Health-mentor
AI that generates reports from health checkup data
Learn moreColonoscopy
Endo-mentor
Polyp detection and insertion guidance based on anatomical location in the colon
Product overview
From insertion to lesion detection and records,
Endo-mentor assists every stage in real time,
supporting safer, more accurate colonoscopy.
- Application
- Colonoscopy
- Deployment
- On-premises
- Regulatory status
- Regulatory approval in progress
Background
The clinical challenge
Colonoscopy quality can vary with the examiner’s skill and focus
at every stage, from insertion and observation to lesion detection.
Recording results against consistent criteria
and standardizing and automating documentation
are also key to improving quality and efficiency.
The Endo-mentor approach
Endo-mentor supports the examiner’s judgment
and procedure based on anatomical location information.
It also records each examination in a standardized format
for accurate and consistent records.
Key features
Real-time location recognition
- Guides the direction of the endoscope during insertion.
Automatic polyp detection
- Detects polyps during observation based on location information.
Automated procedure records
- Writes up the results in a standard format after the procedure.
Related research
Patents and papers from our research team on the same topic as this product.
- 2Patent applications filed by the company
- 4SCI-indexed papers
Method and system for estimating anatomical location from endoscopic images
Method and system for real-time perforation risk prediction and warning during endoscopic procedures
Impact of User’s Background Knowledge and Polyp Characteristics in Colonoscopy with Computer-Aided Detection
Read paper (opens in a new tab)Density clustering-based automatic anatomical section recognition in colonoscopy video using deep learning
Read paper (opens in a new tab)Colonoscopic image synthesis with generative adversarial network for enhanced detection of sessile serrated lesions using convolutional neural network
Read paper (opens in a new tab)AI-powered hierarchical classification of ampullary neoplasms: a deep learning approach using white-light and narrow-band imaging
Read paper (opens in a new tab)