Severity level classification and detection of breast cancer using computer-aided mammography techniques
Punitha Stephan, Fadi M. Al-Turjman, Thompson Stephan · 2020
Breast cancer is the main cause of increase in the cancer death rate among women globally. Early diagnosis of the breast tumors at premature stages prevents the increase in the mortality rate all around the world. Mammography is currently the most efficient and effective way of diagnosing breast cancers to prevent the patients from unwanted therapies and biopsies. The main objective of the proposed work is to help the radiologist to identify the severity level by appropriate grading of the breast cancers using computer-aided mammography (CAM) techniques. The accurate detection of the breast tumors in the proposed work is done using a modified region growing (MRG) followed by a semantic segmentation algorithm. The proposed system uses two-stage classification systems in which the first stage uses an optimized genetic fuzzy classifier (OGFC) to classify the mammograms as normal and abnormal taking statistical features and the wavelet features as input. Further, the abnormal images are classified to identify the stages of the breast cancer as stage I, stage II, stage III, and stage IV using the second stage classification system which consists of a hybrid neural network optimized using genetic algorithms and trained using the grading dataset taking the shape and size features of the malignant tissue as input. The performance of the proposed system will be analyzed using the true-positive (TP), true-negative (TN), false-positive (FP), and false-negative (FN) values, and accuracy. The proposed system is evaluated using various digital mammograms.