A superpixel based self-attention network for uterine fibroid segmentation in high intensity focused ultrasound guidance images
Abstract Ultrasound guidance images are widely used for high intensity focused ultrasound (HIFU) therapy; however, the speckles, acoustic shadows, and signal attenuation in ultrasound guidance images hinder the observation of the images by radiologists and make segmentation of ultrasound guidance im...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-08711-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849335008144130048 |
|---|---|
| author | Shen Wen Dong Zhang Yuting Lei Yan Yang |
| author_facet | Shen Wen Dong Zhang Yuting Lei Yan Yang |
| author_sort | Shen Wen |
| collection | DOAJ |
| description | Abstract Ultrasound guidance images are widely used for high intensity focused ultrasound (HIFU) therapy; however, the speckles, acoustic shadows, and signal attenuation in ultrasound guidance images hinder the observation of the images by radiologists and make segmentation of ultrasound guidance images more difficult. To address these issues, we proposed the superpixel based attention network, a network integrating superpixels and self-attention mechanisms that can automatically segment tumor regions in ultrasound guidance images. The method is implemented based on the framework of region splitting and merging. The ultrasound guidance image is first over-segmented into superpixels, then features within the superpixels are extracted and encoded into superpixel feature matrices with the uniform size. The network takes superpixel feature matrices and their positional information as input, and classifies superpixels using self-attention modules and convolutional layers. Finally, the superpixels are merged based on the classification results to obtain the tumor region, achieving automatic tumor region segmentation. The method was applied to a local dataset consisting of 140 ultrasound guidance images from uterine fibroid HIFU therapy. The performance of the proposed method was quantitatively evaluated by comparing the segmentation results with those of the pixel-wise segmentation networks. The proposed method achieved 75.95% and 7.34% in mean intersection over union (IoU) and mean normalized Hausdorff distance (NormHD). In comparison to the segmentation transformer (SETR), this represents an improvement in performance by 5.52% for IoU and 1.49% for NormHD. Paired t-tests were conducted to evaluate the significant difference in IoU and NormHD between the proposed method and the comparison methods. All p-values of the paired t-tests were found to be less than 0.05. The analysis of evaluation metrics and segmentation results indicates that the proposed method performs better than existing pixel-wise segmentation networks in segmenting the tumor region on ultrasound guidance images. |
| format | Article |
| id | doaj-art-900101caf5df4c0e864e7fd6262ea2fe |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-900101caf5df4c0e864e7fd6262ea2fe2025-08-20T03:45:24ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-08711-xA superpixel based self-attention network for uterine fibroid segmentation in high intensity focused ultrasound guidance imagesShen Wen0Dong Zhang1Yuting Lei2Yan Yang3School of Physics and Technology, Wuhan UniversitySchool of Physics and Technology, Wuhan UniversitySchool of Physics and Technology, Wuhan UniversitySchool of Physics and Technology, Wuhan UniversityAbstract Ultrasound guidance images are widely used for high intensity focused ultrasound (HIFU) therapy; however, the speckles, acoustic shadows, and signal attenuation in ultrasound guidance images hinder the observation of the images by radiologists and make segmentation of ultrasound guidance images more difficult. To address these issues, we proposed the superpixel based attention network, a network integrating superpixels and self-attention mechanisms that can automatically segment tumor regions in ultrasound guidance images. The method is implemented based on the framework of region splitting and merging. The ultrasound guidance image is first over-segmented into superpixels, then features within the superpixels are extracted and encoded into superpixel feature matrices with the uniform size. The network takes superpixel feature matrices and their positional information as input, and classifies superpixels using self-attention modules and convolutional layers. Finally, the superpixels are merged based on the classification results to obtain the tumor region, achieving automatic tumor region segmentation. The method was applied to a local dataset consisting of 140 ultrasound guidance images from uterine fibroid HIFU therapy. The performance of the proposed method was quantitatively evaluated by comparing the segmentation results with those of the pixel-wise segmentation networks. The proposed method achieved 75.95% and 7.34% in mean intersection over union (IoU) and mean normalized Hausdorff distance (NormHD). In comparison to the segmentation transformer (SETR), this represents an improvement in performance by 5.52% for IoU and 1.49% for NormHD. Paired t-tests were conducted to evaluate the significant difference in IoU and NormHD between the proposed method and the comparison methods. All p-values of the paired t-tests were found to be less than 0.05. The analysis of evaluation metrics and segmentation results indicates that the proposed method performs better than existing pixel-wise segmentation networks in segmenting the tumor region on ultrasound guidance images.https://doi.org/10.1038/s41598-025-08711-xHIFU therapyUltrasound image segmentationSuperpixelsDeep learning |
| spellingShingle | Shen Wen Dong Zhang Yuting Lei Yan Yang A superpixel based self-attention network for uterine fibroid segmentation in high intensity focused ultrasound guidance images Scientific Reports HIFU therapy Ultrasound image segmentation Superpixels Deep learning |
| title | A superpixel based self-attention network for uterine fibroid segmentation in high intensity focused ultrasound guidance images |
| title_full | A superpixel based self-attention network for uterine fibroid segmentation in high intensity focused ultrasound guidance images |
| title_fullStr | A superpixel based self-attention network for uterine fibroid segmentation in high intensity focused ultrasound guidance images |
| title_full_unstemmed | A superpixel based self-attention network for uterine fibroid segmentation in high intensity focused ultrasound guidance images |
| title_short | A superpixel based self-attention network for uterine fibroid segmentation in high intensity focused ultrasound guidance images |
| title_sort | superpixel based self attention network for uterine fibroid segmentation in high intensity focused ultrasound guidance images |
| topic | HIFU therapy Ultrasound image segmentation Superpixels Deep learning |
| url | https://doi.org/10.1038/s41598-025-08711-x |
| work_keys_str_mv | AT shenwen asuperpixelbasedselfattentionnetworkforuterinefibroidsegmentationinhighintensityfocusedultrasoundguidanceimages AT dongzhang asuperpixelbasedselfattentionnetworkforuterinefibroidsegmentationinhighintensityfocusedultrasoundguidanceimages AT yutinglei asuperpixelbasedselfattentionnetworkforuterinefibroidsegmentationinhighintensityfocusedultrasoundguidanceimages AT yanyang asuperpixelbasedselfattentionnetworkforuterinefibroidsegmentationinhighintensityfocusedultrasoundguidanceimages AT shenwen superpixelbasedselfattentionnetworkforuterinefibroidsegmentationinhighintensityfocusedultrasoundguidanceimages AT dongzhang superpixelbasedselfattentionnetworkforuterinefibroidsegmentationinhighintensityfocusedultrasoundguidanceimages AT yutinglei superpixelbasedselfattentionnetworkforuterinefibroidsegmentationinhighintensityfocusedultrasoundguidanceimages AT yanyang superpixelbasedselfattentionnetworkforuterinefibroidsegmentationinhighintensityfocusedultrasoundguidanceimages |