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

• Published in: Ultrasound in medicine & biology Vol. 28; no. 10; pp. 1301 - 1310
• Main Authors: Chen, Dar-Ren, Chang, Ruey-Feng, Kuo, Wen-Jia, Chen, Ming-Chun, Huang, Y.u-Len
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.10.2002; Elsevier
• Subjects: Biological and medical sciences; Breast Diseases - diagnostic imaging; Breast Neoplasms - diagnostic imaging; Breast tumor; Diagnosis, Computer-Assisted - methods; Diagnosis, Differential; Female; Genital system. Mammary gland; Humans; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Neural network; Neural Networks (Computer); Sensitivity and Specificity; Ultrasonic; Ultrasonic investigative techniques; Ultrasonography; Wavelet transform; Wavelet transform; Neural network; Breast tumor; Ultrasonic; Sonography; Human; Differential diagnostic; Image quality; Mammary gland diseases; Wavelet transformation; Technology; Echography; Tumor; Mammary gland; Technique; Mathematical model; Computer aid
• ISSN: 0301-5629; 1879-291X
• DOI: 10.1016/S0301-5629(02)00620-8

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@ms13.hinet.net)