A new endoscopic system powered by artificial intelligence (AI) has been shown to automatically identify colorectal adenomas during a colonoscopy. The system was developed in Japan and has recently been tested in one of the first prospective trials of AI-assisted endoscopy in a clinical setting.
The new computer-aided diagnostic system uses an endocytoscopic image, a 500-fold magnified view of a colorectal polyp, to analyze around 300 features of the polyp after applying narrow-band imaging (NBI) mode or staining with methylene blue. The system compares the features of each polyp against more than 30,000 endocytoscopic images that were used for machine learning. This allows the system to predict the lesion pathology in less than a second. Early studies demonstrated the feasibility of using such a system to classify colorectal polyp but until today no prospective studies have been reported.
The study was led by Dr. Yuichi Mori from Showa University in Yokohama, Japan. The study involved 205 men and women who had colorectal polyps detected in their bodies using endocytoscopy. The AI system was used to predict the pathology of each polyp and the predictions were compared with the pathological report from the final resected specimens. Overall, 306 polyps were assessed in real-time by using the AI-assisted system with a sensitivity of 94 percent, specificity of 94 percent, accuracy of 86 percent and positive and negative predictive values of 79 percent and 93 percent respectively in identifying neoplastic changes.
Dr. Mori said, "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. This allows the complete resection of adenomatous polyps and prevents unnecessary polypectomy of non-neoplastic polyps. We believe these results are acceptable for clinical application and our immediate goal is to obtain regulatory approval for the diagnostic system."
The research team is now undertaking a multicenter study for this purpose and the team is working on developing an automatic polyp detection system.
"Precise on-site identification of adenomas during colonoscopy contributes to the complete resection of neoplastic lesions," said Dr. Mori. "This is thought to decrease the risk of colorectal cancer and, ultimately, cancer-related death."
This research was presented at the 25th UEG Week in Barcelona, Spain.