Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Development of a lipid bioactive-loaded bigel food system for elderly individuals with dysphagia.

Food chemistry·2026

Same author

Aralianudasides C-E: three undescribed triterpenoid saponins from the buds of <i>Aralia elata</i> and its airway inflammation inhibitory activity.

Natural product research·2025

Same author

Functions of <i>Pugionium cornutum</i> (L.) Gaertn Extracts: Investigating the Mechanism of Gastroparesis Amelioration from the Perspective of the Gut Microbiota and Its Metabolites.

Foods (Basel, Switzerland)·2025

Same author

Synergistic Effects of Walnut Oil and Nervonic Acid on Antioxidant Activity and Cognitive Impairment.

Journal of food science·2025

Same author

Self-activating and chromosomally colocalized LsERF166 positively regulates costunolide biosynthesis in lettuce.

The New phytologist·2025

Same author

Multi-omics study reveals a light-dependent regulatory network of flavonoid biosynthesis in lettuce (Lactuca sativa L.).

Science China. Life sciences·2025

Search research articles

Related Experiment Video

Updated: Aug 19, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Global-local multi-stage temporal convolutional network for cataract surgery phase recognition.

Lixin Fang^1,2, Lei Mou², Yuanyuan Gu^3,4

¹College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou, 310014, China.

Biomedical Engineering Online

|November 30, 2022

Summary

This summary is machine-generated.

A novel global-local multi-stage temporal convolutional network (GL-MSTCN) enhances surgical video phase recognition by analyzing subtle differences and temporal variations in cataract surgeries, achieving high accuracy.

Keywords:

Cataract surgery videos Deep learning Surgical phase recognition Temporal convolutional networks

More Related Videos

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery

Published on: December 1, 2023

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

Related Experiment Videos

Last Updated: Aug 19, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery

Author Spotlight: Unraveling the Molecular Mechanisms in PCO and Fibrosis Following Cataract Surgery

Published on: December 1, 2023

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

Area of Science:

Computer-assisted surgery
Medical image analysis
Surgical phase recognition

Background:

Surgical video phase recognition is crucial for computer-assisted surgery, aiding procedure standardization and post-surgical analysis.
High similarity between phases and temporal variations in cataract videos present significant challenges for accurate recognition.

Purpose of the Study:

To develop a novel method for improved surgical phase recognition in cataract videos.
To address the challenges of high phase similarity and temporal variations in surgical videos.

Main Methods:

Introduced a global-local multi-stage temporal convolutional network (GL-MSTCN).
Employed a triple-stream network (pupil, instrument, video frame) for fine-grained feature extraction.
Utilized a multi-stage temporal convolutional network with dilated convolutions to capture long-range temporal dependencies.

Main Results:

Achieved 95.8% accuracy on the CSVideo dataset (32 videos) and 96.5% accuracy on the Cataract101 dataset (101 videos).
Outperformed existing state-of-the-art approaches in surgical phase recognition.

Conclusions:

Global and local feature integration effectively enhances the model's ability to discern fine-grained details.
The proposed GL-MSTCN mitigates temporal and spatial variations, significantly improving surgical phase recognition performance.