用Transformer融合甲状腺结构信息，提升超声图像结节分割精度
Anatomy-Guided Representation Learning Using a Transformer-Based Network for Thyroid Nodule Segmentation in Ultrasound Images
- 分阶段训练：先无监督增强特征提取，再多任务联合优化
- 在TN3K和DDTI数据集上达到最新最高性能
- 适合需要高精度结节分割的临床辅助诊断场景
甲状腺结节在超声图像中的准确分割对诊断和治疗规划至关重要。然而，结节与周围组织边界模糊、尺寸差异大以及标注数据稀缺给自动化分割带来挑战。现有深度学习模型难以有效利用甲状腺整体上下文信息且泛化能力不足。为此，我们提出SSMT-Net——一种基于Transformer的半监督多任务网络，在初始无监督阶段利用未标注数据增强编码器特征提取能力；在监督阶段联合优化结节分割、腺体分割和结节大小估计，融合局部与全局上下文特征。在TN3K和DDTI数据集上的大量评估表明，SSMT-Net优于当前最优方法，具有更高准确率和鲁棒性，展现出实际临床应用潜力。
原文摘要 · Abstract (English)
Accurate thyroid nodule segmentation in ultrasound images is critical for diagnosis and treatment planning. However, ambiguous boundaries between nodules and surrounding tissues, size variations, and the scarcity of annotated ultrasound data pose significant challenges for automated segmentation. Existing deep learning models struggle to incorporate contextual information from the thyroid gland and generalize effectively across diverse cases. To address these challenges, we propose SSMT-Net, a Semi-Supervised Multi-Task Transformer-based Network that leverages unlabeled data to enhance Transformer-centric encoder feature extraction capability in an initial unsupervised phase. In the supervised phase, the model jointly optimizes nodule segmentation, gland segmentation, and nodule size estimation, integrating both local and global contextual features. Extensive evaluations on the TN3K and DDTI datasets demonstrate that SSMT-Net outperforms state-of-the-art methods, with higher accuracy and robustness, indicating its potential for real-world clinical applications.
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。