Automated cardiovascular magnetic resonance image analysis with fully convolutional networks

Wenjia Bai1, Matthew Sinclair1, Giacomo Tarroni1, Ozan Oktay1, Martin Rajchl1, Ghislain Vaillant1, Aaron M. Lee2, Nay Aung2, Elena Lukaschuk3, Mihir M. Sanghvi2, Filip Zemrak2, Kenneth Fung2, José Miguel Paiva2, Valentina Carapella3, Young Jin Kim3, Hideaki Suzuki4, Bernhard Kainz1, Paul M. Matthews4, Steffen E. Petersen2, Stefan K. Piechnik3, Stefan Neubauer3, Ben Glocker1, Daniel Rueckert1
1Biomedical Image Analysis Group, Department of Computing, Imperial College London, London, UK
2NIHR Biomedical Research Centre at Barts, Queen Mary University of London, London, UK
3Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
4Division of Brain Sciences, Department of Medicine, Imperial College London, London, UK

Tóm tắt

Từ khóa


Tài liệu tham khảo

World Health Organisation. Cardiovascular diseases (CVDs) fact sheet. http://www.who.int/mediacentre/factsheets/fs317/en/. Accessed 11 July 2017.

Ripley, 2016, Cardiovascular magnetic resonance imaging: what the general cardiologist should know, Heart, 102, 1589, 10.1136/heartjnl-2015-307896

Fihn, 2012, 2012 ACCF/AHA/ACP/AATS/PCNA/SCAI/STS guideline for the diagnosis and management of patients with stable ischemic heart disease, Circulation, 60, 44

McMurray, 2012, ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure 2012, Eur J Heart Fail, 14, 803, 10.1093/eurjhf/hfs105

UK Biobank Imaging Study. http://imaging.ukbiobank.ac.uk/. Accessed 11 July 2017.

He, 2015, Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification

Silver, 2016, Mastering the game of Go with deep neural networks and tree search, Nature, 529, 484, 10.1038/nature16961

Esteva, 2017, Dermatologist-level classification of skin cancer with deep neural networks, Nature, 542, 115, 10.1038/nature21056

Long, 2017, An artificial intelligence platform for the multihospital collaborative management of congenital cataracts, Nat Biomed Eng, 1, 0024, 10.1038/s41551-016-0024

Avendi, 2016, A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI, Med Image Anal, 30, 108, 10.1016/j.media.2016.01.005

Ngo, 2017, Combining deep learning and level set for the automated segmentation of the left ventricle of the heart from cardiac cine magnetic resonance, Med Image Anal, 35, 159, 10.1016/j.media.2016.05.009

Tran PV. A fully convolutional neural network for cardiac segmentation in short-axis MRI. arXiv:1604.00494. 2017.

Lieman-Sifry, 2017, FastVentricle: Cardiac segmentation with ENet

Kaggle Second Annual Data Science Bowl. https://www.kaggle.com/c/second-annual-data-science-bowl/. Accessed 11 July 2017.

MICCAI 2017 ACDC Challenge. https://www.creatis.insa-lyon.fr/Challenge/acdc/. Accessed 25 Oct 2017.

UK Biobank Data Showcase. http://biobank.ctsu.ox.ac.uk/crystal/label.cgi. Accessed 19 Nov 2017.

Petersen, 2016, UK Biobank's cardiovascular magnetic resonance protocol, J Cardiovasc Magn Reson, 18, 8, 10.1186/s12968-016-0227-4

Petersen, 2017, Reference ranges for cardiac structure and function using cardiovascular magnetic resonance (CMR) in Caucasians from the UK Biobank population cohort, J Cardiovasc Magn Reson, 19, 18, 10.1186/s12968-017-0327-9

Long, 2015, Fully convolutional networks for semantic segmentation

Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations. San Diego: 2015. p. 1–14.

Ronneberger, 2015, U-Net: Convolutional networks for biomedical image segmentation

Kingma D, Ba J. Adam: A method for stochastic optimization. In: International Conference on Learning Representations. San Diego: 2015.

Grothues, 2002, Comparison of interstudy reproducibility of cardiovascular magnetic resonance with two-dimensional echocardiography in normal subjects and in patients with heart failure or left ventricular hypertrophy, Am J Cardiol, 90, 29, 10.1016/S0002-9149(02)02381-0

Rider, 2009, Determinants of left ventricular mass in obesity; a cardiovascular magnetic resonance study, J Cardiovasc Magn Reson, 11, 9, 10.1186/1532-429X-11-9

He, 2016, Deep residual learning for image recognition

Fry, 2017, Comparison of sociodemographic and health-related characteristics of UK biobank participants with those of the general population, Am J Epidemiol, 186, 1026, 10.1093/aje/kwx246

Radau P, et al. Evaluation framework for algorithms segmenting short axis cardiac MRI. The MIDAS Journal - Cardiac MR Left Ventricle Segmentation Challenge. 2009. http://hdl.handle.net/10380/3070.

Bernard O, et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved?IEEE Trans Med Imaging, in early access. 2018.

MICCAI 2009 LV Segmentation Challenge. http://smial.sri.utoronto.ca/LV_Challenge/Data.html. Accessed 1 Feb 2018.

Marcus G. Deep learning: A critical appraisal. arXiv:1801.00631. 2018.

Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning. Lille: 2015. p. 448–56.

Transposed convolution. http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html. Accessed 30 Jan 2018.

Ngo, 2013, Left ventricle segmentation from cardiac MRI combining level set methods with deep belief networks

UK Biobank Register and Apply. http://www.ukbiobank.ac.uk/register-apply/. Accessed 11 July 2017.