TY - JOUR
T1 - Artificial Intelligence-based Analytics for Diagnosis of Small Bowel Enteropathies and Black Box Feature Detection
AU - Syed, Sana
AU - Ehsan, Lubaina
AU - Shrivastava, Aman
AU - Sengupta, Saurav
AU - Khan, Marium
AU - Kowsari, Kamran
AU - Guleria, Shan
AU - Sali, Rasoul
AU - Kant, Karan
AU - Kang, Sung Jun
AU - Sadiq, Kamran
AU - Iqbal, Najeeha T.
AU - Cheng, Lin
AU - Moskaluk, Christopher A.
AU - Kelly, Paul
AU - Amadi, Beatrice C.
AU - Asad Ali, Syed
AU - Moore, Sean R.
AU - Brown, Donald E.
N1 - Funding Information:
Funding: Research reported in this manuscript was supported by National Institute of Diabetes and Digestive and Kidney Diseases of the National Institutes of Health under award number K23DK117061-01A1 (Syed), Bill and Melinda Gates Foundation under award numbers OPP1066203 (Ali) and OPP1066118 (Kelly), University of Virginia Center for Engineering in Medicine Grant (Syed and Brown), and University of Virginia THRIV Scholar Career Development Award (Syed). The content is solely the responsibility of the authors and does not necessarily represent the official views of the funding agencies.
Funding Information:
We acknowledge the following individuals from Aga Khan University, Karachi, Pakistan, for contributing to this manuscript: Drs Romana Idrees, MBBS, FCPS, and Zubair Ahmad, MBBS, FCPS, FRCPath, for assessment of stain color normalized biopsy images, Saad Mallick, medical student, for the organization of image activation mappings, Dr Saman Siddiqui, MD, for coordinating with the pathologists at Aga Khan University, and field workers (community health workers, led by Sadaf Jakhro, MSc, and coordinated by Dr Tauseef Akhund, MBBS), data management unit (Najeeb Rahman, BS), and laboratory staff (Aneeta Hotwani, BS) for contributing to the data collection in this work. Patcharin Pramoonjago, PhD, Biorepository and Tissue Research Facility, University of Virginia, Charlottesville, assisted in data collection for this work. All individuals were compensated for their time.
Publisher Copyright:
Copyright © 2021 Espghan and Naspghan.
PY - 2021/6/1
Y1 - 2021/6/1
N2 - Objectives: Striking histopathological overlap between distinct but related conditions poses a 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 the secondary analysis was obtained from three primary studies at different sites. The image analysis platform for EE and CD was developed using CNNs including one with multizoom architecture. Gradient-weighted class activation mappings (Grad-CAMs) were used to visualize the models' decision-making process for classifying each disease. A team of medical experts simultaneously reviewed the stain color normalized images done for bias reduction and Grad-CAMs to confirm structural preservation and biomedical relevance, respectively. Results: Four hundred and sixty-one high-resolution biopsy images from 150 children were acquired. Median age (interquartile range) was 37.5 (19.0-121.5) 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 models' ability to learn different microscopic morphological features for EE, CD, and controls. Conclusions: Our AI-based image analysis platform demonstrated high classification accuracy for small bowel enteropathies which was capable of identifying biologically relevant microscopic features and emulating human pathologist decision-making process. Grad-CAMs illuminated the otherwise "black box"of deep learning in medicine, allowing for increased physician confidence in adopting these new technologies in clinical practice.
AB - Objectives: Striking histopathological overlap between distinct but related conditions poses a 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 the secondary analysis was obtained from three primary studies at different sites. The image analysis platform for EE and CD was developed using CNNs including one with multizoom architecture. Gradient-weighted class activation mappings (Grad-CAMs) were used to visualize the models' decision-making process for classifying each disease. A team of medical experts simultaneously reviewed the stain color normalized images done for bias reduction and Grad-CAMs to confirm structural preservation and biomedical relevance, respectively. Results: Four hundred and sixty-one high-resolution biopsy images from 150 children were acquired. Median age (interquartile range) was 37.5 (19.0-121.5) 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 models' ability to learn different microscopic morphological features for EE, CD, and controls. Conclusions: Our AI-based image analysis platform demonstrated high classification accuracy for small bowel enteropathies which was capable of identifying biologically relevant microscopic features and emulating human pathologist decision-making process. Grad-CAMs illuminated the otherwise "black box"of deep learning in medicine, allowing for increased physician confidence in adopting these new technologies in clinical practice.
KW - biopsy image analysis
KW - convolutional neural networks
KW - environmental enteropathy
KW - global health
KW - intestinal structure
UR - http://www.scopus.com/inward/record.url?scp=85106539343&partnerID=8YFLogxK
U2 - 10.1097/MPG.0000000000003057
DO - 10.1097/MPG.0000000000003057
M3 - Article
C2 - 33534362
AN - SCOPUS:85106539343
SN - 0277-2116
VL - 72
SP - 833
EP - 841
JO - Journal of Pediatric Gastroenterology and Nutrition
JF - Journal of Pediatric Gastroenterology and Nutrition
IS - 6
ER -