|Location||University of New South Wales, South Western Sydney Clinical School|
|Eligibility||Open to international applicants|
Scientia PhD scholarship: Using Machine Learning to Improve Cancer Outcomes
We are seeking highly motivated students wishing to pursue a PhD applying automation and machine learning concepts to real-world, high-impact problems in medicine. The opportunity exists under the prestigious UNSW Scientia PhD scholarship scheme and will involve the chance to work with an experienced multidisciplinary team of supervisors through the Ingham Institute for Applied Medical Research. The application process is open now for scholarships starting in the first semester of 2018.
- Work on high quality research projects in the medical field
- $40K a year stipend for four years
- Tuition fees covered for the full 4 year period
- Coaching and mentoring will form a critical part of your highly personalised leadership development plan
- Up to $10k each year to build your career and support your international research collaborations
Interested candidates with a background in physics, mathematics, computer science/engineering, image processing or related industry are encouraged to apply.
To apply follow the application process outlined from this link:
Applications close: 21st July 2017
Start date: First semester of 2018
Supervisors: Prof Geoff Delaney, A/Prof Lois Holloway, Dr Matthew Field
Project title : Using Machine Learning to Improve Cancer Outcomes
Cancer treatments such as radiotherapy deal with many forms of uncertainty in order to deliver appropriate dosage to the disease. Ideally appropriate treatment recommendations are based not only on data from clinical trials but also past histories of similar patients undergoing routine care across multiple cancer care providers. This project will investigate novel machine learning methods of accessing routine clinical data and then quantifying uncertainties and risks from this data and incorporating these into decision support aids in informative ways for radiation oncology. One challenging aspect of this project is that this data is not centralized and therefore the proposed methods will need to operate in an environment where data is distributed across a network of hospitals. The outcomes of this work will impact on future cancer treatments with the potential to expand into other medical areas and other machine learning areas.
More details on the program:
More details on our research group:
See our full disclaimer