Skip to main content

Software-Based Method for Automated Segmentation and Measurement of Wounds on Photographs Using Mask R-CNN: a Validation Study

Abstract

In clinical routine, wound documentation is one of the most important contributing factors to treating patients with acute or chronic wounds. The wound documentation process is currently very time-consuming, often examiner-dependent, and therefore imprecise. This study aimed to validate a software-based method for automated segmentation and measurement of wounds on photographic images using the Mask R-CNN (Region-based Convolutional Neural Network). During the validation, five medical experts manually segmented an independent dataset with 35 wound photographs at two different points in time with an interval of 1 month. Simultaneously, the dataset was automatically segmented using the Mask R-CNN. Afterwards, the segmentation results were compared, and intra- and inter-rater analyses performed. In the statistical evaluation, an analysis of variance (ANOVA) was carried out and dice coefficients were calculated. The ANOVA showed no statistically significant differences throughout all raters and the network in the first segmentation round (F = 1.424 and p > 0.228) and the second segmentation round (F = 0.9969 and p > 0.411). The repeated measure analysis demonstrated no statistically significant differences in the segmentation quality of the medical experts over time (F = 6.05 and p > 0.09). However, a certain intra-rater variability was apparent, whereas the Mask R-CNN consistently provided identical segmentations regardless of the point in time. Using the software-based method for segmentation and measurement of wounds on photographs can accelerate the documentation process and improve the consistency of measured values while maintaining quality and precision.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

References

  1. 1.

    Posnett J, Gottrup F, Lundgren H, Saal G: The resource impact of wounds on health-care providers in Europe. Journal of wound care 18:154-161, 2009

    CAS  Article  Google Scholar 

  2. 2.

    Guest JF, Vowden K, Vowden P: The health economic burden that acute and chronic wounds impose on an average clinical commissioning group/health board in the UK. Journal of wound care 26:292-303, 2017

    CAS  Article  Google Scholar 

  3. 3.

    Constantine RS, Bills JD, Lavery LA, Davis KE: Validation of a laser-assisted wound measurement device in a wound healing model. International wound journal 13:614-618, 2016

    Article  Google Scholar 

  4. 4.

    Voegeli D, et al.: Skin breakdown: the silent epidemic, 2007

  5. 5.

    Lindholm C, Searle R: Wound management for the 21st century: combining effectiveness and efficiency. International wound journal 13 Suppl 2:5-15, 2016

    Article  Google Scholar 

  6. 6.

    Flanagan M: Wound measurement: can it help us to monitor progression to healing? Journal of wound care 12:189-194, 2003

    CAS  Article  Google Scholar 

  7. 7.

    Russell L: The importance of wound documentation and classification. British journal of nursing (Mark Allen Publishing) 8:1342–1343, 1346, 1348 passim, 1999

  8. 8.

    Gartlan J, et al.: An audit of the adequacy of acute wound care documentation of surgical inpatients. Journal of clinical nursing 19:2207-2214, 2010

    Article  Google Scholar 

  9. 9.

    Khoo R, Jansen S: The evolving field of wound measurement techniques: a literature review. Wounds : a compendium of clinical research and practice 28:175-181, 2016

    Google Scholar 

  10. 10.

    Paul DW, et al.: Noninvasive imaging technologies for cutaneous wound assessment: a review. Wound repair and regeneration : official publication of the Wound Healing Society [and] the European Tissue Repair Society 23:149–162, 2015

  11. 11.

    Bishop CM: Pattern Recognition and Machine Learning: Springer, 2006

  12. 12.

    Esteva A, et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:115-118, 2017

    CAS  Article  Google Scholar 

  13. 13.

    Yamashita R, Nishio M, Do RKG, Togashi K: Convolutional neural networks: an overview and application in radiology. Insights into imaging 9:611-629, 2018

    Article  Google Scholar 

  14. 14.

    Sampaio WB, Diniz EM, Silva AC, de Paiva AC, Gattass M: Detection of masses in mammogram images using CNN, geostatistic functions and SVM. Computers in biology and medicine 41:653-664, 2011

    Article  Google Scholar 

  15. 15.

    Gao XW, Hui R, Tian Z: Classification of CT brain images based on deep learning networks. Computer methods and programs in biomedicine 138:49-56, 2017

    Article  Google Scholar 

  16. 16.

    Liu C, et al.: Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation, 2019

  17. 17.

    He K, Gkioxari G, Dollár P, Girshick R: Mask R-CNN. Proc. 2017 IEEE International Conference on Computer Vision (ICCV): City, 22–29 Oct. 2017 Year

  18. 18.

    Wang C, et al.: A unified framework for automatic wound segmentation and analysis with deep convolutional neural networks. Conference proceedings : Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE Engineering in Medicine and Biology Society Annual Conference 2015:2415-2418, 2015

    Google Scholar 

  19. 19.

    He K, Gkioxari G, Dollar P, Girshick R: Mask R-CNN. IEEE transactions on pattern analysis and machine intelligence, 2018

  20. 20.

    Pan SJ, Yang Q: A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22:1345-1359, 2010

    Article  Google Scholar 

  21. 21.

    Bengio Y: Deep Learning of Representations for Unsupervised and Transfer Learning, Proceedings of Machine Learning Research: PMLR, 2012

  22. 22.

    Dai J, He K, Sun J: Instance-aware semantic segmentation via multi-task network cascades, 2016

  23. 23.

    Li Y, Qi H, Dai J, Ji X, Wei Y: Fully convolutional instance-aware semantic segmentation. Proc. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR): City, 21–26 July 2017 Year

  24. 24.

    Lin T-Y, et al.: Microsoft COCO: Common Objects in Context. Proc. Computer Vision – ECCV 2014: Cham, 2014

  25. 25.

    Association AER, Association AP, Novick MR, Education NCoMi, Educational CtDSf, Testing P: Standards for Educational and Psychological Testing: American Psychological Association, 1985

  26. 26.

    Dutta A, Zisserman A: The VGG Image Annotator (VIA), 2019

  27. 27.

    Sørensen TJ: A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on Danish Commons: I kommission hos E. Munksgaard, 1948

  28. 28.

    Dice LR: Measures of the amount of ecologic association between species. Ecology 26:297-302, 1945

    Article  Google Scholar 

  29. 29.

    Keast DH, Bowering CK, Evans AW, Mackean GL, Burrows C, D'Souza L: MEASURE: A proposed assessment framework for developing best practice recommendations for wound assessment. Wound repair and regeneration : official publication of the Wound Healing Society [and] the European Tissue Repair Society 12:S1–17, 2004

  30. 30.

    Bryant JL, Brooks TL, Schmidt B, Mostow EN: Reliability of wound measuring techniques in an outpatient wound center. Ostomy/wound management 47:44-51, 2001

    CAS  PubMed  Google Scholar 

  31. 31.

    Jorgensen LB, Sorensen JA, Jemec GB, Yderstraede KB: Methods to assess area and volume of wounds - a systematic review. International wound journal 13:540-553, 2016

    Article  Google Scholar 

  32. 32.

    Seat A, Seat C: A prospective trial of interrater and intrarater reliability of wound measurement using a smartphone app versus the traditional ruler. Wounds : a compendium of clinical research and practice 29:E73-E77, 2017

    Google Scholar 

  33. 33.

    Rogers LC, Bevilacqua NJ, Armstrong DG, Andros G: Digital planimetry results in more accurate wound measurements: a comparison to standard ruler measurements. J Diabetes Sci Technol 4:799-802, 2010

    Article  Google Scholar 

  34. 34.

    Shetty R, Sreekar H, Lamba S, Gupta AK: A novel and accurate technique of photographic wound measurement. Indian J Plast Surg 45:425-429, 2012

    Article  Google Scholar 

  35. 35.

    Mayrovitz HN, Soontupe LB: Wound areas by computerized planimetry of digital images: accuracy and reliability. Advances in skin & wound care 22:222-229, 2009

    Article  Google Scholar 

  36. 36.

    Sugama J, Matsui Y, Sanada H, Konya C, Okuwa M, Kitagawa A: A study of the efficiency and convenience of an advanced portable Wound Measurement System (VISITRAK). Journal of clinical nursing 16:1265-1269, 2007

    Article  Google Scholar 

  37. 37.

    Chang AC, Dearman B, Greenwood JE: A comparison of wound area measurement techniques: visitrak versus photography. Eplasty 11:e18, 2011

  38. 38.

    Darwin ES, Jaller JA, Hirt PA, Kirsner RS: Comparison of 3-dimensional wound measurement with laser-assisted and hand measurements: a retrospective chart review. Wound management & prevention 65:36-41, 2019

    Article  Google Scholar 

  39. 39.

    Kolesnik M, Fexa A: Segmentation of wounds in the combined color-texture feature space. Proc SPIE 5370, 2004

  40. 40.

    Au Y, Beland B, Anderson JAE, Sasseville D, Wang SC: Time-saving comparison of wound measurement between the Ruler Method and the Swift Skin and Wound App. Journal of cutaneous medicine and surgery 23:226-228, 2019

    Article  Google Scholar 

  41. 41.

    Brehm A, Maus V, Khadhraoui E, Psychogios MN: Image review on mobile devices for suspected stroke patients: evaluation of the mRay software solution. PloS One 14:e0219051, 2019

  42. 42.

    Vetter SY, et al.: Tablets for image review and communication in daily routine of orthopedic surgeons-an evaluation study. Journal of digital imaging 31:74-83, 2018

    Article  Google Scholar 

  43. 43.

    Stember JN, et al.: Eye tracking for deep learning segmentation using convolutional neural networks. Journal of digital imaging 32:597-604, 2019

    CAS  Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Sven Yves Vetter.

Ethics declarations

Ethical Approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.

Informed Consent

As only existing anonymized image data was used, no informed consent was required for the present study.

Conflict of Interest

The authors declare the following potential conflicts of interest concerning the research, authorship, and publication of this article: The BG Trauma Center Ludwigshafen and mbits imaging GmbH (Heidelberg, Germany) cooperate in the field of medical digitalization. This cooperation influenced neither the outcome of the study nor the manuscript. Michael Müller and Hannah Syrek are employees of mbits imaging GmbH. They provided us with the software prototypes for wound segmentation and supported us in the use of these.

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

Verify currency and authenticity via CrossMark

Cite this article

Privalov, M., Beisemann, N., Barbari, J.E. et al. Software-Based Method for Automated Segmentation and Measurement of Wounds on Photographs Using Mask R-CNN: a Validation Study. J Digit Imaging 34, 788–797 (2021). https://doi.org/10.1007/s10278-021-00490-x

Download citation

Keywords

  • Medical image processing
  • Convolutional neural networks
  • Wound segmentation
  • Wound measurement