Fine-Grained Action Segmentation for Renorrhaphy in Robot-Assisted Partial Nephrectomy

TL;DR

This paper introduces a benchmark for fine-grained action segmentation during renorrhaphy in robot-assisted partial nephrectomy, comparing four temporal models on clinical videos with detailed evaluation metrics.

Contribution

It defines a new benchmark dataset (SIA-RAPN) with annotations and evaluates multiple models, highlighting DiffAct's superior performance in key metrics.

Findings

DiffAct achieves highest F1, frame accuracy, edit score, and frame mAP.

MS-TCN++ attains highest balanced accuracy.

Benchmark includes cross-domain evaluation on a separate dataset.

Abstract

Fine-grained action segmentation during renorrhaphy in robot-assisted partial nephrectomy requires frame-level recognition of visually similar suturing gestures with variable duration and substantial class imbalance. The SIA-RAPN benchmark defines this problem on 50 clinical videos acquired with the da Vinci Xi system and annotated with 12 frame-level labels. The benchmark compares four temporal models built on I3D features: MS-TCN++, AsFormer, TUT, and DiffAct. Evaluation uses balanced accuracy, edit score, segmental F1 at overlap thresholds of 10, 25, and 50, frame-wise accuracy, and frame-wise mean average precision. In addition to the primary evaluation across five released split configurations on SIA-RAPN, the benchmark reports cross-domain results on a separate single-port RAPN dataset. Across the strongest reported values over those five runs on the primary dataset, DiffAct achieves the highest F1, frame-wise accuracy, edit score, and frame mAP, while MS-TCN++ attains the highest balanced accuracy.