An Algorithm for the Segmentation of Highly Abnormal Hearts Using a Generic Statistical Shape Model

被引:29
作者
Alba, Xenia [1 ]
Pereanez, Marco [1 ]
Hoogendoorn, Corne [1 ]
Swift, Andrew J. [2 ]
Wild, Jim M. [2 ]
Frangi, Alejandro F. [3 ]
Lekadir, Karim [1 ]
机构
[1] Univ Pompeu Fabra, Ctr Computat Imaging & Simulat Technol Biomed CIS, Barcelona 08018, Spain
[2] Univ Sheffield, Acad Unit Radiol, Sheffield S10 2JF, S Yorkshire, England
[3] Univ Sheffield, Dept Elect Engn, Ctr Computat Imaging & Simulat Technol Biomed CIS, Sheffield S1 3JD, S Yorkshire, England
关键词
Abnormal hearts; cardiac segmentation; hypertrophic cardiomyopathy; magnetic resonance imaging; pulmonary hypertension; statistical shape models; LEFT-VENTRICULAR SEGMENTATION; CARDIAC CINE MRI; AUTOMATIC SEGMENTATION; PULMONARY-HYPERTENSION; ATLAS; REGISTRATION; CIRCULATION; APPEARANCE; FRAMEWORK; ACCURACY;
D O I
10.1109/TMI.2015.2497906
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Statistical shape models (SSMs) have been widely employed in cardiac image segmentation. However, in conditions that induce severe shape abnormality and remodeling, such as in the case of pulmonary hypertension (PH) or hypertrophic cardiomyopathy (HCM), a single SSM is rarely capable of capturing the anatomical variability in the extremes of the distribution. This work presents a new algorithm for the segmentation of severely abnormal hearts. The algorithm is highly flexible, as it does not require a priori knowledge of the involved pathology or any specific parameter tuning to be applied to the cardiac image under analysis. The fundamental idea is to approximate the gross effect of the abnormality with a virtual remodeling transformation between the patient-specific geometry and the average shape of the reference model (e.g., average normal morphology). To define this mapping, a set of landmark points are automatically identified during boundary point search, by estimating the reliability of the candidate points. With the obtained transformation, the feature points extracted from the patient image volume are then projected onto the space of the reference SSM, where the model is used to effectively constrain and guide the segmentation process. The extracted shape in the reference space is finally propagated back to the original image of the abnormal heart to obtain the final segmentation. Detailed validation with patients diagnosed with PH and HCM shows the robustness and flexibility of the technique for the segmentation of highly abnormal hearts of different pathologies.
引用
收藏
页码:845 / 859
页数:15
相关论文
共 51 条
[11]   Pulmonary hypertension: Accuracy of detection with left ventricular septal-to-free wall curvature ratio measured at cardiac MRI [J].
Dellegrottaglie, Santo ;
Sanz, Javier ;
Poon, Michael ;
Viles-Gonzalez, Juan F. ;
Sulica, Roxana ;
Goyenechea, Martin ;
Macaluso, Frank ;
Fuster, Valentin ;
Rajagopalan, Sanjay .
RADIOLOGY, 2007, 243 (01) :63-69
[12]   Statistical models of sets of curves and surfaces based on currents [J].
Durrleman, Stanley ;
Pennec, Xavier ;
Trouve, Alain ;
Ayache, Nicholas .
MEDICAL IMAGE ANALYSIS, 2009, 13 (05) :793-808
[13]   An automated myocardial segmentation in cardiac MRI [J].
El Berbari, R. ;
Bloch, I. ;
Redheuil, A. ;
Angelini, E. ;
Mousseaux, E. ;
Frouin, F. ;
Herment, A. .
2007 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-16, 2007, :4508-+
[14]   Segmentation by retrieval with guided random walks: Application to left ventricle segmentation in MRI [J].
Eslami, Abouzar ;
Karamalis, Athanasios ;
Katouzian, Amin ;
Navab, Nassir .
MEDICAL IMAGE ANALYSIS, 2013, 17 (02) :236-253
[15]  
Gilbert K, 2014, LECT NOTES COMPUT SC, V8674, P546, DOI 10.1007/978-3-319-10470-6_68
[16]   Automatic cardiac ventricle segmentation in MR images: a validation study [J].
Grosgeorge, Damien ;
Petitjean, Caroline ;
Caudron, Jerome ;
Fares, Jeannette ;
Dacher, Jean-Nicolas .
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2011, 6 (05) :573-581
[17]  
Gupta A., 1993, Proceedings. Computers in Cardiology 1993 (Cat. No.93CH3384-5), P747, DOI 10.1109/CIC.1993.378377
[18]   A High-Resolution Atlas and Statistical Model of the Human Heart From Multislice CT [J].
Hoogendoorn, Corne ;
Duchateau, Nicolas ;
Sanchez-Quintana, Damian ;
Whitmarsh, Tristan ;
Sukno, Federico M. ;
De Craene, Mathieu ;
Lekadir, Karim ;
Frangi, Alejandro F. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2013, 32 (01) :28-44
[19]   Automatic segmentation of the left ventricle in cardiac MR and CT images [J].
Jolly, Marie-Pierre .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2006, 70 (02) :151-163
[20]  
Katouzian Amin, 2006, Conf Proc IEEE Eng Med Biol Soc, V2006, P3074, DOI 10.1109/IEMBS.2006.260405