Adaptive Fruitfly Based Modified Region Growing Algorithm for Cardiac Fat Segmentation Using Optimal Neural Network

Epicardial adipose tissue is a visceral fat that has remained an entity of concern for decades owing to its high correlation with coronary heart disease. It continues to stump medical practitioners on the pretext of its relevance with pericardial fat and its dependence on a numerous other parameters including ethnicity and physique of an individual. This calls for a fool-proof algorithm that promises accurate classification and segmentation, hence an immaculate prediction. CT is immensely popular and widely preferred for diagnosis. Implementation of an improvised algorithm in CT would be a natural necessity. This research work proposes a Fruitfly Algorithm based Modified region growing algorithm is applied to the acquired CT images to segment fat accurately. The proposed methodology promises image registration and classification in order to segment two cardiac fats namely epicardial, pericardial and mediastinal. The main contributions are (1) Fat feature extraction: Construction of GLCM features CT image (2) Development of GWO based optimal neural network for classification; (3) Modeling the fat segmentation using modified region growing algorithm with Fruitfly optimization. The entire experimentation has been implemented in MATLAB simulation environment and final result is expected to flaunt a definite distinction between cardiac mediastinal and epicardial fats. Parallely, the accuracy, sensitivity, specificity, FPR and FNR have been stated and contrasted methodically with the existing methodology. This venture aims at spurring the healthcare industry towards smarter computational techniques that multiplies efficiency manifold.

[1]  C. Rochitte,et al.  Epicardial fat is associated with severity of subclinical coronary atherosclerosis in familial hypercholesterolemia. , 2016, Atherosclerosis.

[2]  S. Anand,et al.  Secured and compound 3-D chaos image encryption using hybrid mutation and crossover operator , 2018, Multimedia Tools and Applications.

[3]  H. Sacks,et al.  Human epicardial adipose tissue: a review. , 2007, American heart journal.

[4]  Moi Hoon Yap,et al.  Enhancement of MRI human thigh muscle segmentation by template-based framework , 2014, 2014 IEEE International Conference on Control System, Computing and Engineering (ICCSCE 2014).

[5]  Takeshi Nakaura,et al.  Effect of iterative reconstruction on variability and reproducibility of epicardial fat volume quantification by cardiac CT. , 2016, Journal of cardiovascular computed tomography.

[6]  Shuai Liu,et al.  Comparisons of fat quantification methods based on MRI segmentation , 2014, 2014 IEEE International Conference on Mechatronics and Automation.

[7]  Daw-Tung Lin,et al.  Autonomous detection of pulmonary nodules on CT images with a neural network-based fuzzy system. , 2005, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[8]  John McManigle,et al.  The association of left atrial low-voltage regions on electroanatomic mapping with low attenuation regions on cardiac computed tomography perfusion imaging in patients with atrial fibrillation. , 2015, Heart rhythm.

[9]  Manuel Graña,et al.  Automated Segmentation of Subcutaneous and Visceral Adipose Tissues from MRI , 2016 .

[10]  D A Bluemke,et al.  Pericardial fat is associated with carotid stiffness in the Multi-Ethnic Study of Atherosclerosis. , 2011, Nutrition, metabolism, and cardiovascular diseases : NMCD.

[11]  Max A. Viergever,et al.  Multi-Atlas-Based Segmentation With Local Decision Fusion—Application to Cardiac and Aortic Segmentation in CT Scans , 2009, IEEE Transactions on Medical Imaging.

[12]  Ukrit Watchareeruetai,et al.  Fat detection algorithm for liver biopsy images , 2014, 2014 International Electrical Engineering Congress (iEECON).

[13]  Jürgen Weese,et al.  Automated segmentation of the left ventricle in cardiac MRI , 2004, Medical Image Anal..

[14]  J J Mallet,et al.  Delineation and quantitation of brain lesions by fuzzy clustering in positron emission tomography. , 1996, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[15]  Fabian Bamberg,et al.  Comparison of epicardial fat volume by computed tomography in black versus white patients with acute chest pain. , 2014, The American journal of cardiology.

[16]  William Puech,et al.  Hierarchical MRI segmentation of the musculoskeletal system using texture analysis and topologigcal constraints , 2014, 2014 5th European Workshop on Visual Information Processing (EUVIP).

[17]  Noel E. O'Connor,et al.  Fat quantification in MRI-defined lumbar muscles , 2014, 2014 4th International Conference on Image Processing Theory, Tools and Applications (IPTA).

[18]  R. Premkumar,et al.  Secured Permutation and Substitution Based Image Encryption Algorithm for Medical Security Applications , 2016 .

[19]  Sundar Chidambaram,et al.  Epicardial fat thickness: A surrogate marker of coronary artery disease - Assessment by echocardiography. , 2016, Indian heart journal.

[20]  Ioannis A. Kakadiaris,et al.  Knowledge-based quantification of pericardial fat in non-contrast CT data , 2010, Medical Imaging.

[21]  Mohamed Marwan,et al.  Quantification of epicardial fat by computed tomography: why, when and how? , 2013, Journal of cardiovascular computed tomography.

[22]  Yan Zhou,et al.  Automatic Liver Segmentation and Hepatic Fat Fraction Assessment in MRI , 2014, 2014 22nd International Conference on Pattern Recognition.

[23]  Mingyue Ding,et al.  Non-rigid multi-modal medical image registration by combining L-BFGS-B with cat swarm optimization , 2015, Inf. Sci..

[24]  Behrouz Khodadad,et al.  Epicardial and Pericardial Fat Volume Correlate with the Severity of Coronary Artery Stenosis , 2014, Journal of cardiovascular and thoracic research.

[25]  Vladimir Zlokolica,et al.  Epicardial fat registration by local adaptive morphology-thresholding based 2D segmentation , 2014, Proceedings ELMAR-2014.

[26]  Ioannis A. Kakadiaris,et al.  Automated Pericardial Fat Quantification in CT Data , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[27]  T. Vogl,et al.  Influence of technical parameters on epicardial fat volume quantification at cardiac CT. , 2015, European journal of radiology.

[28]  Mauro Pepi,et al.  Comparison of cardiac computed tomography versus cardiac magnetic resonance for characterization of left atrium anatomy before radiofrequency catheter ablation of atrial fibrillation. , 2015, International journal of cardiology.

[29]  Aura Conci,et al.  Towards the automated segmentation of epicardial and mediastinal fats: A multi-manufacturer approach using intersubject registration and random forest , 2015, 2015 IEEE International Conference on Industrial Technology (ICIT).

[30]  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..

[31]  Olivera Sveljo,et al.  Estimation of subcutaneous and visceral fat tissue volume on abdominal MR images , 2014, 12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL).

[32]  Hong Song,et al.  Breast tissue segmentation on MR images using KFCM with spatial constraints , 2014, 2014 IEEE International Conference on Granular Computing (GrC).

[33]  Piotr J. Slomka,et al.  Automated epicardial fat volume quantification from non-contrast CT , 2014, Medical Imaging.

[34]  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.