Brain Extraction from Magnetic Resonance Images Using UNet modified with Residual and Dense Layers

Basit Öğe Kaydı
dc.contributor.authorGurkahraman, Kali
dc.contributor.authorDaşgın, Çağrı
dc.date.accessioned2024-10-26T17:42:46Z
dc.date.available2024-10-26T17:42:46Z
dc.date.issued2023
dc.departmentSivas Cumhuriyet Üniversitesi
dc.description.abstractThe main goal of brain extraction is to separate the brain from non-brain parts, which enables accurate detection or classification of abnormalities within the brain region. The precise brain extraction process significantly influences the quality of successive neuroimaging analyses. Brain extraction is a challenging task mainly due to the similarity of intensity values between brain and non-brain structure. In this study, a UNet model improved with ResNet50 or DenseNet121 feature extraction layers was proposed for brain extraction from Magnetic Resonance Imaging (MRI) images. Three publicly available datasets (IBSR, NFBS and CC-359) were used for training the deep learning models. The findings of a comparison between different feature extraction layer types added to UNet shows that residual connections taken from ResNet50 is more successful across all datasets. The ResNet50 connections proved effective in enhancing the distinction of weak but significant gradient values in brain boundary regions. In addition, the best results were obtained for CC-359. The improvement achieved with CC-359 can be attributed to its larger number of samples with more slices, indicating that the model learned better. The performance of our proposed model, evaluated using test data, is found to be comparable to the results obtained in the literature.
dc.identifier.doi10.46810/tdfd.1339665
dc.identifier.endpage151
dc.identifier.issn2149-6366
dc.identifier.issue3
dc.identifier.startpage144
dc.identifier.trdizinid1198568
dc.identifier.urihttps://doi.org/10.46810/tdfd.1339665
dc.identifier.urihttps://search.trdizin.gov.tr/tr/yayin/detay/1198568
dc.identifier.urihttps://hdl.handle.net/20.500.12418/24797
dc.identifier.volume12
dc.indekslendigikaynakTR-Dizin
dc.language.isoen
dc.relation.ispartofTürk Doğa ve Fen Dergisi
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectDeep learning
dc.subjectBrain extraction
dc.subjectSkull stripping
dc.subjectDense connection
dc.subjectResidual connection
dc.subjectUNet.
dc.titleBrain Extraction from Magnetic Resonance Images Using UNet modified with Residual and Dense Layers
dc.typeArticle

Dosyalar

Koleksiyon

TR-Dizin İndeksli Yayınlar Koleksiyonu