pylori infected status, and 79.2% for post H. The diagnostic accuracy of the LCI-CAD system was 84.2% for H. Following this, a computer-aided diagnosis (CAD) system based on LCI combined with deep learning was developed. AI technology with IEE is likely to become a useful image tool for diagnosing gastritis, GIM, and EGC. ![]() pylori infection with BLI-bright and LCI. The developed AI method had an excellent ability to diagnose H. We were able to obtain several color images and detailed information micro-surface patterns and micro-vascular patterns were represented using the LCI mode, although this was not possible with the WLI mode.ĭeep learning is a type of artificial intelligence (AI) that imitates the neural network in the brain. LCI is brighter than WLI and useful for the screening of gastrointestinal lesions even as a distant view from the large lumen such as the stomach. LCI shows a mucosal color similar to WLI and also produces different color patterns of the mucosa from WLI due to emission intensity at certain wavelengths. Consequently, the regions that were originally red appear redder, and regions that were originally white appear whiter, but with natural tones. ![]() Digital signal/image processing in LCI systems emphasizes slight color differences and provides a better color contrast within the red color range. With a wavelength of 410 nm, both the microstructure and microvasculature in the superficial layer of the mucosa are emphasized. LCI detects the mucosal surface patterns clearly including the microstructure because of the high intensity at short wavelengths including 410 nm and 450 nm.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |