Classification of Brain Tumors from MR Images Using a New CNN Architecture

Basit Öğe Kaydı
dc.authoridOZDEMIR, Cuneyt/0000-0002-9252-5888
dc.contributor.authorOzdemir, Cuneyt
dc.date.accessioned2024-12-24T19:30:31Z
dc.date.available2024-12-24T19:30:31Z
dc.date.issued2023
dc.departmentSiirt Üniversitesi
dc.description.abstractAccurately classifying brain tumors is a crucial factor in combatting, intervening , treating the disease. By automating the tumor diagnosis process without the involvement of human factors, it is possible to decrease the occurrence of human errors during the diagnosis process. In a new deep convolutional neural network architecture was developed to tackle the brain tumor classification problem, resulting in the successful classification of three distinct types of brain tumors -meningioma, glioma , pituitary. With the propose CNN architecture, a classification accuracy of 98.69% was achieved in brain tumor classification. The recommend model is simple and very fast. It was observed that giving high kernel size and strides values in the first layers and low values in the middle layers of the convolutional layers, and keeping the strides value small in the pooling layer had greatly increased on the model performance. The recommend CNN architecture was compared with studies using the same dataset and transfer learning models in the literature. As a result of these comparisons, high-scoring results were obtained with the recommend model. The classification success achieved by the model is state-of-the-art among stand-alone models.
dc.identifier.doi10.18280/ts.400219
dc.identifier.endpage618
dc.identifier.issn0765-0019
dc.identifier.issn1958-5608
dc.identifier.issue2
dc.identifier.scopus2-s2.0-85162154270
dc.identifier.scopusqualityN/A
dc.identifier.startpage611
dc.identifier.urihttps://doi.org/10.18280/ts.400219
dc.identifier.urihttps://hdl.handle.net/20.500.12604/7555
dc.identifier.volume40
dc.identifier.wosWOS:000996210200019
dc.identifier.wosqualityQ4
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherInt Information & Engineering Technology Assoc
dc.relation.ispartofTraitement Du Signal
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20241222
dc.subjectbrain tumor
dc.subjectCNN
dc.subjectkernel size
dc.subjectstrides
dc.titleClassification of Brain Tumors from MR Images Using a New CNN Architecture
dc.typeArticle

Dosyalar

Koleksiyon

WOS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu