Phase-Informed Tool Segmentation for Manual Small-Incision Cataract Surgery

TL;DR

This paper introduces Sankara-MSICS, a new dataset for manual small-incision cataract surgery, and proposes ToolSeg, a phase-informed tool segmentation framework that significantly improves segmentation accuracy and generalizes across datasets.

Contribution

The paper presents the first comprehensive MSICS dataset and a novel phase-informed segmentation method that leverages surgical phases and semi-supervised learning for improved tool segmentation.

Findings

ToolSeg improves segmentation Dice scores by 23.77% to 38.10%.

The dataset contains 53 videos with 18 phases and pixel-level tool annotations.

ToolSeg generalizes well to other surgical datasets like CaDIS.

Abstract

Cataract surgery is the most common surgical procedure globally, with a disproportionately higher burden in developing countries. While automated surgical video analysis has been explored in general surgery, its application to ophthalmic procedures remains limited. Existing works primarily focus on Phaco cataract surgery, an expensive technique not accessible in regions where cataract treatment is most needed. In contrast, Manual Small-Incision Cataract Surgery (MSICS) is the preferred low-cost, faster alternative in high-volume settings and for challenging cases. However, no dataset exists for MSICS. To address this gap, we introduce Sankara-MSICS, the first comprehensive dataset containing 53 surgical videos annotated for 18 surgical phases and 3,527 frames with 13 surgical tools at the pixel level. We benchmark this dataset on state-of-the-art models and present ToolSeg, a novel framework that enhances tool segmentation by introducing a phase-conditional decoder and a simple yet effective semi-supervised setup leveraging pseudo-labels from foundation models. Our approach significantly improves segmentation performance, achieving a $23.77\%$ to $38.10\%$ increase in mean Dice scores, with a notable boost for tools that are less prevalent and small. Furthermore, we demonstrate that ToolSeg generalizes to other surgical settings, showcasing its effectiveness on the CaDIS dataset.