Related Experiment Video
Updated: Feb 25, 2026
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
43.7K
Automatic detection of surgical haemorrhage using computer vision
Alvaro Garcia-Martinez1, Jose María Vicente-Samper1, José María Sabater-Navarro1
1Systems and Automatics Engineering Department, Miguel Hernández University, Avinguda de la Universitat d'Elx, Elche, 03202, Spain.
Artificial Intelligence in Medicine
|August 3, 2017
Summary
This study introduces a computer vision algorithm for detecting hemorrhages during laparoscopic surgery. The system analyzes camera images to identify blood pixels, aiding surgeons in real-time.
Area of Science:
- Medical Imaging
- Computer Vision
- Surgical Technology
Background:
- Hemorrhage is a critical complication in surgical interventions, particularly in laparoscopic procedures.
- Limited vision and mobility in minimally invasive surgery exacerbate hemorrhage risks.
Purpose of the Study:
- To develop and evaluate a computer vision algorithm for automatic blood and hemorrhage detection in laparoscopic surgery.
- To enhance surgeon's vision and improve patient safety during operations.
Main Methods:
- A computer vision algorithm analyzes laparoscopic camera images.
- Pixels are classified as blood or background based on RGB color space parameters (B/R, G/R).
- Hemorrhage detection is achieved by analyzing variations in pixel classification and blood pixel count.
Main Results:
- The algorithm achieved over 96% accuracy on in vitro images.
- In vivo analysis showed 88% accuracy, with 78% accuracy for hemorrhage detection.
- Performance is affected by factors like illumination and camera movement.
Conclusions:
- The algorithm serves as a foundation for automated blood detection in surgical settings.
- Potential applications include augmented reality visualization to alert surgeons to impending hemorrhages.
