This Earmarked Scholarship project is aligned with a recently awarded Category 1 research grant. It offers you the opportunity to work with leading researchers and contribute to large projects of national significance.
Supervisor - Dr Lei Guo, l.guo3@uq.edu.au
With the increased demands for low-cost, portable and fast medical imaging modalities, electromagnetic medical imaging (EMI) as a newly developed imaging modality is drawing more research nowadays.
This project aims to develop the new generation of EMI system, specifically for brain stroke imaging and classification.
Develop EMI for brain stroke imaging and classification has its unique advantages, such as the portable and low-cost features of EMI enable the system can be used in ambulance and rural areas. Considering the lack of practical medical imaging system in those scenarios, the outcome of this project has huge potential to fill a blank area in medical instrument market.
This project will involve two general aspects, the hardware and software. In the hardware part, different antenna types will be investigated to fulfil the portable and low-cost requirements of the EMI system. This research might include investigations about wearable antennas, metamaterial antennas, or reconfigurable antennas.
In the software part, novel EM imaging and classification algorithms will be developed. The EM imaging algorithms include radar-based algorithms, e.g., confocal and beamforming-based methods, etc, and tomography-based algorithms, e.g., Born/distorted Born iterative and contrast source inversion-based methods, etc. The classification algorithms aim to distinguish two types of brain strokes, i.e., the hemorrhagic and ischemic strokes. The development of classification algorithms include machine learning based methods by using the produced tomography images or the measured time domain/frequency domain data from EMI system.
This project is funded by an Advanced Queensland Industry project, collaborates with EMvision Medical Company and Princess Alexandra Hospital at Brisbane. The student has the opportunity to work with industry design team and specialists at hospital. Clinical data can be accessed to test the developed hardware and imaging algorithms. The student will also work with the UQ Electromagnetic Innovations team (EMAGIN), conduct experiments at the UQ electromagnetic imaging lab.
Preferred educational background
Applications will be judged on a competitive basis taking into account the applicant's previous academic record, publication record, honours and awards, and employment history.
A working knowledge of electromagnetic theory, solving electromagnetic inverse problem, machine learning for pattern recognition and classification, and signal processing would be of benefit to someone working on this project.
The applicant will demonstrate academic achievement in the field(s) of electromagnetic and machine learning and the potential for scholastic success.
A background or knowledge of convex optimisation is highly desirable.
*The successful candidate must commence by Research Quarter 2, 2022. You should apply at least 3 months prior to the research quarter commencement date. International applicants may need to apply much earlier for visa reasons.