Precise Segmentation and Classification of Epithelial Rete-Pegs Signature in Assessing Lower Limb Wound Healing Progression
- 44 Downloads
Automated identification of healing progression in lower limb wounds is an important clinical challenge since such wounds fail to heal in an orderly and timely manner. Selection of suitable target features and employment of appropriate analytical tool are critical for the precise monitoring of the healing progression through automated diagnostic method. The present study aims at automated detection of healing trend based on characteristics of epithelial rete pegs, which is considered as an important parameter for monitoring and hence healing progression of epithelial maturation. To this aim, the applicability of various segmentation methods namely, watershed, marker-controlled watershed, k-means clustering and active contour method and comprehensive characterization of rete-pegs are studied and compared. Among them active contour provided better performance in terms of non-linear objective assessments including performance metrics like-peak-signal-to-noise-ratio, processing speed and Mean Square Error. Further, support vector machine is trained for classification of the rete-peg features at different time points of clinically diagnosed non-healing wounds treated with a specific protocol. Kappa scoring tests inter-rater agreement between applied segmentation protocol and ground truth images. The overall accuracy of the system has been found to be 95%. It is thus concluded that with the aid of the proposed segmentation and classification method an automated detection system can be developed for precise monitoring of lower limb wound healing progression.
KeywordsComputer-aided diagnosis Wound healing Epithelial rete pegs Active contour snake model Kappa scoring SVM classifier Non-linear objective assessment
Authors would like to acknowledge Mr. Westley Hayes for his valuable suggestions.
Compliance with Ethical Standards
Conflict of interest
The authors declared that they have no conflict of interest.
- 5.Loizou, P., Kasparis, T., Mitsi, O., & Polyviou, M. (2012). Evaluation of wound healing process based on texture analysis. In Proceedings of IEEE international conference on bioinformatics and bioengineering (pp. 709–714).Google Scholar
- 6.Engstorm, O. (2015). Altering the size of skin micrografts affects the healing quality of cutaneous wounds. Degree Project, Uppsala University.Google Scholar
- 8.Seyhan, T. (2011). Split-thickness skin grafts. In M. Spear (Ed.), Skin grafts—Indications, applications and current research. London: InTechOpen. ISBN 978-953-307-509-9.Google Scholar
- 9.Polito, D. B., Sato, S., Ritman, G., Mota, L. F., & Caffesse, R. G. (2001). Computer assisted image analysis methods for evaluation of periodontal wound healing. The Brazilian Dental Journal, 12(3), 167–172.Google Scholar
- 10.Song, B., & Sacan, A. (2012). Automated wound identification system based on image segmentation and artificial neural networks. In IEEE international conference on bioinformatics and biomedicines (pp. 619–622).Google Scholar
- 13.Wang, L., Li, C., Sun, Q., Xia, D., & Kao C. Y. (2008). Brain MRI image segmentation using local and global intensity fitting active contours/surfaces. In Proceedings of medical image computing and computer aided intervention. Lecture notes in computer science (Vol. 5241, Part I, pp. 384–392). Berlin: Springer.Google Scholar
- 14.Jadhav, A. S., Banerjee, S., Dutta, P. K., et al. (2006). Quantitative analysis of histopathological features of precancerous lesion and condition using image processing technique. In IEEE international symposium on computer-based medical systems (pp. 231–236).Google Scholar
- 16.Wannous, H., Treuillet, S., & Lucas, Y. (2007). Supervised tissue classification from color images for a complete wound assessment tool. In Proceedings of the 29th annual international conference of IEEE-EMBS, Engineering in Medicine and Biology Society (EMBC’07), pp. 6031–6034, August 2007.Google Scholar
- 17.Nayak, R., Kumar, P., & Galigekere, R. R. (2009). Towards a comprehensive assessment of wound-composition using color-image processing. In Proceeding of the IEEE international conference on image processing (ICIP’09) (pp. 4185–4188). https://doi.org/10.1109/icip.2009.5414527.
- 20.Briskillal, C. D., & Kumar, K. M. (2014). Assessment and analysis on color image classification techniques of dermatological ulcers. International Journal of Advanced Research in Electronics and Communication Engineering (IJARECE), 3(11), 1440–1447.Google Scholar
- 21.Gonsalves, A., Machado, R., Michael, G., & Yadav, O. (2015). Comparative evaluation of thresholding and segmentation algorithms. International Journal of Computer Science and Information Technology (IJCSIT), 6(2), 1107–1110.Google Scholar
- 22.Wang, L., Pederson, P. C., et al. (2015). An automatic assessment system of diabetic foot ulcers based on wound area determination, color segmentation, and healing score evaluation. Journal of Diabetes Science and Technology, 10(2), 421–428. https://doi.org/10.1177/1932296815599004.CrossRefGoogle Scholar
- 24.Itoiz, M. E. (2002). FA Carranza (2002) The Gingiva. In M. G. Newman, H. H. Takei, & F. A. Carranza (Eds.), Carranza’s clinical periodontology (9th ed., pp. 204–228). Philadelphia, PA: W.B. Saunders Company.Google Scholar
- 27.Gonzalez, R. C., & Woods, R. E. (2013). Digital image processing (3rd ed.). Upper Saddle River, NJ: Pearson. ISBN 978-81-317-2695-2.Google Scholar
- 28.Jayaraman, S., Esakkirajan, S., & Veerakumar, T. (2009). Digital image processing (17th ed.). New Delhi: McGraw Hill Education. ISBN 978-0-07-014479-8.Google Scholar
- 29.Kaur, A., & Verma, A. (2013). The marker-based watershed segmentation—A review. International Journal of Engineering and Innovative Technology (IJEIT), 3(3), 171–174.Google Scholar
- 30.Sonka, M., Hlavac, V., & Boyle, R. (2014). Image processing and analysis and machine vision (3rd ed.). Stamford, CT: CENGAGE Learning. ISBN 978-81-315-1883.Google Scholar
- 34.Yadav, S. K., Kumar, R., & Dubey, P. K. (2013). Implementation and comparisons of different segmentation algorithm based on entropy and energy. International Journal of Scientific Research Engineering & Technology (IJSRET), 2(5), 279–285.Google Scholar
- 36.Kaushik, P., & Sharma, Y. (2012). Comparison of different image enhancement techniques based upon PSNR & MSE. International Journal of Applied Engineering Research, 7(11), 2010–2014.Google Scholar
- 37.Huestis, S. (2014). Sensitivity and specificity. In F. R. Volkmar (Ed.), Encyclopedia of autism spectral disorder (pp. 2761–2762). Cham: Springer.Google Scholar
- 38.Pandya, K., Bulsari, S., & Sinha, S. (2014). SPSS in simple steps. New Delhi: KOGENT Learning Solutions. ISBN 978-93-5004-251-9.Google Scholar
- 40.Unnikrishnan, R., Pantofaru, C., & Hebert, M. (2005). A measure for objective evaluation of image segmentation algorithms. In Workshop on Empirical evaluation methods in computer vision and pattern recognition (CVPR ‘05), June 2005.Google Scholar
- 41.Pal, R., Yang, J., Ortiz, D., Qiu, S., Resto, V., McCammon, S., et al. (2015). In-vivo nonlinear optical microscopy (NLOM) of epithelial-connective tissue interface (ECTI) reveals quantitative measures of neoplasia in hamster oral mucosa. PLoS ONE. https://doi.org/10.1371/journal.pone.0116754.Google Scholar
- 45.Pal, R., Shilagard, T., Yang, J., Villarreal, P., et al. (2016). Remodeling of the epithelial-connective tissue interface (ECTI) in oral epithelial dysplasia as visualized by noninvasive 3D imaging. Cancer Research, 76(16), 4637–4647. https://doi.org/10.1158/0008-5472.CAN-16-0252.CrossRefGoogle Scholar
- 47.Barui, A., Banerjee, P., Das, R. K., Basu, S. K., Dhara, S., & Chatterjee, J. (2011). Immunohistochemical evaluation of p63, E-cadherin, collagen I and III expression in lower limb wound healing under honey. Evidence-Based Complementary and Alternative Medicine. https://doi.org/10.1155/2011/239864.Google Scholar
- 50.Thampi, S. M., Bandyopadhyay, S., Krishnan, S., Li, K.-C., Mosin, S., & Maode, M. (2015). Advances in signal processing and intelligent recognition systems. In Proceedings of second international symposium on signal processing and intelligent recognition systems (SIRS-2015), 16–19 December 2015, Trivandrum, India.Google Scholar
- 51.Barui, A., Banerjee, P., Das, R. K., Dhara, S., & Chatterjee, J. (2010). Correlating optical biopsy with histopathology of wounds under topical intervention with honey. In IEEE International conference on systems in medicine and biology (ICSMB). https://doi.org/10.1109/ICSMB.2010.5735373.