Yuanyi Zhu
PhD:
Automatic generation of chest X-ray interpretation reports (Wellcome Trust project). My research aims to use large multimodal models to generate clinically accurate reports. I have developed a transformer-based report segmentation+classification model for use as an evaluation tool for the generated reports. I have also attempted to use temporal modelling to track the progression of abnormalities over time across multiple patient visits in order to address the discrepancy between image and report.
Supervisors: Giovanni Montana, Maria Liakata
Publications:
- Zhu, Y., Liakata, M., and Montana, G., 2024, May. A multi-task transformer model for fine-grained labelling of chest X-ray reports. LREC-COLING 2024. [pdf]
- Cid, Y.D., Macpherson, M., Gervais-Andre, L., Zhu, Y., Franco, G., Santeramo, R., Lim, C., Selby, I., Muthuswamy, K., Amlani, A., Hopewell, H., Indrajeet, D., Liakata, M., Hutchinson, C.E., Goh, V., and Montana, G., 2023, December Development and validation of open-source deep neural networks for comprehensive chest x-ray reading: a retrospective, multicentre study. The Lancet Digital Health, 6(1), pp.e44-e57. [pdf]
Research Interests:
Deep Learning, Natural Language Processing, Natural Language Generation, Multimodal Models.
MSc Project:
Understanding the Resilience of Cyber-Physical Systems Using Complex Networks Theory
Supervisors: Subhash Lakshminarayana, Weisi Guo.
Group Project:
Data analytics approach to extreme events in space weather
Supervisors: Professor Sandra Chapman, Malcolm Dunlop (RAL).
Background:
- BSc Mathematics with Intercalated Year, University of Warwick, 2014 - 2018
- Abroad In KOMaba (AIKOM) programme with JASSO scholarship, University of Tokyo, 2016 - 2017
Other commitments:
- IB1210 Business Statistics, IB1220 Business Analytics seminar tutor 2019 - 2020
- SSLC secretary 2018 - 2019
- Intermediate Japanese teacher for World at Warwick 2018 - 2019
CV:
Last updated May 2023Link opens in a new window