Data for: Assessing Red Blood Cell Deformability from Microscopy Images Using Deep Learning

Abstract: Red blood cell (RBC) deformability is a key biophysical property that enables their navigation through small spaces in the microvasculature. The loss of RBC deformability can be due to pathology, natural ageing, or storage, and can impede proper cell function. Established methods to assess RBC deformability require specialized equipment, long measurement time, and skilled personnel. To address this, we used a deep learning image classification approach to differentiate between softer and harder RBCs. Ground truth deformability assessment was conducted using a microfluidic ratchet sorting device. After microfluidic deformability sorting, cells were imaged in brightfield at 40X magnification. Our model predicted individual RBC deformability with 81 ± 11% accuracy averaged across ten donors. This produced RBC deformability assessments within 10.4 ± 6.8% of the value obtained using the microfluidic device. Measuring RBC deformability using imaging is desirable as it only requires a standard imaging microscope, expanding its accessibility to clinics or research groups where this evaluation would otherwise not be feasible. Technical Information: 40X brightfield microscopy images of red blood cells in a 96-well imaging plate. Full well image scans were conducted using a DS-Qi2 camera on a Nikon Ti-2E inverted microscope, capturing images of 2424 x 2424 pixels.