Comparison of deep convolution and least squares GANs for diabetic retinopathy image synthesis

Basit Öğe Kaydı
dc.authorid0000-0003-4094-9598en_US
dc.contributor.authorAtaş, İsa
dc.date.accessioned2023-10-25T11:03:00Z
dc.date.available2023-10-25T11:03:00Z
dc.date.issued2023en_US
dc.departmentDicle Üniversitesi, Diyarbakır Teknik Bilimler Meslek Yüksekokulu, Bilgisayar Teknolojileri Bölümüen_US
dc.description.abstractInaccessibility to medical image datasets in today’s technology limits deep-learning studies in the healthcare field. Generative adversarial networks (GANs) can fill this gap by synthesizing data comparable to actual images. GAN is a generative-modeling approach that emulates dataset content using deep learning techniques. Vanilla GAN is not compatible enough to synthesize images, so variants have been developed. In this study, the performances of the deep convolutional GAN (DCGAN) using the sigmoid-based cross-entropy loss function and the least squares GAN (LSGAN) using the mean square error function on diabetic retinopathy images were analyzed. Inception score, which measures visual acuity, and Frechet inception distance, which calculates structural similarity, were used to validate the qualitative results of the generated images. In detailed analyzes, the DCGAN model performed better than the LSGAN model. The evaluations made depend on the loss of generator and discriminator, classification accuracy, quality of generated images and training epoch of the models. As a result, were reported the effect of changing hyperparameters in DCGAN and LSGAN models and the compatibility of the produced images with the quantitative results.en_US
dc.identifier.citationAtaş, İ. (2023). Comparison of deep convolution and least squares GANs for diabetic retinopathy image synthesis. Neural Computing and Applications, 35(19), 14431-14448.en_US
dc.identifier.doi10.1007/s00521-023-08482-4
dc.identifier.endpage14448en_US
dc.identifier.issn0941-0643
dc.identifier.issue19en_US
dc.identifier.scopus2-s2.0-85150964657
dc.identifier.scopusqualityQ1
dc.identifier.startpage14431en_US
dc.identifier.urihttps://link.springer.com/article/10.1007/s00521-023-08482-4
dc.identifier.urihttps://hdl.handle.net/11468/12933
dc.identifier.volume35en_US
dc.identifier.wosWOS:000959191000003
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorAtaş, İsa
dc.language.isoenen_US
dc.publisherSpringer Science and Business Mediaen_US
dc.relation.ispartofNeural Computing and Applications
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectDeep learningen_US
dc.subjectGANen_US
dc.subjectFIDen_US
dc.subjectISen_US
dc.subjectMedical imagesen_US
dc.subjectRetinaen_US
dc.titleComparison of deep convolution and least squares GANs for diabetic retinopathy image synthesisen_US
dc.titleComparison of deep convolution and least squares GANs for diabetic retinopathy image synthesis
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
Comparison of deep convolution and least squares GANs for diabetic retinopathy image synthesis.pdf
Boyut:
3.96 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Makale Dosyası
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Diyarbakır Teknik Bilimler Meslek Yüksekokulu Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu