| Title | The use of machine learning in diagnosis of visceral leishmaniasis. |
|---|---|
| Supervisors | not found cdes10 Crawford Revie |
| Research Area | |
| Description | Leishmaniasis is a serious health threat. Diagnosis can be completed using different techniques but the gold standard is identifying parasites in stained samples from infected individuals. In this project we will look at using machine learning in parasite diagnosis. Visceral leishmaniasis is a disease which causes considerable morbidity and mortality (1). Diagnosis can be carried out using molecular or immunological technique but the gold standard is identifying parasites in stained samples from infected individuals (2), which requires specialist training. However, it is now possible to train a computer to identify images using machine learning (3). In this project we will determine whether we can use machine learning to identify parasites in stained samples. We will also relate parasite burdens to specific antibody levels, using samples from Leishmania donovani infected hamsters. This project will be carried out in collaboration with Professor Revie (Department of Computing and Information Science). This project will be an excellent introduction to machine learning and how it can be used in clinical studies. The student on this project would be trained in a number of techniques including culture of parasites, use of IVIS imaging equipment, in vivo animal experiments, assessment of parasite burdens, analysis and presentation of data, and machine learning |
| Techniques Used | Tissue culture, parasite maintenance IVIS imaging, computer science, machine learning |
| References | 1. Sundar S, Singh OP, Chakravarty J. Visceral leishmaniasis elimination targets in India, strategies for preventing resurgence. Expert Rev Anti Infect Ther. 2018, 16:805-812. 2. van Griensven J, Diro E. Visceral Leishmaniasis: Recent Advances in Diagnostics and Treatment Regimens. Infect Dis Clin North Am. 2019, 3:79-99. 3. Xu J, Xue K, Zhang K. Current status and future trends of clinical diagnoses via image-based deep learning. Theranostics. 2019, 9:7556-7565. |
| Conditions | Applicants should possess or be about to obtain a 1st class or 2:1 Honours degree or equivalent in a relevant discipline in addition to receipt of satisfactory references and an IELTS score of 6.5 where appropriate. |
| Bench Fee | Running costs of £10000 p.a. will be associated with this project in addition to University tuition fees. |
| Suitable For | This is a multi-disciplinary project and would be good training for a student |
| Apply Now |