Quantifying the deformability of malaria-infected red blood cells using deep learning trained on synthetic cells

Daniel T Rademaker; Joshua J Koopmans; Gwendolyn M S M Thyen; Aigars Piruska; Wilhelm T S Huck; Gert Vriend; Peter A C 't Hoen; Taco W A Kooij; Martijn A Huynen; Nicholas I Proellochs

doi:10.1016/j.isci.2023.108542

Quantifying the deformability of malaria-infected red blood cells using deep learning trained on synthetic cells

iScience. 2023 Nov 23;26(12):108542. doi: 10.1016/j.isci.2023.108542. eCollection 2023 Dec 15.

Affiliations

¹ Medical BioSciences, Radboud University Medical Center, 6525 GA Nijmegen, the Netherlands.
² Radboud Center for Infectious Diseases, Medical Microbiology, Radboud University Medical Center, 6525 GA Nijmegen, the Netherlands.
³ Institute for Molecules and Materials, Radboud University, 6525 AJ Nijmegen, the Netherlands.
⁴ Baco Institute for Protein Science, Mindoro 5201, Philippines.

Abstract

Several hematologic diseases, including malaria, diabetes, and sickle cell anemia, result in a reduced red blood cell deformability. This deformability can be measured using a microfluidic device with channels of varying width. Nevertheless, it is challenging to algorithmically recognize large numbers of red blood cells and quantify their deformability from image data. Deep learning has become the method of choice to handle noisy and complex image data. However, it requires a significant amount of labeled data to train the neural networks. By creating images of cells and mimicking noise and plasticity in those images, we generate synthetic data to train a network to detect and segment red blood cells from video-recordings, without the need for manually annotated labels. Using this new method, we uncover significant differences between the deformability of RBCs infected with different strains of Plasmodium falciparum, providing clues to the variation in virulence of these strains.

Keywords: Biological sciences; Biotechnology; Computer science.