Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Reconstruction of Lower Lip-Neck Contracture Using Skin Graft and Circumflex Scapular Artery-Augmented Occipito-cervico-dorsal Flap.

Plastic and reconstructive surgery. Global open·2026
Same author

Management of Acute Postoperative Infections Following Microtia Reconstruction With Costal Cartilage Grafts.

Plastic and reconstructive surgery. Global open·2026
Same author

Japanese Consensus Document on NexoBrid<sup>®</sup>, a Burn Eschar Removal Agent.

European burn journal·2026
Same author

A New Surgical Field Expansion Technique in Robot-Assisted Gastrectomy: "Bursal Space Lifting Approach".

Asian journal of endoscopic surgery·2026
Same author

Volumetric Assessment of a Soft-Tissue Tumor Using Smartphone Light Detection and Ranging and Neural Radiance Fields: A Single Case.

Plastic and reconstructive surgery. Global open·2026
Same author

Keloid may be a modern inflammatory disease: A historical and clinicopathological perspective.

Journal of plastic, reconstructive & aesthetic surgery : JPRAS·2026

Related Experiment Video

Updated: Sep 15, 2025

A Training and Testing System for Performing Vascular Reconstruction In Vitro
09:52

A Training and Testing System for Performing Vascular Reconstruction In Vitro

Published on: October 26, 2019

8.1K

Applying machine learning to safe vascular anastomosis.

Hiroki Umezawa1, Akatsuki Kondo1, Marie Taga1

  • 1Department of Plastic, Reconstructive and Aesthetic Surgery, Nippon Medical School Hospital, 1-1-5 Sendagi, Bunkyo-ku, Tokyo, Japan.

JPRAS Open
|July 18, 2025
PubMed
Summary

Machine learning algorithms trained on exoscope images show potential for detecting thrombus-predicting signs in microsurgery. This technology can enhance surgical safety and aid in training surgeons to identify at-risk vessels during anastomosis.

Keywords:
Artificial intelligenceMachine-learningMicrosurgeryReal-time processingVascular anastomosis

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Development of a Murine Model for Femoral Artery Anastomotic Stenosis
05:42

Development of a Murine Model for Femoral Artery Anastomotic Stenosis

Published on: April 18, 2025

319

Related Experiment Videos

Last Updated: Sep 15, 2025

A Training and Testing System for Performing Vascular Reconstruction In Vitro
09:52

A Training and Testing System for Performing Vascular Reconstruction In Vitro

Published on: October 26, 2019

8.1K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Development of a Murine Model for Femoral Artery Anastomotic Stenosis
05:42

Development of a Murine Model for Femoral Artery Anastomotic Stenosis

Published on: April 18, 2025

319

Area of Science:

  • Medical technology
  • Surgical innovation
  • Artificial intelligence in medicine

Background:

  • Machine learning (ML) is increasingly integrated into healthcare, assisting in diagnostics, patient analysis, and surgical procedures.
  • Advances in exoscopes and monitors are driving a transition from traditional microscope-based microsurgery to heads-up microsurgery.
  • High-definition exoscope imagery offers a valuable resource for training ML algorithms.

Purpose of the Study:

  • To investigate the feasibility of using exoscope images to train a machine learning algorithm for detecting signs predictive of thrombus formation.
  • To develop a tool that can aid microsurgery by identifying vessels at risk of unsafe microvascular anastomosis.
  • To enhance surgical training by providing objective feedback on vessel assessment.

Main Methods:

  • Annotated 9150 ORBEYE™ exoscope images of arterial anastomosis, identifying arterial clots, intimal-wall damage, debris, and stumps.
  • Utilized annotated images to train a You Only Look Once (YOLO) model for detecting thrombus-predicting signs.
  • Executed the YOLO model training within the Google Colaboratory environment.

Main Results:

  • The trained YOLO algorithm successfully detected the four specified objects in real-time after 100 epochs.
  • The algorithm exhibited high rates of both false-positive and false-negative detections.
  • Despite limitations, the results demonstrate the potential of ML on exoscope data.

Conclusions:

  • Machine learning applied to exoscope images holds promise for developing algorithms that improve the safety of microsurgical anastomosis.
  • The accessibility of Python, Google Colaboratory, and models like YOLO empowers even novice programmers to create effective ML algorithms.
  • Continued advancements in computing hardware and processing methods are expected to further enhance ML applications in surgery and medical education.