{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T09:00:04Z","timestamp":1772787604613,"version":"3.50.1"},"reference-count":22,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T00:00:00Z","timestamp":1715644800000},"content-version":"vor","delay-in-days":134,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"UKBB"},{"DOI":"10.13039\/501100000287","name":"Royal Academy of Engineering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000287","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Frontier Research","award":["EP\/Y030494\/1"],"award-info":[{"award-number":["EP\/Y030494\/1"]}]},{"DOI":"10.13039\/100014653","name":"NIHR Manchester Biomedical Research Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014653","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003921","name":"Department of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Aims<\/jats:title>\n                  <jats:p>Cardiovascular diseases (CVDs) are the leading cause of mortality worldwide. Cardiac image and mesh are two primary modalities to present the shape and structure of the heart and have been demonstrated to be efficient in CVD prediction and diagnosis. However, previous research has been generally focussed on a single modality (image or mesh), and few of them have tried to jointly consider the image and mesh representations of heart. To obtain efficient and explainable biomarkers for CVD prediction and diagnosis, it is needed to jointly consider both representations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods and results<\/jats:title>\n                  <jats:p>We design a novel multi-channel variational auto-encoder, mesh-image variational auto-encoder, to learn joint representation of paired mesh and image. After training, the shape-aware image representation (SAIR) can be learned directly from the raw images and applied for further CVD prediction and diagnosis. We demonstrate our method on data from UK Biobank study and two other datasets via extensive experiments. In acute myocardial infarction prediction, SAIR achieves 81.43% accuracy, significantly higher than traditional biomarkers like metadata and clinical indices (left ventricle and right ventricle clinical indices of cardiac function like chamber volume, mass, and ejection fraction).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Our mesh-image variational auto-encoder provides a novel approach for 3D cardiac mesh reconstruction from images. The extraction of SAIR is fast and without need of segmentation masks, and its focussing can be visualized in the corresponding cardiac meshes. SAIR archives better performance than traditional biomarkers and can be applied as an efficient supplement to them, which is of significant potential in CVD analysis.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/ehjimp\/qyae042","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T16:43:16Z","timestamp":1715704996000},"source":"Crossref","is-referenced-by-count":3,"title":["Joint shape\/texture representation learning for cardiovascular disease diagnosis from magnetic resonance imaging"],"prefix":"10.1093","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4203-4578","authenticated-orcid":false,"given":"Xiang","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computing, University of Leeds , Woodhouse, LS2 9JT Leeds , UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computing, University of Leeds , Woodhouse, LS2 9JT Leeds , UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2165-7154","authenticated-orcid":false,"given":"Erica","family":"Dall'Armellina","sequence":"additional","affiliation":[{"name":"School of Medicine, University of Leeds , Woodhouse, LS2 9JT Leeds , UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nishant","family":"Ravikumar","sequence":"additional","affiliation":[{"name":"School of Computing, University of Leeds , Woodhouse, LS2 9JT Leeds , UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2675-528X","authenticated-orcid":false,"given":"Alejandro F","family":"Frangi","sequence":"additional","affiliation":[{"name":"Christabel Pankhurst Institute, The University of Manchester , Oxford Rd, M13 9PL Manchester , UK"},{"name":"Department of Computer Science, School of Engineering, The University of Manchester , Oxford Rd, M13 9PL Manchester , UK"},{"name":"Division of Informatics, Imaging, and Data Sciences, School of Health Sciences, The University of Manchester , Oxford Rd, M13 9PL Manchester , UK"},{"name":"NIHR Manchester Biomedical Research Centre, Manchester Academic Health Science Centre , Oxford Rd, M13 9PL Manchester , UK"},{"name":"Medical Imaging Research Center (MIRC), University Hospital Gasthuisberg , UZ Herestraat 49 - bus 7003, 3000 Leuven , Belgium"},{"name":"Department of Cardiovascular Sciences, KU Leuven , UZ Herestraat 49 - box 911, 3000 Leuven , Belgium"},{"name":"Department of Electrical Engineering, KU Leuven , Kasteelpark Arenberg 10 postbus 2440, 3001 Leuven , Belgium"},{"name":"Alan Turing Institute , British Library, 96 Euston Rd., NW1 2DB London , UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,5,14]]},"reference":[{"key":"2024071810114084500_qyae042-B1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2018\/1437125","article-title":"An overview on image registration techniques for cardiac diagnosis and treatment","volume":"2018","author":"Khalil","year":"2018","journal-title":"Cardiol Res Pract"},{"key":"2024071810114084500_qyae042-B2","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1038\/s42256-019-0019-2","article-title":"Deep-learning cardiac motion analysis for human survival prediction","volume":"1","author":"Bello","year":"2019","journal-title":"Nat Mach Intell"},{"key":"2024071810114084500_qyae042-B3","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1038\/s44161-022-00048-2","article-title":"Genetic and environmental determinants of diastolic heart function","volume":"1","author":"Thanaj","year":"2022","journal-title":"Nat Cardiovasc Res"},{"key":"2024071810114084500_qyae042-B4","doi-asserted-by":"crossref","first-page":"102498","DOI":"10.1016\/j.media.2022.102498","article-title":"Automatic 3D+t four-chamber CMR quantification of the UK biobank: integrating imaging and non-imaging data priors at scale","volume":"80","author":"Xia","year":"2022","journal-title":"Med Image Anal"},{"key":"2024071810114084500_qyae042-B5","first-page":"012003","article-title":"Deep learning in medical image registration","volume":"3","author":"Chen","year":"2021","journal-title":"Prog Biomed Eng"},{"key":"2024071810114084500_qyae042-B6","first-page":"46","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Chen","year":"2021"},{"key":"2024071810114084500_qyae042-B7","first-page":"1305","volume-title":"IEEE 15th International Symposium on Biomedical Imaging","author":"Sarmiento","year":"2018"},{"key":"2024071810114084500_qyae042-B8","doi-asserted-by":"crossref","first-page":"3488","DOI":"10.1007\/s00330-022-09323-z","article-title":"Prediction of incident cardiovascular events using machine learning and CMR radiomics","volume":"33","author":"Pujadas","year":"2022","journal-title":"Eur Radiol"},{"key":"2024071810114084500_qyae042-B9","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s12968-016-0227-4","article-title":"UK biobanks cardiovascular magnetic resonance protocol","volume":"18","author":"Petersen","year":"2015","journal-title":"J Cardiovasc Magn Reson"},{"key":"2024071810114084500_qyae042-B10","doi-asserted-by":"crossref","first-page":"2514","DOI":"10.1109\/TMI.2018.2837502","article-title":"Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved?","volume":"37","author":"Bernard","year":"2018","journal-title":"IEEE Trans Med Imaging"},{"key":"2024071810114084500_qyae042-B11","doi-asserted-by":"crossref","first-page":"3543","DOI":"10.1109\/TMI.2021.3090082","article-title":"Multi-centre, multi-vendor and multi-disease cardiac segmentation: the M&Ms challenge","volume":"40","author":"Campello","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"2024071810114084500_qyae042-B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s42003-022-03218-x","article-title":"A multi-encoder variational autoencoder controls multiple transformational features in single-cell image analysis","volume":"5","author":"Ternes","year":"2022","journal-title":"Commun Biol"},{"key":"2024071810114084500_qyae042-B13","first-page":"302","volume-title":"International Conference on Machine Learning","author":"Antelmi","year":"2019"},{"key":"2024071810114084500_qyae042-B14","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/s42256-021-00427-7","article-title":"Predicting myocardial infarction through retinal scans and minimal personal information","volume":"4","author":"Diaz-Pinto","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2024071810114084500_qyae042-B15","first-page":"704","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Ranjan","year":"2018"},{"key":"2024071810114084500_qyae042-B16","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"Van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"2024071810114084500_qyae042-B17","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1007\/s12350-018-1304-x","article-title":"Machine learning in the integration of simple variables for identifying patients with myocardial ischemia","volume":"27","author":"Juarez-Orozco","year":"2020","journal-title":"J Nucl Cardiol"},{"key":"2024071810114084500_qyae042-B18","first-page":"1","article-title":"Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach","volume":"5","author":"Aerts","year":"2014","journal-title":"Nat Commun"},{"key":"2024071810114084500_qyae042-B19","first-page":"374","article-title":"A deep learning approach for assessment of regional wall motion abnormality from echocardiographic images","volume":"13","author":"Kusunose","year":"2020","journal-title":"Cardiovasc Imaging"},{"key":"2024071810114084500_qyae042-B20","doi-asserted-by":"crossref","first-page":"102228","DOI":"10.1016\/j.media.2021.102228","article-title":"Shape registration with learned deformations for 3D shape reconstruction from sparse and incomplete point clouds","volume":"74","author":"Chen","year":"2021","journal-title":"Med Image Anal"},{"key":"2024071810114084500_qyae042-B21","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1136\/heartjnl-2021-319238","article-title":"Cross-sectional analysis of educational inequalities in primary prevention statin use in UK biobank","volume":"108","author":"Carter","year":"2022","journal-title":"Heart"},{"key":"2024071810114084500_qyae042-B22","doi-asserted-by":"crossref","first-page":"2139","DOI":"10.12688\/f1000research.21679.3","article-title":"R package \u2018QRISK3\u2019: an unofficial research purposed implementation of ClinRisk\u2019s QRISK3 algorithm into R","volume":"8","author":"Li","year":"2020","journal-title":"F1000Res"}],"container-title":["European Heart Journal - Imaging Methods and Practice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ehjimp\/advance-article-pdf\/doi\/10.1093\/ehjimp\/qyae042\/57653635\/qyae042.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjimp\/article-pdf\/2\/1\/qyae042\/58557116\/qyae042.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjimp\/article-pdf\/2\/1\/qyae042\/58557116\/qyae042.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T10:15:24Z","timestamp":1721297724000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjimp\/article\/doi\/10.1093\/ehjimp\/qyae042\/7672911"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1,16]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjimp\/qyae042","relation":{},"ISSN":["2755-9637"],"issn-type":[{"value":"2755-9637","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,1]]},"published":{"date-parts":[[2024,1]]},"article-number":"qyae042"}}