TEMSET-24K: Densely Annotated Dataset for Indexing Multipart Endoscopic Videos using Surgical Timeline Segmentation

TL;DR

This paper introduces TEMSET-24K, a large, densely annotated dataset of endoscopic videos with hierarchical labels, enabling automated surgical workflow analysis using advanced deep learning models.

Contribution

The creation of TEMSET-24K, a comprehensive, expert-annotated dataset for endoscopic videos, and benchmarking of transformer-based models for surgical phase segmentation.

Findings

High accuracy (up to 0.99) in phase segmentation.

Transformer models perform well on well-represented phases.

TEMSET-24K sets a new standard for surgical video datasets.

Abstract

Indexing endoscopic surgical videos is vital in surgical data science, forming the basis for systematic retrospective analysis and clinical performance evaluation. Despite its significance, current video analytics rely on manual indexing, a time-consuming process. Advances in computer vision, particularly deep learning, offer automation potential, yet progress is limited by the lack of publicly available, densely annotated surgical datasets. To address this, we present TEMSET-24K, an open-source dataset comprising 24,306 trans-anal endoscopic microsurgery (TEMS) video micro-clips. Each clip is meticulously annotated by clinical experts using a novel hierarchical labeling taxonomy encompassing phase, task, and action triplets, capturing intricate surgical workflows. To validate this dataset, we benchmarked deep learning models, including transformer-based architectures. Our in silico evaluation demonstrates high accuracy (up to 0.99) and F1 scores (up to 0.99) for key phases like Setup and Suturing. The STALNet model, tested with ConvNeXt, ViT, and SWIN V2 encoders, consistently segmented well-represented phases. TEMSET-24K provides a critical benchmark, propelling state-of-the-art solutions in surgical data science.