An automated algorithm for the quantification of hCG level in novel fabric-based home pregnancy test kits

Abstract

We report a new image processing algorithm that extracts quantitative information about the concentration of human chorionic gonadotropin (hCG), an important early pregnancy marker, from commercially available qualitative home pregnancy kits. The algorithm could potentially be ported onto a simple camera based cell phone making it a low-cost, portable point-of-care device as opposed to costly and time consuming clinical labs for accurate quantitative determination of hCG. The algorithm takes the image of the test result as input, classifies and determines the hCG concentration based on the RGB intensities of the test line. The efficacy of the algorithm is demonstrated using control samples on commercially available strips as well as novel fabric based strips designed for this application.

An enhanced algorithm for the quantification of human chorionic gonadotropin (hCG) level in commercially available home pregnancy test kits

“…7a says that the classifier correctly classified 98.78% of input points belonging to the 25 mIU/ml class and misclassified 1.12% of the points as belonging to the 0 mIU/ml class. The classification performance is consistently higher than 95% across classes, which is a significant improvement over the previously obtained 80% in [2].…”

“…Recently, there has been growing interest in using low cost imaging devices like mobile phones to quantify such tests at home [2] [3], [4]. The proposed algorithm is an attempt to reduce the cost by using cheap processing power available on mobile devices as opposed to relatively expensive ELISA plate readers or autoanalyzers in identifying the concentration of -hCG and is an extension and improvement over the previous work done by Manasa K. et al [2].…”

“…The proposed algorithm is an attempt to reduce the cost by using cheap processing power available on mobile devices as opposed to relatively expensive ELISA plate readers or autoanalyzers in identifying the concentration of -hCG and is an extension and improvement over the previous work done by Manasa K. et al [2]. Levels of the hormone between 5 mIU/mL and 1000 mIU/mL are relevant for clinical applications.…”

Portable point-of-care diagnostic devices

“…Over the last decade, many innovative approaches to POC diagnostics have been developed utilizing smart phones, nanotechnology, and microuidic technologies. For example, various kinds of glucose meters 17,18 and pregnancy test kits [19][20][21][22] have been developed and have been made commercially available. On the basis of this review, we provide a novel framework to assess examples that we feel have the most potential to make an impact as POC diagnostics in resourcelimited settings.…”