Synthesis of neural network structure for the analysis of complex structured ocular fundus images

This paper proposes an algorithm for synthesizing a neural network (NN) structure to analyze complex structured, low entropy, ocular fundus images, characterized by iterative tuning of the adaptive model's solver modules. This algorithm will assist in synthesizing models of NNs that meet the pr...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Tatarkanov Aslan, Alexandrov Islam, Glashev Rasul
Formato: article
Lenguaje:EN
Publicado: Institut za istrazivanja i projektovanja u privredi 2021
Materias:
T
Acceso en línea:https://doaj.org/article/3306733cf374425bbaf9aff124d49e7b
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:3306733cf374425bbaf9aff124d49e7b
record_format dspace
spelling oai:doaj.org-article:3306733cf374425bbaf9aff124d49e7b2021-12-05T21:23:07ZSynthesis of neural network structure for the analysis of complex structured ocular fundus images1451-41171821-319710.5937/jaes0-31238https://doaj.org/article/3306733cf374425bbaf9aff124d49e7b2021-01-01T00:00:00Zhttps://scindeks-clanci.ceon.rs/data/pdf/1451-4117/2021/1451-41172102344T.pdfhttps://doaj.org/toc/1451-4117https://doaj.org/toc/1821-3197This paper proposes an algorithm for synthesizing a neural network (NN) structure to analyze complex structured, low entropy, ocular fundus images, characterized by iterative tuning of the adaptive model's solver modules. This algorithm will assist in synthesizing models of NNs that meet the predetermined characteristics of the classification quality. The relevance of automating the process of ocular diagnostics of fundus pathologies is due to the need to develop domestic medical decision-making systems. Because of using the developed algorithm, the NN structure is synthesized, which will include two solver modules, and is intended to classify the dual-alternative information. Automated hybrid NN structures for intelligent segmentation of complex structured, low entropy, retinal images should provide increased efficiency of ocular diagnostics of fundus pathologies, reduce the burden on specialists, and decrease the negative impact of the human factor in diagnosis.Tatarkanov AslanAlexandrov IslamGlashev RasulInstitut za istrazivanja i projektovanja u privrediarticleartificial neural networkssynthesis algorithmcomplex structured imagesdiagnosis of ocular fundus pathologiesautomation of non-invasive diagnosticsTechnologyTEngineering (General). Civil engineering (General)TA1-2040ENIstrazivanja i projektovanja za privredu, Vol 19, Iss 2, Pp 344-355 (2021)
institution DOAJ
collection DOAJ
language EN
topic artificial neural networks
synthesis algorithm
complex structured images
diagnosis of ocular fundus pathologies
automation of non-invasive diagnostics
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
spellingShingle artificial neural networks
synthesis algorithm
complex structured images
diagnosis of ocular fundus pathologies
automation of non-invasive diagnostics
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Tatarkanov Aslan
Alexandrov Islam
Glashev Rasul
Synthesis of neural network structure for the analysis of complex structured ocular fundus images
description This paper proposes an algorithm for synthesizing a neural network (NN) structure to analyze complex structured, low entropy, ocular fundus images, characterized by iterative tuning of the adaptive model's solver modules. This algorithm will assist in synthesizing models of NNs that meet the predetermined characteristics of the classification quality. The relevance of automating the process of ocular diagnostics of fundus pathologies is due to the need to develop domestic medical decision-making systems. Because of using the developed algorithm, the NN structure is synthesized, which will include two solver modules, and is intended to classify the dual-alternative information. Automated hybrid NN structures for intelligent segmentation of complex structured, low entropy, retinal images should provide increased efficiency of ocular diagnostics of fundus pathologies, reduce the burden on specialists, and decrease the negative impact of the human factor in diagnosis.
format article
author Tatarkanov Aslan
Alexandrov Islam
Glashev Rasul
author_facet Tatarkanov Aslan
Alexandrov Islam
Glashev Rasul
author_sort Tatarkanov Aslan
title Synthesis of neural network structure for the analysis of complex structured ocular fundus images
title_short Synthesis of neural network structure for the analysis of complex structured ocular fundus images
title_full Synthesis of neural network structure for the analysis of complex structured ocular fundus images
title_fullStr Synthesis of neural network structure for the analysis of complex structured ocular fundus images
title_full_unstemmed Synthesis of neural network structure for the analysis of complex structured ocular fundus images
title_sort synthesis of neural network structure for the analysis of complex structured ocular fundus images
publisher Institut za istrazivanja i projektovanja u privredi
publishDate 2021
url https://doaj.org/article/3306733cf374425bbaf9aff124d49e7b
work_keys_str_mv AT tatarkanovaslan synthesisofneuralnetworkstructurefortheanalysisofcomplexstructuredocularfundusimages
AT alexandrovislam synthesisofneuralnetworkstructurefortheanalysisofcomplexstructuredocularfundusimages
AT glashevrasul synthesisofneuralnetworkstructurefortheanalysisofcomplexstructuredocularfundusimages
_version_ 1718370993900093440