Multimodal Learning for Human-Centered Healthcare: Motion Understanding and Medical Imaging University of Bristol in United Kingdom

This PhD project at the University of Bristol focuses on developing advanced multimodal machine learning methods for healthcare data analysis. The research aims to integrate diverse healthcare data types to enhance disease monitoring and diagnostic capabilities, with applications in mobility assessment and computer-assisted diagnosis. The project is structured around two main themes: human action and mobility assessment, and medical image analysis.

For human pose estimation and action understanding, the project leverages RGB images, video data, 3D skeletal representations, and wearable sensors to enable robust analysis of human movement. The research is particularly relevant for indoor monitoring of individuals with Parkinson’s disease and mobility impairments such as stroke. Applications include rehabilitation video analysis and gait lab data, supporting accurate pose estimation and action quality assessment for patient monitoring and recovery.

The second theme focuses on multimodal learning for interpretable and data-efficient medical image analysis. The project will develop AI-driven methods for robust analysis across diverse medical imaging modalities, exploring how multimodal signals—such as expert attention, sparse annotations, and clinical text reports—can be integrated with diagnostic imaging. The goal is to build data-efficient, interpretable, and clinically reliable models for disease diagnosis and decision support.

As a candidate, you will need an MSc in a relevant field (computer science, applied mathematics, image processing, or biomedical engineering), a strong background in deep learning and machine learning, and programming skills in Python and PyTorch or TensorFlow. Preferred qualifications include biomedical imaging experience, a publication or open-source track record, and GPU/HPC experience. The project offers opportunities to work with real clinical data and collaborate with interdisciplinary partners in medicine and healthcare research.

To apply, send your CV to Dr QM Men at [email protected]. The application deadline is February 28, 2027. For more information and formal submission, visit the FindAPhD project page.