TY - JOUR
T1 - Deep learning-assisted ultra-accurate smartphone testing of paper-based colorimetric ELISA assays
AU - Duan, Sixuan
AU - Cai, Tianyu
AU - Zhu, Jia
AU - Yang, Xi
AU - Lim, Eng Gee
AU - Huang, Kaizhu
AU - Hoettges, Kai
AU - Zhang, Quan
AU - Fu, Hao
AU - Guo, Qiang
AU - Liu, Xinyu
AU - Yang, Zuming
AU - Song, Pengfei
N1 - Funding Information:
The authors thank the financial support from the programs of Natural Science Foundation of the Jiangsu Higher Education ( 20KJB460024 , 22KJB460033 ), Jiangsu Science and Technology Programme - Young Scholar ( BK2020041995 ), Jiangsu Province High-level Innovation and Entrepreneurship Talent Plan ( 2020–30803 ), XJTLU Key Programme Special Fund – Exploratory Research Programme ( KSF-E-39 ), and XJTLU Research Development Fund ( RDF-18-02-20 ). The authors also acknowledge the financial support from Xi'an Jiaotong – Liverpool University to S. Duan ( PGRS1912019 ).
Publisher Copyright:
© 2023 Elsevier B.V.
PY - 2023/4/1
Y1 - 2023/4/1
N2 - Smartphone has long been considered as one excellent platform for disease screening and diagnosis, especially when combined with microfluidic paper-based analytical devices (μPADs) 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 μPAD 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 μPADs 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 μPADs for use by laypersons in low-resource areas and can be facilely adapted to the real disease protein biomarkers detection by c-ELISA on μPADs.
AB - Smartphone has long been considered as one excellent platform for disease screening and diagnosis, especially when combined with microfluidic paper-based analytical devices (μPADs) 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 μPAD 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 μPADs 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 μPADs for use by laypersons in low-resource areas and can be facilely adapted to the real disease protein biomarkers detection by c-ELISA on μPADs.
KW - Colorimetric enzyme-linked immunosorbent assay
KW - Deep learning
KW - Microfluidic paper-based analytical devices
KW - Smartphone point-of-care testing
UR - http://www.scopus.com/inward/record.url?scp=85147189737&partnerID=8YFLogxK
U2 - 10.1016/j.aca.2023.340868
DO - 10.1016/j.aca.2023.340868
M3 - Article
C2 - 36813452
AN - SCOPUS:85147189737
SN - 0003-2670
VL - 1248
JO - Analytica Chimica Acta
JF - Analytica Chimica Acta
M1 - 340868
ER -