A novel diagnostic framework for breast cancer: Combining deep learning with mammogram-DBT feature fusion

• The extended-tuned adaptive frost filtering (Ext-AFF) helps to reduce noise and enhance the image's quality, improving the contrast, and hence yielding clear and more accurate feature extraction in both mammogram and DBT images. • Disentangled variational autoencoder (D-VAE) is a deep learning generative model used in the extraction of detailed texture features from mammograms and DBT images. By considering disentangled VAE, the model can capture subtle differences between benign and malignant tissues with improved performance. • Deep generalized canonical correlation analysis (Dg-CCA) fuses the features from mammogram and DBT images into a unified representation that maximizes the feature correlation and improves the discriminative power of the dataset. • Fully elman neural network (FENN) approach, employing progressive training and exploiting recurrent architectures that are quintessential in modeling intricate relationships and temporal dependencies of image data to improve the system for classifying breast cancer. Breast cancer detection remains a critical challenge in medical imaging due to the complexity of tumor features and variability in breast tissue. Conventional mammography struggles with dense tissues, leading to missed diagnoses. Digital Breast Tomosynthesis (DBT) offers improved 3D imaging but brings significant computational burdens. This study proposes a novel framework using the Fully Elman Neural Network (FENN) with feature fusion to enhance the accuracy and reliability of breast cancer diagnosis. Mammogram images from the CBIS-DDSM dataset and DBT images from the Breast-Cancer-Screening-DBT dataset were used. The preprocessing step involved Extended-Tuned Adaptive Frost Filtering (Ext-AFF) to enhance image quality by reducing noise. Feature extraction was performed using Disentangled Variational Autoencoder (D-VAE), capturing critical texture features. These features were fused using Deep Generalized Canonical Correlation Analysis (Dg-CCA) to maximize feature correlation across modalities. Finally, a Fully Elman Neural Network was employed for classification, distinguishing between benign, malignant, biopsy-proven cancer, and normal tissues. The proposed FENN-based framework achieved superior classification performance compared to existing methods. Key metrics such as accuracy, sensitivity, specificity, and Matthew's correlation coefficient (MCC) demonstrated significant improvements. The fusion of mammogram and DBT images led to enhanced discriminative power, reducing false positives and negatives across various breast cancer classes. The integration of mammogram and DBT image data with advanced machine learning techniques, such as d -VAE and FENN, enhances diagnostic precision. The proposed framework shows promise for improving clinical decision-making in breast cancer screening by overcoming the limitations of traditional imaging methods. The system's ability to handle complex interdependencies in imaging data offers substantial potential for earlier and more accurate diagnosis. Future research will focus on real-time clinical deployment of the framework, incorporating real-time image acquisition and analysis for faster diagnoses. Additionally, scaling the system for large datasets with varying image quality will further validate its robustness and applicability in diverse clinical environments.