@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} } @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} } @misc{OPUS4-6079, title = {Bildverarbeitung f{\"u}r die Medizin 2023}, editor = {Deserno, Thomas M. and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-41656-0}, issn = {1431-472X}, doi = {10.1007/978-3-658-41657-7}, pages = {317}, abstract = {Seit mehr als 25 Jahren ist der Workshop "Bildverarbeitung f{\"u}r die Medizin" als erfolgreiche Veranstaltung etabliert. Ziel ist auch 2023 wieder die Darstellung aktueller Forschungsergebnisse und die Vertiefung der Gespr{\"a}che zwischen Wissenschaftlern, Industrie und Anwendern. Die Beitr{\"a}ge dieses Bandes - viele davon in englischer Sprache - umfassen alle Bereiche der medizinischen Bildverarbeitung, insbesondere die Bildgebung und -akquisition, Segmentierung und Analyse, Visualisierung und Animation, computerunterst{\"u}tzte Diagnose sowie bildgest{\"u}tzte Therapieplanung und Therapie. Hierbei kommen Methoden des maschinelles Lernens, der biomechanischen Modellierung sowie der Validierung und Qualit{\"a}tssicherung zum Einsatz.}, subject = {Bildverarbeitung}, language = {de} } @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} } @misc{OPUS4-7967, title = {Bildverarbeitung f{\"u}r die Medizin 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 M.}, publisher = {Springer Fachmedien Wiesbaden}, address = {Wiesbaden}, isbn = {978-3-658-47421-8}, issn = {1431-472X}, doi = {10.1007/978-3-658-47422-5}, pages = {XXIII, 354}, abstract = {Die Konferenz "BVM - Bildverarbeitung f{\"u}r die Medizin" ist seit vielen Jahren als die nationale Plattform f{\"u}r den Austausch von Ideen und die Diskussion der neuesten Forschungsergebnisse im Bereich der Medizinischen Bildverarbeitung und der K{\"u}nstlichen Intelligenz (KI) etabliert. Auch 2025 werden wir aktuelle Forschungsergebnisse vorstellen und Gespr{\"a}che zwischen (jungen) Wissenschaftler*innen, Industrie und Anwender*innen vertiefen. Die Beitr{\"a}ge dieses Bandes - die meisten davon in englischer Sprache - umfassen alle Bereiche der medizinischen Bildverarbeitung, insbesondere die Bildgebung und -akquisition, Segmentierung und Analyse, Registrierung, Visualisierung und Animation, computerunterst{\"u}tzte Diagnose sowie bildgest{\"u}tzte Therapieplanung und Therapie. Hierbei kommen Methoden des maschinellen Lernens, der biomechanischen Modellierung sowie der Validierung und Qualit{\"a}tssicherung zum Einsatz. Das Kapitel "Leveraging multiple total body segmentators and anatomy-informed post-processing for segmenting bones in Lung CTs" ist unter einer Creative Commons Attribution 4.0 International License {\"u}ber link.springer.com frei verf{\"u}gbar (Open Access). Die Herausgebenden Prof. Palm forscht im Bereich KI f{\"u}r die Medizin mit einem Schwerpunkt in der Analyse endoskopischer Bilddaten zur computerunterst{\"u}tzten Diagnose und Therapie. Prof. Breininger entwickelt robuste Ans{\"a}tze des maschinellen Lernens in verschiedenen interdisziplin{\"a}ren Bereichen, mit einem Schwerpunkt auf medizinischen Bilddaten. Prof. Deserno forscht in Biosignal- und Bilderzeugung und -verarbeitung, insbesondere in der videobasierten Vitaldatenmessung. Prof. Handels entwickelt problemoptimierte, lernf{\"a}hige Bildverarbeitungsmethoden und integriert diese in hybride Bildverarbeitungssysteme zur Unterst{\"u}tzung der medizinischen Diagnostik und Therapie. Prof. Maier entwickelt Anwendungen in der medizinischen Bildverarbeitung zur Diagnoseunterst{\"u}tzung bis hin zur Schichtbildberechnung durch k{\"u}nstliche Intelligenz. Prof. Maier-Hein forscht im Bereich maschinelles Lernen und entwickelt Open-Source-L{\"o}sungen wie das Medical Imaging Interaction Toolkit (MITK), Kaapana oder das nnU-Net. Prof. em. Tolxdorff ist Experte f{\"u}r maschinelles Lernen, biomedizinisches Datenmanagement, Datenvisualisierung und -analyse sowie Medizinproduktentwicklung in klinischen Workflows.}, subject = {Bildverarbeitung}, 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 = {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} } @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} } @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} }