000868442 001__ 868442
000868442 005__ 20210130004220.0
000868442 0247_ $$2doi$$a10.1109/ACCESS.2019.2959037
000868442 0247_ $$2Handle$$a2128/23781
000868442 0247_ $$2WOS$$aWOS:000509483800029
000868442 037__ $$aFZJ-2020-00036
000868442 082__ $$a621.3
000868442 1001_ $$00000-0001-6199-2312$$aPawar, Kamlesh$$b0$$eCorresponding author
000868442 245__ $$aA Deep Learning Framework for Transforming Image Reconstruction Into Pixel Classification
000868442 260__ $$aNew York, NY$$bIEEE$$c2019
000868442 3367_ $$2DRIVER$$aarticle
000868442 3367_ $$2DataCite$$aOutput Types/Journal article
000868442 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1578311558_25173
000868442 3367_ $$2BibTeX$$aARTICLE
000868442 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000868442 3367_ $$00$$2EndNote$$aJournal Article
000868442 520__ $$aA deep learning framework is presented that transforms the task of MR image reconstruction from randomly undersampled k-space data into pixel classification. A DL network was trained to remove incoherent undersampling artifacts from MR images. The underlying, fully sampled, target image was represented as a discrete quantized image. The quantization step enables the design of a convolutional neural network (CNN) that can classify each pixel in the input image to a discrete quantized level. The reconstructed image quality of the proposed DL classification model was compared with conventional compressed sensing (CS) and a DL regression model. The reconstructed images using the DL classification model outperformed the state-of-the-art compressed sensing and DL regression models with a similar number of parameters assessed using quantitative measures. The experiments reveal that the proposed deep learning method is robust to noise and is able to reconstruct high-quality images in low SNR scenarios where conventional CS reconstructions and DL regression networks perform poorly. A generic design framework for transforming MR image reconstruction into pixel classification is developed. The proposed method can be easily incorporated into other DL-based image reconstruction methods.
000868442 536__ $$0G:(DE-HGF)POF3-573$$a573 - Neuroimaging (POF3-573)$$cPOF3-573$$fPOF III$$x0
000868442 588__ $$aDataset connected to CrossRef
000868442 7001_ $$00000-0002-0173-6090$$aChen, Zhaolin$$b1
000868442 7001_ $$0P:(DE-Juel1)131794$$aShah, N. J.$$b2$$ufzj
000868442 7001_ $$00000-0002-3186-4026$$aEgan, Gary. F.$$b3
000868442 773__ $$0PERI:(DE-600)2687964-5$$a10.1109/ACCESS.2019.2959037$$gVol. 7, p. 177690 - 177702$$p177690 - 177702$$tIEEE access$$v7$$x2169-3536$$y2019
000868442 8564_ $$uhttps://juser.fz-juelich.de/record/868442/files/08931762.pdf$$yOpenAccess
000868442 8564_ $$uhttps://juser.fz-juelich.de/record/868442/files/08931762.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000868442 909CO $$ooai:juser.fz-juelich.de:868442$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000868442 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131794$$aForschungszentrum Jülich$$b2$$kFZJ
000868442 9131_ $$0G:(DE-HGF)POF3-573$$1G:(DE-HGF)POF3-570$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lDecoding the Human Brain$$vNeuroimaging$$x0
000868442 9141_ $$y2019
000868442 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000868442 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology
000868442 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000868442 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bIEEE ACCESS : 2017
000868442 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal
000868442 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ
000868442 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000868442 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000868442 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5
000868442 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000868442 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review
000868442 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000868442 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List
000868442 9201_ $$0I:(DE-Juel1)INM-4-20090406$$kINM-4$$lPhysik der Medizinischen Bildgebung$$x0
000868442 980__ $$ajournal
000868442 980__ $$aVDB
000868442 980__ $$aUNRESTRICTED
000868442 980__ $$aI:(DE-Juel1)INM-4-20090406
000868442 9801_ $$aFullTexts