A multiple instance learning approach for detecting COVID-19 in peripheral blood smears
Open Access
- 19 August 2022
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS Digital Health
- Vol. 1 (8) , e0000078
Abstract
A wide variety of diseases are commonly diagnosed via the visual examination of cell morphology within a peripheral blood smear. For certain diseases, such as COVID-19, morphological impact across the multitude of blood cell types is still poorly understood. In this paper, we present a multiple instance learning-based approach to aggregate high-resolution morphological information across many blood cells and cell types to automatically diagnose disease at a per-patient level. We integrated image and diagnostic information from across 236 patients to demonstrate not only that there is a significant link between blood and a patient’s COVID-19 infection status, but also that novel machine learning approaches offer a powerful and scalable means to analyze peripheral blood smears. Our results both backup and enhance hematological findings relating blood cell morphology to COVID-19, and offer a high diagnostic efficacy; with a 79% accuracy and a ROC-AUC of 0.90.Keywords
All Related Versions
Funding Information
- Duke-Coulter
- Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada
- 3M Nontenured Faculty Award
This publication has 30 references indexed in Scilit:
- Potential Biases in Machine Learning Algorithms Using Electronic Health Record DataJAMA Internal Medicine, 2018
- Significance of green granules in neutrophils and monocytesBaylor University Medical Center Proceedings, 2017
- A deep convolutional neural network for classification of red blood cells in sickle cell anemiaPLOS Computational Biology, 2017
- Densely Connected Convolutional Networks2017
- Cyclical Learning Rates for Training Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- Purpose and Criteria for Blood Smear Scan, Blood Smear Examination, and Blood Smear ReviewAnnals of Laboratory Medicine, 2013
- Torchvision the machine-vision package of torch2010
- Examination of peripheral blood films using automated microscopy; evaluation of Diffmaster Octavia and Cellavision DM96Journal of Clinical Pathology, 2006
- Nuclear Blebs in Human Leukaemic CellsNature, 1967