Skip to main content
SpringerLink
Log in

Automatic Skin Lesion Segmentation—A Novel Approach of Lesion Filling through Pixel Path

  • APPLIED PROBLEMS
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

Lesion segmentation is a vital step in a melanoma recognition system. Many algorithms were developed for the efficient skin lesion segmentation. Most of them fails to realize a perfect segmentation. This paper proposes a novel, fully automatic system, for the lesion segmentation in dermatograms. The proposed approach executes in two steps. Selection of root seed is the first step. All the lesion pixels in the dermatogram are identified during the second step. Traversal through a predefined lesion pixel path ensures the reachability of all lesion pixels irrespective of the possible lesion discontinuity. The proposed algorithm is tested with two publically available dataset, PH2 and images of ISBI2016 challenge. Out of the six evaluation parameters, the proposed method shows the best values for specificity, accuracy, Hammuode distance and XOR. This confirms the merit of the proposal with respect to existing popular methods.

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.

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

Similar content being viewed by others

REFERENCES

  1. Cancer.org. Key Statistics for Melanoma Skin Cancer (2018). https://www.cancer.org/cancer/melanoma-skin-cancer/about/key-statistics.html. Accessed September 14, 2018.

  2. O. Abuzaghleh, B. D. Barkana, and M. Faezipour, “Noninvasive real-time automated skin lesion analysis system for melanoma early detection and prevention,” IEEE J. Trans. Eng. Health Med. 3, 2900310 (2015). https://doi.org/10.1109/JTEHM.2015.2419612

    Article  Google Scholar 

  3. J. Glaister, A. Wong, and D. Clausi, “Segmentation of skin lesions from digital images using joint statistical texture distinctiveness,” IEEE Trans. Biomed. Eng. 61 (4), 1220–1230 (2014).

    Article  Google Scholar 

  4. M. Silveira et al., “Comparison of segmentation methods for melanoma diagnosis in dermoscopy images,” IEEE J. Sel. Top. Signal Process. 3, 35–45 (2009).

    Article  Google Scholar 

  5. M. E. Celebi, G. Schaefer, H. Iyatomi, and W. V. Stoecker., “Lesion border detection in dermoscopy images,” Comput. Med. Imaging Graphics 33, 148–153 (2009).

    Article  Google Scholar 

  6. O. B. Akinrinade, P. Adewale Owolawi, C. Tu, and T. Mapayi, “Graph-cuts technique for melanoma segmentation over different color spaces,” in 2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC) (2018), pp. 1–5. https://doi.org/10.1109/ICONIC.2018.8601269

  7. F. Melgani, “Robust image binarization with ensembles of thresholding algorithms,” J. Electron. Imaging 15 (2), 023010 (2008). https://doi.org/10.1117/1.2194767

    Article  Google Scholar 

  8. M. Emre Celebi et al., “Border detection in dermoscopy images using statistical region merging,” Skin Res. Technol. 14, 347–353 (2008).

    Article  Google Scholar 

  9. J. Wang, H. Jiang, Z. Yuan, M.-M. Cheng, X. Hu, and N. Zheng, “Salient object detection: A discriminative regional feature integration approach,” Int. J. Comput. Vis. 123 (2), 251–268 (2017).

    Article  Google Scholar 

  10. M. Jahanifar, N. Zamani Tajeddin, B. Mohammadzadeh Asl, and A. Gooya, “Supervised saliency map driven segmentation of lesions in dermoscopic images,” IEEE J. Biomed. Health Inf. 23 (2), 509–518 (2019). https://doi.org/10.1109/JBHI.2018.2839647

    Article  Google Scholar 

  11. M. Attia, M. Hossny, S. Nahavandi, and A. Yazdabadi, “Skin melanoma segmentation using recurrent and convolutional neural networks,” in 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) (Melbourne, 2017), pp. 292–296. https://doi.org/10.1109/ISBI.2017.7950522

  12. L. Yu, H. Chen, Q. Dou, J. Qin, and P. Heng, “Automated melanoma recognition in dermoscopy images via very deep residual networks,” IEEE Trans. Med. Imaging 36 (4), 994–1004 (2017). https://doi.org/10.1109/TMI.2016.2642839

    Article  Google Scholar 

  13. L. Bi, J. Kim, E. Ahn, D. Feng, and M. Fulham, “Automatic melanoma detection via multi-scale lesion-biased representation and joint reverse classification,” in 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI) (Prague, 2016), pp. 1055–1058. https://doi.org/10.1109/ISBI.2016.7493447

  14. S. Pathan, K. Prabhu, and P. Siddalingaswamy, “Hair detection and lesion segmentation in dermoscopic images using domain knowledge,” Med. Biol. Eng. Comput. 56 (11), 2051–2065 (2018). https://doi.org/10.1007/s11517-018-1837-9

    Article  Google Scholar 

  15. H. Fan, F. Xie, Y. Li, et al., “Automatic segmentation of dermoscopy images using saliency combined with Otsu threshold,” Comput. Biol. Med. 85, 75–85 (2017). https://doi.org/10.1016/j.compbiomed.2017.03.025

    Article  Google Scholar 

  16. F. Riaz, H. Farhan, A. Hassan, M. Javed, and M. Coimbra, “Detecting melanoma in dermoscopy images using scale adaptive local binary patterns,” in 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2014) (2014), pp. 6758–6761. https://doi.org/10.1109/EMBC.2014.6945179

  17. M. Khan et al., “An implementation of normal distribution based segmentation and entropy controlled features selection for skin lesion detection and classification,” BMC Cancer 18 (1), (2018). https://doi.org/10.1186/s12885-018-4465-8

  18. O. B. Akinrinade, P. Adewale Owolawi, C. Tu, and T. Mapayi, “Graph-cuts technique for melanoma segmentation over different color spaces,” in 2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC) (Plaine Magnien, 2018), pp. 1–5. https://doi.org/10.1109/ICONIC.2018.8601269

  19. F. Riaz, S. Naeem, R. Nawaz, and M. Coimbra, “Active contours based segmentation and lesion periphery analysis for characterization of skin lesions in dermoscopy images,” IEEE J. Biomed. Health Inf. 23 (2), 489–500 (2019). https://doi.org/10.1109/JBHI.2018.2832455

    Article  Google Scholar 

  20. T. Mendonca, P. M. Ferreira, J. S. Marques, A. R. Marcal, and J. Rozeira, “Ph2—a dermoscopic image database for research and benchmarking,” Int. Conf. IEEE Eng. Med. Biol. Soc. 2013, 5437–5440 (2013). http://www.fc.up.pt/addi/ph2.

  21. D. Gutman et al., “Skin lesion analysis toward melanoma detection: A challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)” (2016). arXiv:1605.01397.

  22. W. R. Crum et al., “Generalized overlap measures for evaluation and validation in medical image analysis,” IEEE Trans. Med. Imaging 25, 1451–1461 (2006).

    Article  Google Scholar 

  23. A. Hammoude, “Computer-assisted endocardial border identification from a sequence of two-dimensional echocardiographic images,” Thesis (Comput. Sci. Dept., Univ. Wash., 1988).

Download references

Author information

Authors and Affiliations

  1. School of Computer Sciences, Mahathma Gandhi University, 686560, Kottayam, Kerala, India

    P. Nikesh

  2. Department of Data Science, Christ (Deemed to be University), Lavasa Campus, 412112, Pune, Maharashtra, India

    G. Raju

Authors
  1. P. Nikesh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. G. Raju
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to P. Nikesh or G. Raju.

Ethics declarations

Conflict of interest. The authors declare that they have no conflict of interest.

Ethical approval. This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Nikesh P. received his B Tech in Computer Science and Engineering (2009) from the Kannur university in kerala and M Tech in Computer Cognition Technology (2012) from University of Mysore. He is currently an assistant professor in the Computer Science and Engineering Department at Government Engineering College Wayanad. His research interests include artificial intelligence, image processing and video processing.

Dr. Raju G. is currently working as Professor in the Department of Data Science, Christ (Deemed to be University), Lavasa, Pune, India. He obtained his masters as well as doctoral degrees from University of Kerala, India. His area of research includes Image Processing, Computer Vision, Machine Learning and Data Analytics. Prior to joining Christ, he worked in Kannur University, Kerala, Government Colleges, Kerala and Waljat Colleges, Sultanate of Oman. He successfully guided eighteen Ph. D. students and also published more than hundred research papers.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Nikesh, P., Raju, G. Automatic Skin Lesion Segmentation—A Novel Approach of Lesion Filling through Pixel Path. Pattern Recognit. Image Anal. 30, 815–826 (2020). https://doi.org/10.1134/S1054661820040215

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661820040215

Keywords:

Search

Navigation