Real-time semantic segmentation of gastric intestinal metaplasia using a deep learning approach

• Published in: Clinical endoscopy Vol. 55; no. 3; pp. 390 - 400
• Main Authors: Vitchaya Siripoppohn, Rapat Pittayanon, Kasenee Tiankanon, Natee Faknak, Anapat Sanpavat, Naruemon Klaikaew, Peerapon Vateekul, Rungsun Rerknimitr
• Format: Journal Article
• Language: Korean
• Published: 대한소화기내시경학회 30.05.2022
• Subjects: Artificial intelligence; Deep learning; Gastric intestinal metaplasia; Real-time; Semantic segmentation; Deep learning; Gastric intestinal metaplasia; Semantic segmentation; Artificial intelligence; Real-time
• ISSN: 2234-2400; 2234-2443

Background/Aims: Previous artificial intelligence (AI) models attempting to segment gastric intestinal metaplasia (GIM) areas have failed to be deployed in real-time endoscopy due to their slow inference speeds. Here, we propose a new GIM segmentation AI model with inference speeds faster than 25 frames per second that maintains a high level of accuracy. Methods: Investigators from Chulalongkorn University obtained 802 histological-proven GIM images for AI model training. Four strategies were proposed to improve the model accuracy. First, transfer learning was employed to the public colon datasets. Second, an image preprocessing technique contrast-limited adaptive histogram equalization was employed to produce clearer GIM areas. Third, data augmentation was applied for a more robust model. Lastly, the bilateral segmentation network model was applied to segment GIM areas in real time. The results were analyzed using different validity values. Results: From the internal test, our AI model achieved an inference speed of 31.53 frames per second. GIM detection showed sensitivity, specificity, positive predictive, negative predictive, accuracy, and mean intersection over union in GIM segmentation values of 93%, 80%, 82%, 92%, 87%, and 57%, respectively. Conclusions: The bilateral segmentation network combined with transfer learning, contrast-limited adaptive histogram equalization, and data augmentation can provide high sensitivity and good accuracy for GIM detection and segmentation.