Improved unsupervised physics‐informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients

Purpose Earlier work showed that IVIM‐NETorig, an unsupervised physics‐informed deep neural network, was faster and more accurate than other state‐of‐the‐art intravoxel‐incoherent motion (IVIM) fitting approaches to diffusion‐weighted imaging (DWI). This study presents a substantially improved versi...

Full description

Saved in:
Bibliographic Details
Published in:Magnetic resonance in medicine Vol. 86; no. 4; pp. 2250 - 2265
Main Authors: Kaandorp, Misha P. T., Barbieri, Sebastiano, Klaassen, Remy, Laarhoven, Hanneke W. M., Crezee, Hans, While, Peter T., Nederveen, Aart J., Gurney‐Champion, Oliver J.
Format: Journal Article
Language:English
Published: United States Wiley Subscription Services, Inc 01.10.2021
John Wiley and Sons Inc
Subjects:
ISSN:0740-3194, 1522-2594, 1522-2594
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Purpose Earlier work showed that IVIM‐NETorig, an unsupervised physics‐informed deep neural network, was faster and more accurate than other state‐of‐the‐art intravoxel‐incoherent motion (IVIM) fitting approaches to diffusion‐weighted imaging (DWI). This study presents a substantially improved version, IVIM‐NEToptim, and characterizes its superior performance in pancreatic cancer patients. Method In simulations (signal‐to‐noise ratio [SNR] = 20), the accuracy, independence, and consistency of IVIM‐NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, number of hidden layers, dropout, batch normalization, learning rate), by calculating the normalized root‐mean‐square error (NRMSE), Spearman’s ρ, and the coefficient of variation (CVNET), respectively. The best performing network, IVIM‐NEToptim was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM‐NEToptim’s performance was evaluated in an independent dataset of 23 patients with pancreatic ductal adenocarcinoma. Fourteen of the patients received no treatment between two repeated scan sessions and nine received chemoradiotherapy between the repeated sessions. Intersession within‐subject standard deviations (wSD) and treatment‐induced changes were assessed. Results In simulations (SNR = 20), IVIM‐NEToptim outperformed IVIM‐NETorig in accuracy (NRMSE(D) = 0.177 vs 0.196; NMRSE(f) = 0.220 vs 0.267; NMRSE(D*) = 0.386 vs 0.393), independence (ρ(D*, f) = 0.22 vs 0.74), and consistency (CVNET(D) = 0.013 vs 0.104; CVNET(f) = 0.020 vs 0.054; CVNET(D*) = 0.036 vs 0.110). IVIM‐NEToptim showed superior performance to the LS and Bayesian approaches at SNRs < 50. In vivo, IVIM‐NEToptim showed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM‐NEToptim detected the most individual patients with significant parameter changes compared to day‐to‐day variations. Conclusion IVIM‐NEToptim is recommended for accurate, informative, and consistent IVIM fitting to DWI data.
AbstractList Earlier work showed that IVIM-NET , an unsupervised physics-informed deep neural network, was faster and more accurate than other state-of-the-art intravoxel-incoherent motion (IVIM) fitting approaches to diffusion-weighted imaging (DWI). This study presents a substantially improved version, IVIM-NET , and characterizes its superior performance in pancreatic cancer patients. In simulations (signal-to-noise ratio [SNR] = 20), the accuracy, independence, and consistency of IVIM-NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, number of hidden layers, dropout, batch normalization, learning rate), by calculating the normalized root-mean-square error (NRMSE), Spearman's ρ, and the coefficient of variation (CV ), respectively. The best performing network, IVIM-NET was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM-NET 's performance was evaluated in an independent dataset of 23 patients with pancreatic ductal adenocarcinoma. Fourteen of the patients received no treatment between two repeated scan sessions and nine received chemoradiotherapy between the repeated sessions. Intersession within-subject standard deviations (wSD) and treatment-induced changes were assessed. In simulations (SNR = 20), IVIM-NET outperformed IVIM-NET in accuracy (NRMSE(D) = 0.177 vs 0.196; NMRSE(f) = 0.220 vs 0.267; NMRSE(D*) = 0.386 vs 0.393), independence (ρ(D*, f) = 0.22 vs 0.74), and consistency (CV (D) = 0.013 vs 0.104; CV (f) = 0.020 vs 0.054; CV (D*) = 0.036 vs 0.110). IVIM-NET showed superior performance to the LS and Bayesian approaches at SNRs < 50. In vivo, IVIM-NET showed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM-NET detected the most individual patients with significant parameter changes compared to day-to-day variations. IVIM-NET is recommended for accurate, informative, and consistent IVIM fitting to DWI data.
PurposeEarlier work showed that IVIM‐NETorig, an unsupervised physics‐informed deep neural network, was faster and more accurate than other state‐of‐the‐art intravoxel‐incoherent motion (IVIM) fitting approaches to diffusion‐weighted imaging (DWI). This study presents a substantially improved version, IVIM‐NEToptim, and characterizes its superior performance in pancreatic cancer patients.MethodIn simulations (signal‐to‐noise ratio [SNR] = 20), the accuracy, independence, and consistency of IVIM‐NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, number of hidden layers, dropout, batch normalization, learning rate), by calculating the normalized root‐mean‐square error (NRMSE), Spearman’s ρ, and the coefficient of variation (CVNET), respectively. The best performing network, IVIM‐NEToptim was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM‐NEToptim’s performance was evaluated in an independent dataset of 23 patients with pancreatic ductal adenocarcinoma. Fourteen of the patients received no treatment between two repeated scan sessions and nine received chemoradiotherapy between the repeated sessions. Intersession within‐subject standard deviations (wSD) and treatment‐induced changes were assessed.ResultsIn simulations (SNR = 20), IVIM‐NEToptim outperformed IVIM‐NETorig in accuracy (NRMSE(D) = 0.177 vs 0.196; NMRSE(f) = 0.220 vs 0.267; NMRSE(D*) = 0.386 vs 0.393), independence (ρ(D*, f) = 0.22 vs 0.74), and consistency (CVNET(D) = 0.013 vs 0.104; CVNET(f) = 0.020 vs 0.054; CVNET(D*) = 0.036 vs 0.110). IVIM‐NEToptim showed superior performance to the LS and Bayesian approaches at SNRs < 50. In vivo, IVIM‐NEToptim showed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM‐NEToptim detected the most individual patients with significant parameter changes compared to day‐to‐day variations.ConclusionIVIM‐NEToptim is recommended for accurate, informative, and consistent IVIM fitting to DWI data.
Earlier work showed that IVIM-NETorig , an unsupervised physics-informed deep neural network, was faster and more accurate than other state-of-the-art intravoxel-incoherent motion (IVIM) fitting approaches to diffusion-weighted imaging (DWI). This study presents a substantially improved version, IVIM-NEToptim , and characterizes its superior performance in pancreatic cancer patients.PURPOSEEarlier work showed that IVIM-NETorig , an unsupervised physics-informed deep neural network, was faster and more accurate than other state-of-the-art intravoxel-incoherent motion (IVIM) fitting approaches to diffusion-weighted imaging (DWI). This study presents a substantially improved version, IVIM-NEToptim , and characterizes its superior performance in pancreatic cancer patients.In simulations (signal-to-noise ratio [SNR] = 20), the accuracy, independence, and consistency of IVIM-NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, number of hidden layers, dropout, batch normalization, learning rate), by calculating the normalized root-mean-square error (NRMSE), Spearman's ρ, and the coefficient of variation (CVNET ), respectively. The best performing network, IVIM-NEToptim was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM-NEToptim 's performance was evaluated in an independent dataset of 23 patients with pancreatic ductal adenocarcinoma. Fourteen of the patients received no treatment between two repeated scan sessions and nine received chemoradiotherapy between the repeated sessions. Intersession within-subject standard deviations (wSD) and treatment-induced changes were assessed.METHODIn simulations (signal-to-noise ratio [SNR] = 20), the accuracy, independence, and consistency of IVIM-NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, number of hidden layers, dropout, batch normalization, learning rate), by calculating the normalized root-mean-square error (NRMSE), Spearman's ρ, and the coefficient of variation (CVNET ), respectively. The best performing network, IVIM-NEToptim was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM-NEToptim 's performance was evaluated in an independent dataset of 23 patients with pancreatic ductal adenocarcinoma. Fourteen of the patients received no treatment between two repeated scan sessions and nine received chemoradiotherapy between the repeated sessions. Intersession within-subject standard deviations (wSD) and treatment-induced changes were assessed.In simulations (SNR = 20), IVIM-NEToptim outperformed IVIM-NETorig in accuracy (NRMSE(D) = 0.177 vs 0.196; NMRSE(f) = 0.220 vs 0.267; NMRSE(D*) = 0.386 vs 0.393), independence (ρ(D*, f) = 0.22 vs 0.74), and consistency (CVNET (D) = 0.013 vs 0.104; CVNET (f) = 0.020 vs 0.054; CVNET (D*) = 0.036 vs 0.110). IVIM-NEToptim showed superior performance to the LS and Bayesian approaches at SNRs < 50. In vivo, IVIM-NEToptim showed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM-NEToptim detected the most individual patients with significant parameter changes compared to day-to-day variations.RESULTSIn simulations (SNR = 20), IVIM-NEToptim outperformed IVIM-NETorig in accuracy (NRMSE(D) = 0.177 vs 0.196; NMRSE(f) = 0.220 vs 0.267; NMRSE(D*) = 0.386 vs 0.393), independence (ρ(D*, f) = 0.22 vs 0.74), and consistency (CVNET (D) = 0.013 vs 0.104; CVNET (f) = 0.020 vs 0.054; CVNET (D*) = 0.036 vs 0.110). IVIM-NEToptim showed superior performance to the LS and Bayesian approaches at SNRs < 50. In vivo, IVIM-NEToptim showed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM-NEToptim detected the most individual patients with significant parameter changes compared to day-to-day variations.IVIM-NEToptim is recommended for accurate, informative, and consistent IVIM fitting to DWI data.CONCLUSIONIVIM-NEToptim is recommended for accurate, informative, and consistent IVIM fitting to DWI data.
Purpose Earlier work showed that IVIM‐NETorig, an unsupervised physics‐informed deep neural network, was faster and more accurate than other state‐of‐the‐art intravoxel‐incoherent motion (IVIM) fitting approaches to diffusion‐weighted imaging (DWI). This study presents a substantially improved version, IVIM‐NEToptim, and characterizes its superior performance in pancreatic cancer patients. Method In simulations (signal‐to‐noise ratio [SNR] = 20), the accuracy, independence, and consistency of IVIM‐NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, number of hidden layers, dropout, batch normalization, learning rate), by calculating the normalized root‐mean‐square error (NRMSE), Spearman’s ρ, and the coefficient of variation (CVNET), respectively. The best performing network, IVIM‐NEToptim was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM‐NEToptim’s performance was evaluated in an independent dataset of 23 patients with pancreatic ductal adenocarcinoma. Fourteen of the patients received no treatment between two repeated scan sessions and nine received chemoradiotherapy between the repeated sessions. Intersession within‐subject standard deviations (wSD) and treatment‐induced changes were assessed. Results In simulations (SNR = 20), IVIM‐NEToptim outperformed IVIM‐NETorig in accuracy (NRMSE(D) = 0.177 vs 0.196; NMRSE(f) = 0.220 vs 0.267; NMRSE(D*) = 0.386 vs 0.393), independence (ρ(D*, f) = 0.22 vs 0.74), and consistency (CVNET(D) = 0.013 vs 0.104; CVNET(f) = 0.020 vs 0.054; CVNET(D*) = 0.036 vs 0.110). IVIM‐NEToptim showed superior performance to the LS and Bayesian approaches at SNRs < 50. In vivo, IVIM‐NEToptim showed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM‐NEToptim detected the most individual patients with significant parameter changes compared to day‐to‐day variations. Conclusion IVIM‐NEToptim is recommended for accurate, informative, and consistent IVIM fitting to DWI data.
Author Crezee, Hans
Nederveen, Aart J.
Gurney‐Champion, Oliver J.
While, Peter T.
Laarhoven, Hanneke W. M.
Barbieri, Sebastiano
Klaassen, Remy
Kaandorp, Misha P. T.
AuthorAffiliation 4 Centre for Big Data Research in Health UNSW Sydney Australia
1 Department of Radiology and Nuclear Medicine Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam Amsterdam the Netherlands
5 Department of Medical Oncology Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam Amsterdam the Netherlands
3 Department of Circulation and Medical Imaging NTNU – Norwegian University of Science and Technology Trondheim Norway
2 Department of Radiology and Nuclear Medicine St. Olav’s University Hospital Trondheim Norway
AuthorAffiliation_xml – name: 1 Department of Radiology and Nuclear Medicine Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam Amsterdam the Netherlands
– name: 2 Department of Radiology and Nuclear Medicine St. Olav’s University Hospital Trondheim Norway
– name: 4 Centre for Big Data Research in Health UNSW Sydney Australia
– name: 3 Department of Circulation and Medical Imaging NTNU – Norwegian University of Science and Technology Trondheim Norway
– name: 5 Department of Medical Oncology Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam Amsterdam the Netherlands
Author_xml – sequence: 1
  givenname: Misha P. T.
  orcidid: 0000-0002-7340-8256
  surname: Kaandorp
  fullname: Kaandorp, Misha P. T.
  email: mpkaando@stud.ntnu.no
  organization: NTNU – Norwegian University of Science and Technology
– sequence: 2
  givenname: Sebastiano
  orcidid: 0000-0002-5919-372X
  surname: Barbieri
  fullname: Barbieri, Sebastiano
  organization: UNSW
– sequence: 3
  givenname: Remy
  surname: Klaassen
  fullname: Klaassen, Remy
  organization: Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam
– sequence: 4
  givenname: Hanneke W. M.
  orcidid: 0000-0003-3546-9709
  surname: Laarhoven
  fullname: Laarhoven, Hanneke W. M.
  organization: Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam
– sequence: 5
  givenname: Hans
  surname: Crezee
  fullname: Crezee, Hans
  organization: Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam
– sequence: 6
  givenname: Peter T.
  orcidid: 0000-0003-2602-0758
  surname: While
  fullname: While, Peter T.
  organization: NTNU – Norwegian University of Science and Technology
– sequence: 7
  givenname: Aart J.
  surname: Nederveen
  fullname: Nederveen, Aart J.
  organization: Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam
– sequence: 8
  givenname: Oliver J.
  orcidid: 0000-0003-1750-6617
  surname: Gurney‐Champion
  fullname: Gurney‐Champion, Oliver J.
  organization: Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34105184$$D View this record in MEDLINE/PubMed
BookMark eNp9ks1u1DAQxy1URLeFAy-AInGBw7b-iJP4glRVfFRqhYR6txxntuvKsYOdBPbGCyDxjDwJs7ulgkogH-bDv_lrxp4jchBiAEKeM3rCKOWnfepPeNNI_ogsmOR8yaUqD8iC1iVdCqbKQ3KU8y2lVKm6fEIORcmoZE25IN8v-iHFGbpiCnkaIM0uYzCsN9nZ_PPbDxdWMfWY6gCGwoNJwYWbApOFC2Myc_wKHl0b15AgjEUfRxcDmg78ljShK2A2fjK7vAvFYIJNgKEtLLqQMDM6rM1PyeOV8Rme3dljcv3u7fX5h-Xlx_cX52eXSyup4ktTMguiU63kVnDVtW0lwVasVg01wjJeMcvrtqZcQqt41dRCMqhoW7OqVrU4Jm_2ssPU4mgWtoN4PSTXm7TR0Tj9901wa30TZ92IilMlUODVnUCKnyfIo-5dtuC9CRCnrLkUSnLGRIPoywfobZxSwOmQkoJLPBypF392dN_K749C4PUesCnmnGB1jzCqt0ugcQn0bgmQPX3AWjfuXh-Hcf5_FV-ch82_pfXVp6t9xS8ZmseE
CitedBy_id crossref_primary_10_1002_mrm_30184
crossref_primary_10_1002_mp_16031
crossref_primary_10_1016_j_cma_2023_116290
crossref_primary_10_1002_mrm_70045
crossref_primary_10_1186_s12885_025_14557_3
crossref_primary_10_3390_magnetochemistry9020058
crossref_primary_10_1002_mrm_29753
crossref_primary_10_1007_s10462_025_11303_w
crossref_primary_10_3390_math12040609
crossref_primary_10_3390_make6010019
crossref_primary_10_1109_ACCESS_2023_3285247
crossref_primary_10_1002_mrm_30294
crossref_primary_10_1002_jmri_28433
crossref_primary_10_1002_jmri_29127
crossref_primary_10_1002_jmri_29008
crossref_primary_10_1002_mrm_30579
crossref_primary_10_1002_nbm_5177
crossref_primary_10_1002_mrm_29429
crossref_primary_10_1002_jmri_28074
crossref_primary_10_1002_mrm_29628
crossref_primary_10_4329_wjr_v15_i1_10
crossref_primary_10_1002_mp_17825
crossref_primary_10_1002_nbm_70136
crossref_primary_10_1016_j_neuroimage_2021_118601
crossref_primary_10_1016_j_media_2024_103414
crossref_primary_10_1016_j_semradonc_2022_06_007
crossref_primary_10_1148_rycan_240115
crossref_primary_10_1007_s00330_024_11010_0
crossref_primary_10_1080_02656736_2024_2321980
crossref_primary_10_1016_j_media_2024_103134
crossref_primary_10_1002_mp_17383
crossref_primary_10_1088_1361_6560_aced77
crossref_primary_10_1002_mrm_30042
crossref_primary_10_1016_j_media_2022_102512
crossref_primary_10_1002_mp_17583
crossref_primary_10_1016_j_ejmp_2025_104978
crossref_primary_10_3389_fonc_2025_1524634
crossref_primary_10_1002_mrm_29450
crossref_primary_10_1002_nbm_5201
crossref_primary_10_2463_mrms_tn_2024_0181
crossref_primary_10_1016_j_mric_2023_09_007
crossref_primary_10_1002_mrm_29612
crossref_primary_10_1016_j_media_2024_103445
crossref_primary_10_3389_fphys_2022_942495
crossref_primary_10_1016_j_media_2025_103768
crossref_primary_10_1088_1361_6560_ac9a1f
crossref_primary_10_1038_s41524_024_01307_5
crossref_primary_10_1016_j_compbiomed_2022_106495
crossref_primary_10_1186_s41747_024_00437_1
crossref_primary_10_3390_app12041907
crossref_primary_10_1038_s41598_024_71173_0
crossref_primary_10_1097_RCT_0000000000001566
crossref_primary_10_1002_mp_17810
crossref_primary_10_1088_1361_6560_ad3db8
crossref_primary_10_1007_s10334_024_01186_3
crossref_primary_10_1109_TASE_2024_3515839
crossref_primary_10_1016_j_media_2025_103535
crossref_primary_10_1162_imag_a_00353
crossref_primary_10_1016_j_cma_2023_115902
crossref_primary_10_1002_mrc_5289
Cites_doi 10.1097/RLI.0000000000000225
10.1002/1878-0261.12688
10.1002/mrm.24649
10.1186/s12885-016-2073-z
10.1016/j.mri.2011.03.004
10.1090/qam/10666
10.1137/0111030
10.1002/nbm.3833
10.1109/TMI.2009.2035616
10.1002/mrm.1910290510
10.1016/j.ejro.2017.07.002
10.1158/1535-7163.MCT-15-0764
10.1007/s00330-012-2604-1
10.1002/jmri.24172
10.1097/RLI.0000000000000505
10.1002/mrm.26598
10.1148/radiology.168.2.3393671
10.1002/mrm.27910
10.1002/mrm.26977
10.1002/mrm.25484
10.1002/mrm.25109
10.21037/qims.2017.02.03
10.1016/j.ijrobp.2018.04.064
10.1002/mrm.24529
10.1007/s00330-014-3511-4
10.21037/qims.2018.04.08
10.1109/TMI.2019.2946501
10.1593/tlo.09268
10.1002/mrm.25765
10.1002/jmri.25411
10.1371/journal.pone.0194590
10.1016/j.mri.2018.02.005
10.1038/s41598-016-0028-x
10.1148/radiol.2015151244
10.1007/s10334-018-0697-5
10.1136/bmj.313.7059.744
10.1200/JCO.19.02274
10.4329/wjr.v7.i10.319
10.1016/j.jmr.2006.01.016
10.1002/jmri.26598
10.1007/s00535-005-1578-z
10.1016/j.nicl.2018.08.030
10.1148/radiol.2019182561
10.3390/ijms21093218
10.1038/s41598-017-16826-z
ContentType Journal Article
Copyright 2021 The Authors. published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine
2021 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
2021. This article is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2021 The Authors. published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine
– notice: 2021 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
– notice: 2021. This article is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 24P
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
8FD
FR3
K9.
M7Z
P64
7X8
5PM
DOI 10.1002/mrm.28852
DatabaseName Wiley Online Library Open Access
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Technology Research Database
Engineering Research Database
ProQuest Health & Medical Complete (Alumni)
Biochemistry Abstracts 1
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Biochemistry Abstracts 1
ProQuest Health & Medical Complete (Alumni)
Engineering Research Database
Technology Research Database
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitleList MEDLINE
Biochemistry Abstracts 1
MEDLINE - Academic

Database_xml – sequence: 1
  dbid: 24P
  name: Wiley Online Library Open Access
  url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  sourceTypes: Publisher
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Physics
DocumentTitleAlternate KAANDORP et al
EISSN 1522-2594
EndPage 2265
ExternalDocumentID PMC8362093
34105184
10_1002_mrm_28852
MRM28852
Genre article
Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: Norges Forskningsråd
  funderid: FRIPRO Researcher Project 302624
– fundername: KWF Kankerbestrijding
  funderid: KWF‐UVA 18410; KWF‐UVA 2013.5932
– fundername: KWF Kankerbestrijding
  grantid: KWF-UVA 2013.5932
– fundername: Norges Forskningsråd
  grantid: FRIPRO Researcher Project 302624
– fundername: KWF Kankerbestrijding
  grantid: KWF-UVA 18410
– fundername: ;
  grantid: FRIPRO Researcher Project 302624
– fundername: ;
  grantid: KWF‐UVA 18410; KWF‐UVA 2013.5932
GroupedDBID ---
-DZ
.3N
.55
.GA
.Y3
05W
0R~
10A
1L6
1OB
1OC
1ZS
24P
31~
33P
3O-
3SF
3WU
4.4
4ZD
50Y
50Z
51W
51X
52M
52N
52O
52P
52R
52S
52T
52U
52V
52W
52X
53G
5GY
5RE
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A01
A03
AAESR
AAEVG
AAHHS
AAHQN
AAIPD
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDPE
ABEML
ABIJN
ABJNI
ABLJU
ABPVW
ABQWH
ABXGK
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACFBH
ACGFO
ACGFS
ACGOF
ACIWK
ACMXC
ACPOU
ACPRK
ACRPL
ACSCC
ACXBN
ACXQS
ACYXJ
ADBBV
ADBTR
ADEOM
ADIZJ
ADKYN
ADMGS
ADNMO
ADOZA
ADXAS
ADZMN
AEEZP
AEGXH
AEIGN
AEIMD
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFFNX
AFFPM
AFGKR
AFPWT
AFRAH
AFWVQ
AFZJQ
AHBTC
AHMBA
AIACR
AIAGR
AITYG
AIURR
AIWBW
AJBDE
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ASPBG
ATUGU
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMXJE
BROTX
BRXPI
BY8
C45
CS3
D-6
D-7
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRMAN
DRSTM
DU5
EBD
EBS
EJD
EMOBN
F00
F01
F04
FEDTE
FUBAC
G-S
G.N
GNP
GODZA
H.X
HBH
HDBZQ
HF~
HGLYW
HHY
HHZ
HVGLF
HZ~
I-F
IX1
J0M
JPC
KBYEO
KQQ
LATKE
LAW
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
M65
MEWTI
MK4
MRFUL
MRMAN
MRSTM
MSFUL
MSMAN
MSSTM
MXFUL
MXMAN
MXSTM
N04
N05
N9A
NF~
NNB
O66
O9-
OIG
OVD
P2P
P2W
P2X
P2Z
P4B
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
QRW
R.K
RGB
RIWAO
RJQFR
ROL
RWI
RX1
RYL
SAMSI
SUPJJ
SV3
TEORI
TUS
TWZ
UB1
V2E
V8K
W8V
W99
WBKPD
WHWMO
WIB
WIH
WIJ
WIK
WIN
WJL
WOHZO
WQJ
WRC
WUP
WVDHM
WXI
WXSBR
X7M
XG1
XPP
XV2
ZGI
ZXP
ZZTAW
~IA
~WT
AAMMB
AAYXX
AEFGJ
AEYWJ
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
O8X
CGR
CUY
CVF
ECM
EIF
NPM
8FD
FR3
K9.
M7Z
P64
7X8
5PM
ID FETCH-LOGICAL-c5092-a41ce3d9b52c329dbb65ec617980a3c1261c27b7025eb92687351e60b7167973
IEDL.DBID 24P
ISICitedReferencesCount 72
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000659057600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0740-3194
1522-2594
IngestDate Tue Nov 04 01:59:45 EST 2025
Fri Jul 11 09:07:43 EDT 2025
Sat Nov 29 14:39:28 EST 2025
Mon Jul 21 05:24:03 EDT 2025
Sat Nov 29 06:34:32 EST 2025
Tue Nov 18 22:14:58 EST 2025
Wed Jan 22 16:29:46 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords pancreatic cancer
IVIM
unsupervised physics-informed deep learning
intravoxel incoherent motion
deep neural network
diffusion-weighted magnetic resonance imaging
Language English
License Attribution
2021 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c5092-a41ce3d9b52c329dbb65ec617980a3c1261c27b7025eb92687351e60b7167973
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0003-2602-0758
0000-0003-1750-6617
0000-0002-7340-8256
0000-0003-3546-9709
0000-0002-5919-372X
OpenAccessLink https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmrm.28852
PMID 34105184
PQID 2553252522
PQPubID 1016391
PageCount 16
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_8362093
proquest_miscellaneous_2539521138
proquest_journals_2553252522
pubmed_primary_34105184
crossref_primary_10_1002_mrm_28852
crossref_citationtrail_10_1002_mrm_28852
wiley_primary_10_1002_mrm_28852_MRM28852
PublicationCentury 2000
PublicationDate October 2021
PublicationDateYYYYMMDD 2021-10-01
PublicationDate_xml – month: 10
  year: 2021
  text: October 2021
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Hoboken
PublicationTitle Magnetic resonance in medicine
PublicationTitleAlternate Magn Reson Med
PublicationYear 2021
Publisher Wiley Subscription Services, Inc
John Wiley and Sons Inc
Publisher_xml – name: Wiley Subscription Services, Inc
– name: John Wiley and Sons Inc
References 2017; 7
1993; 29
2017; 4
2015; 73
2013; 23
2019; 54
2015; 74
2017; 45
2016; 75
2020; 14
2013; 70
2006; 179
2018; 8
2017; 30
2010; 29
2017; 78
1944; 2
2014; 15
2016; 279
2011; 29
2018; 31
2018; 79
2015; 1
2020; 83
2017; 22
2018; 102
2020; 39
2005; 40
1988; 168
2020; 38
2016; 51
2016; 16
2018; 20
2015; 7
2016; 15
1999
2015; 25
1963; 11
2020
2019; 49
2016
2015
2018; 50
2020; 21
2014; 39
1996; 313
2009; 2
2019; 292
2014; 71
2018; 13
e_1_2_8_28_1
Srivastava N (e_1_2_8_23_1) 2014; 15
e_1_2_8_47_1
e_1_2_8_26_1
e_1_2_8_49_1
e_1_2_8_3_1
e_1_2_8_5_1
Ioffe S (e_1_2_8_24_1) 2015; 1
e_1_2_8_7_1
e_1_2_8_9_1
e_1_2_8_20_1
e_1_2_8_43_1
e_1_2_8_22_1
e_1_2_8_45_1
e_1_2_8_41_1
e_1_2_8_17_1
e_1_2_8_19_1
Paszke A (e_1_2_8_21_1) 2017; 22
e_1_2_8_13_1
e_1_2_8_36_1
e_1_2_8_15_1
e_1_2_8_38_1
e_1_2_8_32_1
e_1_2_8_11_1
e_1_2_8_34_1
e_1_2_8_51_1
e_1_2_8_30_1
e_1_2_8_29_1
e_1_2_8_25_1
e_1_2_8_46_1
e_1_2_8_27_1
e_1_2_8_48_1
e_1_2_8_2_1
e_1_2_8_4_1
e_1_2_8_6_1
e_1_2_8_8_1
e_1_2_8_42_1
e_1_2_8_44_1
e_1_2_8_40_1
e_1_2_8_18_1
e_1_2_8_39_1
e_1_2_8_14_1
e_1_2_8_35_1
e_1_2_8_16_1
e_1_2_8_37_1
Friedman N (e_1_2_8_53_1) 1999
e_1_2_8_10_1
e_1_2_8_31_1
e_1_2_8_12_1
e_1_2_8_33_1
e_1_2_8_54_1
e_1_2_8_52_1
e_1_2_8_50_1
References_xml – volume: 25
  start-page: 994
  year: 2015
  end-page: 1004
  article-title: The histogram analysis of diffusion‐weighted intravoxel incoherent motion (IVIM) imaging for differentiating the gleason grade of prostate cancer
  publication-title: Eur Radiol
– volume: 7
  start-page: 1
  year: 2017
  end-page: 9
  article-title: Predictive and prognostic value of intravoxel incoherent motion (IVIM) MR imaging in patients with advanced cervical cancers undergoing concurrent chemo‐radiotherapy
  publication-title: Sci Rep
– volume: 4
  start-page: 101
  year: 2017
  end-page: 107
  article-title: Intravoxel incoherent motion (IVIM) histogram biomarkers for prediction of neoadjuvant treatment response in breast cancer patients
  publication-title: Eur J Radiol Open
– volume: 50
  start-page: 1
  year: 2018
  end-page: 9
  article-title: Repeatability and correlations of dynamic contrast enhanced and T2* MRI in patients with advanced pancreatic ductal adenocarcinoma
  publication-title: Magn Reson Imaging
– volume: 71
  start-page: 411
  year: 2014
  end-page: 420
  article-title: Improved intravoxel incoherent motion analysis of diffusion weighted imaging by data driven Bayesian modeling
  publication-title: Magn Reson Med
– volume: 8
  start-page: 301
  year: 2018
  end-page: 310
  article-title: Quantitative parameters of intravoxel incoherent motion diffusion weighted imaging (IVIM‐DWI): potential application in predicting pathological grades of pancreatic ductal adenocarcinoma
  publication-title: Quant Imaging Med Surg
– volume: 30
  start-page: 1
  year: 2017
  end-page: 11
  article-title: Diffusion parameter mapping with the combined intravoxel incoherent motion and kurtosis model using artificial neural networks at 3 T
  publication-title: NMR Biomed
– volume: 40
  start-page: 518
  year: 2005
  end-page: 525
  article-title: Differential diagnosis of pancreatic tumors using ultrasound contrast imaging
  publication-title: J Gastroenterol
– volume: 23
  start-page: 428
  year: 2013
  end-page: 434
  article-title: Measurement reproducibility of perfusion fraction and pseudodiffusion coefficient derived by intravoxel incoherent motion diffusion‐weighted MR imaging in normal liver and metastases
  publication-title: Eur Radiol
– volume: 11
  start-page: 431
  year: 1963
  end-page: 441
  article-title: An algorithm for least‐squares estimation of nonlinear parameters
  publication-title: J Soc Ind Appl Math
– volume: 45
  start-page: 1325
  year: 2017
  end-page: 1334
  article-title: Evaluation of intravoxel incoherent motion fitting methods in low‐perfused tissue
  publication-title: J Magn Reson Imaging
– volume: 49
  start-page: e26
  year: 2019
  end-page: e39
  article-title: Recommendations towards standards for quantitative MRI (qMRI) and outstanding needs
  publication-title: J Magn Reson Imaging
– volume: 21
  start-page: 3218
  year: 2020
  article-title: Pancreatic cancer and its microenvironment—recent advances and current controversies
  publication-title: Int J Mol Sci
– volume: 70
  start-page: 972
  year: 2013
  end-page: 984
  article-title: Comprehensive framework for accurate diffusion MRI parameter estimation
  publication-title: Magn Reson Med
– volume: 29
  start-page: 766
  year: 2011
  end-page: 776
  article-title: Toward an optimal distribution of b values for intravoxel incoherent motion imaging
  publication-title: Magn Reson Imaging
– volume: 73
  start-page: 306
  year: 2015
  end-page: 311
  article-title: The effect of low b‐values on the intravoxel incoherent motion derived pseudodiffusion parameter in liver
  publication-title: Magn Reson Med
– volume: 2
  start-page: 164
  year: 1944
  end-page: 168
  article-title: A method for the solution of certain non‐linear problems in Least squares
  publication-title: Q Appl Math
– volume: 83
  start-page: 312
  year: 2020
  end-page: 321
  article-title: Deep learning how to fit an intravoxel incoherent motion model to diffusion‐weighted MRI
  publication-title: Magn Reson Med
– volume: 39
  start-page: 1268
  year: 2020
  end-page: 1277
  article-title: Modl‐mussels: model‐based deep learning for multishot sensitivity‐encoded diffusion MRI
  publication-title: IEEE Trans Med Imaging
– volume: 7
  start-page: 319
  year: 2015
  article-title: Diffusion‐weighted imaging of pancreatic cancer
  publication-title: World J Radiol
– volume: 1
  start-page: 448
  year: 2015
  end-page: 456
  article-title: Batch normalization: accelerating deep network training by reducing internal covariate shift
  publication-title: 32nd Int Conf Mach Learn ICML 2015
– volume: 15
  start-page: 680
  year: 2016
  end-page: 688
  article-title: SPARC‐independent delivery of nab‐paclitaxel without depleting tumor stroma in patient‐derived pancreatic cancer xenografts
  publication-title: Mol Cancer Ther
– volume: 13
  start-page: 1
  year: 2018
  end-page: 18
  article-title: Comparison of six fit algorithms for the intravoxel incoherent motion model of diffusion‐weighted magnetic resonance imaging data of pancreatic cancer patients
  publication-title: PLoS One
– volume: 22
  start-page: 2
  year: 2017
  end-page: 8
  article-title: Automatic differentiation in PyTorch
  publication-title: NIPS‐W
– volume: 279
  start-page: 784
  year: 2016
  end-page: 794
  article-title: Comparison of intravoxel incoherent motion parameters across MR imagers and field strengths: evaluation in upper abdominal organs
  publication-title: Radiology
– volume: 74
  start-page: 1077
  year: 2015
  end-page: 1085
  article-title: Comparison of fitting methods and b‐value sampling strategies for intravoxel incoherent motion in breast cancer
  publication-title: Magn Reson Med
– volume: 168
  start-page: 497
  year: 1988
  end-page: 505
  article-title: Separation of diffusion and perfusion in intravoxel incoherent motion MR imaging
  publication-title: Radiology
– volume: 79
  start-page: 3055
  year: 2018
  end-page: 3071
  article-title: Learning a variational network for reconstruction of accelerated MRI data
  publication-title: Magn Reson Med
– volume: 78
  start-page: 2373
  year: 2017
  end-page: 2387
  article-title: A comparative simulation study of Bayesian fitting approaches to intravoxel incoherent motion modeling in diffusion‐weighted MRI
  publication-title: Magn Reson Med
– volume: 179
  start-page: 317
  year: 2006
  end-page: 322
  article-title: Analytically exact correction scheme for signal extraction from noisy magnitude MR signals
  publication-title: J Magn Reson
– volume: 2
  start-page: 231
  year: 2009
  end-page: 235
  article-title: Applications of the repeatability of quantitative imaging biomarkers: a review of statistical analysis of repeat data sets
  publication-title: Transl Oncol
– volume: 31
  start-page: 715
  year: 2018
  end-page: 723
  article-title: Comparison of methods for estimation of the intravoxel incoherent motion (IVIM) diffusion coefficient (D) and perfusion fraction (f)
  publication-title: Magn Reson Mater Phys Biol Med
– start-page: 206
  year: 1999
  end-page: 215
  article-title: Data analysis with Bayesian networks: a bootstrap approach
  publication-title: Uncertainty Artif Intell
– volume: 29
  start-page: 642
  year: 1993
  end-page: 647
  article-title: On the use of bayesian probability theory for analysis of exponential decay date: an example taken from intravoxel incoherent motion experiments
  publication-title: Magn Reson Med
– volume: 51
  start-page: 211
  year: 2016
  end-page: 220
  article-title: Minimizing the acquisition time for intravoxel incoherent motion magnetic resonance imaging acquisitions in the liver and pancreas
  publication-title: Invest Radiol
– volume: 14
  start-page: 2176
  year: 2020
  end-page: 2189
  article-title: Pathological validation and prognostic potential of quantitative MRI in the characterization of pancreas cancer: preliminary experience
  publication-title: Mol Oncol
– start-page: 1
  year: 2015
  end-page: 15
– volume: 54
  start-page: 16
  year: 2019
  end-page: 22
  article-title: Accurate therapeutic response assessment of pancreatic ductal adenocarcinoma using quantitative dynamic contrast‐enhanced magnetic resonance imaging with a point‐of‐care perfusion phantom: a pilot study
  publication-title: Invest Radiol
– volume: 38
  start-page: 1763
  year: 2020
  end-page: 1774
  article-title: Original reports abstract preoperative chemoradiotherapy versus immediate surgery for resectable and borderline resectable pancreatic cancer: results of the dutch randomized phase III PREOPANC Trial
  publication-title: J Clin Oncol
– start-page: 1
  year: 2016
  end-page: 14
– volume: 20
  start-page: 705
  year: 2018
  end-page: 714
  article-title: Intravoxel incoherent motion MRI in neurological and cerebrovascular diseases
  publication-title: NeuroImage Clin
– volume: 7
  start-page: 1
  year: 2017
  end-page: 9
  article-title: Apparent diffusion coefficient (ADC) predicts therapy response in pancreatic ductal adenocarcinoma
  publication-title: Sci Rep
– volume: 313
  start-page: 744
  year: 1996
  article-title: Statistics notes: measurement error
  publication-title: BMJ
– volume: 16
  start-page: 1
  year: 2016
  end-page: 8
  article-title: Evaluating early response of cervical cancer under concurrent chemo‐radiotherapy by intravoxel incoherent motion MR imaging
  publication-title: BMC Cancer
– volume: 39
  start-page: 317
  year: 2014
  end-page: 325
  article-title: Intravoxel incoherent motion (IVIM) MR imaging of colorectal liver metastases: are we only looking at tumor necrosis?
  publication-title: J Magn Reson Imaging
– year: 2020
– volume: 7
  start-page: 59
  year: 2017
  end-page: 78
  article-title: Liver intravoxel incoherent motion (IVIM) magnetic resonance imaging: a comprehensive review of published data on normal values and applications for fibrosis and tumor evaluation
  publication-title: Quant Imaging Med Surg
– volume: 15
  start-page: 1929
  year: 2014
  end-page: 1958
  article-title: Dropout: a simple way to prevent neural networks from overfitting
  publication-title: J Mach Learn Res
– volume: 75
  start-page: 2175
  year: 2016
  end-page: 2184
  article-title: Impact of the calculation algorithm on biexponential fitting of diffusion‐weighted MRI in upper abdominal organs
  publication-title: Magn Reson Med
– volume: 102
  start-page: 1052
  year: 2018
  end-page: 1062
  article-title: Evaluation of six diffusion‐weighted MRI models for assessing effects of neoadjuvant chemoradiation in pancreatic cancer patients
  publication-title: Int J Radiat Oncol Biol Phys
– volume: 29
  start-page: 196
  year: 2010
  end-page: 205
  article-title: A toolbox for intensity‐based medical image registration
  publication-title: IEEE Trans Med Imaging
– volume: 292
  start-page: 628
  year: 2019
  end-page: 635
  article-title: Perfusion CT to assess response to neoadjuvant chemotherapy and radiation therapy in pancreatic ductal adenocarcinoma: initial experience
  publication-title: Radiology
– ident: e_1_2_8_52_1
  doi: 10.1097/RLI.0000000000000225
– ident: e_1_2_8_6_1
  doi: 10.1002/1878-0261.12688
– ident: e_1_2_8_16_1
  doi: 10.1002/mrm.24649
– ident: e_1_2_8_46_1
  doi: 10.1186/s12885-016-2073-z
– ident: e_1_2_8_22_1
– ident: e_1_2_8_32_1
  doi: 10.1016/j.mri.2011.03.004
– ident: e_1_2_8_29_1
  doi: 10.1090/qam/10666
– volume: 15
  start-page: 1929
  year: 2014
  ident: e_1_2_8_23_1
  article-title: Dropout: a simple way to prevent neural networks from overfitting
  publication-title: J Mach Learn Res
– ident: e_1_2_8_30_1
  doi: 10.1137/0111030
– ident: e_1_2_8_18_1
  doi: 10.1002/nbm.3833
– ident: e_1_2_8_38_1
  doi: 10.1109/TMI.2009.2035616
– ident: e_1_2_8_14_1
  doi: 10.1002/mrm.1910290510
– ident: e_1_2_8_3_1
  doi: 10.1016/j.ejro.2017.07.002
– ident: e_1_2_8_48_1
  doi: 10.1158/1535-7163.MCT-15-0764
– ident: e_1_2_8_11_1
  doi: 10.1007/s00330-012-2604-1
– ident: e_1_2_8_47_1
  doi: 10.1002/jmri.24172
– ident: e_1_2_8_42_1
  doi: 10.1097/RLI.0000000000000505
– ident: e_1_2_8_17_1
  doi: 10.1002/mrm.26598
– ident: e_1_2_8_2_1
  doi: 10.1148/radiology.168.2.3393671
– ident: e_1_2_8_12_1
  doi: 10.1002/mrm.27910
– ident: e_1_2_8_19_1
  doi: 10.1002/mrm.26977
– ident: e_1_2_8_31_1
  doi: 10.1002/mrm.25484
– ident: e_1_2_8_33_1
  doi: 10.1002/mrm.25109
– ident: e_1_2_8_9_1
  doi: 10.21037/qims.2017.02.03
– ident: e_1_2_8_36_1
  doi: 10.1016/j.ijrobp.2018.04.064
– ident: e_1_2_8_54_1
  doi: 10.1002/mrm.24529
– ident: e_1_2_8_8_1
  doi: 10.1007/s00330-014-3511-4
– volume: 22
  start-page: 2
  year: 2017
  ident: e_1_2_8_21_1
  article-title: Automatic differentiation in PyTorch
  publication-title: NIPS‐W
– ident: e_1_2_8_5_1
  doi: 10.21037/qims.2018.04.08
– ident: e_1_2_8_26_1
– ident: e_1_2_8_20_1
  doi: 10.1109/TMI.2019.2946501
– ident: e_1_2_8_39_1
  doi: 10.1593/tlo.09268
– ident: e_1_2_8_15_1
  doi: 10.1002/mrm.25765
– ident: e_1_2_8_51_1
  doi: 10.1002/jmri.25411
– ident: e_1_2_8_10_1
  doi: 10.1371/journal.pone.0194590
– ident: e_1_2_8_35_1
  doi: 10.1016/j.mri.2018.02.005
– ident: e_1_2_8_4_1
  doi: 10.1038/s41598-016-0028-x
– ident: e_1_2_8_27_1
  doi: 10.1148/radiol.2015151244
– ident: e_1_2_8_25_1
– ident: e_1_2_8_34_1
  doi: 10.1007/s10334-018-0697-5
– ident: e_1_2_8_40_1
  doi: 10.1136/bmj.313.7059.744
– ident: e_1_2_8_37_1
  doi: 10.1200/JCO.19.02274
– ident: e_1_2_8_43_1
  doi: 10.4329/wjr.v7.i10.319
– ident: e_1_2_8_28_1
  doi: 10.1016/j.jmr.2006.01.016
– ident: e_1_2_8_13_1
  doi: 10.1002/jmri.26598
– start-page: 206
  year: 1999
  ident: e_1_2_8_53_1
  article-title: Data analysis with Bayesian networks: a bootstrap approach
  publication-title: Uncertainty Artif Intell
– ident: e_1_2_8_44_1
  doi: 10.1007/s00535-005-1578-z
– ident: e_1_2_8_50_1
  doi: 10.1002/mrm.25765
– ident: e_1_2_8_7_1
  doi: 10.1016/j.nicl.2018.08.030
– volume: 1
  start-page: 448
  year: 2015
  ident: e_1_2_8_24_1
  article-title: Batch normalization: accelerating deep network training by reducing internal covariate shift
  publication-title: 32nd Int Conf Mach Learn ICML 2015
– ident: e_1_2_8_49_1
  doi: 10.1148/radiol.2019182561
– ident: e_1_2_8_45_1
  doi: 10.3390/ijms21093218
– ident: e_1_2_8_41_1
  doi: 10.1038/s41598-017-16826-z
SSID ssj0009974
Score 2.607884
Snippet Purpose Earlier work showed that IVIM‐NETorig, an unsupervised physics‐informed deep neural network, was faster and more accurate than other state‐of‐the‐art...
Earlier work showed that IVIM-NET , an unsupervised physics-informed deep neural network, was faster and more accurate than other state-of-the-art...
PurposeEarlier work showed that IVIM‐NETorig, an unsupervised physics‐informed deep neural network, was faster and more accurate than other state‐of‐the‐art...
Earlier work showed that IVIM-NETorig , an unsupervised physics-informed deep neural network, was faster and more accurate than other state-of-the-art...
SourceID pubmedcentral
proquest
pubmed
crossref
wiley
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 2250
SubjectTerms Adenocarcinoma
Algorithms
Artificial neural networks
Bayes Theorem
Bayesian analysis
Cancer
Chemoradiotherapy
Chemotherapy
Coefficient of variation
Computer architecture
Consistency
Deep Learning
deep neural network
Diffusion Magnetic Resonance Imaging
diffusion‐weighted magnetic resonance imaging
Humans
intravoxel incoherent motion
IVIM
Machine learning
Motion
Neural networks
Pancreatic cancer
Pancreatic Neoplasms - diagnostic imaging
Parameters
Patients
Performance evaluation
Physics
Radiation therapy
Reproducibility of Results
s—Computer Processing and Modeling
unsupervised physics‐informed deep learning
Title Improved unsupervised physics‐informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients
URI https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmrm.28852
https://www.ncbi.nlm.nih.gov/pubmed/34105184
https://www.proquest.com/docview/2553252522
https://www.proquest.com/docview/2539521138
https://pubmed.ncbi.nlm.nih.gov/PMC8362093
Volume 86
WOSCitedRecordID wos000659057600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library Free Content
  customDbUrl:
  eissn: 1522-2594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0009974
  issn: 0740-3194
  databaseCode: WIN
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
– providerCode: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1522-2594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0009974
  issn: 0740-3194
  databaseCode: DRFUL
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fb9MwELemDRAvA8a_wpgM4oGXsMR27Fg8IaACiVbTNETfIttxt0pbWjXttEe-ABKfkU_CnZ2mVAMJCUWKkviSOMnd-Wf78jtCXhrps7G2MuEVk4mANi8xtqgS4ZTOhR8L49KQbEINh8VopI-2yJvVvzCRH6IbcEPLCP4aDdzY5nBNGnoxv3jNiiIH_7uTZbzAvA1MHK0Zd3WkYFYCHY0WK1qhlB12p242RtcQ5vVAyd8BbGiB-nf-q-53yW4LPOnbqCn3yJav98itQTu1vkduhlhQ19wn3-NAg6_osm6WM3QmDezEMZDm57cfkWwVDlXez2ibd-KUwkE6wSe4nF75c4q0D2f4M-GCxlRBNGTdQUlTV3RNMw6SFHxShK-OOtTDOW0JX5sH5KT_4eTdx6TN2pA4AB8sMSJznlfa5sxxpitrZe6dRGK01HCXQZfNMWUVgC1vNZOF4nnmZWoVzggp_pBs19PaPyZUMcMBATKjLLga5fDKADf1WFrhpHA98mr19UrXMppjYo3zMnIxsxLecxnec4-86ERnkcbjT0L7KxUoW0tuSuhycZbDAsXPu2KwQZxYMbWfLlGGQzVRCXvkUdSY7i4c42ihG90jakOXOgHk994sqSdngee7AHCRag6PGXTp7xUvB8eDsPHk30WfktsMw3NCXOI-2V7Ml_4ZueEuF5NmfhBMCdZqVByQnffH_S-fYe_rp-EvmXYpiw
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NbtQwEB5V5fdSoPxtKWAQBy5pE9uJY4kLQlSt6K4QWoneotjx0pXa7GqzW3HkBZB4xj5JZ-xsllVBQkK5JPYkcZKZ8Wd78g3AmzJzyUibLBIVzyKJfV5UmryKpFU6lW4kSxv7ZBNqMMhPTvTnDXi3_Bcm8EN0E25kGd5fk4HThPT-ijX0fHa-x_M8RQd8QyLQoMQNX48GK8pdHTiYlSRPo-WSVyjm-92p673RNYh5PVLydwTru6CDe__X-Puw1UJP9j7oygPYcPU23O63i-vbcMtHg9rmIfwMUw2uYou6WUzJnTR4EGZBmssfvwLdKhZVzk1Zm3niG8NCNqZHuJh8d2eMiB9O6XfCOQvJgpjPu0OSZV2xFdE4SjL0SgHAWmZJE2espXxtHsHw4OPww2HU5m2ILMIPHpUysU5U2qTcCq4rY7LU2Yyo0eJS2AQHbZYroxBuOaN5liuRJi6LjaI1ISUew2Y9qd1TYIqXAjEgL5VBZ6MsXRkBpx5lRtpM2h68XX6-wrac5pRa46wIbMy8wPdc-Pfcg9ed6DQQefxJaHepA0Vry02Bgy7BU9yw-lVXjVZISytl7SYLkhHYzCQReQ-eBJXp7iIokhYH0j1Qa8rUCRDD93pNPT71TN85wotYC3xMr0x_b3jR_9L3Ozv_LvoS7hwO-8fF8dHg0zO4yylYx0cp7sLmfLZwz-GmvZiPm9kLb1dXoSwqTA
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fb9MwED9NHUy88Gf8KwwwiAdewhLbiWOJF8SoQKzVNA1pb1HsuKzSllZNO_HIF0DiM_JJuLPTlGogIaG8JPYlcZK788_25XcAL8vMJWNtskhUPIsk9nlRafIqklbpVLqxLG3sk02o0Sg_PdVHW_Bm9S9M4IfoJtzIMry_JgN3s2q8v2YNvZhfvOZ5nqID3paURKYH2wfHg8-Ha9JdHViYlSRfo-WKWSjm-93Jm_3RFZB5NVbydwzrO6HBrf9r_m242YJP9jZoyx3YcvUu7Azb5fVduO7jQW1zF76HyQZXsWXdLGfkUBo8CPMgzc9vPwLhKhZVzs1Ym3viC8NCNqFHuJx-deeMqB_O6IfCBQvpgpjPvEOSZV2xNdU4SjL0SwHCWmZJF-esJX1t7sHJ4P3Juw9Rm7khsghAeFTKxDpRaZNyK7iujMlSZzMiR4tLYRMctlmujELA5YzmWa5EmrgsNopWhZS4D716WruHwBQvBaJAXiqD7kZZujJCTj3OjLSZtH14tfp8hW1ZzSm5xnkR-Jh5ge-58O-5Dy860Vmg8viT0N5KB4rWmpsCh12Cp7hh9fOuGu2QFlfK2k2XJCOwmUki8j48CCrT3UVQLC0OpfugNpSpEyCO782aenLmub5zBBixFviYXpn-3vBieDz0O4_-XfQZ7BwdDIrDj6NPj-EGp2gdH6a4B73FfOmewDV7uZg086etYf0Cmqkq9Q
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=Improved+unsupervised+physics-informed+deep+learning+for+intravoxel+incoherent+motion+modeling+and+evaluation+in+pancreatic+cancer+patients&rft.jtitle=Magnetic+resonance+in+medicine&rft.au=Kaandorp%2C+Misha+P+T&rft.au=Barbieri%2C+Sebastiano&rft.au=Klaassen%2C+Remy&rft.au=van+Laarhoven%2C+Hanneke+W+M&rft.date=2021-10-01&rft.issn=1522-2594&rft.eissn=1522-2594&rft.volume=86&rft.issue=4&rft.spage=2250&rft_id=info:doi/10.1002%2Fmrm.28852&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0740-3194&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0740-3194&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0740-3194&client=summon