Effective segmentation and classification for HCC biopsy images

被引:102
作者
Huang, Po-Whei [1 ]
Lai, Yan-Hao [1 ]
机构
[1] Natl Chung Hsing Univ, Dept Comp Sci & Engn, Taichung 40227, Taiwan
关键词
HCC biopsy image; Morphological grayscale reconstruction; k-nearest neighbor; Support vector machine; Feature selection; Decision-graph; PATHOLOGICAL IMAGES; CELLS; ALGORITHMS; CARCINOMA; FEATURES; SNAKES;
D O I
10.1016/j.patcog.2009.10.014
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Accurate grading for hepatocellular carcinoma (HCC) biopsy images is important to prognosis and treatment planning. In this paper, we propose an automatic system for grading HCC biopsy images. In preprocessing, we use a dual morphological grayscale reconstruction method to remove noise and accentuate nuclear shapes. A marker-controlled watershed transform is applied to obtain the initial contours of nuclei and a snake model is used to segment the shapes of nuclei smoothly and precisely. Fourteen features are then extracted based on six types of characteristics for HCC classification. Finally, we propose a SVM-based decision-graph classifier to classify HCC biopsy images. Experimental results show that 94.54% of classification accuracy can be achieved by using our SVM-based decision-graph classifier while 90.07% and 92.88% of classification accuracy can be achieved by using k-NN and SVM classifiers, respectively. (C) 2009 Elsevier Ltd. All rights reserved.
引用
收藏
页码:1550 / 1563
页数:14
相关论文
共 63 条
[31]   Asymptotic behaviors of support vector machines with Gaussian kernel [J].
Keerthi, SS ;
Lin, CJ .
NEURAL COMPUTATION, 2003, 15 (07) :1667-1689
[32]   Study on texture analysis of renal cell carcinoma nuclei based on the Fuhrman grading system [J].
Kim, TY ;
Choi, HJ ;
Cha, SJ ;
Choi, HK .
Healthcom 2005: 7th International Workshop on Enterprise Networking and Computing in Healthcare Industry, Proceedings, 2005, :384-387
[33]   Comparison of algorithms that select features for pattern classifiers [J].
Kudo, M ;
Sklansky, J .
PATTERN RECOGNITION, 2000, 33 (01) :25-41
[34]  
Kumar BR, 2002, DSP 2002: 14TH INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING PROCEEDINGS, VOLS 1 AND 2, P619, DOI 10.1109/ICDSP.2002.1028167
[35]  
Lezoray O., 1999, ACTA STEREOLOGICA, V18, P1
[36]  
LIU B, 2003, P 20 CAN C EL COMP E, V1022, P1022
[37]  
Liu LF, 2001, 2001 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL III, PROCEEDINGS, P1071, DOI 10.1109/ICIP.2001.958312
[38]   Comparison of standardized and nonstandardized nuclear grade of renal cell carcinoma to predict outcome among 2,042 patients [J].
Lohse, CM ;
Blute, ML ;
Zincke, H ;
Weaver, AL ;
Cheville, JC .
AMERICAN JOURNAL OF CLINICAL PATHOLOGY, 2002, 118 (06) :877-886
[39]  
Malpica N, 1997, CYTOMETRY, V28, P289, DOI 10.1002/(SICI)1097-0320(19970801)28:4<289::AID-CYTO3>3.0.CO
[40]  
2-7