Automated skin melanoma diagnostics based on mathematical model of artificial convolutional neural network
In the last 10 years there has been a revolu on in the fi eld of computer image analysis and pa ern recogni on. Modern algorithms of computer vision equaled and even in some problems surpassed human capabili es. This jerk is largely due to the emergence and development of the technology of deep convo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
QUASAR, LLC
2018-09-01
|
| Series: | Исследования и практика в медицине |
| Subjects: | |
| Online Access: | https://www.rpmj.ru/rpmj/article/view/299 |
| _version_ | 1826559292102148096 |
|---|---|
| author | D. A. Gavrilov E. I. Zakirov E. V. Gameeva V. Yu. Semenov O. Yu. Aleksandrova |
| author_facet | D. A. Gavrilov E. I. Zakirov E. V. Gameeva V. Yu. Semenov O. Yu. Aleksandrova |
| author_sort | D. A. Gavrilov |
| collection | DOAJ |
| description | In the last 10 years there has been a revolu on in the fi eld of computer image analysis and pa ern recogni on. Modern algorithms of computer vision equaled and even in some problems surpassed human capabili es. This jerk is largely due to the emergence and development of the technology of deep convolu onal neural networks.Recent developments in the fi eld of image processing and machine learning open up the prospect of crea ng systems based on ar fi cial neural convolu onal networks, superior to humans in problems of image classifi ca on, in par cular, in solving problems of analysis of various medical images. Among the most promising applica ons: automated recogni on and classifi ca on of skin diseases, detec on of pathologies on X-ray, CT, MRI, ultrasound imaging. In the proposed project, we will focusour a en on on the diagnosis of human skin diseases.At the moment, melanoma is one of the most dangerous types of malignant tumors of the skin with a lot of deaths due to rapid metastasis, which is difficult to treat. The development of computer vision technology has allowed the development of technical vision systems that allow detec on and classifi ca on of skin diseases with a quality that is comparable and in some cases exceeds the values a ained by man.In this paper, the authors propose an algorithm for the primary diagnosis of skin melanoma based on deep neural networks, achieving an accuracy of 91% for melanoma in dermatoscopic images. At the moment, the algorithm is implemented programma cally and is used in the test version of the online system for detec ng and classifying skin diseases, available at skincheckup.online.Thanks to this development, the prospect of a signifi cantincrease in the propor on of people subjected to preven ve examina on for the presence of skin diseases opens up. Along with this, an addi onal source of informa on for specialized professionals can also play a role in seng the right diagnosis. |
| first_indexed | 2024-04-10T01:26:16Z |
| format | Article |
| id | doaj.art-a3852a77e75c469394c77971b0afa217 |
| institution | Directory Open Access Journal |
| issn | 2410-1893 |
| language | Russian |
| last_indexed | 2025-03-14T08:58:04Z |
| publishDate | 2018-09-01 |
| publisher | QUASAR, LLC |
| record_format | Article |
| series | Исследования и практика в медицине |
| spelling | doaj.art-a3852a77e75c469394c77971b0afa2172025-03-02T12:44:08ZrusQUASAR, LLCИсследования и практика в медицине2410-18932018-09-015311011610.17709/2409-2231-2018-5-3-11222Automated skin melanoma diagnostics based on mathematical model of artificial convolutional neural networkD. A. Gavrilov0E. I. Zakirov1E. V. Gameeva2V. Yu. Semenov3O. Yu. Aleksandrova4Moscow Institute of Physics and Technology (MIPT)Moscow Institute of Physics and Technology (MIPT)P.Hertsen Moscow Oncology Research Institute – Branch of the National Medical Radiology Research Centre of the Ministry of Health of the Russian FederationInstitute for Coronary and Vascular Surgery, A.N.Bakulev National Medical Research Center of Cardiovascular Surgery of the Ministry of Health of the Russian FederationM.Vladimirskiy Moscow Regional Research Clinical InstituteIn the last 10 years there has been a revolu on in the fi eld of computer image analysis and pa ern recogni on. Modern algorithms of computer vision equaled and even in some problems surpassed human capabili es. This jerk is largely due to the emergence and development of the technology of deep convolu onal neural networks.Recent developments in the fi eld of image processing and machine learning open up the prospect of crea ng systems based on ar fi cial neural convolu onal networks, superior to humans in problems of image classifi ca on, in par cular, in solving problems of analysis of various medical images. Among the most promising applica ons: automated recogni on and classifi ca on of skin diseases, detec on of pathologies on X-ray, CT, MRI, ultrasound imaging. In the proposed project, we will focusour a en on on the diagnosis of human skin diseases.At the moment, melanoma is one of the most dangerous types of malignant tumors of the skin with a lot of deaths due to rapid metastasis, which is difficult to treat. The development of computer vision technology has allowed the development of technical vision systems that allow detec on and classifi ca on of skin diseases with a quality that is comparable and in some cases exceeds the values a ained by man.In this paper, the authors propose an algorithm for the primary diagnosis of skin melanoma based on deep neural networks, achieving an accuracy of 91% for melanoma in dermatoscopic images. At the moment, the algorithm is implemented programma cally and is used in the test version of the online system for detec ng and classifying skin diseases, available at skincheckup.online.Thanks to this development, the prospect of a signifi cantincrease in the propor on of people subjected to preven ve examina on for the presence of skin diseases opens up. Along with this, an addi onal source of informa on for specialized professionals can also play a role in seng the right diagnosis.https://www.rpmj.ru/rpmj/article/view/299automated classification of skin diseasesneural networkvision systemsdeep learning neural network |
| spellingShingle | D. A. Gavrilov E. I. Zakirov E. V. Gameeva V. Yu. Semenov O. Yu. Aleksandrova Automated skin melanoma diagnostics based on mathematical model of artificial convolutional neural network Исследования и практика в медицине automated classification of skin diseases neural network vision systems deep learning neural network |
| title | Automated skin melanoma diagnostics based on mathematical model of artificial convolutional neural network |
| title_full | Automated skin melanoma diagnostics based on mathematical model of artificial convolutional neural network |
| title_fullStr | Automated skin melanoma diagnostics based on mathematical model of artificial convolutional neural network |
| title_full_unstemmed | Automated skin melanoma diagnostics based on mathematical model of artificial convolutional neural network |
| title_short | Automated skin melanoma diagnostics based on mathematical model of artificial convolutional neural network |
| title_sort | automated skin melanoma diagnostics based on mathematical model of artificial convolutional neural network |
| topic | automated classification of skin diseases neural network vision systems deep learning neural network |
| url | https://www.rpmj.ru/rpmj/article/view/299 |
| work_keys_str_mv | AT dagavrilov automatedskinmelanomadiagnosticsbasedonmathematicalmodelofartificialconvolutionalneuralnetwork AT eizakirov automatedskinmelanomadiagnosticsbasedonmathematicalmodelofartificialconvolutionalneuralnetwork AT evgameeva automatedskinmelanomadiagnosticsbasedonmathematicalmodelofartificialconvolutionalneuralnetwork AT vyusemenov automatedskinmelanomadiagnosticsbasedonmathematicalmodelofartificialconvolutionalneuralnetwork AT oyualeksandrova automatedskinmelanomadiagnosticsbasedonmathematicalmodelofartificialconvolutionalneuralnetwork |