Image-based tracking of medical instruments is an integral part of surgical data science applications. Previous research has addressed the tasks of detecting, segmenting and tracking medical instruments based on laparoscopic video data. However, the proposed methods still tend to fail when applied to challenging images and do not generalize well to data they have not been trained on. This paper introduces the Heidelberg Colorectal (HeiCo) data set - the first publicly available data set enabling comprehensive benchmarking of medical instrument detection and segmentation algorithms with a specific emphasis on method robustness and generalization capabilities. Our data set comprises 30 laparoscopic videos and corresponding sensor data from medical devices in the operating room for three different types of laparoscopic surgery. Annotations include surgical phase labels for all video frames as well as information on instrument presence and corresponding instance-wise segmentation masks for surgical instruments (if any) in more than 10,000 individual frames. The data has successfully been used to organize international competitions within the Endoscopic Vision Challenges 2017 and 2019.
@article{arxiv.2005.03501,
title = {Heidelberg Colorectal Data Set for Surgical Data Science in the Sensor Operating Room},
author = {Lena Maier-Hein and Martin Wagner and Tobias Ross and Annika Reinke and Sebastian Bodenstedt and Peter M. Full and Hellena Hempe and Diana Mindroc-Filimon and Patrick Scholz and Thuy Nuong Tran and Pierangela Bruno and Anna Kisilenko and Benjamin Müller and Tornike Davitashvili and Manuela Capek and Minu Tizabi and Matthias Eisenmann and Tim J. Adler and Janek Gröhl and Melanie Schellenberg and Silvia Seidlitz and T. Y. Emmy Lai and Bünyamin Pekdemir and Veith Roethlingshoefer and Fabian Both and Sebastian Bittel and Marc Mengler and Lars Mündermann and Martin Apitz and Annette Kopp-Schneider and Stefanie Speidel and Hannes G. Kenngott and Beat P. Müller-Stich},
journal= {arXiv preprint arXiv:2005.03501},
year = {2021}
}