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

About the project

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 For more information about this project, please visit our GEMS website. ------------------------------------------------------------------------------------ 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 research topic. If you feel you are a good fit, submit your application here and ensure that you enter the same research topic as advertised on this webpage. To review the application requirements, please refer to our application submission guide . More information about the scholarships and the course application process is available here .

Research areas