Personal profile
Overview
Dr Mobarak Hoque is a Senior Lecturer (Associate Professor) in Multimodal Agentic AI for Healthcare, at the Division of Informatics, Imaging and Data Science, University of Manchester. He also currently appointed as an honorary senior research fellow positions at University College London. He holds a PhD in AI from the National University of Singapore and was a postdoctoral researcher at the Hawkes Institute at UCL, and the BioMedIA group at Imperial College London. Before his academic career, he gained extensive industry experience in real-world translation of machine learning and computer vision research as a Senior Software Engineer at Samsung R&D Institute.
His pioneering work on multimodal medical imaging AI has been widely recognised by leading international groups across academia and industry. His research focuses on developing safe, trustworthy, and adaptive multimodal large vision-language models and AI agents for medical imaging and surgical intelligence. He has published over 100 papers in top-tier peer-reviewed journals and conferences in medical imaging AI and multimodal LLM. He serves as Area Chair and Session Chair for MICCAI (2022–2025) and IPCAI (2024–2026), Senior Program Committee Member for AAAI 2026, and Organising several international workshops, including MICCAI-DART (2022–2023), MICCAI-UNSURE 2025, and IROS-C4SR+ 2025. He also serves on the Editorial Board of Nature Scientific Reports.
Research interests
- Mulitmodal LLM Agent in Healthcare
- Medical Imaging AI
- Safe and Trusted AI
- Foundation Model
- Biomedical Data Science
My group
Find details about my group at: https://mobarakol.github.io/
Education/Academic qualification
Doctor of Philosophy, Representation Learning in Multimodal Spatiotemporal Image-Guided Medical Procedures, National University of Singapore (NUS)
1 Aug 2015 → 3 Aug 2019
Award Date: 31 Dec 2019
External positions
Honorary Senior Research Fellow, University College London (UCL)
1 Jul 2025 → 30 Jun 2028
Senior Research Fellow, University College London (UCL)
1 Aug 2022 → 30 Jun 2025
Research Associate, Imperial College London
1 Feb 2020 → 30 Jul 2022
Research Fellow, National University of Singapore (NUS)
1 Aug 2019 → 31 Jan 2020
Areas of expertise
- QA75 Electronic computers. Computer science
- Medical Imaging AI
- Artificial Intelligence (AI)
- Multimodal LLM/VLM
- Safe and Responsible AI
- Agentic AI
Accepting PhD students
- Accepting PhD students
Expertise related to UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This person’s work contributes towards the following SDG(s):
-
SDG 3 Good Health and Well-being
-
SDG 9 Industry, Innovation, and Infrastructure
Fingerprint
- 1 Similar Profiles
-
SurgFusion-Net: Diversified Adaptive Multimodal Fusion Network for Surgical Skill Assessment
He, R., Tesfai, F. M., Boal, M. W. E., Sirajudeen, N., Anastasiou, D., Xu, J., Hoque, M. I., Kelly, J. D., Sridhar, A., Kadkhodamohammadi, A., Chandrasekaran, D., Clarkson, M. J., Stoyanov, D., Francis, N. & Mazomenos, E. B., 18 Feb 2026, (Submitted) arXiv, 11 p.Research output: Preprint/Working paper › Preprint
File2 Downloads (Pure) -
TemporalDoRA: Temporal PEFT for Robust Surgical Video Question Answering
Carlini, L., Lena, C., Hassan, C., Stoyanov, D., Momi, E. D., Bano, S. & Hoque, M. I., 10 Mar 2026, (Submitted) arXiv, p. 1-10, 10 p.Research output: Preprint/Working paper › Preprint
File3 Downloads (Pure) -
Controllable illumination invariant GAN for diverse temporally-consistent surgical video synthesis
Chen, L., Hoque, M. I., Min, Z., Clarkson, M. & Dowrick, T., 31 Oct 2025, In: Medical Image Analysis. 105, 103731.Research output: Contribution to journal › Article › peer-review
-
Endo-FASt3r: Endoscopic Foundation Model Adaptation for Structure from Motion
Sheikh Zeinoddin, M., Hoque, M. I., Tandogdu, Z., Shaw, G. L., Clarkson, M. J., Mazomenos, E. B. & Stoyanov, D., 20 Sept 2025, International Conference on Medical Image Computing and Computer-Assisted Intervention. p. 117-126 10 p.Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review
Open Access -
Multimodal graph representation learning for robust surgical workflow recognition with adversarial feature disentanglement
Bai, L., Ma, B., Wang, R., Wang, G., Cui, B., Jiang, Z., Islam, M., Min, Z., Lai, J., Navab, N. & Ren, H., Nov 2025, In: Information Fusion.Research output: Contribution to journal › Article › peer-review