Breast Abnormality Boundary Extraction in Mammography Image Using Variational Level Set and Self-Organizing Map (SOM)

A mammography provides a grayscale image of the breast. The main challenge analyzing images is to extract region boundary breast abnormality for further analysis. In computer vision, this method also known as segmentation. variational level set mathematical model has been proven be effective Several selective types models have recently formulated accurately segment specific object on images. However, these are incapable handling complex intensity inhomogeneity images, and segmentation process tends slow. Therefore, study new type that incorporate machine learning algorithm Self-Organizing Map (SOM). addition that, Gaussian function was applied in regularizer speed up processing time. Then, accuracy segmentation’s output evaluated using Jaccard, Dice, Accuracy Error metrics, while efficiency assessed by recording computational Experimental results indicated proposed able with highest fastest compared other iterative models.