Detection of architectural distortion in prior mammograms of interval-cancer cases with neural networks

Abstract

Architectural distortion is a commonly missed sign of breast cancer. This paper investigates the detection of architectural distortion, in mammograms of interval-cancer cases taken prior to the diagnosis of breast cancer, using Gabor filters, phase portrait analysis, fractal dimension, and texture analysis. The methods were used to detect initial candidates for sites of architectural distortion in prior mammograms of interval-cancer and also normal cases. A total of 4212 regions of interest (ROIs) were automatically obtained from 106 prior mammograms of 56 interval-cancer cases, including 262 ROIs related to architectural distortion, and from 52 prior mammograms of 13 normal cases. For each ROI, the fractal dimension and Haralick's texture features were computed. Feature selection was performed using stepwise logistic regression and in terms of the area under the receiver operating characteristics (ROC) curve (AUC). The best results achieved, in terms of AUC, are 0.75 with the Bayesian classifier, 0.71 with Fisher linear discriminant analysis, and 0.76 with an artificial neural network (ANN) based on radial basis functions (RBF). Analysis of the performance of the methods with free-response receiver operating characteristics indicated a sensitivity of 0.80 at 10.5 false positives per image.