Analyte Quantity Detection from Lateral Flow Assay Using a Smartphone.

Area of Science:

• Biochemistry
• Biomedical Engineering
• Analytical Chemistry

Background:

• Conventional laboratory tests are complex, costly, and time-consuming.
• Lateral flow assay (LFA) technology offers a simple, rapid, and low-cost alternative.
• There is a need for accurate and robust analyte quantification methods using LFA.

Purpose of the Study:

• To develop a robust smartphone-based method for quantifying analytes on LFA strips.
• To achieve high estimation accuracy under diverse illumination conditions without extra equipment.
• To leverage image processing and machine learning for improved LFA analysis.

Main Methods:

• A smartphone camera was used to capture images of LFA strips.
• Novel image processing and machine learning techniques were employed for analysis.
• Linear regression approximated analyte quantity, followed by Support Vector Machine (SVM) classification.

Main Results:

• The method demonstrated high accuracy in estimating albumin protein quantities on LFA strips.
• The smartphone application achieved 98% average accuracy in detecting albumin protein in real-time.
• The technique proved robust under various illumination conditions.

Conclusions:

• The proposed smartphone-based method offers a simple, accurate, and rapid solution for LFA analyte detection.
• This approach enhances the utility of LFA technology for biochemical analysis.
• The method has significant potential for point-of-care diagnostics and field testing.