@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} } @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} } @misc{KlausmannRueckertRauberetal., author = {Klausmann, Leonard and Rueckert, Tobias and Rauber, David and Maerkl, Raphaela and Yildiran, Suemeyye R. and Gutbrod, Max and Palm, Christoph}, title = {Abstract: DIY Challenge Blueprint}, series = {Bildverarbeitung f{\"u}r die Medizin 2025: Proceedings, German Conference on Medical Image Computing, L{\"u}beck March 15-17, 2026}, journal = {Bildverarbeitung f{\"u}r die Medizin 2025: Proceedings, German Conference on Medical Image Computing, L{\"u}beck March 15-17, 2026}, editor = {Handels, Heinz and Breininger, Katharina and Deserno, Thomas M. and Maier, Andreas and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, doi = {10.1007/978-3-658-51100-5_27}, pages = {131 -- 131}, abstract = {The high cost of challenge platforms prevents many people from organizing their own competitions. The do-it-yourself (DIY) challenge blueprint [1] allows you to host your own biomedical AI benchmark challenge. Our DIY approach circumvents the current constraints of commercial challenge platforms. A sovereign, extensible and cost-efficient deployment is provided via containerised, identity-managed and reproducible pipelines. Focus lies on GDPR-compliant hosting via infrastructure-as-code, automated evaluation, modular orchestration, and role-based identity and access management. The framework integrates Docker-based execution and standardised interfaces for task definitions, dataset curation and evaluation. All in all it is designed to be flexible and modular, as demonstrated in the MICCAI 2024 PhaKIR challenge [2, 3]. In this case study, different medical tasks on a multicentre laparoscopic dataset with framewise labels for phases and spatial annotations for instruments across fulllength videos were supported. This case study empirically validates the DIY challenge blueprint as a reproducible and customizable challenge-hosting infrastructure. The full code can be found at https://github.com/remic-othr/PhaKIR_DIY.}, subject = {Bildverarbeitung}, language = {en} }