Mammographic Lesion Segmentation with Lightweight Models: A Comparative Study

TL;DR

This study compares lightweight deep learning models for mammographic lesion segmentation, demonstrating that models like MobileNetV2 can achieve competitive accuracy with significantly fewer parameters, suitable for resource-limited settings.

Contribution

It provides a comprehensive evaluation of lightweight architectures for mammogram segmentation, highlighting MobileNetV2's effectiveness over traditional models like U-Net.

Findings

MobileNetV2 with SCSE achieved a Dice score of 0.5766.

Lightweight models used approximately 75% fewer parameters than U-Net.

Cross-dataset evaluation showed reduced accuracy but maintained high recall.

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, FPN, 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.