Application of automated machine learning for histological evaluation of feline endoscopic samples

抄録

Differentiating intestinal T-cell lymphoma from chronic enteropathy (CE) in endoscopic samples is often challenging. In the present study, automated machine learning systems were developed to distinguish between the two diseases, predict clonality, and detect prognostic factors of intestinal lymphoma in cats. Four models were created for four experimental conditions: experiment 1 to distinguish between intestinal T-cell lymphoma and CE; experiment 2 to distinguish large cell lymphoma, small cell lymphoma, and CE; experiment 3 to distinguish granzyme B+ lymphoma, granzyme B- lymphoma, and CE; and experiment 4 to distinguish between T-cell receptor (TCR) clonal population and TCR polyclonal population. After each experiment, a pathologist reviewed the test images and scored for lymphocytic infiltration, epitheliotropism, and epithelial injury. The models of experiments 1–4 achieved area under the receiver operating characteristic curve scores of 0.943 (precision, 87.59%; recall, 87.59%), 0.962 (precision, 86.30%; recall, 86.30%), 0.904 (precision, 82.86%; recall, 80%), and 0.904 (precision, 81.25%; recall, 81.25%), respectively. The images predicted as intestinal T-cell lymphoma showed significant infiltration of lymphocytes and epitheliotropism than CE. These models can provide evaluation tools to assist pathologists with differentiating between intestinal T-cell lymphoma and CE.