학술논문
Computer-Automated Malaria Diagnosis and Quantitation Using Convolutional Neural Networks
Document Type
Conference
Author
Mehanian, Courosh; Jaiswal, Mayoore; Delahunt, Charles; Thompson, Clay; Horning, Matt; Hu, Liming; McGuire, Shawn; Ostbye, Travis; Mehanian, Martha; Wilson, Ben; Champlin, Cary; Long, Earl; Proux, Stephane; Gamboa, Dionicia; Chiodini, Peter; Carter, Jane; Dhorda, Mehul; Isaboke, David; Ogutu, Bernhards; Oyibo, Wellington; Villasis, Elizabeth; Tun, Kyaw Myo; Bachman, Christine; Bell, David
Source
2017 IEEE International Conference on Computer Vision Workshops (ICCVW) Computer Vision Workshop (ICCVW), 2017 IEEE International Conference on. :116-125 Oct, 2017
Subject
Language
ISSN
2473-9944
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.