Fully-automated patient-level malaria assessment on field-prepared thin blood film microscopy images

• Published in: 2019 IEEE Global Humanitarian Technology Conference (GHTC) pp. 1 - 8
• Main Authors: Delahunt, Charles B., Gebrehiwot, Roman, Wilson, Benjamin K., Long, Earl, Proux, Stephane, Gamboa, Dionicia, Chiodini, Peter, Carter, Jane, Dhorda, Mehul, Isaboke, David, Ogutu, Bernhards, Jaiswal, Mayoore S., Oyibo, Wellington, Villasis, Elizabeth, Tun, Kyaw Myo, Bachman, Christine, Bell, David, Mehanian, Courosh, Horning, Matthew P., Janko, Samantha, Thompson, Clay M., Kulhare, Sourabh, Hu, Liming, Ostbye, Travis, Yun, Grace
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-10-2019
• Subjects: automated microscopy; deep neural networks; gradient boosted trees; malaria
• DOI: 10.1109/GHTC46095.2019.9033083

Malaria is a life-threatening disease affecting millions. Microscopy-based assessment of thin blood films is a standard method to (i) determine malaria species and (ii) quantitate high-parasitemia infections. Full automation of malaria microscopy by machine learning (ML) is a challenging task because field-prepared slides vary widely in quality and presentation, and artifacts often heavily outnumber relatively rare parasites. In this work, we describe a complete, fully-automated framework for thin film malaria analysis that applies ML methods, including convolutional neural nets (CNNs), trained on a large and diverse dataset of field-prepared thin blood films. Quantitation and species identification results are close to sufficiently accurate for the concrete needs of drug resistance monitoring and clinical use-cases on field-prepared samples. We focus our methods and our performance metrics on the field use-case requirements. We discuss key issues and important metrics for the application of ML methods to malaria microscopy.