GEMS: Toward Distribution-Robust Medical Imaging Models in the Wild

About the Project

While deep learning has shown remarkable performance in medical imaging benchmarks, translating these results to real-world clinical deployment remains challenging. Models trained on data from one hospital or population often fail when applied elsewhere due to distributional shifts. These shifts violate the independently and identically distributed (i.i.d.) assumption, causing significant drops in accuracy, miscalibration, and biased predictions for underrepresented groups. Since acquiring new labeled data is often costly or infeasible due to rare diseases, limited expert availability, and privacy constraints, robust solutions are essential. This PhD project will develop methods for building reliable medical imaging models that generalize across distribution shifts without retraining. The project will focus on automated distributional shift detection and monitoring, invariant and distributionally robust representation learning methods, and deployment-time calibration with uncertainty quantification using approaches such as conformal prediction. The outcome will be a robust pipeline for deploying medical imaging models that remain reliable and fair across diverse real-world clinical settings.

We seek a motivated candidate with a strong background in machine/deep learning, computer vision, or applied statistics. Solid programming skills in Python and experience with deep learning frameworks (e.g., PyTorch or TensorFlow) are required. Familiarity with medical imaging data or clinical AI applications is an advantage but not essential. An interest in developing reliable and trustworthy AI systems for healthcare is highly desirable.

For enquiries, please contact Dr Chern Hong Lim

How to Apply

It is suggested that you first contact the main supervisor and provide them with your academic background and achievements to determine whether you are a 'fit' for this GEMS research topic. If you feel you are a 'fit', please click here to complete an Expression of Interest, including your research proposal relevant to this GEMS project. Your EoI will be assessed and if you are eligible, you will be invited to apply for PhD candidature and may be selected to interview for the GEMS scholarship. Interviews are likely to take place in March 2026 with successful applicants notified shortly afterwards.

Funding Notes

The Global Excellence and Mobility Scholarship (GEMS), funded by Monash University Malaysia, features regional mobility and is awarded to highly qualified students seeking to work on projects of regional and global relevance.

Recipients of GEMS will be funded for an immersive year in either Monash University Australia, Monash University Indonesia, or the Indian Institute of Technology Bombay of up to 9 months and have access to Monash University’s global network of research expertise and infrastructure during their candidature period.

Eligibility

To be eligible for GEMS, you must possess a minimum academic qualification of First Class Honours (H1) or its equivalence (H1E) recognised by Monash University Malaysia and satisfy the English language requirements.