Block Attention and Switchable Normalization Based Deep Learning Framework for Segmentation of Retinal Vessels

Basit Öğe Kaydı
dc.authoridUlukaya, Sezer/0000-0003-0473-7547
dc.authoridoksuz, ilkay/0000-0001-6478-0534
dc.authorwosidUlukaya, Sezer/N-9772-2015
dc.authorwosidoksuz, ilkay/I-8364-2014
dc.contributor.authorDeari, Sabri
dc.contributor.authorOksuz, Ilkay
dc.contributor.authorUlukaya, Sezer
dc.date.accessioned2024-06-12T11:13:37Z
dc.date.available2024-06-12T11:13:37Z
dc.date.issued2023
dc.departmentTrakya Üniversitesien_US
dc.description.abstractThe presence of high blood sugar levels damages blood vessels and causes an eye condition called diabetic retinopathy. The ophthalmologist can detect this disease by looking at the variations in retinal blood vasculature. Manual segmentation of vessels requires highly skilled specialists, and not possible for many patients to be done quickly in their daily routine. For these reasons, it is of great importance to isolate retinal vessels precisely, quickly, and accurately. The difficulty distinguishing the retinal vessels from the background, and the small number of samples in the databases make this segmentation problem difficult. In this study, we propose a novel network called Block Feature Map Distorted Switchable Normalization U-net with Global Context Informative Convolutional Block Attention Module (BFMD SN U-net with GCI- CBAM). We improve the traditional Fully Convolutional Segmentation Networks in multiple aspects with the proposed model as follows; The model converges in earlier epochs, adapts more flexibly to different data, is more robust against overfitting, and gets better feature refinement at different dilation rates to cope with different sizes of retinal vessels. We evaluate the proposed network on two reference retinal datasets, DRIVE and CHASE DB1, and achieve state-of-the-art performances with 97.00 % accuracy and 98.71 % AUC in DRIVE and 97.62 % accuracy and 99.11 % AUC on CHASE DB1 databases. Additionally, the convergence step of the model is reduced and it has fewer parameters than the baseline U-net. In summary, the proposed model surpasses the U-net -based approaches used for retinal vessel separation in the literature.en_US
dc.description.sponsorshipTUBITAK [118C353]en_US
dc.description.sponsorshipThis paper has been produced benefiting from the 2232 International Fellowship for Outstanding Researchers Program of TUBITAK (Project No: 118C353). However, the entire responsibility of the publication/paper belongs to the owner of the article. The financial support received from TUBITAK does not mean that the content of the publication is approved in a scientific sense by TUBITAK.en_US
dc.identifier.doi10.1109/ACCESS.2023.3265729
dc.identifier.endpage38274en_US
dc.identifier.issn2169-3536
dc.identifier.scopus2-s2.0-85153351075en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage38263en_US
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2023.3265729
dc.identifier.urihttps://hdl.handle.net/20.500.14551/23617
dc.identifier.volume11en_US
dc.identifier.wosWOS:000979802600001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIEEE-Inst Electrical Electronics Engineers Incen_US
dc.relation.ispartofIeee Accessen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectRetinal Vesselsen_US
dc.subjectSwitchesen_US
dc.subjectImage Analysisen_US
dc.subjectBlood Vesselsen_US
dc.subjectDistortionen_US
dc.subjectDiabetesen_US
dc.subjectRetinal Vesselen_US
dc.subjectSegmentationen_US
dc.subjectDisouten_US
dc.subjectBlock Attentionen_US
dc.subjectSwitchable Normalizationen_US
dc.subjectU-Neten_US
dc.subjectDropouten_US
dc.titleBlock Attention and Switchable Normalization Based Deep Learning Framework for Segmentation of Retinal Vesselsen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu