Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI
Current deep learning approaches for diffusion MRI modeling circumvent the need for densely-sampled diffusion-weighted images (DWIs) by directly predicting microstructural indices from sparsely-sampled DWIs. However, they implicitly make unrealistic assumptions of static q-space sampling during trai...
Saved in:
Published in | Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 pp. 530 - 540 |
---|---|
Main Authors | , , , |
Format | Book Chapter |
Language | English |
Published |
Cham
Springer International Publishing
2021
|
Series | Lecture Notes in Computer Science |
Online Access | Get full text |
Cover
Loading…
Abstract | Current deep learning approaches for diffusion MRI modeling circumvent the need for densely-sampled diffusion-weighted images (DWIs) by directly predicting microstructural indices from sparsely-sampled DWIs. However, they implicitly make unrealistic assumptions of static q-space sampling during training and reconstruction. Further, such approaches can restrict downstream usage of variably sampled DWIs for usages including the estimation of microstructural indices or tractography. We propose a generative adversarial translation framework for high-quality DWI synthesis with arbitrary q-space sampling given commonly acquired structural images (e.g., B0, T1, T2). Our translation network linearly modulates its internal representations conditioned on continuous q-space information, thus removing the need for fixed sampling schemes. Moreover, this approach enables downstream estimation of high-quality microstructural maps from arbitrarily subsampled DWIs, which may be particularly important in cases with sparsely sampled DWIs. Across several recent methodologies, the proposed approach yields improved DWI synthesis accuracy and fidelity with enhanced downstream utility as quantified by the accuracy of scalar microstructure indices estimated from the synthesized images. Code is available at https://github.com/mengweiren/q-space-conditioned-dwi-synthesis. |
---|---|
AbstractList | Current deep learning approaches for diffusion MRI modeling circumvent the need for densely-sampled diffusion-weighted images (DWIs) by directly predicting microstructural indices from sparsely-sampled DWIs. However, they implicitly make unrealistic assumptions of static q-space sampling during training and reconstruction. Further, such approaches can restrict downstream usage of variably sampled DWIs for usages including the estimation of microstructural indices or tractography. We propose a generative adversarial translation framework for high-quality DWI synthesis with arbitrary q-space sampling given commonly acquired structural images (e.g., B0, T1, T2). Our translation network linearly modulates its internal representations conditioned on continuous q-space information, thus removing the need for fixed sampling schemes. Moreover, this approach enables downstream estimation of high-quality microstructural maps from arbitrarily subsampled DWIs, which may be particularly important in cases with sparsely sampled DWIs. Across several recent methodologies, the proposed approach yields improved DWI synthesis accuracy and fidelity with enhanced downstream utility as quantified by the accuracy of scalar microstructure indices estimated from the synthesized images. Code is available at https://github.com/mengweiren/q-space-conditioned-dwi-synthesis. |
Author | Dey, Neel Kim, Heejong Gerig, Guido Ren, Mengwei |
Author_xml | – sequence: 1 givenname: Mengwei surname: Ren fullname: Ren, Mengwei – sequence: 2 givenname: Heejong surname: Kim fullname: Kim, Heejong email: heejong.kim@nyu.edu – sequence: 3 givenname: Neel surname: Dey fullname: Dey, Neel – sequence: 4 givenname: Guido surname: Gerig fullname: Gerig, Guido |
BookMark | eNpFkMtOwzAQRQ0Uibb0D1j4Bwx-JLWzROVVqQUBRSwtx482NI0rOxFixa_jFCRWM3PvzB3pjMCg8Y0F4ILgS4Ixvyq4QAxhhpHglGWIyhwfgRFLykFgx2BIpoQgxrLi5N9g-QAMU09RwTN2BiYxfmCMKWdUED4E388o7pW2cOYbU7VV-mrgKqgm1qqf4KNtP33YRuh8gDdVsLqXVQ1fv5p2Y2MVoXfJcK6L_f67rdabNoXMd2pt01nwO7js6rZCO2_6uzZ0uu1Capcv83Nw6lQd7eSvjsHb3e1q9oAWT_fz2fUCaVoIjLTQWWlsRqhjpRWs5DkVguPc5AVJhlNThcWUlKVxjlo3zbEqDDcFES7TOmdjQH9z4z5UzdoGWXq_jZJg2fOVia9kMoGSB5yy58t-AGJlbf8 |
CitedBy_id | crossref_primary_10_3389_fneur_2023_1168833 crossref_primary_10_1016_j_nicl_2023_103483 |
ContentType | Book Chapter |
Copyright | Springer Nature Switzerland AG 2021 |
Copyright_xml | – notice: Springer Nature Switzerland AG 2021 |
DOI | 10.1007/978-3-030-87234-2_50 |
DatabaseTitleList | |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Applied Sciences Computer Science |
EISBN | 3030872343 9783030872342 |
EISSN | 1611-3349 |
Editor | Cotin, Stéphane Essert, Caroline Cattin, Philippe C. de Bruijne, Marleen Speidel, Stefanie Padoy, Nicolas Zheng, Yefeng |
Editor_xml | – sequence: 1 givenname: Marleen orcidid: 0000-0002-6328-902X surname: de Bruijne fullname: de Bruijne, Marleen email: marleen.debruijne@erasmusmc.nl – sequence: 2 givenname: Philippe C. orcidid: 0000-0001-8785-2713 surname: Cattin fullname: Cattin, Philippe C. email: philippe.cattin@unibas.ch – sequence: 3 givenname: Stéphane orcidid: 0000-0002-2661-505X surname: Cotin fullname: Cotin, Stéphane email: stephane.cotin@inria.fr – sequence: 4 givenname: Nicolas orcidid: 0000-0002-5010-4137 surname: Padoy fullname: Padoy, Nicolas email: npadoy@unistra.fr – sequence: 5 givenname: Stefanie orcidid: 0000-0002-4590-1908 surname: Speidel fullname: Speidel, Stefanie email: stefanie.speidel@nct-dresden.de – sequence: 6 givenname: Yefeng orcidid: 0000-0003-2195-2847 surname: Zheng fullname: Zheng, Yefeng email: yefengzheng@tencent.com – sequence: 7 givenname: Caroline orcidid: 0000-0003-2572-9730 surname: Essert fullname: Essert, Caroline email: essert@unistra.fr |
EndPage | 540 |
GroupedDBID | -DT -GH -~X 1SB 29L 2HA 2HV 5QI 875 AASHB ABMNI ACGFS ADCXD AEFIE ALMA_UNASSIGNED_HOLDINGS EJD F5P FEDTE HVGLF LAS LDH P2P RIG RNI RSU SVGTG VI1 ~02 |
ID | FETCH-LOGICAL-c2980-c8c4bde412f3be83b75288705d591bdefa6a0861bbdff2ef650a9d7d918f4cc53 |
ISBN | 3030872335 9783030872335 |
ISSN | 0302-9743 |
IngestDate | Tue Oct 01 19:52:08 EDT 2024 |
IsDoiOpenAccess | false |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c2980-c8c4bde412f3be83b75288705d591bdefa6a0861bbdff2ef650a9d7d918f4cc53 |
Notes | Electronic supplementary materialThe online version of this chapter (https://doi.org/10.1007/978-3-030-87234-2_50) contains supplementary material, which is available to authorized users. M. Ren and H. Kim—These authors contributed equally. |
OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9662206 |
PageCount | 11 |
ParticipantIDs | springer_books_10_1007_978_3_030_87234_2_50 |
PublicationCentury | 2000 |
PublicationDate | 2021-00-00 |
PublicationDateYYYYMMDD | 2021-01-01 |
PublicationDate_xml | – year: 2021 text: 2021-00-00 |
PublicationDecade | 2020 |
PublicationPlace | Cham |
PublicationPlace_xml | – name: Cham |
PublicationSeriesSubtitle | Image Processing, Computer Vision, Pattern Recognition, and Graphics |
PublicationSeriesTitle | Lecture Notes in Computer Science |
PublicationSeriesTitleAlternate | Lect.Notes Computer |
PublicationSubtitle | 24th International Conference, Strasbourg, France, September 27 – October 1, 2021, Proceedings, Part VII |
PublicationTitle | Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 |
PublicationYear | 2021 |
Publisher | Springer International Publishing |
Publisher_xml | – name: Springer International Publishing |
RelatedPersons | Hartmanis, Juris Gao, Wen Bertino, Elisa Woeginger, Gerhard Goos, Gerhard Steffen, Bernhard Yung, Moti |
RelatedPersons_xml | – sequence: 1 givenname: Gerhard surname: Goos fullname: Goos, Gerhard – sequence: 2 givenname: Juris surname: Hartmanis fullname: Hartmanis, Juris – sequence: 3 givenname: Elisa surname: Bertino fullname: Bertino, Elisa – sequence: 4 givenname: Wen surname: Gao fullname: Gao, Wen – sequence: 5 givenname: Bernhard orcidid: 0000-0001-9619-1558 surname: Steffen fullname: Steffen, Bernhard – sequence: 6 givenname: Gerhard orcidid: 0000-0001-8816-2693 surname: Woeginger fullname: Woeginger, Gerhard – sequence: 7 givenname: Moti orcidid: 0000-0003-0848-0873 surname: Yung fullname: Yung, Moti |
SSID | ssj0002732817 ssj0002792 |
Score | 2.0884182 |
Snippet | Current deep learning approaches for diffusion MRI modeling circumvent the need for densely-sampled diffusion-weighted images (DWIs) by directly predicting... |
SourceID | springer |
SourceType | Publisher |
StartPage | 530 |
Title | Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI |
URI | http://link.springer.com/10.1007/978-3-030-87234-2_50 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07b9swECbcdCk69I22aQoO3QwWEh-SNWQI0jyRBGiatNkESSQBB7A12EaRLP3L_Qm940NSnCzpIti0IYl3H47He3wk5IuRPK_ATWXKpJLJTBpW2zRlqtBq0shCG479zqdn2eGlPL5SV6PR30HV0mpZf21uH-wr-R-twhjoFbtkH6HZ7qYwAJ9Bv3AFDcN1zfm9G2adRppaFPDRDMtu_OkMseMwntWA0kc9ah_5i7WNscJBjEEJuztHY57wTvTn3hBhuetvM-1z9DO_SpnrNix26P6Gk6uN6Qo1DmDiznwcrKa6HSLyOwPr1eCrYpocGZK051b35XjYe4xVYo4gIppiF6f8cTMHNzUwp3ybWrvCEN_4l4vq4txQAgvfKeMaitms1ZXLuK8azytyeu6jw6gWs9g-CZmTs3bpCtJ6gQVbNwyG8HQtGBKDoWvh1D6id2f3LBwdIheeLyV2kcEKAXssb3SNXxQypHoUnlo1GHoVskneZ1CecurecjSsQIE7M3yaZLzEINOTvAAr_HRn7_jkZxcV5MidlHYhgwTpHX0ezL8Vdid1b-35o_rvg87Qhx55L9fvXKiLl-Q5ttVQ7HcBob0iIzN_TV6ETRANYl_AUFRFHHtD_gTk0AFy6AA5NCKHAnLoADm0Qw5tLe2QQyNyqEcOReTQAXJojxwKyHlLLvf3LnYPWTg4hDW8mCSsAStTayNTbkVtJqLOFYfFNFFaFSn8YKusgq18WtfaWm4s7FKqQue6SCdWNo0S78jGHObynlBeaKtELSstKmklbO-tynSeGFj4wNm2H8g4CrVEU7AoIw84qKAUJaigdCooUQUfH_XvTfKsx_gnsgFTN1vgAi_rzwE3_wBGz6wq |
link.rule.ids | 785,786,790,799,27956 |
linkProvider | Library Specific Holdings |
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%3Abook&rft.genre=bookitem&rft.title=Medical+Image+Computing+and+Computer+Assisted+Intervention+%E2%80%93+MICCAI+2021&rft.au=Ren%2C+Mengwei&rft.au=Kim%2C+Heejong&rft.au=Dey%2C+Neel&rft.au=Gerig%2C+Guido&rft.atitle=Q-space+Conditioned+Translation+Networks+for+Directional+Synthesis+of+Diffusion+Weighted+Images+from+Multi-modal+Structural+MRI&rft.series=Lecture+Notes+in+Computer+Science&rft.date=2021-01-01&rft.pub=Springer+International+Publishing&rft.isbn=9783030872335&rft.issn=0302-9743&rft.eissn=1611-3349&rft.spage=530&rft.epage=540&rft_id=info:doi/10.1007%2F978-3-030-87234-2_50 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0302-9743&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0302-9743&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0302-9743&client=summon |