2018 Robotic Scene Segmentation Challenge

TLDR

In 2015, a sub‑challenge at the EndoVis workshop at MICCAI in Munich used endoscope images of ex‑vivo tissue with automatically generated annotations from robot forward kinematics and instrument CAD models. The 2017 challenge introduced a robotic instrument segmentation dataset with 10 teams performing binary, articulating‑parts, and type segmentation of da Vinci instruments, and the 2018 edition expanded the classes to include anatomical objects and medical devices while retaining porcine data for simplicity. The initial dataset’s limited background variation and simple motion rendered it uninformative for learning suitable segmentation techniques, whereas the 2017–2018 challenges, featuring realistic instrument motion and complex porcine tissue, were widely tackled by modifying U‑Nets and other popular CNN architectures.

Abstract

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.