A Wrapper based feature extraction framework based on AlexNet deep convolutional neural network parameters optimized using gradient‐based optimizer for mammogram images

• Published in: Concurrency and computation Vol. 34; no. 18
• Main Authors: Sakthivel, N. K., Subasree, S., Malik, Shaveta, Tyagi, Amit Kumar
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 15-08-2022; Wiley Subscription Services, Inc
• Subjects: AlexNet deep convolutional neural network; Artificial intelligence; Artificial neural networks; Breast cancer; Feature extraction; Fields (mathematics); gradient‐based optimizer Wrapper‐based feature extraction unit; Image analysis; Image classification; Image enhancement; Machine learning; Mammography; Medical imaging; Medical screening; Muscles; Neural networks; Parameters; Support vector machines; SVM classifier mammogram images
• ISSN: 1532-0626; 1532-0634
• DOI: 10.1002/cpe.7008

In this manuscript, a Wrapper based feature extraction framework based on AlexNet deep convolutional neural network (ADCNN) with gradient‐based optimizer (GBO) is proposed for early detection of breast cancer. In this input images are occupied as mini‐mammography image analysis society (MIAS) database. Then the images are pre‐processed to eliminate that noises using Markov random field (MRF) method. Image features are extracted by the process of Wrapper based feature extraction framework with ADCNN. Then, the weight parameters of ADCNN are optimizing through the aid of GBO. Then the mammogram images are characterized as normal or abnormal (malignant and benign) with SVM classifier. The simulation process is implemented on MATLAB platform. The proposed ADCNN‐SVM‐GBO attains higher accuracy 34.64%, 28.86%, 19.86%, 24.64%, 32.86%, higher Precision 28.07%, 18.96%, 16.86%, 25.86%, 26.86%, higher recall 27.86%, 32.54%, 27.86%, 23.95%, 19.97%, and the efficiency of the proposed method FE‐ADCNN‐GBO‐SVM is likened with the existing processes. Classification of mammograms depends features removal processes with support vector machine (FE‐LBP‐GLCM‐SVM), breast cancer classification with global discriminate features on mammographic images (FE‐GLCM‐ANN), enhancing breast cancer classification with (SMOTE) technique and pectoral muscle removal on mammographic images (FE‐SMOTE‐RF), application of artificial intelligence depends deep learning on breast cancer screening and imaging diagnosis (FE‐CNN‐CDCNN) respectively.