Postgraduate research project

Using machine learning to evaluate atomic force microscopy nanoindentation data

Funding
Fully funded (UK and international)
Type of degree
Doctor of Philosophy
Entry requirements
UK 2:1 honours degree View full entry requirements
Faculty graduate school
Faculty of Engineering and Physical Sciences
Closing date

About the project

The University is expanding its PhD research in the area of medical data analysis. We aim to implement machine learning to analyse atomic force microscopy nanoindentation data towards automated diagnosis of cancer biopsies. 

In addition to the research project outlined below you will receive substantial training in scientific, technical, and commercial skills.

We have developed a new method based on atomic force microscopy (AFM), named indentation-type atomic force microscopy (IT-AFM), suitable for diagnostics of osteoarthritis, cancer, and atherosclerosis. The method represents a breakthrough in diagnostics and therapy, and allows for the diagnosis of structural and functional changes in tissue-related conditions, at the nanometre scale.

We have published a paper in Bioengineering that describes the aim of the project. Read The Revolution in Breast Cancer Diagnostics: From Visual Inspection of Histopathology Slides to Using Desktop Tissue Analysers for Automated Nanomechanical Profiling of Tumours.

We are convinced that diagnostic errors, which are leading to the death of thousands of patients in the UK every year, can be significantly reduced by employing the IT-AFM technology. We started to make a new generation of desktop tissue analysers to allow cancer surgeons to make better decisions. Towards bringing the IT-AFM technology to clinical applications the analysis of force-curves needs to be automated, fast requiring the implementation of machine learning techniques. 

We have hundreds of force-maps that have been monitored by IT-AFM on normal and osteoarthritic articular cartilage that are the basis for the above and other papers. In a first step, we want to re-do the analysis of force-maps but now using machine learning to then compare the results with previous conventional data analysis. We aim to learn about the advantages and limitations of such AI-approach.

The project will help you to develop skills and expertise in tool development, atomic force microscopy, mechanobiology.