Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks

被引:175
作者
Chen, DR
Chang, RF
Kuo, WJ
Chen, MC
Huang, YL
机构
[1] China Med Coll & Hosp, Dept Gen Surg, Taichung, Taiwan
[2] Natl Chung Cheng Univ, Dept Comp Sci & Informat Engn, Chiayi, Taiwan
关键词
ultrasonic; breast tumor; wavelet transform; neural network;
D O I
10.1016/S0301-5629(02)00620-8
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
To increase the ability of ultrasonographic technology for the differential diagnosis of solid breast tumors, we describe a novel computer-aided diagnosis (CADx) system using neural networks for classification of breast tumors. Tumor regions and surrounding tissues are segmented from the physician-located region-of-interest (ROI) images by applying our proposed segmentation algorithm. Cooperating with the segmentation algorithm, three feasible features, including variance contrast, autocorrelation contrast and distribution distortion of wavelet coefficients, were extracted from the ROI images for further classification. A multilayered perceptron (MLP) neural network trained using error back-propagation algorithm with momentum was then used for the differential diagnosis of breast tumors on sonograms. In the experiment, 242 cases (including benign breast tumors from 161 patients and carcinomas from 82 patients) were sampled with k-fold cross-validation (k = 10) to evaluate the performance. The receiver operating characteristic (ROC) area index for the proposed CADx system is 0.9396 +/- 0.0183, the sensitivity is 98.77%, the specificity is 81.37%, the positive predictive value is 72.73% and the negative predictive value is 99.24%. Experimental results showed that our diagnosis model performed very well for breast tumor diagnosis. (E-mail: dlchen88@msl3.hinet.net) (C) 2002 World Federation for Ultrasound in Medicine Biology.
引用
收藏
页码:1301 / 1310
页数:10
相关论文
共 29 条
[1]   Image coding using wavelet transform [J].
Antonini, Marc ;
Barlaud, Michel ;
Mathieu, Pierre ;
Daubechies, Ingrid .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1992, 1 (02) :205-220
[2]   Image compression using wavelet transform and multiresolution decomposition [J].
Averbuch, A ;
Lazar, D ;
Israeli, M .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1996, 5 (01) :4-15
[3]  
BASSETT LW, 1993, J ULTRAS MED, V13, P267
[4]   CANCER STATISTICS, 1994 [J].
BORING, CC ;
SQUIRES, TS ;
TONG, T ;
MONTGOMERY, S .
CA-A CANCER JOURNAL FOR CLINICIANS, 1994, 44 (01) :7-26
[5]  
Chang SG, 1998, 1998 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING - PROCEEDINGS, VOL 1, P545, DOI 10.1109/ICIP.1998.723560
[6]   Texture analysis and classification with tree-structured wavelet transform [J].
Chang, Tianhorng ;
Kuo, C. -C. Jay .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1993, 2 (04) :429-441
[7]   Texture analysis of breast tumors on sonograms [J].
Chen, DR ;
Chang, RF ;
Huang, YL ;
Chou, YH ;
Tiu, CM ;
Tsai, PP .
SEMINARS IN ULTRASOUND CT AND MRI, 2000, 21 (04) :308-316
[8]   Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis [J].
Chou, YH ;
Tiu, CM ;
Hung, GS ;
Wu, SC ;
Chang, TY ;
Chiang, HK .
ULTRASOUND IN MEDICINE AND BIOLOGY, 2001, 27 (11) :1493-1498
[9]   Analysis of mammographic microcalcifications using gray-level image structure features [J].
Dhawan, AP ;
Chitre, Y ;
KaiserBonasso, C ;
Moskowitz, M .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1996, 15 (03) :246-259
[10]  
Egan JP., 1975, SIGNAL DETECTION THE