Multi-modal endoscopic and surgical AI

This PhD research project focuses on developing innovative methods in multi-modal AI for healthcare applications, specifically in endoscopic and surgical contexts. The project aims to develop methods that provide insights into meaningful information while using multiple modalities such as clinical text data, imagery, voice recordings and videos. Computer vision has been widely used in various industries, including healthcare, and while deep learning has transformed several developments, the use of multimodal AI has strengthened it further. However, these approaches require careful understanding of what constitutes reliable information in big and diverse data scenarios. The successful PhD candidate will work with experts in the field of computer vision and machine learning, consultant gastroenterologists/endoscopists, and surgeons in an interdisciplinary environment. They will have the opportunity to directly understand both the technical developments and advancement needed from expert computational scientists and understand the broader surgical landscape with an expert clinical team. The candidate will be integrated directly into the AI for Medicine and Surgery group, which has a world-leading reputation for delivering high-quality research. This opportunity is funded through the EPSRC Doctoral Landscape Award, providing full academic fees together with a tax-free maintenance grant at the standard UKRI rate (£20,780 in academic session 2025/26) for 3.5 years. Training and support will also be provided. The project is based at the School of Computer Science, University of Leeds, under the supervision of Dr Sharib Ali and Dr Toni Lassila, with additional supervision from Dr Venkataraman Subramanian.