Development and Validation of a 3-Dimensional Convolutional Neural Network for Automatic Surgical Skill Assessment Based on Spatiotemporal Video Analysis

Key Points Question Is it possible to apply deep learning–based spatiotemporal video analysis using a 3-dimensional convolutional neural network to automate surgical skill assessment? Findings In this prognostic study, 1480 video clips from 74 laparoscopic colorectal surgical videos with reliable skill assessment scores were extracted and assigned 4:1 to training and test sets. The proposed model automatically classified video clips into 3 different score groups with 75% accuracy. Meaning A 3-dimensional convolutional neural network, which analyzes videos instead of static images, has the potential to be applied to automatic surgical skill assessment.

Paper

Full text

PDF

Development and Validation of a 3-Dimensional Convolutional Neural Network for Automatic Surgical Skill Assessment Based on Spatiotemporal Video Analysis

Semantic Scholar · Medicine · 2021

Abstract

Key Points Question Is it possible to apply deep learning–based spatiotemporal video analysis using a 3-dimensional convolutional neural network to automate surgical skill assessment? Findings In this prognostic study, 1480 video clips from 74 laparoscopic colorectal surgical videos with reliable skill assessment scores were extracted and assigned 4:1 to training and test sets. The proposed model automatically classified video clips into 3 different score groups with 75% accuracy. Meaning A 3-dimensional convolutional neural network, which analyzes videos instead of static images, has the potential to be applied to automatic surgical skill assessment.

References (35)

Scroll for more · 23 remaining

Similar papers

© 2026 NYSGPT2525 LLC