학술논문
SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge
Document Type
Working Paper
Author
Psychogyios, Dimitrios; Colleoni, Emanuele; Van Amsterdam, Beatrice; Li, Chih-Yang; Huang, Shu-Yu; Li, Yuchong; Jia, Fucang; Zou, Baosheng; Wang, Guotai; Liu, Yang; Boels, Maxence; Huo, Jiayu; Sparks, Rachel; Dasgupta, Prokar; Granados, Alejandro; Ourselin, Sebastien; Xu, Mengya; Wang, An; Wu, Yanan; Bai, Long; Ren, Hongliang; Yamada, Atsushi; Harai, Yuriko; Ishikawa, Yuto; Hayashi, Kazuyuki; Simoens, Jente; DeBacker, Pieter; Cisternino, Francesco; Furnari, Gabriele; Mottrie, Alex; Ferraguti, Federica; Kondo, Satoshi; Kasai, Satoshi; Hirasawa, Kousuke; Kim, Soohee; Lee, Seung Hyun; Lee, Kyu Eun; Kong, Hyoun-Joong; Fu, Kui; Li, Chao; An, Shan; Krell, Stefanie; Bodenstedt, Sebastian; Ayobi, Nicolas; Perez, Alejandra; Rodriguez, Santiago; Puentes, Juanita; Arbelaez, Pablo; Mohareri, Omid; Stoyanov, Danail
Source
Subject
Language
Abstract
Surgical tool segmentation and action recognition are fundamental building blocks in many computer-assisted intervention applications, ranging from surgical skills assessment to decision support systems. Nowadays, learning-based action recognition and segmentation approaches outperform classical methods, relying, however, on large, annotated datasets. Furthermore, action recognition and tool segmentation algorithms are often trained and make predictions in isolation from each other, without exploiting potential cross-task relationships. With the EndoVis 2022 SAR-RARP50 challenge, we release the first multimodal, publicly available, in-vivo, dataset for surgical action recognition and semantic instrumentation segmentation, containing 50 suturing video segments of Robotic Assisted Radical Prostatectomy (RARP). The aim of the challenge is twofold. First, to enable researchers to leverage the scale of the provided dataset and develop robust and highly accurate single-task action recognition and tool segmentation approaches in the surgical domain. Second, to further explore the potential of multitask-based learning approaches and determine their comparative advantage against their single-task counterparts. A total of 12 teams participated in the challenge, contributing 7 action recognition methods, 9 instrument segmentation techniques, and 4 multitask approaches that integrated both action recognition and instrument segmentation. The complete SAR-RARP50 dataset is available at: https://rdr.ucl.ac.uk/projects/SARRARP50_Segmentation_of_surgical_instrumentation_and_Action_Recognition_on_Robot-Assisted_Radical_Prostatectomy_Challenge/191091