A Hybrid Architecture for Benign-Malignant Classification of Mammography ROIs
For medical imaging researchers, it offers an efficient hybrid model that balances local and global feature extraction, though the improvement over existing methods is not quantified.
The paper proposes a hybrid architecture combining EfficientNetV2-M with Vision Mamba for benign-malignant classification of mammography ROIs, achieving strong performance on the CBIS-DDSM dataset.
Accurate characterization of suspicious breast lesions in mammography is important for early diagnosis and treatment planning. While Convolutional Neural Networks (CNNs) are effective at extracting local visual patterns, they are less suited to modeling long-range dependencies. Vision Transformers (ViTs) address this limitation through self-attention, but their quadratic computational cost can be prohibitive. This paper presents a hybrid architecture that combines EfficientNetV2-M for local feature extraction with Vision Mamba, a State Space Model (SSM), for efficient global context modeling. The proposed model performs binary classification of abnormality-centered mammography regions of interest (ROIs) from the CBIS-DDSM dataset into benign and malignant classes. By combining a strong CNN backbone with a linear-complexity sequence model, the approach achieves strong lesion-level classification performance in an ROI-based setting.