Deep Learning-Assisted Label-Free Parallel Cell Sorting with Digital Microfluidics.

Abstract

Sorting specific cells from heterogeneous samples is important for research and clinical applications. In this work, a novel label-free cell sorting method is presented that integrates deep learning image recognition with microfluidic manipulation to differentiate cells based on morphology. Using an Active-Matrix Digital Microfluidics (AM-DMF) platform, the YOLOv8 object detection model ensures precise droplet classification, and the Safe Interval Path Planning algorithm manages multi-target, collision-free droplet path planning. Simulations and experiments revealed that detection model precision, concentration ratios, and sorting cycles significantly affect recovery rates and purity. With HeLa cells and polystyrene beads as samples, the method achieved 98.5% sorting precision, 96.49% purity, and an 80% recovery over three cycles. After a series of experimental validations, this method can also be used to sort HeLa cells from red blood cells, cancer cells from white blood cells (represented by HeLa and Jurkat cells), and differentiate white blood cell subtypes (represented by HL-60 cells and Jurkat cells). Cells sorted using this method can be lysed directly on chip within their hosting droplets, ensuring minimal sample loss and suitability for downstream bioanalysis. This innovative AM-DMF cell sorting technique holds significant potential to advance diagnostics, therapeutics, and fundamental research in cell biology.