In 2015 we began a sub-challenge at the EndoVis workshop at MICCAI in Munich using endoscope images of ex-vivo tissue with automatically generated annotations from robot forward kinematics and instrument CAD models. However, the limited background variation and simple motion rendered the dataset uninformative in learning about which techniques would be suitable for segmentation in real surgery. In 2017, at the same workshop in Quebec we introduced the robotic instrument segmentation dataset with 10 teams participating in the challenge to perform binary, articulating parts and type segmentation of da Vinci instruments. This challenge included realistic instrument motion and more complex porcine tissue as background and was widely addressed with modifications on U-Nets and other popular CNN architectures. In 2018 we added to the complexity by introducing a set of anatomical objects and medical devices to the segmented classes. To avoid over-complicating the challenge, we continued with porcine data which is dramatically simpler than human tissue due to the lack of fatty tissue occluding many organs.
@article{arxiv.2001.11190,
title = {2018 Robotic Scene Segmentation Challenge},
author = {Max Allan and Satoshi Kondo and Sebastian Bodenstedt and Stefan Leger and Rahim Kadkhodamohammadi and Imanol Luengo and Felix Fuentes and Evangello Flouty and Ahmed Mohammed and Marius Pedersen and Avinash Kori and Varghese Alex and Ganapathy Krishnamurthi and David Rauber and Robert Mendel and Christoph Palm and Sophia Bano and Guinther Saibro and Chi-Sheng Shih and Hsun-An Chiang and Juntang Zhuang and Junlin Yang and Vladimir Iglovikov and Anton Dobrenkii and Madhu Reddiboina and Anubhav Reddy and Xingtong Liu and Cong Gao and Mathias Unberath and Myeonghyeon Kim and Chanho Kim and Chaewon Kim and Hyejin Kim and Gyeongmin Lee and Ihsan Ullah and Miguel Luna and Sang Hyun Park and Mahdi Azizian and Danail Stoyanov and Lena Maier-Hein and Stefanie Speidel},
journal= {arXiv preprint arXiv:2001.11190},
year = {2020}
}