Myocardium segmentation on 3D spect images

This paper presents a segmentation process of the myocardium, endocardium and epicardium surfaces of the heart from 3D SPECT images to compute a heterogeneity index. This index represents the distribution of the activity in the myocardium. Because of the low resolution of SPECT images, the thickness of the myocardium is 1 to 4 voxels and a sub-voxel accuracy is therefore needed. The segmentation process is based on the minimization of an energy by dynamic programming after a coarse segmentation to define the center surface of the myocardium. A Gaussian mixture is fitted on the data to ensure subvoxel accuracy. The heterogeneity index is compared to the reference index on 58 SPECT images and the segmentation is visually validated on 300 SPECT images by a clinician.

[1]  Huaifei Hu,et al.  Hybrid segmentation of left ventricle in cardiac MRI using Gaussian-mixture model and region restricted dynamic programming. , 2013, Magnetic resonance imaging.

[2]  M. Carlsson,et al.  Time resolved three-dimensional automated segmentation of the left ventricle , 2005, Computers in Cardiology, 2005.

[3]  Michel Desvignes,et al.  Contour tracking by minimal cost path approach: application to cephalometry , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[4]  Johan Montagnat,et al.  4D deformable models with temporal constraints: application to 4D cardiac image segmentation , 2005, Medical Image Anal..

[5]  G Germano,et al.  A new algorithm for the quantitation of myocardial perfusion SPECT. I: technical principles and reproducibility. , 2000, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[6]  Alejandro F. Frangi,et al.  Automatic Construction of 3D-ASM Intensity Models by Simulating Image Acquisition: Application to Myocardial Gated SPECT Studies , 2008, IEEE Transactions on Medical Imaging.

[7]  Piotr J. Slomka,et al.  Heart chambers and whole heart segmentation techniques: review , 2012, J. Electronic Imaging.

[8]  Einar Heiberg,et al.  Development and validation of a new automatic algorithm for quantification of left ventricular volumes and function in gated myocardial perfusion SPECT using cardiac magnetic resonance as reference standard , 2011, Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology.

[9]  Caroline Petitjean,et al.  A review of segmentation methods in short axis cardiac MR images , 2011, Medical Image Anal..

[10]  Yi-Hwa Liu,et al.  Quantification of nuclear cardiac images: The Yale approach , 2007, Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology.

[11]  Michel Barlaud,et al.  Space-time segmentation using level set active contours applied to myocardial gated SPECT , 2001, IEEE Transactions on Medical Imaging.

[12]  K. Sun,et al.  Segmentation of the left ventricle in myocardial perfusion SPECT using variational level set formulation , 2007, 2007 IEEE Nuclear Science Symposium Conference Record.

[13]  K. Gould,et al.  Clinical evaluation of a new concept: resting myocardial perfusion heterogeneity quantified by markovian analysis of PET identifies coronary microvascular dysfunction and early atherosclerosis in 1,034 subjects. , 2005, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[14]  E V Garcia,et al.  New algorithm for quantification of myocardial perfusion SPECT. , 2001, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[15]  Amine Chikh,et al.  Endocardial Border Detection in Cardiac Magnetic Resonance Images Using Level Set Method , 2012, Journal of Digital Imaging.

[16]  P H Murphy,et al.  Hemodialysis in a patient being treated with 153Sm. , 2001, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[17]  Yi Wang,et al.  Automatic Left Ventricle Segmentation Using Iterative Thresholding and an Active Contour Model With Adaptation on Short-Axis Cardiac MRI , 2010, IEEE Transactions on Biomedical Engineering.

[18]  Anna Celler,et al.  A template-based approach to semi-quantitative SPECT myocardial perfusion imaging: Independent of normal databases. , 2011, Medical physics.

[19]  Lu Huang,et al.  Automatic Segmentation of the Left Ventricle in Cardiac MRI Using Local Binary Fitting Model and Dynamic Programming Techniques , 2014, PloS one.