Mass Detection Using a Texture Feature Coding Method

Summary

Detection of masses is much more difficult than that of microcalcifications (MCCs) because breast masses are part of tissues that may not be detected effectively by the techniques developed for detection of MCCs. In this chapter, we present a texture feature coding method (TFCM) to extract features that could characterize special properties of masses. It extracts gradient variations of gray level co-occurrence matrix as texture features. As a result, the TFCM is more sensitive to changes in texture. Three neural network architectures, backpropagation neural network, probabilistic neural network, and radial basis function neural network are used for mass detection with inputs provided by TFCM-extracted features. The experimental results show that our TFCM-based neural network approaches can achieve a detection rate of approximately 87% with a 10% false alarm rate.