Breast Cancer Classification with Enhanced Interpretability: DALAResNet50 and DT Grad-CAM
This addresses the problem of accurate and interpretable breast cancer diagnosis for medical professionals, with incremental improvements in model architecture and visualization techniques.
The paper tackles breast cancer classification in histopathology images by proposing DALAResNet50, which integrates a lightweight attention mechanism into ResNet50, achieving improved accuracy and performance metrics on imbalanced datasets like BreakHis, BACH, and Mini-DDSM. It also introduces DT Grad-CAM for enhanced interpretability through clearer visualizations.
Automatic classification of breast cancer in histopathology images is crucial for accurate diagnosis and effective treatment planning. Recently, classification methods based on the ResNet architecture have gained prominence due to their ability to improve accuracy significantly. This is achieved by employing skip connections to mitigate vanishing gradient issues, enabling the integration of low-level and high-level feature information. However, the conventional ResNet architecture faces challenges such as data imbalance and limited interpretability, which necessitate cross-domain knowledge and collaboration among medical experts. To address these challenges, this study proposes a novel method for breast cancer classification: the Dual-Activated Lightweight Attention ResNet50 (DALAResNet50) model. This model integrates a pre-trained ResNet50 architecture with a lightweight attention mechanism, embedding an attention module in the fourth layer of ResNet50, and incorporates two fully connected layers with LeakyReLU and ReLU activation functions to enhance feature learning capabilities. Extensive experiments conducted on the BreakHis, BACH, and Mini-DDSM datasets demonstrate that DALAResNet50 outperforms state-of-the-art models in accuracy, F1 score, IBA, and GMean, particularly excelling in classification tasks involving imbalanced datasets. Furthermore, the proposed Dynamic Threshold Grad-CAM (DT Grad-CAM) method provides clearer and more focused visualizations, enhancing interpretability and assisting medical experts in identifying key features.