A team of researchers led by professors Peter Lillehoj and Kevin McHugh at Rice University’s George R. Brown School of Engineering and Computing has developed an innovative, AI-enabled, low-cost device that makes flow cytometry more affordable and accessible. This technique, traditionally used to analyze cells or particles in a fluid using a laser beam, is now available in a compact and cost-effective prototype. The device provides rapid results from unpurified blood samples with accuracy comparable to conventional flow cytometers, making it ideal for point-of-care clinical applications, especially in low-resource and rural areas.
Flow cytometry, a cornerstone of medical diagnostics and research since its inception in the 1950s, has been constrained by the high cost and size of conventional devices, limiting its use to specialized laboratories. The Rice University team addressed these limitations by developing a pump-free design, leveraging gravity-based slug flow to reduce both the cost and size of the device. Desh Deepak Dixit and Tyler Graf, graduate students under Lillehoj and McHugh, optimized the microfluidic device to maintain constant fluid velocity, essential for accurate cell analysis.
The device’s second innovation lies in its integration of AI. The researchers trained a convolutional neural network to rapidly and accurately count CD4+ T cells, a critical immune cell type, from unpurified blood samples. This capability is significant for diagnosing and monitoring conditions like HIV/AIDS and COVID-19. The platform technology can be adapted to sort and analyze various cell types using different antibodies, offering broad potential for disease diagnosis and biomedical research.
The research, supported by the National Institutes of Health and Rice University, was published in Microsystems and Nanoengineering. The authors acknowledge the support of the funders but emphasize that the content reflects the authors’ views only.
