EUVIMEDScopri EUVIMED
Open access · CC BY 4.0

Symmetry-Aware SwinUNet with Integrated Attention for Transformer-Based Segmentation of Thyroid Ultrasound Images

Ammar Oad, Imtiaz Hussain Koondhar, Feng Dong, Weibing Liu, Beiji Zou, Weichun Liu, Yun Chen, Yaoqun Wu

Symmetry · 2026-01-10 · 18 (1) · 141

DOI: 10.3390/sym18010141 ↗

At a glance

Journal article in Symmetry, published online on 2026-01-10. Written by Ammar Oad and 7 co-authors. Cited 4 times so far (Crossref); 57 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Key R&D Program of China, National Natural Science Foundation of China, Key Research and Development Program of Hunan Province.

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

Accurate segmentation of thyroid nodules in ultrasound images remains challenging due to low contrast, speckle noise, and inter-patient variability that disrupt the inherent spatial symmetry of thyroid anatomy. This study proposes a symmetry-aware SwinUNet framework with integrated spatial attention for thyroid nodule segmentation. The hierarchical window-based Swin Transformer encoder preserves spatial symmetry and scale consistency while capturing both global contextual information and fine-grained local features. Attention modules in the decoder emphasize symmetry consistent anatomical regions and asymmetric nodule boundaries, effectively suppressing irrelevant background responses. The proposed method was evaluated on the publicly available TN3K thyroid ultrasound dataset. Experimental results demonstrate strong performance, achieving a Dice Similarity Coefficient of 85.51%, precision of 87.05%, recall of 89.13%, an IoU of 78.00%, accuracy of 97.02%, and an AUC of 99.02%. Compared with the baseline model, the proposed approach improves the IoU and Dice score by 15.38% and 12.05%, respectively, confirming its ability to capture symmetry-preserving nodule morphology and boundary asymmetry. These findings indicate that the proposed symmetry-aware SwinUNet provides a robust and clinically promising solution for thyroid ultrasound image analysis and computer-aided diagnosis.

Funding

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • Key Research and Development Program of Hunan Province
  • Natural Science Research in China
  • Hunan Provincial Natural Science Foundation Committee
  • Shaoyang Science and Technology Bureau, Hunan, China

Cite

APA

Oad, A., Koondhar, I. H., Dong, F., Liu, W., Zou, B., Liu, W., Chen, Y., & Wu, Y. (2026). Symmetry-Aware SwinUNet with Integrated Attention for Transformer-Based Segmentation of Thyroid Ultrasound Images. Symmetry, 18(1), 141. https://doi.org/10.3390/sym18010141

Vancouver

Oad A, Koondhar IH, Dong F, Liu W, Zou B, Liu W, et al. Symmetry-Aware SwinUNet with Integrated Attention for Transformer-Based Segmentation of Thyroid Ultrasound Images. Symmetry. 2026;18(1):141. doi:10.3390/sym18010141

BibTeX
@article{Oad2026,
  author = {Oad, Ammar and Koondhar, Imtiaz Hussain and Dong, Feng and Liu, Weibing and Zou, Beiji and Liu, Weichun and Chen, Yun and Wu, Yaoqun},
  title = {Symmetry-Aware SwinUNet with Integrated Attention for Transformer-Based Segmentation of Thyroid Ultrasound Images},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {1},
  pages = {141},
  doi = {10.3390/sym18010141}
}
Start for free →