Fast contour propagation for MR‐guided prostate radiotherapy using convolutional neural networks

Purpose To quickly and automatically propagate organ contours from pretreatment to fraction images in magnetic resonance (MR)‐guided prostate external‐beam radiotherapy. Methods Five prostate cancer patients underwent 20 fractions of image‐guided external‐beam radiotherapy on a 1.5 T MR‐Linac system...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Medical physics (Lancaster) Ročník 47; číslo 3; s. 1238 - 1248
Hlavní autori:	Eppenhof, K.A.J., Maspero, M., Savenije, M.H.F., de Boer, J.C.J., van der Voort van Zyp, J.R.N., Raaymakers, B.W., Raaijmakers, A.J.E., Veta, M., van den Berg, C.A.T., Pluim, J.P.W.
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States John Wiley and Sons Inc 01.03.2020
Predmet:	contour propagation deep learning Dose Fractionation, Radiation EMERGING IMAGING AND THERAPY MODALITIES Humans Image Processing, Computer-Assisted - methods image registration Magnetic Resonance Imaging Male MR-guided radiotherapy Neural Networks, Computer prostate Prostatic Neoplasms - diagnostic imaging Prostatic Neoplasms - radiotherapy Radiotherapy, Image-Guided Time Factors MR-guided radiotherapy contour propagation deep learning prostate image registration
ISSN:	0094-2405, 2473-4209, 2473-4209
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Purpose To quickly and automatically propagate organ contours from pretreatment to fraction images in magnetic resonance (MR)‐guided prostate external‐beam radiotherapy. Methods Five prostate cancer patients underwent 20 fractions of image‐guided external‐beam radiotherapy on a 1.5 T MR‐Linac system. For each patient, a pretreatment T2‐weighted three‐dimensional (3D) MR imaging (MRI) scan was used to delineate the clinical target volume (CTV) contours. The same scan was repeated during each fraction, with the CTV contour being manually adapted if necessary. A convolutional neural network (CNN) was trained for combined image registration and contour propagation. The network estimated the propagated contour and a deformation field between the two input images. The training set consisted of a synthetically generated ground truth of randomly deformed images and prostate segmentations. We performed a leave‐one‐out cross‐validation on the five patients and propagated the prostate segmentations from the pretreatment to the fraction scans. Three variants of the CNN, aimed at investigating supervision based on optimizing segmentation overlap, optimizing the registration, and a combination of the two were compared to results of the open‐source deformable registration software package Elastix. Results The neural networks trained on segmentation overlap or the combined objective achieved significantly better Hausdorff distances between predicted and ground truth contours than Elastix, at the much faster registration speed of 0.5 s. The CNN variant trained to optimize both the prostate overlap and deformation field, and the variant trained to only maximize the prostate overlap, produced the best propagation results. Conclusions A CNN trained on maximizing prostate overlap and minimizing registration errors provides a fast and accurate method for deformable contour propagation for prostate MR‐guided radiotherapy.
AbstractList	To quickly and automatically propagate organ contours from pretreatment to fraction images in magnetic resonance (MR)-guided prostate external-beam radiotherapy.PURPOSETo quickly and automatically propagate organ contours from pretreatment to fraction images in magnetic resonance (MR)-guided prostate external-beam radiotherapy.Five prostate cancer patients underwent 20 fractions of image-guided external-beam radiotherapy on a 1.5 T MR-Linac system. For each patient, a pretreatment T2-weighted three-dimensional (3D) MR imaging (MRI) scan was used to delineate the clinical target volume (CTV) contours. The same scan was repeated during each fraction, with the CTV contour being manually adapted if necessary. A convolutional neural network (CNN) was trained for combined image registration and contour propagation. The network estimated the propagated contour and a deformation field between the two input images. The training set consisted of a synthetically generated ground truth of randomly deformed images and prostate segmentations. We performed a leave-one-out cross-validation on the five patients and propagated the prostate segmentations from the pretreatment to the fraction scans. Three variants of the CNN, aimed at investigating supervision based on optimizing segmentation overlap, optimizing the registration, and a combination of the two were compared to results of the open-source deformable registration software package Elastix.METHODSFive prostate cancer patients underwent 20 fractions of image-guided external-beam radiotherapy on a 1.5 T MR-Linac system. For each patient, a pretreatment T2-weighted three-dimensional (3D) MR imaging (MRI) scan was used to delineate the clinical target volume (CTV) contours. The same scan was repeated during each fraction, with the CTV contour being manually adapted if necessary. A convolutional neural network (CNN) was trained for combined image registration and contour propagation. The network estimated the propagated contour and a deformation field between the two input images. The training set consisted of a synthetically generated ground truth of randomly deformed images and prostate segmentations. We performed a leave-one-out cross-validation on the five patients and propagated the prostate segmentations from the pretreatment to the fraction scans. Three variants of the CNN, aimed at investigating supervision based on optimizing segmentation overlap, optimizing the registration, and a combination of the two were compared to results of the open-source deformable registration software package Elastix.The neural networks trained on segmentation overlap or the combined objective achieved significantly better Hausdorff distances between predicted and ground truth contours than Elastix, at the much faster registration speed of 0.5 s. The CNN variant trained to optimize both the prostate overlap and deformation field, and the variant trained to only maximize the prostate overlap, produced the best propagation results.RESULTSThe neural networks trained on segmentation overlap or the combined objective achieved significantly better Hausdorff distances between predicted and ground truth contours than Elastix, at the much faster registration speed of 0.5 s. The CNN variant trained to optimize both the prostate overlap and deformation field, and the variant trained to only maximize the prostate overlap, produced the best propagation results.A CNN trained on maximizing prostate overlap and minimizing registration errors provides a fast and accurate method for deformable contour propagation for prostate MR-guided radiotherapy.CONCLUSIONSA CNN trained on maximizing prostate overlap and minimizing registration errors provides a fast and accurate method for deformable contour propagation for prostate MR-guided radiotherapy. Purpose To quickly and automatically propagate organ contours from pretreatment to fraction images in magnetic resonance (MR)‐guided prostate external‐beam radiotherapy. Methods Five prostate cancer patients underwent 20 fractions of image‐guided external‐beam radiotherapy on a 1.5 T MR‐Linac system. For each patient, a pretreatment T2‐weighted three‐dimensional (3D) MR imaging (MRI) scan was used to delineate the clinical target volume (CTV) contours. The same scan was repeated during each fraction, with the CTV contour being manually adapted if necessary. A convolutional neural network (CNN) was trained for combined image registration and contour propagation. The network estimated the propagated contour and a deformation field between the two input images. The training set consisted of a synthetically generated ground truth of randomly deformed images and prostate segmentations. We performed a leave‐one‐out cross‐validation on the five patients and propagated the prostate segmentations from the pretreatment to the fraction scans. Three variants of the CNN, aimed at investigating supervision based on optimizing segmentation overlap, optimizing the registration, and a combination of the two were compared to results of the open‐source deformable registration software package Elastix. Results The neural networks trained on segmentation overlap or the combined objective achieved significantly better Hausdorff distances between predicted and ground truth contours than Elastix, at the much faster registration speed of 0.5 s. The CNN variant trained to optimize both the prostate overlap and deformation field, and the variant trained to only maximize the prostate overlap, produced the best propagation results. Conclusions A CNN trained on maximizing prostate overlap and minimizing registration errors provides a fast and accurate method for deformable contour propagation for prostate MR‐guided radiotherapy. To quickly and automatically propagate organ contours from pretreatment to fraction images in magnetic resonance (MR)-guided prostate external-beam radiotherapy. Five prostate cancer patients underwent 20 fractions of image-guided external-beam radiotherapy on a 1.5 T MR-Linac system. For each patient, a pretreatment T2-weighted three-dimensional (3D) MR imaging (MRI) scan was used to delineate the clinical target volume (CTV) contours. The same scan was repeated during each fraction, with the CTV contour being manually adapted if necessary. A convolutional neural network (CNN) was trained for combined image registration and contour propagation. The network estimated the propagated contour and a deformation field between the two input images. The training set consisted of a synthetically generated ground truth of randomly deformed images and prostate segmentations. We performed a leave-one-out cross-validation on the five patients and propagated the prostate segmentations from the pretreatment to the fraction scans. Three variants of the CNN, aimed at investigating supervision based on optimizing segmentation overlap, optimizing the registration, and a combination of the two were compared to results of the open-source deformable registration software package Elastix. The neural networks trained on segmentation overlap or the combined objective achieved significantly better Hausdorff distances between predicted and ground truth contours than Elastix, at the much faster registration speed of 0.5 s. The CNN variant trained to optimize both the prostate overlap and deformation field, and the variant trained to only maximize the prostate overlap, produced the best propagation results. A CNN trained on maximizing prostate overlap and minimizing registration errors provides a fast and accurate method for deformable contour propagation for prostate MR-guided radiotherapy.
Author	van der Voort van Zyp, J.R.N. Pluim, J.P.W. Raaijmakers, A.J.E. Raaymakers, B.W. van den Berg, C.A.T. Eppenhof, K.A.J. Savenije, M.H.F. de Boer, J.C.J. Veta, M. Maspero, M.
AuthorAffiliation	3 Department of Radiotherapy University Medical Center Utrecht Utrecht The Netherlands 2 Computational Imaging Group for MR Diagnostics & Therapy, Center for Image Sciences University Medical Center Utrecht Utrecht The Netherlands 4 Image Sciences Institute University Medical Center Utrecht Utrecht The Netherlands 1 Medical Image Analysis Group, Department of Biomedical Engineering Eindhoven University of Technology Eindhoven The Netherlands
AuthorAffiliation_xml	– name: 4 Image Sciences Institute University Medical Center Utrecht Utrecht The Netherlands – name: 1 Medical Image Analysis Group, Department of Biomedical Engineering Eindhoven University of Technology Eindhoven The Netherlands – name: 3 Department of Radiotherapy University Medical Center Utrecht Utrecht The Netherlands – name: 2 Computational Imaging Group for MR Diagnostics & Therapy, Center for Image Sciences University Medical Center Utrecht Utrecht The Netherlands
Author_xml	– sequence: 1 givenname: K.A.J. surname: Eppenhof fullname: Eppenhof, K.A.J. email: k.a.j.eppenhof@tue.nl organization: Eindhoven University of Technology – sequence: 2 givenname: M. surname: Maspero fullname: Maspero, M. organization: University Medical Center Utrecht – sequence: 3 givenname: M.H.F. surname: Savenije fullname: Savenije, M.H.F. organization: University Medical Center Utrecht – sequence: 4 givenname: J.C.J. surname: de Boer fullname: de Boer, J.C.J. organization: University Medical Center Utrecht – sequence: 5 givenname: J.R.N. surname: van der Voort van Zyp fullname: van der Voort van Zyp, J.R.N. organization: University Medical Center Utrecht – sequence: 6 givenname: B.W. surname: Raaymakers fullname: Raaymakers, B.W. organization: University Medical Center Utrecht – sequence: 7 givenname: A.J.E. surname: Raaijmakers fullname: Raaijmakers, A.J.E. organization: University Medical Center Utrecht – sequence: 8 givenname: M. surname: Veta fullname: Veta, M. organization: Eindhoven University of Technology – sequence: 9 givenname: C.A.T. surname: van den Berg fullname: van den Berg, C.A.T. organization: University Medical Center Utrecht – sequence: 10 givenname: J.P.W. surname: Pluim fullname: Pluim, J.P.W. organization: University Medical Center Utrecht
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/31876300$$D View this record in MEDLINE/PubMed
BookMark	eNp1kctO3DAUhi1EBcNF4gmqLLvJ9PgyE2dTqUJcKoFaVWVtnTjOYJrYqe0wmh2PwDPyJM3MUGirdnUW5_v_c_kPyK7zzhByQmFKAdj7rp9SXpZih0yYKHguGJS7ZAJQipwJmO2TgxjvAGDOZ7BH9jmVxZwDTEh1jjFl2rvkh5D1wfe4wGS9yxofsuuvTw-Pi8HWpl73YsJksoC19enWBOxX2RCtW6z1974d1jpsM2eGsClp6cP3eETeNNhGc_xcD8nN-dm308v86vPFp9OPV7kWFEQ-Z01Ri7rSjFLJyprVmiMtUAqmKzGexzQyqYUUJQMhkFaymQmKkulZhRL5Ifmw9e2HqjO1Ni6Na6g-2A7DSnm06s-Os7dq4e9VAUUJpRwN3j0bBP9jMDGpzkZt2had8UNUjPORpKKAEX37-6yXIb8e--qlx7fFYJoXhIJaZ6a6Xm0yG9HpX6i2aZPBuKVt_yXIt4Klbc3qv8bq-suW_wkDEqoN
CitedBy_id	crossref_primary_10_1016_j_radonc_2022_09_004 crossref_primary_10_3390_s21124085 crossref_primary_10_1002_mp_16056 crossref_primary_10_1002_mp_16397 crossref_primary_10_1007_s10278_023_00779_z crossref_primary_10_1002_mp_17000 crossref_primary_10_1007_s11547_023_01708_4 crossref_primary_10_1259_bjro_20230030 crossref_primary_10_1016_j_ejmp_2022_08_011 crossref_primary_10_1177_15330338251350909 crossref_primary_10_1016_j_phro_2023_100483 crossref_primary_10_1088_1361_6560_ade8d0 crossref_primary_10_1016_j_radonc_2024_110345 crossref_primary_10_1088_1361_6560_ac60b9 crossref_primary_10_1109_ACCESS_2021_3090825 crossref_primary_10_1186_s13014_020_01524_4 crossref_primary_10_1186_s13014_020_01528_0 crossref_primary_10_1016_j_zemedi_2023_05_001 crossref_primary_10_3389_fonc_2021_634507 crossref_primary_10_1002_mp_15793 crossref_primary_10_1016_j_semradonc_2022_06_003 crossref_primary_10_1016_j_semradonc_2022_06_001 crossref_primary_10_1016_j_phro_2023_100498 crossref_primary_10_1016_j_zemedi_2025_04_008 crossref_primary_10_1007_s00066_024_02277_9 crossref_primary_10_1016_j_bspc_2023_104755 crossref_primary_10_1140_epjp_s13360_024_05660_8 crossref_primary_10_1016_j_semradonc_2022_06_007 crossref_primary_10_1186_s13014_023_02330_4 crossref_primary_10_1016_j_ejmp_2021_05_010 crossref_primary_10_1016_j_phro_2022_06_001 crossref_primary_10_1186_s13014_020_01571_x crossref_primary_10_1016_j_radonc_2021_12_007 crossref_primary_10_1016_j_phro_2022_06_005
Cites_doi	10.1118/1.2965263 10.1118/1.2842076 10.1007/978-3-319-67558-9_24 10.1007/978-3-030-00928-1_82 10.1109/TMI.2019.2953788 10.1117/12.2292443 10.1016/j.ijrobp.2019.03.051 10.1117/1.JMI.4.4.041302 10.1117/1.JMI.5.2.021208 10.1109/TMI.2018.2878316 10.1016/j.media.2018.07.002 10.1023/A:1020830525823 10.1118/1.2222077 10.1088/0031-9155/60/22/R323 10.1088/0031-9155/60/7/2837 10.1109/TMI.2006.872745 10.1016/j.radonc.2019.01.024 10.1007/978-3-319-67558-9_28 10.1109/TBME.2018.2822826 10.1609/aaai.v31i1.10510 10.1007/978-3-030-00946-5_2 10.1117/12.2512824 10.1007/978-3-319-66182-7_27 10.1007/978-3-319-66182-7_35 10.1016/j.clon.2018.08.009 10.1117/12.2506962 10.1088/1361-6560/aa9517 10.1007/s11548-018-1841-4 10.1109/CVPR.2018.00964 10.1016/j.radonc.2016.04.014 10.1016/S1361-8415(01)80026-8 10.1109/TMI.2009.2035616 10.1117/12.2512428 10.1088/1361-6560/ab5539 10.1007/978-3-319-46723-8_49 10.1016/j.media.2018.11.010 10.1088/0031-9155/54/12/N01 10.1109/ICCV.2015.316 10.1016/j.semradonc.2014.02.008 10.1016/j.ijrobp.2019.08.007 10.1007/978-3-319-66182-7_31 10.1056/NEJMoa1606220 10.1002/mp.13416
ContentType	Journal Article
Copyright	2019 The Authors. Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.
Copyright_xml	– notice: 2019 The Authors. Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.
DBID	24P AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 5PM
DOI	10.1002/mp.13994
DatabaseName	Wiley Online Library Open Access CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic MEDLINE
Database_xml	– sequence: 1 dbid: 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	Prostate contour propagation in MRgRT
EISSN	2473-4209
EndPage	1248
ExternalDocumentID	PMC7079098 31876300 10_1002_mp_13994 MP13994
Genre	article Journal Article
GroupedDBID	--- --Z -DZ .GJ 0R~ 1OB 1OC 24P 29M 2WC 33P 36B 3O- 4.4 53G 5GY 5RE 5VS AAHHS AAHQN AAIPD AAMNL AANLZ AAQQT AASGY AAXRX AAYCA AAZKR ABCUV ABDPE ABEFU ABFTF ABJNI ABLJU ABQWH ABTAH ABXGK ACAHQ ACBEA ACCFJ ACCZN ACGFO ACGFS ACGOF ACPOU ACXBN ACXQS ADBBV ADBTR ADKYN ADOZA ADXAS ADZMN AEEZP AEGXH AEIGN AENEX AEQDE AEUYR AFBPY AFFPM AFWVQ AHBTC AIACR AIAGR AITYG AIURR AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMYDB ASPBG BFHJK C45 CS3 DCZOG DRFUL DRMAN DRSTM DU5 EBD EBS EJD EMB EMOBN F5P HDBZQ HGLYW I-F KBYEO LATKE LEEKS LOXES LUTES LYRES MEWTI O9- OVD P2P P2W PALCI PHY RJQFR RNS ROL SAMSI SUPJJ SV3 TEORI TN5 TWZ USG WOHZO WXSBR XJT ZGI ZVN ZXP ZY4 ZZTAW AAMMB AAYXX ABUFD ADMLS AEFGJ AEYWJ AGHNM AGXDD AGYGG AIDQK AIDYY AIQQE CITATION LH4 CGR CUY CVF ECM EIF NPM 7X8 5PM
ID	FETCH-LOGICAL-c4104-62f7d4dbc211829d2dc3a17a842cb41392ca28c48492044a1b8f541a82c5ba8a3
IEDL.DBID	24P
ISICitedReferencesCount	40
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000508900600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0094-2405 2473-4209
IngestDate	Tue Nov 04 01:59:23 EST 2025 Thu Oct 02 06:53:10 EDT 2025 Mon Jul 21 06:00:02 EDT 2025 Sat Nov 29 06:02:41 EST 2025 Tue Nov 18 22:49:39 EST 2025 Wed Jan 22 16:34:05 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	3
Keywords	MR-guided radiotherapy contour propagation deep learning prostate image registration
Language	English
License	Attribution 2019 The Authors. Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists 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-c4104-62f7d4dbc211829d2dc3a17a842cb41392ca28c48492044a1b8f541a82c5ba8a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
OpenAccessLink	https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmp.13994
PMID	31876300
PQID	2330791470
PQPubID	23479
PageCount	11
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_7079098 proquest_miscellaneous_2330791470 pubmed_primary_31876300 crossref_primary_10_1002_mp_13994 crossref_citationtrail_10_1002_mp_13994 wiley_primary_10_1002_mp_13994_MP13994
PublicationCentury	2000
PublicationDate	March 2020
PublicationDateYYYYMMDD	2020-03-01
PublicationDate_xml	– month: 03 year: 2020 text: March 2020
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: Hoboken
PublicationTitle	Medical physics (Lancaster)
PublicationTitleAlternate	Med Phys
PublicationYear	2020
Publisher	John Wiley and Sons Inc
Publisher_xml	– name: John Wiley and Sons Inc
References	2017; 62 2017; 4 2019; 52 2002; 50 2006; 33 2019; 104 2019; 105 2019; 38 2014; 24 2008; 35 2003; 19 2018; 65 2018; 49 2009; 54 2018; 5 2015; 60 2019; 64 2016; 119 2010; 29 2019; 46 2006; 25 2019 2016; 375 2018 2017 2018; 30 2016 1998; 2 2015 2019; 134 2018; 13 e_1_2_7_6_1 e_1_2_7_5_1 e_1_2_7_4_1 e_1_2_7_3_1 Bol G (e_1_2_7_39_1) 2003; 19 e_1_2_7_9_1 e_1_2_7_8_1 e_1_2_7_7_1 e_1_2_7_19_1 e_1_2_7_18_1 e_1_2_7_17_1 e_1_2_7_16_1 e_1_2_7_40_1 e_1_2_7_2_1 e_1_2_7_15_1 e_1_2_7_41_1 e_1_2_7_14_1 e_1_2_7_42_1 e_1_2_7_13_1 e_1_2_7_43_1 e_1_2_7_12_1 e_1_2_7_44_1 e_1_2_7_11_1 e_1_2_7_45_1 e_1_2_7_10_1 e_1_2_7_46_1 e_1_2_7_47_1 e_1_2_7_26_1 e_1_2_7_27_1 e_1_2_7_28_1 e_1_2_7_29_1 e_1_2_7_30_1 e_1_2_7_25_1 e_1_2_7_31_1 e_1_2_7_24_1 e_1_2_7_32_1 e_1_2_7_23_1 e_1_2_7_33_1 e_1_2_7_22_1 e_1_2_7_34_1 e_1_2_7_21_1 e_1_2_7_35_1 e_1_2_7_20_1 e_1_2_7_36_1 e_1_2_7_37_1 e_1_2_7_38_1
References_xml	– volume: 49 start-page: 1 year: 2018 end-page: 13 article-title: Weakly‐supervised convolutional neural networks for multimodal image registration publication-title: Med Image Anal – volume: 13 start-page: 1687 year: 2018 end-page: 1696 article-title: Deep dense multi‐path neural network for prostate segmentation in magnetic resonance imaging publication-title: Int J Comput Assist Radiol Surg – volume: 2 start-page: 1 year: 1998 end-page: 36 article-title: A survey of medical image registration publication-title: Med Image Anal – volume: 134 start-page: 50 year: 2019 end-page: 54 article-title: Feasibility of stereotactic radiotherapy using a 1.5T MRlinac: multi‐fraction treatment of pelvic lymph node oligometastases publication-title: Radiother Oncol – volume: 4 start-page: 1 year: 2017 end-page: 12 article-title: Automatic magnetic resonance prostate segmentation by deep learning with holistically nested networks publication-title: J Med Imag – volume: 30 start-page: 692 year: 2018 end-page: 701 article-title: Magnetic resonance imaging only workflow for radiotherapy simulation and planning in prostate cancer publication-title: Clin Oncol (R Coll Radiol) – volume: 54 start-page: N229 year: 2009 end-page: N237 article-title: Integrating a 1.5 T MRI scanner with a 6 MV accelerator: proof of concept publication-title: Phys Med Biol – volume: 60 start-page: 2837 year: 2015 end-page: 2851 article-title: An adaptive MR‐CT registration method for MRI‐guided prostate cancer radiotherapy publication-title: Phys Med Biol – volume: 65 start-page: 1900 year: 2018 end-page: 1911 article-title: Deformable image registration using a cue‐aware deep regression network publication-title: IEEE Trans Biomed Eng – volume: 119 start-page: 371 year: 2016 end-page: 380 article-title: MRI‐guided prostate adaptive radiotherapy: a systematic review publication-title: Radiother Oncol – year: 2016 – volume: 33 start-page: 3304 year: 2006 end-page: 3312 article-title: A deformable image registration method to handle distended rectums in prostate cancer radiotherapy publication-title: Med Phys – year: 2018 – volume: 64 start-page: 235008 year: 2019 article-title: Soft‐tissue prostate intrafraction motion tracking in 3D cine‐MR for MR‐guided radiotherapy publication-title: Phys Med Biol – volume: 104 start-page: 778 year: 2019 end-page: 789 article-title: Stereotactic body radiation therapy for localized prostate cancer: a systematic review and meta‐analysis of over 6,000 patients treated on prospective studies publication-title: Int J Radiat Oncol Biol Phys – volume: 35 start-page: 4019 year: 2008 end-page: 4025 article-title: Accuracy and sensitivity of finite element model‐based deformable registration of the prostate publication-title: Med Phys – volume: 5 start-page: 1 year: 2018 end-page: 6 article-title: PSNet: prostate segmentation on MRI based on a convolutional neural network publication-title: J Med Imag – volume: 52 start-page: 128 year: 2019 end-page: 143 article-title: A deep learning framework for unsupervised affine and deformable image registration publication-title: Med Image Anal – volume: 35 start-page: 1407 year: 2008 end-page: 1417 article-title: Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information publication-title: Med Phys – year: 2019 article-title: Progressively trained convolutional neural networks for deformable image registration publication-title: IEEE Trans Med Imaging – volume: 60 start-page: R323 year: 2015 end-page: R361 article-title: Radiotherapy planning using MRI publication-title: Phys Med Biol – volume: 375 start-page: 1415 year: 2016 end-page: 1424 article-title: 10‐Year outcomes after monitoring, surgery, or radiotherapy for localized prostate cancer publication-title: N Engl J Med – volume: 19 start-page: 80 year: 2003 article-title: Volumetool: an image evaluation, registration, and delineation system for radiotherapy publication-title: Physica Med – volume: 62 start-page: L41 year: 2017 end-page: L50 article-title: First patients treated with a 1.5 T MRI‐Linac: clinical proof of concept of a high‐precision, high‐field MRI guided radiotherapy treatment publication-title: Phys Med Biol – volume: 24 start-page: 196 year: 2014 end-page: 199 article-title: The viewray system: magnetic resonance guided and controlled radiotherapy publication-title: Semin Radiat Oncol – volume: 46 start-page: 1707 year: 2019 end-page: 1718 article-title: Deeply supervised 3D fully convolutional networks with group dilated convolution for automatic MRI prostate segmentation publication-title: Med Phys – volume: 50 start-page: 329 year: 2002 end-page: 343 article-title: Variational methods for multimodal image matching publication-title: Int J Comput Vision – volume: 38 start-page: 1097 year: 2019 end-page: 1105 article-title: Registration through supervised learning with convolutional neural networks publication-title: IEEE Trans Med Imaging – 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 – year: 2017 – year: 2019 – volume: 25 start-page: 626 year: 2006 end-page: 639 article-title: Deformation‐based mapping of volume change from serial brain MRI in the presence of local tissue contrast change publication-title: IEEE Trans Med Imaging – volume: 105 start-page: 1086 year: 2019 end-page: 1094 article-title: A prospective single‐arm phase II study of stereotactic magnetic‐resonance‐guided adaptive radiotherapy for prostate cancer: early toxicity results publication-title: Int J Radiat Oncol – year: 2015 – ident: e_1_2_7_14_1 doi: 10.1118/1.2965263 – ident: e_1_2_7_13_1 doi: 10.1118/1.2842076 – ident: e_1_2_7_22_1 doi: 10.1007/978-3-319-67558-9_24 – ident: e_1_2_7_25_1 doi: 10.1007/978-3-030-00928-1_82 – ident: e_1_2_7_38_1 doi: 10.1109/TMI.2019.2953788 – ident: e_1_2_7_33_1 doi: 10.1117/12.2292443 – ident: e_1_2_7_5_1 doi: 10.1016/j.ijrobp.2019.03.051 – ident: e_1_2_7_17_1 doi: 10.1117/1.JMI.4.4.041302 – ident: e_1_2_7_18_1 doi: 10.1117/1.JMI.5.2.021208 – ident: e_1_2_7_37_1 doi: 10.1109/TMI.2018.2878316 – ident: e_1_2_7_36_1 doi: 10.1016/j.media.2018.07.002 – ident: e_1_2_7_45_1 doi: 10.1023/A:1020830525823 – ident: e_1_2_7_12_1 doi: 10.1118/1.2222077 – ident: e_1_2_7_40_1 – ident: e_1_2_7_3_1 doi: 10.1088/0031-9155/60/22/R323 – ident: e_1_2_7_15_1 doi: 10.1088/0031-9155/60/7/2837 – ident: e_1_2_7_44_1 doi: 10.1109/TMI.2006.872745 – ident: e_1_2_7_10_1 doi: 10.1016/j.radonc.2019.01.024 – ident: e_1_2_7_46_1 doi: 10.1007/978-3-319-67558-9_28 – ident: e_1_2_7_34_1 doi: 10.1109/TBME.2018.2822826 – ident: e_1_2_7_16_1 doi: 10.1609/aaai.v31i1.10510 – ident: e_1_2_7_26_1 doi: 10.1007/978-3-030-00946-5_2 – ident: e_1_2_7_28_1 doi: 10.1117/12.2512824 – ident: e_1_2_7_32_1 doi: 10.1007/978-3-319-66182-7_27 – ident: e_1_2_7_30_1 doi: 10.1007/978-3-319-66182-7_35 – ident: e_1_2_7_4_1 doi: 10.1016/j.clon.2018.08.009 – ident: e_1_2_7_27_1 doi: 10.1117/12.2506962 – ident: e_1_2_7_8_1 doi: 10.1088/1361-6560/aa9517 – ident: e_1_2_7_19_1 doi: 10.1007/s11548-018-1841-4 – ident: e_1_2_7_23_1 doi: 10.1109/CVPR.2018.00964 – ident: e_1_2_7_11_1 doi: 10.1016/j.radonc.2016.04.014 – ident: e_1_2_7_21_1 doi: 10.1016/S1361-8415(01)80026-8 – ident: e_1_2_7_43_1 doi: 10.1109/TMI.2009.2035616 – ident: e_1_2_7_35_1 doi: 10.1117/12.2512428 – ident: e_1_2_7_47_1 doi: 10.1088/1361-6560/ab5539 – ident: e_1_2_7_41_1 doi: 10.1007/978-3-319-46723-8_49 – ident: e_1_2_7_24_1 doi: 10.1016/j.media.2018.11.010 – ident: e_1_2_7_6_1 doi: 10.1088/0031-9155/54/12/N01 – ident: e_1_2_7_29_1 doi: 10.1109/ICCV.2015.316 – ident: e_1_2_7_7_1 doi: 10.1016/j.semradonc.2014.02.008 – ident: e_1_2_7_9_1 doi: 10.1016/j.ijrobp.2019.08.007 – ident: e_1_2_7_31_1 doi: 10.1007/978-3-319-66182-7_31 – ident: e_1_2_7_2_1 doi: 10.1056/NEJMoa1606220 – ident: e_1_2_7_42_1 – volume: 19 start-page: 80 year: 2003 ident: e_1_2_7_39_1 article-title: Volumetool: an image evaluation, registration, and delineation system for radiotherapy publication-title: Physica Med – ident: e_1_2_7_20_1 doi: 10.1002/mp.13416
SSID	ssj0006350
Score	2.4933474
Snippet	Purpose To quickly and automatically propagate organ contours from pretreatment to fraction images in magnetic resonance (MR)‐guided prostate external‐beam... To quickly and automatically propagate organ contours from pretreatment to fraction images in magnetic resonance (MR)-guided prostate external-beam...
SourceID	pubmedcentral proquest pubmed crossref wiley
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	1238
SubjectTerms	contour propagation deep learning Dose Fractionation, Radiation EMERGING IMAGING AND THERAPY MODALITIES Humans Image Processing, Computer-Assisted - methods image registration Magnetic Resonance Imaging Male MR-guided radiotherapy Neural Networks, Computer prostate Prostatic Neoplasms - diagnostic imaging Prostatic Neoplasms - radiotherapy Radiotherapy, Image-Guided Time Factors
Title	Fast contour propagation for MR‐guided prostate radiotherapy using convolutional neural networks
URI	https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmp.13994 https://www.ncbi.nlm.nih.gov/pubmed/31876300 https://www.proquest.com/docview/2330791470 https://pubmed.ncbi.nlm.nih.gov/PMC7079098
Volume	47
WOSCitedRecordID	wos000508900600001&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 Full Collection 2020 customDbUrl: eissn: 2473-4209 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006350 issn: 0094-2405 databaseCode: DRFUL dateStart: 19970101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NTtwwEB4VKBWX_lBK0x-USghOKbEz2dhHRLvqgUUrVKS9RY6T0JUgrDa7SNz6CDwjT8KMkw1dQaVKvcSKPE6szHhmHM98A7AreqawYSkDFo8ARY6BKkUcSFSGrF9Yxqp0xSaSkxM1GulhG1XJuTANPkT3w41XhtPXvMBNVh88gIZeTr6S96JxBdaEiBSXbZA47LQwGdIm_UQjnyDEC-DZUB4sRi6bokf-5eMwyT_dV2d_-q_-Z-av4WXrdfqHjZi8gWdFtQkvBu25-iasu0BQW7-FrG_qmc8B7DTGp9mSwnHM88m79Qend79vz-fjvMi5z2Uj-VOTj9s8rhuf4-jPefx1K9P0WsbMdI2LOK-34Kz__efRj6CtwxBYpN1a0JNlkmOeWcm7EZ3L3EZGJEahtBkZQS2tkcqiQi1DRCMyVcYojJI2zowy0TtYra6q4j34ZY_uY2VL1bNkFrWxSGbUxNpiXOhIe7C_YElqW5ByrpVxkTbwyjK9nKTu43nwpaOcNMAcT9EsuJrSquGjEFMVV_M6lRHpNi0wCT3YbrjcPYW0XMJAZB4kS_zvCBiRe7mnGv9yyNwMNxhq5cGe4_9fJ5YOhq798K-EH2FD8kbfBb99gtXZdF58huf2ejaupztO8umajNQOrH077Z8d3wMrKAq3
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT9wwEB7xKLSXPigtaWmbSlV7CiTeycYWp6qwomJ3hRBI3CLHSWClElabXSRu_Qn9jfwSZpwHrGilSpysyOPEyjxtz3wG-BJ0dWb8XHgsHh4GKXoyD0JPoNTk_fw8lLm9bCIaDuXpqTpcgJ2mFqbCh2g33FgzrL1mBecN6e071NCL8RaFLwoXYRlJiki8l3ePeif91hCTL60qUBTyIULYYM_6YrsZO--NHoSYDzMl70ew1gX1Xjxq8i_heR15ut8rUXkFC1mxBquD-mx9DVZsMqgpX0PS0-XU5SR2GuPSdMnoWAa6FOG6g6Ob33_OZqM0S7nPViS5E52O6lqua5dz6c94_FUt1_RZxs20jc06L9fhpLd3_GPfq-9i8AzSis3rijxKMU2M4BWJSkVqOjqItERhEnKEShgtpEGJSviIOkhkHmKgpTBhoqXuvIGl4rLINsDNu_QcSpPLriHXqLRBcqU6VAbDTHWUA98ansSmBirn-zJ-xRXEsogvxrH9eQ58binHFTjH32gatsakOXwcoovsclbGokP2TQUY-Q68rdjcvoUsXcRgZA5EcwLQEjAq93xPMTq36NwMOegr6cBXKwD_nFg8OLTtu_8l_ARP948H_bj_c3jwHp4JXvjbZLhNWJpOZtkHeGKupqNy8rFWhFs6aA21
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fa9RAEB_qVYsvrdaqqa1GEH1Km-xNLrv4JG2DYu84ioW-hc1utj2w6XG5K_jmR_Az9pN0Z_PHHlUQfFpCZpMl83ezM78BeBcNZKFCwwISjwAjjQE3URww5NJ6v9DE3LhmE8loxM_OxHgFPra1MDU-RPfDjTTD2WtS8GKqzf5v1NDL6Z4NXwQ-gFWkHjI9WD08SU-PO0NsfWldgSKQDhHiFns2ZPvt3GVvdC_EvJ8peTeCdS4o3fivxT-B9Sby9D_VovIUVopyE9aGzdn6JjxyyaCqegZ5Kqu5T0nsdo5vl2uNjmOgbyNcf3hy8_PX-WKiC033XEWSP5N60tRy_fApl_6c5l83cm1fS7iZbnBZ59UWnKZH3w4-B00vhkCh3bEFA2YSjTpXjHYkQjOt-jJKJEemcusIBVOScYUcBQsRZZRzE2MkOVNxLrnsP4deeVUWL8E3A3sdc2X4QFnXKKRC60plLBTGhegLDz60PMlUA1RO_TK-ZzXEMssup5n7eB687SinNTjHn2hatmZWc-g4RJbF1aLKWN_aNxFhEnrwomZz9xRr6RICI_MgWRKAjoBQuZfvlJMLh85NkIOh4B68dwLw14Vlw7Ebt_-V8A2sjQ_T7PjL6OsreMxo3-9y4XagN58til14qK7nk2r2utGDW7P7DTA
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=Fast+contour+propagation+for+MR%E2%80%90guided+prostate+radiotherapy+using+convolutional+neural+networks&rft.jtitle=Medical+physics+%28Lancaster%29&rft.au=Eppenhof%2C+K.A.J.&rft.au=Maspero%2C+M.&rft.au=Savenije%2C+M.H.F.&rft.au=de+Boer%2C+J.C.J.&rft.date=2020-03-01&rft.issn=0094-2405&rft.eissn=2473-4209&rft.volume=47&rft.issue=3&rft.spage=1238&rft.epage=1248&rft_id=info:doi/10.1002%2Fmp.13994&rft.externalDBID=n%2Fa&rft.externalDocID=10_1002_mp_13994
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0094-2405&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0094-2405&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0094-2405&client=summon