| Application: | 18545, Biobank Brain and Cardiac Mutual Risk Indexing (BBC MRI) study |
| Title: | Automated cardiovascular magnetic resonance image analysis with fully convolutional networks |
| Size: | 520103 B |
| Archived: | 16 Jan 2020 |
| Stability: | Updateable |
| Personal: | Contains individual-level data |
Return 1886
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Notes
Cardiovascular resonance (CMR) imaging is a standard imaging modality for assessing cardiovascular diseases (CVDs), the leading cause of death globally. CMR enables accurate quantification of the cardiac chamber volume, ejection fraction and myocardial mass, providing information for diagnosis and monitoring of CVDs. However, for years, clinicians have been relying on manual approaches for CMR image analysis, which is time consuming and prone to subjective errors. It is a major clinical challenge to automatically derive quantitative and clinically relevant information from CMR images.We show that an automated method achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures.
Application 18545
Biobank Brain and Cardiac Mutual Risk Indexing (BBC MRI) study
The prevalence of both brain and cardiac disease rises with age and there are functional interactions between the two organs in health and disease (the heart-brain axis). However, cardiac and brain co-morbidities in later life are poorly explored and risk factors or markers that may suggest interacting pathophysiological mechanisms remain to be elucidated. The aim of our research is to investigate brain-heart axis using brain and cardiac MRI images and carotid IMT data in the context of clinical, genetic and lifestyle (e.g., smoking, alcohol use) data in UK Biobank. The results of our study will lead to better understanding of brain-heart axis and may improve the prevention, diagnosis and treatment of both brain and cardiac diseases in later life. We will perform analyses of the heart and brain images and review clinical histories of people in UK Biobank to identify signs of diseases such as stroke or signs of impaired heart or brain functions. We will work to understand relationships between these and how they may be influenced by a person?s genes or other medical conditions or their lifestyle. We hope to understand how to better assess the risk of brain and cardiac disease in later life and how the health of the two organs is related. To have the greatest power for the range of nested analyses, data from the full cohort of subjects with imaging data available at the time of this application are requested (~5000 individuals anticipated). As future imaging data are able to be released, we would like to supplement the study group to test exploratory hypotheses generated from the initial (~5000 subject) data using a test dataset covering an additional 15,000 people.
| Lead investigator: | Professor Paul Matthews |
| Lead institution: | Imperial College London |
1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 1887 | Automated cardiovascular magnetic resonance image analysis with fully convolutional networks | Wenjia Bai (+22) | 2018 | Journal of Cardiovascular Magnetic Resonance |
Enabling scientific discoveries that improve human health