Green AI-Enhanced Deep Learning Model for Breast Cancer Detection and Classification in Mammography Images: BC-Net-512

This study champions a sustainable approach for developing a Deep Learning (DL) model for medical image analysis, specifically focusing on breast cancer (BC) detection in mammograms. By prioritizing low-computing algorithms to achieve high diagnostic accuracy while minimizing the model's environmental footprint, that aligns with the principles of Green AI. In this paper, an innovative architecture called BC-Net-512 was constructed for the classification of BC mammography. It is composed of lightweight Convolutional Neural Network (CNN) blocks for texture, density, and structure feature extraction and detection, a thin, fully connected layer for learning complex patterns and correlations in the extracted features, and a dropout layer for mitigating overfitting concerns. Five CNN architectures are also proposed to assess the structural effectiveness of the BC-Net-512 model in terms of computational complexity and classification accuracy. The proposed BC-Net-512 model demonstrated peak accuracy and significantly reduced computational complexity, surpassing DL methods and other state-of-the-art algorithms, meeting the Green AI requirements for efficient and sustainable AI models. It demonstrates promising results for accurate BC classification tasks. Due to experimental investigations, BC-Net-512 outperformed other related works on the two benchmark datasets, achieving 93.16% classification accuracy in the DDSM dataset and 100% in the INbreast dataset, surpassing state-of-the-art methods by 2.0% and 0.3%, respectively. Moreover, BC-Net-512 demonstrated a remarkable 98.80% decrease in computing complexity, underscoring its computational efficiency.