Skip to main content
construction release_alert
Scholars@Duke will be undergoing maintenance April 11-15. Some features may be unavailable during this time.
cancel

A multiple instance learning approach for detecting COVID-19 in peripheral blood smears.

Publication ,  Journal Article
Cooke, CL; Kim, K; Xu, S; Chaware, A; Yao, X; Yang, X; Neff, J; Pittman, P; McCall, C; Glass, C; Jiang, XS; Horstmeyer, R
Published in: PLOS Digit Health
August 2022

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.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

PLOS Digit Health

DOI

EISSN

2767-3170

Publication Date

August 2022

Volume

1

Issue

8

Start / End Page

e0000078

Location

United States
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Cooke, C. L., Kim, K., Xu, S., Chaware, A., Yao, X., Yang, X., … Horstmeyer, R. (2022). A multiple instance learning approach for detecting COVID-19 in peripheral blood smears. PLOS Digit Health, 1(8), e0000078. https://doi.org/10.1371/journal.pdig.0000078
Cooke, Colin L., Kanghyun Kim, Shiqi Xu, Amey Chaware, Xing Yao, Xi Yang, Jadee Neff, et al. “A multiple instance learning approach for detecting COVID-19 in peripheral blood smears.PLOS Digit Health 1, no. 8 (August 2022): e0000078. https://doi.org/10.1371/journal.pdig.0000078.
Cooke CL, Kim K, Xu S, Chaware A, Yao X, Yang X, et al. A multiple instance learning approach for detecting COVID-19 in peripheral blood smears. PLOS Digit Health. 2022 Aug;1(8):e0000078.
Cooke, Colin L., et al. “A multiple instance learning approach for detecting COVID-19 in peripheral blood smears.PLOS Digit Health, vol. 1, no. 8, Aug. 2022, p. e0000078. Pubmed, doi:10.1371/journal.pdig.0000078.
Cooke CL, Kim K, Xu S, Chaware A, Yao X, Yang X, Neff J, Pittman P, McCall C, Glass C, Jiang XS, Horstmeyer R. A multiple instance learning approach for detecting COVID-19 in peripheral blood smears. PLOS Digit Health. 2022 Aug;1(8):e0000078.

Published In

PLOS Digit Health

DOI

EISSN

2767-3170

Publication Date

August 2022

Volume

1

Issue

8

Start / End Page

e0000078

Location

United States