Smartphone Assay Reading via Low-Variance Intensity Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for reading lateral flow tests (LFTs) using smartphones are inconsistent due to variations in imaging hardware, requiring accessories or hardware modifications, and fail to account for angular orientation and lighting conditions, leading to inaccurate results, especially in point-of-care settings.
Innovation Solution
A method that captures multiple images of the LFT under varying conditions, groups pixel intensity values into clusters, selects the cluster with the smallest variance, and calculates the mean intensity value to ensure accuracy without additional hardware, using algorithms like HDR processing and convolutional neural networks to extract and process the region of interest.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If benchtop lateral-flow readers are used to ensure consistent imaging conditions, then measurement precision is improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent creates a digital copy of the reference imaging pattern and embeds it within the assay device itself. This reference pattern serves as a built-in calibration standard that can be captured simultaneously with the test region, eliminating the need for separate calibration procedures and complex external reference standards while maintaining measurement consistency across different smartphone devices
Solution Approach 2:
The patent introduces a reference imaging pattern as an intermediary element that mediates between the variable imaging conditions and the test region. This reference pattern captures the actual lighting and imaging conditions present during each test, serving as a proxy that allows the system to compensate for environmental variations without requiring controlled conditions or complex hardware
2Measurement precision
If accessories or hardware modifications are added to smartphones to control imaging conditions, then measurement precision is improved, but ease of operation and accessibility deteriorate
Solution Approach 1:
The assay device performs self-calibration by containing its own reference imaging pattern. The system automatically captures both the test region and reference pattern, then uses the reference pattern to compensate for imaging conditions without requiring user intervention for calibration or setup. This makes the device as easy to use as simply capturing an image with a smartphone camera
Solution Approach 2:
The patent merges the reference standard and the test assay into a single integrated device. The reference imaging pattern is printed on the same substrate as the test region, allowing both to be captured in a single image. This integration eliminates the need for separate calibration tools or accessories, enabling use with any smartphone without additional hardware
3Measurement precision
If multiple images are captured under varying conditions, then accuracy is improved through averaging, but loss of time increases due to multiple captures
Solution Approach 1:
The patent employs periodic capture of multiple images at different exposure settings (multiple snapshots with varying exposure times). By capturing several images rapidly with different exposure parameters and then selecting or averaging the best results, the system achieves robust measurements that are resistant to transient artifacts while maintaining rapid overall test completion
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for reading a test region of an assay, the method comprising: capturing a plurality of images of an assay with an imaging device; from each image of the plurality of images, extracting a region of interest comprising pixels of the image associated with a test region of the assay; from each extracted region of interest, estimating respective intensity values of at least a portion of the pixels; grouping the estimated intensity values into one or more clusters, said grouping comprising determining a total number of intensity values grouped into each cluster and a variance of each cluster; selecting the cluster having a total number of intensity values at or above a predetermined threshold and a smallest variance; calculating a mean intensity value of the selected cluster; and outputting the calculated mean intensity value as a result of the assay.