Please use this identifier to cite or link to this item:
https://dspace.ncfu.ru/handle/20.500.12258/13666
Title: | Method for determining skin lesions from images using neural network |
Authors: | Lyakhova, U. A. Ляхова, У. А. Lyakhov, P. A. Ляхов, П. А. Chervyakov, N. I. Червяков, Н. И. |
Keywords: | Convolutional neural networks;Deep learning;Image recognition;Medical imaging;Melanoma;Skin lesions;Convolution;Dermatology;Diagnosis;Tumors |
Issue Date: | 2020 |
Publisher: | Institute of Electrical and Electronics Engineers Inc. |
Citation: | Lyakhova, U.A., Lyakhov, P.A., Chervyakov, N.I., Kaplun, D.I., Voznesensky, A.S. Method for determining skin lesions from images using neural network // 2020 9th Mediterranean Conference on Embedded Computing, MECO 2020. - 2020. - Номер статьи 9134162 |
Series/Report no.: | 2020 9th Mediterranean Conference on Embedded Computing, MECO 2020 |
Abstract: | The paper proposes a system for determining malignant skin neoplasms. The use of convolutional neural networks for determining skin tumors from images is considered. A convolutional neural network of deep learning has been developed and modeled, which allows you to determine and classify pigmented skin lesions by examining photographs. The article proposes a system for determining malignant skin neoplasms. The proposed neural network has the basic parameters of the VGG-A architecture with a maximum number of epoch training of 10. The accuracy of the determination of the proposed model of the convolutional neural network is at least 77%. The minimum learning loss function was 0.5577. As a result of the work, a database of training photos of real pigmented skin formations taken from the international open archive ISIC Melanoma Project was used, which is a database of digital images of various types of skin lesions, was formed. Using the proposed model can be of great help in determining and diagnosing malignant skin lesions by dermatologists |
URI: | http://hdl.handle.net/20.500.12258/13666 |
Appears in Collections: | Статьи, проиндексированные в SCOPUS, WOS |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
scopusresults 1345 .pdf Restricted Access | 1.51 MB | Adobe PDF | View/Open | |
WoS 1023 .pdf Restricted Access | 260.76 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.