Simultaneous Recognition of Atrophic Gastritis and Intestinal Metaplasia on White Light Endoscopic Images Based on Convolutional Neural Networks: A Multicenter Study

Abstract

INTRODUCTION: Patients with atrophic gastritis (AG) or gastric intestinal metaplasia (GIM) have elevated risk of gastric adenocarcinoma. Endoscopic screening and surveillance have been implemented in high incidence countries. The study aimed to evaluate the accuracy of a deep convolutional neural network (CNN) for simultaneous recognition of AG and GIM. METHODS: Archived endoscopic white light images with corresponding gastric biopsies were collected from 14 hospitals located in different regions of China. Corresponding images by anatomic sites containing AG, GIM, and chronic non-AG were categorized using pathology reports. The participants were randomly assigned (8:1:1) to the training cohort for developing the CNN model (TResNet), the validation cohort for fine-tuning, and the test cohort for evaluating the diagnostic accuracy. The area under the curve (AUC), sensitivity, specificity, and accuracy with 95% confidence interval (CI) were calculated. RESULTS: A total of 7,037 endoscopic images from 2,741 participants were used to develop the CNN for recognition of AG and/or GIM. The AUC for recognizing AG was 0.98 (95% CI 0.97–0.99) with sensitivity, specificity, and accuracy of 96.2% (95% CI 94.2%–97.6%), 96.4% (95% CI 94.8%–97.9%), and 96.4% (95% CI 94.4%–97.8%), respectively. The AUC for recognizing GIM was 0.99 (95% CI 0.98–1.00) with sensitivity, specificity, and accuracy of 97.9% (95% CI 96.2%–98.9%), 97.5% (95% CI 95.8%–98.6%), and 97.6% (95% CI 95.8%–98.6%), respectively. DISCUSSION: CNN using endoscopic white light images achieved high diagnostic accuracy in recognizing AG and GIM.

Diagnostic value of artificial intelligence-assisted endoscopy for chronic atrophic gastritis: a systematic review and meta-analysis

“…Two studies ( 43 , 47 ) were from the same team, one of which ( 47 ) constructed and tested a CAG diagnostic model, and the other ( 43 ) performed a further test; hence, we selected the more extensive test set of data ( 43 ) included in this meta-analysis. Two other studies ( 41 , 48 ) were also from the same team; one study ( 41 ) used AI to identify AG and IM, and another study ( 48 ) added the identification of GC to the former, and we chose the first ( 41 ) to be included in this meta-analysis. Three studies were excluded because only IM was identified ( 49 – 51 ).…”

Endoscopic Grading of Gastric Intestinal Metaplasia Using Magnifying and Nonmagnifying Narrow-Band Imaging Endoscopy

“…In particular, the computer-aided detection system proposed in one study achieved diagnostic accuracy for gastric precancerous conditions comparable to that of experts and superior to that of nonexperts [ 19 ]. Furthermore, deep convolutional neural network recognition of atrophic gastritis and gastric IM was achieved in another study [ 20 ]. However, the European Society of Gastrointestinal Endoscopy guidelines recently addressed the potential usefulness of AI systems, stating that AI-assisted diagnosis of atrophy and IM should be comparable to that provided by the established biopsy protocol, including extent estimation and subsequent allocation to the appropriate endoscopic surveillance interval [ 21 ].…”

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.…”

“…36 In their efforts to establish an AI model for atrophic gastritis detection, Guimaraes et al 37 achieved 93.0% accuracy by training the model with 200 images. Lin et al 38 replicated this approach with greater accuracy, achieving 96.4% accuracy in the detection of atrophic gastritis; they also detected intestinal metaplasia with 97.6% accuracy. Furthermore, researchers in China demonstrated that a trained AI model could review dynamic video and detect CAG with 92.37% accuracy 39 ; the key aspect of their work was its demonstration that an AI model could identify CAGs by assessing clinical videos.…”