Abstract
In this article, we propose a new BSS approach for identifying skin diseases from RGB images that proceeds in two steps. We begin by separating the three main chromophores (oxyhemoglobin, deoxyhemoglobin and melanin) using Non-negative Matrix Factorization (NMF). For this purpose, we propose a special initialization of the solution matrices based on the sparsity of the chromophores, instead of initializing them with random matrices as is the case for basic versions of NMF. We then propose a new disease identification criterion that exploits the three contributions of each chromophore on the three spectral bands of our RGB dermatological image. To validate our approach, we used an open access database containing RGB images of melanoma and neavus. The results obtained showed good performance for our approach in terms of chromophore separation, compared to the most commonly used method in the literature, as well as disease identification compared to identification based on the most popular criterion.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Indeed, for example a biopsy is painful, costly and time-consuming, especially considering that it may need to be repeated for further examination.
- 2.
The goal of this transformation defined by the operator f(.) is to transform a matrix of dimensions \(n_x\times n_y\) into a row matrix of dimension \(1\times n_x\cdot n_y\), by assembling its columns one after the other.
- 3.
A signal is sparse if the majority of its elements are zero or very close to zero.
- 4.
According to the information provided in [21].
- 5.
The median corresponds to the value located in the middle of the data. It divides the data into two equal parts, such that 50% of the values are below the median and 50% are above it.
References
Abrard, F., Deville, Y.: A time-frequency blind signal separation method applicable to underdetermined mixtures of dependent sources. Signal Process. 85(7), 1389–1403 (2005)
Adam, A., Rivlin, E., Shimshoni, I.: Robust fragments-based tracking using the integral histogram. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), vol. 1, pp. 798–805. IEEE (2006)
Anderson, R.R., Parrish, J.A.: The optics of human skin. J. Investig. Dermatol. 77(1), 13–19 (1981)
Besse, P.: https://www.math.univ-toulouse.fr/$~$besse/Wikistat/pdf/st-m-explo-nmf.pdf. Accessed 28 Mar 2023
Boutsidis, C., Gallopoulos, E.: Svd based initialization: a head start for nonnegative matrix factorization. Pattern Recogn. 41(4), 1350–1362 (2008)
Comon, P., Jutten, C.: Handbook of Blind Source Separation: Independent component analysis and applications. Academic press (2010)
Févotte, C., Idier, J.: Algorithms for nonnegative matrix factorization with the \(\beta \)-divergence. Neural Comput. 23(9), 2421–2456 (2011)
Giotis, I., Molders, N., Land, S., Biehl, M., Jonkman, M.F., Petkov, N.: Med-node: a computer-assisted melanoma diagnosis system using non-dermoscopic images. Expert Syst. Appl. 42(19), 6578–6585 (2015)
Gong, H., Desvignes, M.: Hemoglobin and melanin quantification on skin images. In: International Conference Image Analysis and Recognition, pp. 198–205. Springer (2012)
Jacques, S.L.: https://omlc.org/~jacquess/library.html. Accessed 28 Mar 2023
Jacques, S.L., Samatham, R., Choudhury, N.: Rapid spectral analysis for spectral imaging. Biomed. Opt. Express 1(1), 157–164 (2010)
Koprowski, R.: Processing of hyperspectral medical images (2017)
Kuzmina, I., Diebele, I., Asare, L., Kempele, A., Abelite, A., Jakovels, D., Spigulis, J.: Multispectral imaging of pigmented and vascular cutaneous malformations: the influence of laser treatment. In: Laser Applications in Life Sciences, vol. 7376, pp. 144–149. SPIE (2010)
Kuzmina, I., et al.: Towards noncontact skin melanoma selection by multispectral imaging analysis. J. Biomed. Opt. 16(6), 060502 (2011)
Kuzmina, I., et al.: Skin chromophore mapping by smartphone rgb camera under spectral band and spectral line illumination. J. Biomed. Opt. 27(2), 026004 (2022)
Lee, D., Seung, H.: Algorithms for non-negative matrix factorization. Adv. Neural Inform. Process. Syst. 13, February 2001
Lee, D.H.: A new edge-based intra-field interpolation method for deinterlacing using locally adaptive-thresholded binary image. IEEE Trans. Consum. Electron. 54(1), 110–115 (2008)
Lihachev, A., Lihacova, I., Plorina, E.V., Lange, M., Derjabo, A., Spigulis, J.: Differentiation of seborrheic keratosis from basal cell carcinoma, nevi and melanoma by rgb autofluorescence imaging. Biomed. Opt. Express 9(4), 1852–1858 (2018)
Lihacova, I.: Evaluation of skin oncologic pathologies by multispectral imaging methods. Ph.D. thesis, July 2015. https://doi.org/10.13140/RG.2.2.12585.70242
Lin, C.J.: Projected gradient methods for nonnegative matrix factorization. Neural Comput. 19(10), 2756–2779 (2007)
LLC, L.: https://www.maxmax.com/nikon_d3x.htm. Accessed 28 Mar 2023
Naik, G.R., Wang, W., et al.: Blind source separation. Berlin: Springer 10, 978–3 (2014)
Ojima, N., Akazaki, S., Hori, K., Tsumura, N., Miyake, Y.: Application of image-based skin chromophore analysis to cosmetics. J. Imaging Sci. Technol. 48(3), 222–226 (2004)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)
Paatero, P., Tapper, U.: Positive matrix factorization: a non-negative factor model with optimal utilization of error estimates of data values. Environmetrics 5(2), 111–126 (1994)
Saknite, I., Jakovels, D., Spigulis, J.: Diffuse reflectance and fluorescence multispectral imaging system for assessment of skin. In: Biophotonics: Photonic Solutions for Better Health Care IV, vol. 9129, pp. 593–598. SPIE (2014)
Spigulis, J., Oshina, I.: 3\(\times \) 3 technique for rgb snapshot mapping of skin chromophores. In: Optics and the Brain, pp. JT3A-39. Optica Publishing Group (2015)
Spigulis, J., Oshina, I., Berzina, A., Bykov, A.: Smartphone snapshot mapping of skin chromophores under triple-wavelength laser illumination. J. Biomed. Opt. 22(9), 091508 (2017)
Van Gemert, M., Jacques, S.L., Sterenborg, H., Star, W.: Skin optics. IEEE Trans. Biomed. Eng. 36(12), 1146–1154 (1989)
Yamamoto, T., Takiwaki, H., Arase, S., Ohshima, H.: Derivation and clinical application of special imaging by means of digital cameras and image j freeware for quantification of erythema and pigmentation. Skin Res. Technol. 14(1), 26–34 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zokay, M., Saylani, H. (2024). A New Approach for Identifying Skin Diseases from Dermatological RGB Images Using Source Separation. In: Waiter, G., Lambrou, T., Leontidis, G., Oren, N., Morris, T., Gordon, S. (eds) Medical Image Understanding and Analysis. MIUA 2023. Lecture Notes in Computer Science, vol 14122. Springer, Cham. https://doi.org/10.1007/978-3-031-48593-0_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-48593-0_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48592-3
Online ISBN: 978-3-031-48593-0
eBook Packages: Computer ScienceComputer Science (R0)