Automated analysis of small intestinal lamina propria to distinguish normal, Celiac Disease, and Non-Celiac Duodenitis biopsy images

• Published in: Computer methods and programs in biomedicine 2023-03, Vol.230, p.107320-107320, Article 107320
• Main Authors: Faust, Oliver, De Michele, Simona, Koh, Joel EW, Jahmunah, V, Lih, Oh Shu, Kamath, Aditya P, Barua, Prabal Datta, Ciaccio, Edward J., Lewis, Suzanne K., Green, Peter H., Bhagat, Govind, Acharya, U. Rajendra
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Biopsy; Celiac Disease; Celiac Disease - diagnosis; Computer-aided diagnosis; Duodenitis - diagnostic imaging; Duodenitis - pathology; Explainable artificial intelligence; Humans; Inflammation; Intestinal Mucosa - diagnostic imaging; Lamina propria; Noncommunicable Diseases
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2022.107320

•Computational, image-based analysis of the small intestinal lamina propria in Celiac Disease and Non-Celiac Duodenitis (and comparison with non-inflamed lamina propria).•Clinical dataset comprised from biopsy images of different disease stages.•Tidily controlled feature engineering with Pyramid Histogram of Gradient algorithms coupled with classification and explainability assessment.•Result validation and interpretation by medical experts. Celiac Disease (CD) is characterized by gluten intolerance in genetically predisposed individuals. High disease prevalence, absence of a cure, and low diagnosis rates make this disease a public health problem. The diagnosis of CD predominantly relies on recognizing characteristic mucosal alterations of the small intestine, such as villous atrophy, crypt hyperplasia, and intraepithelial lymphocytosis. However, these changes are not entirely specific to CD and overlap with Non-Celiac Duodenitis (NCD) due to various etiologies. We investigated whether Artificial Intelligence (AI) models could assist in distinguishing normal, CD, and NCD (and unaffected individuals) based on the characteristics of small intestinal lamina propria (LP). Our method was developed using a dataset comprising high magnification biopsy images of the duodenal LP compartment of CD patients with different clinical stages of CD, those with NCD, and individuals lacking an intestinal inflammatory disorder (controls). A pre-processing step was used to standardize and enhance the acquired images. For the normal controls versus CD use case, a Support Vector Machine (SVM) achieved an Accuracy (ACC) of 98.53%. For a second use case, we investigated the ability of the classification algorithm to differentiate between normal controls and NCD. In this use case, the SVM algorithm with linear kernel outperformed all the tested classifiers by achieving 98.55% ACC. To the best of our knowledge, this is the first study that documents automated differentiation between normal, NCD, and CD biopsy images. These findings are a stepping stone toward automated biopsy image analysis that can significantly benefit patients and healthcare providers.