File Download

There are no files associated with this item.

Supplementary

Conference Paper: Gibbs-Ringing Artifact Reduction in MRI via Machine Learning Using Convolutional Neural Network

TitleGibbs-Ringing Artifact Reduction in MRI via Machine Learning Using Convolutional Neural Network
Authors
Issue Date2018
PublisherInternational Society for Magnetic Resonance in Medicine.
Citation
Proceedings of International Society for Magnetic Resonance in Medicine & The European Society for Magnetic Resonance in Medicine and Biology (ISMRM-ESMRMB) Joint Annual Meeting, Paris, France, 16-21 June 2018, abstract no. 0429 How to Cite?
AbstractThe Gibbs-ringing artifact is caused by the insufficient sampling of the high frequency data. Existing methods generally exploit smooth constraints to reduce intensity oscillations near high-contrast boundaries but at the cost of blurring details. This work presents a convolutional neural network (CNN) method that maps ringing images to their ringing-free counterparts for Gibbs-ringing artifact removal in MRI. The experimental results demonstrate that the proposed method can effectively remove Gibbs-ringing without introducing noticeable blurring.
Descriptione-Poster Session: Machine Learning Unleashed - Acquisition, Reconstruction & Analysis - Abstract #0429
Persistent Identifierhttp://hdl.handle.net/10722/261183

 

DC FieldValueLanguage
dc.contributor.authorZHANG, Q-
dc.contributor.authorRUAN, G-
dc.contributor.authorYANG, W-
dc.contributor.authorZHAO, K-
dc.contributor.authorWu, EX-
dc.contributor.authorFENG, Y-
dc.date.accessioned2018-09-14T08:53:52Z-
dc.date.available2018-09-14T08:53:52Z-
dc.date.issued2018-
dc.identifier.citationProceedings of International Society for Magnetic Resonance in Medicine & The European Society for Magnetic Resonance in Medicine and Biology (ISMRM-ESMRMB) Joint Annual Meeting, Paris, France, 16-21 June 2018, abstract no. 0429-
dc.identifier.urihttp://hdl.handle.net/10722/261183-
dc.descriptione-Poster Session: Machine Learning Unleashed - Acquisition, Reconstruction & Analysis - Abstract #0429-
dc.description.abstractThe Gibbs-ringing artifact is caused by the insufficient sampling of the high frequency data. Existing methods generally exploit smooth constraints to reduce intensity oscillations near high-contrast boundaries but at the cost of blurring details. This work presents a convolutional neural network (CNN) method that maps ringing images to their ringing-free counterparts for Gibbs-ringing artifact removal in MRI. The experimental results demonstrate that the proposed method can effectively remove Gibbs-ringing without introducing noticeable blurring.-
dc.languageeng-
dc.publisherInternational Society for Magnetic Resonance in Medicine.-
dc.relation.ispartofISMRM-ESMRMB Joint Annual Meeting 2018-
dc.titleGibbs-Ringing Artifact Reduction in MRI via Machine Learning Using Convolutional Neural Network-
dc.typeConference_Paper-
dc.identifier.emailWu, EX: ewu@eee.hku.hk-
dc.identifier.authorityWu, EX=rp00193-
dc.identifier.hkuros291504-
dc.identifier.spageabstract no. 0429-
dc.identifier.epageabstract no. 0429-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats