Qi Zhou
ABSTRACT
Abstract—Accurate and effective segmentation of thyroid nodules in ultrasound images is critical for computer-aided nodule diagnosis and treatment. However, due to the ill-defined margin of ultrasound images and the complexity of thyroid tissue structure, accurate segmentation of fine contours is still challenging. We propose a dual-stream network-assisted U-Net (DA-UNet) for these issues, which fully integrates features extracted by convolutional neural networks and vision transformer (ViT), applying them to the decoder and skip connection stages. The model is evaluated on the publicly available dataset TN3K, and the experimental results show that DA-UNet achieves 84.43% and 85.55% in Dice coefficient and F1-score respectively, with an average improvement of 3.75% and 3.12% compared to the current popular segmentation networks, reaching the optimal level.
- J. Chen, and H. You. “A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images,” Computer methods and programs in biomedicine, vol. 185, pp. 105329, 2020.Google Scholar
Digital Library
- J. Zhao, W. Zheng, L. Zhang, and H. Tian. “Segmentation of ultrasound images of thyroid nodule for assisting fine needle aspiration cytology,” Health information science and systems, vol. 1, pp. 1-12, 2013.Google ScholarCross Ref
- W. Du, and N. Sang. “An effective method for ultrasound thyroid nodules segmentation,” International symposium on bioelectronics and bioinformatics, pp. 207-210, 2015.Google ScholarCross Ref
- H. Gong, G. Chen, R. Wang, X. Xie, M. Mao, and Y. Yu. “Multi-task learning for thyroid nodule segmentation with thyroid region prior,” International symposium on biomedical imaging, pp. 257-261, 2021.Google ScholarCross Ref
- H. Bi, C. Cai, J. Sun, Y. Jiang, G. Lu and H. Shu. “BPAT-UNet: Boundary preserving assembled transformer UNet for ultrasound thyroid nodule segmentation,” Computer methods and programs in biomedicine, vol. 238, pp. 107614, 2023.Google ScholarDigital Library
- O. Ronneberger, P. Fischer, and T. Brox. “U-net: Convolutional networks for biomedical image segmentation,” Medical image computing and computer-assisted intervention, pp. 234-241, 2015.Google ScholarCross Ref
- O. Oktay, J. Schlemper, L. L. Folgoc, M. Lee, M. Heinrich, and K. Misawa, “Attention U-Net: learning where to look for the pancreas,” Preprint arXiv:1804.03999, 2018.Google Scholar
- Z. Zhou, M.Rahman Siddiquee, N. Tajbakhsh, and J. Liang. “Unet++: A nested u-net architecture for medical image segmentation,” Deep learning in medical image analysis and multimodal learning for clinical decision support, pp. 3-11, 2018.Google ScholarDigital Library
- L. Chen, Y. Zhu, G. Papandreou, and F. Schroff. “Encoder-decoder with atrous separable convolution for semantic image segmentation,” European conference on computer vision, pp. 833-851, 2018.Google ScholarDigital Library
- A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, and X. Zhai. “An image is worth 16x16 words: Transformers for image recognition at scale,” Preprint arXiv:2010.11929, 2020.Google Scholar
- J. Chen, Y. Lu, Q. Yu, X. Luo, E. Adeli, and Y. Wang. “Transunet: Transformers make strong encoders for medical image segmentation,” Preprint arXiv:2102.04306, 2021.Google Scholar
- A. Hatamizadeh, V. Nath, Y. Tang, D. Yang, H. R. Roth, and D. Xu. “Swin UNETR: Swin transformers for semantic segmentation of brain tumors in MRI images,” International miccai brainlesion workshop, pp. 272-284, 2021.Google Scholar
- Z. Liu, H. Mao, C. Y. Wu, C. Feichtenhofer, T. Darrell, and S Xie. “A convnet for the 2020s,” International conference on computer vision and pattern recognition, pp. 11976-11986, 2022.Google ScholarCross Ref
- T. Zhen, D. Hua, Y. Shi, W. Wang, X. Wang, and S. Ren. “Local and context-attention adaptive LCA-Net for thyroid nodule segmentation in ultrasound images,” Sensors, vol. 22(16), pp. 5984, 2022.Google ScholarCross Ref
Index Terms
- Dual-stream Assisted U-Net for Thyroid Nodule Segmentation
Recommendations
A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images
Highlights- Categorize methods into four groups according to their theoretical bases.
- ...
AbstractBackground and objective Thyroid image segmentation is an indispensable part in computer-aided diagnosis systems and medical image diagnoses of thyroid diseases. There have been dozens of studies on thyroid gland segmentation and ...
Coarse to Fine Ensemble Network for Thyroid Nodule Segmentation
Segmentation, Classification, and Registration of Multi-modality Medical Imaging DataAbstractA thyroid nodule is defined as a small lump of tissue (either solid or cystic - filled with fluid), usually more than one-quarter of an inch in diameter, that may protrude from the neck’s surface or may form in the thyroid gland itself. The nodule ...
Ultrasound Image Segmentation Algorithm of Thyroid Nodules Based on Improved U-Net Network
CCRIS '22: Proceedings of the 2022 3rd International Conference on Control, Robotics and Intelligent SystemThyroid nodule is a common clinical case, and there are different cancer risks according to the benign and malignant grades of the nodules. The shape, edge, and size of thyroid nodules are all important basis for judging the nature of thyroid nodules in ...
Comments