Cataract-1K: Cataract Surgery Dataset for Scene Segmentation, Phase Recognition, and Irregularity Detection

TL;DR

Cataract-1K is a large-scale cataract surgery video dataset designed to advance scene segmentation, phase recognition, and irregularity detection using deep learning, supporting improved surgical workflow analysis and post-operative assessment.

Contribution

The paper introduces the largest cataract surgery video dataset with comprehensive annotations, enabling new research in surgical scene understanding and domain adaptation.

Findings

Benchmarking of neural networks for phase recognition shows high accuracy.

Dataset quality validated through segmentation and recognition performance.

Initial domain adaptation experiments highlight challenges in instrument segmentation.

Abstract

In recent years, the landscape of computer-assisted interventions and post-operative surgical video analysis has been dramatically reshaped by deep-learning techniques, resulting in significant advancements in surgeons' skills, operation room management, and overall surgical outcomes. However, the progression of deep-learning-powered surgical technologies is profoundly reliant on large-scale datasets and annotations. Particularly, surgical scene understanding and phase recognition stand as pivotal pillars within the realm of computer-assisted surgery and post-operative assessment of cataract surgery videos. In this context, we present the largest cataract surgery video dataset that addresses diverse requisites for constructing computerized surgical workflow analysis and detecting post-operative irregularities in cataract surgery. We validate the quality of annotations by benchmarking the performance of several state-of-the-art neural network architectures for phase recognition and surgical scene segmentation. Besides, we initiate the research on domain adaptation for instrument segmentation in cataract surgery by evaluating cross-domain instrument segmentation performance in cataract surgery videos. The dataset and annotations will be publicly available upon acceptance of the paper.