Deep learning-assisted ultra-accurate smartphone testing of paper-based colorimetric ELISA assays

Smartphone has long been considered as one excellent platform for disease screening and diagnosis, especially when combined with microfluidic paper-based analytical devices (mu PADs) that feature low cost, ease of use, and pump-free operations. In this paper, we report a deep learning-assisted smartphone platform for ultra-accurate testing of paper-based microfluidic colorimetric enzyme-linked immunosorbent assay (c-ELISA). Different from existing smartphone-based mu PAD platforms, whose sensing reliability is suffered from uncontrolled ambient lighting conditions, our platform is able to eliminate those random lighting influences for enhanced sensing accuracy. We first constructed a dataset that contains c-ELISA results (n = 2048) of rabbit IgG as the model target on mu PADs under eight controlled lighting conditions. Those images are then used to train four different mainstream deep learning algorithms. By training with these images, the deep learning algorithms can well eliminate the influences of lighting conditions. Among them, the GoogLeNet algorithm gives the highest accuracy (>97%) in quantitative rabbit IgG concentration classification/prediction, which also provides 4% higher area under curve (AUC) value than that of the traditional curve fitting results analysis method. In addition, we fully automate the whole sensing process and achieve the image in, answer out to maximize the convenience of the smartphone. A simple and user-friendly smartphone application has been developed that controls the whole process. This newly developed platform further enhances the sensing performance of mu PADs for use by laypersons in low-resource areas and can be facilely adapted to the real disease protein biomarkers detection by c-ELISA on mu PADs.

Automated summary

This paper presents a smartphone platform assisted by deep learning for ultra-accurate testing of paper-based microfluidic colorimetric enzyme-linked immunosorbent assay (c-ELISA). The platform eliminates the influences of random lighting conditions and achieves high accuracy in classifying/predicting the concentration of rabbit IgG. A user-friendly smartphone application has been developed to fully automate the sensing process.