A new machine-learning technique lights up field microscopy images, detecting white blood cells and rare circulating tumor cells (CTCs) in a patient's blood sample, according to a study published July 22 in Scientific Reports.
This method analyzes the presence of CTCs with an overall accuracy of about 89% in patient blood samples and 97% in cultured cells, according to the findings.
Researchers collected the blood samples using a commercial enrichment kit and a microfluidic device that they developed to catch and release CTCs. The team also is developing a device that combines optical image machine learning and acoustic sorting to automatically process the sample.
This label-free method for detecting these cells may be a breakthrough considering CellSearch is the only U.S. Food and Drug Administration-approved method for CTC detection.
