Intracranial arterial flow velocity mapping in quantitative time-of-flight MR angiography using deep machine learning
To evaluate the application of deep machine learning (DML) to 3D quantitative time-of-flight (qTOF) magnetic resonance angiography (MRA) to measure blood flow velocity within the intracranial arteries. Intracranial qTOF MRA was acquired in 15 subjects at 3 T. Blood flow velocity quantitation with qT...
Saved in:
Published in | Magnetic resonance imaging Vol. 100; pp. 10 - 17 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Netherlands
Elsevier Inc
01.07.2023
|
Subjects | |
Online Access | Get full text |
ISSN | 0730-725X 1873-5894 1873-5894 |
DOI | 10.1016/j.mri.2023.02.005 |
Cover
Abstract | To evaluate the application of deep machine learning (DML) to 3D quantitative time-of-flight (qTOF) magnetic resonance angiography (MRA) to measure blood flow velocity within the intracranial arteries.
Intracranial qTOF MRA was acquired in 15 subjects at 3 T. Blood flow velocity quantitation with qTOF MRA was done using a non-DML computer-vision procedure, and using convolutional DML neural networks. 3D phase contrast (PC) MRA was used as the comparator. Using PC velocity measures as the output target and qTOF two-echo source image data as inputs, DML neural networks were trained to predict component blood flow velocities. Total velocities and peak intracranial arterial blood flow velocities were computed from component velocities.
Compared to non-DML image analysis, DML-based analysis of qTOF MRA image data improved agreement with PC for mean component velocity (intraclass correlation coefficient (ICC) = 0.966 versus 0.939), mean total velocity (ICC = 0.835 versus 0.723), and peak velocity (ICC = 0.816 versus 0.597), as well as narrowed the 95% Bland-Altman limits of agreement for mean component velocity ([−5.16, +4.31]cm/s versus [−6.86, +6.53]cm/s), mean total velocity ([−6.78,+3.59]cm/s versus [−9.39, +7.09]cm/s) and peak velocity ([−13.5,+10.2]cm/s versus [−21.3, +10.2]cm/s). Compared to non-DML analysis, DML image analysis reduced the root-mean-square deviation from PC velocity measures by 28%–36%, and shortened calculation times by 35-fold.
The application of DML image analysis to intracranial qTOF MRA for velocity quantitation markedly shortened calculation times, substantially improved the agreement of component, total, and peak arterial blood flow velocities, and provided excellent agreement of hemodynamic measures with respect to 3D PC.
•Deep machine learning (DML) can improve intracranial arterial velocimetry with qTOF MRA•Component, total, and peak flow velocity measures were improved with DML•DML-derived flow velocity measures showed excellent agreement with 3D phase contrast•DML reduced calculation times for intracranial arterial flow velocity mapping by 35-fold |
---|---|
AbstractList | To evaluate the application of deep machine learning (DML) to 3D quantitative time-of-flight (qTOF) magnetic resonance angiography (MRA) to measure blood flow velocity within the intracranial arteries.
Intracranial qTOF MRA was acquired in 15 subjects at 3 T. Blood flow velocity quantitation with qTOF MRA was done using a non-DML computer-vision procedure, and using convolutional DML neural networks. 3D phase contrast (PC) MRA was used as the comparator. Using PC velocity measures as the output target and qTOF two-echo source image data as inputs, DML neural networks were trained to predict component blood flow velocities. Total velocities and peak intracranial arterial blood flow velocities were computed from component velocities.
Compared to non-DML image analysis, DML-based analysis of qTOF MRA image data improved agreement with PC for mean component velocity (intraclass correlation coefficient (ICC) = 0.966 versus 0.939), mean total velocity (ICC = 0.835 versus 0.723), and peak velocity (ICC = 0.816 versus 0.597), as well as narrowed the 95% Bland-Altman limits of agreement for mean component velocity ([−5.16, +4.31]cm/s versus [−6.86, +6.53]cm/s), mean total velocity ([−6.78,+3.59]cm/s versus [−9.39, +7.09]cm/s) and peak velocity ([−13.5,+10.2]cm/s versus [−21.3, +10.2]cm/s). Compared to non-DML analysis, DML image analysis reduced the root-mean-square deviation from PC velocity measures by 28%–36%, and shortened calculation times by 35-fold.
The application of DML image analysis to intracranial qTOF MRA for velocity quantitation markedly shortened calculation times, substantially improved the agreement of component, total, and peak arterial blood flow velocities, and provided excellent agreement of hemodynamic measures with respect to 3D PC.
•Deep machine learning (DML) can improve intracranial arterial velocimetry with qTOF MRA•Component, total, and peak flow velocity measures were improved with DML•DML-derived flow velocity measures showed excellent agreement with 3D phase contrast•DML reduced calculation times for intracranial arterial flow velocity mapping by 35-fold To evaluate the application of deep machine learning (DML) to 3D quantitative time-of-flight (qTOF) magnetic resonance angiography (MRA) to measure blood flow velocity within the intracranial arteries.PURPOSETo evaluate the application of deep machine learning (DML) to 3D quantitative time-of-flight (qTOF) magnetic resonance angiography (MRA) to measure blood flow velocity within the intracranial arteries.Intracranial qTOF MRA was acquired in 15 subjects at 3 T. Blood flow velocity quantitation with qTOF MRA was done using a non-DML computer-vision procedure, and using convolutional DML neural networks. 3D phase contrast (PC) MRA was used as the comparator. Using PC velocity measures as the output target and qTOF two-echo source image data as inputs, DML neural networks were trained to predict component blood flow velocities. Total velocities and peak intracranial arterial blood flow velocities were computed from component velocities.MATERIALS AND METHODSIntracranial qTOF MRA was acquired in 15 subjects at 3 T. Blood flow velocity quantitation with qTOF MRA was done using a non-DML computer-vision procedure, and using convolutional DML neural networks. 3D phase contrast (PC) MRA was used as the comparator. Using PC velocity measures as the output target and qTOF two-echo source image data as inputs, DML neural networks were trained to predict component blood flow velocities. Total velocities and peak intracranial arterial blood flow velocities were computed from component velocities.Compared to non-DML image analysis, DML-based analysis of qTOF MRA image data improved agreement with PC for mean component velocity (intraclass correlation coefficient (ICC) = 0.966 versus 0.939), mean total velocity (ICC = 0.835 versus 0.723), and peak velocity (ICC = 0.816 versus 0.597), as well as narrowed the 95% Bland-Altman limits of agreement for mean component velocity ([-5.16, +4.31]cm/s versus [-6.86, +6.53]cm/s), mean total velocity ([-6.78,+3.59]cm/s versus [-9.39, +7.09]cm/s) and peak velocity ([-13.5,+10.2]cm/s versus [-21.3, +10.2]cm/s). Compared to non-DML analysis, DML image analysis reduced the root-mean-square deviation from PC velocity measures by 28%-36%, and shortened calculation times by 35-fold.RESULTSCompared to non-DML image analysis, DML-based analysis of qTOF MRA image data improved agreement with PC for mean component velocity (intraclass correlation coefficient (ICC) = 0.966 versus 0.939), mean total velocity (ICC = 0.835 versus 0.723), and peak velocity (ICC = 0.816 versus 0.597), as well as narrowed the 95% Bland-Altman limits of agreement for mean component velocity ([-5.16, +4.31]cm/s versus [-6.86, +6.53]cm/s), mean total velocity ([-6.78,+3.59]cm/s versus [-9.39, +7.09]cm/s) and peak velocity ([-13.5,+10.2]cm/s versus [-21.3, +10.2]cm/s). Compared to non-DML analysis, DML image analysis reduced the root-mean-square deviation from PC velocity measures by 28%-36%, and shortened calculation times by 35-fold.The application of DML image analysis to intracranial qTOF MRA for velocity quantitation markedly shortened calculation times, substantially improved the agreement of component, total, and peak arterial blood flow velocities, and provided excellent agreement of hemodynamic measures with respect to 3D PC.CONCLUSIONThe application of DML image analysis to intracranial qTOF MRA for velocity quantitation markedly shortened calculation times, substantially improved the agreement of component, total, and peak arterial blood flow velocities, and provided excellent agreement of hemodynamic measures with respect to 3D PC. To evaluate the application of deep machine learning (DML) to 3D quantitative time-of-flight (qTOF) magnetic resonance angiography (MRA) to measure blood flow velocity within the intracranial arteries. Intracranial qTOF MRA was acquired in 15 subjects at 3 T. Blood flow velocity quantitation with qTOF MRA was done using a non-DML computer-vision procedure, and using convolutional DML neural networks. 3D phase contrast (PC) MRA was used as the comparator. Using PC velocity measures as the output target and qTOF two-echo source image data as inputs, DML neural networks were trained to predict component blood flow velocities. Total velocities and peak intracranial arterial blood flow velocities were computed from component velocities. Compared to non-DML image analysis, DML-based analysis of qTOF MRA image data improved agreement with PC for mean component velocity (intraclass correlation coefficient (ICC) = 0.966 versus 0.939), mean total velocity (ICC = 0.835 versus 0.723), and peak velocity (ICC = 0.816 versus 0.597), as well as narrowed the 95% Bland-Altman limits of agreement for mean component velocity ([-5.16, +4.31]cm/s versus [-6.86, +6.53]cm/s), mean total velocity ([-6.78,+3.59]cm/s versus [-9.39, +7.09]cm/s) and peak velocity ([-13.5,+10.2]cm/s versus [-21.3, +10.2]cm/s). Compared to non-DML analysis, DML image analysis reduced the root-mean-square deviation from PC velocity measures by 28%-36%, and shortened calculation times by 35-fold. The application of DML image analysis to intracranial qTOF MRA for velocity quantitation markedly shortened calculation times, substantially improved the agreement of component, total, and peak arterial blood flow velocities, and provided excellent agreement of hemodynamic measures with respect to 3D PC. |
Author | Huang, Rong Koktzoglou, Ioannis |
AuthorAffiliation | 1 Department of Radiology, NorthShore University HealthSystem, Evanston, IL, USA 2 University of Chicago Pritzker School of Medicine, Chicago, IL, USA |
AuthorAffiliation_xml | – name: 1 Department of Radiology, NorthShore University HealthSystem, Evanston, IL, USA – name: 2 University of Chicago Pritzker School of Medicine, Chicago, IL, USA |
Author_xml | – sequence: 1 givenname: Ioannis surname: Koktzoglou fullname: Koktzoglou, Ioannis email: ikoktzoglou@gmail.com organization: Department of Radiology, NorthShore University HealthSystem, Evanston, IL, USA – sequence: 2 givenname: Rong surname: Huang fullname: Huang, Rong organization: Department of Radiology, NorthShore University HealthSystem, Evanston, IL, USA |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36822451$$D View this record in MEDLINE/PubMed |
BookMark | eNqFkU9v1DAQxS1URLeFD8AF5cgli__E60QcEKqgrVSEhEDiZnmdye4sjp06zqL99jhsqaCHchrLfr8343ln5MQHD4S8ZHTJKFu92S37iEtOuVhSvqRUPiELVitRyrqpTsiCKkFLxeX3U3I2jjuaFVzIZ-RUrGrOK8kWZLr2KRobjUfjChMTxPnQufCz2IMLFtOh6M0woN8U6IvbyfiEySTcQ5GwhzJ0Zedws03Fpy-F8RsMm2iG7aGYxplpAYZsYLfooXBgos-3z8nTzrgRXtzVc_Lt44evF1flzefL64v3N6WVlKfSMN7IyoJsJe2q1VxUXVVrUdVtVZtOdh3thGpaWldWiDVthBJsxeRaNqqpGnFO3h19h2ndQ2th_qzTQ8TexIMOBvW_Lx63ehP2mtFsqRjNDq_vHGK4nWBMusfRgnPGQ5hGzVWdpZSrWfrq72b3Xf4sOwvYUWBjGMcI3b2EUT0Hqnc6B6rnQDXlOseVGfWAsb-3H-Z50T1Kvj2SkBe8R4h6tAjeQosRbNJtwEfp5gFtHXq0xv2Aw3_YX7tTz6I |
CitedBy_id | crossref_primary_10_1002_jmri_29395 crossref_primary_10_1002_jmri_29398 crossref_primary_10_1002_jmri_29701 |
Cites_doi | 10.1002/mrm.1910090117 10.1016/0090-3019(94)90394-8 10.1111/j.1552-6569.2012.00711.x 10.1148/radiol.2018171820 10.1097/00004728-198609000-00001 10.1159/000506924 10.1007/s002340050645 10.1148/radiology.193.1.8090890 10.1148/radiology.154.2.3966130 10.1179/016164106X130380 10.1002/mrm.1910170215 10.1148/radiology.183.2.1561338 10.1161/STROKEAHA.113.003133 10.1002/mrm.28969 10.1126/science.aaa8415 10.2466/pr0.1966.19.1.3 10.1186/s40537-019-0192-5 10.2463/mrms.mp.2016-0060 10.1097/WCO.0000000000000341 10.1016/0730-725X(82)90170-9 10.1037/1040-3590.6.4.284 10.1007/s12194-017-0406-5 10.1002/mrm.29060 10.1002/mrm.21763 10.2214/ajr.155.1.2112840 10.3233/JAD-190977 10.1002/jmri.26288 10.1152/physrev.1959.39.2.183 10.1002/jmri.20828 |
ContentType | Journal Article |
Copyright | 2023 Elsevier Inc. Copyright © 2023 Elsevier Inc. All rights reserved. |
Copyright_xml | – notice: 2023 Elsevier Inc. – notice: Copyright © 2023 Elsevier Inc. All rights reserved. |
DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 5PM |
DOI | 10.1016/j.mri.2023.02.005 |
DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic PubMed Central (Full Participant titles) |
DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
DatabaseTitleList | MEDLINE - Academic MEDLINE |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine |
EISSN | 1873-5894 |
EndPage | 17 |
ExternalDocumentID | PMC10084710 36822451 10_1016_j_mri_2023_02_005 S0730725X23000395 |
Genre | Journal Article Research Support, N.I.H., Extramural |
GrantInformation_xml | – fundername: NIBIB NIH HHS grantid: R01 EB027475 |
GroupedDBID | --- --K --M .1- .FO .GJ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 29M 3O- 4.4 457 4CK 4G. 53G 5GY 5RE 5VS 7-5 71M 8P~ 9JM 9JN AABNK AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYWO ABBQC ABDPE ABFNM ABGSF ABJNI ABMAC ABMZM ABNEU ABOCM ABUDA ABWVN ABXDB ACDAQ ACFVG ACGFS ACIEU ACIUM ACNNM ACRLP ACRPL ACVFH ADBBV ADCNI ADEZE ADMUD ADNMO ADUVX AEBSH AEHWI AEIPS AEKER AENEX AEUPX AEVXI AFFNX AFJKZ AFPUW AFRHN AFTJW AFXIZ AGCQF AGHFR AGQPQ AGRDE AGUBO AGYEJ AHHHB AIEXJ AIGII AIIUN AIKHN AITUG AIVDX AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX APXCP ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV CS3 EBS EFJIC EFKBS EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HEI HMK HMO HVGLF HZ~ IHE J1W KOM M29 M41 MO0 N9A O-L O9- OAUVE OGIMB OI~ OU0 OZT P-8 P-9 P2P PC. Q38 R2- ROL RPZ SAE SCC SDF SDG SDP SEL SES SEW SPC SPCBC SSH SSQ SSU SSZ T5K WUQ XPP Z5R ZGI ZMT ~G- ~S- AACTN AAIAV ABLVK ABYKQ AFCTW AFKWA AJBFU AJOXV AMFUW DOVZS EFLBG G8K LCYCR RIG AAYXX AGRNS CITATION CGR CUY CVF ECM EIF NPM 7X8 ACLOT ~HD 5PM |
ID | FETCH-LOGICAL-c502t-a12954ce5d50f465d507844b348d48af5ff0f379d084c33b093731615b5979493 |
IEDL.DBID | AIKHN |
ISSN | 0730-725X 1873-5894 |
IngestDate | Thu Aug 21 18:32:40 EDT 2025 Sat Sep 27 18:19:01 EDT 2025 Mon Jul 21 05:14:23 EDT 2025 Thu Apr 24 23:11:09 EDT 2025 Tue Jul 01 01:55:28 EDT 2025 Fri Feb 23 02:40:32 EST 2024 Tue Aug 26 16:33:45 EDT 2025 |
IsDoiOpenAccess | false |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Deep learning TOF Quantitative MRI MRA |
Language | English |
License | Copyright © 2023 Elsevier Inc. All rights reserved. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c502t-a12954ce5d50f465d507844b348d48af5ff0f379d084c33b093731615b5979493 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 Ioannis Koktzoglou: Conceptualization, Methodology, Software, Formal Analysis, Investigation, Writing – Original Draft, Writing – Review and Editing, Funding Acquisition. Rong Huang: Conceptualization, Methodology, Software, Formal Analysis, Writing – Review and Editing. |
OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/10084710 |
PMID | 36822451 |
PQID | 2780080270 |
PQPubID | 23479 |
PageCount | 8 |
ParticipantIDs | pubmedcentral_primary_oai_pubmedcentral_nih_gov_10084710 proquest_miscellaneous_2780080270 pubmed_primary_36822451 crossref_primary_10_1016_j_mri_2023_02_005 crossref_citationtrail_10_1016_j_mri_2023_02_005 elsevier_sciencedirect_doi_10_1016_j_mri_2023_02_005 elsevier_clinicalkey_doi_10_1016_j_mri_2023_02_005 |
ProviderPackageCode | CITATION AAYXX |
PublicationCentury | 2000 |
PublicationDate | 2023-07-01 |
PublicationDateYYYYMMDD | 2023-07-01 |
PublicationDate_xml | – month: 07 year: 2023 text: 2023-07-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Netherlands |
PublicationPlace_xml | – name: Netherlands |
PublicationTitle | Magnetic resonance imaging |
PublicationTitleAlternate | Magn Reson Imaging |
PublicationYear | 2023 |
Publisher | Elsevier Inc |
Publisher_xml | – name: Elsevier Inc |
References | Sailer, Wagemans, Nelemans, de Graaf, van Zwam (bb0025) 2014; 45 Edelman, Koktzoglou (bb0030) 2019; 49 Seber, Lee (bb0175) 2003 Dumoulin, Souza, Walker, Wagle (bb0070) 1989; 9 Korogi, Takahashi, Mabuchi, Miki, Shiga, Watabe (bb0020) 1994; 193 Suzuki (bb0185) 2017; 10 Yamashita, Isoda, Hirano, Takeda, Inagawa, Takehara (bb0095) 2007; 25 Cicchetti (bb0180) 1994; 6 Araki, Kohmura, Tsukaguchi (bb0105) 1994; 15 Enzmann, Ross, Marks, Pelc (bb0085) 1994; 15 Koktzoglou, Huang, Edelman (bb0125) 2022; 87 Ikawa, Sumida, Uozumi, Kuwabara, Kiya, Kurisu (bb0110) 1994; 42 Doepp, Valdueza, Schreiber (bb0035) 2006; 28 Altman, Bland (bb0170) 1983; 32 Marshall, Pavol, Cheung, Asllani, Lazar (bb0045) 2020; 10 Ross, Pelc, Enzmann (bb0080) 1993; 14 Choy, Khalilzadeh, Michalski, Do, Samir, Pianykh (bb0140) 2018; 288 Lassen (bb0005) 1959; 39 Johnson, Lum, Turski, Block, Mistretta, Wieben (bb0100) 2008; 60 Moran (bb0055) 1982; 1 Schnell, Wu, Ansari (bb0120) 2016; 29 Gu, Korosec, Block, Fain, Turk, Lum (bb0090) 2005; 26 Tegeler, Crutchfield, Katsnelson, Kim, Tang, Passmore Griffin (bb0040) 2013; 23 Gulli, Pal (bb0155) 2017 Klein (bb0145) 2021 Bartko (bb0165) 1966; 19 Fukuyama, Isoda, Morita, Mori, Watanabe, Ishiguro (bb0190) 2017; 16 Thomas, Tarumi, Sheng, Tseng, Womack, Cullum (bb0050) 2020; 75 Kim, Eisenmenger, Turski, Johnson (bb0130) 2022; 87 Johnson, Khoshgoftaar (bb0160) 2019; 6 Pernicone, Siebert, Potchen, Pera, Dumoulin, Souza (bb0075) 1990; 155 Nayler, Firmin, Longmore (bb0065) 1986; 10 Oelerich, Lentschig, Zunker, Reimer, Rummeny, Schuierer (bb0115) 1998; 40 Jordan, Mitchell (bb0135) 2015; 349 Moran, Moran, Karstaedt (bb0060) 1985; 154 Parker, Yuan, Blatter (bb0010) 1991; 17 Blatter, Parker, Ahn, Bahr, Robison, Schwartz (bb0015) 1992; 183 Ronneberger, Fischer, Brox (bb0150) 2015 Oelerich (10.1016/j.mri.2023.02.005_bb0115) 1998; 40 Johnson (10.1016/j.mri.2023.02.005_bb0100) 2008; 60 Dumoulin (10.1016/j.mri.2023.02.005_bb0070) 1989; 9 Suzuki (10.1016/j.mri.2023.02.005_bb0185) 2017; 10 Edelman (10.1016/j.mri.2023.02.005_bb0030) 2019; 49 Ikawa (10.1016/j.mri.2023.02.005_bb0110) 1994; 42 Tegeler (10.1016/j.mri.2023.02.005_bb0040) 2013; 23 Gu (10.1016/j.mri.2023.02.005_bb0090) 2005; 26 Johnson (10.1016/j.mri.2023.02.005_bb0160) 2019; 6 Sailer (10.1016/j.mri.2023.02.005_bb0025) 2014; 45 Cicchetti (10.1016/j.mri.2023.02.005_bb0180) 1994; 6 Yamashita (10.1016/j.mri.2023.02.005_bb0095) 2007; 25 Fukuyama (10.1016/j.mri.2023.02.005_bb0190) 2017; 16 Lassen (10.1016/j.mri.2023.02.005_bb0005) 1959; 39 Araki (10.1016/j.mri.2023.02.005_bb0105) 1994; 15 Ronneberger (10.1016/j.mri.2023.02.005_bb0150) 2015 Thomas (10.1016/j.mri.2023.02.005_bb0050) 2020; 75 Ross (10.1016/j.mri.2023.02.005_bb0080) 1993; 14 Jordan (10.1016/j.mri.2023.02.005_bb0135) 2015; 349 Kim (10.1016/j.mri.2023.02.005_bb0130) 2022; 87 Doepp (10.1016/j.mri.2023.02.005_bb0035) 2006; 28 Schnell (10.1016/j.mri.2023.02.005_bb0120) 2016; 29 Bartko (10.1016/j.mri.2023.02.005_bb0165) 1966; 19 Moran (10.1016/j.mri.2023.02.005_bb0055) 1982; 1 Pernicone (10.1016/j.mri.2023.02.005_bb0075) 1990; 155 Klein (10.1016/j.mri.2023.02.005_bb0145) 2021 Choy (10.1016/j.mri.2023.02.005_bb0140) 2018; 288 Korogi (10.1016/j.mri.2023.02.005_bb0020) 1994; 193 Gulli (10.1016/j.mri.2023.02.005_bb0155) 2017 Enzmann (10.1016/j.mri.2023.02.005_bb0085) 1994; 15 Moran (10.1016/j.mri.2023.02.005_bb0060) 1985; 154 Nayler (10.1016/j.mri.2023.02.005_bb0065) 1986; 10 Parker (10.1016/j.mri.2023.02.005_bb0010) 1991; 17 Altman (10.1016/j.mri.2023.02.005_bb0170) 1983; 32 Blatter (10.1016/j.mri.2023.02.005_bb0015) 1992; 183 Marshall (10.1016/j.mri.2023.02.005_bb0045) 2020; 10 Koktzoglou (10.1016/j.mri.2023.02.005_bb0125) 2022; 87 Seber (10.1016/j.mri.2023.02.005_bb0175) 2003 |
References_xml | – volume: 1 start-page: 197 year: 1982 end-page: 203 ident: bb0055 article-title: A flow velocity zeugmatographic interlace for NMR imaging in humans publication-title: Magn Reson Imaging – volume: 16 start-page: 311 year: 2017 end-page: 316 ident: bb0190 article-title: Influence of spatial resolution in three-dimensional cine phase contrast magnetic resonance imaging on the accuracy of hemodynamic analysis publication-title: Magn Reson Med Sci – volume: 193 start-page: 187 year: 1994 end-page: 193 ident: bb0020 article-title: Intracranial vascular stenosis and occlusion: diagnostic accuracy of three-dimensional, Fourier transform, time-of-flight MR angiography publication-title: Radiology – volume: 39 start-page: 183 year: 1959 end-page: 238 ident: bb0005 article-title: Cerebral blood flow and oxygen consumption in man publication-title: Physiol Rev – volume: 6 start-page: 27 year: 2019 ident: bb0160 article-title: Survey on deep learning with class imbalance publication-title: J Big Data – year: 2015 ident: bb0150 article-title: U-Net: Convolutional networks for biomedical image segmentation. ArXiv:150504597 [Cs] – volume: 9 start-page: 139 year: 1989 end-page: 149 ident: bb0070 article-title: Three-dimensional phase contrast angiography publication-title: Magn Reson Med – volume: 32 start-page: 307 year: 1983 end-page: 317 ident: bb0170 article-title: Measurement in medicine: the analysis of method comparison studies publication-title: J Royal Stat Soc Series D (The Statistician) – volume: 28 start-page: 645 year: 2006 end-page: 649 ident: bb0035 article-title: Transcranial and extracranial ultrasound assessment of cerebral hemodynamics in vascular and Alzheimer’s dementia publication-title: Neurol Res – volume: 19 start-page: 3 year: 1966 end-page: 11 ident: bb0165 article-title: The Intraclass correlation coefficient as a measure of reliability publication-title: Psychol Rep – volume: 6 start-page: 284 year: 1994 end-page: 290 ident: bb0180 article-title: Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology publication-title: Psychol Assess – year: 2021 ident: bb0145 article-title: PyElastix - Python wrapper for the Elastix nonrigid registration toolkit – volume: 288 start-page: 318 year: 2018 end-page: 328 ident: bb0140 article-title: Current applications and future impact of machine learning in radiology publication-title: Radiology – year: 2017 ident: bb0155 article-title: Deep learning with Keras – year: 2003 ident: bb0175 article-title: Linear regression analysis – volume: 45 start-page: 119 year: 2014 end-page: 126 ident: bb0025 article-title: Diagnosing intracranial aneurysms with MR angiography: systematic review and meta-analysis publication-title: Stroke – volume: 26 start-page: 743 year: 2005 end-page: 749 ident: bb0090 article-title: PC VIPR: a high-speed 3D phase-contrast method for flow quantification and high-resolution angiography publication-title: AJNR Am J Neuroradiol – volume: 60 start-page: 1329 year: 2008 end-page: 1336 ident: bb0100 article-title: Improved 3D phase contrast MRI with off-resonance corrected dual echo VIPR publication-title: Magn Reson Med – volume: 17 start-page: 434 year: 1991 end-page: 451 ident: bb0010 article-title: MR angiography by multiple thin slab 3D acquisition publication-title: Magn Reson Med – volume: 10 start-page: 257 year: 2017 end-page: 273 ident: bb0185 article-title: Overview of deep learning in medical imaging publication-title: Radiol Phys Technol – volume: 155 start-page: 167 year: 1990 end-page: 176 ident: bb0075 article-title: Three-dimensional phase-contrast MR angiography in the head and neck: preliminary report publication-title: AJR Am J Roentgenol – volume: 349 start-page: 255 year: 2015 end-page: 260 ident: bb0135 article-title: Machine learning: trends, perspectives, and prospects publication-title: Science – volume: 42 start-page: 287 year: 1994 end-page: 292 ident: bb0110 article-title: Comparison of three-dimensional phase-contrast magnetic resonance angiography with three-dimensional time-of-flight magnetic resonance angiography in cerebral aneurysms publication-title: Surg Neurol – volume: 10 start-page: 21 year: 2020 end-page: 27 ident: bb0045 article-title: Cognitive impairment correlates linearly with mean flow velocity by transcranial Doppler below a definable threshold publication-title: Cerebrovasc Dis Extra – volume: 14 start-page: 19 year: 1993 end-page: 25 ident: bb0080 article-title: Qualitative phase contrast MRA in the normal and abnormal circle of Willis publication-title: AJNR Am J Neuroradiol – volume: 40 start-page: 567 year: 1998 end-page: 573 ident: bb0115 article-title: Intracranial vascular stenosis and occlusion: comparison of 3D time-of-flight and 3D phase-contrast MR angiography publication-title: Neuroradiology – volume: 183 start-page: 379 year: 1992 end-page: 389 ident: bb0015 article-title: Cerebral MR angiography multiple overlapping thin slab acquisition. Part II Early clinical experience publication-title: Radiology – volume: 49 start-page: 355 year: 2019 end-page: 373 ident: bb0030 article-title: Noncontrast MR angiography: an update publication-title: J Magn Reson Imaging – volume: 15 start-page: 1618 year: 1994 end-page: 1623 ident: bb0105 article-title: A pitfall in detection of intracranial unruptured aneurysms on three-dimensional phase-contrast MR angiography publication-title: AJNR Am J Neuroradiol – volume: 29 start-page: 419 year: 2016 end-page: 428 ident: bb0120 article-title: Four-dimensional MRI flow examinations in cerebral and extracerebral vessels – ready for clinical routine? publication-title: Curr Opin Neurol – volume: 10 start-page: 715 year: 1986 end-page: 722 ident: bb0065 article-title: Blood flow imaging by cine magnetic resonance publication-title: J Comput Assist Tomogr – volume: 25 start-page: 473 year: 2007 end-page: 478 ident: bb0095 article-title: Visualization of hemodynamics in intracranial arteries using time-resolved three-dimensional phase-contrast MRI publication-title: J Magn Reson Imaging – volume: 87 start-page: 1401 year: 2022 end-page: 1417 ident: bb0130 article-title: Simultaneous 3D-TOF angiography and 4D-flow MRI with enhanced flow signal using multiple overlapping thin slab acquisition and magnetization transfer publication-title: Magn Reson Med – volume: 15 start-page: 123 year: 1994 end-page: 129 ident: bb0085 article-title: Blood flow in major cerebral arteries measured by phase-contrast cine MR publication-title: AJNR Am J Neuroradiol – volume: 154 start-page: 433 year: 1985 end-page: 441 ident: bb0060 article-title: Verification and evaluation of internal flow and motion. True magnetic resonance imaging by the phase gradient modulation method publication-title: Radiology – volume: 87 start-page: 150 year: 2022 end-page: 162 ident: bb0125 article-title: Quantitative time-of-flight MR angiography for simultaneous luminal and hemodynamic evaluation of the intracranial arteries publication-title: Magn Reson Med – volume: 23 start-page: 466 year: 2013 end-page: 472 ident: bb0040 article-title: Transcranial Doppler velocities in a large, healthy population publication-title: J Neuroimaging – volume: 75 start-page: 617 year: 2020 end-page: 631 ident: bb0050 article-title: Brain perfusion change in patients with mild cognitive impairment after 12 months of aerobic exercise training publication-title: J Alzheimers Dis – volume: 14 start-page: 19 year: 1993 ident: 10.1016/j.mri.2023.02.005_bb0080 article-title: Qualitative phase contrast MRA in the normal and abnormal circle of Willis publication-title: AJNR Am J Neuroradiol – volume: 9 start-page: 139 year: 1989 ident: 10.1016/j.mri.2023.02.005_bb0070 article-title: Three-dimensional phase contrast angiography publication-title: Magn Reson Med doi: 10.1002/mrm.1910090117 – volume: 42 start-page: 287 year: 1994 ident: 10.1016/j.mri.2023.02.005_bb0110 article-title: Comparison of three-dimensional phase-contrast magnetic resonance angiography with three-dimensional time-of-flight magnetic resonance angiography in cerebral aneurysms publication-title: Surg Neurol doi: 10.1016/0090-3019(94)90394-8 – volume: 23 start-page: 466 year: 2013 ident: 10.1016/j.mri.2023.02.005_bb0040 article-title: Transcranial Doppler velocities in a large, healthy population publication-title: J Neuroimaging doi: 10.1111/j.1552-6569.2012.00711.x – volume: 288 start-page: 318 year: 2018 ident: 10.1016/j.mri.2023.02.005_bb0140 article-title: Current applications and future impact of machine learning in radiology publication-title: Radiology doi: 10.1148/radiol.2018171820 – volume: 10 start-page: 715 year: 1986 ident: 10.1016/j.mri.2023.02.005_bb0065 article-title: Blood flow imaging by cine magnetic resonance publication-title: J Comput Assist Tomogr doi: 10.1097/00004728-198609000-00001 – volume: 10 start-page: 21 year: 2020 ident: 10.1016/j.mri.2023.02.005_bb0045 article-title: Cognitive impairment correlates linearly with mean flow velocity by transcranial Doppler below a definable threshold publication-title: Cerebrovasc Dis Extra doi: 10.1159/000506924 – volume: 40 start-page: 567 year: 1998 ident: 10.1016/j.mri.2023.02.005_bb0115 article-title: Intracranial vascular stenosis and occlusion: comparison of 3D time-of-flight and 3D phase-contrast MR angiography publication-title: Neuroradiology doi: 10.1007/s002340050645 – volume: 193 start-page: 187 year: 1994 ident: 10.1016/j.mri.2023.02.005_bb0020 article-title: Intracranial vascular stenosis and occlusion: diagnostic accuracy of three-dimensional, Fourier transform, time-of-flight MR angiography publication-title: Radiology doi: 10.1148/radiology.193.1.8090890 – volume: 32 start-page: 307 year: 1983 ident: 10.1016/j.mri.2023.02.005_bb0170 article-title: Measurement in medicine: the analysis of method comparison studies publication-title: J Royal Stat Soc Series D (The Statistician) – volume: 154 start-page: 433 year: 1985 ident: 10.1016/j.mri.2023.02.005_bb0060 article-title: Verification and evaluation of internal flow and motion. True magnetic resonance imaging by the phase gradient modulation method publication-title: Radiology doi: 10.1148/radiology.154.2.3966130 – volume: 28 start-page: 645 year: 2006 ident: 10.1016/j.mri.2023.02.005_bb0035 article-title: Transcranial and extracranial ultrasound assessment of cerebral hemodynamics in vascular and Alzheimer’s dementia publication-title: Neurol Res doi: 10.1179/016164106X130380 – volume: 17 start-page: 434 year: 1991 ident: 10.1016/j.mri.2023.02.005_bb0010 article-title: MR angiography by multiple thin slab 3D acquisition publication-title: Magn Reson Med doi: 10.1002/mrm.1910170215 – volume: 183 start-page: 379 year: 1992 ident: 10.1016/j.mri.2023.02.005_bb0015 article-title: Cerebral MR angiography multiple overlapping thin slab acquisition. Part II Early clinical experience publication-title: Radiology doi: 10.1148/radiology.183.2.1561338 – volume: 45 start-page: 119 year: 2014 ident: 10.1016/j.mri.2023.02.005_bb0025 article-title: Diagnosing intracranial aneurysms with MR angiography: systematic review and meta-analysis publication-title: Stroke doi: 10.1161/STROKEAHA.113.003133 – volume: 87 start-page: 150 year: 2022 ident: 10.1016/j.mri.2023.02.005_bb0125 article-title: Quantitative time-of-flight MR angiography for simultaneous luminal and hemodynamic evaluation of the intracranial arteries publication-title: Magn Reson Med doi: 10.1002/mrm.28969 – volume: 349 start-page: 255 year: 2015 ident: 10.1016/j.mri.2023.02.005_bb0135 article-title: Machine learning: trends, perspectives, and prospects publication-title: Science doi: 10.1126/science.aaa8415 – volume: 19 start-page: 3 year: 1966 ident: 10.1016/j.mri.2023.02.005_bb0165 article-title: The Intraclass correlation coefficient as a measure of reliability publication-title: Psychol Rep doi: 10.2466/pr0.1966.19.1.3 – volume: 6 start-page: 27 year: 2019 ident: 10.1016/j.mri.2023.02.005_bb0160 article-title: Survey on deep learning with class imbalance publication-title: J Big Data doi: 10.1186/s40537-019-0192-5 – volume: 26 start-page: 743 year: 2005 ident: 10.1016/j.mri.2023.02.005_bb0090 article-title: PC VIPR: a high-speed 3D phase-contrast method for flow quantification and high-resolution angiography publication-title: AJNR Am J Neuroradiol – year: 2003 ident: 10.1016/j.mri.2023.02.005_bb0175 – volume: 16 start-page: 311 year: 2017 ident: 10.1016/j.mri.2023.02.005_bb0190 article-title: Influence of spatial resolution in three-dimensional cine phase contrast magnetic resonance imaging on the accuracy of hemodynamic analysis publication-title: Magn Reson Med Sci doi: 10.2463/mrms.mp.2016-0060 – volume: 29 start-page: 419 year: 2016 ident: 10.1016/j.mri.2023.02.005_bb0120 article-title: Four-dimensional MRI flow examinations in cerebral and extracerebral vessels – ready for clinical routine? publication-title: Curr Opin Neurol doi: 10.1097/WCO.0000000000000341 – year: 2017 ident: 10.1016/j.mri.2023.02.005_bb0155 – volume: 1 start-page: 197 year: 1982 ident: 10.1016/j.mri.2023.02.005_bb0055 article-title: A flow velocity zeugmatographic interlace for NMR imaging in humans publication-title: Magn Reson Imaging doi: 10.1016/0730-725X(82)90170-9 – volume: 6 start-page: 284 year: 1994 ident: 10.1016/j.mri.2023.02.005_bb0180 article-title: Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology publication-title: Psychol Assess doi: 10.1037/1040-3590.6.4.284 – volume: 10 start-page: 257 year: 2017 ident: 10.1016/j.mri.2023.02.005_bb0185 article-title: Overview of deep learning in medical imaging publication-title: Radiol Phys Technol doi: 10.1007/s12194-017-0406-5 – volume: 87 start-page: 1401 year: 2022 ident: 10.1016/j.mri.2023.02.005_bb0130 article-title: Simultaneous 3D-TOF angiography and 4D-flow MRI with enhanced flow signal using multiple overlapping thin slab acquisition and magnetization transfer publication-title: Magn Reson Med doi: 10.1002/mrm.29060 – volume: 60 start-page: 1329 year: 2008 ident: 10.1016/j.mri.2023.02.005_bb0100 article-title: Improved 3D phase contrast MRI with off-resonance corrected dual echo VIPR publication-title: Magn Reson Med doi: 10.1002/mrm.21763 – volume: 155 start-page: 167 year: 1990 ident: 10.1016/j.mri.2023.02.005_bb0075 article-title: Three-dimensional phase-contrast MR angiography in the head and neck: preliminary report publication-title: AJR Am J Roentgenol doi: 10.2214/ajr.155.1.2112840 – year: 2015 ident: 10.1016/j.mri.2023.02.005_bb0150 – volume: 15 start-page: 1618 year: 1994 ident: 10.1016/j.mri.2023.02.005_bb0105 article-title: A pitfall in detection of intracranial unruptured aneurysms on three-dimensional phase-contrast MR angiography publication-title: AJNR Am J Neuroradiol – volume: 75 start-page: 617 year: 2020 ident: 10.1016/j.mri.2023.02.005_bb0050 article-title: Brain perfusion change in patients with mild cognitive impairment after 12 months of aerobic exercise training publication-title: J Alzheimers Dis doi: 10.3233/JAD-190977 – volume: 49 start-page: 355 year: 2019 ident: 10.1016/j.mri.2023.02.005_bb0030 article-title: Noncontrast MR angiography: an update publication-title: J Magn Reson Imaging doi: 10.1002/jmri.26288 – volume: 15 start-page: 123 year: 1994 ident: 10.1016/j.mri.2023.02.005_bb0085 article-title: Blood flow in major cerebral arteries measured by phase-contrast cine MR publication-title: AJNR Am J Neuroradiol – volume: 39 start-page: 183 year: 1959 ident: 10.1016/j.mri.2023.02.005_bb0005 article-title: Cerebral blood flow and oxygen consumption in man publication-title: Physiol Rev doi: 10.1152/physrev.1959.39.2.183 – year: 2021 ident: 10.1016/j.mri.2023.02.005_bb0145 – volume: 25 start-page: 473 year: 2007 ident: 10.1016/j.mri.2023.02.005_bb0095 article-title: Visualization of hemodynamics in intracranial arteries using time-resolved three-dimensional phase-contrast MRI publication-title: J Magn Reson Imaging doi: 10.1002/jmri.20828 |
SSID | ssj0005235 |
Score | 2.406164 |
Snippet | To evaluate the application of deep machine learning (DML) to 3D quantitative time-of-flight (qTOF) magnetic resonance angiography (MRA) to measure blood flow... |
SourceID | pubmedcentral proquest pubmed crossref elsevier |
SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
StartPage | 10 |
SubjectTerms | Blood Flow Velocity Cerebral Arteries - diagnostic imaging Deep learning Hemodynamics Humans Imaging, Three-Dimensional - methods Machine Learning Magnetic Resonance Angiography - methods Magnetic Resonance Imaging - methods MRA MRI Quantitative TOF |
Title | Intracranial arterial flow velocity mapping in quantitative time-of-flight MR angiography using deep machine learning |
URI | https://www.clinicalkey.com/#!/content/1-s2.0-S0730725X23000395 https://dx.doi.org/10.1016/j.mri.2023.02.005 https://www.ncbi.nlm.nih.gov/pubmed/36822451 https://www.proquest.com/docview/2780080270 https://pubmed.ncbi.nlm.nih.gov/PMC10084710 |
Volume | 100 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1La9tAEB7ygNJL6btO2rCFngobr_ZhSccQGpwW59A2kNsiaXddFUd2E5vc8tszI61M3NIUerJs7ZhFM5r5lvlmBuCDMIXyQQtuch24Tn3Cc-ckl74IRsnSJ4EyupOz0fhcf74wF1tw3NfCEK0y-v7Op7feOv4yjE9zuKjr4TcyzlTiYUu1FaZmG3YlRns8ge0enX4Zn91jenRzNnE9J4E-udnSvC6v6kMaId517jR_C09_ws_fWZT3wtLJU3gS8SQ76rb8DLZ88xweTWLG_AWsTkmswoiEhsZaAiddhNn8hhFdqEIUzi4L6tIwZXXDfq2Kpq07Qy_IaPA8nwceZnSEZ5OvrGimdWxyzYgyP2XO-wX-AVEyPYszKKYv4fzk0_fjMY-jFnhlhFzyIqF8X-WNMyLoEX2kmdal0pnTGaotBBFUmjuR6UqpUiCqUQQWSzyQ5DpXr2CnmTf-DTCRhmyEoBEDndBOmaJEhOYQF7kqyCrVAxD9E7ZV7ENO4zBmtiec_bSoFEtKsUJaVMoAPq5FFl0TjocWy15ttq8uRX9oMUQ8JKTXQhvm9y-x971dWHwtKddSNH6-urYyzdoy5lQM4HVnJ-utqxFRd00ygGzDgtYLqOX35p2m_tG2_qZWTAgnxN7_7XcfHtO3jm78FnaWVyv_DkHVsjyA7cPb5CC-OndVCSGD |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9NAEB6VVIJeEG_Cc5E4IS3Z7CO2j1VFldAmB2il3la2dzcYpU5aEvH3mbHXUQOiSJwc2TvRyjOe-VbzzQzAe2Fy5YMW3GQ6cJ34Ic-ck1z6PBglCz8MlNGdzkbjc_35wlzswVFXC0O0yuj7W5_eeOt4ZxDf5mBVVYOvZJyJxMOWaipMzR3Y1wZ9cg_2Dycn49kNpkc7ZxPXcxLokpsNzevyuvpII8Tbzp3mb-HpT_j5O4vyRlg6fgD3I55kh-2WH8Kerx_B3WnMmD-GzYTESoxIaGisIXDSj7BY_mREFyoRhbPLnLo0zFlVs6tNXjd1Z-gFGQ2e58vAw4KO8Gz6heX1vIpNrhlR5ufMeb_CPyBKpmdxBsX8CZwffzo7GvM4aoGXRsg1z4eU7yu9cUYEPaJLkmpdKJ06naLaQhBBJZkTqS6VKgSiGkVgscADSaYz9RR69bL2z4GJJKQjBI0Y6IR2yuQFIjSHuMiVQZaJ7oPo3rAtYx9yGoexsB3h7LtFpVhSihXSolL68GErsmqbcNy2WHZqs111KfpDiyHiNiG9Fdoxv3-JvevswuJnSbmWvPbLzQ8rk7QpY05EH561drLduhoRddcM-5DuWNB2AbX83n1SV9-a1t_UignhhHjxf_t9C_fGZ9NTezqZnbyEA3rSUo9fQW99vfGvEWCtizfxA_oFI1AjaQ |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Intracranial+arterial+flow+velocity+mapping+in+quantitative+time-of-flight+MR+angiography+using+deep+machine+learning&rft.jtitle=Magnetic+resonance+imaging&rft.au=Koktzoglou%2C+Ioannis&rft.au=Huang%2C+Rong&rft.date=2023-07-01&rft.issn=1873-5894&rft.eissn=1873-5894&rft.volume=100&rft.spage=10&rft_id=info:doi/10.1016%2Fj.mri.2023.02.005&rft.externalDBID=NO_FULL_TEXT |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0730-725X&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0730-725X&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0730-725X&client=summon |