Identifying Surgical Instruments in Pedagogical Cataract Surgery Videos through an Optimized Aggregation Network

TL;DR

This paper introduces a novel deep learning model based on YOLOV9 architecture, enhanced with PGI and Go-ELAN, for real-time identification of surgical instruments in cataract surgery videos, achieving high accuracy on a custom dataset.

Contribution

The paper proposes a new optimized aggregation network and PGI mechanism integrated into YOLOV9 for improved instrument detection in surgical videos.

Findings

Achieved a mAP of 73.74 at IoU 0.5 on the dataset.

Outperformed YOLO v5, v7, v8, vanilla YOLOV9, Laptool, and DETR.

Demonstrated real-time detection capability with high accuracy.

Abstract

Instructional cataract surgery videos are crucial for ophthalmologists and trainees to observe surgical details repeatedly. This paper presents a deep learning model for real-time identification of surgical instruments in these videos, using a custom dataset scraped from open-access sources. Inspired by the architecture of YOLOV9, the model employs a Programmable Gradient Information (PGI) mechanism and a novel Generally-Optimized Efficient Layer Aggregation Network (Go-ELAN) to address the information bottleneck problem, enhancing Minimum Average Precision (mAP) at higher Non-Maximum Suppression Intersection over Union (NMS IoU) scores. The Go-ELAN YOLOV9 model, evaluated against YOLO v5, v7, v8, v9 vanilla, Laptool and DETR, achieves a superior mAP of 73.74 at IoU 0.5 on a dataset of 615 images with 10 instrument classes, demonstrating the effectiveness of the proposed model.