PATH Diagnostic Data Repository

Related program: Diagnostics

Global rapid diagnostic test image database to support the development of connected diagnostics for low-resource settings.

Access to reliable, complete, and ethically sourced diagnostic data is a key challenge to developing high-quality digital health technologies for low-resource settings. PATH has created a scalable, user-friendly, and secure library of rapid diagnostic test (RDT) images and related metadata to support and accelerate the development and validation of digital diagnostics. This diagnostic image repository can be made available to diagnostic developers demonstrating commercial efforts to support health needs in low-resource settings.

This information can enable our partners to develop diagnostic technologies such as digital readers and machine learning algorithms that support test result interpretation (i.e., controlled images taken under varying conditions can be used to train computer vision models) and digital connectivity to improve access and the quality of appropriate, integrated diagnostic systems in LMICs.

The PATH Diagnostic Image Repository is housed on a Microsoft SharePoint platform with carefully managed permissions and access controls. Users can access, export, and leverage diagnostic datasets while maintaining privacy and standards. Currently, the repository offers images of COVID-19 and HIV RDTs, with additional disease areas and diagnostic technologies open to review for future expansion.

The COVID-19 dataset currently contains over 40,000 images and associated metadata. This also includes a library of 24,000 images for training machine learning algorithms and approximately 8,000 images for algorithm validation. These images represent a variety of conditions with over a dozen attributes, such as defined lighting conditions, sample concentrations, and backgrounds. Images were taken using mobile devices and conditions chosen to address developer needs and mimic real-world usage of diagnostic tests in low-resource settings.

The HIV dataset contains 12,000 images, each with an accompanying annotation file containing 12 attributes.

To access the repository, please complete this Image Repository Access Request Form. Requests will be reviewed focusing on global access commitments that must be confirmed before access is provided.

Please email dximagerepo@path.org with questions, comments, or feedback. PATH is open to additional funding and collaboration opportunities to support this work further.