A novel approach for detecting breast cancer in mammography images using RBF-ELM model

Currently, detecting breast cancer is crucial for women all over the world in order to preserve lives. Because of their lack of training and expertise in cancer diagnosis, doctors and radiologists may fail to notice the anomaly. Model training, feature extraction, data segmentation, and preprocessing are the four key components. Image binarization and active contour are two of the preprocessing procedures. Segmentation is a way to improve the representation of an image in terms of its utility, understandability, and actionability. The GLCM, or Gray Level Co-occurrence Matrix, is employed for feature extraction. For more accurate results, we trained the model using the RBF-ELM. Outperforming rival methods like RBF and ELM, the proposed approach attained an accuracy of 97.02%.