Objectives: Striking histopathological overlap between distinct but related conditions
poses a significant disease diagnostic challenge. There is a major clinical need to
develop computational methods enabling clinicians to translate heterogeneous
biomedical images into accurate and quantitative diagnostics. This need is particularly
salient with small bowel enteropathies; Environmental Enteropathy (EE) and Celiac
Disease (CD). We built upon our preliminary analysis by developing an artificial
intelligence (AI)-based image analysis platform utilizing deep learning convolutional
neural networks (CNNs) for these enteropathies.
Methods: Data for secondary analysis was obtained from three primary studies at
different sites. The image analysis platform for EE and CD was developed using
convolutional neural networks (CNNs: ResNet and custom Shallow CNN). Gradient-weighted
Class Activation Mappings (Grad-CAMs) were used to visualize the decision making process of the models. A team of medical experts simultaneously reviewed the stain color normalized images done for bias reduction and Grad-CAM visualizations to confirm structural preservation and biological relevance, respectively.
Results: 461 high-resolution biopsy images from 150 children were acquired. Median age (interquartile range) was 37.5 (19.0 to 121.5) months with a roughly equal sex
distribution; 77 males (51.3%). ResNet50 and Shallow CNN demonstrated 98% and
96% case-detection accuracy, respectively, which increased to 98.3% with an
ensemble. Grad-CAMs demonstrated ability of the models to learn distinct microscopic
morphological features.
Conclusion: Our AI-based image analysis platform demonstrated high classification
accuracy for small bowel enteropathies which was capable of identifying biologically
relevant microscopic features, emulating human pathologist decision making process,
performing in the case of suboptimal computational environment, and being modified
for improving disease classification accuracy. Grad-CAMs that were employed
illuminated the otherwise black box of deep learning in medicine, allowing for
increased physician confidence in adopting these new technologies in clinical practice.