people

My research focuses on statistical machine learning for reliable AI, particularly uncertainty quantification and evaluation, with an emphasis on clear statistical principles, theoretical guarantees, and practical use in medical applications.

I have the personality of an old-school statistician in a modern AI lab — I care about elegant theory and careful assumptions, but I am always happy to collaborate across disciplines, preferably with a good coffee nearby.

Uncertainty quantification, probabilistic model calibration, and cardiac diffusion tensor imaging.

Medical Image Analysis, Generative Model, Digital Twins and Virtual Patients Modelling.

INTJ

Image Registration, Motion Tracking, Inverse Problems, Generative Modelling, Multimodal Learning.

Remember where you started.

I develop computational methods that make medicine more precise, predictive, and personalised. My work spans two connected frontiers: computational phenomics, which combines imaging, genetic, and clinical data to reveal what makes each patient unique; and in silico science, which creates virtual patients to test new devices and therapies safely before they reach the clinic. Together, these tools help bring better treatments to patients faster — and shape the regulatory science that gets them there.

Husband to a brilliant woman and dad to eight wonderfully different humans (four boys, four girls). Off-duty, you'll find me cooking or making music with the family, lost in philosophy of science, or championing neurodivergent thinkers everywhere.

Integrating experiments, theory, and computer simulations to develop mechanistic models spanning computational mechanics, materials science, and biomedical engineering.

I am a Project Officer supporting the coordination and day-to-day delivery of the group's projects and organisational activities. I manage communications, organise events and meetings, coordinate timelines and administrative processes, and act as a link between different teams across the University.

I'm naturally curious, creative, and enjoy working with people just as much as I enjoy a well-organised spreadsheet. Outside work, I love live music, pub quizzes, exploring the countryside, and cuddling my cats.

Mobarak Hoque leads research on agentic AI to help clinicians better understand complex and multimodal patient data and improve early diagnosis, personalised treatments, and clinical decision making in hospitals and operating rooms. His research aims to develop reliable AI systems that work as trusted clinical partners, supporting adaptive, efficient, and safer healthcare through close collaboration between clinicians and AI. This research envisions a future where trustworthy AI enhances medical decision making, improves patient outcomes, and supports safer healthcare delivery.

I enjoy appreciating life's simple moments and exploring different cultures through everyday experiences. Interacting with people from diverse backgrounds continually broadens my perspective and reminds me of the importance of empathy, curiosity, and human connection in both research and life.

My work focuses on cross-topology shape generation for virtual patients and foundation generative models.

Outside of research, I enjoy cooking (and eating), travelling, playing the violin, and video games.

Academic ophthalmologist using artificial intelligence and images of the eye to predict and prevent major health events such as heart attacks and strokes.

When I'm not working, you'll likely find me traveling, soaking up the atmosphere at a music festival, or experimenting with new recipes in a cooking class.

My research focuses on advancing neuroradiology by developing faster, safer imaging techniques to improve the detection and understanding of neurological conditions, supporting better diagnosis and patient care. Alongside my research, I am committed to education, teaching medical students, radiology residents, and radiographers. I strive to build strong foundational knowledge and clinical reasoning skills across all levels, preparing the next generation of imaging professionals for the demands of modern radiological practice.

As a mother of two and a wife who has lived across multiple countries and cultures, diversity is simply my way of life. This rich experience shapes how I connect with every person I meet, making me adaptable, empathetic, and genuinely curious about people.

Programme Manager for CIMIM and UK CEiRSI. Key focus is enabling the use of in silico approaches in health and life sciences and supporting the development of legislation, guidance, standards.

I'm the father to three daughters and we love animals! We have 4 cats and a dog. In my spare time, I enjoy trail running, and am involved in running a number of youth groups including chairman of a league club that was set up to support children in a deprived area and leader for youth music and drama group in Leyland.

My research focuses on the theoretical foundations of deep learning, specifically within optimization and learning theory. I am particularly driven to bridge these theoretical insights with practice by developing deep learning frameworks for physics-informed models.

Like many others, I was inspired by the spirit of curiosity that Richard Feynman embodied. I enjoy solving problems and finding intuitive, elegant, and sometimes witty ways of thinking about them. I also appreciate clever humour, especially the kind found in Monty Python. If you ever have an idea you'd like to discuss, I'd be more than happy to chat over email or in person.

3D generative model.

Powered by sunshine, coffee, and good vibes.

Focusing deep learning-assisted molecular dynamics simulations (machine learning potentials), molecular representation learning, and agentic AI for drug discovery.

Love traveling and reading, or just sleeping.

Develops deep learning methods for medical image analysis. Algorithmic strengths include class-imbalanced, fully supervised, semi-supervised, and self-supervised learning, enabling AI to work with limited expert labels and uneven disease distributions. Application areas include digital twin reconstruction, virtual population generation, and AI agents that automate research and clinical workflows for disease modelling, risk prediction, and treatment planning.

Passionate about turning medical AI research into practical, scalable solutions, connecting academic innovation with clinical and business value, and helping ideas move closer to real-world impact.

My research focuses on developing computational models for in-silico trials of cardiovascular and neurovascular medical devices. I have expertise in fluid dynamics, fluid-structure interaction, numerical methods, reduced order models and scientific machine learning.

I work with determination to reach my goals and I strive to be kind and compassionate with others. Outside of work, I enjoy getting outside for hiking, running and sometimes to play football. I also love to cook.

Graph Neural Networks, Time Series Analysis, Multimodal Learning, Generative AI.

Enjoy collaborative research and thoughtful discussions.

Mathematical modelling and optimisation techniques for machine learning and the analysis of large-scale complex data including text, images, and networks.

Theory of deep learning and scientific machine learning / AI for science applications.

Computational modeling of cerebral hemodynamics and the performance of intrasaccular devices to improve treatment planning and outcomes through efficient patient-specific simulations.

I enjoy playing chess, reading, and watching films in my free time. I value long conversations over tea or coffee, and strive to follow a dharmic, vegan lifestyle.

Interim Innovation Director — helping to develop UK CEiRSI, with a focus on strategy, funding, government affairs, marketing, and communications.

I like analytical and creative work.

I am currently doing research on leveraging representation learning, geometric deep learning, computer vision methods, and generative AI to synthesize anatomies that capture the normal and disease patterns present in patient populations. My aim is to make the generation process robust and easier to interpret, as well as to diversify the population with controlled and meaningful attributes.

I am enthusiastic on learning new things related to my field of interest. I also enjoy staying physically active through sports and working out.

Senior Research Software Engineer working on the MULTI-X application, to allow cohort discovery from multiple distributed sources and execution of algorithms on data using high performance compute resources.

I mostly spend my time outside of work transporting my children around, but also enjoy ballroom and latin dancing! I also work on the SpiNNaker Neuromorphic project in Manchester.

My research focuses on artificial intelligence (AI) for science and health, with an emphasis on geometric deep learning and neural operators for complex physics simulations, including cardiovascular blood flow and automotive aerodynamics. I am particularly interested in developing methods that generalise well in practical settings and scale to large, complex problems, while remaining reliable under limited data through the incorporation of inductive biases such as symmetries and physics-based conservation laws.

I enjoy staying active in my free time, especially in the mountains while skiing, hiking, rope climbing, or bouldering. I'm also interested in urban and nature photography and enjoy reading.

Medical images are often low resolution, noisy or blurred. A deep neural network can be trained to generate guesses of the signal underlying an observation. It's impossible to know what the true signal is, so the network should be able to generate multiple plausible guesses. And clean training images are rarely available, so the network should train with only degraded observations. I aim meet these criteria by approaching problems with an understanding of the degradation process.

I enjoy karting and am often going to gigs.

Cardiovascular Biomechanics, Cardiovascular Fluid Dynamics, Computational Mechanics, Cardiovascular Medical Devices, In-Silico Trials, Scientific Machine Learning.

Deep learning for medical image analysis, with a focus on multi-modal generative AI for virtual patient populations in in-silico trials.

Mostly searching, occasionally finding, always seeking.

I apply mathematical and computational simulations to virtually assess medical devices before they reach patients. My current work focuses on the deployment of transcatheter heart valves and minimising associated conduction disturbances. I also contribute to a UK CEiRSI pilot study, developing a framework to integrate digital evidence into the regulatory approval of device design modifications.

Outside of work, I enjoy reading, hiking, and listening to classical music. I also like playing video games and bridge with friends.

Medical image analysis and AI; my research focuses on generating and validating digital representations of patient anatomy from clinical scans and multimodal data, helping improve treatment, in silico medical device testing, and personalised healthcare.

Outside of work, I enjoy cooking and long walks.

AI for patient-specific cardiac modeling and digital twin generation from medical images.

Chasing growth, basketball, and every meaningful moment — I'm gonna live every minute of it.

3D vessel reconstruction and generation.

Seeking truth beyond narratives, and building value beyond trends.