Fully Automatic Segmentation and Assessment of Atrial Scars for Atrial Fibrillation Patients Using LGE MRI
Lead Research Organisation:
Imperial College London
Department Name: UNLISTED
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
Technical Summary
The main objectives of this proposal are to (1) develop a novel data harmonisation method based on recently proposed domain adaptation and generative adversarial models; (2) carry out an initial two-centre cross-national validation study on the retrospectively collected LGE MRI data; (3) independent testing of a multicentre study consists of data collected from four centres, i.e., Brompton (UK), Anam (South Korea), KCL (UK), and Utah (USA), where the data from KCL and Utah are with open access; (4) strengthen further teaching, training and research collaboration links between UK and South Korea clinicians and technicians to gain more understanding about LGE MRI data and deep learning based fibrosis assessment; and (5) enable large-scale basic science and technical development projects and prospective clinical trials at two nations and further international studies.
Publications
Liu Y
(2021)
Deep Learning Enables Prostate MRI Segmentation: A Large Cohort Evaluation With Inter-Rater Variability Analysis.
in Frontiers in oncology
BonmatĂ LM
(2022)
CHAIMELEON Project: Creation of a Pan-European Repository of Health Imaging Data for the Development of AI-Powered Cancer Management Tools.
in Frontiers in oncology
Astaraki M
(2021)
A Comparative Study of Radiomics and Deep-Learning Based Methods for Pulmonary Nodule Malignancy Prediction in Low Dose CT Images.
in Frontiers in oncology
Xing X
(2023)
HDL: Hybrid Deep Learning for the Synthesis of Myocardial Velocity Maps in Digital Twins for Cardiac Analysis.
in IEEE journal of biomedical and health informatics
Chen J
(2022)
JAS-GAN: Generative Adversarial Network Based Joint Atrium and Scar Segmentations on Unbalanced Atrial Targets.
in IEEE journal of biomedical and health informatics
Tang Z
(2023)
Adversarial Transformer for Repairing Human Airway Segmentation.
in IEEE journal of biomedical and health informatics
Zhang W
(2023)
Multiple Adversarial Learning Based Angiography Reconstruction for Ultra-Low-Dose Contrast Medium CT.
in IEEE journal of biomedical and health informatics
Li Y
(2023)
Global Transformer and Dual Local Attention Network via Deep-Shallow Hierarchical Feature Fusion for Retinal Vessel Segmentation.
in IEEE transactions on cybernetics
Li M
(2023)
Explainable COVID-19 Infections Identification and Delineation Using Calibrated Pseudo Labels
in IEEE Transactions on Emerging Topics in Computational Intelligence
Description | Cambridge Mathematics of Information in Healthcare Hub |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Department | Centre for Mathematical Imaging in Healthcare |
Country | United Kingdom |
Sector | Charity/Non Profit |
PI Contribution | Developing new collaborations working on MRI denoising models. |
Collaborator Contribution | Prof Carola-Bibiane Schönlieb and Dr Angelica I. Aviles-Rivero provide guidance and intellectual knowledge input for my PhD student Jiahao Huang via this collaboration. We have regular research meetings and we have joint publications under submission. |
Impact | Currently, one conference paper is under review and one journal paper is under submission. |
Start Year | 2022 |
Description | Collaboration with Prof Sung Ho Hwang and Dr Yongwon Cho at Korea University Anam Hospital |
Organisation | Korea University |
Country | Korea, Republic of |
Sector | Academic/University |
PI Contribution | This project supports our collaboration with Prof Sung Ho Hwang and Dr Yongwon Cho at Korea University Anam Hospital to research into multicentre and multinational LGE CMR data. |
Collaborator Contribution | We have on-going discussions and efforts on building up a multicentre and multinational LGE CMR database. |
Impact | Publications in preparation. |
Start Year | 2021 |
Description | Prof. Pietro Lio (Cambridge University) on super-resolution for cardiac images |
Organisation | University of Cambridge |
Department | Computer Laboratory |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | We work with Prof. Pietro Lio (Cambridge University) for solving the super-resolution for cardiac images. |
Collaborator Contribution | Prof. Pietro Lio has expertise in bioinformatics, computational biology models and machine learning, and research studies in integrating various types of data (molecular and clinical, drugs, social and lifestyle) across different spatial and temporal scales of biological complexity to address personalised and precision medicine. Prof. Pietro Lio has contributed his knowledge in our research studies and helped us designed novel super-resolution techniques for cardiac images. He has also provided us guidance and support for our further funding applications. |
Impact | This collaboration is multi-disciplinary. Prof Pietro Lio has got expertise in medical image analysis. Zhu, Jin, Chuan Tan, Junwei Yang, Guang Yang, and Pietro Lio'. "Arbitrary scale super-resolution for medical images." International Journal of Neural Systems 31, no. 10 (2021): 2150037. Jin Zhu, Guang Yang, Tom Wong, Raad Mohiaddin, David Firmin, Jennifer Keegan, and Pietro Lio. A Single-Image Super-Resolution Method for Late Gadolinium Enhance- ment CMR. In the International Society for Magnetic Resonance in Medicine 27th Annual Meeting (ISMRM) 2019 Jin Zhu, Guang Yang, Pedro Ferreira, Andrew Scott, Sonia Nielles-Vallespin, Jennifer Keegan, Dudley Pennell, Pietro Lio, and David Firmin. A ROI Focused Multi-Scale Super- Resolution Method for the Di usion Tensor Cardiac Magnetic Resonance. In the International Society for Magnetic Resonance in Medicine 27th Annual Meeting (ISMRM) 2019 |
Start Year | 2018 |