AI improves polyp detection during colonoscopy: 6 things to know

A machine-learning algorithm developed by Shanghai Wision AI can detect polyps during colonoscopies in real-time and with high sensitivity and specificity, according to a study in Nature Biomedical Engineering.

Here are six things to know:

1. The algorithm was developed using 5,545 images from the colonoscopy reports of 1,290 patients; 65.5 percent of the images contained polyps.

2. The algorithm was then validated on four independent datasets. Validation on dataset A, which included 27,113 images from patients undergoing colonoscopy at the Endoscopy Center of Sichuan Provincial People's Hospital in China, found a per-image-sensitivity of 94.4 percent and a per-image-specificity of 95.9 percent.

2. Validation on dataset B, which was based on a public database of 612 colonoscopy images acquired from the Hospital Clinic of Barcelona in Spain found a per-image-sensitivity of 88.2 percent.

3. Validation on dataset C, which included a series of colonoscopy videos containing 138 polyps, found a per-image sensitivity of 91.6 percent among 60,914 frames of video and a per-polyp sensitivity of 100 percent.

4. Validation on dataset D, which contained 54 colonoscopy videos with polyps, found a per-image-specificity of 95.4 percent among 1,072,483 frames.

5. The total processing time per image frame was 76.8 milliseconds, including preprocessing and displaying times before and after execution of the deep-learning algorithm.

6. Shanghai Wision AI develops computer-aided diagnostic algorithms and systems to improve the accuracy and effectiveness of diagnostic imaging.

Copyright © 2024 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.

 

Featured Webinars

Featured Whitepapers

Featured Podcast