A novel exploratory hybrid deep neural network to predict breast cancer for mammography based on wavelet features

• Published in: Multimedia tools and applications 2024-01, Vol.83 (24), p.65441-65467
• Main Authors: Karthiga, Rengarajan, Narasimhan, Kumaravelu, Chinthaginjala, Ravikumar, Anbazhagan, Rajesh, Chinnusamy, Manikandan, Pau, Giovanni, Satish, Kumar, Amirtharajan, Rengarajan, Abbas, Mohamed
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Artificial neural networks; Breast cancer; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Deep learning; Feature extraction; Image contrast; Machine learning; Mammography; Medical imaging; Multimedia Information Systems; Neural networks; Special Purpose and Application-Based Systems; Track 2: Medical Applications of Multimedia
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-18012-y

A drastic rise in the incidence of breast cancer in patients is witnessed as per the new roadmap launched by the World Health Organization in 2023. Premature breast cancer detection improves survival chances by allowing for more effective clinical treatments. The artificial intelligence-enabled digital mammography examination supports the early finding of breast cancer. However, detecting tumour shape and location variations is challenging because of mammogram images’ low contrast and noise. The mammogram images are preprocessed in this work, and the features are extracted using Haar wavelet that is further applied to machine learning and deep learning prototypes. As the modified convolution neural network categorizes the local images based on handcrafted features and global features based on preprocessed statistics, the hybrid deep neural network effectively classifies the benign and malignant diagnosis. The hybrid deep neural network model achieved significant experimental results compared to machine learning techniques. The results are substantial and have an area under the curve of 0.92.