3D Segmentation of Perivascular Spaces on T1-Weighted 3 Tesla MR Images With a Convolutional Autoencoder and a U-Shaped Neural Network

We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance...

Full description

Saved in:

Bibliographic Details
Published in:	Frontiers in neuroinformatics Vol. 15; p. 641600
Main Authors:	Boutinaud, Philippe, Tsuchida, Ami, Laurent, Alexandre, Adonias, Filipa, Hanifehlou, Zahra, Nozais, Victor, Verrecchia, Violaine, Lampe, Leonie, Zhang, Junyi, Zhu, Yi-Cheng, Tzourio, Christophe, Mazoyer, Bernard, Joliot, Marc
Format:	Journal Article
Language:	English
Published:	Switzerland Frontiers Research Foundation 18.06.2021 Frontiers Media Frontiers Media S.A
Subjects:	Algorithms Basal ganglia brain cohort Brain research Cognitive ability Deep learning Dementia Life Sciences Magnetic resonance imaging Medical imaging Medical research MRI Neural networks Neuroscience Performance evaluation perivascular space Santé publique et épidémiologie Segmentation Substantia alba Traumatic brain injury U-net Young adults perivascular space deep learning segmentation brain cohort MRI U-net Deep learning Brain cohort Segmentation Perivascular space
ISSN:	1662-5196, 1662-5196
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults. An important feature of this approach is the ability to learn from relatively sparse data, which gives the present algorithm a major advantage over other DL algorithms. Here, we trained the algorithm with 40 T1-weighted MRI datasets in which all “visible” PVSs were manually annotated by an experienced operator. After learning, performance was assessed using another set of 10 MRI scans from the same database in which PVSs were also traced by the same operator and were checked by consensus with another experienced operator. The Sorensen-Dice coefficients for PVS voxel detection in DWM (resp. BG) were 0.51 (resp. 0.66), and 0.64 (resp. 0.71) for PVS cluster detection (volume threshold of 0.5 within a range of 0 to 1). Dice values above 0.90 could be reached for detecting PVSs larger than 10 mm 3 and 0.95 for PVSs larger than 15 mm 3 . We then applied the trained algorithm to the rest of the database (1,782 individuals). The individual PVS load provided by the algorithm showed a high agreement with a semi-quantitative visual rating done by an independent expert rater, both for DWM and for BG. Finally, we applied the trained algorithm to an age-matched sample from another MRI database acquired using a different scanner. We obtained a very similar distribution of PVS load, demonstrating the interoperability of this algorithm.
AbstractList	We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults. An important feature of this approach is the ability to learn from relatively sparse data, which gives the present algorithm a major advantage over other DL algorithms. Here, we trained the algorithm with 40 T1-weighted MRI datasets in which all “visible” PVSs were manually annotated by an experienced operator. After learning, performance was assessed using another set of 10 MRI scans from the same database in which PVSs were also traced by the same operator and were checked by consensus with another experienced operator. The Sorensen-Dice coefficients for PVS voxel detection in DWM (resp. BG) were 0.51 (resp. 0.66), and 0.64 (resp. 0.71) for PVS cluster detection (volume threshold of 0.5 within a range of 0 to 1). Dice values above 0.90 could be reached for detecting PVSs larger than 10 mm3 and 0.95 for PVSs larger than 15 mm3. We then applied the trained algorithm to the rest of the database (1,782 individuals). The individual PVS load provided by the algorithm showed a high agreement with a semi-quantitative visual rating done by an independent expert rater, both for DWM and for BG. Finally, we applied the trained algorithm to an age-matched sample from another MRI database acquired using a different scanner. We obtained a very similar distribution of PVS load, demonstrating the interoperability of this algorithm. We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults. An important feature of this approach is the ability to learn from relatively sparse data, which gives the present algorithm a major advantage over other DL algorithms. Here, we trained the algorithm with 40 T1-weighted MRI datasets in which all “visible” PVSs were manually annotated by an experienced operator. After learning, performance was assessed using another set of 10 MRI scans from the same database in which PVSs were also traced by the same operator and were checked by consensus with another experienced operator. The Sorensen-Dice coefficients for PVS voxel detection in DWM (resp. BG) were 0.51 (resp. 0.66), and 0.64 (resp. 0.71) for PVS cluster detection (volume threshold of 0.5 within a range of 0 to 1). Dice values above 0.90 could be reached for detecting PVSs larger than 10 mm 3 and 0.95 for PVSs larger than 15 mm 3 . We then applied the trained algorithm to the rest of the database (1,782 individuals). The individual PVS load provided by the algorithm showed a high agreement with a semi-quantitative visual rating done by an independent expert rater, both for DWM and for BG. Finally, we applied the trained algorithm to an age-matched sample from another MRI database acquired using a different scanner. We obtained a very similar distribution of PVS load, demonstrating the interoperability of this algorithm. We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults. An important feature of this approach is the ability to learn from relatively sparse data, which gives the present algorithm a major advantage over other DL algorithms. Here, we trained the algorithm with 40 T1-weighted MRI datasets in which all "visible" PVSs were manually annotated by an experienced operator. After learning, performance was assessed using another set of 10 MRI scans from the same database in which PVSs were also traced by the same operator and were checked by consensus with another experienced operator. The Sorensen-Dice coefficients for PVS voxel detection in DWM (resp. BG) were 0.51 (resp. 0.66), and 0.64 (resp. 0.71) for PVS cluster detection (volume threshold of 0.5 within a range of 0 to 1). Dice values above 0.90 could be reached for detecting PVSs larger than 10 mm(3) and 0.95 for PVSs larger than 15 mm(3). We then applied the trained algorithm to the rest of the database (1,782 individuals). The individual PVS load provided by the algorithm showed a high agreement with a semi-quantitative visual rating done by an independent expert rater, both for DWM and for BG. Finally, we applied the trained algorithm to an age-matched sample from another MRI database acquired using a different scanner. We obtained a very similar distribution of PVS load, demonstrating the interoperability of this algorithm. We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults. An important feature of this approach is the ability to learn from relatively sparse data, which gives the present algorithm a major advantage over other DL algorithms. Here, we trained the algorithm with 40 T1-weighted MRI datasets in which all "visible" PVSs were manually annotated by an experienced operator. After learning, performance was assessed using another set of 10 MRI scans from the same database in which PVSs were also traced by the same operator and were checked by consensus with another experienced operator. The Sorensen-Dice coefficients for PVS voxel detection in DWM (resp. BG) were 0.51 (resp. 0.66), and 0.64 (resp. 0.71) for PVS cluster detection (volume threshold of 0.5 within a range of 0 to 1). Dice values above 0.90 could be reached for detecting PVSs larger than 10 mm3 and 0.95 for PVSs larger than 15 mm3. We then applied the trained algorithm to the rest of the database (1,782 individuals). The individual PVS load provided by the algorithm showed a high agreement with a semi-quantitative visual rating done by an independent expert rater, both for DWM and for BG. Finally, we applied the trained algorithm to an age-matched sample from another MRI database acquired using a different scanner. We obtained a very similar distribution of PVS load, demonstrating the interoperability of this algorithm.We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults. An important feature of this approach is the ability to learn from relatively sparse data, which gives the present algorithm a major advantage over other DL algorithms. Here, we trained the algorithm with 40 T1-weighted MRI datasets in which all "visible" PVSs were manually annotated by an experienced operator. After learning, performance was assessed using another set of 10 MRI scans from the same database in which PVSs were also traced by the same operator and were checked by consensus with another experienced operator. The Sorensen-Dice coefficients for PVS voxel detection in DWM (resp. BG) were 0.51 (resp. 0.66), and 0.64 (resp. 0.71) for PVS cluster detection (volume threshold of 0.5 within a range of 0 to 1). Dice values above 0.90 could be reached for detecting PVSs larger than 10 mm3 and 0.95 for PVSs larger than 15 mm3. We then applied the trained algorithm to the rest of the database (1,782 individuals). The individual PVS load provided by the algorithm showed a high agreement with a semi-quantitative visual rating done by an independent expert rater, both for DWM and for BG. Finally, we applied the trained algorithm to an age-matched sample from another MRI database acquired using a different scanner. We obtained a very similar distribution of PVS load, demonstrating the interoperability of this algorithm. We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia (BG). This algorithm is based on an autoencoder and a U-shaped network (U-net), and was trained and tested using T1-weighted magnetic resonance imaging (MRI) data from a large database of 1,832 healthy young adults. An important feature of this approach is the ability to learn from relatively sparse data, which gives the present algorithm a major advantage over other DL algorithms. Here, we trained the algorithm with 40 T1-weighted MRI datasets in which all "visible" PVSs were manually annotated by an experienced operator. After learning, performance was assessed using another set of 10 MRI scans from the same database in which PVSs were also traced by the same operator and were checked by consensus with another experienced operator. The Sorensen-Dice coefficients for PVS voxel detection in DWM (resp. BG) were 0.51 (resp. 0.66), and 0.64 (resp. 0.71) for PVS cluster detection (volume threshold of 0.5 within a range of 0 to 1). Dice values above 0.90 could be reached for detecting PVSs larger than 10 mm and 0.95 for PVSs larger than 15 mm . We then applied the trained algorithm to the rest of the database (1,782 individuals). The individual PVS load provided by the algorithm showed a high agreement with a semi-quantitative visual rating done by an independent expert rater, both for DWM and for BG. Finally, we applied the trained algorithm to an age-matched sample from another MRI database acquired using a different scanner. We obtained a very similar distribution of PVS load, demonstrating the interoperability of this algorithm.
Author	Hanifehlou, Zahra Mazoyer, Bernard Joliot, Marc Laurent, Alexandre Zhu, Yi-Cheng Boutinaud, Philippe Verrecchia, Violaine Nozais, Victor Tsuchida, Ami Lampe, Leonie Tzourio, Christophe Adonias, Filipa Zhang, Junyi
AuthorAffiliation	6 Faculty of Computer Engineering, University of Isfahan , Isfahan , Iran 10 Centre Hospitalier Universitaire de Bordeaux , Bordeaux , France 5 UMR 5293, GIN, IMN, CEA , Bordeaux , France 4 UMR 5293, GIN, IMN, CNRS , Bordeaux , France 8 Department of Neurology, Peking Union Medical College Hospital , Beijing , China 3 UMR 5293, GIN, IMN, Univ. Bordeaux , Bordeaux , France 7 Integrative Model-based Cognitive Neuroscience Research Unit Universiteit van Amsterdam, Amsterdam, Netherlands & Max Planck Institute for Human Cognitive and Brain Sciences Leipzig , Germany 9 U1219, INSERM, Bordeaux Population Health, University Bordeaux , Bordeaux , France 1 Genesislab , Bordeaux , France 2 Fealinx , Lyon , France
AuthorAffiliation_xml	– name: 6 Faculty of Computer Engineering, University of Isfahan , Isfahan , Iran – name: 2 Fealinx , Lyon , France – name: 1 Genesislab , Bordeaux , France – name: 8 Department of Neurology, Peking Union Medical College Hospital , Beijing , China – name: 7 Integrative Model-based Cognitive Neuroscience Research Unit Universiteit van Amsterdam, Amsterdam, Netherlands & Max Planck Institute for Human Cognitive and Brain Sciences Leipzig , Germany – name: 9 U1219, INSERM, Bordeaux Population Health, University Bordeaux , Bordeaux , France – name: 3 UMR 5293, GIN, IMN, Univ. Bordeaux , Bordeaux , France – name: 10 Centre Hospitalier Universitaire de Bordeaux , Bordeaux , France – name: 5 UMR 5293, GIN, IMN, CEA , Bordeaux , France – name: 4 UMR 5293, GIN, IMN, CNRS , Bordeaux , France
Author_xml	– sequence: 1 givenname: Philippe surname: Boutinaud fullname: Boutinaud, Philippe – sequence: 2 givenname: Ami surname: Tsuchida fullname: Tsuchida, Ami – sequence: 3 givenname: Alexandre surname: Laurent fullname: Laurent, Alexandre – sequence: 4 givenname: Filipa surname: Adonias fullname: Adonias, Filipa – sequence: 5 givenname: Zahra surname: Hanifehlou fullname: Hanifehlou, Zahra – sequence: 6 givenname: Victor surname: Nozais fullname: Nozais, Victor – sequence: 7 givenname: Violaine surname: Verrecchia fullname: Verrecchia, Violaine – sequence: 8 givenname: Leonie surname: Lampe fullname: Lampe, Leonie – sequence: 9 givenname: Junyi surname: Zhang fullname: Zhang, Junyi – sequence: 10 givenname: Yi-Cheng surname: Zhu fullname: Zhu, Yi-Cheng – sequence: 11 givenname: Christophe surname: Tzourio fullname: Tzourio, Christophe – sequence: 12 givenname: Bernard surname: Mazoyer fullname: Mazoyer, Bernard – sequence: 13 givenname: Marc surname: Joliot fullname: Joliot, Marc
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/34262443$$D View this record in MEDLINE/PubMed https://hal.science/hal-03327352$$DView record in HAL
BookMark	eNp9kk2P0zAQhiO0iP2AH8AFWeIChxR_xHFyQarKx1YqC6JFe7QcZ9y6pHHXTor4A_xunM2y2u2Bk0czz7xjj9_z5KR1LSTJS4InjBXlO9Pa1kwopmSSZyTH-ElyRvKcppyU-cmD-DQ5D2GLcU5zLp4lpyyjOc0ydpb8YR_QEtY7aDvVWdciZ9A38Paggu4b5dFyrzQEFCsrkl6DXW86qBFDKwiNQl--o_lOrSNwbbsNUmjm2oNr-kFKNWjadw5a7WrwSLV1rP9Ilxu1jwpX0PtIXEH3y_mfz5OnRjUBXtydF8nq08fV7DJdfP08n00XqeZUdGnNNMsFZkIpyATBwhS4oBUlQmtlSlMpwqA2jCqaGcGFUKyiBZAYEs4Nu0jmo2zt1Fbuvd0p_1s6ZeVtwvm1VL6zugEJNWM51kVGcZmRShQEF3HDGqoqA6NZ1Ho_au37age1jhuMD3ok-rjS2o1cu4MsqGAlEVHg7SiwOWq7nC7kkMOMRZTTA4nsm7th3t30EDq5s0FD06gWXB8k5ZxiXlI8oK-P0K3rffyNgcoYL0SR8Ui9enj7-_n_nBEBMgLauxA8mHuEYDm4T966Tw7uk6P7Yo846tF2tFVcgG3-0_kX9HfeMw
CitedBy_id	crossref_primary_10_3389_fnins_2022_1021311 crossref_primary_10_1002_jmri_70023 crossref_primary_10_1038_s41591_023_02269_9 crossref_primary_10_1002_alz_70196 crossref_primary_10_1097_RLI_0000000000001077 crossref_primary_10_3389_fnins_2023_1038011 crossref_primary_10_1002_jmri_28369 crossref_primary_10_1016_j_neuroimage_2022_119528 crossref_primary_10_3390_life13101955 crossref_primary_10_1016_j_jneumeth_2023_110037 crossref_primary_10_1177_13872877251372926 crossref_primary_10_1186_s40035_023_00359_9 crossref_primary_10_1212_WNL_0000000000013077 crossref_primary_10_1038_s41598_023_34850_0 crossref_primary_10_1212_WNL_0000000000209306 crossref_primary_10_1016_j_neuroimage_2024_120803 crossref_primary_10_1016_j_ynirp_2023_100162 crossref_primary_10_1002_dad2_12578 crossref_primary_10_3389_fneur_2022_889884 crossref_primary_10_1016_j_parkreldis_2024_107089 crossref_primary_10_1016_j_mri_2022_07_016 crossref_primary_10_1016_j_neuroimage_2024_120685 crossref_primary_10_1186_s10194_025_02070_8 crossref_primary_10_3389_fnagi_2024_1457405 crossref_primary_10_1038_s41598_024_81870_5 crossref_primary_10_1007_s11357_025_01880_7 crossref_primary_10_1097_RCT_0000000000001720 crossref_primary_10_1093_cvr_cvae165 crossref_primary_10_3389_fneur_2025_1504645 crossref_primary_10_1002_hbm_26548 crossref_primary_10_1016_j_arr_2023_102042 crossref_primary_10_1016_j_neuroscience_2025_07_022 crossref_primary_10_1162_imag_a_00497 crossref_primary_10_3389_fnins_2025_1526897 crossref_primary_10_1002_alz_70212 crossref_primary_10_1016_j_cccb_2025_100396
Cites_doi	10.1016/j.neuroimage.2019.116126 10.1148/radiol.2017170205 10.1161/STROKEAHA.117.019309 10.1145/1656274.1656280 10.3174/ajnr.A2366 10.1109/TBME.2016.2638918 10.1161/STROKEAHA.109.564914 10.1161/STROKEAHA.110.591586 10.1212/WNL.0000000000001054 10.1212/WNL.0000000000007124 10.1097/NEN.0b013e31823ac627 10.1016/j.neuroimage.2015.02.071 10.1016/j.neuroimage.2015.10.078 10.1177/1747493019830321 10.1161/STROKEAHA.111.000620 10.1136/jnnp.2003.030858 10.1159/000375153 10.1038/s41598-018-19781-5 10.1016/j.neuroimage.2018.10.026 10.1038/s42256-019-0018-3 10.1109/34.232073 10.1001/jamaneurol.2018.3122 10.1038/s41592-020-01008-z 10.1101/2020.06.17.154666 10.1016/j.jneumeth.2015.09.010 10.1038/s41598-019-48910-x 10.1016/j.media.2020.101767 10.1001/jamaneurol.2017.1397 10.1084/jem.46.4.615 10.1016/S1474-4422(13)70124-8 10.1016/j.media.2020.101840 10.3233/JAD-2010-100378 10.1212/wnl.53.1.132 10.1042/CS20170051 10.1007/s10571-016-0343-6 10.1016/S1474-4422(07)70291-0 10.1109/ACCESS.2019.2896911 10.1016/j.media.2018.02.009 10.1109/TMI.2019.2959609
ContentType	Journal Article
Copyright	Copyright © 2021 Boutinaud, Tsuchida, Laurent, Adonias, Hanifehlou, Nozais, Verrecchia, Lampe, Zhang, Zhu, Tzourio, Mazoyer and Joliot. 2021. This work is licensed 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. Attribution Copyright © 2021 Boutinaud, Tsuchida, Laurent, Adonias, Hanifehlou, Nozais, Verrecchia, Lampe, Zhang, Zhu, Tzourio, Mazoyer and Joliot. 2021 Boutinaud, Tsuchida, Laurent, Adonias, Hanifehlou, Nozais, Verrecchia, Lampe, Zhang, Zhu, Tzourio, Mazoyer and Joliot
Copyright_xml	– notice: Copyright © 2021 Boutinaud, Tsuchida, Laurent, Adonias, Hanifehlou, Nozais, Verrecchia, Lampe, Zhang, Zhu, Tzourio, Mazoyer and Joliot. – notice: 2021. This work is licensed 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. – notice: Attribution – notice: Copyright © 2021 Boutinaud, Tsuchida, Laurent, Adonias, Hanifehlou, Nozais, Verrecchia, Lampe, Zhang, Zhu, Tzourio, Mazoyer and Joliot. 2021 Boutinaud, Tsuchida, Laurent, Adonias, Hanifehlou, Nozais, Verrecchia, Lampe, Zhang, Zhu, Tzourio, Mazoyer and Joliot
DBID	AAYXX CITATION NPM 3V. 7XB 88I 8FE 8FH 8FK ABUWG AFKRA AZQEC BBNVY BENPR BHPHI CCPQU DWQXO GNUQQ HCIFZ LK8 M2P M7P PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS Q9U 7X8 1XC VOOES 5PM DOA
DOI	10.3389/fninf.2021.641600
DatabaseName	CrossRef PubMed ProQuest Central (Corporate) ProQuest Central (purchase pre-March 2016) Science Database (Alumni Edition) ProQuest SciTech Collection ProQuest Natural Science Collection ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials Biological Science Collection ProQuest Central Natural Science Collection ProQuest One Community College ProQuest Central ProQuest Central Student SciTech Premium Collection ProQuest Biological Science Collection Science Database Biological Science Database ProQuest Central Premium ProQuest One Academic Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic MEDLINE - Academic Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access) PubMed Central (Full Participant titles) DOAJ Open Access Full Text
DatabaseTitle	CrossRef PubMed Publicly Available Content Database ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Natural Science Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences Natural Science Collection ProQuest Central Korea Biological Science Collection ProQuest Central (New) ProQuest Science Journals (Alumni Edition) ProQuest Biological Science Collection ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition Biological Science Database ProQuest SciTech Collection ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	CrossRef Publicly Available Content Database MEDLINE - Academic PubMed
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Anatomy & Physiology
EISSN	1662-5196
ExternalDocumentID	oai_doaj_org_article_ed3360c8420941b78108600cebb4efc3 PMC8273917 oai:HAL:hal-03327352v1 34262443 10_3389_fninf_2021_641600
Genre	Journal Article
GroupedDBID	--- 29H 2WC 53G 5GY 5VS 88I 8FE 8FH 9T4 AAFWJ AAKPC AAYXX ABUWG ACGFO ACGFS ADBBV ADRAZ AEGXH AENEX AFFHD AFKRA AFPKN AIAGR ALMA_UNASSIGNED_HOLDINGS AOIJS ARCSS AZQEC BAWUL BBNVY BCNDV BENPR BHPHI BPHCQ CCPQU CITATION CS3 DIK DWQXO E3Z F5P GNUQQ GROUPED_DOAJ GX1 HCIFZ HYE KQ8 LK8 M2P M48 M7P M~E O5R O5S OK1 OVT PGMZT PHGZM PHGZT PIMPY PQGLB PQQKQ PROAC RNS RPM TR2 ACXDI C1A IPNFZ NPM RIG 3V. 7XB 8FK PKEHL PQEST PQUKI PRINS Q9U 7X8 1XC VOOES 5PM
ID	FETCH-LOGICAL-c527t-d3c367037aae47107f8082b217ccaf9fba13edf32a24f7577a3b28e1757155f3
IEDL.DBID	M2P
ISICitedReferencesCount	39
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000671899100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1662-5196
IngestDate	Mon Nov 10 04:31:16 EST 2025 Tue Nov 04 02:01:15 EST 2025 Tue Oct 14 20:48:13 EDT 2025 Sun Nov 09 10:09:51 EST 2025 Fri Jul 25 11:58:42 EDT 2025 Mon Jul 21 06:04:39 EDT 2025 Sat Nov 29 02:31:32 EST 2025 Tue Nov 18 22:10:29 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Keywords	perivascular space deep learning segmentation brain cohort MRI U-net Deep learning Brain cohort Segmentation Perivascular space
Language	English
License	Copyright © 2021 Boutinaud, Tsuchida, Laurent, Adonias, Hanifehlou, Nozais, Verrecchia, Lampe, Zhang, Zhu, Tzourio, Mazoyer and Joliot. Attribution: http://creativecommons.org/licenses/by This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c527t-d3c367037aae47107f8082b217ccaf9fba13edf32a24f7577a3b28e1757155f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Reviewed by: Xiaoying Tang, Southern University of Science and Technology, China; Florian Dubost, Erasmus Medical Center, Netherlands Edited by: Sean L. Hill, Krembil Centre for Neuroinformatics, Centre for Addiction and Mental Health, Canada
ORCID	0000-0001-5160-6203 0000-0001-7792-308X 0000-0003-0970-2837 0000-0002-2385-3079 0000-0003-1138-7063 0000-0001-5198-6955 0000-0003-2529-1839 0000-0002-6517-2984
OpenAccessLink	https://www.proquest.com/docview/2543587845?pq-origsite=%requestingapplication%
PMID	34262443
PQID	2543587845
PQPubID	4424404
ParticipantIDs	doaj_primary_oai_doaj_org_article_ed3360c8420941b78108600cebb4efc3 pubmedcentral_primary_oai_pubmedcentral_nih_gov_8273917 hal_primary_oai_HAL_hal_03327352v1 proquest_miscellaneous_2552059201 proquest_journals_2543587845 pubmed_primary_34262443 crossref_primary_10_3389_fninf_2021_641600 crossref_citationtrail_10_3389_fninf_2021_641600
PublicationCentury	2000
PublicationDate	2021-06-18
PublicationDateYYYYMMDD	2021-06-18
PublicationDate_xml	– month: 06 year: 2021 text: 2021-06-18 day: 18
PublicationDecade	2020
PublicationPlace	Switzerland
PublicationPlace_xml	– name: Switzerland – name: Lausanne
PublicationTitle	Frontiers in neuroinformatics
PublicationTitleAlternate	Front Neuroinform
PublicationYear	2021
Publisher	Frontiers Research Foundation Frontiers Media Frontiers Media S.A
Publisher_xml	– name: Frontiers Research Foundation – name: Frontiers Media – name: Frontiers Media S.A
References	Glorot (B15) 2010 Zhu (B48) 2011; 32 Kingma (B21) 2013 Zhu (B50); 41 Zhou (B47) 2021; 67 Schwartz (B36) 2019; 202 Ronneberger (B34) 2015; 9351 Dubost (B11) 2020; 65 Milletari (B28) 2016 Tsuchida (B41) 2020 Pedregosa (B31) 2011; 12 Berthold (B5) 2009; 11 Schmidt (B35) 1999; 53 Seshadri (B38) 2007; 6 Jung (B20) 2019; 7 Ciresan (B7) 2011 Debette (B8) 2019; 76 Wang (B42) 2016; 257 Zhu (B49); 22 Adams (B2) 2013; 44 Lutnick (B24) 2019; 1 Lian (B23) 2018; 46 Sudre (B40) 2019; 102 Abadi (B1) 2016 Zhou (B46) 2020; 39 Potter (B32) 2015; 39 Huttenlocher (B17) 1993; 15 Lawrence (B22) 1927; 46 Sepehrband (B37) 2019; 9 Boespflug (B6) 2018; 286 Marin-Padilla (B26) 2011; 70 Isensee (B19) 2021; 18 Gonzalez-Castro (B16) 2017; 131 Zong (B51) 2016; 125 Srivastava (B39) 2014; 15 Duperron (B13) 2018; 49 Mazoyer (B27) 2016; 124 Dubost (B12) 2019; 185 Francis (B14) 2019; 14 Patek (B30) 1941; 38 Maclullich (B25) 2004; 75 Ramirez (B33) 2016; 36 Wardlaw (B43) 2013; 12 Passiak (B29) 2019; 92 Doubal (B10) 2010; 41 Yakushiji (B44) 2014; 83 Ding (B9) 2017; 74 Ballerini (B3) 2018; 8 Bergstra (B4) 2013 Ioffe (B18) 2015 Zhang (B45) 2017; 64
References_xml	– start-page: 265 year: 2016 ident: B1 article-title: TensorFlow: a system for large-scale machine learning publication-title: Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16) – volume: 202 year: 2019 ident: B36 article-title: Autoidentification of perivascular spaces in white matter using clinical field strength T1 and FLAIR MR imaging. publication-title: Neuroimage doi: 10.1016/j.neuroimage.2019.116126 – volume: 286 start-page: 632 year: 2018 ident: B6 article-title: MR Imaging-based multimodal autoidentification of perivascular spaces (mMAPS): automated morphologic segmentation of enlarged perivascular spaces at clinical field strength. publication-title: Radiology doi: 10.1148/radiol.2017170205 – start-page: 115 year: 2013 ident: B4 article-title: Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures publication-title: Proceedings of the 30th International Conference on International Conference on Machine Learning – volume: 49 start-page: 282 year: 2018 ident: B13 article-title: Burden of dilated perivascular spaces, an emerging marker of cerebral small vessel disease, is highly heritable. publication-title: Stroke doi: 10.1161/STROKEAHA.117.019309 – volume: 11 start-page: 26 year: 2009 ident: B5 article-title: KNIME - the konstanz information miner: version 2.0 and beyond. publication-title: SIGKDD Explor. Newsl. doi: 10.1145/1656274.1656280 – volume: 32 start-page: 709 year: 2011 ident: B48 article-title: Frequency and location of dilated virchow-robin spaces in elderly people: a population-based 3D MR imaging study. publication-title: AJNR Am. J. Neuroradiol. doi: 10.3174/ajnr.A2366 – volume: 64 start-page: 2803 year: 2017 ident: B45 article-title: Structured learning for 3-D perivascular space segmentation using vascular features. publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2016.2638918 – volume: 41 start-page: 450 year: 2010 ident: B10 article-title: Enlarged perivascular spaces on MRI are a feature of cerebral small vessel disease. publication-title: Stroke doi: 10.1161/STROKEAHA.109.564914 – volume: 41 start-page: 2483 ident: B50 article-title: Severity of dilated virchow-robin spaces is associated with age, blood pressure, and MRI markers of small vessel disease: a population-based study. publication-title: Stroke doi: 10.1161/STROKEAHA.110.591586 – start-page: 1237 year: 2011 ident: B7 article-title: Flexible, high performance convolutional neural networks for image classification publication-title: Proceedings of the 22nd International Joint Conference on Artificial Intelligence – year: 2015 ident: B18 article-title: Batch normalization: accelerating deep network training by reducing internal covariate shift publication-title: Proceedings of the 32nd International Conference on International Conference on Machine Learning – volume: 83 start-page: 2116 year: 2014 ident: B44 article-title: Topography and associations of perivascular spaces in healthy adults: the Kashima scan study. publication-title: Neurology doi: 10.1212/WNL.0000000000001054 – volume: 92 start-page: e1309 year: 2019 ident: B29 article-title: Perivascular spaces contribute to cognition beyond other small vessel disease markers. publication-title: Neurology doi: 10.1212/WNL.0000000000007124 – volume: 70 start-page: 1060 year: 2011 ident: B26 article-title: Developmental aspects of the intracerebral microvasculature and perivascular spaces: insights into brain response to late-life diseases. publication-title: J. Neuropathol. Exp. Neurol. doi: 10.1097/NEN.0b013e31823ac627 – volume: 124 start-page: 1225 year: 2016 ident: B27 article-title: BIL&GIN: a neuroimaging, cognitive, behavioral, and genetic database for the study of human brain lateralization. publication-title: Neuroimage doi: 10.1016/j.neuroimage.2015.02.071 – year: 2016 ident: B28 article-title: V-net: fully convolutional neural networks for volumetricmedical image segmentation publication-title: Proceedings of the 4th International Conference on 3D Vision – volume: 125 start-page: 895 year: 2016 ident: B51 article-title: Visualization of perivascular spaces in the human brain at 7 T: sequence optimization and morphology characterization. publication-title: Neuroimage doi: 10.1016/j.neuroimage.2015.10.078 – volume: 14 start-page: 359 year: 2019 ident: B14 article-title: Perivascular spaces and their associations with risk factors, clinical disorders and neuroimaging features: a systematic review and meta-analysis. publication-title: Int. J. Stroke doi: 10.1177/1747493019830321 – volume: 12 start-page: 2825 year: 2011 ident: B31 article-title: Scikit-learn: machine learning in python. publication-title: J. Mach. Learn. Res. – volume: 44 start-page: 1732 year: 2013 ident: B2 article-title: Rating method for dilated virchow-robin spaces on magnetic resonance imaging. publication-title: Stroke doi: 10.1161/STROKEAHA.111.000620 – volume: 75 start-page: 1519 year: 2004 ident: B25 article-title: Enlarged perivascular spaces are associated with cognitive function in healthy elderly men. publication-title: J. Neurol. Neurosurg. Psychiatry doi: 10.1136/jnnp.2003.030858 – volume: 39 start-page: 224 year: 2015 ident: B32 article-title: Cerebral perivascular spaces visible on magnetic resonance imaging: development of a qualitative rating scale and its observer reliability. publication-title: Cerebrovasc. Dis. doi: 10.1159/000375153 – volume: 102 start-page: 447 year: 2019 ident: B40 article-title: 3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects. publication-title: Procc. Mach. Learn. Res. – year: 2010 ident: B15 article-title: Understanding the difficulty of training deep forward neural networks publication-title: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics – volume: 8 year: 2018 ident: B3 article-title: Perivascular spaces segmentation in brain MRI using optimal 3D filtering. publication-title: Sci. Rep. doi: 10.1038/s41598-018-19781-5 – volume: 185 start-page: 534 year: 2019 ident: B12 article-title: Enlarged perivascular spaces in brain MRI: automated quantification in four regions. publication-title: Neuroimage doi: 10.1016/j.neuroimage.2018.10.026 – year: 2013 ident: B21 article-title: Auto-encoding variational bayes publication-title: Proceedings of the 2nd International Conference on Learning Representations (ICLR) – volume: 15 start-page: 1929 year: 2014 ident: B39 article-title: Dropout: a simple way to prevent neural networks from overfitting. publication-title: J. Mach. Learn. Res. – volume: 1 start-page: 112 year: 2019 ident: B24 article-title: An integrated iterative annotation technique for easing neural network training in medical image analysis. publication-title: Nat. Mach. Intell. doi: 10.1038/s42256-019-0018-3 – volume: 15 start-page: 850 year: 1993 ident: B17 article-title: Comparing images using the Hausdorff distance. publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.232073 – volume: 76 start-page: 81 year: 2019 ident: B8 article-title: Clinical Significance of magnetic resonance imaging markers of vascular brain injury: a systematic review and meta-analysis. publication-title: JAMA Neurol. doi: 10.1001/jamaneurol.2018.3122 – volume: 18 start-page: 203 year: 2021 ident: B19 article-title: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. publication-title: Nat. Methods doi: 10.1038/s41592-020-01008-z – year: 2020 ident: B41 article-title: The MRi-Share database: brain imaging in a cross-sectional cohort of 1,870 university students. publication-title: bioRxiv doi: 10.1101/2020.06.17.154666 – volume: 257 start-page: 34 year: 2016 ident: B42 article-title: Development and initial evaluation of a semi-automatic approach to assess perivascular spaces on conventional magnetic resonance images. publication-title: J. Neurosci. Methods doi: 10.1016/j.jneumeth.2015.09.010 – volume: 9 year: 2019 ident: B37 article-title: Image processing approaches to enhance perivascular space visibility and quantification using MRI. publication-title: Sci. Rep. doi: 10.1038/s41598-019-48910-x – volume: 65 year: 2020 ident: B11 article-title: Weakly supervised object detection with 2D and 3D regression neural networks. publication-title: Med. Image Anal. doi: 10.1016/j.media.2020.101767 – volume: 74 start-page: 1105 year: 2017 ident: B9 article-title: Large perivascular spaces visible on magnetic resonance imaging, cerebral small vessel disease progression, and risk of dementia. The Age, Gene/Environment Susceptibility-Reykjavik Study. publication-title: JAMA Neurol. doi: 10.1001/jamaneurol.2017.1397 – volume: 46 start-page: 615 year: 1927 ident: B22 article-title: A study of the perivascular tissues of the central nervous system with the supravital technique. publication-title: J. Exp. Med. doi: 10.1084/jem.46.4.615 – volume: 12 start-page: 822 year: 2013 ident: B43 article-title: Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration. publication-title: Lancet Neurol. doi: 10.1016/S1474-4422(13)70124-8 – volume: 67 year: 2021 ident: B47 article-title: Models genesis. publication-title: Med. Image Anal. doi: 10.1016/j.media.2020.101840 – volume: 22 start-page: 663 ident: B49 article-title: High degree of dilated virchow-robin spaces on MRI is associated with increased risk of dementia. publication-title: J. Alzheimers Dis doi: 10.3233/JAD-2010-100378 – volume: 53 start-page: 132 year: 1999 ident: B35 article-title: MRI white matter hyperintensities: three-year follow-up of the austrian stroke prevention study. publication-title: Neurology doi: 10.1212/wnl.53.1.132 – volume: 131 start-page: 1465 year: 2017 ident: B16 article-title: Reliability of an automatic classifier for brain enlarged perivascular spaces burden and comparison with human performance. publication-title: Clin Sci (Lond) doi: 10.1042/CS20170051 – volume: 38 start-page: 1 year: 1941 ident: B30 article-title: The perivascular spaces of the mammalian brain. publication-title: Anat. Rec. – volume: 36 start-page: 289 year: 2016 ident: B33 article-title: Imaging the perivascular space as a potential biomarker of neurovascular and neurodegenerative diseases. publication-title: Cell Mol. Neurobiol. doi: 10.1007/s10571-016-0343-6 – volume: 6 start-page: 1106 year: 2007 ident: B38 article-title: Lifetime risk of stroke and dementia: current concepts, and estimates from the Framingham Study. publication-title: Lancet Neurol. doi: 10.1016/S1474-4422(07)70291-0 – volume: 9351 start-page: 234 year: 2015 ident: B34 article-title: U-net: Convolutional networks for biomedical image segmentation. publication-title: Med. Image Comput. Comp. Assist. Interv. – volume: 7 start-page: 18382 year: 2019 ident: B20 article-title: Enhancement of perivascular spaces using densely connected deep convolutional neural network. publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2896911 – volume: 46 start-page: 106 year: 2018 ident: B23 article-title: Multi-channel multi-scale fully convolutional network for 3D perivascular spaces segmentation in 7T MR images. publication-title: Med. Image Anal. doi: 10.1016/j.media.2018.02.009 – volume: 39 start-page: 1856 year: 2020 ident: B46 article-title: U-net++: redesigning skip connections to exploit multiscale features in image segmentation. publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2019.2959609
SSID	ssj0062657
Score	2.4386082
Snippet	We implemented a deep learning (DL) algorithm for the 3-dimensional segmentation of perivascular spaces (PVSs) in deep white matter (DWM) and basal ganglia...
SourceID	doaj pubmedcentral hal proquest pubmed crossref
SourceType	Open Website Open Access Repository Aggregation Database Index Database Enrichment Source
StartPage	641600
SubjectTerms	Algorithms Basal ganglia brain cohort Brain research Cognitive ability Deep learning Dementia Life Sciences Magnetic resonance imaging Medical imaging Medical research MRI Neural networks Neuroscience Performance evaluation perivascular space Santé publique et épidémiologie Segmentation Substantia alba Traumatic brain injury U-net Young adults
SummonAdditionalLinks	– databaseName: DOAJ Open Access Full Text dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nj9MwELXQigMXBCwfgQUZhDgghU3spLaPZWG1SFCtaNHuLXL8sa1EnapNK_EH-N3MOGnVggQXjomdZOR5jt84kzeEvFa1yo1mAF7HXFrYQqZw5FOhIJoQWW5rm8ViE2I0ktfX6nKv1BfmhHXywN3AnTrL-SAzsmAQiOS1kFgaKMuMq-vCeRN1PjOhtsFU9w4Gll6K7hsmhGDq1AdwFwSDLH83AAaCv7PtrUJRrB_WlimmQv7JM39Pl9xbf87vkbs9caTDzuD75JYLD8jxMEDQPP9B39CYyhn3yI_JT_6Bjt3NvP-vKNDG00uA2jbtlI4XmIlFoWWSp1dxd9RZyunEAULol6_00xzeMyt6NWunVNOzJmx6iKIJ67ZB-UvrllQHC-3f0vFUL-AOKPUBPUZdbvlDMjn_ODm7SPuCC6kpmWhTyw3quXGhtYNFKxNeAkOoIWoBP3vla51zZz1nmhVelEJoXjPpgIEIoCWePyJHoQnuCaHGmcFAlVxpA5SHacmU5bVR0hSKcy4Skm3HvzK9GDnWxPheQVCCLquiyyp0WdW5LCFvd5csOiWOv3V-j07ddUQR7XgCoFX10Kr-Ba2EvAJIHNzjYvi5wnMZ58D7SrbJE3KyRUzVT_9VhQoDpRSyKBPyctcMExe_xujgmjX2KRlwWyBgCXncAWz3KI51AooCLBAH0Duw5bAlzKZRHFyCXRCCP_0fA_CM3MExxcy4XJ6Qo3a5ds_JbbNpZ6vlizjjfgGhpC74 priority: 102 providerName: Directory of Open Access Journals
Title	3D Segmentation of Perivascular Spaces on T1-Weighted 3 Tesla MR Images With a Convolutional Autoencoder and a U-Shaped Neural Network
URI	https://www.ncbi.nlm.nih.gov/pubmed/34262443 https://www.proquest.com/docview/2543587845 https://www.proquest.com/docview/2552059201 https://hal.science/hal-03327352 https://pubmed.ncbi.nlm.nih.gov/PMC8273917 https://doaj.org/article/ed3360c8420941b78108600cebb4efc3
Volume	15
WOSCitedRecordID	wos000671899100001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1662-5196 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062657 issn: 1662-5196 databaseCode: DOA dateStart: 20070101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1662-5196 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062657 issn: 1662-5196 databaseCode: M~E dateStart: 20070101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 1662-5196 dateEnd: 20211231 omitProxy: false ssIdentifier: ssj0062657 issn: 1662-5196 databaseCode: M7P dateStart: 20071102 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1662-5196 dateEnd: 20211231 omitProxy: false ssIdentifier: ssj0062657 issn: 1662-5196 databaseCode: BENPR dateStart: 20071102 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1662-5196 dateEnd: 20211231 omitProxy: false ssIdentifier: ssj0062657 issn: 1662-5196 databaseCode: PIMPY dateStart: 20071102 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database (subscription) customDbUrl: eissn: 1662-5196 dateEnd: 20211231 omitProxy: false ssIdentifier: ssj0062657 issn: 1662-5196 databaseCode: M2P dateStart: 20071102 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3Nb9MwFLfYxoELX-MjMCqDEAeksMROaueEutFpk2gVrUUrp8ixnbUSTUq_JC4c-bt5z0nLCtIuXCIlz0mf-n62f89-fo-Qt0mehFoxAK9l1o9MJH24K3yRgDchgtDkJnDFJkS_L0ejJG0W3BZNWOVmTHQDtak0rpEf46HtWAoZxR9n332sGoW7q00JjT1yAMwmxJCuHks3IzFw9VjUO5ngiCXHRQlGA5eQhR_awEPwUNuNucil7IcZZowBkf-yzb-DJm_MQmcP_lf_h-R-wz9ppwbMI3LHlo_JYacE33v6g76jLiLULbUfkl_8Ex3Y62lzPKmkVUFTQOwmepUOZhjQRUEyDP0rt8hqDeV0aAFotHdJL6YwXC3o1WQ5poqeVuW6QTqqsFpWmEXT2DlVpQH5F38wVjP4AmYMgRb9OkT9CRmedYen535Tt8HXMRNL33CNaeG4UMrC3BeIQgLRyMH5AbgUSZGrkFtTcKZYVIhYCMVzJi0QGQHspuBPyX5ZlfY5odrqdjuJeaI0MCemJEsMz3UidZRwzoVHgo0BM93kNMfSGt8y8G3Q5pmzeYY2z2qbe-T99pVZndDjtsYniIptQ8zF7R5U8-us6dqZNZy3Ay0jBq5ymAuJxauCQNs8j2yhuUfeAKZ2vnHe-Zzhs4BzoI8xW4ceOdrAJmtGkUX2BzMeeb0VQ__HTR1V2mqFbWIGFBl4nEee1Qjd_hTHcgNRBBqIHezu6LIrKSdjl2Ncgl7gyb-4Xa2X5B7-Wxg6F8ojsr-cr-wrclevl5PFvEX2xEi2yMFJt59ettxqR8t1ULwKd_3ZBXl60Uu__gaOOETP
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bb9MwFLbGQIIXbuMSGGAQ8IAUlthJbT8gVDamVuuqihZtb5HjOGslmpQ2Ldof4N_wHzknl7KCtLc98JjYcU6c79zs43MIea1i5RvNALyWWTdIAunCVeoKBd6E8PwkTryy2ITo9-XpqRpskV_NWRgMq2xkYimok9zgGvkeHtoOpZBB-HH23cWqUbi72pTQqGBxZM9_gMu2-NA9gP_7hrHDz6P9jltXFXBNyEThJtxg0jIutLYgmT2RSlCDMZjm8DGpSmPtc5uknGkWpCIUQvOYSQtqVoDuTTkMe41cDzCxGEYKskEj-ME1CEW1cQp-n9pLM8AIeKDMf98CswfP0F1QfWWFAFBoY4y__Ne4_TtG84LSO7zzn03XXXK7tq5pu2KHe2TLZvfJTjvTRT49p29pGe9abiTskJ_8gA7t2bQ-fJXRPKUD4McmNpcOZxiuRqFl5Lsn5RKyTSinIwtsRI-_0O4UhPGCnkyKMdV0P89WNR8jCcsixxyhiZ1TnSXQ_tUdjvUMRsB8KNCjXwXgPyCjq5iQh2Q7yzP7mFBjTaulQq60AbuQaclUwmOjpAkU51w4xGvwEpk6YzsWDvkWgeeGEItKiEUIsaiCmEPerR-ZVelKLuv8CUG47oiZxssb-fwsqgVXZBPOW56RAfNU4MdCYmkuzzM2jgObGu6QVwDhjTE67V6E9zzOwTgO2cp3yG6D0qiWkYvoD0Qd8nLdDNINt6x0ZvMl9gkZOABgpTrkUcUQ61dxLKYQBECB2GCVDVo2W7LJuMygLoEu5Ysnl5P1gtzsjI57Ua_bP3pKbuHMYZCgL3fJdjFf2mfkhlkVk8X8eSkHKImumJF-Ay1LmNw
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bb9MwFLZGhxAv3MalMMAg4AEpNLGT2n5AqKxUq7ZVFSvaeIocx1kr0aS0adH-AP-Jf8c5uZQVpL3tgcfEjnPifOdmH59DyCsVKc9oBuC1zDp-7EsHrhJHKPAmhOvFUewWxSbEYCBPT9Vwi_yqz8JgWGUtEwtBHWcG18hbeGg7kEL6QSupwiKG3d6H2XcHK0jhTmtdTqOEyIE9_wHu2-J9vwv_-jVjvU-jvX2nqjDgmICJ3Im5wQRmXGhtQUq7IpGgEiMw0-HDEpVE2uM2TjjTzE9EIITmEZMWVK4APZxwGPYa2QaL3GcNsj3sHw2_1moAHIVAlNuo4AWqVpICYsAfZd67NhhBeKLugiIs6gWAehtjNOa_pu7fEZsXVGDv9n88eXfIrcrupp2SUe6SLZveIzudVOfZ9Jy-oUUkbLHFsEN-8i49tmfT6lhWSrOEDoFT66hdejzDQDYKLSPPOSkWl21MOR1ZYDB69Jn2pyCmF_Rkko-ppntZuqo4HElY5hlmD43tnOo0hvYvzvFYz2AEzJQCPQZlaP59MrqKCXlAGmmW2keEGmvabRVwpQ1YjExLpmIeGSWNrzjnokncGjuhqXK5Y0mRbyH4dAi3sIBbiHALS7g1ydv1I7MykcllnT8iINcdMQd5cSObn4WVSAttzHnbNdJnrvK9SEgs2uW6xkaRbxPDm-QlwHljjP3OYYj3XM7BbA7YymuS3RqxYSU9F-EfuDbJi3UzyD3czNKpzZbYJ2DgGoD92iQPS-ZYv4pjmQXfBwrEBtts0LLZkk7GRW51CXQpTzy-nKzn5AbwT3jYHxw8ITdx4jB60JO7pJHPl_YpuW5W-WQxf1YJBUrCK-ak39YAoyU
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=3D+Segmentation+of+Perivascular+Spaces+on+T1-Weighted+3+Tesla+MR+Images+With+a+Convolutional+Autoencoder+and+a+U-Shaped+Neural+Network&rft.jtitle=Frontiers+in+neuroinformatics&rft.au=Boutinaud%2C+Philippe&rft.au=Tsuchida%2C+Ami&rft.au=Laurent%2C+Alexandre&rft.au=Adonias%2C+Filipa&rft.date=2021-06-18&rft.pub=Frontiers+Media+S.A&rft.eissn=1662-5196&rft.volume=15&rft_id=info:doi/10.3389%2Ffninf.2021.641600&rft_id=info%3Apmid%2F34262443&rft.externalDocID=PMC8273917
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1662-5196&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1662-5196&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1662-5196&client=summon