During a colonoscopy, the computer-assisted diagnostic system magnifies colorectal polyps to compare their features with those of 30,000 endocytoscopic images. In a study of 300-plus polyps, the system was able to identify, analyze and predict the pathology of a polyp in less than one second with 86 percent accuracy.
“The most remarkable breakthrough with this system is that artificial intelligence enables real-time optical biopsy of colorectal polyps during colonoscopy, regardless of the endoscopists’ skill,” Dr. Yuichi Mori, lead researcher from Yokohama, Japan-based Showa University, said in a statement.
More articles on artificial intelligence:
Zocdoc applies AI model to verify patients’ insurance details
Survey: 10 things people want AI to do for them
Intel collaborates with Facebook on computer chip for AI
