0 38

Cited 0 times in

Effect of Scan Time on Neuro F-18-Fluorodeoxyglucose Positron Emission Tomography Image Generated Using Deep Learning

DC FieldValueLanguage
dc.contributor.authorKim, Jaewon-
dc.contributor.authorKang, Sungsik-
dc.contributor.authorLee, Konsu-
dc.contributor.authorJung, Jin Ho-
dc.contributor.authorKim, Garam-
dc.contributor.authorLim, Hyun Keong-
dc.contributor.authorChoi, Yong-
dc.contributor.authorLee, Sangwon-
dc.contributor.authorYun, Mijin-
dc.date.accessioned2021-03-31T01:31:34Z-
dc.date.available2021-03-31T01:31:34Z-
dc.date.created2021-02-22-
dc.date.issued2021-03-
dc.identifier.issn2156-7018-
dc.identifier.urihttps://ir.ymlib.yonsei.ac.kr/handle/22282913/181843-
dc.description.abstractThe purpose of this study was to generate the PET images with high signal-to-noise ratio (SNR) acquired for typical scan durations (H-PET) from short scan time PET images with low SNR (L-PET) using deep learning and to evaluate the effect of scan time on the quality of predicted PET image. A convolutional neural network (CNN) with a concatenated connection and residual learning framework was implemented. PET data from 27 patients were acquired for 900 s, starting 60 minutes after the intravenous administration of FDG using a commercial PET/CT scanner. To investigate the effect of scan time on the quality of the predicted H-PETs, 10 s, 30 s, 60 s, and 120 s PET data were generated by sorting the 900 s LMF data into the LMF data acquired for each scan time. Twenty-three of the 27 patient images were used for training of the proposed CNN and the remaining four patient images were used for test of the CNN. The predicted H-PETs generated by the CNN were compared to ground-truth H-PETs, L-PETS, and filtered L-PETS processed with four commonly used denoising algorithms. The peak signal-to-noise ratios (PSNRs), normalized root mean square errors (NRMSEs), and average region-of-interest (ROI) differences as a function of scan time were calculated. The quality of the predicted H-PETs generated by the CNN was superior to that of the L-PETs and filtered L-PETs. Lower NRMSEs and higher PSNRs were also obtained from predicted H-PETs compared to the L-PETS and filtered L-PETS. ROI differences in the predicted H-PETs were smaller than those of the L-PETS. The quality of the predicted H-PETs gradually improved with increasing scan times. The lowest NRMSEs, highest PSNRs, and smallest ROI differences were obtained using the predicted H-PETs for 120 s. Various performance test results for the proposed CNN indicate that it is possible to generate H-PETs from neuro FDG L-PETS using the proposed CNN method, which might allow reductions in both scan time and injection dose.-
dc.language영어-
dc.publisherAMER SCIENTIFIC PUBLISHERS-
dc.relation.isPartOfJOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS-
dc.titleEffect of Scan Time on Neuro F-18-Fluorodeoxyglucose Positron Emission Tomography Image Generated Using Deep Learning-
dc.typeArticle-
dc.contributor.googleauthorKim, Jaewon-
dc.contributor.googleauthorKang, Sungsik-
dc.contributor.googleauthorLee, Konsu-
dc.contributor.googleauthorJung, Jin Ho-
dc.contributor.googleauthorKim, Garam-
dc.contributor.googleauthorLim, Hyun Keong-
dc.contributor.googleauthorChoi, Yong-
dc.contributor.googleauthorLee, Sangwon-
dc.contributor.googleauthorYun, Mijin-
dc.identifier.doi10.1166/jmihi.2021.3316-
dc.relation.journalcodeJ03359-
dc.identifier.eissn2156-7026-
dc.subject.keywordDeep Learning-
dc.subject.keywordPET-
dc.subject.keywordScan Time Reduction-
dc.subject.keywordCNN-
dc.subject.keywordDenoising-
dc.subject.keywordHuman Brain-
dc.contributor.affiliatedAuthorYun, Mijin-
dc.identifier.wosid000603078500004-
dc.citation.titleJOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS-
dc.citation.volume11-
dc.citation.number3-
dc.citation.startPage681-
dc.citation.endPage687-
dc.identifier.bibliographicCitationJOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, Vol.11(3) : 681-687, 2021-03-
dc.identifier.rimsid67565-
dc.type.rimsART-
dc.description.journalClass1-
dc.description.journalClass1-
dc.subject.keywordAuthorDeep Learning-
dc.subject.keywordAuthorPET-
dc.subject.keywordAuthorScan Time Reduction-
dc.subject.keywordAuthorCNN-
dc.subject.keywordAuthorDenoising-
dc.subject.keywordAuthorHuman Brain-
dc.subject.keywordPlusALZHEIMERS-DISEASE-
dc.subject.keywordPlusPET IMAGES-
dc.subject.keywordPlusFDG-PET-
dc.subject.keywordPlusPARCELLATION-
dc.subject.keywordPlusTRANSFORM-
dc.type.docTypeArticle-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClassscie-
dc.relation.journalWebOfScienceCategoryMathematical & Computational Biology-
dc.relation.journalWebOfScienceCategoryRadiology, Nuclear Medicine & Medical Imaging-
dc.relation.journalResearchAreaMathematical & Computational Biology-
dc.relation.journalResearchAreaRadiology, Nuclear Medicine & Medical Imaging-
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Nuclear Medicine (핵의학교실) > 1. Journal Papers

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.