Detailed malaria diagnostics with intelligent microscopy

The best way to diagnose malaria remains microscopic examination of blood smears, to identify the plasmodium parasites that are responsible. This takes around 30 minutes of microscopy, done by a trained technician - skilled workers who are in short supply. This project will create an intelligent microscope that can greatly multiply the skills of a technician by scanning over the smears automatically, and allowing them to review only the suspicious blood cells on a tablet computer after the smear has been scanned.

Malaria is one of the world's most prevalent infectious diseases. It affects 200 million per year, and causes around 400 thousand deaths - most of them children in ODA countries in sub-Saharan Africa. Impressive progress is being made in reducing the incidence of malaria, which makes good diagnosis of the condition ever more important; it is increasingly inaccurate to assume that every patient with a fever has malaria, and doing so will waste drugs and leave potentially life threatening fevers untreated.

The key to reliable, useful diagnosis with an automated microscope lies in computer vision; simply acquiring digital images and tiling them together into a digital smear is an important first step, but robust analysis of the digital images means the technician need not sift through many images of healthy cells. Instead, they can concentrate their efforts on parts of the image where the algorithm identified suspicious features. Once trained, our algorithm will be able to identify many parasites, only asking for the technician's opinion in challenging, ambiguous cases when it could not identify objects with certainty. Fully automated counts of healthy and infected cells will then allow consistent quantification of test results, informing the clinician prescribing treatment and aiding in disease monitoring.

Analysis of medical images raises fundamental issues with the standard "deep learning" approach of training a multi-layer neural network on hundreds of thousands of images. Such algorithms cannot accurately quantify their uncertainty (i.e. flag up when a diagnosis may be inaccurate), nor describe the reasoning that led to a given classification for an image. They require extremely large training datasets, which must often be labelled by hand. We will build a generative probabilistic model which, while not feasible in most applications due to the huge range of objects that might conceivably be found in a photograph, is possible in the relatively controlled imaging environment of a microscope. This will allow us to give a probabilistic verdict on each cell, and highlight cells that couldn't be reliably classified as healthy, infected, or something else. The generative model will also be able to identify features that led to a classification, for example highlighting infected cells in a large image of a smear. Both of these features will enable greater trust in the algorithm, and allow it to be used to support, rather than replace, existing clinical staff as well as collecting images that will allow us to improve the algorithm's performance.

Computer vision is a powerful technique, but it requires high-resolution digital representations of blood smears in order to work. Our project therefore has a hardware component, where we will build on our earlier work with the OpenFlexure Microscope to create a slide-scanning instrument, capable of digitising blood smears in the field. This instrument will use low cost components and desktop digital manufacturing, so that it can be produced locally - freeing clinics from expensive international supply chains, and creating opportunities for local entrepreneurs that build valuable engineering and design skills. We have already trialled this approach with the first version of the microscope, which will shortly be available for purchase in Tanzania and Kenya, and we hope to achieve an even greater impact with a fully automated instrument.

The ultimate beneficiaries of this work will be patients in sub-Saharan Africa, who will have faster, more reliable malaria diagnosis available to them and thus receive better healthcare - particularly as progress is made in lowering the incidence of the disease. This benefit will come through healthcare professionals, particularly technicians, who are able to treat and diagnose more patients thanks to assistance in blood smear analysis from the software and hardware instrument we will develop in this project. By replacing time-consuming manual microscopy with automated microscopy, and subsequent review of samples on a screen, we will not only multiply the skills of trained technicians, but make it much easier for trainee technicians to learn the features to look for when analysing a blood smear. Sharing a screen is far easier than observing the same sample through microscope eyepieces, and images displayed on-screen are much easier to compare with reference images than microscope slides viewed through eyepieces.

By working with Ifakara Health Institute, a Tanzanian research organisation, we ensure that our research can be immediately used to help certify a medical device in Tanzania; IHI have an ongoing relationship with the national standards bodies NIMR and TFDA and are familiar with the approval process. We have also carefully considered how our improved method will gain acceptance by medical technicians - by improving their existing practice rather than replacing it with a totally new method, or replacing the technician with a machine, we enhance their jobs rather than remove them. The instrument will be able to explain its results, highlighting parasites, eliminating healthy cells, and flagging areas where it cannot classify a feature. These difficult areas can be reviewed by a trained technician, ensuring the instrument does not give unreliable diagnoses and allowing us to collect useful images to improve future versions of the algorithm.

Our strategy of creating locally manufacturable instruments will also benefit local engineers, technicians and entrepreneurs. Releasing our designs open source, and making extensive use of digital manufacturing techniques such as 3D printing, enables high quality automated microscopes to be brought to market in ODA nations without relying on expensive imports, or the legal and financial complications resulting from patents. By moving as much as possible of the commercialisation process to Tanzania, we can bring a product to market faster and with less capital. We also ensure that local entrepreneurs adapt and market the instrument to meet local needs, and that there is an after-sale support network that does not rely on expensive international shipping. Through the Tech for Trade network, we will be able to quickly grow the number of countries where this technology is produced, and we have included budget for some initial work in Kenya.

We are also committed to public engagement in the UK, and our use of low cost hardware lends itself to workshops and exhibitions from school age to adults. We will attend science festivals, such as the Bath Taps into Science festival, as well as working with other groups to run workshops around our open source designs. We are also working with the Raspberry Pi foundation to create teaching materials related to computer-controlled microscopy, joining up ICT, Physics and Biology and bringing school lab technology up to date with modern developments.