Medical Image Analysis with Machine Learning Techniques

Summary

Develop artificial intelligence for computer-assisted diagnosis from medical scans.

Supervisor

Dr Luping Zhou.

Research location

Electrical and Computer Engineering

Program type

PHD

Synopsis

Medical image analysis is a research field where advanced image analysis techniques are developed to solve or analyse medical problems, e.g., designing models to predict, diagnose or monitor diseases. Computer-assisted automatic processing and analysis of medical images is in high demand due to its better precision, repeatability and objectivity compared with conventional diagnosis in many scenarios, and it achieves promising performance nowadays with the equipment of advanced machine learning techniques. Our research focuses on developing image analysis algorithms and systems based on machine learning techniques to solve a number of very important yet challenging medical image analysis problems. This includes (but is not limited to) the early diagnosis of multiple mental disorders (e.g., Alzheimer's disease, attention-deficit/hyperactivity disorder and schizophrenia), image-guided radiation therapy for prostate cancer, automatic cell image classification (for the diagnosis of some autoimmune diseases), and brain tumour segmentation (for brain cancer staging), etc.

Additional information

Use of research technique/methodology/technology

• image processing, computer vision & machine learning

Potential topics of interest for the research opportunity

• multiple modality based medical image segmentation using deep learning technology
• "dose-less" medical imaging with machine learning technology
• network analysis for imaging-based dementia study

Eligibility criteria / candidate profile

• Master in engineering and computer science is required
• Good programming skills
• Research experience on image data is a plus but not necessary
• Knowledge in medicine is not necessary

Want to find out more?

Opportunity ID

The opportunity ID for this research opportunity is 2384