Algorithm for analyzing the characteristics of the pigment network in the diagnosis of melanoma

V. G. Nikitaev ; O. B. Tamrazova ; A. N. Pronichev ; V. Yu. Sergeev ; E. A. Druzhinina

Matematičeskoe modelirovanie, Tome 33 (2021) no. 2, pp. 67-81.

Résumé

The paper offers an algorithm for analyzing the characteristics of the pigment network of skin neoplasms. The algorithm is based on the study of the coefficient of variation of average lengths of the segments of pigment network in local areas of tumors from the average value of the lengths of the line segments pigment network throughout the area of the tumor. The algorithm allows you to distinguish a typical pigment network from an atypical one. An atypical pigment network is an essential feature in determining early-stage melanoma. The algorithm can be used in automated systems for supporting medical decision — making in the diagnosis of skin neoplasms.

Détail

Keywords: digital image processing, skeletonization, atypical pigment network, dermatoscopy, diagnosis of melanoma.
Mots-clés : segmentation

Bibliographie

[1] G. A. Galil-Ogly, V. A. Molochkov, YU. V. Sergeyev (red.), Dermatoonkologiya, Meditsina dlya vsekh, M., 2005, 872 pp.

[2] V. Yu. Sergeev, Yu. Yu. Sergeev, O. B. Tamrazova, V. G. Nikitaev, A. N. Pronichev, “Automated remote diagnosis of dermatological neoplasms”, Biomed. Eng., 53:3 (2019), 194–195 | DOI | MR

[3] V. G. Nikitaev, A. N. Pronichev, O. B. Tamrazova, V. Yu. Sergeev, Yu. Yu. Sergeev, A. V. Kozyreva, E. V. Polyakov, E. A. Druzhinina, “Automated analysis of the pigment network in dermatoscopic images of melanocytic skin tumors”, Biomed. Eng., 53:4 (2019), 254–257 | DOI

[4] V. G. Nikitaev, “Medical and biological measurements: Experimental high-technology information-measuring complexes of cancer diagnosis: Problems and key points of the construction methodology”, Measurement Techniques, 58:2 (2015), 214–218 | DOI

[5] V. G. Nikitaev, “Expert systems in information measuring complexes of oncological diagnoses”, Measurement Techniques, 58:6 (2015), 719–723 | DOI

[6] V. G. Nikitaev, “Modern measurement principles in intellectual systems for a histological diagnosis of oncological illnesses”, Measurement Techniques, 58:4 (2015), 68–70 | DOI

[7] H. Kittler, C. Rosendahl, A. Cameron, P. Tschandl, Dermatoscopy: Pattern analysis of pigmented and non-pigmented lesions, Facultas Publ. AG, Vienna, Austria, 2018, 394 pp.

[8] Yu. Yu. Sergeyev, V. V. Mordovtseva, “Melanoma kogi s yavleniyamy regressa: opisanie klinicheskogo sluchaya i obzor literatury”, Klinicheskaya dermatologiya i venerologiya, 2017, no. 5, 36–41

[9] T. Russo et al, “Dermoscopy pathology correlation in melanoma”, J. Dermatol., 44 (2017), 507–514 | DOI

[10] H. Kittler et al, “Standardization of terminology in dermoscopy/dermatoscopy: Results of the third consensus conference of the International Society of Dermoscopy”, J. Am. Acad. Dermatol., 74 (2016), 1093–106 | DOI

[11] Yu. Yu. Sergeyev, V. V. Mordovtseva, “Opyt diagnostiki melanomy kozhi diametrom meneye 6 mm”, Klinicheskaya dermatologiya i venerologiya, 17:4 (2018), 97–104

[12] S. Fischer, P. Schmid, J. Guillod, “Analysis of skin lesions with pigmented networks”, Proc. of IEEE Intern. Conference on Image Proc., 1996, no. 1, 323–326 | DOI

[13] M. G. Fleming, C. Steger, J. Zhang, J. Gao, A. B. Cognetta, L. Pollak, C. R. Dyer, “Techniques for a structural analysis of dermatoscopic imagery”, Computerized Medical Imaging and Graphics, 22:5 (1998), 375–389 | DOI

[14] M. Sadeghi, M. Razmara, T. K. Lee, M. S. Atkins, “A novel method for detection of pigment network in dermoscopic images using graphs”, Computerized Medical Imaging and Graphics, 35:2 (2011), 137–143 | DOI

[15] M. Sadeghi, M. Razmara, P. Wighton, T. K. Lee, M. S. Atkins, “Modeling the dermoscopic structure pigment network using a clinically inspired feature set”, Lecture Notes in Comp. Science, 6326, 2010, 467–474 | DOI

[16] J. L. García-Arroyo, B. G. Zapirain, “Detection of pigment network in dermoscopy images using supervised machine learning and structural analysis”, Computers in Biology and Medicine, 44:1 (2014), 144–157

[17] J. L. Garcia-Arroyo, B. García-Zapirain, “Recognition of pigment network pattern in dermoscopy images based on fuzzy classification of pixels”, Computer Methods and Programs in Biomedicine, 153 (2018), 61–69 | DOI

[18] K. Kropidłowski, M. Kociołek, M. Strzelecki, D. Czubiński, “Model based approach for melanoma segmentation”, Lecture Notes in Computer Science, 8671, 2014, 347–55 | DOI

[19] K. Kropidłowski, M. Kociołek, M. Strzelecki, D. Czubiński, “Nevus atypical pigment network distinction and irregular streaks detection in skin lesions images”, Signal Proc. Algorithms, Architectures, Arrangements, and Applications Conf. Proc., SPA, 2015, 66–70

[20] M. Pap, B. Harangi, A. Hajdu, “Automatic pigment network classification using a combination of classical texture descriptors and CNN features”, Proc. of IEEE Symposium on Computer-Based Medical Systems, 2017, 343–348

[21] V. G. Nikitaev, A. N. Pronichev, E. Yu. Berdnikovich, K. S. Chistov, “Strategiya postroeniya vysokotehnologichnyh komplexov komputernoy mikroskopii: opit razrabotki i vnedreniya v atomnuyu promyshlennost i medicinu”, Pribory i sistemy. Upravlenie control, diagnostic, 2011, no. 10, 1–4

[22] V. G. Nikitaev, O. V. Nagornov, A. N. Pronichev, E. V. Polyakov, V. V. Dmitrieva, S. M. Zaitsev, V. Yu. Selchuk, O. B. Tamrazova, V. Yu. Sergeev, S. A. Kobelev, A. V. Kozyreva, A. S. Skripnik, Sposob raspoznavaniya pigmentnyh novoobrazovaniy kogi, Patent na izobretenie RU 2712919 C1, 03.02.2020

[23] D. Bradley, G. Roth, Augmenting non-rigid objects with realistic lighting, Tech. Rep. NRC 47398, National Research Council of Canada, 2004