Application of machine learning in a rodent malaria model for rapid, accurate, and consistent parasite counts

Abstract

AbstractRodent malaria models serve as important preclinical antimalarial and vaccine testing tools. Evaluating treatment outcomes in these models often requires manually counting parasite-infected red blood cells (iRBCs), a time-consuming process, which can be inconsistent between individuals and labs. We have developed an easy-to-use machine learning (ML)-based software, Malaria Screener R, to expedite and standardize such studies by automating the counting ofPlasmodiumiRBCs in rodents. This software can process Giemsa-stained blood smear images captured by any camera-equipped microscope. It features an intuitive graphical user interface that facilitates image processing and visualization of the results. The software has been developed as a desktop application that processes images on standard Windows and Mac OS computers. A previous ML model created by the authors designed to countP. falciparum-infected human RBCs did not perform well countingPlasmodium-infected mouse RBCs. We leveraged that model by loading the pre-trained weights and training the algorithm with newly collected data to targetP. yoeliiandP. bergheimouse iRBCs. This new model reliably measured bothP. yoeliiandP. bergheiparasitemia (R2= 0.9916). Additional rounds of training data to incorporate variances due to length of Giemsa staining, microscopes etc, have produced a generalizable model, meeting WHO Competency Level 1 for the sub-category of parasite counting using independent microscopes. Reliable, automated analyses of blood-stage parasitemia will facilitate rapid and consistent evaluation of novel vaccines and antimalarials across labs in an easily accessiblein vivomalaria model.