Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning

TL;DR

This paper presents a deep learning-based method for pixel-wise segmentation of robotic surgical instruments, achieving state-of-the-art results in binary and multi-class segmentation tasks for robot-assisted surgery videos.

Contribution

The authors introduce novel deep neural network architectures that significantly improve instrument segmentation accuracy in surgical videos, winning the MICCAI 2017 challenge.

Findings

Outperforms previous methods in binary segmentation accuracy

Achieves superior results in multi-class segmentation of surgical instruments

Provides publicly available source code for reproducibility

Abstract

Semantic segmentation of robotic instruments is an important problem for the robot-assisted surgery. One of the main challenges is to correctly detect an instrument's position for the tracking and pose estimation in the vicinity of surgical scenes. Accurate pixel-wise instrument segmentation is needed to address this challenge. In this paper we describe our winning solution for MICCAI 2017 Endoscopic Vision SubChallenge: Robotic Instrument Segmentation. Our approach demonstrates an improvement over the state-of-the-art results using several novel deep neural network architectures. It addressed the binary segmentation problem, where every pixel in an image is labeled as an instrument or background from the surgery video feed. In addition, we solve a multi-class segmentation problem, where we distinguish different instruments or different parts of an instrument from the background. In this setting, our approach outperforms other methods in every task subcategory for automatic instrument segmentation thereby providing state-of-the-art solution for this problem. The source code for our solution is made publicly available at https://github.com/ternaus/robot-surgery-segmentation