Automated Detection of Celiac Disease on Duodenal Biopsy Slides: A Deep Learning Approach

• Published in: Journal of pathology informatics Vol. 10; no. 1; p. 7
• Main Authors: Wei, Jason W., Wei, Jerry W., Jackson, Christopher R., Ren, Bing, Suriawinata, Arief A., Hassanpour, Saeed
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.01.2019; Medknow Publications & Media Pvt. Ltd; Wolters Kluwer - Medknow; Elsevier
• Subjects: Accuracy; Artificial intelligence; Artificial neural networks; Atrophy; Autoimmune diseases; Automation; Biopsy; Celiac disease; Classification; Datasets; Deep learning; Diabetic retinopathy; Diagnosis; digital pathology; duodenal biopsy; Endoscopy; Image classification; Image detection; Inflammation; Laboratories; Machine learning; Medical imaging; Model testing; Neural networks; Original Research; Pathology; Patients; State of the art; Studies; whole-slide imaging; whole-slide imaging; Celiac disease; deep learning; digital pathology; duodenal biopsy
• ISSN: 2153-3539; 2229-5089; 2153-3539
• DOI: 10.4103/jpi.jpi_87_18

Context: Celiac disease (CD) prevalence and diagnosis have increased substantially in recent years. The current gold standard for CD confirmation is visual examination of duodenal mucosal biopsies. An accurate computer-aided biopsy analysis system using deep learning can help pathologists diagnose CD more efficiently. Subjects and Methods: In this study, we trained a deep learning model to detect CD on duodenal biopsy images. Our model uses a state-of-the-art residual convolutional neural network to evaluate patches of duodenal tissue and then aggregates those predictions for whole-slide classification. We tested the model on an independent set of 212 images and evaluated its classification results against reference standards established by pathologists. Results: Our model identified CD, normal tissue, and nonspecific duodenitis with accuracies of 95.3%, 91.0%, and 89.2%, respectively. The area under the receiver operating characteristic curve was >0.95 for all classes. Conclusions: We have developed an automated biopsy analysis system that achieves high performance in detecting CD on biopsy slides. Our system can highlight areas of interest and provide preliminary classification of duodenal biopsies before review by pathologists. This technology has great potential for improving the accuracy and efficiency of CD diagnosis.