Segmentation of Fibro-Glandular Discs in Digital Mammograms Using Log-Normal Distribution

摘要

Segmentation is an important and challenging task in a computer-aided diagnosis (CAD) system. Accurate segmentation could improve the accuracy in lesion detection and characterization. In this paper, we present a new technique for Segmentation of Fibro-Glandular Discs based on Split-merge technique applied on histogram of the breast image and the Log-Normal distribution. The proposed new segmentation technique aims at improving the performance level of breast mass segmentation in mammography to provide accurate features for classification purposes. The proposed technique has been experimented with using various breast images. We observed better segmentation results of the proposed technique as compared to the existing methods.