Towards Robotic Knee Arthroscopy: Multi-Scale Network for Tissue-Tool Segmentation

TL;DR

This paper introduces a multi-scale, shape-aware segmentation model designed to improve tissue and tool identification in arthroscopic videos, addressing challenges like limited features and high intra-class variation.

Contribution

The study proposes a novel densely connected multi-scale network that captures tissue features and integrates shape information for enhanced segmentation accuracy.

Findings

Achieved 5.09% accuracy improvement on a public polyp dataset.

Effectively captures multi-scale tissue features in challenging arthroscopic videos.

Demonstrated robustness across three distinct datasets.

Abstract

Tissue awareness has a great demand to improve surgical accuracy in minimally invasive procedures. In arthroscopy, it is one of the challenging tasks due to surgical sites exhibit limited features and textures. Moreover, arthroscopic surgical video shows high intra-class variations. Arthroscopic videos are recorded with endoscope known as arthroscope which records tissue structures at proximity, therefore, frames contain minimal joint structure. As consequences, fully conventional network-based segmentation model suffers from long- and short- term dependency problems. In this study, we present a densely connected shape aware multi-scale segmentation model which captures multi-scale features and integrates shape features to achieve tissue-tool segmentations. The model has been evaluated with three distinct datasets. Moreover, with the publicly available polyp dataset our proposed model achieved 5.09 % accuracy improvement.