基于深度学习甲状腺结节的分割与识别的国内外研究现状，具体到文献

近来，深度学习在医学影像领域得到了广泛应用。甲状腺结节的分割与识别也是其中的研究热点之一。下面列举一些国内外相关文献：

1. Zhao W, Yang J, Sun Y, et al. Automatic thyroid nodule recognition and segmentation using deep convolutional neural networks and graph cut[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2016: 594-602.

2. Koh J, Nam S J, Kim E K, et al. Automated thyroid nodule detection and segmentation using deep learning and level set method[J]. Computers in biology and medicine, 2018, 100: 128-138.

3. Shin H C, Roth H R, Gao M, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning[J]. IEEE transactions on medical imaging, 2016, 35(5): 1285-1298.

4. Wang L, Liang P, Zhang Y, et al. Deep learning for thyroid nodule segmentation and classification in ultrasound images[J]. Journal of medical systems, 2019, 43(3): 53.

5. Wu X, Zhang Y, Zhang S, et al. Intelligent Analysis of Thyroid Ultrasound Images Based on Deep Learning[C]//International Conference on Artificial Intelligence and Security. Springer, Cham, 2018: 21-31.

6. Zhang Y, Chen W, Zhang L, et al. Automatic thyroid nodule recognition and segmentation based on deep convolutional neural networks and the level set method[J]. Medical physics, 2019, 46(5): 2184-2197.

这些文献主要采用了深度学习模型（如卷积神经网络）进行甲状腺结节的自动识别和分割，其中许多研究采用了图像处理方法（如图割、水平集）辅助深度学习模型进行分割。这些研究证明了深度学习在甲状腺结节识别与分割中的有效性。