Skip to main content

Advertisement

SpringerLink
Log in

Deep transfer learning-based visual classification of pressure injuries stages

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Pressure injury follow-up and treatment is a very costly and significant health care problem for many countries. Early and accurate diagnosis and treatment planning are critical for effective treatment of pressure injuries. Interventional information retrieval methods are both painful for patients and increase the risk of infection. However, thanks to non-invasive techniques such as imaging systems, it is possible to monitor pressure wounds more easily without causing any harm to patients. The purpose of this research is to develop a deep learning-based system for the analysis and monitoring of pressure injuries that provides an automatic classification of pressure injury stages. This paper introduces the pressure injury images dataset (PIID): a novel dataset for the classification of pressure injuries stages. We hope that PIID will encourage further research on the automatic visual classification of pressure injury stages. We also perform extensive analyses on PIID using state-the-of-art convolutional neural networks architectures with the power of transfer learning and image augmentation techniques.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

References

  1. Klonoff DC (2009) The increasing incidence of diabetes in the 21st century. J Diabetes Sci Technol 3(1):1–2. https://doi.org/10.1177/193229680900300101

    Article  Google Scholar 

  2. Pieper B (2015) Pressure ulcers: impact, etiology, and classification. In: Acute and chronic wounds: current management concepts, pp 124–139

  3. Horn SD, Bender SA, Ferguson ML et al (2004) The national pressure ulcer long-term care study: pressure ulcer development in long-term care residents. J Am Geriatr Soc 52:359–367

    Article  Google Scholar 

  4. Berlowitz D, Vandeusen Lukas C, Parker V et al (2018) Preventing pressure ulcers in Hospitals. Agency for Healthcare Research and Quality, Rockville, MD. https://www.ahrq.gov/patientsafety/settings/hospital/resource/pressureulcer/tool/index.html

  5. Brown G (2003) Long-term outcomes of full-thickness pressure ulcers: healing and mortality. Ostomy Wound Manage 49:42–50

    Google Scholar 

  6. Soldevilla Agreda JJ et al (2007) The burden of pressure ulcers in Spain. Wounds Compend Clin Res Pract 19(7):201–206

    Google Scholar 

  7. Tubaishat A, Papanikolaou P, Anthony D, Habiballah L (2018) Pressure ulcers prevalence in the acute care setting: a systematic review, 2000–2015. Clin Nurs Res 27:643–659. https://doi.org/10.1177/1054773817705541

    Article  Google Scholar 

  8. Zahia S, Garcia Zapirain MB, Sevillano X et al (2020) Pressure injury image analysis with machine learning techniques: a systematic review on previous and possible future methods. Artif Intell Med 102:101742. https://doi.org/10.1016/j.artmed.2019.101742

    Article  Google Scholar 

  9. Edsberg LE, Black JM, Goldberg M et al (2016) Revised national pressure ulcer advisory panel pressure injury staging system: revised pressure injury staging system. J Wound Ostomy Cont Nurs 43:585

    Article  Google Scholar 

  10. Jiang Q, Li X, Qu X et al (2014) The incidence, risk factors and characteristics of pressure ulcers in hospitalized patients in China. Int J Clin Exp Pathol 7:2587

    Google Scholar 

  11. Kasikci M, Aksoy M, Ay E (2018) Investigation of the prevalence of pressure ulcers and patient-related risk factors in hospitals in the province of Erzurum: a cross-sectional study. J Tissue Viabil 27:135–140. https://doi.org/10.1016/j.jtv.2018.05.001

    Article  Google Scholar 

  12. David OP, Sierra-Sosa D, Zapirain BG (2017) Pressure ulcer image segmentation technique through synthetic frequencies generation and contrast variation using toroidal geometry. Biomed Eng Online 16:1–19. https://doi.org/10.1186/s12938-016-0298-3

    Article  Google Scholar 

  13. Leachtenauer J, Kell S, Turner B et al (2006) A non-contact imaging-based approach to detecting stage pressure ulcers. Annu Int Conf IEEE Eng Med Biol Proc. https://doi.org/10.1109/IEMBS.2006.259513

    Article  Google Scholar 

  14. Guadagnin R, De Neves RS, Santana LA, Guilhem DB (2014) An image mining based approach to detect pressure ulcer stage. Pattern Recognit Image Anal 24:292–296. https://doi.org/10.1134/S1054661814020084

    Article  Google Scholar 

  15. Hansen GL, Sparrow EM, Kokate JY et al (1997) Wound status evaluation using color image processing. IEEE Trans Med Imaging 16:78–86. https://doi.org/10.1109/42.552057

    Article  Google Scholar 

  16. Mankar NB (2013) Comparision of different ımaging techniques used for chronic wounds. Int J Res Eng Technol 02:68–70. https://doi.org/10.15623/ijret.2013.0207009

    Article  Google Scholar 

  17. Kermany DS, Goldbaum M, Cai W et al (2018) Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172:1122–1131

    Article  Google Scholar 

  18. Zahia S, Sierra-Sosa D, Garcia-Zapirain B, Elmaghraby A (2018) Tissue classification and segmentation of pressure injuries using convolutional neural networks. Comput Methods Programs Biomed 159:51–58

    Article  Google Scholar 

  19. Garcia-Zapirain B, Shalaby A, El-Baz A, Elmaghraby A (2017) Automated framework for accurate segmentation of pressure ulcer images. Comput Biol Med 90:137–145

    Article  Google Scholar 

  20. Silva RHL, Machado AMC (2021) Automatic measurement of pressure ulcers using support vector machines and grabcut. Comput Methods Progr Biomed. https://doi.org/10.1016/j.cmpb.2020.105867

    Article  Google Scholar 

  21. Elmogy M, Garcia-Zapirain B, Burns C et al (2018) Tissues classification for pressure ulcer images based on 3D convolutional neural network. Proc Int Conf Image Process ICIP. https://doi.org/10.1109/ICIP.2018.8451119

    Article  Google Scholar 

  22. Zahia S, Garcia-Zapirain B, Elmaghraby A (2020) Integrating 3D model representation for an accurate non-invasive assessment of pressure injuries with deep learning. Sensors (Switzerland) 20:1–15. https://doi.org/10.3390/s20102933

    Article  Google Scholar 

  23. Chakraborty C (2019) Computational approach for chronic wound tissue characterization. Inform Med Unlocked 17:100162

    Article  Google Scholar 

  24. Yilmaz B, Atagun E, Demircan FO, Yucedag I (2021) Classification of pressure ulcer images with logistic regression. Int Conf Innov Intell Syst Appl INISTA 2021 Proc. https://doi.org/10.1109/INISTA52262.2021.9548585

    Article  Google Scholar 

  25. Kosmopoulos DI, Tzevelekou FL (2007) Automated pressure ulcer lesion diagnosis for telemedicine systems. IEEE Eng Med Biol Mag 26:18–22

    Article  Google Scholar 

  26. Marijanović D, Filko D (2020) A systematic overview of recent methods for non-contact chronic wound analysis. Appl Sci 10:1–28. https://doi.org/10.3390/app10217613

    Article  Google Scholar 

  27. Bedo MVN, Santos LFD, Oliveira WD et al (2015) Color and texture influence on computer-aided diagnosis of dermatological ulcers. Proc IEEE Symp Comput Med Syst. https://doi.org/10.1109/CBMS.2015.33

    Article  Google Scholar 

  28. Mukherjee R, Manohar DD, Das DK et al (2014) Automated tissue classification framework for reproducible chronic wound assessment. Biomed Res Int. https://doi.org/10.1155/2014/851582

    Article  Google Scholar 

  29. Chakraborty C, Gupta B, Ghosh SK et al (2016) Telemedicine supported chronic wound tissue prediction using classification approaches. J Med Syst 40:68

    Article  Google Scholar 

  30. Veredas F, Mesa H, Morente L (2009) Binary tissue classification on wound images with neural networks and bayesian classifiers. IEEE Trans Med Imaging 29:410–427

    Article  Google Scholar 

  31. Chakraborty C, Gupta B, Ghosh SK (2015) Chronic wound tissue characterization under telemedicine framework. In: 2015 17th ınternational conference on E-health networking, application & services (HealthCom). pp 569–573

  32. Wannous H, Lucas Y, Treuillet S (2010) Enhanced assessment of the wound-healing process by accurate multiview tissue classification. IEEE Trans Med Imaging 30:315–326

    Article  Google Scholar 

  33. Veredas FJ, Luque-Baena RM, Martin-Santos FJ et al (2015) Wound image evaluation with machine learning. Neurocomputing 164:112–122

    Article  Google Scholar 

  34. Wannous H, Treuillet S, Lucas Y (2010) Robust tissue classification for reproducible wound assessment in telemedicine environments. J Electron Imaging 19:23002

    Article  Google Scholar 

  35. Mesa H, Veredas FJ, Morente L (2008) A hybrid approach for tissue recognition on wound images. In: 2008 eighth ınternational conference on hybrid ıntelligent systems. pp 120–125

  36. García-Zapirain B, Elmogy M, El-Baz A, Elmaghraby AS (2018) Classification of pressure ulcer tissues with 3D convolutional neural network. Med Biol Eng Comput 56:2245–2258. https://doi.org/10.1007/s11517-018-1835-y

    Article  Google Scholar 

  37. Ahmad Fauzi MF, Khansa I, Catignani K et al (2015) Computerized segmentation and measurement of chronic wound images. Comput Biol Med 60:74–85. https://doi.org/10.1016/j.compbiomed.2015.02.015

    Article  Google Scholar 

  38. Shenoy VN, Foster E, Aalami L et al (2019) Deepwound: automated postoperative wound assessment and surgical site surveillance through convolutional neural networks. Proc 2018 IEEE Int Conf Bioinform Biomed BIBM 2018. https://doi.org/10.1109/BIBM.2018.8621130

    Article  Google Scholar 

  39. Nejati H, Ghazijahani HA, Abdollahzadeh M et al (2018) Fine-grained wound tissue analysis using deep neural network. ICASSP IEEE Int Conf Acoust Speech Signal Process Proc. https://doi.org/10.1109/ICASSP.2018.8461927

    Article  Google Scholar 

  40. V. Godeiro, J. S. Neto, B. Carvalho, B. Santana, J. Ferraz and R. Gama, (2018) Chronic wound tıssue classıfıcatıon usıng convolutıonal networks and color space reduction. IEEE 28th ınternational workshop on machine learning for signal processing (MLSP), pp 1–6, https://doi.org/10.1109/MLSP.2018.8517026.

  41. Pholberdee N, Pathompatai C, Taeprasartsit P (2018) Study of chronic wound ımage segmentation: ımpact of tissue type and color data augmentation. In: Proceeding 2018 15th Int Jt Conf Comput Sci Softw Eng JCSSE 2018, pp 1–6, https://doi.org/10.1109/JCSSE.2018.8457392

  42. Haesler E (2019) European Pressure ulcer advisory panel, national pressure ınjury advisory panel, and pan pacific ınjury alliance. In: Prev Treat Press ulcers/injuries Clin Pract Guidel Int Guidel EPUAP/NPIAP/PPPIA

  43. Ren S, He K, Girshick R, Sun J (2016) Faster R-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137–1149

    Article  Google Scholar 

  44. Barone AVM, Haddow B, Germann U, Sennrich R (2017) Regularization techniques for fine-tuning in neural machine translation. arXiv Prepr arXiv:1707.09920

Download references

Funding

The study was reviewed and approved by the ethics committee of Firat University, Turkey. The work reported on in this paper was substantially performed using computing resources from Big Data and Artificial Intelligence Laboratory (BVYZLab) at Firat University.

Author information

Authors and Affiliations

  1. Department of Computer Engineering, Firat University, Elazig, Turkey

    Betul Ay & Galip Aydin

  2. Department of Mechatronics Engineering, Firat University, Elazig, Turkey

    Beyda Tasar

  3. Department of Dermatology, Erzurum Regional Training and Research Hospital, Erzurum, Turkey

    Zeynep Utlu

  4. Department of Internal Medical Sciences, Firat University Hospital, Elazig, Turkey

    Kevser Ay

Authors
  1. Betul Ay
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Beyda Tasar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zeynep Utlu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kevser Ay
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Galip Aydin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Betul Ay.

Ethics declarations

Conflict of interest

All authors declare that they have no conflict of interest.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ay, B., Tasar, B., Utlu, Z. et al. Deep transfer learning-based visual classification of pressure injuries stages. Neural Comput & Applic 34, 16157–16168 (2022). https://doi.org/10.1007/s00521-022-07274-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07274-6

Keywords

Search

Navigation