Deep learning predicts cardiovascular disease risks from lung cancer screening low dose computed tomography

Cancer patients have a higher risk of cardiovascular disease (CVD) mortality than the general population. Low dose computed tomography (LDCT) for lung cancer screening offers an opportunity for simultaneous CVD risk estimation in at-risk patients. Our deep learning CVD risk prediction model, trained with 30,286 LDCTs from the National Lung Cancer Screening Trial, achieves an area under the curve (AUC) of 0.871 on a separate test set of 2,085 subjects and identifies patients with high CVD mortality risks (AUC of 0.768). We validate our model against ECG-gated cardiac CT based markers, including coronary artery calcification (CAC) score, CAD-RADS score, and MESA 10-year risk score from an independent dataset of 335 subjects. Our work shows that, in high-risk patients, deep learning can convert LDCT for lung cancer screening into a dual-screening quantitative tool for CVD risk estimation.

[1]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[2]  R. Detrano,et al.  Quantification of coronary artery calcium using ultrafast computed tomography. , 1990, Journal of the American College of Cardiology.

[3]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[4]  Xiao-Hua Zhou,et al.  Statistical Methods in Diagnostic Medicine , 2002 .

[5]  Udo Hoffmann,et al.  Pericardial Fat, Visceral Abdominal Fat, Cardiovascular Disease Risk Factors, and Vascular Calcification in a Community-Based Sample: The Framingham Heart Study , 2008, Circulation.

[6]  Qingshan Liu,et al.  Lesion-Specific Coronary Artery Calcium Quantification for Predicting Cardiac Event with Multiple Instance Support Vector Machines , 2010, MICCAI.

[7]  W. Brown.  Framingham Heart Study. , 2011, Journal of Clinical Lipidology.

[8]  Maria A. Zuluaga,et al.  Learning from Only Positive and Unlabeled Data to Detect Lesions in Vascular CT Images , 2011, MICCAI.

[9]  Jame Abraham,et al.  Reduced lung cancer mortality with low-dose computed tomographic screening , 2011 .

[10]  C. Gatsonis,et al.  Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening , 2012 .

[11]  Dorin Comaniciu,et al.  Detection, Grading and Classification of Coronary Stenoses in Computed Tomography Angiography , 2011, MICCAI.

[12]  Laura M. Chihara,et al.  Mathematical Statistics with Resampling and R , 2011 .

[13]  D. Berry,et al.  Benefits and harms of CT screening for lung cancer: a systematic review. , 2012, JAMA.

[14]  E. Mohammadi,et al.  Barriers and facilitators related to the implementation of a physiological track and trigger system: A systematic review of the qualitative evidence , 2017, International journal for quality in health care : journal of the International Society for Quality in Health Care.

[15]  Max A. Viergever,et al.  Automatic Coronary Calcium Scoring in Low-Dose Chest Computed Tomography , 2012, IEEE Transactions on Medical Imaging.

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  William Pavlicek,et al.  Non-Calcified Coronary Atherosclerotic Plaque Characterization by Dual Energy Computed Tomography , 2014, IEEE Journal of Biomedical and Health Informatics.

[18]  Heang-Ping Chan,et al.  Computerized detection of noncalcified plaques in coronary CT angiography: evaluation of topological soft gradient prescreening method and luminal analysis. , 2014, Medical physics.

[19]  David Yankelevitz,et al.  Combined detection of coronary artery disease and lung cancer. , 2014, European heart journal.

[20]  M. Biddle,et al.  A report from the American Heart Association Council on Cardiovascular and Stroke Nursing. , 2015, The Journal of cardiovascular nursing.

[21]  P. Conway,et al.  Screening for lung cancer with low-dose CT--translating science into Medicare coverage policy. , 2015, The New England journal of medicine.

[22]  Max A. Viergever,et al.  Automatic Coronary Calcium Scoring in Non-Contrast-Enhanced ECG-Triggered Cardiac CT With Ambiguity Detection , 2015, IEEE Transactions on Medical Imaging.

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[24]  Lorenzo Torresani,et al.  Learning Spatiotemporal Features with 3D Convolutional Networks , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[25]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[26]  Scott G. Baginski,et al.  Association of Coronary Artery Calcification and Mortality in the National Lung Screening Trial: A Comparison of Three Scoring Methods. , 2015, Radiology.

[27]  R. Kronmal,et al.  10-Year Coronary Heart Disease Risk Prediction Using Coronary Artery Calcium and Traditional Risk Factors: Derivation in the MESA (Multi-Ethnic Study of Atherosclerosis) With Validation in the HNR (Heinz Nixdorf Recall) Study and the DHS (Dallas Heart Study). , 2015, Journal of the American College of Cardiology.

[28]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  J. Coatrieux,et al.  Automatic coronary calcium scoring using noncontrast and contrast CT images. , 2016, Medical physics.

[30]  Max A. Viergever,et al.  Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks , 2016, Medical Image Anal..

[31]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[32]  F. Rybicki,et al.  CAD-RADS™: Coronary Artery Disease - Reporting and Data System: An Expert Consensus Document of the Society of Cardiovascular Computed Tomography (SCCT), the American College of Radiology (ACR) and the North American Society for Cardiovascular Imaging (NASCI). Endorsed by the American College of Car , 2016, Journal of the American College of Radiology : JACR.

[33]  Max A. Viergever,et al.  Deep convolutional neural networks for automatic coronary calcium scoring in a screening study with low-dose chest CT , 2016, SPIE Medical Imaging.

[34]  Ramprasaath R. Selvaraju,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[35]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[36]  Andrew Zisserman,et al.  Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Max A. Viergever,et al.  Automatic Calcium Scoring in Low-Dose Chest CT Using Deep Neural Networks With Dilated Convolutions , 2017, IEEE Transactions on Medical Imaging.

[38]  Abhinav Gupta,et al.  Non-local Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[39]  Huangjian Yi,et al.  An automatic multi-class coronary atherosclerosis plaque detection and classification framework , 2018, Medical & Biological Engineering & Computing.

[40]  Raúl San José Estépar,et al.  Automated Agatston score computation in non-ECG gated CT scans using deep learning , 2018, Medical Imaging.

[41]  M. Jensen,et al.  Epicardial adipose tissue predicts incident cardiovascular disease and mortality in patients with type 2 diabetes , 2019, Cardiovascular Diabetology.

[42]  Lei Deng,et al.  A population-based study of cardiovascular disease mortality risk in US cancer patients. , 2019, European heart journal.

[43]  G. Corrado,et al.  End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography , 2019, Nature Medicine.

[44]  Liran Goshen,et al.  Unsupervised Abnormality Detection through Mixed Structure Regularization (MSR) in Deep Sparse Autoencoders , 2019, Medical physics.

[45]  Francesca N. Delling,et al.  Heart Disease and Stroke Statistics—2019 Update: A Report From the American Heart Association , 2019, Circulation.

[46]  K. Kumamaru,et al.  Diagnostic accuracy of 3D deep-learning-based fully automated estimation of patient-level minimum fractional flow reserve from coronary computed tomography angiography. , 2019, European heart journal cardiovascular Imaging.

[47]  Nikolas Lessmann,et al.  Direct Automatic Coronary Calcium Scoring in Cardiac and Chest CT , 2019, IEEE Transactions on Medical Imaging.

[48]  Ben Glocker,et al.  TeTrIS: Template Transformer Networks for Image Segmentation With Shape Priors , 2019, IEEE Transactions on Medical Imaging.

[49]  Yasutaka Baba,et al.  Machine-learning integration of CT histogram analysis to evaluate the composition of atherosclerotic plaques: Validation with IB-IVUS. , 2019, Journal of cardiovascular computed tomography.

[50]  S. Digumarthy,et al.  Impact of Significant Coronary Artery Calcification Reported on Low-Dose Computed Tomography Lung Cancer Screening , 2019, Journal of thoracic imaging.

[51]  Jun Fu,et al.  Dual Attention Network for Scene Segmentation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Max A. Viergever,et al.  A Recurrent CNN for Automatic Detection and Classification of Coronary Artery Plaque and Stenosis in Coronary CT Angiography , 2018, IEEE Transactions on Medical Imaging.

[53]  B. Zacharia,et al.  Stroke among cancer patients , 2019, Nature Communications.

[54]  M. Kunitski,et al.  Double-slit photoelectron interference in strong-field ionization of the neon dimer , 2018, Nature Communications.

[55]  Max A. Viergever,et al.  Direct Prediction of Cardiovascular Mortality from Low-dose Chest CT using Deep Learning , 2018, Medical Imaging: Image Processing.

[56]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[57]  Harry J de Koning,et al.  Reduced Lung-Cancer Mortality with Volume CT Screening in a Randomized Trial. , 2020, The New England journal of medicine.

[58]  A. A. Shabestari,et al.  A new approach to cardiac fat volume assessment and the correlation with coronary artery calcification , 2020, Romanian journal of internal medicine = Revue roumaine de medecine interne.

[59]  Kipp W. Johnson,et al.  Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network , 2020, Nature Medicine.

[60]  Qianli Liao,et al.  Theoretical issues in deep networks , 2020, Proceedings of the National Academy of Sciences.

[61]  Nicholas G Zaorsky,et al.  Fatal heart disease among cancer patients , 2020, Nature Communications.

[62]  Nicholas G Zaorsky,et al.  Long‐term causes of death among pediatric patients with cancer , 2020, Cancer.

[63]  Knowledge-Based Analysis for Mortality Prediction From CT Images , 2019, IEEE Journal of Biomedical and Health Informatics.

[64]  Michael T. Lu,et al.  Deep convolutional neural networks to predict cardiovascular risk from computed tomography , 2021, Nature Communications.