Sickle cell disease, a genetic disorder affecting a sizeable global demographic, manifests in sickle red blood cells (sRBCs) with altered shape and biomechanics. sRBCs show heightened adhesive interactions with inflamed endothelium, triggering painful vascular occlusion events. Numerous studies employ microfluidic-assay-based monitoring tools to quantify characteristics of adhered sRBCs from high resolution channel images. The current image analysis workflow relies on detailed morphological characterization and cell counting by a specially trained worker. This is time and labor intensive, and prone to user bias artifacts. Here we establish a morphology based classification scheme to identify two naturally arising sRBC subpopulations—deformable and non-deformable sRBCs—utilizing novel visual markers that link to underlying cell biomechanical properties and hold promise for clinically relevant insights. We then set up a standardized, reproducible, and fully automated image analysis workflow designed to carry out this classification. This relies on a two part deep neural network architecture that works in tandem for segmentation of channel images and classification of adhered cells into subtypes. Network training utilized an extensive data set of images generated by the SCD BioChip, a microfluidic assay which injects clinical whole blood samples into protein-functionalized microchannels, mimicking physiological conditions in the microvasculature. Here we carried out the assay with the sub-endothelial protein laminin. The machine learning approach segmented the resulting channel images with 99.1±0.3% mean IoU on the validation set across 5 k-folds, classified detected sRBCs with 96.0±0.3% mean accuracy on the validation set across 5 k-folds, and matched trained personnel in overall characterization of whole channel images with R2 = 0.992, 0.987 and 0.834 for total, deformable and non-deformable sRBC counts respectively. Average analysis time per channel image was also improved by two orders of magnitude (∼ 2 minutes vs ∼ 2-3 hours) over manual characterization. Finally, the network results show an order of magnitude less variance in counts on repeat trials than humans. This kind of standardization is a prerequisite for the viability of any diagnostic technology, making our system suitable for affordable and high throughput disease monitoring.

AbstractSickle cell disease (SCD), a group of inherited blood disorders with significant morbidity and early mortality, affects a sizeable global demographic largely of African and Indian descent. It is manifested in a mutated form of hemoglobin that distorts the red blood cells into a characteristic sickle shape with altered biophysical properties. Sickle red blood cells (sRBCs) show heightened adhesive interactions with inflamed endothelium, triggering obstruction of blood vessels and painful vaso-occlusive crisis events. Numerous studies have reported microfluidic-assay-based disease monitoring tools which rely on quantifying adhesion characteristics of adhered sRBCs from high resolution channel images. The current workflow for analyzing images from these assays relies on manual cell counting and detailed morphological characterization by a specially trained worker, which is time and labor intensive. Moreover manual counts by different individuals are prone to artifacts due to user bias. We present here a standardized and reproducible image analysis workflow designed to tackle these issues, using a two part deep neural network architecture that works in tandem for automatic, fast and reliable segmentation and classification into subtypes of adhered cell images. Our training utilized an exhaustive data set of images generated by the SCD BioChip, a microfluidic assay which injects clinical whole blood samples into protein-functionalized microchannels, mimicking physiological conditions in the microvasculature. The automated image analysis performs robustly in comparison to human classification: accuracies were similar to or better than those of the trained personnel, while the overall analysis time was improved by two orders of magnitude.

No abstract