Automated Detection of P. falciparum Using Machine Learning Algorithms with Quantitative Phase Images of Unstained Cells.

Park, Han Sang

Rinehart, Matthew T

Walzer, Katelyn A

Chi, Jen-Tsan Ashley

Wax, Adam

Sullivan, David J

2020-04-01T13:21:39Z

2020-04-01T13:21:39Z

2016-01

2020-04-01T13:21:37Z

Malaria detection through microscopic examination of stained blood smears is a diagnostic challenge that heavily relies on the expertise of trained microscopists. This paper presents an automated analysis method for detection and staging of red blood cells infected by the malaria parasite Plasmodium falciparum at trophozoite or schizont stage. Unlike previous efforts in this area, this study uses quantitative phase images of unstained cells. Erythrocytes are automatically segmented using thresholds of optical phase and refocused to enable quantitative comparison of phase images. Refocused images are analyzed to extract 23 morphological descriptors based on the phase information. While all individual descriptors are highly statistically different between infected and uninfected cells, each descriptor does not enable separation of populations at a level satisfactory for clinical utility. To improve the diagnostic capacity, we applied various machine learning techniques, including linear discriminant classification (LDC), logistic regression (LR), and k-nearest neighbor classification (NNC), to formulate algorithms that combine all of the calculated physical parameters to distinguish cells more effectively. Results show that LDC provides the highest accuracy of up to 99.7% in detecting schizont stage infected cells compared to uninfected RBCs. NNC showed slightly better accuracy (99.5%) than either LDC (99.0%) or LR (99.1%) for discriminating late trophozoites from uninfected RBCs. However, for early trophozoites, LDC produced the best accuracy of 98%. Discrimination of infection stage was less accurate, producing high specificity (99.8%) but only 45.0%-66.8% sensitivity with early trophozoites most often mistaken for late trophozoite or schizont stage and late trophozoite and schizont stage most often confused for each other. Overall, this methodology points to a significant clinical potential of using quantitative phase imaging to detect and stage malaria infection without staining or expert analysis.

PONE-D-16-10490

1932-6203

1932-6203

https://hdl.handle.net/10161/20286

eng

Public Library of Science (PLoS)

PloS one

10.1371/journal.pone.0163045

Erythrocytes

Humans

Plasmodium falciparum

Algorithms

Automation

Machine Learning

Automated Detection of P. falciparum Using Machine Learning Algorithms with Quantitative Phase Images of Unstained Cells.

Journal article

Chi, Jen-Tsan Ashley|0000-0003-3433-903X

e0163045

9

Pratt School of Engineering

Physics

Biomedical Engineering

Duke Cancer Institute

Duke Institute for Brain Sciences

Duke

Trinity College of Arts & Sciences

Institutes and Centers

School of Medicine

University Institutes and Centers

Institutes and Provost's Academic Units

Molecular Genetics and Microbiology

Pharmacology & Cancer Biology

Radiation Oncology

Medicine, Rheumatology and Immunology

Basic Science Departments

Clinical Science Departments

Medicine

Published

11