Skip to main content
Log in

RETRACTED ARTICLE: Applying deep learning in football ankle injury for value of high-power magnetic resonance bioimaging evaluation

The Journal of Supercomputing Aims and scope Submit manuscript

This article was retracted on 15 February 2024

This article has been updated

Abstract

This study was to evaluate the performance of magnetic resonance imaging (MRI) reconstruction algorithm based on convolutional neural network (CNN) in the diagnosis of ankle injury of football player. An MRI image reconstruction algorithm based on CNN (CNN-MRI) was constructed, and it was compared with the generalized autocalibrating partially parallel acquisitions (GRAPPA), iterative self-consistent parallel imaging reconstruction from arbitrary k-space (SPIRiT), and simultaneous autocalibrating and k-space estimation (SAKE) in MRI image of patients with ankle injury. They were compared regarding MRI image reconstruction quality (image score, peak signal-to-noise ratio (PSNR), structural similarity (SSIM), root mean square error (RMSE), and running time) and the assessment accuracy for each lesion. The detection rate of ankle joint injury and evaluation accuracy of the bone contusion, ligament injury, tendon injury focus, and different stages of osteochondral injury of the patients were recorded. The reconstructed image score, PSNR, SSIM, RMSE, and running time were calculated accordingly. The results showed that the detection rates of osteochondral injury (97.58%), joint effusion (91.21%), and soft tissue swelling (93.47%) in the CNN-MRI group were higher than those in GRAPPA (81.14%, 74.24%, and 76.11%), SPIRiT (80.66%, 73.66%, and 74.87%), and SAKE (86.96%, 82.61%, and 80.5%) groups (P < 0.05). The number of patients with 5 scores of reconstructed images in the CNN-MRI group (19 cases) was remarkably higher than that in GRAPPA (12 cases), SPIRiT (11 cases), and SAKE groups (14 cases) (P < 0.05). PSNR and SSIM of reconstructed image of patients in CNN-MRI group were much higher in contrast to those in GRAPPA, SPIRiT, and SAKE groups (P < 0.05), while the RMSE and running time were much lower than other algorithms (P < 0.05). In addition, the accuracy of evaluating the osteochondral injury in stage I and stage II for the patients in the CNN-MRI group was obviously higher than that in GRAPPA, SPIRiT, and SAKE groups (P < 0.05). In short, CNN-MRI algorithm could greatly improve the quality and PSNR of MRI reconstructed images, shorten the running time, and had excellent performance in showing the details of tendon injury, ligament injury, and bone contusion lesions. Moreover, it had a good effect on image processing of football players, could improve the accuracy of the diagnosis of ankle joint injuries, and could assist clinicians in the imaging diagnosis of ankle joint injuries of the football players.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Change history

References

  1. Crema MD, Krivokapic B, Guermazi A et al (2019) MRI of ankle sprain: the association between joint effusion and structural injury severity in a large cohort of athletes. Eur Radiol 29(11):6336–6344. https://doi.org/10.1007/s00330-019-06156-1

    Article  PubMed  Google Scholar 

  2. Teramoto A, Akatsuka Y, Takashima H et al (2020) 3D MRI evaluation of morphological characteristics of lateral ankle ligaments in injured patients and uninjured controls. J Orthop Sci 25(1):183–187. https://doi.org/10.1016/jos.2019.02.018

    Article  PubMed  Google Scholar 

  3. Alvarez CAD, Hattori S, Kato Y et al (2019) Dynamic high-resolution ultrasound in the diagnosis of calcaneofibular ligament injury in chronic lateral ankle injury: a comparison with three-dimensional magnetic resonance imaging. J Med Ultrason 43:313–317. https://doi.org/10.1007/s10396-019-00993-9

    Article  Google Scholar 

  4. Cao S, Wang C, Ma X et al (2018) Imaging diagnosis for chronic lateral ankle ligament injury: a systemic review with meta-analysis. J Orthop Surg Res 13(1):122. https://doi.org/10.1186/s13018-018-0811-4

    Article  PubMed  PubMed Central  Google Scholar 

  5. Atat R, Liu L, Wu J et al (2018) Big data meet cyber-physical systems: a panoramic survey. IEEE Access 6:73603–73636. https://doi.org/10.1007/s10916-019-1468-1

    Article  Google Scholar 

  6. Wu J, Guo S, Li J et al (2016) Big data meet green challenges: greening big data. IEEE Syst J 10(3):873–887. https://doi.org/10.1186/s12889-018-5030-8

    Article  ADS  Google Scholar 

  7. Warner SJ, Garner MR, Fabricant PD et al (2019) The Diagnostic accuracy of radiographs and magnetic resonance imaging in predicting deltoid ligament ruptures in ankle fractures. HSS J 15(2):115–121. https://doi.org/10.1007/s11420-018-09655-x

    Article  PubMed  PubMed Central  Google Scholar 

  8. Lv Z, Kong W, Zhang X et al (2019) Intelligent security planning for regional distributed energy internet. IEEE Trans Indus Infer 16(5):3540–3547. https://doi.org/10.1016/S0140-6736(17)31958-X

    Article  Google Scholar 

  9. Persaud S, Hentges MJ, Catanzariti AR (2019) Occurrence of lateral ankle ligament disease with stage 2 to 3 adult-acquired flatfoot deformity confirmed via magnetic resonance imaging: a retrospective study. J Foot Ankle Surg 58(2):243–247. https://doi.org/10.1053/j.jfas.2018.08.030

    Article  PubMed  Google Scholar 

  10. Jang H, Kim NR, Moon SG et al (2019) Qualitative analysis on magnetic resonance imaging for preoperative evaluation of chronic lateral ankle ligament injury. J Korean Soc Radiol 80(6):1121–1131. https://doi.org/10.1161/STROKEAHA.120.029685

    Article  Google Scholar 

  11. Guo C, Lu J, Tian Z et al (2019) Optimization of critical parameters of PEM fuel cell using TLBO-DE based on Elman neural network. Energy Convers Manage 183:149–158. https://doi.org/10.1186/s13018-018-0891-1

    Article  Google Scholar 

  12. Yang HQ, Zhang L, Xue J et al (2019) Unsaturated soil slope characterization with Karhunen-Loève and polynomial chaos via Bayesian approach. Eng Comput 35(1):337–350. https://doi.org/10.1177/0734242X15572178

    Article  MathSciNet  CAS  Google Scholar 

  13. Yavuz İA, Yildirim AO, Oken OF et al (2019) Is It an overlooked injury? magnetic resonance imaging examination of occult talus lesions concomitant to tibial shaft fracture. J Foot Ankle Surg 58(3):447–452. https://doi.org/10.1053/j.jfas.2018.09.007

    Article  PubMed  Google Scholar 

  14. Ersoz E, Tokgoz N, Kaptan AY et al (2019) Anatomical variations related to pathological conditions of the peroneal tendon: evaluation of ankle MRI with a 3D SPACE sequence in symptomatic patients. Skeletal Radiol 48(8):1221–1231. https://doi.org/10.1007/s00256-019-3151-5

    Article  PubMed  Google Scholar 

  15. Gros C, De Leener B, Badji A et al (2019) Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks. Neuroimage 184:901–915. https://doi.org/10.1016/j.neuroimage.2018.09.081

    Article  PubMed  Google Scholar 

  16. Samaher A Smart system to create an optimal higher education environment using IDA and IOTs. Int J Comput Appl 42(3): 244–259. doi: https://doi.org/10.1080/1206212X.2018.1512460

  17. Al-Janabi S, Alkaim AF, Adel Z (2020) An innovative synthesis of deep learning techniques (DCapsNet & DCOM) for generation electrical renewable energy from wind energy. Soft Comput 24(1). doi:https://doi.org/10.1007/s00500-020-04905-9

  18. Al-Janabi S, Mohammad M, Yousif AY (2020) 2 3 Soft computing a fusion of foundations, methodologies and applications a new method for prediction of air pollution based on intelligent computation. doi:https://doi.org/10.1007/s00500-019-04495-1

  19. Al-Janabi S, Alkaim AF (2020) A nifty collaborative analysis to predicting a novel tool (DRFLLS) for missing values estimation. Soft Comput 24(1). doi:https://doi.org/10.1007/s00500-019-03972-x

  20. Alkaim AF, Al_Janabi S (2020) Multi objectives optimization to gas flaring reduction from oil production. doi: https://doi.org/10.1007/978-3-030-23672-4_10

  21. Ali SH (2012) Miner for OACCR: case of medical data analysis in knowledge discovery. IEEE 962–975. doi: https://doi.org/10.1109/SETIT.2012.6482043

  22. Durastanti G, Leardini A, Siegler S et al (2019) Comparison of cartilage and bone morphological models of the ankle joint derived from different medical imaging technologies. Quant Imaging Med Surg 9(8):1368. https://doi.org/10.21037/qims.2019.08.08

    Article  PubMed  PubMed Central  Google Scholar 

  23. Li SL, Zhao WJ, Hao S et al (2015) Imaging study of ankle injury in professional soccer player of males. Nat Med J China 95(17):1290–1294. https://doi.org/10.1136/bjsports-2018-100298

    Article  Google Scholar 

  24. van Leeuwen C, Haak T, Kop M et al (2019) The additional value of gravity stress radiographs in predicting deep deltoid ligament integrity in supination external rotation ankle fractures. Eur J Trauma Emerg Surg 45(4):727–735. https://doi.org/10.1007/s00068-018-0923-x

    Article  PubMed  Google Scholar 

  25. Tawk S, Lecouvet F, Putineanu DC et al (2019) Unusual proximal fragment migration of an os peroneum fracture with associated peroneus longus tendon injury—a tree often hides a forest. Skeletal Radiol 48(2):317–322. https://doi.org/10.1007/s00256-018-3019-0

    Article  PubMed  Google Scholar 

  26. Guo S, Chen R, Li H et al (2019) Identify Severity Bug Report with Distribution Imbalance by CR-SMOTE and ELM. Int J Softw Eng Knowl Eng 29(2):139–175. https://doi.org/10.1093/ee/nvx157

    Article  Google Scholar 

  27. Zhang D (2019) Electrochemical impedance spectroscopy evaluation of corrosion protection of X65 carbon steel by halloysite nanotube-filled epoxy composite coatings in 3.5% NaCl solution. Int J Electrochem Sci 4659–4667. doi: https://doi.org/10.3760/cma.j.issn.1002-0098.2019.04.009

  28. Seok H, Lee SH, Yun SJ (2020) Diagnostic performance of ankle ultrasound for diagnosing anterior talofibular and calcaneofibular ligament injuries: a meta-analysis. Acta Radiol 61(5):651–661. https://doi.org/10.1177/0284185119873119

    Article  PubMed  Google Scholar 

  29. Lubberts B, D’Hooghe P, Bengtsson H et al (2019) Epidemiology and return to play following isolated syndesmotic injuries of the ankle: a prospective cohort study of 3677 male professional footballers in the UEFA Elite Club Injury Study. Br J Sports Med 53(15):959–964. https://doi.org/10.1136/bjsports-2017-097710

    Article  PubMed  Google Scholar 

  30. Teixeira PAG, Formery AS, Balazuc G et al (2019) Comparison between subtalar joint quantitative kinematic 4-D CT parameters in healthy volunteers and patients with joint stiffness or chronic ankle instability: a preliminary study. Eur J Radiol 114:76–84. https://doi.org/10.1016/j.ejrad.2019.03.001

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by Educational Science Planning in Jiangxi Province in 2018 “Study on Motivation Strategies of College Students’ Sports Learning Motivation Based on Self-determination Theory: Taking the Training of Campus Football Referees as an Example” (NO.18YB094). This work was supported by Research Topics on Teaching Reform of East China University of Technology in 2018 “Research and Practice on the Hybrid Teaching Model of Football Course Based on SPOC” (NO.DHJG-18-29).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Shuang Liu.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article has been retracted. Please see the retraction notice for more detail: https://doi.org/10.1007/s11227-024-05966-5"

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xie, J., Zhang, J., Liu, S. et al. RETRACTED ARTICLE: Applying deep learning in football ankle injury for value of high-power magnetic resonance bioimaging evaluation. J Supercomput 78, 3500–3516 (2022). https://doi.org/10.1007/s11227-021-04004-y

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-021-04004-y

Keywords

Navigation