About the Project
Funding Source: Health Data Research UK
Proposed start date: September 2021
Closing date for applications: June 7th 2021
Eligibility: UK/EU applicants only
Department/School: University of Leicester Department of Cardiovascular Sciences and Department of Informatics
Project Title: Machine learning and Monte-Carlo simulation approaches to computer-guided interpretation of stroke brain images
Stroke affects over 100 000 people each year in the UK, and up to 50% of patients are left with significant disability . Accurate interpretation of brain images to confidently identify the source of a stroke or transient ischaemic attack (TIA) ensures patients receive appropriate treatment to prevent future strokes which has potential to lead to better outcomes. The recent development of 3D stroke simulations, and artificial intelligence and machine learning methods for automated feature extraction and learning from brain images, provides an unprecedented opportunity to accelerate clinical workflows and improve patient care. This PhD project will support clinical translation of computer-aided interpretation of brain imaging findings for rapid identification of the cause of a stroke.
The successful applicant will gain experience in segmentation of MR images using commercially available image analysis software to extract brain, vessel, and lesion volumes from existing MRI images obtained from groups of patients with confirmed sources of emboli, obtained through the University Hospitals of Leicester NHS Trust stroke unit. Classification of images via modelling (Monte-Carlo) and machine learning approaches involving image feature extraction and classification will then be used to determine the sensitivity and specificity of both techniques for classifying the origins of lesions. The overall aim of this PhD is to develop and test diagnostic software for computer-aided interpretation of brain imaging findings to support clinicians in rapid identification of the cause of a stroke.
This project offers an excellent opportunity for a PhD student to work on an innovative project that spans multiple disciplines (informatics, medical physics, and clinical medicine), with a strong focus on clinical translation. Dr Chung has a background in Medical Physics, including clinical evaluation of novel image analysis methods within the NHS. Dr Zare is a Bioinformatics expert specialising in medical image analysis using machine learning tools. Dr Beishon is a Clinical Academic specialising in Geriatric and Stroke Medicine. Dr Hague is an international expert in stroke simulation techniques based at the Open University. This project will result in the creation of a large database of stroke images including retrospective outcome data obtained in collaboration with NHS partners, from which we anticipate a legacy of downstream, high impact publications and collaborations with external centres.
The student will gain skills in medical image processing and machine learning approaches to image analysis, including deep learning. In addition to being based 50% of the time within the shared HDR UK facility at the University of Leicester, the student will be part of the Cerebral Haemodynamic in Ageing and Stroke Medicine (ChiASM) group, which has strong links with the University Hospitals of Leicester stroke unit and Department of Medical Physics. This project will suit a student with good communication and computational skills and a desire to benefit patients. The successful applicant is likely to have a first degree in informatics, engineering, physics, or mathematics, but we welcome applications form a range of backgrounds.
Our inter-disciplinary research group has an excellent track record in supervising and developing PhD students. The successful candidate will gain skills in the development of 3D stroke models, artificial intelligence techniques, and the application of these to real-world patient data.
Applicants are required to hold/or expect to obtain a UK Bachelor Degree 2:1 or better in a relevant subject.
The University of Leicester English language requirements apply where applicable.
To apply please refer to the guidance at: https://le.ac.uk/study/research-degrees/funded-opportunities/cvs-hdr-uk-chung
Application enquiries to [Email Address Removed]
• UK/EU tuition fee waiver
• Annual stipend rates as follows: 2021/22: £19,612, 2022/23: £19,906, 2023/24: £20,205.
 Liew SL, Aglin JM, Banks NW et al. (2018) A large, open sources dataset of stroke anatomical brain images and manual lesion segmentations. Sci Data. 5: 180011
 Chung EML, Hague JP, Evans DH. Revealing the mechanisms underlying embolic stroke using computational modelling. Phys. Med. Biol., 2007;52: 7153-66
 Chung EML. ‘Virtual patient' modelling of embolic stroke Circulation: European perspectives. Circulation 2012; 125: f102 (Invited).
 Hague JP and Chung EML. Statistical physics of cerebral embolization leading to stroke. Physical Review E. 2009; 80(5), 051912.
 Hague JP, C. Banahan and Chung EML. Modelling of impaired cerebral blood flow due to gaseous emboli. Physics in Medicine and Biology 2013 58:4381-4394 [IoP featured article].
 Keelan J, Chung EML, Hague JP. Development of a globally optimised model of the cerebral arteries. Physics in Medicine and Biology. 2019; 64(12):21
 Keelan J, Chung EML, Hague JP. Simulated annealing approach to vascular structure with application to the coronary arteries. Royal Society Open 2016
 Patel N, Horsfield MA, Banahan C, Thomas AG, Nath J, Ambrosi PB, and Chung EML. Detection of focal longitudinal changes in the brain by subtraction of MR images. American Journal of Neuroradiology 2017 38(5) 923-927
 Patel N, Horsfield MA, Banahan C, Janus J, Masters K, Morlese J, Egan V, and Chung EML. Impact of perioperative infarcts after cardiac surgery. Stroke. 2015; 46:680-686.
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.