@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{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} } @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} } @misc{RueckertRueckertPalm, author = {R{\"u}ckert, Tobias and R{\"u}ckert, Daniel and Palm, Christoph}, title = {Corrigendum to "Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art" [Comput. Biol. Med. 169 (2024) 107929]}, series = {Computers in Biology and Medicine}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier}, doi = {10.1016/j.compbiomed.2024.108027}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70337}, pages = {1}, abstract = {The authors regret that the SAR-RARP50 dataset is missing from the description of publicly available datasets presented in Chapter 4.}, language = {en} } @article{HammerNunesHammeretal., author = {Hammer, Simone and Nunes, Danilo Weber and Hammer, Michael and Zeman, Florian and Akers, Michael and G{\"o}tz, Andrea and Balla, Annika and Doppler, Michael Christian and Fellner, Claudia and Da Platz Batista Silva, Natascha and Thurn, Sylvia and Verloh, Niklas and Stroszczynski, Christian and Wohlgemuth, Walter Alexander and Palm, Christoph and Uller, Wibke}, title = {Deep learning-based differentiation of peripheral high-flow and low-flow vascular malformations in T2-weighted short tau inversion recovery MRI}, series = {Clinical hemorheology and microcirculation}, journal = {Clinical hemorheology and microcirculation}, edition = {Pre-press}, publisher = {IOP Press}, doi = {10.3233/CH-232071}, pages = {1 -- 15}, abstract = {BACKGROUND Differentiation of high-flow from low-flow vascular malformations (VMs) is crucial for therapeutic management of this orphan disease. OBJECTIVE A convolutional neural network (CNN) was evaluated for differentiation of peripheral vascular malformations (VMs) on T2-weighted short tau inversion recovery (STIR) MRI. METHODS 527 MRIs (386 low-flow and 141 high-flow VMs) were randomly divided into training, validation and test set for this single-center study. 1) Results of the CNN's diagnostic performance were compared with that of two expert and four junior radiologists. 2) The influence of CNN's prediction on the radiologists' performance and diagnostic certainty was evaluated. 3) Junior radiologists' performance after self-training was compared with that of the CNN. RESULTS Compared with the expert radiologists the CNN achieved similar accuracy (92\% vs. 97\%, p = 0.11), sensitivity (80\% vs. 93\%, p = 0.16) and specificity (97\% vs. 100\%, p = 0.50). In comparison to the junior radiologists, the CNN had a higher specificity and accuracy (97\% vs. 80\%, p <  0.001; 92\% vs. 77\%, p <  0.001). CNN assistance had no significant influence on their diagnostic performance and certainty. After self-training, the junior radiologists' specificity and accuracy improved and were comparable to that of the CNN. CONCLUSIONS Diagnostic performance of the CNN for differentiating high-flow from low-flow VM was comparable to that of expert radiologists. CNN did not significantly improve the simulated daily practice of junior radiologists, self-training was more effective.}, language = {en} } @article{RueckertRauberMaerkletal., author = {Rueckert, 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 Wang, An 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 Palm, Christoph and Wilhelm, Dirk and Feussner, Hubertus and Rueckert, Daniel and Speidel, Stefanie and Nasirihaghighi, Sahar and Al Khalil, Yasmina and Li, Yiping and Arbel{\´a}ez, Pablo and Ayobi, Nicol{\´a}s and Hosie, Olivia and Lyons, Juan Camilo}, title = {Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge}, series = {Medical Image Analysis}, volume = {109}, journal = {Medical Image Analysis}, publisher = {Elsevier}, issn = {1361-8415}, doi = {10.1016/j.media.2026.103945}, pages = {31}, 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} } @misc{RueckertRauberKlausmannetal., author = {Rueckert, Tobias and Rauber, David and Klausmann, Leonard and Gutbrod, Max and Rueckert, Daniel and Feussner, Hubertus and Wilhelm, Dirk and Palm, Christoph}, title = {PhaKIR Dataset - Surgical Procedure Phase, Keypoint, and Instrument Recognition [Data set]}, doi = {10.5281/zenodo.15740620}, abstract = {Note: A script for extracting the individual frames from the video files while preserving the challenge-compliant directory structure and frame-to-mask naming conventions is available on GitHub and can be accessed here: https://github.com/remic-othr/PhaKIR_Dataset. The dataset is described in the following publications: Rueckert, Tobias et al.: Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge. arXiv preprint, https://arxiv.org/abs/2507.16559. 2025. Rueckert, Tobias et al.: Video Dataset for Surgical Phase, Keypoint, and Instrument Recognition in Laparoscopic Surgery (PhaKIR). arXiv preprint, https://arxiv.org/abs/2511.06549. 2025. The proposed dataset was used as the training dataset in the PhaKIR challenge (https://phakir.re-mic.de/) as part of EndoVis-2024 at MICCAI 2024 and consists of eight real-world videos of human cholecystectomies ranging from 23 to 60 minutes in duration. The procedures were performed by experienced physicians, and the videos were recorded in three hospitals. In addition to existing datasets, our annotations provide pixel-wise instance segmentation masks of surgical instruments for a total of 19 categories, coordinates of relevant instrument keypoints (instrument tip(s), shaft-tip transition, shaft), both at an interval of one frame per second, and specifications regarding the intervention phases for a total of eight different phase categories for each individual frame in one dataset and thus comprehensively cover instrument localization and the context of the operation. Furthermore, the provision of the complete video sequences offers the opportunity to include the temporal information regarding the respective tasks and thus further optimize the resulting methods and outcomes.}, language = {en} } @misc{GutbrodRauberWeberNunesetal., author = {Gutbrod, Max and Rauber, David and Weber Nunes, Danilo and Palm, Christoph}, title = {A cleaned subset of the first five CATARACTS test videos [Data set]}, doi = {10.5281/zenodo.14924735}, abstract = {This dataset is a subset of the original CATARACTS test dataset and is used by the OpenMIBOOD framework to evaluate a specific out-of-distribution setting. When using this dataset, it is mandatory to cite the corresponding publication (OpenMIBOOD (10.1109/CVPR52734.2025.02410)) and follow the acknowledgement and citation requirements of the original dataset (CATARACTS). The original CATARACTS dataset (associated publication,Homepage) consists of 50 videos of cataract surgeries, split into 25 train and 25 test videos. This subset contains the frames of the first 5 test videos. Further, black frames at the beginning of each video were removed.}, language = {en} }