Classification of Benign and Malignant Thyroid Nodules Using Wavelet Texture Analysis of Sonograms.

OBJECTIVES: The purpose of this study was to evaluate a computer-aided diagnostic system using texture analysis to improve radiologic accuracy for identification of thyroid nodules as malignant or benign. METHODS: The database comprised 26 benign and 34 malignant thyroid nodules. Wavelet transform was applied to extract texture feature parameters as descriptors for each selected region of interest in 3 normalization schemes (default, µ ± 3σ, and 1%-9%). Linear discriminant analysis and nonlinear discriminant analysis were used for texture analysis of the thyroid nodules. The first-nearest neighbor classifier was applied to features resulting from linear discriminant analysis. Nonlinear discriminant analysis features were classified by using an artificial neural network. Receiver operating characteristic curve analysis was used to examine the performance of the texture analysis methods. RESULTS: Wavelet features under default normalization schemes from nonlinear discriminant analysis indicated the best performance for classification of benign and malignant thyroid nodules and showed 100% sensitivity, specificity, and accuracy; the area under the receiver operating characteristic curve was 1. CONCLUSIONS: Wavelet features have a high potential for effective differentiation of benign from malignant thyroid nodules on sonography.

Application of Texture Analysis in Diagnosis of Multiple Sclerosis by Magnetic Resonance Imaging.

INTRODUCTION: Visual inspection by magnetic resonance (MR) images cannot detect microscopic tissue changes occurring in MS in normal appearing white matter (NAWM) and may be perceived by the human eye as having the same texture as normal white matter (NWM). The aim of the study was to evaluate computer aided diagnosis (CAD) system using texture analysis (TA) in MR images to improve accuracy in identification of subtle differences in brain tissue structure. MATERIAL & METHODS: The MR image database comprised 50 MS patients and 50 healthy subjects. Up to 270 statistical texture features extract as descriptors for each region of interest. The feature reduction methods used were the Fisher method, the lowest probability of classification error and average correlation coefficients (POE+ACC) method and the fusion Fisher plus the POE+ACC (FFPA) to select the best, most effective features to differentiate between MS lesions, NWM and NAWM. The features parameters were used for texture analysis with principle component analysis (PCA) and linear discriminant analysis (LDA). Then first nearest-neighbour (1-NN) classifier was used for features resulting from PCA and LDA. Receiver operating characteristic (ROC) curve analysis was used to examine the performance of TA methods. RESULTS: The highest performance for discrimination between MS lesions, NAWM and NWM was recorded for FFPA feature parameters using LDA; this method showed 100% sensitivity, specificity and accuracy and an area of Az=1 under the ROC curve. CONCLUSION: TA is a reliable method with the potential for effective use in MR imaging for the diagnosis and prediction of MS.

Application of texture analysis method for classification of benign and malignant thyroid nodules in ultrasound images.

BACKGROUND: The aim of this study was to evaluate computer aided diagnosis (CAD) system with texture analysis (TA) to improve radiologists' accuracy in identification of thyroid nodules as malignant or benign. METHODS: A total of 70 cases (26 benign and 44 malignant) were analyzed in this study. We extracted up to 270 statistical texture features as a descriptor for each selected region of interests (ROIs) in three normalization schemes (default, 3s and 1%-99%). Then features by the lowest probability of classification error and average correlation coefficients (POE+ACC), and Fisher coefficient (Fisher) eliminated to 10 best and most effective features. These features were analyzed under standard and nonstandard states. For TA of the thyroid nodules, Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Non-Linear Discriminant Analysis (NDA) were applied. First Nearest-Neighbour (1-NN) classifier was performed for the features resulting from PCA and LDA. NDA features were classified by artificial neural network (A-NN). Receiver operating characteristic (ROC) curve analysis was used for examining the performance of TA methods. RESULTS: The best results were driven in 1-99% normalization with features extracted by POE+ACC algorithm and analyzed by NDA with the area under the ROC curve ( Az) of 0.9722 which correspond to sensitivity of 94.45%, specificity of 100%, and accuracy of 97.14%. CONCLUSION: Our results indicate that TA is a reliable method, can provide useful information help radiologist in detection and classification of benign and malignant thyroid nodules.

Classification of breast tumors using sonographic texture analysis.

OBJECTIVES: The purpose of this study was to evaluate a computer-aided diagnostic system with texture analysis to improve radiologists' accuracy in identification of breast tumors as malignant or benign. METHODS: The database included 20 benign and 12 malignant tumors. We extracted 300 statistical texture features as descriptors for each selected region of interest in 3 normalization schemes (default, µ - 3σ, and µ + 3σ, where µ and σ were the mean value and standard deviation, respectively, of the gray-level intensity and 1%-99%). Then features determined by the Fisher coefficient and the lowest probability of classification error + average correlation coefficient yielded the 10 best and most effective features. We analyzed these features under 2 standardization states (standard and nonstandard). For texture analysis of the breast tumors, we applied principle component, linear discriminant, and nonlinear discriminant analyses. First-nearest neighbor classification was performed for the features resulting from the principle component and linear discriminant analyses. Nonlinear discriminant analysis features were classified by an artificial neural network. Receiver operating characteristic curve analysis was used for examining the performance of the texture analysis methods. RESULTS: Standard feature parameters extracted by the Fisher coefficient under the default and 3σ normalization schemes via nonlinear discriminant analysis showed high performance for discrimination between benign and malignant tumors, with sensitivity of 94.28%, specificity of 100%, accuracy of 97.80%, and an area under the receiver operating characteristic curve of 0.9714. CONCLUSIONS: Texture analysis is a reliable method and has the potential to be used effectively for classification of benign and malignant tumors on breast sonography.