@Article{Ross2021, author = {Tobias Ross and Annika Reinke and Peter M. Full and Martin Wagner and Hannes Kenngott and Martin Apitz and Hellena Hempe and Diana Mindroc-Filimon and Patrick Scholz and Thuy Nuong Tran and Pierangela Bruno and Pablo Arbeláez and Gui-Bin Bian and Sebastian Bodenstedt and Jon Lindström Bolmgren and Laura Bravo-Sánchez and Hua-Bin Chen and Cristina González and Dong Guo and Paal Halvorsen and Pheng-Ann Heng and Enes Hosgor and Zeng-Guang Hou and Fabian Isensee and Debesh Jha and Tingting Jiang and Yueming Jin and Kadir Kirtac and Sabrina Kletz and Stefan Leger and Zhixuan Li and Klaus H. Maier-Hein and Zhen-Liang Ni and Michael A. Riegler and Klaus Schoeffmann and Ruohua Shi and Stefanie Speidel and Michael Stenzel and Isabell Twick and Gutai Wang and Jiacheng Wang and Liansheng Wang and Lu Wang and Yujie Zhang and Yan-Jie Zhou and Lei Zhu and Manuel Wiesenfarth and Annette Kopp-Schneider and Beat P. Müller-Stich and Lena Maier-Hein}, journal = {Medical Image Analysis}, title = {{Comparative validation of multi-instance instrument segmentation in endoscopy: Results of the ROBUST-MIS 2019 challenge}}, year = {2021}, issn = {1361-8415}, month = {may}, number = {66}, pages = {1--62}, volume = {70}, abstract = {Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions. In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).}, doi = {10.1016/j.media.2020.101920}, keywords = {Multi-instance instrument, minimally invasive surgery, robustness and generalization, surgical data science}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/pii/S136184152030284X} }