Cheng Ouyang PhD DIC MS BEng

Dr. Cheng Ouyang is a Departmental Lecturer at the Institute of Biomedical Engineering, Department of Engineering Science. His research centres on data-efficient, robust, and user-friendly machine learning approaches for medical image/signal computing. His research topics include but are not limited to domain generalization, few-/zero-shot learning, uncertainty modeling, and multimodal machine learning for the interpretation and analysis of medical data, primarily images such as ultrasound and MRI. Prior to joining Oxford, he was a postdoctoral researcher on cardiac imaging at the Institute of Clinical Sciences, Imperial College London. He obtained his PhD from the Department of Computing at Imperial College London.

• Multimodal machine learning for medical data (e.g., image, signal, and language).
• Domain generalization and uncertainty modeling for trustworthy machine learning in medical image computing (e.g., image reconstruction, classification, and segmentation).
• Few-/zero-shot learning for data-efficient machine learning in medical image computing.
• Machine learning for medical sciences (e.g., for the understanding of cardiovascular diseases).

Applications of the above learning approaches in addressing clinical and medical research challenges. We seek for real-world benefits of machine learning techniques that may go beyond one-off publications.

I am looking for self-motivated DPhil (Oxford abbreviation of PhD) students in medical image computing. Topics include but are not limited to uncertainty modeling, few-shot/zero-shot learning, multi-modal learning, etc. — all in the broad context of improving the efficiency, trustworthiness, and user-friendliness for human-machine collaboration in medical imaging. Please find more information about DPhil in Engineering Science program here.

Please feel free to drop me an email if you are interested.

Challenge winner:

• Multi-Center Fetal Brain Tissue Annotation (FeTA) Challenge @MICCAI 2022
• Multi-sequence Cardiac MR Segmentation Challenge @MICCAI 2019