Skip to content
2000
Volume 21, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
file format text download EPUB
side by side viewer icon HTML

Abstract

Objective:

To address insufficient segmentation accuracy in athletes' soft tissue injury analysis, this study proposes an enhanced Swin-Unet model with multi-scale feature fusion the FPN (Feature Pyramid Network) and an adaptive window selection mechanism for dynamic receptive field adjustment.

Methods:

A weighted hybrid loss function integrating Dice Loss, Cross-Entropy Loss, and boundary auxiliary loss optimizes segmentation precision and boundary recognition.

Results:

Evaluated on the OAI-ZIB dataset using 10-fold cross-validation, the model achieves a DSC (Dice Similarity Coefficient) of 0.978, outperforming baseline Swin-Unet and mainstream architectures. Superior performance is demonstrated in IoU (Intersection over Union) (0.968) and boundary Hausdorff distance (3.21), alongside significantly reduced diagnosis time (6.0 minutes vs. 16.8 minutes manually).

Conclusion:

This framework enhances real-time medical imaging analysis for athlete injuries, offering improved accuracy, efficiency, and clinical utility in soft tissue segmentation tasks.

© 2025 The Author(s). Published by Bentham Science Publishers.
This is an open access article published under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/legalcode
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056403181250925102654
2025-10-15
2025-12-10

  • From This Site

    /content/journals/cmir/10.2174/0115734056403181250925102654
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmir/21/1/CMIR-21-E15734056403181.html?itemId=/content/journals/cmir/10.2174/0115734056403181250925102654&mimeType=html&fmt=ahah

References

  1. XiaohongL. YueG. QiangL. PanS. Sports-induced muscle injury: Mechanism, quantitative evaluation by magnetic resonance imaging and progress in treatment.Chin. J. Tissue Eng. Res.2021251422802280
     [Google Scholar]
  2. ZhenW. LinH. FeiH. LinW. Exercise activates skeletal muscle satellite cells: Exercise prevention and treatment of age-related sarcopenia and muscle damage repair.Chin. J. Tissue Eng. Res.2021252337523752
     [Google Scholar]
  3. ChanZ. LinH. TingH. YingL. ZhangB. Clinical effect of early rehabilitation treatment after repair of dorsum skin and soft tissue defect with extensor tendon injury.Chin. J. of Burns and Wound Repair2024404365372
     [Google Scholar]
  4. YuanY. ZhangZ. MaP. HuX. JianX. MRI quantitative study on the correlation between the degree of supraspinatus tendon injury and fat infiltration and muscle atrophy.J. Bengbu Med Coll.202045811001103
     [Google Scholar]
  5. ParsonsJ.L. CoenS.E. BekkerS. Anterior cruciate ligament injury: Towards a gendered environmental approach.Br. J. Sports Med.2021551798499010.1136/bjsports‑2020‑10317333692033
     [Google Scholar]
  6. BramJ.T. MageeL.C. MehtaN.N. PatelN.M. GanleyT.J. Anterior cruciate ligament injury incidence in adolescent athletes: A systematic review and meta-analysis.Am. J. Sports Med.20214971962197210.1177/036354652095961933090889
     [Google Scholar]
  7. DuboisB. EsculierJ.F. Soft-tissue injuries simply need PEACE and LOVE.Br. J. Sports Med.2020542727310.1136/bjsports‑2019‑10125331377722
     [Google Scholar]
  8. LiR.T. SalataM.J. RambhiaS. SheehanJ. VoosJ.E. Does overexertion correlate with increased injury? The relationship between player workload and soft tissue injury in professional American football players using wearable technology.Sports Health2020121667310.1177/194173811986847731469616
     [Google Scholar]
  9. BenjaminiD. IaconoD. KomloshM.E. PerlD.P. BrodyD.L. BasserP.J. Diffuse axonal injury has a characteristic multidimensional MRI signature in the human brain.Brain2021144380081610.1093/brain/awaa44733739417
     [Google Scholar]
  10. FronzaM. ThavendiranathanP. ChanV. KarurG.R. UdellJ.A. WaldR.M. HongR. HannemanK. Myocardial injury pattern at MRI in COVID-19 vaccine–associated myocarditis.Radiology2022304355356210.1148/radiol.21255935166587
     [Google Scholar]
  11. RicciV. RicciC. CoccoG. GervasoniF. DonatiD. FarìG. ÖzçakarL. Histopathology and high-resolution ultrasound imaging for peripheral nerve (injuries).J. Neurol.202226973663367510.1007/s00415‑022‑10988‑135091803
     [Google Scholar]
  12. KoneruS. NguyenV.T. HacquebordJ.H. AdlerR.S. Brachial plexus nerve injuries and disorders.Magn. Reson. Imaging Clin. N. Am.202331225526710.1016/j.mric.2023.01.00637019549
     [Google Scholar]
  13. PengH. QiZ. ChaoL. A review of image segmentation methods.J. Wuhan Univ.2020666519531
     [Google Scholar]
  14. HongH. RongfeiL. TaoJ. YuanL. ZhangJ. A segmentation algorithm for pulmonary nodules in CT images based on improved U-Net++.Guangzi Xuebao20215027383
     [Google Scholar]
  15. WuC. Application of musculoskeletal ultrasound in the diagnosis of traumatic superficial soft tissue injuries.J. Pract. Hand Surg.20203419798
     [Google Scholar]
  16. YangW.H. ZhangQ.L. ZhangX.H. Diagnosis value of MRI in acute rotator interval injury.Zhongguo Gu Shang202134217517933666008
     [Google Scholar]
  17. WangZ. XiaoP. TanH. Spinal magnetic resonance image segmentation based on U-net.J. Radiat. Res. Appl. Sci.202316310062710062710.1016/j.jrras.2023.10062737670740
     [Google Scholar]
  18. AliO. AliH. ShahS.A.A. ShahzadA. Implementation of a modified U-Net for medical image segmentation on edge devices.IEEE Trans. Circuits Syst. II Express Briefs202269114593459710.1109/TCSII.2022.3181132
     [Google Scholar]
  19. LiangX. LouY. ZhouH. Fast knee joint model reconstruction based on U-Net network for SAR estimation.J. Spectrosc.2020372144151
     [Google Scholar]
  20. SunR. ZhangW. Anatomical structure segmentation of human ear cartilage MRI images based on 3D U-Net.Zhongguo Shengwu Yixue Gongcheng Xuebao2021405531539
     [Google Scholar]
  21. WangS. JiangZ. YangH. LiX. YangZ. Automatic segmentation of lumbar spine MRI images based on improved attention U‐net.Comput. Intell. Neurosci.20222022111010.1155/2022/425947136156962
     [Google Scholar]
  22. RahmanH. BukhtT.F.N. ImranA. TariqJ. TuS. AlzahraniA. A deep learning approach for liver and tumor segmentation in CT images using ResUNet.Bioengineering20229836836810.3390/bioengineering908036836004893
     [Google Scholar]
  23. CaoY. LiuS. PengY. LiJ. DenseUNet: Densely connected UNet for electron microscopy image segmentation.IET Image Process.202014122682268910.1049/iet‑ipr.2019.1527
     [Google Scholar]
  24. SarrafS. SarrafA. DeSouzaD.D. AndersonJ.A.E. KabiaM. The Alzheimer’s Disease Neuroimaging Initiative OViTAD: Optimized vision transformer to predict various stages of Alzheimer’s disease using resting-state fMRI and structural MRI data.Brain Sci.202313226026010.3390/brainsci1302026036831803
     [Google Scholar]
  25. AkinyeluA.A. ZaccagnaF. GristJ.T. CastelliM. RundoL. Brain tumor diagnosis using machine learning, convolutional neural networks, capsule neural networks and vision transformers, applied to MRI: A survey.J. Imaging20228820520510.3390/jimaging808020535893083
     [Google Scholar]
  26. WangT. WangY. ZhuH. LiuZ. ChenY.C. WangL. DuanS. YinX. JiangL. Automatic substantia nigra segmentation with Swin-Unet in susceptibility- and T2-weighted imaging: Application to Parkinson disease diagnosis.Quant. Imaging Med. Surg.20241496337635110.21037/qims‑24‑2739281181
     [Google Scholar]
  27. XiaoD. KangZ. FuY. LiZ. RanM. Csswin-unet: A Swin-unet network for semantic segmentation of remote sensing images by aggregating contextual information and extracting spatial information.Int. J. Remote Sens.202344237598762510.1080/01431161.2023.2285738
     [Google Scholar]
  28. HeK. GouF. WuJ. Image segmentation technology based on transformer in medical decision‐making system.IET Image Process.202317103040305410.1049/ipr2.12854
     [Google Scholar]
  29. WuJ. XuQ. ShenY. ChenW. XuK. QiX.R. Swin transformer improves the IDH mutation status prediction of gliomas free of MRI-based tumor segmentation.J. Clin. Med.202211154625462510.3390/jcm1115462535956236
     [Google Scholar]
  30. HuangW. ShuX. WangZ. ZhangL. ChenC. XuJ. YiZ. Feature pyramid network with level-aware attention for meningioma segmentation.IEEE Trans. Emerg. Top. Comput. Intell.2022651201121010.1109/TETCI.2022.3146965
     [Google Scholar]
  31. SunZ. MengC. ChengJ. ZhangZ. ChangS. A multi-scale feature pyramid network for detection and instance segmentation of marine ships in SAR images.Remote Sens.202214246312631210.3390/rs14246312
     [Google Scholar]
  32. SongY. ElibolA. ChongN.Y. Abdominal multi-organ segmentation based on feature pyramid network and spatial recurrent neural network.IFAC-PapersOnLine20235623001300810.1016/j.ifacol.2023.10.1426
     [Google Scholar]
  33. YangH. ChenJ. YueP. Study on automatic labeling and segmentation of dam surface concrete cracks based on Swin-Unet.Shuili Fadian Xeubao202443122333
     [Google Scholar]
  34. GanM. AnZ. ZhangX. Study on prediction of aortic restenosis based on Swin-Unet.J. Guangdong Univ. Technol.202340053440
     [Google Scholar]
  35. LiuX. SongL. LiuS. ZhangY. A review of deep-learning-based medical image segmentation methods.Sustainability20211331224122410.3390/su13031224
     [Google Scholar]
  36. LiZ. LiY. LiQ. WangP. GuoD. LuL. JinD. ZhangY. HongQ. Lvit: Language meets vision transformer in medical image segmentation.IEEE Trans. Med. Imaging20244319610710.1109/TMI.2023.329171937399157
     [Google Scholar]
  37. ZhangL. YinX. LiuX. LiuZ. Medical image segmentation by combining feature enhancement Swin Transformer and UperNet.Sci. Rep.2025151145651456510.1038/s41598‑025‑97779‑640281077
     [Google Scholar]
  38. ZouP. WuJ.S. SwinE-UNet3+: Swin transformer encoder network for medical image segmentation.Prog. Artif. Intell.20231219910510.1007/s13748‑023‑00300‑1
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056403181250925102654
Loading
Multi-Scale Fusion for Real-Time Image Observation and Data Analysis of Athletes after Soft Tissue Injury
Curr. Med. Imaging 21, E15734056403181 (2025); https://doi.org/10.2174/0115734056403181250925102654
/content/journals/cmir/10.2174/0115734056403181250925102654
/content/journals/cmir/10.2174/0115734056403181250925102654
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Athlete injuries; FPN; Image segmentation; Medical imaging; Multi-scale fusion; Soft tissue injury

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test