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

Search research articles

Related Experiment Video

Updated: Jan 11, 2026

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

Toward robust surgical phase recognition via deep ensemble learning.

Flakë Bajraktari¹, Lina Hauser², Peter P Pott²

¹Institute of Medical Device Technology, University of Stuttgart, Pfaffenwaldring 9, 70569, Stuttgart, Germany. flake.bajraktari@imt.uni-stuttgart.de.

International Journal of Computer Assisted Radiology and Surgery

|November 8, 2025

Summary

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

Soft Everting Robots for Medical Applications: A Review.

IEEE transactions on bio-medical engineering·2026

Same author

Few-shot learning for surgical phase recognition: Performance and generalization in cholecystectomy.

Computer methods and programs in biomedicine·2026

Same author

Novel low-cost approach to build large-scale flexible sensors for spatially distributed ground reaction force measurements.

Biomedizinische Technik. Biomedical engineering·2025

Same author

Combined gamma radiation source detector and ultrasound imaging system: Proof of concept and first results.

Computers in biology and medicine·2025

Same author

Investigation and Validation of New Heart Rate Measurement Sites for Wearable Technologies.

Sensors (Basel, Switzerland)·2025

Same author

Design and evaluation of new user control devices for improved ergonomics in flexible robotic endoscopy.

Frontiers in robotics and AI·2025

Ensemble learning significantly improves surgical phase recognition by combining diverse deep learning models. This approach enhances accuracy and reliability, offering clinically meaningful benefits for AI-guided surgery.

Area of Science:

Computer Vision
Artificial Intelligence
Medical Informatics

Background:

Automatic surgical workflow recognition is crucial for context-aware operating room systems.
High accuracy in surgical phase recognition is challenging due to procedure complexity and limitations of individual deep learning models.

Purpose of the Study:

To investigate ensemble learning for improving surgical phase recognition.
To combine diverse deep learning architectures to mitigate individual model weaknesses.
To enhance performance using the Cholec80 dataset.

Main Methods:

Integrated various advanced deep learning architectures into ensembles.
Selected and tuned 15 unique models to ensure diversity.
Explored different ensemble strategies, including majority voting and StackingNet.

Keywords:

Deep ensemble learning Model diversity Phase recognition Surgical assistance

Related Experiment Videos

Last Updated: Jan 11, 2026

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

Main Results:

Ensemble learning significantly boosted performance compared to individual models.
Majority voting and StackingNet showed superior results.
Optimal ensembles with high model diversity improved accuracy by 1.48%, F1-score by 3.68%, and Jaccard Index by 5.43%.

Conclusions:

Ensemble learning substantially enhances surgical phase recognition by leveraging diverse deep learning models.
Ensemble size, diversity, and meta-model selection are key performance factors.
Improvements offer clinically meaningful benefits, increasing reliability and surgeon trust in AI.