Automatic localization of craniofacial landmarks for assisted cephalometry

被引:56
作者
El-Feghi, I [1 ]
Sid-Ahmed, MA [1 ]
Ahmadi, M [1 ]
机构
[1] Univ Windsor, Dept Elect & Comp Engn, Windsor, ON N9B 3P4, Canada
关键词
cephalometry; landmarks; k-means clustering; fuzzy linguistics; gradient decent; Fisher discriminant;
D O I
10.1016/j.patcog.2003.09.002
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we propose a system for localization of cephalometric landmarks. The process of localization is carried out in two steps: deriving a smaller expectation window for each landmark using a trained neuro-fuzzy system (NFS) then applying a template-matching algorithm to pin point the exact location of the landmark. Four points are located on each image using edge detection. The four points are used to extract more features such as distances, shifts and rotation angles of the skull. Limited numbers of representative groups that will be used for training are selected based on k-means clustering. The most effective features are selected based on a Fisher discriminant for each feature set. Using fuzzy linguistics if-then rules, membership degree is assigned to each of the selected features and fed to the FNS. The FNS is trained, utilizing gradient descent, to learn the relation between the sizes, rotations and translations of landmarks and their locations. The data for training is obtained manually from one image from each cluster. Images whose features are located closer to the center of their cluster are used for extracting data for the training set. The expected locations on target images can then be predicted using the trained FNS. For each landmark a parametric template space is constructed from a set of templates extracted from several images based on the clarity of the landmark in that image. The template is matched to the search windows to find the exact location of the landmark. Decomposition of landmark shapes is used to desensitize the algorithm to size differences. The system is trained to locate 20 landmarks on a database of 565 images. Preliminary results show a recognition rate of more than 90%. (C) 2003 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
引用
收藏
页码:609 / 621
页数:13
相关论文
共 31 条
[1]  
ABUALNADI D, 1999, P IEEE INT C FUZZ SY, V2, P1102
[2]  
[Anonymous], P 4 INT C ART INT
[3]  
Broadbent BH., 1931, Angle Orthod, V1, P45, DOI DOI 10.1043/0003-3219(1931)001<0045:ANXTAI>2.0.CO
[4]  
2
[5]   AN IMAGE-PROCESSING SYSTEM FOR LOCATING CRANIOFACIAL LANDMARKS [J].
CARDILLO, J ;
SIDAHMED, MA .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1994, 13 (02) :275-289
[6]  
Chiu SL., 1994, J INTELL FUZZY SYST, V2, P267, DOI [DOI 10.3233/IFS-1994-2306, 10.3233/IFS-1994-2306]
[7]  
Cohen A M, 1984, Br J Orthod, V11, P143
[8]  
Cohen A M, 1986, Br J Orthod, V13, P105
[9]  
CONTERERASVIDAL JL, 1990, P CAN C EL COMP ENG
[10]   KNOWLEDGE-BASED CEPHALOMETRIC ANALYSIS - A COMPARISON WITH CLINICIAN USING INTERACTIVE COMPUTER METHODS [J].
DAVIS, DN ;
FORSYTH, D .
COMPUTERS AND BIOMEDICAL RESEARCH, 1994, 27 (03) :210-228