Right ventricular segmentation in cardiac MRI with moving mesh correspondences

This study investigates automatic propagation of the right ventricle (RV) endocardial and epicardial boundaries in 4D (3D+time) magnetic resonance imaging (MRI) sequences. Based on a moving mesh (or grid generation) framework, the proposed algorithm detects the endocardium and epicardium within each cardiac phase via point-to-point correspondences. The proposed method has the following advantages over prior RV segmentation works: (1) it removes the need for a time-consuming, manually built training set; (2) it does not make prior assumptions as to the intensity distributions or shape; (3) it provides a sequence of corresponding points over time, a comprehensive input that can be very useful in cardiac applications other than segmentation, e.g., regional wall motion analysis; and (4) it is more flexible for congenital heart disease where the RV undergoes high variations in shape. Furthermore, the proposed method allows comprehensive RV volumetric analysis over the complete cardiac cycle as well as automatic detections of end-systolic and end-diastolic phases because it provides a segmentation for each time step. Evaluated quantitatively over the 48-subject data set of the MICCAI 2012 RV segmentation challenge, the proposed method yielded an average Dice score of 0.84±0.11 for the epicardium and 0.79±0.17 for the endocardium. Further, quantitative evaluations of the proposed approach in comparisons to manual contours over 23 infant hypoplastic left heart syndrome patients yielded a Dice score of 0.82±0.14, which demonstrates the robustness of the algorithm.

[1]  Terry M. Peters,et al.  Right Ventricle Segmentation with Probability Product Kernel Constraints , 2013, MICCAI.

[2]  Milan Sonka,et al.  Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images , 2001, IEEE Transactions on Medical Imaging.

[3]  Simon R. Arridge,et al.  An Atlas-Based Segmentation Propagation Framework Using Locally Affine Registration - Application to Automatic Whole Heart Segmentation , 2008, MICCAI.

[4]  L. Tavazzi,et al.  Independent and additive prognostic value of right ventricular systolic function and pulmonary artery pressure in patients with chronic heart failure. , 2001, Journal of the American College of Cardiology.

[5]  Kumaradevan Punithakumar,et al.  Cardiac right ventricular segmentation via point correspondence , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[6]  H. Palevsky,et al.  Chronic cor pulmonale : etiology and management , 1990 .

[7]  Karl-Eugen Kurrer.  The Development of the Deformation Method , 2003 .

[8]  A. Ardeshir Goshtasby.  Image Registration: Principles, Tools and Methods , 2012 .

[9]  Daniel Rueckert,et al.  Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II , 2017, Lecture Notes in Computer Science.

[10]  N. Paragios.  A level set approach for shape-driven segmentation and tracking of the left ventricle , 2003, IEEE Transactions on Medical Imaging.

[11]  Daniel Rueckert,et al.  Right ventricle segmentation from cardiac MRI: A collation study , 2015, Medical Image Anal..

[12]  Daniel Rueckert,et al.  Segmentation of 4D Cardiac MR Images Using a Probabilistic Atlas and the EM Algorithm , 2003, MICCAI.

[13]  William M. Wells,et al.  Medical Image Computing and Computer-Assisted Intervention — MICCAI’98 , 1998, Lecture Notes in Computer Science.

[14]  E Falk,et al.  Right ventricular infarction: frequency, size and topography in coronary heart disease: a prospective study comprising 107 consecutive autopsies from a coronary care unit. , 1987, Journal of the American College of Cardiology.

[15]  Milan Sonka,et al.  4-D Cardiac MR Image Analysis: Left and Right Ventricular Morphology and Function , 2010, IEEE Transactions on Medical Imaging.

[16]  C. H. Lorenz,et al.  The Range of Normal Values of Cardiovascular Structures in Infants, Children, and Adolescents Measured by Magnetic Resonance Imaging , 2000, Pediatric Cardiology.

[17]  Shuo Li,et al.  Tracking Endocardial Motion Via Multiple Model Filtering , 2010, IEEE Transactions on Biomedical Engineering.

[18]  C. Davatzikos,et al.  Multi-Atlas Segmentation of the Cardiac MR Right Ventricle , 2012 .

[19]  Shuo Li,et al.  A Parameterization of Deformation Fields for Diffeomorphic Image Registration and Its Application to Myocardial Delineation , 2010, MICCAI.

[20]  Christos Davatzikos,et al.  Segmentation of the Left Ventricle Using Distance Regularized Two-Layer Level Set Approach , 2013, MICCAI.

[21]  S. Yusuf,et al.  Impact of right ventricular involvement on mortality and morbidity in patients with inferior myocardial infarction. , 2001, Journal of the American College of Cardiology.

[22]  Marc A. Simon,et al.  Assessment and treatment of right ventricular failure , 2013, Nature Reviews Cardiology.

[23]  S. Hunt,et al.  Right Ventricular Function in Cardiovascular Disease, Part I: Anatomy, Physiology, Aging, and Functional Assessment of the Right Ventricle , 2008, Circulation.

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

[25]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Richard D. White,et al.  ACR practice guideline for the performance and interpretation of cardiac magnetic resonance imaging (MRI). , 2006, Journal of the American College of Radiology : JACR.

[27]  Su Ruan,et al.  Right ventricle segmentation by graph cut with shape prior , 2012 .

[28]  Juha Koikkalainen,et al.  Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images , 2004, Medical Image Anal..

[29]  Terry M. Peters,et al.  Left ventricle segmentation in MRI via convex relaxed distribution matching , 2013, Medical Image Anal..

[30]  Vijay K. Devabhaktuni,et al.  Fast, accurate, and fully automatic segmentation of the right ventricle in short-axis cardiac MRI , 2014, Comput. Medical Imaging Graph..

[31]  Xavier Jaïs,et al.  [Treatment of pulmonary arterial hypertension]. , 2014, Presse medicale.

[32]  B. Cowan,et al.  In-line automated tracking for ventricular function with magnetic resonance imaging. , 2010, JACC. Cardiovascular imaging.

[33]  Bo Li,et al.  GPU Accelerated Non-rigid Registration for the Evaluation of Cardiac Function , 2008, MICCAI.

[34]  Yingli Lu,et al.  Left Ventricle Tracking Using Overlap Priors , 2008, MICCAI.

[35]  Himanshu Gupta,et al.  Role of cardiac magnetic resonance imaging in the management of patients with pulmonary arterial hypertension. , 2008, Journal of the American College of Cardiology.

[36]  D. Rueckert,et al.  Multi-Atlas Based Segmentation with Local Label Fusion for Right Ventricle MR Images , 2012 .

[37]  Xingling Zhou,et al.  On Uniqueness Theorem of a Vector Function , 2006 .

[38]  Alejandro F Frangi,et al.  Active shape models with invariant optimal features (IOF-ASM) application to cardiac MRI segmentation , 2003, Computers in Cardiology, 2003.

[39]  Dudley J Pennell,et al.  Reference right ventricular systolic and diastolic function normalized to age, gender and body surface area from steady-state free precession cardiovascular magnetic resonance. , 2006, European heart journal.

[40]  Caroline Petitjean,et al.  Cardiac MRI assessment of right ventricular function in acquired heart disease: factors of variability. , 2012, Academic radiology.

[41]  Shuo Li,et al.  Max-flow segmentation of the left ventricle by recovering subject-specific distributions via a bound of the Bhattacharyya measure , 2012, Medical Image Anal..

[42]  R. Quaife,et al.  The pressure-overloaded right ventricle in pulmonary hypertension. , 1998, Chest.