Academic Journal
Ses: a Swin-Unet Edge-aware Segmentation network for uterine fibroid ultrasound images.
| Τίτλος: | Ses: a Swin-Unet Edge-aware Segmentation network for uterine fibroid ultrasound images. |
|---|---|
| Συγγραφείς: | Wang X; Children's Hospital of Shanxi & Women Health Center of Shanxi, Taiyuan, 030013, Shanxi, China., Shi L; Children's Hospital of Shanxi & Women Health Center of Shanxi, Taiyuan, 030013, Shanxi, China. etyycsk@126.com., Wang W; Shanxi International Travel Healthcare Center (Taiyuan Customs Port Clinic), Taiyuan, 030021, Shanxi, China., Guo L; Children's Hospital of Shanxi & Women Health Center of Shanxi, Taiyuan, 030013, Shanxi, China. |
| Πηγή: | Biomedical engineering online [Biomed Eng Online] 2026 May 04; Vol. 25 (1). Date of Electronic Publication: 2026 May 04. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: BioMed Central Country of Publication: England NLM ID: 101147518 Publication Model: Electronic Cited Medium: Internet ISSN: 1475-925X (Electronic) Linking ISSN: 1475925X NLM ISO Abbreviation: Biomed Eng Online Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : BioMed Central, [2002- |
| Ιατρικοί όροι (MeSH): | Leiomyoma*/diagnostic imaging , Image Processing, Computer-Assisted*/methods, Ultrasonography ; Humans ; Female |
| Περίληψη: | Uterine fibroids represent one of the most prevalent gynecological tumors; however, their ultrasound images frequently exhibit indistinct boundaries and complex morphologies, thereby complicating accurate segmentation. An enhanced Swin-Unet-based framework, designated the Swin-Unet Edge-Sensitive Segmentation (SES) network, is proposed herein to advance boundary delineation and segmentation accuracy. The SES network incorporates the Residual Channel Attention Network (RCAN) to recalibrate feature responses via channel attention weighting, thereby reinforcing the representation of lesion regions, and the Richer Convolutional Features (RCF) module to preserve multi-scale spatial information through hierarchical feature integration, effectively addressing pixel-level classification in regions with blurred boundaries. The model was evaluated on annotated ultrasound images provided by Shanxi Provincial Children's Hospital. Experimental findings demonstrate that SES consistently outperforms established architectures, including U-Net, U-Net++, Attention U-Net, and TransUNet, achieving superior performance across multiple indices (Dice coefficient: 0.9452; IoU: 0.8721; accuracy: 0.9358). Ablation analyses further substantiate the pivotal contributions of the RCAN and RCF modules to the overall segmentation performance. The proposed SES framework integrates global modeling capacity, multi-scale attention mechanisms, and edge-sensitive feature extraction to deliver a more accurate and robust solution for the ultrasound image segmentation of uterine fibroids, highlighting its substantial potential for clinical application. (© 2026. The Author(s).) |
| Competing Interests: | Declarations. Ethics approval and consent to participate: This study has received formal approval from Children’s Hospital of Shanxi and Shanxi International Travel Healthcare Cente. The entire research process strictly adheres to the relevant provisions of the "Declaration of Helsinki of the World Medical Association" (revised Edition 2013) and the "Measures for the Ethical Review of Biomedical Research Involving Humans" (Order No. 11 of the National Health Commission), ensuring that the research design and implementation comply with ethical requirements. Consent for publication: The patients involved in this paper or their families all agree to authorize their relevant data to Children’s Hospital of Shanxi for medical research, academic paper publication, academic conference exchange and exhibition and other legitimate medical professional purposes in the form of anonymization (processing method to ensure that personal identity cannot be identified). Competing interests: The authors declare no conflict of interest. |
| References: | Mourad A, Kamga-Ngande C, Albaini O, Antaki R. Enhancing surgical performance: the role of robotic surgery in myomectomies, a systematic review and metanalysis. J Robot Surg. 2024;18(1):184. (PMID: 10.1007/s11701-024-01953-3) Liu XY, Yuan ZL, Cong FZ, Mao L, Li XL, Zhou Z, et al. Deep learning assisted detection and segmentation of uterine fibroids using multi-orientation magnetic resonance imaging. Abdom Radiol. 2025;50(10):4927–38. (PMID: 10.1007/s00261-025-04934-8) Borella F, Mancarella M, Castellano MPMSSBLPVTP. Uterine smooth muscle tumors: a multicenter, retrospective, comparative study of clinical and ultrasound features. Int J Gynecol Cancer. 2024;34(2):244–50. (PMID: 10.1136/ijgc-2023-004880) Kaushik R, Sharma KP, Malik S, Shanbhog M. An analysis conducted retrospectively on the use: Artificial intelligence in the detection of uterine fibroid. In: 2024 11th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO). Yang T, Yuan L, Li P, Liu P. Real-time automatic assisted detection of uterine fibroid in ultrasound images using a deep learning detector. Ultrasound Med Biol. 2023. Shahzad A, Mushtaq A, Sabeeh AQ, Ghadi YY, Mushtaq Z, Arif S, et al. Automated uterine fibroids detection in ultrasound images using deep convolutional neural networks. Healthcare (2227-9032). 2023;11(10). Militello C, Vitabile S, Rundo L, Russo G, Midiri M, Gilardi MC. A fully automatic 2D segmentation method for uterine fibroid in mrgfus treatment evaluation. Comput Biol Med. 2015;62:277–92. (PMID: 10.1016/j.compbiomed.2015.04.030) Mason SA, White IM, Lalondrelle S, Bamber JC, Harris EJ. The stacked-ellipse algorithm: an ultrasound-based 3-D uterine segmentation tool for enabling adaptive radiotherapy for uterine cervix cancer. Ultrasound Med Biol. 2020;46(4):1040–52. (PMID: 10.1016/j.ultrasmedbio.2019.09.001) Ning G, Zhang X, Liao H. Morphological active contour without edge-based model for real-time and non-rigid uterine fibroid tracking in hifu treatment. Healthc Technol Lett. 2019;6(6):172–5. (PMID: 10.1049/htl.2019.0067) Zhang J, Saha A, Zhu Z, Mazurowski MA. Hierarchical convolutional neural networks for segmentation of breast tumors in mri with application to radiogenomics. IEEE Trans Med Imaging PP(2). 2018:1–1. Dilna KT, Anitha J, Angelopoulou A, Kapetanios E, Chaussalet T, Hemanth D. Classification of uterine fibroids in ultrasound images using deep learning model. Cham: Springer; 2022. (PMID: 10.1007/978-3-031-08757-8_5) Kurata Y, Nishio M, Kido A, Fujimoto K, Togashi K. Automatic segmentation of the uterus on mri using a convolutional neural network. Comput Biol Med. 2019;114:103438. (PMID: 10.1016/j.compbiomed.2019.103438) Ning G, Zhang X, Zhang Q, Wang Z, Liao H. Real-time and multimodality image-guided intelligent HIFU therapy for uterine fibroid. Theranostics. 2020;10(10):4676–93. (PMID: 10.7150/thno.42830) Zhang C, Shu H, Yang G, Li F, Coatrieux JL. Hifunet: Multi-class segmentation of uterine regions from mr images using global convolutional networks for hifu surgery planning. IEEE Trans Med Imaging PP(99). 2020:1–1. Yupu L, Pengfei Z, Xiaojuan Z, Zhaojing Z, Ziyi W, Pengfei Q. MRI image analytics combined with ResNet101 deep learning for differentiating lumbar brucellosis spondylitis from spinal metastatic cancer. Chin J Med Imag Technol. 2025;41(6):958–62. Zhiwei L, ChengNv S, Chengwei L, Fajin L. 3D segmentation of uterine fibroids based on deep supervision and an attention gate. Front Oncol. 2025;15(6):958–62. Zhao AJ, Du X, Wang S, Wang W, Yuan S, Ma W, Yan W, Shen W, Zhu X. A cnn-transformer hybrid network for recognizing uterine fibroids. 2022 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia). 2022. p. 1–4. Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q, Wang M. Swin-unet: Unet-like pure transformer for medical image segmentation. 2021. Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B. Swin transformer: Hierarchical vision transformer using shifted windows. 2021. Liu Y, Cheng MM, Fan DP, Zhang L, Bian JW, Tao D. Semantic edge detection with diverse deep supervision. Int J Comput Vision. 2022;130(1):179–98. (PMID: 10.1007/s11263-021-01539-8) Ghosh S, Chaki A, Santosh K. Improved U-Net architecture with VGG-16 for brain tumor segmentation. Phys Eng Sci Med. 2021;44(3):703–12. (PMID: 10.1007/s13246-021-01019-w) Jiang L, Hu J, Huang T. Improved SwinUnet with fusion transformer and large kernel convolutional attention for liver and tumor segmentation in CT images. Sci Rep. 2025;15:14286. (PMID: 10.1038/s41598-025-98938-5) Sapkota N, Shi H, Zhang Y, Ma X, Zheng B, Chen DZ. When swin transformer meets kans: an improved transformer architecture for medical image segmentation. 2025. Lim YJ, Nam JH, Hwang Y. Small bowel bleeding detection using Swin Transformer in capsule endoscopy. Endoscopy. 2025;57(Sup2):125. Zhang Y, Li K, Li K, Wang L, Zhong B, Fu Y. Image super-resolution using very deep residual channel attention networks. 2018. Li C, Tan Y, Chen W, Luo X, Gao Y, Jia X, et al. Attention unet++: a nested attention-aware u-net for liver ct image segmentation. 2020:345–9. Chen J, Lu Y, Yu Q, Luo X, Zhou Y. Transunet: transformers make strong encoders for medical image segmentation. 2021. |
| Contributed Indexing: | Keywords: RCAN; RCF; Ultrasound image segmentation; Uterine fibroids |
| Entry Date(s): | Date Created: 20260505 Date Completed: 20260623 Latest Revision: 20260726 |
| Update Code: | 20260726 |
| PubMed Central ID: | PMC13289386 |
| DOI: | 10.1186/s12938-026-01575-w |
| PMID: | 42083029 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1475-925X |
|---|---|
| DOI: | 10.1186/s12938-026-01575-w |