1. Computer-Automated Malaria Diagnosis and Quantitation Using Convolutional Neural Networks
- Author
-
Mayoore S. Jaiswal, Wellington Oyibo, Matthew P. Horning, Earl G. Long, Christine Bachman, Kyaw Myo Tun, Cary Champlin, Mehul Dhorda, Charles B. Delahunt, Clay M. Thompson, Bernhards Ogutu, Derek Bell, Liming Hu, Martha Mehanian, Elizabeth Villasis, Peter L. Chiodini, David Isaboke, Ben Wilson, Travis Ostbye, Courosh Mehanian, Dionicia Gamboa, Jane Carter, Shawn K. McGuire, and Stephane Proux
- Subjects
Training set ,Computer science ,business.industry ,Deep learning ,030231 tropical medicine ,02 engineering and technology ,Drug resistance ,medicine.disease ,Machine learning ,computer.software_genre ,Convolutional neural network ,World health ,03 medical and health sciences ,0302 clinical medicine ,parasitic diseases ,0202 electrical engineering, electronic engineering, information engineering ,medicine ,020201 artificial intelligence & image processing ,Artificial intelligence ,Medical diagnosis ,business ,computer ,Malaria - Abstract
The optical microscope remains a widely-used tool for diagnosis and quantitation of malaria. An automated system that can match the performance of well-trained technicians is motivated by a shortage of trained microscopists. We have developed a computer vision system that leverages deep learning to identify malaria parasites in micrographs of standard, field-prepared thick blood films. The prototype application diagnoses P. falciparum with sufficient accuracy to achieve competency level 1 in the World Health Organization external competency assessment, and quantitates with sufficient accuracy for use in drug resistance studies. A suite of new computer vision techniques-global white balance, adaptive nonlinear grayscale, and a novel augmentation scheme-underpin the system's state-of-the-art performance. We outline a rich, global training set; describe the algorithm in detail; argue for patient-level performance metrics for the evaluation of automated diagnosis methods; and provide results for P. falciparum.
- Published
- 2017
- Full Text
- View/download PDF