Thyroid Nodule Ultrasound Image Segmentation Based on Improved Swin Transformer
To address the issue of inaccurate segmentation caused by blurred edges and strong noise in thyroid nodule ultrasound images, an image segmentation method based on an improved Swin Transformer is proposed. First, depthwise convolutional layers are integrated into the encoder/decoder of the Swin Tran...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10847842/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575578154205184 |
|---|---|
| author | Yue Wu Lin Huang Tiejun Yang |
| author_facet | Yue Wu Lin Huang Tiejun Yang |
| author_sort | Yue Wu |
| collection | DOAJ |
| description | To address the issue of inaccurate segmentation caused by blurred edges and strong noise in thyroid nodule ultrasound images, an image segmentation method based on an improved Swin Transformer is proposed. First, depthwise convolutional layers are integrated into the encoder/decoder of the Swin Transformer to enhance global-local feature representations. Second, a multi-scale feature fusion module is introduced through skip connections between the encoder and decoder to improve information flow and feature integration. Additionally, a multi-level patch embedding convolution is designed to enable layer-by-layer feature extraction from coarse to fine levels. Experimental results show that the proposed method achieves superior segmentation accuracy compared to state-of-the-art methods such as Attention U-Net, with Dice scores of 82.26% and 78.64% and IoU values of 73.00% and 67.93% on the TN3K and DDTI datasets, respectively. |
| format | Article |
| id | doaj-art-3f5648d7e96041ae8b2fad2db1574b79 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-3f5648d7e96041ae8b2fad2db1574b792025-01-31T23:04:37ZengIEEEIEEE Access2169-35362025-01-0113197881979510.1109/ACCESS.2025.353226410847842Thyroid Nodule Ultrasound Image Segmentation Based on Improved Swin TransformerYue Wu0Lin Huang1https://orcid.org/0000-0002-2678-2085Tiejun Yang2https://orcid.org/0000-0002-8644-4651College of Intelligent Medicine and Biotechnology, Guilin Medical University, Guilin, Guangxi, ChinaCollege of Physics and Electronic Information Engineering, Guilin University of Technology, Guilin, Guangxi, ChinaCollege of Intelligent Medicine and Biotechnology, Guilin Medical University, Guilin, Guangxi, ChinaTo address the issue of inaccurate segmentation caused by blurred edges and strong noise in thyroid nodule ultrasound images, an image segmentation method based on an improved Swin Transformer is proposed. First, depthwise convolutional layers are integrated into the encoder/decoder of the Swin Transformer to enhance global-local feature representations. Second, a multi-scale feature fusion module is introduced through skip connections between the encoder and decoder to improve information flow and feature integration. Additionally, a multi-level patch embedding convolution is designed to enable layer-by-layer feature extraction from coarse to fine levels. Experimental results show that the proposed method achieves superior segmentation accuracy compared to state-of-the-art methods such as Attention U-Net, with Dice scores of 82.26% and 78.64% and IoU values of 73.00% and 67.93% on the TN3K and DDTI datasets, respectively.https://ieeexplore.ieee.org/document/10847842/Image segmentationtransformerthyroid noduleultrasound image |
| spellingShingle | Yue Wu Lin Huang Tiejun Yang Thyroid Nodule Ultrasound Image Segmentation Based on Improved Swin Transformer IEEE Access Image segmentation transformer thyroid nodule ultrasound image |
| title | Thyroid Nodule Ultrasound Image Segmentation Based on Improved Swin Transformer |
| title_full | Thyroid Nodule Ultrasound Image Segmentation Based on Improved Swin Transformer |
| title_fullStr | Thyroid Nodule Ultrasound Image Segmentation Based on Improved Swin Transformer |
| title_full_unstemmed | Thyroid Nodule Ultrasound Image Segmentation Based on Improved Swin Transformer |
| title_short | Thyroid Nodule Ultrasound Image Segmentation Based on Improved Swin Transformer |
| title_sort | thyroid nodule ultrasound image segmentation based on improved swin transformer |
| topic | Image segmentation transformer thyroid nodule ultrasound image |
| url | https://ieeexplore.ieee.org/document/10847842/ |
| work_keys_str_mv | AT yuewu thyroidnoduleultrasoundimagesegmentationbasedonimprovedswintransformer AT linhuang thyroidnoduleultrasoundimagesegmentationbasedonimprovedswintransformer AT tiejunyang thyroidnoduleultrasoundimagesegmentationbasedonimprovedswintransformer |