Expert‐level automated malaria diagnosis on routine blood films with deep neural networks

Abstract

Over 200 million malaria cases globally lead to half a million deaths annually. Accurate malaria diagnosis remains a challenge. Automated imaging processing approaches to analyze Thick Blood Films (TBF) could provide scalable solutions, for urban healthcare providers in the holoendemic malaria sub‐Saharan region. Although several approaches have been attempted to identify malaria parasites in TBF, none have achieved negative and positive predictive performance suitable for clinical use in the west sub‐Saharan region. While malaria parasite object detection remains an intermediary step in achieving automatic patient diagnosis, training state‐of‐the‐art deep‐learning object detectors requires the human‐expert labor‐intensive process of labeling a large dataset of digitized TBF. To overcome these challenges and to achieve a clinically usable system, we show a novel approach. It leverages routine clinical‐microscopy labels from our quality‐controlled malaria clinics, to train a Deep Malaria Convolutional Neural Network classifier (DeepMCNN) for automated malaria diagnosis. Our system also provides total Malaria Parasite (MP) and White Blood Cell (WBC) counts allowing parasitemia estimation in MP/μL, as recommended by the WHO. Prospective validation of the DeepMCNN achieves sensitivity/specificity of 0.92/0.90 against expert‐level malaria diagnosis. Our approach PPV/NPV performance is of 0.92/0.90, which is clinically usable in our holoendemic settings in the densely populated metropolis of Ibadan. It is located within the most populous African country (Nigeria) and with one of the largest burdens of Plasmodium falciparum malaria. Our openly available method is of importance for strategies aimed to scale malaria diagnosis in urban regions where daily assessment of thousands of specimens is required.

Data-driven malaria prevalence prediction in large densely populated urban holoendemic sub-Saharan West Africa

“…Table 2). Our prospectively collected dataset is linked to and amalgamates our childhood malaria case-control and longitudinal studies and bio-banks [18][19][20][21][22][23][24][25] , as well as our research and development of an fast automated machine-learning-driven optical-malaria-diagnostic microscope 26 . The aggregated data used in this study is described in Tables 1, 2 and Supp.…”

Optical mesoscopy, machine learning, and computational microscopy enable high information content diagnostic imaging of blood films

“…Microscopic analysis of blood films is fundamental to many areas of haematology from research to clinical diagnosis [1]. Automated assessment of digitized blood films [2,3] has potential to transform overstretched clinical services that require prompt and accurate assessment of large numbers of specimens. This need is particularly acute in low‐resource settings where human expert analysis of the blood film is the only tool available.…”

Structure-dependent amplification for denoising and background correction in Fourier ptychographic microscopy

“…8(b 1 ) the cytoplasmic ring of the malarial parasite in the upper part of the cell is only visible in the SdA reconstructed image. Such fine morphological features are of critical importance for diagnostic applications [ 23 ].…”