To be considered for the project, candidates must:
- Possess an Upper second (2.1) UK BEng Honours or MEng degree in a relevant engineering or physics related subject
- Have skills and understanding of Matlab data analysis
- Be a UK or eligible EU national and adhere to Research Council (RCUK) eligibility criteria
Expertise in experimental research in signal analysis would also be preferable.
Eligibility for RCUK studentships
- Research Council (RC) fees and stipend can only be awarded to UK and EU students and not to EEA or International students.
- EU students are only eligible for RC stipend if they have been resident in the UK for 3 years, including for study purposes, immediately prior to starting their PhD.
- If an EU student cannot fulfil this condition then they are eligible for a fees only studentship.
- International students cannot be funded from RC funds unless they are ‘settled’ in the UK. ‘Settled’ means being ordinarily resident in the UK without any immigration restrictions on the length of stay in the UK. To be ‘settled’ a student must either have the Right to Abode or Indefinite leave to remain in the UK or have the right of permanent residence in the UK under EC law. If the student’s passport describes them as a British citizen they have the Right of Abode.
- Students with full Refugee status are eligible for fees and stipend.
Project Details This project focuses on developing a system for automatically diagnosing and classifying lesions associated with breast cancer from “tactile images.” The project is run in conjunction with PPS, the developer of novel medical instrumentation that uses pressure sensors to emulate manual palpation and produces a tactile image of the region under examination (www.suretouch.us). A database of some 20,000 examples of both real cancerous legions and representative phantoms will be provided. The aim is to develop an algorithm which will provide an automatic classification of previously unseen legions based on machine learning and pattern recognition applied to the database as well as expertise gathered in consultation with medical practitioners. A similar approach has been successfully applied to fault classification within nuclear power stations, where defects seen in signals and ultrasonic images of the fuel channel surface have been successfully detected and classified.
An estimated 1.38 million women worldwide were diagnosed with breast cancer in 2008, accounting for nearly a quarter (23%) of all cancers diagnosed in women (11% of the total in men and women). During that year, it was estimated that breast cancer was responsible for almost 460,000 deaths worldwide. In the UK, breast cancer is typically detected through self-examination which induces a visit to the General Practitioner (GP), or through the screening of women over the age of fifty using mammography. There is significant scope to improve the accuracy of GP referrals to secondary care, where only 8% of patients referred have cancer. This project will investigate a new technology for breast cancer screening based on tactile imaging that has the potential to significantly improve these referrals, reducing patient anxiety and reducing the financial strain on the NHS.
In recent years, a relatively new modality for cancer diagnostics termed Elasticity Imaging (EI) has emerged. EI allows visualization and semi-quantitative assessment of mechanical properties of soft tissue. Mechanical properties of tissues (i.e. elastic modulus and viscosity) are highly sensitive to tissue structural changes accompanying various physiological and pathological processes. A change in Young’s modulus of tissue during the development of a tumour could reach thousands of percent. Elasticity Imaging is based on generating a stress in the tissue using various static or dynamic means and measuring resulting strain by ultrasound or MRI. Tactile Imaging (TI) is an alternative form of Elastic Imaging that more closely mimics manual palpation. In Tactile imaging, compression is applied by a probe and the resulting stress image measured directly using an array of pressure sensors on the probe’s face (similar to human fingers during clinical examination).
SureTouch provides an estimate of a detected lesion’s width, length and elasticity relative to the background tissue, but currently does not go as far as to provide a diagnosis. PPS currently hold a database of clinical data relating to 20,000 SureTouch examinations. The aim of this project is to generate diagnosis algorithms using both knowledge based and data driven approaches. This would include:
- Identify key lesion metrics for lesion characterisation. These may include relative elasticity, size, variations in size between examinations, lesion roughness, and other parameters. This would include interviewing existing clinicians to understand their approach to diagnosis (knowledge-based approach) and purely data-driven strategies using labelled data.
- Develop algorithms to demonstrate diagnosis on existing clinical data.
- Develop representative phantoms for the various types of lesion.
- Demonstrate new algorithms integrated into the existing SureTouch unit when examining phantoms.
The candidate may also consider:
- The use of finite element tools to better understand the stress interactions between lesion, breast and tactile probe.
- Investigate methods to extract an absolute measure of breast elasticity (currently SureTouch can only estimate relative elasticity between lesion and breast). This may include the integration of additional sensors such as an accelerometer into the SureTouch system.
- Across the population, there is significant variation in the anatomy and firmness of breast tissue. Investigate the automated generation of automated algorithms to optimise SureTouch’s parameters to the patient under examination.
The primary supervisor will be Dr Gordon Dobie, Lecturer in Centre for Ultrasonic Engineering (CUE), within the Institute for Sensors, Signals and Communications. Dr Dobie's research interests include 3D fusion and visualisation of structural inspection and medical imaging data. He leads the engagement with contributing industry partner, PPS
The secondary supervior will be Dr Graeme West, Lecturer in the Institute for Energy and Environment. Dr West's research expertise is in the application of intelligent techniques to provide expert decision support.
How to apply
Candidates interested in applying should first email Dr Gordon Dobie or tel: +44 (0)141 548 2463 for an informal discussion. Thereafter, they should submit their CV, academic transcript, and a covering letter outlining their suitability for the position, to him.
Following review of the application submissions, selected candidates will be invited for interview.
Application submission deadline is 31 August 2017.
The project will start on 1 October 2017.