Automated laboratory diagnostics

Linkair.ug

Work with Alfred Andama (College of Health Sciences, Makerere University), Fred Kiwanuka (College of Computing and Information Sciences, Makerere University), Kenan Pollack (Omusono Labs).

Recent innovations in mobile phone camera-based microscopy have opened up an entirely new way to diagnose infectious diseases remotely. We propose to build and distribute a durable microscope imaging system which allows automated lab testing to be carried out with existing microscopes and smartphones. This system has two components, hardware and software. The hardware component is to prototype adapters that can be used with many models of smartphone. This adapter should enable any medical clinic equipped with a microscope to easily capture and transmit images.

Additive manufacturing, or 3D printing, provides an opportunity to create one-off customized adapters for any cameraphone and microscope combination, as long as we know the geometry of each. It also dramatically reduces the development costs for new products, allows rapid prototyping capabilities and easy repair. The software component is to apply recent advances in medical imaging and computer vision in order to automate various diagnosis tasks, such as the detection of plasmodium or tryapanosomes in blood samples, or ova and parasite detection in stool samples. In principle, any microscopical lab test can be automated, leading long term to a “lab-on- a-phone”.

J.A. Quinn, A. Andama, I. Munabi, F.N. Kiwanuka. Automated Blood Smear Analysis for Mobile Malaria Diagnosis. Chapter in Mobile Point-of-Care Monitors and Diagnostic Device Design, eds. W. Karlen and K. Iniewski, CRC Press, 2014. pdf

M. Mubangizi, C. Ikae, A. Spiliopoulou, J.A. Quinn. Coupling Spatiotemporal Disease Modeling with Diagnosis. Conference of the Association for the Advancement of Artificial Intelligence (AAAI), 2012. pdf

Image collection in Mulago National Referral Hospital, with 3D printed smartphone adapter mounted on Olympus microscope.
Image collection in Mulago National Referral Hospital, with 3D printed smartphone adapter mounted on Olympus microscope.
Tuberculosis organisms imaged with the hardware adapter above and a Samsung Galaxy phone.
Tuberculosis organisms imaged with the equipment setup above and a Samsung Galaxy phone.
Detection of malaria parasites in images with deep learning methods.
Detection of malaria parasites in a thick blood smear image with deep learning methods.
Part for microscope imaging adapter being 3D printed in the Makerere AI lab
Part for microscope imaging adapter being manufactured in the Makerere AI lab