Сonvolutional neural networks in the diagnosis of skin neoplasms
The problem of using artificial intelligence technologies in the diagnosis of skin neoplasms is considered. Dermatoscopic images for 8 nosologies were considered as the object of research. The melanoma was one of them. Melanoma is responsible for the most deaths of all skin cancers. The aim of the...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Joint Stock Company "Experimental Scientific and Production Association SPELS
2021-12-01
|
| Series: | Безопасность информационных технологий |
| Subjects: | |
| Online Access: | https://bit.mephi.ru/index.php/bit/article/view/1381 |
| _version_ | 1797723809363525632 |
|---|---|
| author | Valentin G. Nikitaev Alexander N. Pronichev Olga B. Tamrazova Vasily Yu. Sergeev Yuri Yu. Sergeev Dmitry V. Gurov Sergei M. Zaitsev Mikhail Solomatin Solomatin Tamara P. Zanegina Vladimir S. Vladimir S. Kozlov |
| author_facet | Valentin G. Nikitaev Alexander N. Pronichev Olga B. Tamrazova Vasily Yu. Sergeev Yuri Yu. Sergeev Dmitry V. Gurov Sergei M. Zaitsev Mikhail Solomatin Solomatin Tamara P. Zanegina Vladimir S. Vladimir S. Kozlov |
| author_sort | Valentin G. Nikitaev |
| collection | DOAJ |
| description | The problem of using artificial intelligence technologies in the diagnosis of skin neoplasms is considered. Dermatoscopic images for 8 nosologies were considered as the object of research. The melanoma was one of them. Melanoma is responsible for the most deaths of all skin cancers. The aim of the study was to evaluate the effectiveness of the use of pre-trained convolutional neural networks for the classification of skin neoplasms. A classification algorithm for an ensemble of convolutional networks was proposed. Pre-trained neural networks have been studied to form the ensemble. Neural network samples were selected from a set of neural networks that have proven themselves in the ImageNet Large Scale Visual Recognition Challenge. According to the results of the experiment the best three of the eight convolutional neural networks were selected for inclusion in the ensemble – MobileNet_v2, ResNet_152, ResNeXt_101_32x8d. The experiment was conducted on a sample of 10015 images representing
8 nosologies. The average classification accuracy for all nosologies was 79%. The paper highlights the features of ensuring information security when using telemedicine diagnostic technologies using the proposed approach in the recognition of images of skin neoplasms. The results of the work can be used in the design of medical decision support systems for the diagnosis of malignant skin neoplasms (including melanoma). |
| first_indexed | 2024-03-12T10:07:57Z |
| format | Article |
| id | doaj.art-ebd0a151f94e40929aa98ea0c923d551 |
| institution | Directory Open Access Journal |
| issn | 2074-7128 2074-7136 |
| language | English |
| last_indexed | 2024-03-12T10:07:57Z |
| publishDate | 2021-12-01 |
| publisher | Joint Stock Company "Experimental Scientific and Production Association SPELS |
| record_format | Article |
| series | Безопасность информационных технологий |
| spelling | doaj.art-ebd0a151f94e40929aa98ea0c923d5512023-09-02T11:08:44ZengJoint Stock Company "Experimental Scientific and Production Association SPELSБезопасность информационных технологий2074-71282074-71362021-12-0128411812610.26583/bit.2021.4.091249Сonvolutional neural networks in the diagnosis of skin neoplasmsValentin G. Nikitaev0Alexander N. Pronichev1Olga B. Tamrazova2Vasily Yu. Sergeev3Yuri Yu. Sergeev4Dmitry V. Gurov5Sergei M. Zaitsev6Mikhail Solomatin Solomatin7Tamara P. Zanegina8Vladimir S. Vladimir S. Kozlov9National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)Russian Peoples' Friendship UniversityCentral State Medical Academy of the Administrative Department of the President of the Russian FederationCentral State Medical Academy of the Administrative Department of the President of the Russian FederationNational Research Nuclear University MEPhI (Moscow Engineering Physics Institute)National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)The problem of using artificial intelligence technologies in the diagnosis of skin neoplasms is considered. Dermatoscopic images for 8 nosologies were considered as the object of research. The melanoma was one of them. Melanoma is responsible for the most deaths of all skin cancers. The aim of the study was to evaluate the effectiveness of the use of pre-trained convolutional neural networks for the classification of skin neoplasms. A classification algorithm for an ensemble of convolutional networks was proposed. Pre-trained neural networks have been studied to form the ensemble. Neural network samples were selected from a set of neural networks that have proven themselves in the ImageNet Large Scale Visual Recognition Challenge. According to the results of the experiment the best three of the eight convolutional neural networks were selected for inclusion in the ensemble – MobileNet_v2, ResNet_152, ResNeXt_101_32x8d. The experiment was conducted on a sample of 10015 images representing 8 nosologies. The average classification accuracy for all nosologies was 79%. The paper highlights the features of ensuring information security when using telemedicine diagnostic technologies using the proposed approach in the recognition of images of skin neoplasms. The results of the work can be used in the design of medical decision support systems for the diagnosis of malignant skin neoplasms (including melanoma).https://bit.mephi.ru/index.php/bit/article/view/1381artificial intelligence, convolutional neural networks, image recognition, melanoma diagnostics, telemedicine technologies, information security. |
| spellingShingle | Valentin G. Nikitaev Alexander N. Pronichev Olga B. Tamrazova Vasily Yu. Sergeev Yuri Yu. Sergeev Dmitry V. Gurov Sergei M. Zaitsev Mikhail Solomatin Solomatin Tamara P. Zanegina Vladimir S. Vladimir S. Kozlov Сonvolutional neural networks in the diagnosis of skin neoplasms Безопасность информационных технологий artificial intelligence, convolutional neural networks, image recognition, melanoma diagnostics, telemedicine technologies, information security. |
| title | Сonvolutional neural networks in the diagnosis of skin neoplasms |
| title_full | Сonvolutional neural networks in the diagnosis of skin neoplasms |
| title_fullStr | Сonvolutional neural networks in the diagnosis of skin neoplasms |
| title_full_unstemmed | Сonvolutional neural networks in the diagnosis of skin neoplasms |
| title_short | Сonvolutional neural networks in the diagnosis of skin neoplasms |
| title_sort | сonvolutional neural networks in the diagnosis of skin neoplasms |
| topic | artificial intelligence, convolutional neural networks, image recognition, melanoma diagnostics, telemedicine technologies, information security. |
| url | https://bit.mephi.ru/index.php/bit/article/view/1381 |
| work_keys_str_mv | AT valentingnikitaev sonvolutionalneuralnetworksinthediagnosisofskinneoplasms AT alexandernpronichev sonvolutionalneuralnetworksinthediagnosisofskinneoplasms AT olgabtamrazova sonvolutionalneuralnetworksinthediagnosisofskinneoplasms AT vasilyyusergeev sonvolutionalneuralnetworksinthediagnosisofskinneoplasms AT yuriyusergeev sonvolutionalneuralnetworksinthediagnosisofskinneoplasms AT dmitryvgurov sonvolutionalneuralnetworksinthediagnosisofskinneoplasms AT sergeimzaitsev sonvolutionalneuralnetworksinthediagnosisofskinneoplasms AT mikhailsolomatinsolomatin sonvolutionalneuralnetworksinthediagnosisofskinneoplasms AT tamarapzanegina sonvolutionalneuralnetworksinthediagnosisofskinneoplasms AT vladimirsvladimirskozlov sonvolutionalneuralnetworksinthediagnosisofskinneoplasms |