Remoscope: a label-free imaging cytometer for malaria diagnostics

Abstract

Background: Malaria diagnostic testing remains a burden on healthcare systems. Here we present Remoscope, a portable imaging cytometer that scans fresh, unstained whole blood using a custom neural network running on low-cost hardware. Remoscope performs label-free, quantitative, stage-specific detection of Plasmodium falciparum (Pf) by screening up to 2 million red blood cells (RBCs) in 1-12 min, without sample fixation, staining or slide scanning. Low-cost disposable cartridges are used to confine flowing blood to an ultrathin sheet for imaging.

Methods: Performance was benchmarked in vitro by titration of cultured Pf (17.1-710 000 parasites/µl) into whole blood. A study of Remoscope's diagnostic accuracy was evaluated in a cohort of 500 individuals in eastern Uganda, comprising 601 unique clinic visits. Parallel measurements of parasitaemia were performed using Remoscope, quantitative polymerase chain reaction (qPCR) and thick blood smears.

Results: Clinically, Remoscope's 10× diluted blood assay had a limit of detection with respect to qPCR of 95.1 parasites/µl, sensitivity of 83%, specificity of 96%, positive predictive value of 91% and negative predictive value of 93%.

Conclusions: Remoscope's speed, accuracy, cost and ease of use address key challenges in malaria diagnosis worldwide. In this pilot study, the diagnostic accuracy approaches that of expert thick smears performed in duplication.

Keywords: AI; diagnostics; global health; label-free; low-cost; malaria.