(45-6) 12 * << * >> * Russian * English * Content * All Issues

Neural network classifier of hyperspectral images of skin pathologies
V.O. Vinokurov 1, I.A. Matveeva 1, Y.A. Khristoforova 1, O.O. Myakinin 1, I.A. Bratchenko 1, L.A. Bratchenko 1, A.A. Moryatov 2, S.G. Kozlov 2, A.S. Machikhin 3, I. Abdulhalim 4, V.P. Zakharov 1

1 Samara National Research University, 443086, Samara, Russia, Moskovskoye Shosse 34,
2 Samara State Medical University, 443079, Russia, Samara, st. Chapaevskaya, 89,

3 Scientific and Technological Center for Unique Instrumentation of the Russian Academy of Sciences,
117342, Russia, Moscow, st. Butlerova, 15,

4 Ben Gurion University of the Negev, Israel, 8410501, Negev, P.O. Box 653 Beer-Sheva

 PDF, 1350 kB

DOI: 10.18287/2412-6179-CO-832

Pages: 879-886.

Full text of article: Russian language.

Abstract:
The paper presents results of using a neural network classifier to analyze images of malignant skin lesions obtained using a hyper-spectral camera. Using a three-block neural network of VGG architecture, we conducted the classification of a set of two-dimensional images of melanoma, papilloma and basal cell carcinoma, obtained in the range of 530 – 570 and 600 – 606 nm, characterized by the highest absorption of melanin and hemoglobin. The sufficiency of the inclusion in the training set of two-dimensional images of a limited spectral range is analyzed. The results obtained show significant prospects of using neural network algorithms for processing hyperspectral data for the classification of skin pathologies. With a relatively small set of training data used in the study, the classification accuracy for the three types of neoplasms was as high as 96 %.

Keywords:
hyperspectral imaging, neural network classifier, melanin, hemoglobin, oncopathology, melanoma, basal cell carcinoma, VGG.

Citation:
Vinokurov VO, Matveeva IA, Khristoforova YA, Myakinin OO, Bratchenko IA, Bratchenko LA, Moryatov AA, Kozlov SG, Machikhin AS, Abdulhalim I, Zakharov VP. Neural network classifier of hyperspectral images of skin pathologies. Computer Optics 2021; 45(6): 879-886. DOI: 10.18287/2412-6179-CO-832.

Acknowledgements:
The reported study was funded by the Russian Foundation for Basic Research under project 19-52-06005 MNTI_a.

References:
  1. Tests for melanoma skin cancer. – 2016. – Source: <https://www.cancer.org/cancer/melanoma-skin-cancer/detection-diagnosis-staging/how-diagnosed.html>.
  2. Boyle P, Parkin D, eds. World cancer report 2008. Lyon: International Agency for Research on Cancer; 2008.
  3. Siegel R. Cancer statistics, 2012. CA Cancer J Clin 2012; 62: 10-29. DOI: 10.3322/caac.20138.
  4. Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019. CA Cancer J Clin 2019; 69: 8-10.
  5. Kaprin AD, Starinsky VV, Petrova GV. Malignant neoplasms in Russia in 2018 (morbidity and mortality) [In Russian]. Moscow: Moscow Scientific Research Institute PA Herzen; 2019.
  6. de Oliveira Santos M. Estimativa 2018: Incidência de câncer no Brasil. Revista Brasileira De Cancerologia 2018; 64(1): 119-120.
  7. de Almeida VL, Leitao A, Reina LdCB, et al. Câncer e agentes antineoplásicos ciclo-celular específicos e ciclo-celular nãoespecíficos que interagem com o dna: uma introdução. Quim Nova 2005; 28(1): 118-129.
  8. Carvalho GC, Alves F. Principais marcadores moleculares para os câncer de pele e mama. NBC-Periodico Cientıfico do Nucleo de Biociencias 2014; 4(07): 11-17.
  9. Figueiredo LC, Cordeiro LN, Arruda AP, et al. Cancer de pele: estudo dos principais marcadores molecularesdo melanoma cutaneo. Rev Bras de Cancerologia 2003; 49(3): 179-183.
  10. Bratchenko IA, Alonova MV, Myakinin OO, Moryatov AA, Kozlov SV, Zakharov VP. Hyperspectral visualization of skin pathologies in visible region. Computer Optics 2016; 40(2): 240-248. DOI: 10.18287/2412- 6179-2016-40-2-240-248.
  11. Clark WH, Reimer RR, Greene M, et al. Origin of familial malignant melanomas from heritable melanocytic lesions. The B-K mole syndrom. Arch Dermatol 1978; 114(5): 732-739.
  12. Elder DE, Leonardi J, Goldman J, et al. Displastic nevus syndrome. A pfenotypic assotiation of sporadic cutaneous melanoma. Cancer 1980; 46(8): 1787-1794.
  13. Romanova OA, Artemieva HG, Solochina MG. Case history of a large progressive dysplastic nevus with subsequent transformation into melanoma [In Russian]. Klinicheskaya Dermatologiya i Venerologiya 2018; 17: 34-37. DOI: 10.17116/klinderma201817234-37.
  14. Gross PE, Strasser-Weippl K, Lee-Bychkovsky BL, et al. Challenges to effective cancer control in China, India, and Russia. Lancet Oncol 2014; 15: 489-538. DOI: 10.1016/S1470- 2045(14)70029-4.
  15. Carli P, De Giorgi V, Soyer H, et al. Dermatoscopy in the diagnosis of pigmented skin lesions: a new semiology for the dermatologist. J Eur Acad Dermatol Venereol 2000; 14(5): 353-369.
  16. Jacques S.L, Ramella-Roman J.C, Lee K. Imaging skin pathology with polarized light. J of Biomed Opt 2002; 7(3): 329-340.
  17. Cicchi R, Cosci A, Rossari S. Combined fluorescence-Raman spectroscopic setup for the diagnosis of melanocytic lesions. J Biophotonics 2014; 7(1-2): 86-95. DOI: 10.1002/jbio.201200230.
  18. Khristoforova YA, Bratchenko IA, Myakinin OO, Artemyev DN, Moryatov AA, Orlov AE, Kozlov SV, Zakharov VP. Portable spectroscopic system for in vivo skin neoplasms diagnostics by Raman and autofluorescence analysis. J Biophotonics 2019; 12(4): e201800400. DOI: 10.1002/jbio.201800400.
  19. Zhao J, Zeng H, Kalia S, Lui H. Incorporating patient demographics into Raman spectroscopy algorithm improves in vivo skin cancer diagnostic specificity. Transl Biophotonics 2019; 1(1-2): e201900016. DOI: 10.1002/tbio.201900016.
  20. Kong K, Rowlands CJ, Varma S. Diagnosis of tumors during tissue-conserving surgery with integrated autofluorescence and Raman scattering microscopy. PNAS 2013; 110(38): 15189-15194. DOI: 10.1073/pnas.1311289110.
  21. Tuchin VV. Tissue optics and photonics: Light-tissue interaction. J of Biomedical Photonics & Eng 2015; 1(2): 98-134. DOI: 10.18287/jbpe-2015-1-2-98.
  22. Zherdeva LA, Bratchenko IA, Myakinin OO. In vivo hyperspectral imaging and differentiation of skin cancer. Proc SPIE 2016; 10024: 100244G. DOI: 10.1117/12.2246433.
  23. Bratchenko IA, Myakinin OO, Sherendak VP, et al. In vivo hyperspectral analysis of skin hemoglobin and melanin content for neoplasia detection. J of Biomedical Photonics & Eng 2018; 4(4): 040301. DOI: 10.18287/JBPE18.04.040301.
  24. Chang CI. Hyperspectral imaging: Techniques for spectral detection and classification. Boston: Springer; 2003. ISBN: 978-0-306-47483-5.
  25. Pan B, Shi Z, Xu X. R-VCANet: A new deep-learning-based hyperspectral image classification method. IEEE J Sel Top Appl Earth Obs Remote Sens 2017; 10(5): 1975-1986.
  26. Sherendak VP, Bratchenko IA, Myakinin OO, Volkhin PN, Khristoforova YuA, Moryatov AA, Machikhin AS, Pozhar VE, Kozlov SG, Zakharov VP. Hyperspectral in vivo analysis of normal skin chromophores and visualization of oncological pathologies. Computer Optics 2019; 43(4): 661-670. DOI: 10.18287/2412-6179-2019-43-4-661-670.
  27. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. NIPS'12 2012; 1: 1097-1105.
  28. Hu W, Huang Y, Wei L, et al. Deep convolutional neural networks for hyperspectral image classification. J Sens 2015; 2015: 258619. DOI: 10.1155/2015/258619.
  29. Ma X, Geng J, Wang H. Hyperspectral image classification via contextual deep learning. EURASIP J Image Video Process 2015; 20(1): 20.
  30. Halicek M, et al. Deep convolutional neural networks for classifying head and neck cancer using hyperspectral imaging. J Biomed Opt 2017; 22: 060503. DOI: 10.1117/1.JBO.22.6.060503.
  31. Pardo A, Gutiérrez-Gutiérrez JA, Lihacova I, López-Higuera JM, Conde OM. On the spectral signature of melanoma: a non-parametric classification framework for cancer detection in hyperspectral imaging of melanocytic lesions. Biomed Opt Express 2018; 9(12): 6283-6301.
  32. Machikhin A, Batshev V, Pozhar V. Aberration analysis of AOTF-based spectral imaging systems. J Opt Soc Am A 2017; 34(7): 1109-1113. DOI: 10.1364/JOSAA.34.001109.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20