A Probabilistic Patch-Based Label Fusion Model for Multi-Atlas Segmentation With Registration Refinement: Application to Cardiac MR Images

被引:165
作者
Bai, Wenjia [1 ]
Shi, Wenzhe [1 ]
O'Regan, Declan P. [2 ]
Tong, Tong [1 ]
Wang, Haiyan [1 ]
Jamil-Copley, Shahnaz [3 ]
Peters, Nicholas S. [3 ]
Rueckert, Daniel [1 ]
机构
[1] Univ London Imperial Coll Sci Technol & Med, Biomed Image Anal Grp, Dept Comp, London SW7 2RH, England
[2] Univ London Imperial Coll Sci Technol & Med, Hammersmith Hosp, MRC Clin Sci Ctr, Robert Steiner MRI Unit, London W12 0NN, England
[3] Imperial Coll Healthcare NHS Trust, St Marys Hosp, Dept Cardiol, London W2 1PG, England
关键词
Image registration; image segmentation; multi-atlas segmentation; patch-based segmentation; MAGNETIC-RESONANCE IMAGES; NONRIGID REGISTRATION; HEART; HIPPOCAMPUS; PROPAGATION; COMBINATION; STRATEGIES; ALGORITHM; VENTRICLE; FRAMEWORK;
D O I
10.1109/TMI.2013.2256922
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The evaluation of ventricular function is important for the diagnosis of cardiovascular diseases. It typically involves measurement of the left ventricular (LV) mass and LV cavity volume. Manual delineation of the myocardial contours is time-consuming and dependent on the subjective experience of the expert observer. In this paper, a multi-atlas method is proposed for cardiac magnetic resonance (MR) image segmentation. The proposed method is novel in two aspects. First, it formulates a patch-based label fusion model in a Bayesian framework. Second, it improves image registration accuracy by utilizing label information, which leads to improvement of segmentation accuracy. The proposed method was evaluated on a cardiac MR image set of 28 subjects. The average Dice overlap metric of our segmentation is 0.92 for the LV cavity, 0.89 for the right ventricular cavity and 0.82 for the myocardium. The results show that the proposed method is able to provide accurate information for clinical diagnosis.
引用
收藏
页码:1302 / 1315
页数:14
相关论文
共 59 条
[1]   Multi-atlas based segmentation of brain images: Atlas selection and its effect on accuracy [J].
Aljabar, P. ;
Heckemann, R. A. ;
Hammers, A. ;
Hajnal, J. V. ;
Rueckert, D. .
NEUROIMAGE, 2009, 46 (03) :726-738
[2]   Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data [J].
Artaechevarria, Xabier ;
Munoz-Barrutia, Arrate ;
Ortiz-de-Solorzano, Carlos .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2009, 28 (08) :1266-1277
[3]   Unified segmentation [J].
Ashburner, J ;
Friston, KJ .
NEUROIMAGE, 2005, 26 (03) :839-851
[4]   Non-local statistical label fusion for multi-atlas segmentation [J].
Asman, Andrew J. ;
Landman, Bennett A. .
MEDICAL IMAGE ANALYSIS, 2013, 17 (02) :194-208
[5]  
Asman AJ, 2012, LECT NOTES COMPUT SC, V7512, P426, DOI 10.1007/978-3-642-33454-2_53
[6]  
Bezdek J. C., 2002, Advances in Soft Computing - AFSS 2002. 2002 AFSS International Conference on Fuzzy Systems. Proceedings (Lecture Notes in Artificial Intelligence Vol.2275), P288
[7]   Nonlocal image and movie denoising [J].
Buades, Antoni ;
Coll, Bartomeu ;
Morel, Jean-Michel .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2008, 76 (02) :123-139
[8]   Cardiac MRI Assessment of Right Ventricular Function in Acquired Heart Disease:Factors of Variability [J].
Caudron, Jerome ;
Fares, Jeannette ;
Lefebvre, Valentin ;
Vivier, Pierre-Hugues ;
Petitjean, Caroline ;
Dacher, Jean-Nicolas .
ACADEMIC RADIOLOGY, 2012, 19 (08) :991-1002
[9]  
Chen XH, 2005, LECT NOTES COMPUT SC, V3565, P126
[10]   An optimized blockwise nonlocal means denoising filter for 3-D magnetic resonance images [J].
Coupe, Pierrick ;
Yger, Pierre ;
Prima, Sylvain ;
Hellier, Pierre ;
Kervrann, Charles ;
Barillot, Christian .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2008, 27 (04) :425-441