Artificial Intelligence-based Eosinophil Counting in Gastrointestinal Biopsies

TL;DR

This paper presents an AI-based method using a UNet neural network to automatically detect and count eosinophils in gastrointestinal biopsy images, aiding early diagnosis of eosinophilia.

Contribution

It introduces a deep learning approach for eosinophil detection in GI biopsies, demonstrating high correlation with manual counts and improving diagnostic efficiency.

Findings

Pearson correlation coefficient of 85% between AI and manual counts

Effective detection of eosinophils using deep neural network

Potential to assist clinicians in diagnosing eosinophilia

Abstract

Normally eosinophils are present in the gastrointestinal (GI) tract of healthy individuals. When the eosinophils increase beyond their usual amount in the GI tract, a patient gets varied symptoms. Clinicians find it difficult to diagnose this condition called eosinophilia. Early diagnosis can help in treating patients. Histopathology is the gold standard in the diagnosis for this condition. As this is an under-diagnosed condition, counting eosinophils in the GI tract biopsies is important. In this study, we trained and tested a deep neural network based on UNet to detect and count eosinophils in GI tract biopsies. We used connected component analysis to extract the eosinophils. We studied correlation of eosinophilic infiltration counted by AI with a manual count. GI tract biopsy slides were stained with H&E stain. Slides were scanned using a camera attached to a microscope and five high-power field images were taken per slide. Pearson correlation coefficient was 85% between the machine-detected and manual eosinophil counts on 300 held-out (test) images.