Machine Learning Approach for Biopsy-Based Identification of Eosinophilic Esophagitis Reveals Importance of Global features

Machine Learning Approach for Biopsy-Based Identification of Eosinophilic Esophagitis Reveals Importance of Global features

<italic>Goal:</italic> Eosinophilic esophagitis (EoE) is an allergic inflammatory condition characterized by eosinophil accumulation in the esophageal mucosa. EoE diagnosis includes a manual assessment of eosinophil levels in mucosal biopsies&#x2013;a time-consuming, laborious task t...

Full description

Saved in:
Bibliographic Details
Main Authors: Tomer Czyzewski, Nati Daniel, Mark Rochman, Julie Caldwell, Garrett Osswald, Margaret Collins, Marc Rothenberg, Yonatan Savir
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Open Journal of Engineering in Medicine and Biology
Subjects:
Decision support system
deep convolutional network
digital pathology
eosinophilic esophagitis
small features detection
Online Access:https://ieeexplore.ieee.org/document/9457060/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:<italic>Goal:</italic> Eosinophilic esophagitis (EoE) is an allergic inflammatory condition characterized by eosinophil accumulation in the esophageal mucosa. EoE diagnosis includes a manual assessment of eosinophil levels in mucosal biopsies&#x2013;a time-consuming, laborious task that is difficult to standardize. One of the main challenges in automating this process, like many other biopsy-based diagnostics, is detecting features that are small relative to the size of the biopsy. <italic>Results:</italic> In this work, we utilized hematoxylin- and eosin-stained slides from esophageal biopsies from patients with active EoE and control subjects to develop a platform based on a deep convolutional neural network (DCNN) that can classify esophageal biopsies with an accuracy of 85&#x0025;, sensitivity of 82.5&#x0025;, and specificity of 87&#x0025;. Moreover, by combining several downscaling and cropping strategies, we show that some of the features contributing to the correct classification are global rather than specific, local features. <italic>Conclusions:</italic> We report the ability of artificial intelligence to identify EoE using computer vision analysis of esophageal biopsy slides. Further, the DCNN features associated with EoE are based on not only local eosinophils but also global histologic changes. Our approach can be used for other conditions that rely on biopsy-based histologic diagnostics.
ISSN:2644-1276

Similar Items