Ball-Scale Based Hierarchical Multi-Object Recognition in 3D Medical Images

被引:4
作者
Bagci, Ulas [1 ]
Udupa, Jayaram K. [2 ]
Chen, Xinjian [3 ]
机构
[1] Univ Nottingham, CMIAG, Nottingham, England
[2] Univ Penn, Dept Radiol, Med Image Proc Grp, Philadelphia, PA 19104 USA
[3] NIH, Ctr Clin, Diagnost Radiol Dept, Bethesda, MD 20892 USA
来源
MEDICAL IMAGING 2010: IMAGE PROCESSING | 2010年 / 7623卷
关键词
Object Recognition; Ball-Scale; Active Shape Modeling; Principal Component Analysis; Hierarchical Recognition; Image Segmentation; SEGMENTATION;
D O I
10.1117/12.839920
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
This paper investigates, using prior shape models and the concept of ball scale (b-scale), ways of automatically recognizing objects in 3D images without performing elaborate searches or optimization. That is, the goal is to place the model in a single shot close to the right pose (position, orientation, and scale) in a given image so that the model boundaries fall in the close vicinity of object boundaries in the image. This is achieved via the following set of key ideas: (a) A semi-automatic way of constructing a multi-object shape model assembly. (b) A novel strategy of encoding, via b-scale, the pose relationship between objects in the training images and their intensity patterns captured in b-scale images. (c) A hierarchical mechanism of positioning the model, in a one-shot way, in a given image from a knowledge of the learnt pose relationship and the b-scale image of the given image to be segmented. The evaluation results on a set of 20 routine clinical abdominal female and male CT data sets indicate the following: (1) Incorporating a large number of objects improves the recognition accuracy dramatically. (2) The recognition algorithm can be thought as a hierarchical framework such that quick replacement of the model assembly is defined as coarse recognition and delineation itself is known as finest recognition. (3) Scale yields useful information about the relationship between the model assembly and any given image such that the recognition results in a placement of the model close to the actual pose without doing any elaborate searches or optimization. (4) Effective object recognition can make delineation most accurate.
引用
收藏
页数:12
相关论文
共 23 条
[1]  
[Anonymous], 1998, Statistical shape analysis
[2]  
[Anonymous], 1996, Digital image processing
[3]  
[Anonymous], 1989, Stat. Sci., DOI DOI 10.1214/SS/1177012582
[4]  
Brejl M, 2000, IEEE T MED IMAGING, V19, P973, DOI 10.1109/42.887613
[5]  
CHEN X, 2010, P SPIE MED IMA UNPUB
[6]  
CHEN X, 2009, P SPIE MED IMAGING
[7]   ACTIVE SHAPE MODELS - THEIR TRAINING AND APPLICATION [J].
COOTES, TF ;
TAYLOR, CJ ;
COOPER, DH ;
GRAHAM, J .
COMPUTER VISION AND IMAGE UNDERSTANDING, 1995, 61 (01) :38-59
[8]   Shape statistics in kernel space for variational image segmentation [J].
Cremers, D ;
Kohlberger, T ;
Schnörr, C .
PATTERN RECOGNITION, 2003, 36 (09) :1929-1943
[9]  
Davies R, 2008, STAT MODELS SHAPE OP
[10]  
DEBRUIJNE M, 2005, P MICCAI, V3216, P168