Robust, valid and interpretable deep learning for quantitative imaging

Project opportunity

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.

One of the biggest challenges in employing artificial intelligence is the “black-box” nature of the models used. This project aims to improve the effectiveness and trustworthiness of deep learning within quantitative magnetic resonance imaging. Deep learning has great promise in speeding-up complex image processing tasks, but currently suffers from variable data inputs, predictions are not guaranteed to be plausible and it is not clear to the end user how reliable the results are. The outcomes intend to deliver advanced knowledge and capability in artificial intelligence and machine learning.

This project will work towards:

  • a framework for deep learning algorithms to include physics constraints to enable valid solutions of ill-posed inversion problems
  • autonomous and self-supervised deep learning image segmentation algorithms to facilitate automatic region-of-interest analyses of quantitative imaging data
  • Integrate the commercial grade algorithms in the C++ software framework on the Siemens magnetic resonance imaging scanner platforms
  • Integrate self-supervised domain adaptation for applying deep learning models to new data deviating from the training data
  • develop models that do not just output the prediction but also uncertainty measures reflecting the data and model quality

Scholarship value

As a scholarship recipient, you'll receive: 

  • living stipend of $32,192 per annum tax free (2023 rate), indexed annually
  • tuition fees covered
  • single Overseas Student Health Cover (OSHC)


Dr Steffen Bollmann

School of Information Technology and Electrical Engineering


Preferred educational background

Your application will be assessed on a competitive basis.

We take into account your

  • previous academic record
  • publication record
  • honours and awards
  • employment history.

A working knowledge of magnetic resonance imaging, deep learning and software development would be of benefit to someone working on this project.

The applicant will demonstrate academic achievement in the field(s) of data science and the potential for scholastic success.

A background or knowledge of c++ is highly desirable.

Latest commencement date

If you are the successful candidate, you must commence by Research Quarter 1, 2023. You should apply at least 3 months prior to the research quarter commencement date.

If you are an international applicant, you may need to apply much earlier for visa requirements.

How to apply

You apply for this project as part of your PhD program application.

View application process