Assessing YOLACT++ for real time and robust instance segmentation of medical instruments in endoscopic procedures

TL;DR

This paper enhances the YOLACT++ model with attention mechanisms to enable real-time, accurate instance segmentation of medical instruments in endoscopic procedures, addressing the need for clinical applicability.

Contribution

It introduces attention mechanisms to YOLACT++, achieving real-time segmentation with improved accuracy on medical instrument datasets, surpassing previous two-stage detector models.

Findings

Achieves 37 fps in real-time segmentation.

Matches robustness scores of top challenge winners.

Improves accuracy over baseline models.

Abstract

Image-based tracking of laparoscopic instruments plays a fundamental role in computer and robotic-assisted surgeries by aiding surgeons and increasing patient safety. Computer vision contests, such as the Robust Medical Instrument Segmentation (ROBUST-MIS) Challenge, seek to encourage the development of robust models for such purposes, providing large, diverse, and annotated datasets. To date, most of the existing models for instance segmentation of medical instruments were based on two-stage detectors, which provide robust results but are nowhere near to the real-time (5 frames-per-second (fps)at most). However, in order for the method to be clinically applicable, real-time capability is utmost required along with high accuracy. In this paper, we propose the addition of attention mechanisms to the YOLACT architecture that allows real-time instance segmentation of instrument with improved accuracy on the ROBUST-MIS dataset. Our proposed approach achieves competitive performance compared to the winner ofthe 2019 ROBUST-MIS challenge in terms of robustness scores,obtaining 0.313 MI_DSC and 0.338 MI_NSD, while achieving real-time performance (37 fps)