Phase-Informed Tool Segmentation for Manual Small-Incision Cataract Surgery
This work addresses a gap in automated surgical video analysis for a low-cost, high-volume cataract surgery method critical in developing countries, though it is incremental in applying existing techniques to a new domain.
The paper tackles the lack of datasets and methods for analyzing Manual Small-Incision Cataract Surgery (MSICS) videos by introducing the Sankara-MSICS dataset and ToolSeg framework, which improves tool segmentation with a 23.77% to 38.10% increase in mean Dice scores and generalizes to other surgical settings.
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.