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

Abstract

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.

Computer‐aided diagnosis in real‐time endoscopy for all stages of gastric carcinogenesis: Development and validation study

“…established a real‐time semantic segmentation model in terms of intestinal metaplasia. 27 Although the diagnostic performance in this study was excellent, this model was not a CADe or CADx model; rather, only gastric intestinal metaplasia could be segmented in real time.…”

Accuracy of artificial intelligence-assisted endoscopy in the diagnosis of gastric intestinal metaplasia: A systematic review and meta-analysis

“…Siripoppohn et al [ 42 ] implemented semantic segmentation of GIM by adding three additional preprocessing techniques to the BiSeNet network and compared it with the classical semantic segmentation algorithms, DeepLabV3+ and U-Net. Diagnostic data were extracted from the improved algorithm using a prospective video test set.…”

Applications of artificial intelligence in gastroscopy: a narrative review

“…Several studies have shown that deep learning models can achieve 87% to 99.18% accuracy in the recognition of IM. 38,40,41 As noted above, most of this research has been focused on image recognition; the clinical value of existing models remains unclear. A few test videos have shown that the models require demanding environmental conditions to achieve the desired recognition effect.…”

“…A few test videos have shown that the models require demanding environmental conditions to achieve the desired recognition effect. 40 Feature extraction and matching are essential for AI image recognition; any factors affecting the clinical presentation will influence AI recognition performance. Such factors include light, lens angle, and distance from the lens to the gastric mucosa.…”