A semi-automatic approach for epicardial adipose tissue segmentation and quantification on cardiac CT scans

Many studies have shown that epicardial fat is associated with a higher risk of heart diseases. Accurate epicardial adipose tissue quantification is still an open research issue. Considering that manual approaches are generally user-dependent and time-consuming, computer-assisted tools can considerably improve the result repeatability as well as reduce the time required for performing an accurate segmentation. Unfortunately, fully automatic strategies might not always identify the Region of Interest (ROI) correctly. Moreover, they could require user interaction for handling unexpected events. This paper proposes a semi-automatic method for Epicardial Fat Volume (EFV) segmentation and quantification. Unlike supervised Machine Learning approaches, the method does not require any initial training or modeling phase to set up the system. As a further key novelty, the method also yields a subdivision into quartiles of the adipose tissue density. Quartile-based analysis conveys information about fat densities distribution, enabling an in-depth study towards a possible correlation between fat amounts, fat distribution, and heart diseases. Experimental tests were performed on 50 Calcium Score (CaSc) series and 95 Coronary Computed Tomography Angiography (CorCTA) series. Area-based and distance-based metrics were used to evaluate the segmentation accuracy, by obtaining Dice Similarity Coefficient (DSC) = 93.74% and Mean Absolute Distance (MAD) = 2.18 for CaSc, as well as DSC = 92.48% and MAD = 2.87 for CorCTA. Moreover, the Pearson and Spearman coefficients were computed for quantifying the correlation between the ground-truth EFV and the corresponding automated measurement, by obtaining 0.9591 and 0.9490 for CaSc, and 0.9513 and 0.9319 for CorCTA, respectively. In conclusion, the proposed EFV quantification and analysis method represents a clinically useable tool assisting the cardiologist to gain insights into a specific clinical scenario and leading towards personalized diagnosis and therapy.

[1]  Davide Moroni,et al.  Quantification of Epicardial Fat by Cardiac CT Imaging , 2010, The open medical informatics journal.

[2]  R M Harrison,et al.  A comparison of two methods for measuring the signal to noise ratio on MR images , 1999, Physics in medicine and biology.

[3]  F. Boas,et al.  CT artifacts: Causes and reduction techniques , 2012 .

[4]  Guang Yang,et al.  Evaluation of algorithms for Multi-Modality Whole Heart Segmentation: An open-access grand challenge , 2019, Medical Image Anal..

[5]  Ao Li,et al.  A novel end-to-end brain tumor segmentation method using improved fully convolutional networks , 2019, Comput. Biol. Medicine.

[6]  Filippo Cademartiri,et al.  Quantification of epicardial fat with cardiac CT angiography and association with cardiovascular risk factors in symptomatic patients: from the ALTER-BIO (Alternative Cardiovascular Bio-Imaging markers) registry. , 2019, Diagnostic and interventional radiology.

[7]  S. Cha,et al.  Epicardial Fat and Its Association with Cardiovascular Risk: A Cross-Sectional Observational Study , 2010, Heart views : the official journal of the Gulf Heart Association.

[8]  P. Sanders,et al.  Epicardial adipose tissue and atrial fibrillation. , 2014, Cardiovascular research.

[9]  Vladimir Zlokolica,et al.  Semiautomatic Epicardial Fat Segmentation Based on Fuzzy c-Means Clustering and Geometric Ellipse Fitting , 2017, Journal of healthcare engineering.

[10]  J. Leipsic,et al.  State of the Art: Iterative CT Reconstruction Techniques. , 2015, Radiology.

[11]  Coert Metz,et al.  Automatic quantification of epicardial fat volume on non-enhanced cardiac CT scans using a multi-atlas segmentation approach. , 2013, Medical physics.

[12]  Max A. Viergever,et al.  ConvNet-Based Localization of Anatomical Structures in 3-D Medical Images , 2017, IEEE Transactions on Medical Imaging.

[13]  M. Nacif,et al.  Cardiac magnetic resonance imaging and computed tomography in ischemic cardiomyopathy: an update* , 2016, Radiologia brasileira.

[14]  Anqi Qiu,et al.  Population Differences in Brain Morphology and Microstructure among Chinese, Malay, and Indian Neonates , 2012, PloS one.

[15]  S. Yamashita,et al.  Abdominal fat: standardized technique for measurement at CT. , 1999, Radiology.

[16]  R. Rajani,et al.  CORONARY ARTERY ANOMALIES : THE NORMAL AND THE ABNORMAL , 2016 .

[17]  Aura Conci,et al.  Machine learning in the prediction of cardiac epicardial and mediastinal fat volumes , 2017, Comput. Biol. Medicine.

[18]  Fredrik Kahl,et al.  Automatic pericardium segmentation and quantification of epicardial fat from computed tomography angiography , 2016, Journal of medical imaging.

[19]  F. Cabitza,et al.  Unintended Consequences of Machine Learning in Medicine , 2017, JAMA.

[20]  Ancient and recent admixture layers in Sicily and Southern Italy trace multiple migration routes along the Mediterranean , 2017, Scientific Reports.

[21]  Arthur W. Toga,et al.  The construction of a Chinese MRI brain atlas: A morphometric comparison study between Chinese and Caucasian cohorts , 2010, NeuroImage.

[22]  Massimo Midiri,et al.  A fully automatic 2D segmentation method for uterine fibroid in MRgFUS treatment evaluation , 2015, Comput. Biol. Medicine.

[23]  F. Leonetti,et al.  Adiponectin expression in human epicardial adipose tissue in vivo is lower in patients with coronary artery disease. , 2005, Cytokine.

[24]  Damini Dey,et al.  Pericardial fat burden on ECG-gated noncontrast CT in asymptomatic patients who subsequently experience adverse cardiovascular events. , 2010, JACC. Cardiovascular imaging.

[25]  Jichao Zhao,et al.  Fully Automatic Left Atrium Segmentation From Late Gadolinium Enhanced Magnetic Resonance Imaging Using a Dual Fully Convolutional Neural Network , 2019, IEEE Transactions on Medical Imaging.

[26]  Danica Marinac-Dabic,et al.  A Road Map for Translational Research on Artificial Intelligence in Medical Imaging: From the 2018 National Institutes of Health/RSNA/ACR/The Academy Workshop. , 2019, Journal of the American College of Radiology : JACR.

[27]  Kortelainen Ml.  Myocardial infarction and coronary pathology in severely obese people examined at autopsy. , 2002 .

[28]  Allan Hanbury,et al.  Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool , 2015, BMC Medical Imaging.

[29]  Roberto Pirrone,et al.  A framework for data-driven adaptive GUI generation based on DICOM , 2018, J. Biomed. Informatics.

[30]  R. F. Wagner,et al.  SNR and DQE analysis of broad spectrum X-ray imaging , 1985 .

[31]  Eugenio Picano,et al.  Pericardial rather than epicardial fat is a cardiometabolic risk marker: an MRI vs echo study. , 2011, Journal of the American Society of Echocardiography : official publication of the American Society of Echocardiography.

[32]  Kuncheng Li,et al.  Construction of brain atlases based on a multi-center MRI dataset of 2020 Chinese adults , 2015, Scientific Reports.

[33]  Filippo Cademartiri,et al.  Quantification of epicardial adipose tissue in coronary calcium score and CT coronary angiography image data sets: comparison of attenuation values, thickness and volumes. , 2016, The British journal of radiology.

[34]  L. Królicki,et al.  Relation of proinflammatory activity of epicardial adipose tissue to the occurrence of atrial fibrillation. , 2014, The American journal of cardiology.

[35]  Piotr J. Slomka,et al.  Automated pericardial fat quantification from coronary magnetic resonance angiography: feasibility study , 2015, MIUA.

[36]  Gözde B. Ünal,et al.  Tumor-Cut: Segmentation of Brain Tumors on Contrast Enhanced MR Images for Radiosurgery Applications , 2012, IEEE Transactions on Medical Imaging.

[37]  Giancarlo Mauri,et al.  USE-Net: incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets , 2019, Neurocomputing.

[38]  Sébastien Ourselin,et al.  GAS: A genetic atlas selection strategy in multi‐atlas segmentation framework , 2019, Medical Image Anal..

[39]  A. Conci,et al.  A novel approach for the automated segmentation and volume quantification of cardiac fats on computed tomography , 2021, Comput. Methods Programs Biomed..

[40]  Kazunari Ishii,et al.  Gender and age differences in normal adult human brain: Voxel‐based morphometric study , 2011, Human brain mapping.

[41]  Juan Antonio Hernández Tamames,et al.  Automated quantification of epicardial adipose tissue in cardiac magnetic resonance imaging , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[42]  J. Shirani,et al.  Clinical significance of epicardial fat measured using cardiac multislice computed tomography. , 2008, The American journal of cardiology.

[43]  J. Min,et al.  Machine learning in cardiac CT: Basic concepts and contemporary data. , 2018, Journal of cardiovascular computed tomography.

[44]  Marie-Pierre Jolly,et al.  Interactive Organ Segmentation Using Graph Cuts , 2000, MICCAI.

[45]  I. Kakadiaris,et al.  Computer-aided non-contrast CT-based quantification of pericardial and thoracic fat and their associations with coronary calcium and Metabolic Syndrome. , 2010, Atherosclerosis.

[46]  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.

[47]  R. Detrano,et al.  The Association of Pericardial Fat With Calcified Coronary Plaque , 2008, Obesity.

[48]  Yuanfang Guan,et al.  Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. , 2018, European heart journal.

[49]  Xu Wang,et al.  Generalizing Deep Models for Ultrasound Image Segmentation , 2018, MICCAI.

[50]  Giancarlo Mauri,et al.  GTVcut for neuro-radiosurgery treatment planning: an MRI brain cancer seeded image segmentation method based on a cellular automata model , 2017, Natural Computing.

[51]  O. Rickards,et al.  Genetic history of the population of Sicily. , 1998, Human biology.

[52]  C. Bartolozzi,et al.  Quantitative analysis of epicardial fat volume: effects of scanning protocol and reproducibility of measurements in non-contrast cardiac CT vs. coronary CT angiography. , 2017, Quantitative imaging in medicine and surgery.

[53]  Prashanthan Sanders,et al.  Pericardial fat is associated with atrial fibrillation severity and ablation outcome. , 2011, Journal of the American College of Cardiology.

[54]  M. Jinzaki,et al.  Increased epicardial fat volume quantified by 64-multidetector computed tomography is associated with coronary atherosclerosis and totally occlusive lesions. , 2009, Circulation journal : official journal of the Japanese Circulation Society.