Fully automatic multi-atlas segmentation of CTA for partial volume correction in cardiac SPECT/CT

Anatomical-based partial volume correction (PVC) has been shown to improve image quality and quantitative accuracy in cardiac SPECT/CT. However, this method requires manual segmentation of various organs from contrast-enhanced computed tomography angiography (CTA) data. In order to achieve fully automatic CTA segmentation for clinical translation, we investigated the most common multi-atlas segmentation methods. We also modified the multi-atlas segmentation method by introducing a novel label fusion algorithm for multiple organ segmentation to eliminate overlap and gap voxels. To evaluate our proposed automatic segmentation, eight canine 99mTc-labeled red blood cell SPECT/CT datasets that incorporated PVC were analyzed, using the leave-one-out approach. The Dice similarity coefficient of each organ was computed. Compared to the conventional label fusion method, our proposed label fusion method effectively eliminated gaps and overlaps and improved the CTA segmentation accuracy. The anatomical-based PVC of cardiac SPECT images with automatic multi-atlas segmentation provided consistent image quality and quantitative estimation of intramyocardial blood volume, as compared to those derived using manual segmentation. In conclusion, our proposed automatic multi-atlas segmentation method of CTAs is feasible, practical, and facilitates anatomical-based PVC of cardiac SPECT/CT images.

[1]  S. Moore,et al.  Clinical Myocardial Perfusion PET/CT* , 2007, Journal of Nuclear Medicine.

[2]  D. Hill,et al.  Medical image registration , 2001, Physics in medicine and biology.

[3]  Xenophon Papademetris,et al.  BioImage Suite: An integrated medical image analysis suite: An update. , 2006, The insight journal.

[4]  I. Buvat,et al.  A review of partial volume correction techniques for emission tomography and their applications in neurology, cardiology and oncology , 2012, Physics in medicine and biology.

[5]  Daniel Rueckert,et al.  Automatic anatomical brain MRI segmentation combining label propagation and decision fusion , 2006, NeuroImage.

[6]  Torsten Rohlfing,et al.  Evaluation of atlas selection strategies for atlas-based image segmentation with application to confocal microscopy images of bee brains , 2004, NeuroImage.

[7]  Hui Liu,et al.  Noise suppressed partial volume correction for cardiac SPECT/CT. , 2016, Medical physics.

[8]  Michael Unser,et al.  Fast parametric elastic image registration , 2003, IEEE Trans. Image Process..

[9]  Yariv Grobshtein,et al.  End-expiration respiratory gating for a high-resolution stationary cardiac SPECT system , 2014, Physics in medicine and biology.

[10]  Márcio Sarroglia Pinho,et al.  Automated Methods for Hippocampus Segmentation: the Evolution and a Review of the State of the Art , 2014, Neuroinformatics.

[11]  Bennett A Landman,et al.  Non-local statistical label fusion for multi-atlas segmentation , 2013, Medical Image Anal..

[12]  Bennett A Landman,et al.  Efficient multi-atlas abdominal segmentation on clinically acquired CT with SIMPLE context learning , 2015, Medical Image Anal..

[13]  Daniel Rueckert,et al.  A Probabilistic Patch-Based Label Fusion Model for Multi-Atlas Segmentation With Registration Refinement: Application to Cardiac MR Images , 2013, IEEE Transactions on Medical Imaging.

[14]  Daniel Rueckert,et al.  Multi-atlas segmentation with augmented features for cardiac MR images , 2015, Medical Image Anal..

[15]  Tianyu Ma,et al.  Anatomical-based partial volume correction for low-dose dedicated cardiac SPECT/CT , 2015, Physics in medicine and biology.

[16]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[17]  D. Louis Collins,et al.  BEaST: Brain extraction based on nonlocal segmentation technique , 2012, NeuroImage.

[18]  Dustin Scheinost,et al.  New open‐source ictal SPECT analysis method implemented in BioImage Suite , 2010, Epilepsia.

[19]  Paul Knaapen,et al.  Diagnosing coronary artery disease with hybrid PET/CT: It takes two to tango , 2013, Journal of Nuclear Cardiology.

[20]  Daniel Rueckert,et al.  Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm , 2004, Medical Image Anal..

[21]  Tianyu Ma,et al.  Scatter and crosstalk corrections for (99m)Tc/(123)I dual-radionuclide imaging using a CZT SPECT system with pinhole collimators. , 2015, Medical physics.

[22]  T van Walsum,et al.  Evaluation of a multi-atlas based method for segmentation of cardiac CTA data: a large-scale, multicenter, and multivendor study. , 2010, Medical physics.

[23]  Rahil Garnavi,et al.  Multi-atlas label fusion using hybrid of discriminative and generative classifiers for segmentation of cardiac MR images , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).