Systems and methods of validation of rapid test device results
Inventors
Needham, James William • Abe, Koji
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12014490-B2
Publication Date
2024-06-18
Expiration Date
Abstract
Embodiments are directed to use of a rapid-test-validation computing device to determine if a result of a rapid test device is valid and identify the result. The rapid-test-validation computing device captures images of the rapid test device and employs a first artificial intelligence mechanism to determine if the rapid test device is properly aligned in the images. The rapid-test-validation computing device then employs a second artificial intelligence mechanism to determine if a result of the rapid test device is valid or invalid. If the result is valid, the rapid-test-validation computing device employs a third artificial intelligence mechanism to determine and present an objective output of the rapid test device result to a user; otherwise, the rapid-test-validation computing device presents a notification to the user that the rapid test device result is invalid.
Core Innovation
The invention relates to an AI-enabled rapid-test-validation workflow that reads a rapid test device by obtaining one or more first images and overlaying a semi-transparent reference of the rapid test device on the one or more first images. The workflow presents the one or more overlaid images to a user in real time as the one or more first images are being obtained, enabling user-visible alignment relative to the semi-transparent reference.
A first artificial intelligence mechanism determines a position of the rapid test device in the one or more first images relative to the semi-transparent reference in response to identification of the rapid test device. When the position is in an acceptable position relative to the semi-transparent reference in at least one of the one or more first images, the system captures a second image and uses a second artificial intelligence mechanism to determine if a result of the rapid test device is valid, and to classify valid or invalid test results.
If the result is invalid, the workflow presents an invalid-test-result notification to the user, and if the result is valid, a third artificial intelligence mechanism determines an objective characteristic of the result of the rapid test device. The objective characteristic is classified as possible objective characteristics output by the rapid test device, and the workflow presents the objective characteristic of the result to the user. The computing device and/or stored instructions further support identifier-based timing and color-validation using a color validation sheet with threshold-based checks prior to obtaining the rapid test-device images.
Claims Coverage
The independent claims cover three main elements: a method for image-based rapid-test validation with AI-based positioning, validity classification, and objective characterization; a rapid-test-validation computing device that performs the same workflow; and a nontransitory processor-readable storage medium that causes a rapid-test-validation computing device to perform a timed, AI-based validity and objective-characteristic determination workflow. Across these independent claims, the inventive features include semi-transparent device overlay and real-time presentation, position acceptance gating using a first AI mechanism, validity/invalid classification using a second AI mechanism, objective-characteristic determination using a third AI mechanism, and a user-notified output for invalid and valid cases.
Semi-transparent reference overlay and real-time presentation
Overlaying a semi-transparent reference of the rapid test device on the one or more first images; presenting the one or more overlaid images to a user in real time as the one or more first images are being obtained.
AI-based acceptable position determination relative to the overlay reference
Employing a first artificial intelligence mechanism to determine a position of the rapid test device in the one or more first images relative to the semi-transparent reference in response to identification of the rapid test device; responsive to the position of the rapid test device being in an acceptable position relative to the semi-transparent reference in at least one of the one or more first images.
AI-based validity classification with invalid-test-result notification
Employing a second artificial intelligence mechanism on the second image to determine if a result of the rapid test device is valid, wherein the second artificial intelligence mechanism is trained to classify valid or invalid test results output by the rapid test device; responsive to the result of the rapid test device being invalid, presenting an invalid-test-result notification to the user.
AI-based objective characteristic determination for valid results
Responsive to the result of the rapid test device being valid, employing a third artificial intelligence mechanism on the second image to determine an objective characteristic of the result of the rapid test device, wherein the third artificial intelligence mechanism is trained to classify possible objective characteristics output by the rapid test device; and presenting the objective characteristic of the result to the user.
Identifier-based timing gating before obtaining the rapid test device image
Capturing a second image of an identifier of the rapid test device; initiating a tinier associated with the rapid test device based on the identifier; and in response to expiration of the tinier, obtaining the image of the rapid test device; employing a first artificial intelligence mechanism on the image to determine if a result of the rapid test device is valid.
The independent claims collectively cover AI-driven rapid-test validation in which semi-transparent overlay and real-time user presentation support alignment, a first AI mechanism determines acceptable device position relative to the overlay, a second AI mechanism classifies results as valid or invalid with an invalid-test-result notification, and when valid, a third AI mechanism determines and presents an objective characteristic. The independent claims also include identifier-based timing gating prior to obtaining the rapid test device image, followed by AI-based validity and objective-characteristic determination.
Stated Advantages
Provides an invalid-test-result notification to the user when the rapid test result is invalid.
Presents an objective characteristic of the result of the rapid test device to the user when the rapid test result is valid.
Enables real-time presentation of one or more overlaid images of the rapid test device relative to a semi-transparent reference during image acquisition.
Documented Applications
AI-enabled rapid-test-validation of rapid test devices using image capture, AI-based device position determination, AI-based validity classification, and AI-based objective result characterization for user presentation.
Interested in licensing this patent?