As a class of point-of-care (POC) assays with visible distance readout (thermometer style), the electrophoresis titration (ET) biosensor affords high robustness, versatility, and simplicity for point-of-care quantification. However, naked-eye observation of the distance readout is unreliable in POC settings and manual processing of distance readout is time-consuming. Herein, we developed a smartphone-deployable and all-in-one machine vision for four ET biosensors (bovine serum albumin, melamine, uric acid, glutathione) to classify and quantify the samples simultaneously. To ensure accurate and rapid quantification on the smartphone, we customized the decolorization methods and edge detection operators to balance the region of interest (ROI) extraction performance and processing speed. We then established a dataset of 180 distance readout images to endow our machine vision with the ability to classify four sample types. Consequently, our machine vision demonstrated high accuracy in determining the sample type (>97.2%) and concentration (>97.3%). Moreover, expanding its applications to other targets was readily achieved by including distance readout images of other ET biosensors (e.g., hemoglobin A1c) in the dataset. Therefore, our strategy of constructing machine vision is compatible with the versatile ET biosensor technique, suggesting that the same strategy can be used for other thermometer-style POC assays.
Read full abstract