Machine learning model with texture analysis for automatic classification of histopathological images of ocular adnexal mucosa-associated lymphoid tissue lymphoma of two different origins.

Purpose: The purpose of this study was to develop artificial intelligence algorithms that can distinguish between orbital and conjunctival mucosa-associated lymphoid tissue (MALT) in pathological images. Methods: Tissue blocks with residual MALT lymphoma and data from histological and flow cytometric studies and molecular genetic analyses such as gene rearrangement were procured for 129 patients treated between April 2008 and April 2020. We collected pathological hematoxylin and eosin-stained images of lymphoma from these patients, and cropped 10 different image patches at a resolution of 2048 × 2048 from pathological images from each patient. A total of 990 images from 99 patients were used to create and evaluate machine-learning models. Each image patch of 3 different magnification rate at×４, ×20, and ×40 underwent texture analysis to extract features, then seven different machine-learning algorithms were applied to the results to create models. Cross-validation on a patient-by-patient basis was used to create and evaluate models, then 300 images from the remaining 30 cases were used to evaluate the average accuracy rate. Results: Ten-fold cross-validation using the support vector machine with linear kernel algorithm was identified as the best algorithm for discriminating between conjunctival MALT and orbital MALT, with an average accuracy rate under cross-validation of 85%.There were ×20 magnification images were more distinguish accuracy between orbital and conjunctival MALT between at×４and ×40. . Conclusion: Artificial intelligence algorithms can successfully distinguish between orbital and conjunctival MALT.