robust mechanisms to ensure the trustworthiness of these systems, especially when faced with unexpected or anomalous inputs. This paper introduces the Open Medical Imaging Benchmarks for Out-Of-Distribution Detection (OpenMIBOOD), a comprehensive framework for evaluating out-of-distribution (OOD) detection methods specifically in medical imaging contexts. OpenMIBOOD includes three benchmarks from diverse medical domains, encompassing 14 datasets divided into covariate-shifted in-distribution, near-OOD, and far-OOD categories. We evaluate 24 post-hoc methods across these benchmarks, providing a standardized reference to advance the development and fair comparison of OOD detection methods. Results reveal that findings from broad-scale OOD benchmarks in natural image domains do not translate to medical applications, underscoring the critical need for such benchmarks in the medical field. By mitigating the risk of exposing AI models to inputs outside their training distribution, OpenMIBOOD aims to support the advancement of reliable and trustworthy AI systems in healthcare. The repository is available at this https URL.}, language = {en} } @article{WeihererEigenbergerEggeretal., author = {Weiherer, Maximilian and Eigenberger, Andreas and Egger, Bernhard and Br{\´e}bant, Vanessa and Prantl, Lukas and Palm, Christoph}, title = {Learning the shape of female breasts: an open-access 3D statistical shape model of the female breast built from 110 breast scans}, series = {The Visual Computer}, volume = {39}, journal = {The Visual Computer}, number = {4}, publisher = {Springer Nature}, doi = {10.1007/s00371-022-02431-3}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-30506}, pages = {1597 -- 1616}, abstract = {We present the Regensburg Breast Shape Model (RBSM)—a 3D statistical shape model of the female breast built from 110 breast scans acquired in a standing position, and the first publicly available. Together with the model, a fully automated, pairwise surface registration pipeline used to establish dense correspondence among 3D breast scans is introduced. Our method is computationally efficient and requires only four landmarks to guide the registration process. A major challenge when modeling female breasts from surface-only 3D breast scans is the non-separability of breast and thorax. In order to weaken the strong coupling between breast and surrounding areas, we propose to minimize the variance outside the breast region as much as possible. To achieve this goal, a novel concept called breast probability masks (BPMs) is introduced. A BPM assigns probabilities to each point of a 3D breast scan, telling how likely it is that a particular point belongs to the breast area. During registration, we use BPMs to align the template to the target as accurately as possible inside the breast region and only roughly outside. This simple yet effective strategy significantly reduces the unwanted variance outside the breast region, leading to better statistical shape models in which breast shapes are quite well decoupled from the thorax. The RBSM is thus able to produce a variety of different breast shapes as independently as possible from the shape of the thorax. Our systematic experimental evaluation reveals a generalization ability of 0.17 mm and a specificity of 2.8 mm. To underline the expressiveness of the proposed model, we finally demonstrate in two showcase applications how the RBSM can be used for surgical outcome simulation and the prediction of a missing breast from the remaining one. Our model is available at https://www.rbsm.re-mic.de/.}, language = {en} } @article{MaierWeihererHuberetal., author = {Maier, Johannes and Weiherer, Maximilian and Huber, Michaela and Palm, Christoph}, title = {Imitating human soft tissue on basis of a dual-material 3D print using a support-filled metamaterial to provide bimanual haptic for a hand surgery training system}, series = {Quantitative Imaging in Medicine and Surgery}, volume = {9}, journal = {Quantitative Imaging in Medicine and Surgery}, number = {1}, publisher = {AME Publishing Company}, doi = {10.21037/qims.2018.09.17}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-979}, pages = {30 -- 42}, abstract = {Background: Currently, it is common practice to use three-dimensional (3D) printers not only for rapid prototyping in the industry, but also in the medical area to create medical applications for training inexperienced surgeons. In a clinical training simulator for minimally invasive bone drilling to fix hand fractures with Kirschner-wires (K-wires), a 3D-printed hand phantom must not only be geometrically but also haptically correct. Due to a limited view during an operation, surgeons need to perfectly localize underlying risk structures only by feeling of specific bony protrusions of the human hand. Methods: The goal of this experiment is to imitate human soft tissue with its haptic and elasticity for a realistic hand phantom fabrication, using only a dual-material 3D printer and support-material-filled metamaterial between skin and bone. We present our workflow to generate lattice structures between hard bone and soft skin with iterative cube edge (CE) or cube face (CF) unit cells. Cuboid and finger shaped sample prints with and without inner hard bone in different lattice thickness are constructed and 3D printed. Results: The most elastic available rubber-like material is too firm to imitate soft tissue. By reducing the amount of rubber in the inner volume through support material (SUP), objects become significantly softer. Without metamaterial, after disintegration, the SUP can be shifted through the volume and thus the body loses its original shape. Although the CE design increases the elasticity, it cannot restore the fabric form. In contrast to CE, the CF design increases not only the elasticity but also guarantees a local limitation of the SUP. Therefore, the body retains its shape and internal bones remain in its intended place. Various unit cell sizes, lattice thickening and skin thickness regulate the rubber material and SUP ratio. Test prints with higher SUP and lower rubber material percentage appear softer and vice versa. This was confirmed by an expert surgeon evaluation. Subjects adjudged pure rubber-like material as too firm and samples only filled with SUP or lattice structure in CE design as not suitable for imitating tissue. 3D-printed finger samples in CF design were rated as realistic compared to the haptic of human tissue with a good palpable bone structure. Conclusions: We developed a new dual-material 3D print technique to imitate soft tissue of the human hand with its haptic properties. Blowy SUP is trapped within a lattice structure to soften rubber-like 3D print material, which makes it possible to reproduce a realistic replica of human hand soft tissue.}, subject = {Handchirurgie}, language = {en} } @article{MaierWeihererHuberetal., author = {Maier, Johannes and Weiherer, Maximilian and Huber, Michaela and Palm, Christoph}, title = {Optically tracked and 3D printed haptic phantom hand for surgical training system}, series = {Quantitative Imaging in Medicine and Surgery}, volume = {10}, journal = {Quantitative Imaging in Medicine and Surgery}, number = {02}, publisher = {AME Publishing Company}, address = {Hong Kong, China}, doi = {10.21037/qims.2019.12.03}, pages = {340 -- 455}, abstract = {Background: For surgical fixation of bone fractures of the human hand, so-called Kirschner-wires (K-wires) are drilled through bone fragments. Due to the minimally invasive drilling procedures without a view of risk structures like vessels and nerves, a thorough training of young surgeons is necessary. For the development of a virtual reality (VR) based training system, a three-dimensional (3D) printed phantom hand is required. To ensure an intuitive operation, this phantom hand has to be realistic in both, its position relative to the driller as well as in its haptic features. The softest 3D printing material available on the market, however, is too hard to imitate human soft tissue. Therefore, a support-material (SUP) filled metamaterial is used to soften the raw material. Realistic haptic features are important to palpate protrusions of the bone to determine the drilling starting point and angle. An optical real-time tracking is used to transfer position and rotation to the training system. Methods: A metamaterial already developed in previous work is further improved by use of a new unit cell. Thus, the amount of SUP within the volume can be increased and the tissue is softened further. In addition, the human anatomy is transferred to the entire hand model. A subcutaneous fat layer and penetration of air through pores into the volume simulate shiftability of skin layers. For optical tracking, a rotationally symmetrical marker attached to the phantom hand with corresponding reference marker is developed. In order to ensure trouble-free position transmission, various types of marker point applications are tested. Results: Several cuboid and forearm sample prints lead to a final 30 centimeter long hand model. The whole haptic phantom could be printed faultless within about 17 hours. The metamaterial consisting of the new unit cell results in an increased SUP share of 4.32\%. Validated by an expert surgeon study, this allows in combination with a displacement of the uppermost skin layer a good palpability of the bones. Tracking of the hand marker in dodecahedron design works trouble-free in conjunction with a reference marker attached to the worktop of the training system. Conclusions: In this work, an optically tracked and haptically correct phantom hand was developed using dual-material 3D printing, which can be easily integrated into a surgical training system.}, subject = {Handchirurgie}, language = {en} } @inproceedings{FranzDreherPrinzenetal., author = {Franz, Daniela and Dreher, Maria and Prinzen, Martin and Teßmann, Matthias and Palm, Christoph and Katzky, Uwe and Perret, Jerome and Hofer, Mathias and Wittenberg, Thomas}, title = {CT-basiertes virtuelles Fr{\"a}sen am Felsenbein}, series = {Bildverarbeitung f{\"u}r die Medizin 2018; Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 11. bis 13. M{\"a}rz 2018 in Erlangen}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2018; Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 11. bis 13. M{\"a}rz 2018 in Erlangen}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-662-56537-7}, doi = {10.1007/978-3-662-56537-7_51}, pages = {176 -- 181}, abstract = {Im Rahmen der Entwicklung eines haptisch-visuellen Trainingssystems f{\"u}r das Fr{\"a}sen am Felsenbein werden ein Haptikarm und ein autostereoskopischer 3D-Monitor genutzt, um Chirurgen die virtuelle Manipulation von kn{\"o}chernen Strukturen im Kontext eines sog. Serious Game zu erm{\"o}glichen. Unter anderem sollen Assistenz{\"a}rzte im Rahmen ihrer Ausbildung das Fr{\"a}sen am Felsenbein f{\"u}r das chirurgische Einsetzen eines Cochlea-Implantats {\"u}ben k{\"o}nnen. Die Visualisierung des virtuellen Fr{\"a}sens muss daf{\"u}r in Echtzeit und m{\"o}glichst realistisch modelliert, implementiert und evaluiert werden. Wir verwenden verschiedene Raycasting Methoden mit linearer und Nearest Neighbor Interpolation und vergleichen die visuelle Qualit{\"a}t und die Bildwiederholfrequenzen der Methoden. Alle verglichenen Verfahren sind sind echtzeitf{\"a}hig, unterscheiden sich aber in ihrer visuellen Qualit{\"a}t.}, subject = {Felsenbein}, language = {de} } @inproceedings{MaierHuberKatzkyetal., author = {Maier, Johannes and Huber, Michaela and Katzky, Uwe and Perret, Jerome and Wittenberg, Thomas and Palm, Christoph}, title = {Force-Feedback-assisted Bone Drilling Simulation Based on CT Data}, series = {Bildverarbeitung f{\"u}r die Medizin 2018; Algorithmen - Systeme - Anwendungen; Proceedings des Workshops vom 11. bis 13. M{\"a}rz 2018 in Erlangen}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2018; Algorithmen - Systeme - Anwendungen; Proceedings des Workshops vom 11. bis 13. M{\"a}rz 2018 in Erlangen}, publisher = {Springer}, address = {Berlin}, doi = {10.1007/978-3-662-56537-7_78}, pages = {291 -- 296}, abstract = {In order to fix a fracture using minimally invasive surgery approaches, surgeons are drilling complex and tiny bones with a 2 dimensional X-ray as single imaging modality in the operating room. Our novel haptic force-feedback and visual assisted training system will potentially help hand surgeons to learn the drilling procedure in a realistic visual environment. Within the simulation, the collision detection as well as the interaction between virtual drill, bone voxels and surfaces are important. In this work, the chai3d collision detection and force calculation algorithms are combined with a physics engine to simulate the bone drilling process. The chosen Bullet-Physics-Engine provides a stable simulation of rigid bodies, if the collision model of the drill and the tool holder is generated as a compound shape. Three haptic points are added to the K-wire tip for removing single voxels from the bone. For the drilling process three modes are proposed to emulate the different phases of drilling in restricting the movement of a haptic device.}, subject = {Handchirurgie}, language = {en} } @inproceedings{EixelbergerWittenbergPerretetal., author = {Eixelberger, Thomas and Wittenberg, Thomas and Perret, Jerome and Katzky, Uwe and Simon, Martina and Schmitt-R{\"u}th, Stephanie and Hofer, Mathias and Sorge, M. and Jacob, R. and Engel, Felix B. and Gostian, A. and Palm, Christoph and Franz, Daniela}, title = {A haptic model for virtual petrosal bone milling}, series = {17. Jahrestagung der Deutschen Gesellschaft f{\"u}r Computer- und Roboterassistierte Chirurgie (CURAC2018), Tagungsband, 2018, Leipzig, 13.-15. September}, volume = {17}, booktitle = {17. Jahrestagung der Deutschen Gesellschaft f{\"u}r Computer- und Roboterassistierte Chirurgie (CURAC2018), Tagungsband, 2018, Leipzig, 13.-15. September}, pages = {214 -- 219}, abstract = {Virtual training of bone milling requires realtime and realistic haptics of the interaction between the "virtual mill" and a "virtual bone". We propose an exponential abrasion model between a virtual one and the mill bit and combine it with a coarse representation of the virtual bone and the mill shaft for collision detection using the Bullet Physics Engine. We compare our exponential abrasion model to a widely used linear abrasion model and evaluate it quantitatively and qualitatively. The evaluation results show, that we can provide virtual milling in real-time, with an abrasion behavior similar to that proposed in the literature and with a realistic feeling of five different surgeons.}, subject = {Osteosynthese}, language = {en} } @inproceedings{PalmSchanze, author = {Palm, Christoph and Schanze, Thomas}, title = {Biomedical Image and Signal Computing (BISC 2013)}, series = {58. Jahrestagung der Deutschen Gesellschaft f{\"u}r Medizinische Informatik, Biometrie und Epidemiologie e.V. (GMDS 2013), L{\"u}beck, 01.-05.09.2013}, booktitle = {58. Jahrestagung der Deutschen Gesellschaft f{\"u}r Medizinische Informatik, Biometrie und Epidemiologie e.V. (GMDS 2013), L{\"u}beck, 01.-05.09.2013}, number = {DocAbstr. 324}, publisher = {German Medical Science GMS Publishing House}, address = {D{\"u}sseldorf}, doi = {doi:10.3205/13gmds257}, language = {en} } @article{EbigboMendelProbstetal., author = {Ebigbo, Alanna and Mendel, Robert and Probst, Andreas and Manzeneder, Johannes and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Palm, Christoph and Messmann, Helmut}, title = {Computer-aided diagnosis using deep learning in the evaluation of early oesophageal adenocarcinoma}, series = {GuT}, volume = {68}, journal = {GuT}, number = {7}, publisher = {British Society of Gastroenterology}, doi = {10.1136/gutjnl-2018-317573}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-68}, pages = {1143 -- 1145}, abstract = {Computer-aided diagnosis using deep learning (CAD-DL) may be an instrument to improve endoscopic assessment of Barrett's oesophagus (BE) and early oesophageal adenocarcinoma (EAC). Based on still images from two databases, the diagnosis of EAC by CAD-DL reached sensitivities/specificities of 97\%/88\% (Augsburg data) and 92\%/100\% (Medical Image Computing and Computer-Assisted Intervention [MICCAI] data) for white light (WL) images and 94\%/80\% for narrow band images (NBI) (Augsburg data), respectively. Tumour margins delineated by experts into images were detected satisfactorily with a Dice coefficient (D) of 0.72. This could be a first step towards CAD-DL for BE assessment. If developed further, it could become a useful adjunctive tool for patient management.}, subject = {Speiser{\"o}hrenkrebs}, language = {en} } @article{WoehlMaierGehmertetal., author = {W{\"o}hl, Rebecca and Maier, Johannes and Gehmert, Sebastian and Palm, Christoph and Riebschl{\"a}ger, Birgit and Nerlich, Michael and Huber, Michaela}, title = {3D Analysis of Osteosyntheses Material using semi-automated CT Segmentation}, series = {BMC Musculoskeletal Disorders}, volume = {19}, journal = {BMC Musculoskeletal Disorders}, publisher = {Springer Nature}, doi = {10.1186/s12891-018-1975-0}, pages = {1 -- 8}, abstract = {Backround Scaphoidectomy and midcarpal fusion can be performed using traditional fixation methods like K-wires, staples, screws or different dorsal (non)locking arthrodesis systems. The aim of this study is to test the Aptus four corner locking plate and to compare the clinical findings to the data revealed by CT scans and semi-automated segmentation. Methods: This is a retrospective review of eleven patients suffering from scapholunate advanced collapse (SLAC) or scaphoid non-union advanced collapse (SNAC) wrist, who received a four corner fusion between August 2011 and July 2014. The clinical evaluation consisted of measuring the range of motion (ROM), strength and pain on a visual analogue scale (VAS). Additionally, the Disabilities of the Arm, Shoulder and Hand (QuickDASH) and the Mayo Wrist Score were assessed. A computerized tomography (CT) of the wrist was obtained six weeks postoperatively. After semi-automated segmentation of the CT scans, the models were post processed and surveyed. Results During the six-month follow-up mean range of motion (ROM) of the operated wrist was 60°, consisting of 30° extension and 30° flexion. While pain levels decreased significantly, 54\% of grip strength and 89\% of pinch strength were preserved compared to the contralateral healthy wrist. Union could be detected in all CT scans of the wrist. While X-ray pictures obtained postoperatively revealed no pathology, two user related technical complications were found through the 3D analysis, which correlated to the clinical outcome. Conclusion Due to semi-automated segmentation and 3D analysis it has been proved that the plate design can keep up to the manufacturers' promises. Over all, this case series confirmed that the plate can compete with the coexisting techniques concerning clinical outcome, union and complication rate.}, subject = {Handchirurgie}, language = {en} } @misc{ScheppachMendelProbstetal., author = {Scheppach, Markus W. and Mendel, Robert and Probst, Andreas and Rauber, David and R{\"u}ckert, Tobias and Meinikheim, Michael and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Real-time detection and delineation of tissue during third-space endoscopy using artificial intelligence (AI)}, series = {Endoscopy}, volume = {55}, journal = {Endoscopy}, number = {S02}, publisher = {Thieme}, doi = {10.1055/s-0043-1765128}, pages = {S53 -- S54}, abstract = {Aims AI has proven great potential in assisting endoscopists in diagnostics, however its role in therapeutic endoscopy remains unclear. Endoscopic submucosal dissection (ESD) is a technically demanding intervention with a slow learning curve and relevant risks like bleeding and perforation. Therefore, we aimed to develop an algorithm for the real-time detection and delineation of relevant structures during third-space endoscopy. Methods 5470 still images from 59 full length videos (47 ESD, 12 POEM) were annotated. 179681 additional unlabeled images were added to the training dataset. Consequently, a DeepLabv3+ neural network architecture was trained with the ECMT semi-supervised algorithm (under review elsewhere). Evaluation of vessel detection was performed on a dataset of 101 standardized video clips from 15 separate third-space endoscopy videos with 200 predefined blood vessels. Results Internal validation yielded an overall mean Dice score of 85\% (68\% for blood vessels, 86\% for submucosal layer, 88\% for muscle layer). On the video test data, the overall vessel detection rate (VDR) was 94\% (96\% for ESD, 74\% for POEM). The median overall vessel detection time (VDT) was 0.32 sec (0.3 sec for ESD, 0.62 sec for POEM). Conclusions Evaluation of the developed algorithm on a video test dataset showed high VDR and quick VDT, especially for ESD. Further research will focus on a possible clinical benefit of the AI application for VDR and VDT during third-space endoscopy.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @inproceedings{FranzKatzkyNeumannetal., author = {Franz, Daniela and Katzky, Uwe and Neumann, Sabine and Perret, Jerome and Hofer, Mathias and Huber, Michaela and Schmitt-R{\"u}th, Stephanie and Haug, Sonja and Weber, Karsten and Prinzen, Martin and Palm, Christoph and Wittenberg, Thomas}, title = {Haptisches Lernen f{\"u}r Cochlea Implantationen}, series = {15. Jahrestagung der Deutschen Gesellschaft f{\"u}r Computer- und Roboterassistierte Chirurgie (CURAC2016), Tagungsband, 2016, Bern, 29.09. - 01.10.}, booktitle = {15. Jahrestagung der Deutschen Gesellschaft f{\"u}r Computer- und Roboterassistierte Chirurgie (CURAC2016), Tagungsband, 2016, Bern, 29.09. - 01.10.}, pages = {21 -- 26}, abstract = {Die Implantation eines Cochlea Implantates ben{\"o}tigt einen chirurgischen Zugang im Felsenbein und durch die Paukenh{\"o}hle des Patienten. Der Chirurg hat eine eingeschr{\"a}nkte Sicht im Operationsgebiet, die weiterhin viele Risikostrukturen enth{\"a}lt. Um eine Cochlea Implantation sicher und fehlerfrei durchzuf{\"u}hren, ist eine umfangreiche theoretische und praktische (teilweise berufsbegleitende) Fortbildung sowie langj{\"a}hrige Erfahrung notwendig. Unter Nutzung von realen klinischen CT/MRT Daten von Innen- und Mittelohr und der interaktiven Segmentierung der darin abgebildeten Strukturen (Nerven, Cochlea, Geh{\"o}rkn{\"o}chelchen,...) wird im HaptiVisT Projekt ein haptisch-visuelles Trainingssystem f{\"u}r die Implantation von Innen- und Mittelohr-Implantaten realisiert, das als sog. „Serious Game" mit immersiver Didaktik gestaltet wird. Die Evaluierung des Demonstrators hinsichtlich Zweckm{\"a}ßigkeit erfolgt prozessbegleitend und ergebnisorientiert, um m{\"o}gliche technische oder didaktische Fehler vor Fertigstellung des Systems aufzudecken. Drei zeitlich versetzte Evaluationen fokussieren dabei chirurgisch-fachliche, didaktische sowie haptisch-ergonomische Akzeptanzkriterien.}, subject = {Cochlea-Implantat}, language = {de} } @inproceedings{SouzaJrHookPapaetal., author = {Souza Jr., Luis Antonio de and Hook, Christian and Papa, Jo{\~a}o Paulo and Palm, Christoph}, title = {Barrett's Esophagus Analysis Using SURF Features}, series = {Bildverarbeitung f{\"u}r die Medizin 2017; Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 12. bis 14. M{\"a}rz 2017 in Heidelberg}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2017; Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 12. bis 14. M{\"a}rz 2017 in Heidelberg}, publisher = {Springer}, address = {Berlin}, doi = {10.1007/978-3-662-54345-0_34}, pages = {141 -- 146}, abstract = {The development of adenocarcinoma in Barrett's esophagus is difficult to detect by endoscopic surveillance of patients with signs of dysplasia. Computer assisted diagnosis of endoscopic images (CAD) could therefore be most helpful in the demarcation and classification of neoplastic lesions. In this study we tested the feasibility of a CAD method based on Speeded up Robust Feature Detection (SURF). A given database containing 100 images from 39 patients served as benchmark for feature based classification models. Half of the images had previously been diagnosed by five clinical experts as being "cancerous", the other half as "non-cancerous". Cancerous image regions had been visibly delineated (masked) by the clinicians. SURF features acquired from full images as well as from masked areas were utilized for the supervised training and testing of an SVM classifier. The predictive accuracy of the developed CAD system is illustrated by sensitivity and specificity values. The results based on full image matching where 0.78 (sensitivity) and 0.82 (specificity) were achieved, while the masked region approach generated results of 0.90 and 0.95, respectively.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @inproceedings{MendelEbigboProbstetal., author = {Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph}, title = {Barrett's Esophagus Analysis Using Convolutional Neural Networks}, series = {Bildverarbeitung f{\"u}r die Medizin 2017; Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 12. bis 14. M{\"a}rz 2017 in Heidelberg}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2017; Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 12. bis 14. M{\"a}rz 2017 in Heidelberg}, publisher = {Springer}, address = {Berlin}, doi = {10.1007/978-3-662-54345-0_23}, pages = {80 -- 85}, abstract = {We propose an automatic approach for early detection of adenocarcinoma in the esophagus. High-definition endoscopic images (50 cancer, 50 Barrett) are partitioned into a dataset containing approximately equal amounts of patches showing cancerous and non-cancerous regions. A deep convolutional neural network is adapted to the data using a transfer learning approach. The final classification of an image is determined by at least one patch, for which the probability being a cancer patch exceeds a given threshold. The model was evaluated with leave one patient out cross-validation. With sensitivity and specificity of 0.94 and 0.88, respectively, our findings improve recently published results on the same image data base considerably. Furthermore, the visualization of the class probabilities of each individual patch indicates, that our approach might be extensible to the segmentation domain.}, subject = {Speiser{\"o}hrenkrebs}, language = {en} } @inproceedings{MaierHaugHuberetal., author = {Maier, Johannes and Haug, Sonja and Huber, Michaela and Katzky, Uwe and Neumann, Sabine and Perret, J{\´e}r{\^o}me and Prinzen, Martin and Weber, Karsten and Wittenberg, Thomas and W{\"o}hl, Rebecca and Scorna, Ulrike and Palm, Christoph}, title = {Development of a haptic and visual assisted training simulation concept for complex bone drilling in minimally invasive hand surgery}, series = {CARS Conference, 5.10.-7.10.2017}, booktitle = {CARS Conference, 5.10.-7.10.2017}, language = {en} } @article{SouzaJrPassosSantanaetal., author = {Souza Jr., Luis Antonio de and Passos, Leandro A. and Santana, Marcos Cleison S. and Mendel, Robert and Rauber, David and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Papa, Jo{\~a}o Paulo and Palm, Christoph}, title = {Layer-selective deep representation to improve esophageal cancer classification}, series = {Medical \& Biological Engineering \& Computing}, volume = {62}, journal = {Medical \& Biological Engineering \& Computing}, publisher = {Springer Nature}, address = {Heidelberg}, doi = {10.1007/s11517-024-03142-8}, pages = {3355 -- 3372}, abstract = {Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their accountability and transparency level must be improved to transfer this success into clinical practice. The reliability of machine learning decisions must be explained and interpreted, especially for supporting the medical diagnosis.For this task, the deep learning techniques' black-box nature must somehow be lightened up to clarify its promising results. Hence, we aim to investigate the impact of the ResNet-50 deep convolutional design for Barrett's esophagus and adenocarcinoma classification. For such a task, and aiming at proposing a two-step learning technique, the output of each convolutional layer that composes the ResNet-50 architecture was trained and classified for further definition of layers that would provide more impact in the architecture. We showed that local information and high-dimensional features are essential to improve the classification for our task. Besides, we observed a significant improvement when the most discriminative layers expressed more impact in the training and classification of ResNet-50 for Barrett's esophagus and adenocarcinoma classification, demonstrating that both human knowledge and computational processing may influence the correct learning of such a problem.}, language = {en} } @article{EbigboMendelProbstetal., author = {Ebigbo, Alanna and Mendel, Robert and Probst, Andreas and Meinikheim, Michael and Byrne, Michael F. and Messmann, Helmut and Palm, Christoph}, title = {Multimodal imaging for detection and segmentation of Barrett's esophagus-related neoplasia using artificial intelligence}, series = {Endoscopy}, volume = {54}, journal = {Endoscopy}, number = {10}, edition = {E-Video}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/a-1704-7885}, pages = {1}, abstract = {The early diagnosis of cancer in Barrett's esophagus is crucial for improving the prognosis. However, identifying Barrett's esophagus-related neoplasia (BERN) is challenging, even for experts [1]. Four-quadrant biopsies may improve the detection of neoplasia, but they can be associated with sampling errors. The application of artificial intelligence (AI) to the assessment of Barrett's esophagus could improve the diagnosis of BERN, and this has been demonstrated in both preclinical and clinical studies [2] [3]. In this video demonstration, we show the accurate detection and delineation of BERN in two patients ([Video 1]). In part 1, the AI system detects a mucosal cancer about 20 mm in size and accurately delineates the lesion in both white-light and narrow-band imaging. In part 2, a small island of BERN with high-grade dysplasia is detected and delineated in white-light, narrow-band, and texture and color enhancement imaging. The video shows the results using a transparent overlay of the mucosal cancer in real time as well as a full segmentation preview. Additionally, the optical flow allows for the assessment of endoscope movement, something which is inversely related to the reliability of the AI prediction. We demonstrate that multimodal imaging can be applied to the AI-assisted detection and segmentation of even small focal lesions in real time.}, language = {en} } @article{KolevKirchgessnerHoubenetal., author = {Kolev, Kalin and Kirchgeßner, Norbert and Houben, Sebastian and Csisz{\´a}r, Agnes and Rubner, Wolfgang and Palm, Christoph and Eiben, Bj{\"o}rn and Merkel, Rudolf and Cremers, Daniel}, title = {A variational approach to vesicle membrane reconstruction from fluorescence imaging}, series = {Pattern Recognition}, volume = {44}, journal = {Pattern Recognition}, number = {12}, publisher = {Elsevier}, doi = {10.1016/j.patcog.2011.04.019}, pages = {2944 -- 2958}, abstract = {Biological applications like vesicle membrane analysis involve the precise segmentation of 3D structures in noisy volumetric data, obtained by techniques like magnetic resonance imaging (MRI) or laser scanning microscopy (LSM). Dealing with such data is a challenging task and requires robust and accurate segmentation methods. In this article, we propose a novel energy model for 3D segmentation fusing various cues like regional intensity subdivision, edge alignment and orientation information. The uniqueness of the approach consists in the definition of a new anisotropic regularizer, which accounts for the unbalanced slicing of the measured volume data, and the generalization of an efficient numerical scheme for solving the arising minimization problem, based on linearization and fixed-point iteration. We show how the proposed energy model can be optimized globally by making use of recent continuous convex relaxation techniques. The accuracy and robustness of the presented approach are demonstrated by evaluating it on multiple real data sets and comparing it to alternative segmentation methods based on level sets. Although the proposed model is designed with focus on the particular application at hand, it is general enough to be applied to a variety of different segmentation tasks.}, subject = {Dreidimensionale Bildverarbeitung}, language = {en} } @inproceedings{MetzlerAachPalmetal., author = {Metzler, V. and Aach, T. and Palm, Christoph and Lehmann, Thomas M.}, title = {Texture Classification of Graylevel Images by Multiscale Cross-Co-Occurrence Matrices}, series = {Proceedings 15th International Conference on Pattern Recognition (ICPR-2000)}, booktitle = {Proceedings 15th International Conference on Pattern Recognition (ICPR-2000)}, doi = {10.1109/ICPR.2000.906133}, pages = {549 -- 552}, abstract = {Local gray level dependencies of natural images can be modelled by means of co-occurrence matrices containing joint probabilities of gray-level pairs. Texture, however, is a resolution-dependent phenomenon and hence, classification depends on the chosen scale. Since there is no optimal scale for all textures we employ a multiscale approach that acquires textural features at several scales. Thus linear and nonlinear scale-spaces are analyzed by multiscale co-occurrence matrices that describe the statistical behavior of a texture in scale-space. Classification is then performed on the basis of texture features taken from the individual scale with the highest discriminatory power. By considering cross-scale occurrences of gray level pairs, the impact of filters on the feature is described and used for classification of natural textures. This novel method was found to improve classification rates of the common co-occurrence matrix approach on standard textures significantly.}, language = {en} } @misc{MeinikheimMendelProbstetal., author = {Meinikheim, Michael and Mendel, Robert and Probst, Andreas and Scheppach, Markus W. and Messmann, Helmut and Palm, Christoph and Ebigbo, Alanna}, title = {Optical Flow als Methode zur Qualit{\"a}tssicherung KI-unterst{\"u}tzter Untersuchungen von Barrett-{\"O}sophagus und Barrett-{\"O}sophagus assoziierten Neoplasien}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {60}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {08}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/s-0042-1754997}, abstract = {Einleitung {\"U}berm{\"a}ßige Bewegung im Bild kann die Performance von auf k{\"u}nstlicher Intelligenz (KI) basierenden klinischen Entscheidungsunterst{\"u}tzungssystemen (CDSS) reduzieren. Optical Flow (OF) ist eine Methode zur Lokalisierung und Quantifizierung von Bewegungen zwischen aufeinanderfolgenden Bildern. Ziel Ziel ist es, die Mensch-Computer-Interaktion (HCI) zu verbessern und Endoskopiker die unser KI-System „Barrett-Ampel" zur Unterst{\"u}tzung bei der Beurteilung von Barrett-{\"O}sophagus (BE) verwenden, ein Echtzeit-Feedback zur aktuellen Datenqualit{\"a}t anzubieten. Methodik Dazu wurden unver{\"a}nderte Videos in „Weißlicht" (WL), „Narrow Band Imaging" (NBI) und „Texture and Color Enhancement Imaging" (TXI) von acht endoskopischen Untersuchungen von histologisch gesichertem BE und mit Barrett-{\"O}sophagus assoziierten Neoplasien (BERN) durch unseren KI-Algorithmus analysiert. Der zur Bewertung der Bildqualit{\"a}t verwendete OF beinhaltete die mittlere Magnitude und die Entropie des Histogramms der Winkel. Frames wurden automatisch extrahiert, wenn die vordefinierten Schwellenwerte von 3,0 f{\"u}r die mittlere Magnitude und 9,0 f{\"u}r die Entropie des Histogramms der Winkel {\"u}berschritten wurden. Experten sahen sich zun{\"a}chst die Videos ohne KI-Unterst{\"u}tzung an und bewerteten, ob St{\"o}rfaktoren die Sicherheit mit der eine Diagnose im vorliegenden Fall gestellt werden kann negativ beeinflussen. Anschließend {\"u}berpr{\"u}ften sie die extrahierten Frames. Ergebnis Gleichm{\"a}ßige Bewegung in eine Richtung, wie etwa beim Vorschieben des Endoskops, spiegelte sich, bei insignifikant ver{\"a}nderter Entropie, in einer Erh{\"o}hung der Magnitude wider. Chaotische Bewegung, zum Beispiel w{\"a}hrend dem Sp{\"u}len, war mit erh{\"o}hter Entropie assoziiert. Insgesamt war eine unruhige endoskopische Darstellung, Fl{\"u}ssigkeit sowie {\"u}berm{\"a}ßige {\"O}sophagusmotilit{\"a}t mit erh{\"o}htem OF assoziiert und korrelierte mit der Meinung der Experten {\"u}ber die Qualit{\"a}t der Videos. Der OF und die subjektive Wahrnehmung der Experten {\"u}ber die Verwertbarkeit der vorliegenden Bildsequenzen korrelierten direkt proportional. Wenn die vordefinierten Schwellenwerte des OF {\"u}berschritten wurden, war die damit verbundene Bildqualit{\"a}t in 94\% der F{\"a}lle f{\"u}r eine definitive Interpretation auch f{\"u}r Experten unzureichend. Schlussfolgerung OF hat das Potenzial Endoskopiker ein Echtzeit-Feedback {\"u}ber die Qualit{\"a}t des Dateninputs zu bieten und so nicht nur die HCI zu verbessern, sondern auch die optimale Performance von KI-Algorithmen zu erm{\"o}glichen.}, language = {de} } @misc{MeinikheimMendelScheppachetal., author = {Meinikheim, Michael and Mendel, Robert and Scheppach, Markus W. and Probst, Andreas and Prinz, Friederike and Schwamberger, Tanja and Schlottmann, Jakob and G{\"o}lder, Stefan Karl and Walter, Benjamin and Steinbr{\"u}ck, Ingo and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Einsatz von k{\"u}nstlicher Intelligenz (KI) als Entscheidungsunterst{\"u}tzungssystem f{\"u}r nicht-Experten bei der Beurteilung von Barrett-{\"O}sophagus assoziierten Neoplasien (BERN)}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {60}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {4}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0042-1745653}, pages = {251}, abstract = {Einleitung Die sichere Detektion und Charakterisierung von Barrett-{\"O}sophagus assoziierten Neoplasien (BERN) stellt selbst f{\"u}r erfahrene Endoskopiker eine Herausforderung dar. Ziel Ziel dieser Studie ist es, den Add-on Effekt eines k{\"u}nstlichen Intelligenz (KI) Systems (Barrett-Ampel) als Entscheidungsunterst{\"u}zungssystem f{\"u}r Endoskopiker ohne Expertise bei der Untersuchung von BERN zu evaluieren. Material und Methodik Zw{\"o}lf Videos in „Weißlicht" (WL), „narrow-band imaging" (NBI) und „texture and color enhanced imaging" (TXI) von histologisch best{\"a}tigten Barrett-Metaplasien oder BERN wurden von Experten und Untersuchern ohne Barrett-Expertise evaluiert. Die Probanden wurden dazu aufgefordert in den Videos auftauchende BERN zu identifizieren und gegebenenfalls die optimale Biopsiestelle zu markieren. Unser KI-System wurde demselben Test unterzogen, wobei dieses BERN in Echtzeit segmentierte und farblich von umliegendem Epithel differenzierte. Anschließend wurden den Probanden die Videos mit zus{\"a}tzlicher KI-Unterst{\"u}tzung gezeigt. Basierend auf dieser neuen Information, wurden die Probanden zu einer Reevaluation ihrer initialen Beurteilung aufgefordert. Ergebnisse Die „Barrett-Ampel" identifizierte unabh{\"a}ngig von den verwendeten Darstellungsmodi (WL, NBI, TXI) alle BERN. Zwei entz{\"u}ndlich ver{\"a}nderte L{\"a}sionen wurden fehlinterpretiert (Genauigkeit=75\%). W{\"a}hrend Experten vergleichbare Ergebnisse erzielten (Genauigkeit=70,8\%), hatten Endoskopiker ohne Expertise bei der Beurteilung von Barrett-Metaplasien eine Genauigkeit von lediglich 58,3\%. Wurden die nicht-Experten allerdings von unserem KI-System unterst{\"u}tzt, erreichten diese eine Genauigkeit von 75\%. Zusammenfassung Unser KI-System hat das Potential als Entscheidungsunterst{\"u}tzungssystem bei der Differenzierung zwischen Barrett-Metaplasie und BERN zu fungieren und so Endoskopiker ohne entsprechende Expertise zu assistieren. Eine Limitation dieser Studie ist die niedrige Anzahl an eingeschlossenen Videos. Um die Ergebnisse dieser Studie zu best{\"a}tigen, m{\"u}ssen randomisierte kontrollierte klinische Studien durchgef{\"u}hrt werden.}, language = {de} } @misc{MeinikheimMendelScheppachetal., author = {Meinikheim, Michael and Mendel, Robert and Scheppach, Markus W. and Probst, Andreas and Prinz, Friederike and Schwamberger, Tanja and Schlottmann, Jakob and G{\"o}lder, Stefan Karl and Walter, Benjamin and Steinbr{\"u}ck, Ingo and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {INFLUENCE OF AN ARTIFICIAL INTELLIGENCE (AI) BASED DECISION SUPPORT SYSTEM (DSS) ON THE DIAGNOSTIC PERFORMANCE OF NON-EXPERTS IN BARRETT´S ESOPHAGUS RELATED NEOPLASIA (BERN)}, series = {Endoscopy}, volume = {54}, journal = {Endoscopy}, number = {S 01}, publisher = {Thieme}, doi = {10.1055/s-00000012}, pages = {S39}, abstract = {Aims Barrett´s esophagus related neoplasia (BERN) is difficult to detect and characterize during endoscopy, even for expert endoscopists. We aimed to assess the add-on effect of an Artificial Intelligence (AI) algorithm (Barrett-Ampel) as a decision support system (DSS) for non-expert endoscopists in the evaluation of Barrett's esophagus (BE) and BERN. Methods Twelve videos with multimodal imaging white light (WL), narrow-band imaging (NBI), texture and color enhanced imaging (TXI) of histologically confirmed BE and BERN were assessed by expert and non-expert endoscopists. For each video, endoscopists were asked to identify the area of BERN and decide on the biopsy spot. Videos were assessed by the AI algorithm and regions of BERN were highlighted in real-time by a transparent overlay. Finally, endoscopists were shown the AI videos and asked to either confirm or change their initial decision based on the AI support. Results Barrett-Ampel correctly identified all areas of BERN, irrespective of the imaging modality (WL, NBI, TXI), but misinterpreted two inflammatory lesions (Accuracy=75\%). Expert endoscopists had a similar performance (Accuracy=70,8\%), while non-experts had an accuracy of 58.3\%. When AI was implemented as a DSS, non-expert endoscopists improved their diagnostic accuracy to 75\%. Conclusions AI may have the potential to support non-expert endoscopists in the assessment of videos of BE and BERN. Limitations of this study include the low number of videos used. Randomized clinical trials in a real-life setting should be performed to confirm these results.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @article{ScheppachMendelProbstetal., author = {Scheppach, Markus W. and Mendel, Robert and Probst, Andreas and Meinikheim, Michael and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {ARTIFICIAL INTELLIGENCE (AI) - ASSISTED VESSEL AND TISSUE RECOGNITION IN THIRD-SPACE ENDOSCOPY}, series = {Endoscopy}, volume = {54}, journal = {Endoscopy}, number = {S01}, publisher = {Thieme}, doi = {10.1055/s-0042-1745037}, pages = {S175}, abstract = {Aims Third-space endoscopy procedures such as endoscopic submucosal dissection (ESD) and peroral endoscopic myotomy (POEM) are complex interventions with elevated risk of operator-dependent adverse events, such as intra-procedural bleeding and perforation. We aimed to design an artificial intelligence clinical decision support solution (AI-CDSS, "Smart ESD") for the detection and delineation of vessels, tissue structures, and instruments during third-space endoscopy procedures. Methods Twelve full-length third-space endoscopy videos were extracted from the Augsburg University Hospital database. 1686 frames were annotated for the following categories: Submucosal layer, blood vessels, electrosurgical knife and endoscopic instrument. A DeepLabv3+neural network with a 101-layer ResNet backbone was trained and validated internally. Finally, the ability of the AI system to detect visible vessels during ESD and POEM was determined on 24 separate video clips of 7 to 46 seconds duration and showing 33 predefined vessels. These video clips were also assessed by an expert in third-space endoscopy. Results Smart ESD showed a vessel detection rate (VDR) of 93.94\%, while an average of 1.87 false positive signals were recorded per minute. VDR of the expert endoscopist was 90.1\% with no false positive findings. On the internal validation data set using still images, the AI system demonstrated an Intersection over Union (IoU), mean Dice score and pixel accuracy of 63.47\%, 76.18\% and 86.61\%, respectively. Conclusions This is the first AI-CDSS aiming to mitigate operator-dependent limitations during third-space endoscopy. Further clinical trials are underway to better understand the role of AI in such procedures.}, language = {en} } @inproceedings{WeberNunesRauberPalm, author = {Weber Nunes, Danilo and Rauber, David and Palm, Christoph}, title = {Self-supervised 3D Vision Transformer Pre-training for Robust Brain Tumor Classification}, series = {Bildverarbeitung f{\"u}r die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, editor = {Palm, Christoph and Breininger, Katharina and Deserno, Thomas M. and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, doi = {10.1007/978-3-658-47422-5_69}, pages = {298 -- 303}, abstract = {Brain tumors pose significant challenges in neurology, making precise classification crucial for prognosis and treatment planning. This work investigates the effectiveness of a self-supervised learning approach-masked autoencoding (MAE)-to pre-train a vision transformer (ViT) model for brain tumor classification. Our method uses non-domain specific data, leveraging the ADNI and OASIS-3 MRI datasets, which primarily focus on degenerative diseases, for pretraining. The model is subsequently fine-tuned and evaluated on the BraTS glioma and meningioma datasets, representing a novel use of these datasets for tumor classification. The pre-trained MAE ViT model achieves an average F1 score of 0.91 in a 5-fold cross-validation setting, outperforming the nnU-Net encoder trained from scratch, particularly under limited data conditions. These findings highlight the potential of self-supervised MAE in enhancing brain tumor classification accuracy, even with restricted labeled data.}, language = {en} } @inproceedings{WeiherervonRiedheimBrebantetal., author = {Weiherer, Maximilian and von Riedheim, Antonia and Br{\´e}bant, Vanessa and Egger, Bernhard and Palm, Christoph}, title = {iRBSM: A Deep Implicit 3D Breast Shape Model}, series = {Bildverarbeitung f{\"u}r die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, editor = {Palm, Christoph and Breininger, Katharina and Deserno, Thomas M. and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, doi = {10.1007/978-3-658-47422-5_11}, pages = {38 -- 43}, abstract = {We present the first deep implicit 3D shape model of the female breast, building upon and improving the recently proposed Regensburg Breast Shape Model (RBSM). Compared to its PCA-based predecessor, our model employs implicit neural representations; hence, it can be trained on raw 3D breast scans and eliminates the need for computationally demanding non-rigid registration, a task that is particularly difficult for feature-less breast shapes. The resulting model, dubbed iRBSM, captures detailed surface geometry including fine structures such as nipples and belly buttons, is highly expressive, and outperforms the RBSM on different surface reconstruction tasks. Finally, leveraging the iRBSM, we present a prototype application to 3D reconstruct breast shapes from just a single image. Model and code publicly available at https://rbsm.re-mic.de/implicit.}, language = {en} } @inproceedings{GutbrodGeislerRauberetal., author = {Gutbrod, Max and Geisler, Benedikt and Rauber, David and Palm, Christoph}, title = {Data Augmentation for Images of Chronic Foot Wounds}, series = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, editor = {Maier, Andreas and Deserno, Thomas M. and Handels, Heinz and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer}, address = {Wiesbaden}, doi = {10.1007/978-3-658-44037-4_71}, pages = {261 -- 266}, abstract = {Training data for Neural Networks is often scarce in the medical domain, which often results in models that struggle to generalize and consequently showpoor performance on unseen datasets. Generally, adding augmentation methods to the training pipeline considerably enhances a model's performance. Using the dataset of the Foot Ulcer Segmentation Challenge, we analyze two additional augmentation methods in the domain of chronic foot wounds - local warping of wound edges along with projection and blurring of shapes inside wounds. Our experiments show that improvements in the Dice similarity coefficient and Normalized Surface Distance metrics depend on a sensible selection of those augmentation methods.}, language = {en} } @misc{SchroederSemmelmannSiegmundetal., author = {Schroeder, Josef A. and Semmelmann, Matthias and Siegmund, Heiko and Grafe, Claudia and Evert, Matthias and Palm, Christoph}, title = {Improved interactive computer-assisted approach for evaluation of ultrastructural cilia abnormalities}, series = {Ultrastructural Pathology}, volume = {41}, journal = {Ultrastructural Pathology}, number = {1}, doi = {10.1080/01913123.2016.1270978}, pages = {112 -- 113}, subject = {Zilie}, language = {en} } @inproceedings{RueckertRiederFeussneretal., author = {R{\"u}ckert, Tobias and Rieder, Maximilian and Feussner, Hubertus and Wilhelm, Dirk and R{\"u}ckert, Daniel and Palm, Christoph}, title = {Smoke Classification in Laparoscopic Cholecystectomy Videos Incorporating Spatio-temporal Information}, series = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2024: Proceedings, German Workshop on Medical Image Computing, March 10-12, 2024, Erlangen}, editor = {Maier, Andreas and Deserno, Thomas M. and Handels, Heinz and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springeer}, address = {Wiesbaden}, doi = {10.1007/978-3-658-44037-4_78}, pages = {298 -- 303}, abstract = {Heavy smoke development represents an important challenge for operating physicians during laparoscopic procedures and can potentially affect the success of an intervention due to reduced visibility and orientation. Reliable and accurate recognition of smoke is therefore a prerequisite for the use of downstream systems such as automated smoke evacuation systems. Current approaches distinguish between non-smoked and smoked frames but often ignore the temporal context inherent in endoscopic video data. In this work, we therefore present a method that utilizes the pixel-wise displacement from randomly sampled images to the preceding frames determined using the optical flow algorithm by providing the transformed magnitude of the displacement as an additional input to the network. Further, we incorporate the temporal context at evaluation time by applying an exponential moving average on the estimated class probabilities of the model output to obtain more stable and robust results over time. We evaluate our method on two convolutional-based and one state-of-the-art transformer architecture and show improvements in the classification results over a baseline approach, regardless of the network used.}, language = {en} } @unpublished{MendelRueckertWilhelmetal., author = {Mendel, Robert and R{\"u}ckert, Tobias and Wilhelm, Dirk and R{\"u}ckert, Daniel and Palm, Christoph}, title = {Motion-Corrected Moving Average: Including Post-Hoc Temporal Information for Improved Video Segmentation}, doi = {10.48550/arXiv.2403.03120}, pages = {9}, abstract = {Real-time computational speed and a high degree of precision are requirements for computer-assisted interventions. Applying a segmentation network to a medical video processing task can introduce significant inter-frame prediction noise. Existing approaches can reduce inconsistencies by including temporal information but often impose requirements on the architecture or dataset. This paper proposes a method to include temporal information in any segmentation model and, thus, a technique to improve video segmentation performance without alterations during training or additional labeling. With Motion-Corrected Moving Average, we refine the exponential moving average between the current and previous predictions. Using optical flow to estimate the movement between consecutive frames, we can shift the prior term in the moving-average calculation to align with the geometry of the current frame. The optical flow calculation does not require the output of the model and can therefore be performed in parallel, leading to no significant runtime penalty for our approach. We evaluate our approach on two publicly available segmentation datasets and two proprietary endoscopic datasets and show improvements over a baseline approach.}, subject = {Deep Learning}, language = {en} } @misc{ScheppachMendelProbstetal., author = {Scheppach, Markus W. and Mendel, Robert and Probst, Andreas and Meinikheim, Michael and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Artificial Intelligence (AI) - assisted vessel and tissue recognition during third space endoscopy (Smart ESD)}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {60}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {08}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/s-0042-1755110}, abstract = {Clinical setting Third space procedures such as endoscopic submucosal dissection (ESD) and peroral endoscopic myotomy (POEM) are complex minimally invasive techniques with an elevated risk for operator-dependent adverse events such as bleeding and perforation. This risk arises from accidental dissection into the muscle layer or through submucosal blood vessels as the submucosal cutting plane within the expanding resection site is not always apparent. Deep learning algorithms have shown considerable potential for the detection and characterization of gastrointestinal lesions. So-called AI - clinical decision support solutions (AI-CDSS) are commercially available for polyp detection during colonoscopy. Until now, these computer programs have concentrated on diagnostics whereas an AI-CDSS for interventional endoscopy has not yet been introduced. We aimed to develop an AI-CDSS („Smart ESD") for real-time intra-procedural detection and delineation of blood vessels, tissue structures and endoscopic instruments during third-space endoscopic procedures. Characteristics of Smart ESD An AI-CDSS was invented that delineates blood vessels, tissue structures and endoscopic instruments during third-space endoscopy in real-time. The output can be displayed by an overlay over the endoscopic image with different modes of visualization, such as a color-coded semitransparent area overlay, or border tracing (demonstration video). Hereby the optimal layer for dissection can be visualized, which is close above or directly at the muscle layer, depending on the applied technique (ESD or POEM). Furthermore, relevant blood vessels (thickness> 1mm) are delineated. Spatial proximity between the electrosurgical knife and a blood vessel triggers a warning signal. By this guidance system, inadvertent dissection through blood vessels could be averted. Technical specifications A DeepLabv3+ neural network architecture with KSAC and a 101-layer ResNeSt backbone was used for the development of Smart ESD. It was trained and validated with 2565 annotated still images from 27 full length third-space endoscopic videos. The annotation classes were blood vessel, submucosal layer, muscle layer, electrosurgical knife and endoscopic instrument shaft. A test on a separate data set yielded an intersection over union (IoU) of 68\%, a Dice Score of 80\% and a pixel accuracy of 87\%, demonstrating a high overlap between expert and AI segmentation. Further experiments on standardized video clips showed a mean vessel detection rate (VDR) of 85\% with values of 92\%, 70\% and 95\% for POEM, rectal ESD and esophageal ESD respectively. False positive measurements occurred 0.75 times per minute. 7 out of 9 vessels which caused intraprocedural bleeding were caught by the algorithm, as well as both vessels which required hemostasis via hemostatic forceps. Future perspectives Smart ESD performed well for vessel and tissue detection and delineation on still images, as well as on video clips. During a live demonstration in the endoscopy suite, clinical applicability of the innovation was examined. The lag time for processing of the live endoscopic image was too short to be visually detectable for the interventionist. Even though the algorithm could not be applied during actual dissection by the interventionist, Smart ESD appeared readily deployable during visual assessment by ESD experts. Therefore, we plan to conduct a clinical trial in order to obtain CE-certification of the algorithm. This new technology may improve procedural safety and speed, as well as training of modern minimally invasive endoscopic resection techniques.}, subject = {Bildgebendes Verfahren}, language = {en} } @misc{MeinikheimMendelProbstetal., author = {Meinikheim, Michael and Mendel, Robert and Probst, Andreas and Scheppach, Markus W. and Messmann, Helmut and Palm, Christoph and Ebigbo, Alanna}, title = {Barrett-Ampel}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {60}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {08}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/s-0042-1755109}, abstract = {Hintergrund Adenokarzinome des {\"O}sophagus sind bis heute mit einer infausten Prognose vergesellschaftet (1). Obwohl Endoskopiker mit Barrett-{\"O}sophagus als Pr{\"a}kanzerose konfrontiert werden, ist vor allem f{\"u}r nicht-Experten die Differenzierung zwischen Barrett-{\"O}sophagus ohne Dysplasie und assoziierten Neoplasien mitunter schwierig. Existierende Biopsieprotokolle (z.B. Seattle Protokoll) sind oftmals unzuverl{\"a}ssig (2). Eine fr{\"u}hzeitige Diagnose des Adenokarzinoms ist allerdings von fundamentaler Bedeutung f{\"u}r die Prognose des Patienten. Forschungsansatz Auf der Grundlage dieser Problematik, entwickelten wir in Kooperation mit dem Forschungslabor „Regensburg Medical Image Computing (ReMIC)" der OTH Regensburg ein auf k{\"u}nstlicher Intelligenz (KI) basiertes Entscheidungsunterst{\"u}tzungssystem (CDSS). Das auf einer DeepLabv3+ neuronalen Netzwerkarchitektur basierende CDSS differenziert mittels Mustererkennung Barrett- {\"O}sophagus ohne Dysplasie von Barrett-{\"O}sophagus mit Dysplasie bzw. Neoplasie („Klassifizierung"). Hierbei werden gemittelte Ausgabewahrscheinlichkeiten mit einem vom Benutzer definierten Schwellenwert verglichen. F{\"u}r Vorhersagen, die den Schwellenwert {\"u}berschreiten, berechnen wir die Kontur der Region und die Fl{\"a}che. Sobald die vorhergesagte L{\"a}sion eine bestimmte Gr{\"o}ße in der Eingabe {\"u}berschreitet, heben wir sie und ihren Umriss hervor. So erm{\"o}glicht eine farbkodierte Visualisierung eine Abgrenzung zwischen Dysplasie bzw. Neoplasie und normalem Barrett-Epithel („Segmentierung"). In einer Studie an Bildern in „Weißlicht" (WL) und „Narrow Band Imaging" (NBI) demonstrierten wir eine Sensitivit{\"a}t von mehr als 90\% und eine Spezifit{\"a}t von mehr als 80\% (3). In einem n{\"a}chsten Schritt, differenzierte unser KI-Algorithmus Barrett- Metaplasien von assoziierten Neoplasien anhand von zuf{\"a}llig abgegriffenen Bildern in Echtzeit mit einer Accuracy von 89.9\% (4). Darauf folgend, entwickelten wir unser System dahingehend weiter, dass unser Algorithmus nun auch dazu in der Lage ist, Untersuchungsvideos in WL, NBI und „Texture and Color Enhancement Imaging" (TXI) in Echtzeit zu analysieren (5). Aktuell f{\"u}hren wir eine Studie in einem randomisiert-kontrollierten Ansatz an unver{\"a}nderten Untersuchungsvideos in WL, NBI und TXI durch. Ausblick Um Patienten mit aus Barrett-Metaplasien resultierenden Neoplasien fr{\"u}hestm{\"o}glich an „High-Volume"-Zentren {\"u}berweisen zu k{\"o}nnen, soll unser KI-Algorithmus zuk{\"u}nftig vor allem Endoskopiker ohne extensive Erfahrung bei der Beurteilung von Barrett- {\"O}sophagus in der Krebsfr{\"u}herkennung unterst{\"u}tzen.}, subject = {Speiser{\"o}hrenkrebs}, language = {de} } @misc{ScheppachMendelProbstetal., author = {Scheppach, Markus W. and Mendel, Robert and Probst, Andreas and Meinikheim, Michael and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Intraprozedurale Strukturerkennung bei Third-Space Endoskopie mithilfe eines Deep-Learning Algorithmus}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {60}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {04}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/s-0042-1745652}, pages = {e250-e251}, abstract = {Einleitung Third-Space Interventionen wie die endoskopische Submukosadissektion (ESD) und die perorale endoskopische Myotomie (POEM) sind technisch anspruchsvoll und mit einem erh{\"o}hten Risiko f{\"u}r intraprozedurale Komplikationen wie Blutung oder Perforation assoziiert. Moderne Computerprogramme zur Unterst{\"u}tzung bei diagnostischen Entscheidungen werden unter Einsatz von k{\"u}nstlicher Intelligenz (KI) in der Endoskopie bereits erfolgreich eingesetzt. Ziel der vorliegenden Arbeit war es, relevante anatomische Strukturen mithilfe eines Deep-Learning Algorithmus zu detektieren und segmentieren, um die Sicherheit und Anwendbarkeit von ESD und POEM zu erh{\"o}hen. Methoden Zw{\"o}lf Videoaufnahmen in voller L{\"a}nge von Third-Space Endoskopien wurden aus der Datenbank des Universit{\"a}tsklinikums Augsburg extrahiert. 1686 Einzelbilder wurden f{\"u}r die Kategorien Submukosa, Blutgef{\"a}ß, Dissektionsmesser und endoskopisches Instrument annotiert und segmentiert. Mit diesem Datensatz wurde ein DeepLabv3+neuronales Netzwerk auf der Basis eines ResNet mit 101 Schichten trainiert und intern anhand der Parameter Intersection over Union (IoU), Dice Score und Pixel Accuracy validiert. Die F{\"a}higkeit des Algorithmus zur Gef{\"a}ßdetektion wurde anhand von 24 Videoclips mit einer Spieldauer von 7 bis 46 Sekunden mit 33 vordefinierten Gef{\"a}ßen evaluiert. Anhand dieses Tests wurde auch die Gef{\"a}ßdetektionsrate eines Experten in der Third-Space Endoskopie ermittelt. Ergebnisse Der Algorithmus zeigte eine Gef{\"a}ßdetektionsrate von 93,94\% mit einer mittleren Rate an falsch positiven Signalen von 1,87 pro Minute. Die Gef{\"a}ßdetektionsrate des Experten lag bei 90,1\% ohne falsch positive Ergebnisse. In der internen Validierung an Einzelbildern wurde eine IoU von 63,47\%, ein mittlerer Dice Score von 76,18\% und eine Pixel Accuracy von 86,61\% ermittelt. Zusammenfassung Dies ist der erste KI-Algorithmus, der f{\"u}r den Einsatz in der therapeutischen Endoskopie entwickelt wurde. Pr{\"a}limin{\"a}re Ergebnisse deuten auf eine mit Experten vergleichbare Detektion von Gef{\"a}ßen w{\"a}hrend der Untersuchung hin. Weitere Untersuchungen sind n{\"o}tig, um die Leistung des Algorithmus im Vergleich zum Experten genauer zu eruieren sowie einen m{\"o}glichen klinischen Nutzen zu ermitteln.}, language = {de} } @article{SouzaJrPachecoPassosetal., author = {Souza Jr., Luis Antonio de and Pacheco, Andr{\´e} G.C. and Passos, Leandro A. and Santana, Marcos Cleison S. and Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {DeepCraftFuse: visual and deeply-learnable features work better together for esophageal cancer detection in patients with Barrett's esophagus}, series = {Neural Computing and Applications}, volume = {36}, journal = {Neural Computing and Applications}, publisher = {Springer}, address = {London}, doi = {10.1007/s00521-024-09615-z}, pages = {10445 -- 10459}, abstract = {Limitations in computer-assisted diagnosis include lack of labeled data and inability to model the relation between what experts see and what computers learn. Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their accountability and transparency level must be improved to transfer this success into clinical practice. The reliability of machine learning decisions must be explained and interpreted, especially for supporting the medical diagnosis. While deep learning techniques are broad so that unseen information might help learn patterns of interest, human insights to describe objects of interest help in decision-making. This paper proposes a novel approach, DeepCraftFuse, to address the challenge of combining information provided by deep networks with visual-based features to significantly enhance the correct identification of cancerous tissues in patients affected with Barrett's esophagus (BE). We demonstrate that DeepCraftFuse outperforms state-of-the-art techniques on private and public datasets, reaching results of around 95\% when distinguishing patients affected by BE that is either positive or negative to esophageal cancer.}, subject = {Deep Learning}, language = {en} } @article{SouzaPachecodeSouzaetal., author = {Souza, Luis A. and Pacheco, Andr{\´e} G.C. and de Souza, Alberto F. and Oliveira-Santos, Thiago and Badue, Claudine and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {TransConv: a lightweight architecture based on transformers and convolutional neural networks for adenocarcinoma and Barrett's esophagus identification}, series = {Neural Computing and Applications}, journal = {Neural Computing and Applications}, number = {37}, publisher = {Springer}, doi = {10.1007/s00521-025-11299-y}, pages = {15535 -- 15546}, abstract = {Barrett's esophagus, also known as BE, is commonly associated with repeated exposure to stomach acid. If not treated properly, it may evolve into esophageal adenocarcinoma, aka esophageal cancer. This paper proposes TransConv, a hybrid architecture that benefits from features learned by pre-trained vision transformers (ViTs) and convolutional neural networks (CNNs), followed by a shallow neural network composed of three normalizations, ReLU activations, and fully connected layers, and a SoftMax head to distinguish between BE and esophageal cancer. TransConv is designed to be training-lightweight, and for the ViT and CNN backbone models, weights are kept frozen during training, i.e., the primary goal of TransConv is to learn the weights of the fully connected layer from both backbones only, avoiding the burden of updating their weights but still learning their final descriptions for the lightweight convolutional model. We report promising results with low computational training costs in two datasets, one public and another private. From our achievements, TransConv was able to deliver balanced accuracy results around 85\% and 86\% for each evaluated dataset, respectively, in a design that required only 50 epochs of model training, a very reduced number compared to state-of-the-art conducted studies in the same domain.}, language = {en} } @unpublished{RueckertRueckertPalm, author = {R{\"u}ckert, Tobias and R{\"u}ckert, Daniel and Palm, Christoph}, title = {Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art}, doi = {10.48550/arXiv.2304.13014}, pages = {25}, abstract = {In the field of computer- and robot-assisted minimally invasive surgery, enormous progress has been made in recent years based on the recognition of surgical instruments in endoscopic images. Especially the determination of the position and type of the instruments is of great interest here. Current work involves both spatial and temporal information with the idea, that the prediction of movement of surgical tools over time may improve the quality of final segmentations. The provision of publicly available datasets has recently encouraged the development of new methods, mainly based on deep learning. In this review, we identify datasets used for method development and evaluation, as well as quantify their frequency of use in the literature. We further present an overview of the current state of research regarding the segmentation and tracking of minimally invasive surgical instruments in endoscopic images. The paper focuses on methods that work purely visually without attached markers of any kind on the instruments, taking into account both single-frame segmentation approaches as well as those involving temporal information. A discussion of the reviewed literature is provided, highlighting existing shortcomings and emphasizing available potential for future developments. The publications considered were identified through the platforms Google Scholar, Web of Science, and PubMed. The search terms used were "instrument segmentation", "instrument tracking", "surgical tool segmentation", and "surgical tool tracking" and result in 408 articles published between 2015 and 2022 from which 109 were included using systematic selection criteria.}, language = {en} } @inproceedings{GutbrodRauberWeberNunesetal., author = {Gutbrod, Max and Rauber, David and Weber Nunes, Danilo and Palm, Christoph}, title = {OpenMIBOOD: Open Medical Imaging Benchmarks for Out-Of-Distribution Detection}, series = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10.-17. June 2025, Nashville}, booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10.-17. June 2025, Nashville}, publisher = {IEEE}, isbn = {979-8-3315-4364-8}, doi = {10.1109/CVPR52734.2025.02410}, pages = {25874 -- 25886}, abstract = {The growing reliance on Artificial Intelligence (AI) in critical domains such as healthcare demands robust mechanisms to ensure the trustworthiness of these systems, especially when faced with unexpected or anomalous inputs. This paper introduces the Open Medical Imaging Benchmarks for Out-Of-Distribution Detection (OpenMIBOOD), a comprehensive framework for evaluating out-of-distribution (OOD) detection methods specifically in medical imaging contexts. OpenMIBOOD includes three benchmarks from diverse medical domains, encompassing 14 datasets divided into covariate-shifted in-distribution, nearOOD, and far-OOD categories. We evaluate 24 post-hoc methods across these benchmarks, providing a standardized reference to advance the development and fair comparison of OODdetection methods. Results reveal that findings from broad-scale OOD benchmarks in natural image domains do not translate to medical applications, underscoring the critical need for such benchmarks in the medical field. By mitigating the risk of exposing AI models to inputs outside their training distribution, OpenMIBOOD aims to support the advancement of reliable and trustworthy AI systems in healthcare. The repository is available at https://github.com/remic-othr/OpenMIBOOD.}, language = {en} } @unpublished{RueckertRauberMaerkletal., author = {R{\"u}ckert, Tobias and Rauber, David and Maerkl, Raphaela and Klausmann, Leonard and Yildiran, Suemeyye R. and Gutbrod, Max and Nunes, Danilo Weber and Moreno, Alvaro Fernandez and Luengo, Imanol and Stoyanov, Danail and Toussaint, Nicolas and Cho, Enki and Kim, Hyeon Bae and Choo, Oh Sung and Kim, Ka Young and Kim, Seong Tae and Arantes, Gon{\c{c}}alo and Song, Kehan and Zhu, Jianjun and Xiong, Junchen and Lin, Tingyi and Kikuchi, Shunsuke and Matsuzaki, Hiroki and Kouno, Atsushi and Manesco, Jo{\~a}o Renato Ribeiro and Papa, Jo{\~a}o Paulo and Choi, Tae-Min and Jeong, Tae Kyeong and Park, Juyoun and Alabi, Oluwatosin and Wei, Meng and Vercauteren, Tom and Wu, Runzhi and Xu, Mengya and an Wang, and Bai, Long and Ren, Hongliang and Yamlahi, Amine and Hennighausen, Jakob and Maier-Hein, Lena and Kondo, Satoshi and Kasai, Satoshi and Hirasawa, Kousuke and Yang, Shu and Wang, Yihui and Chen, Hao and Rodr{\´i}guez, Santiago and Aparicio, Nicol{\´a}s and Manrique, Leonardo and Lyons, Juan Camilo and Hosie, Olivia and Ayobi, Nicol{\´a}s and Arbel{\´a}ez, Pablo and Li, Yiping and Khalil, Yasmina Al and Nasirihaghighi, Sahar and Speidel, Stefanie and R{\"u}ckert, Daniel and Feussner, Hubertus and Wilhelm, Dirk and Palm, Christoph}, title = {Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge}, pages = {36}, abstract = {Reliable recognition and localization of surgical instruments in endoscopic video recordings are foundational for a wide range of applications in computer- and robot-assisted minimally invasive surgery (RAMIS), including surgical training, skill assessment, and autonomous assistance. However, robust performance under real-world conditions remains a significant challenge. Incorporating surgical context - such as the current procedural phase - has emerged as a promising strategy to improve robustness and interpretability. To address these challenges, we organized the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) sub-challenge as part of the Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We introduced a novel, multi-center dataset comprising thirteen full-length laparoscopic cholecystectomy videos collected from three distinct medical institutions, with unified annotations for three interrelated tasks: surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation. Unlike existing datasets, ours enables joint investigation of instrument localization and procedural context within the same data while supporting the integration of temporal information across entire procedures. We report results and findings in accordance with the BIAS guidelines for biomedical image analysis challenges. The PhaKIR sub-challenge advances the field by providing a unique benchmark for developing temporally aware, context-driven methods in RAMIS and offers a high-quality resource to support future research in surgical scene understanding.}, language = {en} }