Anari Shokofeh, Sadeghi Soroush, Sheikhi Ghazaal, Ranjbarzadeh Ramin, Bendechache Malika
Department of Accounting, Economic and Financial Sciences, Islamic Azad University, South Tehran Branch, Tehran, Iran.
School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran.
Sci Rep. 2025 Jan 6;15(1):1027. doi: 10.1038/s41598-024-84504-y.
This study utilizes the Breast Ultrasound Image (BUSI) dataset to present a deep learning technique for breast tumor segmentation based on a modified UNet architecture. To improve segmentation accuracy, the model integrates attention mechanisms, such as the Convolutional Block Attention Module (CBAM) and Non-Local Attention, with advanced encoder architectures, including ResNet, DenseNet, and EfficientNet. These attention mechanisms enable the model to focus more effectively on relevant tumor areas, resulting in significant performance improvements. Models incorporating attention mechanisms outperformed those without, as reflected in superior evaluation metrics. The effects of Dice Loss and Binary Cross-Entropy (BCE) Loss on the model's performance were also analyzed. Dice Loss maximized the overlap between predicted and actual segmentation masks, leading to more precise boundary delineation, while BCE Loss achieved higher recall, improving the detection of tumor areas. Grad-CAM visualizations further demonstrated that attention-based models enhanced interpretability by accurately highlighting tumor areas. The findings denote that combining advanced encoder architectures, attention mechanisms, and the UNet framework can yield more reliable and accurate breast tumor segmentation. Future research will explore the use of multi-modal imaging, real-time deployment for clinical applications, and more advanced attention mechanisms to further improve segmentation performance.
本研究利用乳腺超声图像（BUSI）数据集，提出一种基于改进的U-Net架构的乳腺肿瘤分割深度学习技术。为提高分割精度，该模型将注意力机制（如卷积块注意力模块（CBAM）和非局部注意力）与先进的编码器架构（包括ResNet、DenseNet和EfficientNet）相结合。这些注意力机制使模型能够更有效地聚焦于相关肿瘤区域，从而显著提高性能。纳入注意力机制的模型表现优于未纳入的模型，这在更高的评估指标中得到体现。还分析了骰子损失（Dice Loss）和二元交叉熵（BCE）损失对模型性能的影响。骰子损失最大化了预测分割掩码与实际分割掩码之间的重叠，从而实现更精确的边界描绘，而BCE损失实现了更高的召回率，改善了肿瘤区域的检测。Grad-CAM可视化进一步表明，基于注意力的模型通过准确突出肿瘤区域提高了可解释性。研究结果表明，将先进的编码器架构、注意力机制和U-Net框架相结合，可以实现更可靠、准确的乳腺肿瘤分割。未来的研究将探索多模态成像的应用、临床应用的实时部署以及更先进的注意力机制，以进一步提高分割性能。
