Mammographic Image segmentation by deformable models

Abstract

Breast cancer is a significant global health concern, necessitating early and accurate diagnosis for effective treatment and improved patient outcomes. Medical imaging techniques, particularly mammography, play a crucial role in breast cancer detection. However, segmenting cancerous regions from mammographic images is challenging due to the complexity and variability of breast tissue, as well as the presence of noise and overlapping structures. This study focuses on two deformable methods, the Chan-Vese and Snakes (Kass) methods, for breast cancer image segmentation. By conducting a comparative study using the publicly available MIAS database, we assess the effectiveness of these methods in accurately segmenting breast cancer regions and compare their performance in terms of accuracy, robustness, and computational efficiency. The results of this research aim to contribute insights into the strengths and limitations of deformable methods for segmentation, with the potential to enhance the development of more robust and accurate algorithms for breast cancer diagnosis and treatment planning