Preview

Proceedings of the National Academy of Sciences of Belarus. Physical-technical series

Advanced search

CONTENT-BASE IMAGE RETRIEVAL AS A METHOD FOR COMPUTER-ASSISTED DIAGNOSIS OF MELANOMA BASED ON DERMOSCOPIC IMAGES

Abstract

A method for computer-aided diagnosis of skin lesions based on image retrieval scheme is proposed. The suggested method is rather simple, reliable and robust. The results of the tests carried out on a publically available image dataset suggest that the performance of the method proposed is comparable with one of a rather complicated conventional method of melanoma diagnosis. The best performance is achieved when combining both methods together.

 

About the Authors

V. A. Liauchuk
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus


V. A. Kovalev
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus


V. V. Barkaline
Belarusian National Technical University
Belarus


U. E. Lazouski
Belarusian National Technical University
Belarus


References

1. Siegel, R. Cancer statistics, 2012 / R. Siegel, D. Naishadham, A. Jemal // CA: Cancer Journal for Clinicians. – 2012. – Vol. 62(1). – P. 10–29.

2. Vestergaard, M. Automated diagnostic instruments for cutaneous melanoma / M. Vestergaard, S. Menzies // Seminars in Cutaneous Medicine and Surgery. – 2008. – Vol. 27(1). – P. 32–36.

3. Data mining with big data / W. Xindong [et al.] // Knowledge and Data Engineering, IEEE Transactions. – 2014. – Vol. 26(1). – P. 97–107.

4. A dermoscopic image database for research and benchmarking / T. Mendonca [et al.] // Proc. of the 35th International Conference of the IEEE Engineering in Medicine and Biology Society. – Japan, 2013. – P. 5437–5440.

5. Barata, C. Detecting the pigment network in dermoscopy images: a directional approach / C. Barata, J. S. Marques, J. Rozeira // Conf Proc IEEE Eng Med Biol Soc. – 2011. – P. 5120–5122.

6. Pigment Network Detection and Analysis / M. Sadeghi [et al.] // Computer Vision Techniques for the Diagnosis of Skin Cancer. – Jan 2014. – P. 1–22

7. Detection and analysis of irregular streaks in dermoscopic images of skin lesions / M. Sadeghi [et al.] // IEEE Transaction on Medical Imaging. – 2013. – Vol 32. – P. 849–61

8. Kovalev, V. Color Co-occurence Descriptors for Querying-by-Example / V. Kovalev, S. Volmer // Proceedings of the 1998 Conference on MultiMedia Modeling. – Switzerland, 1998. – P. 32–38.

9. BTBDB: Web-Services [Электронный ресурс]. – Режим доступа: http://imlab.grid.by/appmelanoma. – Дата досту- па: 04.03.2015.


Review

Views: 602


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 1561-8358 (Print)
ISSN 2524-244X (Online)