Weakly Supervised YOLO Network for Surgical Instrument Localization in Endoscopic Videos

TL;DR

This paper introduces WS-YOLO, a weakly supervised learning framework that leverages category labels to localize surgical instruments in endoscopic videos, reducing annotation effort while maintaining high accuracy.

Contribution

The novel WS-YOLO framework utilizes weak supervision and an unsupervised multi-round training strategy for effective surgical instrument localization.

Findings

Achieves high localization accuracy on Endoscopic Vision Challenge 2023 dataset.

Reduces annotation effort compared to fully supervised methods.

Demonstrates robustness in weakly supervised surgical instrument localization.

Abstract

In minimally invasive surgery, surgical instrument localization is a crucial task for endoscopic videos, which enables various applications for improving surgical outcomes. However, annotating the instrument localization in endoscopic videos is tedious and labor-intensive. In contrast, obtaining the category information is easy and efficient in real-world applications. To fully utilize the category information and address the localization problem, we propose a weakly supervised localization framework named WS-YOLO for surgical instruments. By leveraging the instrument category information as the weak supervision, our WS-YOLO framework adopts an unsupervised multi-round training strategy for the localization capability training. We validate our WS-YOLO framework on the Endoscopic Vision Challenge 2023 dataset, which achieves remarkable performance in the weakly supervised surgical instrument localization. The source code is available at https://github.com/Breezewrf/WS-YOLO.