Statistical textural features for detection of microcalcifications in digitized mammograms

Abstract

Clustered microcalcifications on X-ray mammograms are an important sign for early detection of breast cancer. Texture-analysis methods can be applied to detect clustered microcalcifications in digitized mammograms. In this paper, a comparative study of texture-analysis methods is performed for the surrounding region-dependence method, which has been proposed by the authors, and conventional texture-analysis methods, such as the spatial gray-level dependence method, the gray-level run-length method, and the gray-level difference method. Textural features extracted by these methods are exploited to classify regions of interest (ROI's) into positive ROI's containing clustered microcalcifications and negative ROI's containing normal tissues. A three-layer backpropagation neural network is used as a classifier. The results of the neural network for the texture-analysis methods are evaluated by using a receiver operating-characteristics (ROC) analysis. The surrounding region-dependence method is shown to be superior to the conventional texture-analysis methods with respect to classification accuracy and computational complexity.

Carotid artery ultrasound texture, cardiovascular risk factors, and subclinical arterial disease: the Multi-Ethnic Study of Atherosclerosis (MESA)

“…GLDS are computed by calculating the absolute difference in greyscale values between pixels at a given distance and direction and can be used to describe pixel-greyscale relationships. 1,3,[10][11][12][24][25][26][27][28] Images that have low GLDS contrast will have more pixels with the same greyscale value and images that have high GLDS contrast will have large differences in greyscale values between pixels ( Figure 1). The LifeQ GLDS algorithm uses the probability density function p δ (i) to express the likelihood that two image pixels, separated by a distance δ = (Δχ, Δy), will have an absolute difference in greyscale value, i…”

Prediction of chemotherapy response in ovarian cancer patients using a new clustered quantitative image marker

“…For the FFT, DCT, Wavelet groups, each group includes 15 features computed using the same statistical measures, which are correlation, energy, entropy, kurtosis, maximum, minimum, range, mean, median, root-mean-square (RMS), skewness, standard deviation, sum deviation, mean deviation, uniformity. The GLDM group included 60 features, i.e., the 15 features associated with the same 15 statistical measures evaluated in each of four directions [37].…”

“…As for the GLDM features, they were derived from the P function [37], which can be expressed as the probability density function of gray level i for any given displacement vector d=(dx,dy),…”

“…The GLDM group included 60 features, i.e. the 15 features associated with the same 15 statistical measures evaluated in each of four directions (Jong Kook and Hyun Wook 1999). By comparison, the shape and density features described entire tumor-containing images, but the FFT, DCT, Wavelet, and GLDM features were block-based localized features.…”

Analysis of the Cluster Prominence Feature for Detecting Calcifications in Mammograms

“…Some methods are proposed to segment several types of microcalcifications using texture features. Kim and Park [14] compared the surrounding region-dependence method (SRDM) to the other conventional texture-analysis methods with respect to detection of clustered microcalcifications in digitized mammograms. The performance results of the classification are usually evaluated using receiver operating curve (ROC) curve that describes the discrimination capacity of the approach [15].…”