Breast Cancer Detection and Classification Using MF-FRFCM Segmentation and IGOA-ELM Model

The unknown cause of cancer and non-diagnosis of breast cancer leads to deaths among women worldwide. Medical professionals would benefit from the automatic detection and classification of breast cancer as it will expedite diagnosis and save time. To classify breast cancer from mammography images, this work presents an improved grasshopper optimization algorithm (GOA) in combination with an extreme learning machine model (IGOA-ELM). A median-filtered fast and robust fuzzy c-mean (MF-FRFCM) segmentation is proposed to detect breast cancers. Wavelet transform is employed to extract the features, which are then supplied as input to the PSO-ELM, APSO-ELM, GOA-ELM, and IGOA-ELM models for classification. The proposed IGOA-ELM model outperforms the traditional machine learning models, achieving 99.25% accuracy.