Breast Cancer Classification with Enhanced Interpretability: DALAResNet50 and DT Grad-CAM

TL;DR

This paper introduces DALAResNet50, a novel breast cancer classification model with integrated attention mechanisms, and DT Grad-CAM for improved interpretability, achieving superior accuracy and clearer visual explanations on multiple datasets.

Contribution

The study presents a new lightweight attention-augmented ResNet50 model and a dynamic threshold Grad-CAM method, enhancing classification accuracy and interpretability in breast cancer histopathology images.

Findings

DALAResNet50 outperforms existing models in accuracy and F1 score.

DT Grad-CAM provides clearer, more focused visual explanations.

Model performs well on imbalanced datasets.

Abstract

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.