The thyroid nodule segmentation of ultrasound images is a critical step for the early diagnosis of thyroid cancers in clinics. Due to the weak edge of ultrasound images and the complexity of thyroid tissue structure, it is still challenging to accurately segment the delicate contour of thyroid nodules. A local and context-attention adaptive network (LCA-Net) for thyroid nodule segmentation is proposed to address these shortcomings, which leverages both local feature information from convolution neural networks and global context information from transformers. Firstly, since most existing thyroid nodule segmentation models are skilled at local detail features and lose some context information, we propose a transformers-based context-attention module to capture more global associative information for the network and perceive the edge information of the nodule contour. Secondly, a backbone module with $7\times 1$, $1\times 7$ convolutions and the activation function Mish is designed, which enlarges the receptive field and extracts more feature details. Furthermore, a nodule adaptive convolution (NAC) module is introduced to adaptively deal with thyroid nodules of different sizes and positions, thereby improving the generalization performance of the model. Simultaneously, an optimized loss function is proposed to solve the pixels class imbalance problem in segmentation. The proposed LCA-Net, validated on the public TN-SCUI2020 and TN3K datasets, achieves Dice scores of 90.26% and 82.08% and PA scores of 98.87% and 96.97%, respectively, which outperforms other state-of-the-art thyroid nodule segmentation models. This paper demonstrates the superiority of the proposed LCA-Net for thyroid nodule segmentation, which possesses strong generalization performance and promising segmentation accuracy. Consequently, the proposed model has wide application prospects for thyroid nodule diagnosis in clinics.

中文翻译：

---

用于超声图像中甲状腺结节分割的局部和上下文注意自适应 LCA-Net

超声图像的甲状腺结节分割是临床甲状腺癌早期诊断的关键步骤。由于超声图像边缘较弱，甲状腺组织结构复杂，准确分割甲状腺结节的精细轮廓仍然具有挑战性。为了解决这些缺点，提出了一种用于甲状腺结节分割的局部和上下文注意自适应网络 (LCA-Net)，它利用了来自卷积神经网络的局部特征信息和来自转换器的全局上下文信息。首先，由于大多数现有的甲状腺结节分割模型都擅长局部细节特征并且丢失了一些上下文信息，我们提出了一个基于transformers的上下文注意模块来为网络捕获更多的全局关联信息并感知结节轮廓的边缘信息。其次，一个骨干模块$7\times 1$,$1\times 7$卷积和激活函数 Mish 的设计，扩大了感受野，提取了更多的特征细节。此外，还引入了结节自适应卷积（NAC）模块来自适应处理不同大小和位置的甲状腺结节，从而提高模型的泛化性能。同时，提出了一种优化的损失函数来解决分割中的像素类不平衡问题。提议的 LCA-Net 在公共 TN-SCUI2020 和 TN3K 数据集上验证，Dice 得分分别为 90.26% 和 82.08%，PA 得分分别为 98.87% 和 96.97%，优于其他最先进的甲状腺结节分割模型。本文展示了所提出的 LCA-Net 在甲状腺结节分割方面的优越性，具有很强的泛化性能和良好的分割精度。因此，该模型在临床甲状腺结节诊断中具有广泛的应用前景。