Improved watershed transform for medical image segmentation using prior information

被引:484
作者
Grau, V [1 ]
Mewes, AUJ
Alcañiz, M
Kikinis, R
Warfield, SK
机构
[1] Univ Politecn Valencia, MedicLab, Valencia 46022, Spain
[2] Brigham & Womens Hosp, Surg Planning Lab, Cambridge, MA 02138 USA
[3] Harvard Univ, Sch Med, Cambridge, MA 02138 USA
关键词
biomedical imaging; image segmentation; morphological operations; tissue classification; watersheds;
D O I
10.1109/TMI.2004.824224
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The watershed transform has interesting properties that make it useful for many different image segmentation applications: it is simple and intuitive, can be parallelized, and always produces a complete division of the image. However, when applied to medical image analysis, it has important drawbacks (oversegmentation, sensitivity to noise, poor detection of thin or low signal to noise ratio structures). We present an improvement to the watershed transform that enables the introduction of prior information in its calculation. We propose to introduce this information via the use of a previous probability calculation. Furthermore, we introduce a method to combine the watershed transform and atlas registration, through the use of markers. We have applied our new algorithm to two challenging applications: knee cartilage and gray matter/white matter segmentation in MR images. Numerical validation of the results is provided, demonstrating the strength of the algorithm for medical image segmentation.
引用
收藏
页码:447 / 458
页数:12
相关论文
共 50 条
[1]  
[Anonymous], 1999, The Prostate Cancer Journal, DOI DOI 10.1046/J.1525-1411.1999.14005.X
[2]   Fully automatic segmentation of the brain in MRI [J].
Atkins, MS ;
Mackiewich, BT .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1998, 17 (01) :98-107
[3]  
BESAG J, 1986, J R STAT SOC B, V48, P259
[4]  
Beucher S, 1994, COMP IMAG VIS, V2, P69
[5]  
Beucher S., 2018, Mathematical morphology in image processing, P433, DOI DOI 10.1201/9781482277234-12
[6]   AUTOMATIC DETECTION OF BRAIN CONTOURS IN MRI DATA SETS [J].
BRUMMER, ME ;
MERSEREAU, RM ;
EISNER, RL ;
LEWINE, RRJ .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1993, 12 (02) :153-166
[7]   Geodesic active contours [J].
Caselles, V ;
Kimmel, R ;
Sapiro, G .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1997, 22 (01) :61-79
[8]  
COCOSCO CA, 1997, NEUROIMAGE 2, V5, pS245
[9]   Knee cartilage topography, thickness, and contact areas from MRI: in-vitro calibration and in-vivo measurements [J].
Cohen, ZA ;
McCarthy, DM ;
Kwak, SD ;
Legrand, P ;
Fogarasi, F ;
Ciaccio, EJ ;
Ateshian, GA .
OSTEOARTHRITIS AND CARTILAGE, 1999, 7 (01) :95-109
[10]  
Dam E, 2000, LECT NOTES COMPUT SC, V1935, P216