Автоматизированная диагностика меланомы на основе алгоритма Штольца

T A Korobkova

doi:10.22213/2410-9304-2024-3-10-16

Authors

T. A. Korobkova Samara National Research University named after Academician S.P. Korolev; SamSMU of the Ministry of Health of Russia

DOI:

https://doi.org/10.22213/2410-9304-2024-3-10-16

Keywords:

ABCD rule, diagnosing of skin tumors, multilayer perceptron, COMPUTER vision in medicine, Stolz algorithm, melanoma

Abstract

The article discusses an algorithm for automating melanoma diagnosing using computer vision and a neural classifier. The aim of the study is to develop an algorithm for efficient classification of melanoma in images, as well as the influence of dermoscopic features on diagnosing. New growths in the image are highlighted. Calculation of parameters for the Stolz formula and calculation of TDS (calculation of diagnosis) were carried out. Based on the calculations performed, the optimization problem was solved to clarify the boundaries of the neoplasm differentiation areas, and the Stolz formula coefficients adjustment, and a set for neural network training was generated; MLP was selected as a classifier. The average accuracy of the algorithm on two independent data sets is 86%. Classification by a neural network of two sets of images according to Stolz parameters is given. Based on the results, a diagnosing was made. Based on the Stolz algorithm, a set of images with skin neoplasms is pre-processed: the neoplasm is isolated, ABCD signs and the overall dermoscopic score are calculated from the image. The proposed algorithm for automated melanoma diagnosing based on the Stolz dermoscopic method showed good results on real sets of images. The reduced accuracy of the model on the HAM10000 set is due to the class imbalance (ratio of classes 1 to 9). A high F-measure value indicated a good balance between sensitivity and specificity of the model, with the model tending to be better at detecting melanoma true positive (TP) cases. High sensitivity is desirable for problems, where reducing false negatives (missing positive cases) is critical, even at the expense of increasing Type I errors. The completeness of the model was 88.54% and 95% and suggests that the model minimizes cases of missing diseases. It is concluded that the more accurately the ABCD parameters are calculated, the more accurately the model will be able to classify the disease; in the future, refining and dividing parameter D into several components can provide the model with additional features for classification.

Author Biography

T. A. Korobkova, Samara National Research University named after Academician S.P. Korolev; SamSMU of the Ministry of Health of Russia

Post-graduate

References

Young AT, Vora NB, Cortez J, et al. The role of technology in melanoma screening and diagnosis. Pigment Cell Melanoma Res. 2021. Vol. 34. P. 288-300.

Thanh D.N., Prasath V.B. et al. Melanoma skin cancer detection method based on adaptive principal curvatue, colournormalisation and feature extraction with the ABCD rule. Journal of Digital Imaging. 2020. Vol. 33 (3). P.574-585.

Senan E.M., Jadhav M.E. Analysis of dermoscopy images by using ABCD rule for early detection of skin cancer. Global Transitions Proceedings. 2021. Vol. 2. Issue 1. P. 1-7.

Sepehr S. G., Hamed K., Hamid G., FaribaF.,M. melanoma diagnosis applying a machine learning method based onthe combination of nonlinear and texture features,Biomedical Signal Processing and Control. 2023.Vol. 80, PART 1. https://doi.org/10.1016/j.bspc.2022.104300.

Saghir U., Devendran V. A Brief Review of Feature Extraction Methods for Melanoma Detection. In Proc. of the 7th International Conference on Advanced Computing and Communication Systems (ICACCS). 2021. Vol. 1. P. 1304-1307.

Rizzi M, Guaragnella C. A Decision Support System for Melanoma Diagnosis from Dermoscopic Images. Applied Sciences. 2022. Vol. 12(14). P.7007. https://doi.org/10.3390/app12147007.

Искусственный интеллект: как работает и критерии оценки / О. Е. Гаранина, И. Л. Шливко, И. А. Клеменова, К. А. Ускова, А. М. Миронычева, В. И. Дардык, В. Н. Ласьков // Consilium Medicum. 2021. № 8. URL: https://cyberleninka.ru/article/n/iskusstvennyy-intellekt-kak-rabotaet-i-kriterii-otsenki (дата обращения: 07.12.2023).

Томакова Р. А., Дзюбин И. А., Брежнев А. В. Метод и алгоритм обучения сверточной нейронной сети, предназначенной для интеллектуальной системы распознавания меланомы // Известия Юго-Западного государственного университета. Серия: Управление, вычислительная техника, информатика. Медицинское приборостроение. 2022. № 12 (1). С. 65-83.

Patel RH, Foltz EA, Witkowski A, Ludzik J. Analysis of Artificial Intelligence-Based Approaches Applied to Non-Invasive Imaging for Early Detection of Melanoma: A Systematic Review. Cancers. 2023. Vol. 15 (19). P. 4694. https://doi.org/10.3390/cancers15194694.

Mandal A., Priyam S., Chan H.H., Gouveia B.M., Guitera P., Song Y., Baker MAB, Vafaee F.Computer-Aided Diagnosis of Melanoma Subtypes Using Reflectance Confocal Images. Cancers. 2023. Vol. 15(5). P. 1428. https://doi.org/10.3390/cancers15051428.

Неинвазивные методы диагностики опухолей кожи и их потенциал применения для скрининга меланомы кожи: систематический обзор литературы / О. Е. Гаранина, И. В. Самойленко, И. Л. Шливко, И. А. Клеменова, М. С. Незнахина, Л. В. Демидов // Медицинский совет. 2020. № 9. С. 102-120.

Dixon AJ, Sladden M, Zouboulis CC, Popescu CM, Nirenberg A, Steinman HK, Longo C, Dixon ZL, Thomas JM. Primary Cutaneous Melanoma-Management in 2024. Journal of Clinical Medicine. 2024. Vol. 13(6). P. 1607. https://doi.org/10.3390/jcm13061607.

Higgins H, Nakhla A, Lotfalla A, Khalil D, Doshi P, Thakkar V, Shirini D, Bebawy M, Ammari S, Lopci E, et al. Recent Advances in the Field of Artificial Intelligence for Precision Medicine in Patients with a Diagnosis of Metastatic Cutaneous Melanoma. Diagnostics. 2023. Vol. 13 (22). P. 3483. https://doi.org/10.3390/diagnostics13223483.

Мошкин А. В. Чувствительность и специфичность как клинические индикаторы качества лабораторных исследований // Лабораторная служба. 2020. № 9 (4). С. 5-6.

Saginala K, Barsouk A, Aluru JS, Rawla P, Barsouk A. Epidemiology of Melanoma. Medical Sciences. 2021. Vol. 9(4). P. 63. https://doi.org/10.3390/medsci9040063.

Kittler H. Evolution of the Clinical, Dermoscopic and Pathologic Diagnosis of Melanoma. Dermatology Practical & Conceptual. 2021. Vol. 11. No. S1. P. 1-10.

Новообразования кожи: современные представления о неинвазивных возможностях и перспективах диагностики / О. В. Минкина, А. С. Дворников, П. А. Скрипкина, Л. В. Оганесян, В. С. Палагина, К. С. Иванова // Профилактическая медицина. 2020. № 23 (6). С. 120-128.

Ляхов П.А., Ляхова У. А. Система нейросетевой классификации пигментных новообразований кожи с предварительным удалением волос на фотографиях // Компьютерная оптика. 2021. № 45 (5). С. 728-735.

Ранняя диагностика меланомы кожи с применением нескольких изображающих систем / К. Г. Кудрин, Е. Н. Римская, И. А. Аполлонова, А. П. Николаев, Н. В. Черномырдин, Д. С. Святославов, Д. В. Давыдов, И. В. Решетов // Оптика и спектроскопия. 2020. № 128 (6). DOI:10.21883/OS.2020.06.49416.53-20.

Козачок А. В., Спирин А. А., Козачок Е. С. Обзор методов раннего обнаружения меланомы // Труды ИСП РАН. 2022. № 34 (4). С. 241-250.