Show simple item record

dc.contributor.authorYıldırım, İsa
dc.contributor.authorErtas, Metin
dc.contributor.authorUnal, Mehmet Ozan
dc.date.accessioned2022-07-04T13:05:46Z
dc.date.available2022-07-04T13:05:46Z
dc.identifier.citationUnal M. O. , Ertas M., Yıldırım İ., "An unsupervised reconstruction method for low-dose CT using deep generative regularization prior", BIOMEDICAL SIGNAL PROCESSING AND CONTROL, cilt.75, 2022
dc.identifier.issn1746-8094
dc.identifier.othervv_1032021
dc.identifier.otherav_398c0c89-67c4-43a8-8240-e7045c5873c3
dc.identifier.urihttp://hdl.handle.net/20.500.12627/182338
dc.identifier.urihttps://doi.org/10.1016/j.bspc.2022.103598
dc.identifier.urihttps://avesis.istanbul.edu.tr/api/publication/398c0c89-67c4-43a8-8240-e7045c5873c3/file
dc.description.abstractLow-dose CT imaging requires reconstruction from noisy indirect measurements which can be defined as an illposed linear inverse problem. In addition to conventional FBP method in CT imaging, recent compressed sensing based methods exploit handcrafted priors which are mostly simplistic and hard to determine. More recently, deep learning (DL) based methods have become popular in medical imaging field. In CT imaging, DL based methods try to learn a function that maps low-dose images to normal-dose images. Although the results of these methods are promising, their success mostly depends on the availability of high-quality massive datasets. In this study, we proposed a method that does not require any training data or a learning process. Our method exploits such an approach that deep convolutional neural networks (CNNs) generate patterns easier than the noise, therefore randomly initialized generative neural networks can be suitable priors to be used in regularizing the reconstruction. In the experiments, the proposed method is implemented with different loss function variants. Both analytical CT phantoms and human CT images are used with different views. Conventional FBP method, a popular iterative method (SART), and TV regularized SART are used in the comparisons. We demonstrated that our method with different loss function variants outperforms the other methods both qualitatively and quantitatively.
dc.language.isoeng
dc.subjectBioengineering
dc.subjectMÜHENDİSLİK, BİYOMEDİKSEL
dc.subjectMühendislik
dc.subjectMühendislik, Bilişim ve Teknoloji (ENG)
dc.subjectBiyomedikal Mühendisliği
dc.subjectMühendislik ve Teknoloji
dc.subjectGeneral Engineering
dc.subjectEngineering (miscellaneous)
dc.subjectBiomedical Engineering
dc.subjectPhysical Sciences
dc.titleAn unsupervised reconstruction method for low-dose CT using deep generative regularization prior
dc.typeMakale
dc.relation.journalBIOMEDICAL SIGNAL PROCESSING AND CONTROL
dc.contributor.departmentİstanbul Teknik Üniversitesi , ,
dc.identifier.volume75
dc.contributor.firstauthorID3415914


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record