Multi-Type Classification of Mammogram Abnormalities by GHM and Multiclass SVM

Cancer is a life-threatening disease, which consumes numerous human lives. However, the lifespan of the patients can be extended, when the disease is treated properly at the right time. This article renders a small contribution to the medical world for detecting the abnormalities in the mammograms. The research goal is attained by four important phases such as mammogram pre-processing, segmentation, feature extraction and classification. In the pre-processing phase, median filter is utilized to enhance the quality of an image. The pre-processed image is then segmented by FCM. The features are extracted from the image by Gaussian Hermite Moments, which are proven to be simple, efficient and noise resistant. Finally, multiclass SVM classifies between the normal, malignant and benign kinds of cancer. The performance of the proposed approach is evaluated against several analogous approaches in terms of accuracy, sensitivity and specificity. The proposed approach shows convincing results.