Rapidly adaptable automated interpretation of point-of-care COVID-19 diagnostics

Abstract

Background Point-of-care diagnostic devices, such as lateral-flow assays, are becoming widely used by the public. However, efforts to ensure correct assay operation and result interpretation rely on hardware that cannot be easily scaled or image processing approaches requiring large training datasets, necessitating large numbers of tests and expert labeling with validated specimens for every new test kit format. Methods We developed a software architecture called AutoAdapt POC that integrates automated membrane extraction, self-supervised learning, and few-shot learning to automate the interpretation of POC diagnostic tests using smartphone cameras in a scalable manner. A base model pre-trained on a single LFA kit is adapted to five different COVID-19 tests (three antigen, two antibody) using just 20 labeled images. Results Here we show AutoAdapt POC to yield 99% to 100% accuracy over 726 tests (350 positive, 376 negative). In a COVID-19 drive-through study with 74 untrained users self-testing, 98% found image collection easy, and the rapidly adapted models achieved classification accuracies of 100% on both COVID-19 antigen and antibody test kits. Compared with traditional visual interpretation on 105 test kit results, the algorithm correctly identified 100% of images; without a false negative as interpreted by experts. Finally, compared to a traditional convolutional neural network trained on an HIV test kit, the algorithm showed high accuracy while requiring only 1/50th of the training images. Conclusions The study demonstrates how rapid domain adaptation in machine learning can provide quality assurance, linkage to care, and public health tracking for untrained users across diverse POC diagnostic tests.

Measuring the performance of computer vision artificial intelligence to interpret images of HIV self-testing results

“…Using machine learning, an AI algorithm can be trained on a set of images of completed tests (all of the same brand) to recognize line patterns for positive and negative results; thereafter, when fed an image of a completed test of that same brand, the AI algorithm can make a determination about (i.e., interpret) the test result. Published examples of this use case largely focus on rapid tests for COVID-19 (25)(26)(27)(28)(29)(30), with a handful of examples from malaria (31), influenza (32), Cryptococcosis fungal infection (33), and HIV (34). The HIV example comes from Turbé et al (34), who trained an AI algorithm using 11,374 images of two brands of HIV RDTs: ABON HIV 1/2/O Tri-Line HIV RDT [ABON Biopharm (Hangzhou) Co., Ltd.,] and Advanced Quality One Step Anti-HIV (1&2) Tri-line Test (InTec PRODUCTS, INC.).…”