Deep Learning Analysis of Cardiac MRI in Legacy Datasets: Multi-Ethnic Study of Atherosclerosis

The Multi-Ethnic Study of Atherosclerosis (MESA), begun in 2000, was the first large cohort study to incorporate cardiovascular magnetic resonance (CMR) to study the mechanisms of cardiovascular disease in over 5,000 initially asymptomatic participants, and there is now a wealth of follow-up data over 20 years. However, the imaging technology used to generate the CMR images is no longer in routine use, and methods trained on modern data fail when applied to such legacy datasets. This study aimed to develop a fully automated CMR analysis pipeline that leverages the ability of machine learning algorithms to enable extraction of additional information from such a large-scale legacy dataset, expanding on the original manual analyses. We combined the original study analyses with new annotations to develop a set of automated methods for customizing 3D left ventricular (LV) shape models to each CMR exam and build a statistical shape atlas. We trained VGGNet convolutional neural networks using a transfer learning sequence between two-chamber, four-chamber, and short-axis MRI views to detect landmarks. A U-Net architecture was used to detect the endocardial and epicardial boundaries in short-axis images. The landmark detection network accurately predicted mitral valve and right ventricular insertion points with average error distance <2.5 mm. The agreement of the network with two observers was excellent (intraclass correlation coefficient >0.9). The segmentation network produced average Dice score of 0.9 for both myocardium and LV cavity. Differences between the manual and automated analyses were small, i.e., <1.0 ± 2.6 mL/m2 for indexed LV volume, 3.0 ± 6.4 g/m2 for indexed LV mass, and 0.6 ± 3.3% for ejection fraction. In an independent atlas validation dataset, the LV atlas built from the fully automated pipeline showed similar statistical relationships to an atlas built from the manual analysis. Hence, the proposed pipeline is not only a promising framework to automatically assess additional measures of ventricular function, but also to study relationships between cardiac morphologies and future cardiac events, in a large-scale population study.

[1]  Antonio J. Plaza,et al.  Image Segmentation Using Deep Learning: A Survey , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  James A. White,et al.  2021 Update on Safety of Magnetic Resonance Imaging: Joint Statement From Canadian Cardiovascular Society/Canadian Society for Cardiovascular Magnetic Resonance/Canadian Heart Rhythm Society. , 2021, The Canadian journal of cardiology.

[3]  Matthew B. Blaschko,et al.  Optimization for Medical Image Segmentation: Theory and Practice When Evaluating With Dice Score or Jaccard Index , 2020, IEEE Transactions on Medical Imaging.

[4]  E. Nagel,et al.  Standardized image interpretation and post-processing in cardiovascular magnetic resonance - 2020 update , 2020, Journal of Cardiovascular Magnetic Resonance.

[5]  E. Nagel,et al.  Standardized cardiovascular magnetic resonance imaging (CMR) protocols: 2020 update , 2020, Journal of Cardiovascular Magnetic Resonance.

[6]  Z. Jane Wang,et al.  An End-to-End Multi-Task Deep Learning Framework for Skin Lesion Analysis , 2020, IEEE Journal of Biomedical and Health Informatics.

[7]  P. Matthews,et al.  Large-scale Quality Control of Cardiac Imaging in Population Studies: Application to UK Biobank , 2020, Scientific Reports.

[8]  W. Curran,et al.  Deep learning in medical image registration: a review , 2019, Physics in medicine and biology.

[9]  2020: Update , 2020 .

[10]  D. Rueckert,et al.  Machine learning in cardiovascular magnetic resonance: basic concepts and applications , 2019, Journal of Cardiovascular Magnetic Resonance.

[11]  D. Rueckert,et al.  A Multicenter, Scan-Rescan, Human and Machine Learning CMR Study to Test Generalizability and Precision in Imaging Biomarker Analysis. , 2019, Circulation. Cardiovascular imaging.

[12]  Daniel Rueckert,et al.  Independent Left Ventricular Morphometric Atlases Show Consistent Relationships with Cardiovascular Risk Factors: A UK Biobank Study , 2019, Scientific Reports.

[13]  S. Plein,et al.  Deep Learning-based Method for Fully Automatic Quantification of Left Ventricle Function from Cine MR Images: A Multivendor, Multicenter Study. , 2019, Radiology.

[14]  Manu Goyal,et al.  Breast ultrasound lesions recognition: end-to-end deep learning approaches , 2018, Journal of medical imaging.

[15]  Alejandro F. Frangi,et al.  Statistical Shape Modeling of the Left Ventricle: Myocardial Infarct Classification Challenge , 2018, IEEE Journal of Biomedical and Health Informatics.

[16]  S. Serai,et al.  Measuring liver T2* and cardiac T2* in a single acquisition , 2018, Abdominal Radiology.

[17]  Alejandro F. Frangi,et al.  Automatic initialization and quality control of large‐scale cardiac MRI segmentations , 2018, Medical Image Anal..

[18]  Paolo Emilio Puddu,et al.  Morphologically normalized left ventricular motion indicators from MRI feature tracking characterize myocardial infarction , 2017, Scientific Reports.

[19]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[20]  Terry K Koo,et al.  A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research. , 2016, Journal Chiropractic Medicine.

[21]  M. Gold,et al.  Image Quality of Cardiac Magnetic Resonance Imaging in Patients With an Implantable Cardioverter Defibrillator System Designed for the Magnetic Resonance Imaging Environment , 2016, Circulation. Cardiovascular imaging.

[22]  Marios Anthimopoulos,et al.  Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network , 2016, IEEE Transactions on Medical Imaging.

[23]  Hoo-Chang Hoo-Chang Shin Shin,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, Ieee Transactions on Medical Imaging.

[24]  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.

[25]  Jae Y. Shin,et al.  Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? , 2016, IEEE transactions on medical imaging.

[26]  Alistair A. Young,et al.  Quantification of LV function and mass by cardiovascular magnetic resonance: multi-center variability and consensus contours , 2015, Journal of Cardiovascular Magnetic Resonance.

[27]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

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

[29]  Alistair A. Young,et al.  Atlas-Based Quantification of Cardiac Remodeling Due to Myocardial Infarction , 2014, PloS one.

[30]  Avan Suinesiaputra,et al.  Left ventricular shape variation in asymptomatic populations: the multi-ethnic study of atherosclerosis , 2014, Journal of Cardiovascular Magnetic Resonance.

[31]  Anuj Srivastava,et al.  Statistical Shape Analysis , 2014, Computer Vision, A Reference Guide.

[32]  Pau Medrano-Gracia,et al.  Atlas-based analysis of cardiac shape and function: correction of regional shape bias due to imaging protocol for population studies , 2013, Journal of Cardiovascular Magnetic Resonance.

[33]  P. Matthews,et al.  Imaging in population science: cardiovascular magnetic resonance in 100,000 participants of UK Biobank - rationale, challenges and approaches , 2013, Journal of Cardiovascular Magnetic Resonance.

[34]  Scott D Flamm,et al.  Standardized image interpretation and post processing in cardiovascular magnetic resonance: Society for Cardiovascular Magnetic Resonance (SCMR) Board of Trustees Task Force on Standardized Post Processing , 2013, Journal of Cardiovascular Magnetic Resonance.

[35]  M. Szklo,et al.  The Multi-Ethnic Study of Atherosclerosis (MESA) , 2012 .

[36]  Alistair A. Young,et al.  The Cardiac Atlas Project—an imaging database for computational modeling and statistical atlases of the heart , 2011, Bioinform..

[37]  L. Senelick It (review) , 2008 .

[38]  David A Bluemke,et al.  Cardiac cine MRI: Quantification of the relationship between fast gradient echo and steady‐state free precession for determination of myocardial mass and volumes , 2008, Journal of magnetic resonance imaging : JMRI.

[39]  S. Lai,et al.  Cardiovascular function in multi-ethnic study of atherosclerosis: normal values by age, sex, and ethnicity. , 2006, AJR. American journal of roentgenology.

[40]  R. Kronmal,et al.  Multi-Ethnic Study of Atherosclerosis: objectives and design. , 2002, American journal of epidemiology.

[41]  W. K. Bolstein,et al.  Basic: Concepts and Applications , 1987 .

[42]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[43]  A. F. Adams,et al.  The Survey , 2021, Dyslexia in Higher Education.