_version_ 1866918316711346176
author Rueckert, Tobias
Rauber, David
Maerkl, Raphaela
Klausmann, Leonard
Yildiran, Suemeyye R.
Gutbrod, Max
Nunes, Danilo Weber
Moreno, Alvaro Fernandez
Luengo, Imanol
Stoyanov, Danail
Toussaint, Nicolas
Cho, Enki
Kim, Hyeon Bae
Choo, Oh Sung
Kim, Ka Young
Kim, Seong Tae
Arantes, Gonçalo
Song, Kehan
Zhu, Jianjun
Xiong, Junchen
Lin, Tingyi
Kikuchi, Shunsuke
Matsuzaki, Hiroki
Kouno, Atsushi
Manesco, João Renato Ribeiro
Papa, João Paulo
Choi, Tae-Min
Jeong, Tae Kyeong
Park, Juyoun
Alabi, Oluwatosin
Wei, Meng
Vercauteren, Tom
Wu, Runzhi
Xu, Mengya
Wang, An
Bai, Long
Ren, Hongliang
Yamlahi, Amine
Hennighausen, Jakob
Maier-Hein, Lena
Kondo, Satoshi
Kasai, Satoshi
Hirasawa, Kousuke
Yang, Shu
Wang, Yihui
Chen, Hao
Rodríguez, Santiago
Aparicio, Nicolás
Manrique, Leonardo
Lyons, Juan Camilo
Hosie, Olivia
Ayobi, Nicolás
Arbeláez, Pablo
Li, Yiping
Khalil, Yasmina Al
Nasirihaghighi, Sahar
Speidel, Stefanie
Rueckert, Daniel
Feussner, Hubertus
Wilhelm, Dirk
Palm, Christoph
author_facet Rueckert, Tobias
Rauber, David
Maerkl, Raphaela
Klausmann, Leonard
Yildiran, Suemeyye R.
Gutbrod, Max
Nunes, Danilo Weber
Moreno, Alvaro Fernandez
Luengo, Imanol
Stoyanov, Danail
Toussaint, Nicolas
Cho, Enki
Kim, Hyeon Bae
Choo, Oh Sung
Kim, Ka Young
Kim, Seong Tae
Arantes, Gonçalo
Song, Kehan
Zhu, Jianjun
Xiong, Junchen
Lin, Tingyi
Kikuchi, Shunsuke
Matsuzaki, Hiroki
Kouno, Atsushi
Manesco, João Renato Ribeiro
Papa, João Paulo
Choi, Tae-Min
Jeong, Tae Kyeong
Park, Juyoun
Alabi, Oluwatosin
Wei, Meng
Vercauteren, Tom
Wu, Runzhi
Xu, Mengya
Wang, An
Bai, Long
Ren, Hongliang
Yamlahi, Amine
Hennighausen, Jakob
Maier-Hein, Lena
Kondo, Satoshi
Kasai, Satoshi
Hirasawa, Kousuke
Yang, Shu
Wang, Yihui
Chen, Hao
Rodríguez, Santiago
Aparicio, Nicolás
Manrique, Leonardo
Lyons, Juan Camilo
Hosie, Olivia
Ayobi, Nicolás
Arbeláez, Pablo
Li, Yiping
Khalil, Yasmina Al
Nasirihaghighi, Sahar
Speidel, Stefanie
Rueckert, Daniel
Feussner, Hubertus
Wilhelm, Dirk
Palm, Christoph
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16559
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge
Rueckert, Tobias
Rauber, David
Maerkl, Raphaela
Klausmann, Leonard
Yildiran, Suemeyye R.
Gutbrod, Max
Nunes, Danilo Weber
Moreno, Alvaro Fernandez
Luengo, Imanol
Stoyanov, Danail
Toussaint, Nicolas
Cho, Enki
Kim, Hyeon Bae
Choo, Oh Sung
Kim, Ka Young
Kim, Seong Tae
Arantes, Gonçalo
Song, Kehan
Zhu, Jianjun
Xiong, Junchen
Lin, Tingyi
Kikuchi, Shunsuke
Matsuzaki, Hiroki
Kouno, Atsushi
Manesco, João Renato Ribeiro
Papa, João Paulo
Choi, Tae-Min
Jeong, Tae Kyeong
Park, Juyoun
Alabi, Oluwatosin
Wei, Meng
Vercauteren, Tom
Wu, Runzhi
Xu, Mengya
Wang, An
Bai, Long
Ren, Hongliang
Yamlahi, Amine
Hennighausen, Jakob
Maier-Hein, Lena
Kondo, Satoshi
Kasai, Satoshi
Hirasawa, Kousuke
Yang, Shu
Wang, Yihui
Chen, Hao
Rodríguez, Santiago
Aparicio, Nicolás
Manrique, Leonardo
Lyons, Juan Camilo
Hosie, Olivia
Ayobi, Nicolás
Arbeláez, Pablo
Li, Yiping
Khalil, Yasmina Al
Nasirihaghighi, Sahar
Speidel, Stefanie
Rueckert, Daniel
Feussner, Hubertus
Wilhelm, Dirk
Palm, Christoph
Computer Vision and Pattern Recognition
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.
title Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.16559