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: Jun 26, 2025

Application of Hemostatic Devices in Laparoscopic Hepatectomy

Application of Hemostatic Devices in Laparoscopic Hepatectomy

Published on: April 19, 2022

Real-time detection of active bleeding in laparoscopic colectomy using artificial intelligence.

Kenta Horita¹, Koya Hida², Yoshiro Itatani¹

¹Department of Surgery, Kyoto University Graduate School of Medicine, 54 Shogoin-Kawahara-Cho, Sakyo-Ku, Kyoto, 606-8507, Japan.

Surgical Endoscopy

|May 17, 2024

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

Colorectal cancer co-opts an epidermal wound healing program during metastasis to generate disseminated tumor cells.

Nature communications·2026

Same author

Standardizing Upper Abdominal Fascial Terminology: A Transdisciplinary Expert Consensus From the Japanese Society for Endoscopic Surgery.

Asian journal of endoscopic surgery·2026

Same author

Robotic Hepatectomy Using the Hugo RAS System: Initial Experience and Technical Considerations.

Asian journal of endoscopic surgery·2026

Same author

Comparison of Minimally Invasive Colectomy Between Intra- Versus Extra-Corporeal Anastomosis Technique (COMMIT Study): Mid-Term Analysis.

Annals of gastroenterological surgery·2026

Same author

Impact of Abdominoperineal Resection on Postoperative Male Sexual Function After Minimally Invasive Rectal Cancer Surgery: A Subgroup Analysis From the LANDMARC Study.

Annals of gastroenterological surgery·2026

Same author

Inter-institutional heterogeneity in high-volume esophageal cancer centers: an ancillary study of JCOG1109 (JCOG2308A).

Esophagus : official journal of the Japan Esophageal Society·2026

This study developed an artificial intelligence (AI) model for real-time detection of active intraoperative bleeding. The AI model achieved high accuracy and processing speed, offering potential for enhanced surgical safety.

Area of Science:

Medical technology
Artificial intelligence in surgery
Surgical safety

Background:

Intraoperative adverse events (iAEs) frequently stem from surgical errors, with bleeding being a primary concern.
Timely recognition of active bleeding is crucial for maintaining surgical safety.
Artificial intelligence (AI) presents a significant opportunity for real-time bleeding detection and surgical support.

Purpose of the Study:

To develop and evaluate a real-time AI model capable of detecting active intraoperative bleeding.
To assess the model's performance in terms of accuracy and processing speed.
To gauge surgeon perception regarding the AI model's sensitivity and overdetection rates.

Main Methods:

Utilized 27 surgical videos from a Japanese multi-institutional database, divided into training, validation, and testing sets.

Keywords:

Artificial intelligence Bleeding Object detection Surgery

More Related Videos

The Role of Indocyanine Green Fluorescence in Complex Laparoscopic Cholecystectomy Navigation

The Role of Indocyanine Green Fluorescence in Complex Laparoscopic Cholecystectomy Navigation

Published on: January 31, 2025

Related Experiment Videos

Last Updated: Jun 26, 2025

Application of Hemostatic Devices in Laparoscopic Hepatectomy

Application of Hemostatic Devices in Laparoscopic Hepatectomy

Published on: April 19, 2022

The Role of Indocyanine Green Fluorescence in Complex Laparoscopic Cholecystectomy Navigation

The Role of Indocyanine Green Fluorescence in Complex Laparoscopic Cholecystectomy Navigation

Published on: January 31, 2025

Employed a pre-trained YOLOv7_6w model, trained to identify both active bleeding and blood pooling.

Quantified performance using Average Precision at an Intersection over Union threshold of 0.5 (AP.50) and frames per second (FPS), alongside surgeon feedback via Likert scale questionnaires.

Main Results:

The AI model achieved an AP.50 of 0.574 for active bleeding detection.
The model demonstrated a real-time processing speed of 48.5 FPS.
Surgeons rated the model highly, with a sensitivity score of 4.92 and an overdetection score of 4.62.

Conclusions:

An AI model for real-time active bleeding detection during surgery was successfully developed.
The model operates at a processing speed suitable for real-time surgical assistance.
This AI tool holds promise for enhancing intraoperative safety by providing real-time surgical support.