提出双分支网络提升超声图像病灶边界分割精度
DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentation
- 设计双分支结构学习病灶与周围组织的关系
- 融合体部与边界特征，使分割边界更清晰
- 在乳腺癌等三类病变上达到87.75%最高分割精度
由于难以区分病灶与周围组织的边界，超声图像中病灶的精准分割极具挑战。尽管深度学习提升了分割准确率，但对边界质量及其与人体结构关系的关注仍不足。为此，我们提出UBBS-Net，一种双分支深度神经网络，通过学习病灶与周围组织的关系来改进分割效果，并设计特征融合模块整合体部与边界信息。在三个公开数据集上的评估显示，UBBS-Net优于现有方法，在乳腺癌、臂丛神经和婴儿血管瘤分割任务中分别取得81.05%、76.41%和87.75%的Dice相似系数。结果表明，UBBS-Net在超声图像分割中具有显著有效性。代码已开源：https://github.com/apple1986/DBF-Net。
原文摘要 · Abstract (English)
Accurately segmenting lesions in ultrasound images is challenging due to the difficulty in distinguishing boundaries between lesions and surrounding tissues. While deep learning has improved segmentation accuracy, there is limited focus on boundary quality and its relationship with body structures. To address this, we introduce UBBS-Net, a dual-branch deep neural network that learns the relationship between body and boundary for improved segmentation. We also propose a feature fusion module to integrate body and boundary information. Evaluated on three public datasets, UBBS-Net outperforms existing methods, achieving Dice Similarity Coefficients of 81.05% for breast cancer, 76.41% for brachial plexus nerves, and 87.75% for infantile hemangioma segmentation. Our results demonstrate the effectiveness of UBBS-Net for ultrasound image segmentation. The code is available at https://github.com/apple1986/DBF-Net.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。