Automated laboratory diagnostics

Although microscopes are common in Uganda and other developing countries, a shortage of lab technicians to operate them means that access to quality diagnostic services is limited for much of the population. This leads to misdiagnoses of disease, which in turn causes life-threatening conditions to be incorrectly treated, drug resistance, and the economic burden of buying unecessary drugs. Even where health facilities have lab technicians, they are often oversubscribed and have difficulty spending enough time on each sample to give a confident diagnosis.

Given that smartphones are widely owned across the developing world, there is a technological opportunity to address this problem: phones can be used to capture and process microscopy images. This project aims to produce a functioning point-of-care diagnosis system on this principle, capable of running on multiple microscope and phone combinations. Our work exploits recent technological advances in 3D printing and deep learning to produce effective hardware and software respectively. The diagnostic challenges being focussed on are malaria (in blood samples), tuberculosis (in sputum samples) and intestinal parasites (in stool samples).


Additive manufacturing, or 3D printing, provides an opportunity to create one-off customised 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, and allows rapid prototyping capabilities and easy repair. 3D shapefiles for printing the adapter

  • Current 3D-printed smartphone/microscope adapter design
  • Image capture in progress at Mulago National Referral Hospital

This hardware on its own has various applications beyond point-of-care diagnostics, including telemedicine, teaching, and the archival of images used for diagnosis (useful for later verification).

The sample images below were captured using our experimental setup:

  • Tuberculosis bacilli
  • Taenia egg


The software component of our work is to train machine learning methods to recognise different pathogen objects, and to test usability at the point of care. Deep learning methods for object detection have allowed us to improve the speed and accuracy of diagnosis compared to previous alternatives.

  • Detection of plasmodium falciparum in thick blood smear image.
  • Detection of tuberculosis bacilli in sputum sample.
December 2016

Complete files accompanying the convolutional networks paper are now available online, including annotated images captured using the smartphone adapter setup shown above, hardware specifications and source code.

If making use of these resources, please cite the paper below.

August 2016

Our paper in Machine Learning in Health Care extends the results on deep convolutional networks to tuberculosis and intestinal parasite detection, and using exclusively images captured by smartphone.

  • J.A. Quinn, R. Nakasi, P.K. Mugagga, P. Byanyima, W. Lubega, A. Andama. Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics. Proceedings of the International Conference on Machine Learning for Health Care, Journal of Machine Learning Research W&C track, Volume 56, 2016.
September 2015

Carlos Sánchez Sánchez, supervised by Chris Williams, has completed his MSc thesis on plasmodium detection, showing that Deep Convolutional Networks give significant accuracy increases for plasmodium detection over the previous methodology.

  • C. Sánchez Sánchez. Deep Learning for Identifying Malaria Parasites in Images, MSc thesis, University of Edinburgh, 2015.
December 2014

A complete reference system for malaria detection, with object detection based on morphological image features, can be downloaded:

Please cite the following paper if making use of this code or data:

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.


Core Team:

External collaborators:

Funded by Grand Challenges Canada, under the Stars in Global Health progam.