Fully-automated patient-level malaria assessment on field-prepared thin blood film microscopy images, including Supplementary Information
This work addresses the problem of automating malaria diagnosis for healthcare providers in field settings, though it appears incremental as it builds on existing ML methods for a specific domain.
The researchers tackled the challenge of fully automating malaria assessment from field-prepared thin blood film microscopy images, using machine learning methods like CNNs trained on a diverse dataset, achieving results close to sufficient accuracy for drug resistance monitoring and clinical use-cases.
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.