Polyp and Surgical Instrument Segmentation with Double Encoder-Decoder Networks

TL;DR

This paper presents an advanced double encoder-decoder neural network for simultaneous segmentation of polyps and surgical instruments in endoscopic images, demonstrating improved accuracy through architectural and optimization enhancements.

Contribution

It introduces a novel double encoder-decoder architecture with enhancements like a stronger encoder, better optimization, and tempered model ensembling for improved segmentation performance.

Findings

Segmentations closely match expert annotations

Enhanced network architecture improves accuracy

Model ensembling boosts robustness

Abstract

This paper describes a solution for the MedAI competition, in which participants were required to segment both polyps and surgical instruments from endoscopic images. Our approach relies on a double encoder-decoder neural network which we have previously applied for polyp segmentation, but with a series of enhancements: a more powerful encoder architecture, an improved optimization procedure, and the post-processing of segmentations based on tempered model ensembling. Experimental results show that our method produces segmentations that show a good agreement with manual delineations provided by medical experts.