Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMask

TL;DR

This paper introduces an adapted AttentionMask system for medical instrument segmentation in minimally invasive surgeries, demonstrating robustness to image issues, generalization across surgery types, and effectiveness with small instruments.

Contribution

We adapt the AttentionMask system with dedicated post-processing for improved medical instrument segmentation in challenging surgical images.

Findings

Achieves state-of-the-art performance on ROBUST-MIS Challenge 2019

Robust to image degradations and small instruments

Generalizes well to unseen surgery types

Abstract

Precisely locating and segmenting medical instruments in images of minimally invasive surgeries, medical instrument segmentation, is an essential first step for several tasks in medical image processing. However, image degradations, small instruments, and the generalization between different surgery types make medical instrument segmentation challenging. To cope with these challenges, we adapt the object proposal generation system AttentionMask and propose a dedicated post-processing to select promising proposals. The results on the ROBUST-MIS Challenge 2019 show that our adapted AttentionMask system is a strong foundation for generating state-of-the-art performance. Our evaluation in an object proposal generation framework shows that our adapted AttentionMask system is robust to image degradations, generalizes well to unseen types of surgeries, and copes well with small instruments.