Mammographic Lesion Segmentation with Lightweight Models: A Comparative Study

arXiv:2604.23899v1 Announce Type: new Abstract: Breast cancer is a leading cause of cancer-related mortality among women worldwide, with mammography as the primary screening tool. While deep learning models have shown strong performance in lesion segmentation, most rely on computationally intensive architectures that limit their use in resource-constrained environments. This study evaluates the performance and efficiency of lightweight models for mammographic lesion segmentation. Architectures including MobileNetV2, EfficientNet Lite, ENet, and Fast-SCNN were compared against a U-Net baseline using the INbreast dataset with 5-fold cross-validation. Performance was assessed using Dice score, Intersection over Union (IoU), and Recall, alongside model complexity. MobileNetV2 with Squeeze-and-Excitation (SCSE) achieved the best performance, with a Dice score of 0.5766 while using approximately 75% fewer parameters than U-Net. Cross-dataset evaluation on the DMID dataset showed reduced accuracy due to domain shift but preserved recall. These results demonstrate that lightweight architectures offer a practical balance between performance and efficiency for deployable CAD systems.

Related

• Multimodal Fusion of Histopathology Images and Electronic Health Records for Early Breast Cancer Diagnosis
• Federated Breast Cancer Detection Enhanced by Synthetic Ultrasound Image Augmentation
• A deep learning pipeline for PAM50 subtype classification using histopathology images and multi-objective patch selection
• A Workflow to Efficiently Generate Dense Tissue Ground Truth Masks for Digital Breast Tomosynthesis
• Region-Affinity Attention for Whole-Slide Breast Cancer Classification in Deep Ultraviolet Imaging

Source: arXiv cs.CV | 2026-04-28