Breast cancer is one of the most occurring cancers in women due to the uncontrolled growth of abnormal cells in the lobules or milk ducts. The treatment for the breast cancer at an early stage is important using Magnetic Resonance Imaging (MRI) which effectively measures the size of the cancer and also checks tumors in the opposite breast. The deposition of calcium components on the breast tissue is known as micro-calcifications. The calcium salts deposited in the breast are involved with the cancer and were not diagnosed accurately due to the low effectiveness of existing imaging technique namely Haralick feature extraction technique. The MRI breast cancer diagnosis creates problems during classification of breast image and leads to misclassifications, such as unidentified calcium deposits in the existing K-Nearest Neighbour (KNN) classifier. The misclassification issues are overcome by an accurate classification and identification of calcium salts and checks whether deposited salt on breast tissue is involved with cancer or not. Initially, Contrast-Limited Adaptive Histogram Equalization (CLAHE) is used to remove the unwanted noise in the MRI and Morphological, Multilevel Otsu’s Thresholding and region growing techniques perform segmentation to mask unwanted breast tissues. The proposed Hybrid LOOP Haralick feature extraction technique is developed by combining the both Local Optimal Oriented Pattern (LOOP) and Haralick texture feature and the hybrid parameters are applied to the Stacked Auto Encoder based (SAE) to classify the breast MRI image as a Malignant or Benign. The performance of the proposed hybrid LOOP Haralick feature extraction shows significant accuracy improvement of 3.83% when compared to the Haralick feature extraction technique.

No abstract

Early classification of breast cancer helps to treat the patient effectively and increases the survival rate. The existing methods involve applying the feature selection methods and deep learning methods to improve the performance of the breast cancer classification. In this research, the binary differential evolution with self learning (BDE-SL) and deep neural network (DNN) method is proposed to improve the performance of the breast cancer classification. The BDE-SL feature selection method involves selecting the relevant features based on the measure of probability difference for each feature and non-dominated sorting. The DNN method has the advantage which effectively analysis the non-linear relationship among the selected features and output.The BI-RADS MRI breast cancer dataset was applied to test the performance of the proposed method. The adaptive histogram equalization and region growing applied in the input images to enhance the image. The dual-tree complex wavelet transform, gray-level co-occurrence matrix, and local directional ternary pattern were the feature extraction method used for the classification. This result shows that BDE-SL with the DNN method has an accuracy of 99.12% and the existing convolutional neural network has 98.33% accuracy.