A self‐supervised strategy for fully automatic segmentation of renal dynamic contrast‐enhanced magnetic resonance images

Purpose An automated accurate segmentation for dynamic contrast‐enhanced magnetic resonance (DCE‐MR) image sequences is essential for quantification of renal function. A self‐supervised strategy is proposed for fully automatic segmentation of the renal DCE‐MR images without using manually labeled da...

Full description

Saved in:
Bibliographic Details
Published in:Medical physics (Lancaster) Vol. 46; no. 10; pp. 4417 - 4430
Main Authors: Huang, Wenjian, Li, Hao, Wang, Rui, Zhang, Xiaodong, Wang, Xiaoying, Zhang, Jue
Format: Journal Article
Language:English
Published: United States 01.10.2019
Subjects:
ISSN:0094-2405, 2473-4209, 2473-4209
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Purpose An automated accurate segmentation for dynamic contrast‐enhanced magnetic resonance (DCE‐MR) image sequences is essential for quantification of renal function. A self‐supervised strategy is proposed for fully automatic segmentation of the renal DCE‐MR images without using manually labeled data. Methods The proposed strategy employed both temporal and spatial information of the DCE‐MR image sequences. First, the kidney area, the seed regions of the cortex, the medulla, and the pelvis were automatically detected in the spatial domain. Subsequently, all the pixels in the kidney were automatically labeled as the cortex, the medulla, or the pelvis based on their time–intensity signal and spatial position using a supervised classifier. The feasibility of the proposed strategy was verified on a dataset of renal DCE‐MR images of 14 subjects without history of kidney diseases. Furthermore, the self‐supervised strategy and the commonly used traditional unsupervised method were quantitatively compared with a reference manual segmentation by an experienced radiologist, using similarity indexes. Results The average Dice coefficient (ADC) for the segmentations of the proposed self‐supervised method is 0.92 using a ransom walker model as the classifier or 0.86 using a K‐nearest neighbor model as the classifier. The ADC of the Kmeans‐based unsupervised methods with three and six clusters were 0.65 and 0.79, respectively. The Dice coefficients of the self‐supervised method were remarkably higher than that of the unsupervised method (one‐tailed paired‐sample t‐test, P‐values <10−3). Conclusions The results indicate that the proposed self‐supervised approach yields a satisfactory similarity with the reference manual segmentation. Compared with the traditional unsupervised clustering method, the new strategy does not require manual intervention during the segmentation process and achieves better results for the segmentation of renal DCE‐MR images.
AbstractList Purpose An automated accurate segmentation for dynamic contrast‐enhanced magnetic resonance (DCE‐MR) image sequences is essential for quantification of renal function. A self‐supervised strategy is proposed for fully automatic segmentation of the renal DCE‐MR images without using manually labeled data. Methods The proposed strategy employed both temporal and spatial information of the DCE‐MR image sequences. First, the kidney area, the seed regions of the cortex, the medulla, and the pelvis were automatically detected in the spatial domain. Subsequently, all the pixels in the kidney were automatically labeled as the cortex, the medulla, or the pelvis based on their time–intensity signal and spatial position using a supervised classifier. The feasibility of the proposed strategy was verified on a dataset of renal DCE‐MR images of 14 subjects without history of kidney diseases. Furthermore, the self‐supervised strategy and the commonly used traditional unsupervised method were quantitatively compared with a reference manual segmentation by an experienced radiologist, using similarity indexes. Results The average Dice coefficient (ADC) for the segmentations of the proposed self‐supervised method is 0.92 using a ransom walker model as the classifier or 0.86 using a K‐nearest neighbor model as the classifier. The ADC of the Kmeans‐based unsupervised methods with three and six clusters were 0.65 and 0.79, respectively. The Dice coefficients of the self‐supervised method were remarkably higher than that of the unsupervised method (one‐tailed paired‐sample t‐test, P‐values <10−3). Conclusions The results indicate that the proposed self‐supervised approach yields a satisfactory similarity with the reference manual segmentation. Compared with the traditional unsupervised clustering method, the new strategy does not require manual intervention during the segmentation process and achieves better results for the segmentation of renal DCE‐MR images.
An automated accurate segmentation for dynamic contrast-enhanced magnetic resonance (DCE-MR) image sequences is essential for quantification of renal function. A self-supervised strategy is proposed for fully automatic segmentation of the renal DCE-MR images without using manually labeled data.PURPOSEAn automated accurate segmentation for dynamic contrast-enhanced magnetic resonance (DCE-MR) image sequences is essential for quantification of renal function. A self-supervised strategy is proposed for fully automatic segmentation of the renal DCE-MR images without using manually labeled data.The proposed strategy employed both temporal and spatial information of the DCE-MR image sequences. First, the kidney area, the seed regions of the cortex, the medulla, and the pelvis were automatically detected in the spatial domain. Subsequently, all the pixels in the kidney were automatically labeled as the cortex, the medulla, or the pelvis based on their time-intensity signal and spatial position using a supervised classifier. The feasibility of the proposed strategy was verified on a dataset of renal DCE-MR images of 14 subjects without history of kidney diseases. Furthermore, the self-supervised strategy and the commonly used traditional unsupervised method were quantitatively compared with a reference manual segmentation by an experienced radiologist, using similarity indexes.METHODSThe proposed strategy employed both temporal and spatial information of the DCE-MR image sequences. First, the kidney area, the seed regions of the cortex, the medulla, and the pelvis were automatically detected in the spatial domain. Subsequently, all the pixels in the kidney were automatically labeled as the cortex, the medulla, or the pelvis based on their time-intensity signal and spatial position using a supervised classifier. The feasibility of the proposed strategy was verified on a dataset of renal DCE-MR images of 14 subjects without history of kidney diseases. Furthermore, the self-supervised strategy and the commonly used traditional unsupervised method were quantitatively compared with a reference manual segmentation by an experienced radiologist, using similarity indexes.The average Dice coefficient (ADC) for the segmentations of the proposed self-supervised method is 0.92 using a ransom walker model as the classifier or 0.86 using a K-nearest neighbor model as the classifier. The ADC of the Kmeans-based unsupervised methods with three and six clusters were 0.65 and 0.79, respectively. The Dice coefficients of the self-supervised method were remarkably higher than that of the unsupervised method (one-tailed paired-sample t-test, P-values <10-3 ).RESULTSThe average Dice coefficient (ADC) for the segmentations of the proposed self-supervised method is 0.92 using a ransom walker model as the classifier or 0.86 using a K-nearest neighbor model as the classifier. The ADC of the Kmeans-based unsupervised methods with three and six clusters were 0.65 and 0.79, respectively. The Dice coefficients of the self-supervised method were remarkably higher than that of the unsupervised method (one-tailed paired-sample t-test, P-values <10-3 ).The results indicate that the proposed self-supervised approach yields a satisfactory similarity with the reference manual segmentation. Compared with the traditional unsupervised clustering method, the new strategy does not require manual intervention during the segmentation process and achieves better results for the segmentation of renal DCE-MR images.CONCLUSIONSThe results indicate that the proposed self-supervised approach yields a satisfactory similarity with the reference manual segmentation. Compared with the traditional unsupervised clustering method, the new strategy does not require manual intervention during the segmentation process and achieves better results for the segmentation of renal DCE-MR images.
An automated accurate segmentation for dynamic contrast-enhanced magnetic resonance (DCE-MR) image sequences is essential for quantification of renal function. A self-supervised strategy is proposed for fully automatic segmentation of the renal DCE-MR images without using manually labeled data. The proposed strategy employed both temporal and spatial information of the DCE-MR image sequences. First, the kidney area, the seed regions of the cortex, the medulla, and the pelvis were automatically detected in the spatial domain. Subsequently, all the pixels in the kidney were automatically labeled as the cortex, the medulla, or the pelvis based on their time-intensity signal and spatial position using a supervised classifier. The feasibility of the proposed strategy was verified on a dataset of renal DCE-MR images of 14 subjects without history of kidney diseases. Furthermore, the self-supervised strategy and the commonly used traditional unsupervised method were quantitatively compared with a reference manual segmentation by an experienced radiologist, using similarity indexes. The average Dice coefficient (ADC) for the segmentations of the proposed self-supervised method is 0.92 using a ransom walker model as the classifier or 0.86 using a K-nearest neighbor model as the classifier. The ADC of the Kmeans-based unsupervised methods with three and six clusters were 0.65 and 0.79, respectively. The Dice coefficients of the self-supervised method were remarkably higher than that of the unsupervised method (one-tailed paired-sample t-test, P-values <10 ). The results indicate that the proposed self-supervised approach yields a satisfactory similarity with the reference manual segmentation. Compared with the traditional unsupervised clustering method, the new strategy does not require manual intervention during the segmentation process and achieves better results for the segmentation of renal DCE-MR images.
Author Huang, Wenjian
Zhang, Xiaodong
Wang, Xiaoying
Li, Hao
Zhang, Jue
Wang, Rui
Author_xml – sequence: 1
  givenname: Wenjian
  surname: Huang
  fullname: Huang, Wenjian
  organization: Peking University
– sequence: 2
  givenname: Hao
  surname: Li
  fullname: Li, Hao
  organization: Peking University
– sequence: 3
  givenname: Rui
  surname: Wang
  fullname: Wang, Rui
  organization: Peking University First Hospital
– sequence: 4
  givenname: Xiaodong
  surname: Zhang
  fullname: Zhang, Xiaodong
  organization: Peking University First Hospital
– sequence: 5
  givenname: Xiaoying
  surname: Wang
  fullname: Wang, Xiaoying
  email: cjr.wangxiaoying@vip.163.com
  organization: Peking University First Hospital
– sequence: 6
  givenname: Jue
  surname: Zhang
  fullname: Zhang, Jue
  email: zhangjue@pku.edu.cn
  organization: Peking University
BackLink https://www.ncbi.nlm.nih.gov/pubmed/31306492$$D View this record in MEDLINE/PubMed
BookMark eNp1kctu1DAUhq2qqJ0WJJ4Aeckmw_Etl2VVQUFqBYt2HXmc4yHIsYOdgCJ10UfoM_IkeDqFShWsbB1__yfrPyfk0AePhLxmsGYA_N0wrpmomDogKy4rUUgOzSFZATSy4BLUMTlJ6RsAlELBETkWTEApG74it2c0obO_7u7TPGL80SfsaJqinnC7UBsitbNzC9XzFAY99Sbj2wH9lO_B02BpRK8d7Ravh_xqgs_hNGUh-q_am6wb9NbjLhoxBb-b0T7PML0kL6x2CV89nqfk5sP76_OPxeXni0_nZ5eFEZypghtWGsmlLUsGdVeLUtiu4mBkaTXYpum05qpiGwEWuK5qpTTWTSVRq01XaXFK3u69YwzfZ0xTO_TJoHPaY5hTy7mqKyEU5xl984jOmwG7doz5q3Fp_zT25DIxpBTR_kUYtLtltMPYPiwjo-tnqOn3veWKevevQLEP_OwdLv8Vt1df9vxvLC6dIQ
CitedBy_id crossref_primary_10_3389_fnins_2022_695888
crossref_primary_10_1109_ACCESS_2021_3078430
crossref_primary_10_1371_journal_pone_0298227
crossref_primary_10_1016_j_ejrad_2021_109535
crossref_primary_10_1016_j_procs_2024_04_158
crossref_primary_10_1681_ASN_2021030404
crossref_primary_10_1016_j_cmpb_2022_107001
crossref_primary_10_1016_j_mric_2023_09_004
crossref_primary_10_3390_s21237942
Cites_doi 10.1016/j.mri.2013.05.002
10.1118/1.4812428
10.1186/s12880-015-0068-x
10.1109/LGRS.2007.905119
10.1007/s00330-012-2382-9
10.1145/1014052.1014118
10.1016/j.procs.2016.09.407
10.1002/jmri.10410
10.1016/j.compmedimag.2008.11.004
10.1016/j.media.2016.05.006
10.1109/ICCV.2007.4408927
10.2214/AJR.12.8657
10.1148/radiol.2231010420
10.1016/j.ics.2005.03.146
10.1007/s10157-017-1404-y
10.1109/ICCV.2015.167
10.1016/j.compmedimag.2011.06.005
10.2214/AJR.09.4104
10.1097/01.ju.0000161217.47446.0b
10.1109/CVPR.2012.6247859
10.1162/jocn.2007.19.9.1498
10.1016/j.mric.2008.07.001
10.1016/S0031-3203(04)00195-5
10.1109/TIP.2015.2488902
10.1109/MEMB.2008.923949
10.1109/ICRA.2011.5980157
10.1016/j.ijrobp.2004.11.014
10.1109/ICASSP.2016.7471989
10.1109/ICASSP.2008.4517662
10.1109/CVPRW.2008.4563025
10.1007/s11063-011-9184-y
10.1056/NEJMra054415
10.1002/jmri.10058
10.1109/IEMBS.2006.260178
10.1109/TMI.2015.2512606
10.1007/978-3-319-46466-4_5
10.1515/pjmpe-2017-0006
10.3390/rs70202171
10.1002/mp.12594
10.1093/ndt/17.suppl_11.2
10.1111/wrr.12495
10.1109/36.285193
10.1109/CVPR.2015.7299008
10.1002/rob.21417
10.1002/rob.21408
10.1002/jmri.21121
10.15607/RSS.2006.II.005
10.1109/TIP.2015.2505184
10.1109/CVPR.2017.218
10.1016/j.ejrad.2009.10.005
10.1007/978-3-642-04271-3_134
10.1002/mrm.21240
10.1145/1718487.1718501
10.1117/12.431013
10.1109/TPAMI.2006.233
10.1007/s10462-010-9155-0
10.3390/rs1041257
ContentType Journal Article
Copyright 2019 American Association of Physicists in Medicine
2019 American Association of Physicists in Medicine.
Copyright_xml – notice: 2019 American Association of Physicists in Medicine
– notice: 2019 American Association of Physicists in Medicine.
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1002/mp.13715
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Physics
EISSN 2473-4209
EndPage 4430
ExternalDocumentID 31306492
10_1002_mp_13715
MP13715
Genre article
Journal Article
GroupedDBID ---
--Z
-DZ
.GJ
0R~
1OB
1OC
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
ID FETCH-LOGICAL-c3215-2c16c424f66108d8363fd720c46fa0f99daa2571b30f02a7855ae8974ea5bd7a3
IEDL.DBID DRFUL
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000481396000001&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 Fri Sep 05 13:10:37 EDT 2025
Thu Apr 03 07:03:11 EDT 2025
Sat Nov 29 06:02:40 EST 2025
Tue Nov 18 22:31:40 EST 2025
Wed Jan 22 16:38:20 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 10
Keywords random walker
DCE-MRI
self-supervised algorithm
unsupervised algorithm
automatic kidney segmentation
Language English
License 2019 American Association of Physicists in Medicine.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3215-2c16c424f66108d8363fd720c46fa0f99daa2571b30f02a7855ae8974ea5bd7a3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 31306492
PQID 2258733522
PQPubID 23479
PageCount 14
ParticipantIDs proquest_miscellaneous_2258733522
pubmed_primary_31306492
crossref_primary_10_1002_mp_13715
crossref_citationtrail_10_1002_mp_13715
wiley_primary_10_1002_mp_13715_MP13715
PublicationCentury 2000
PublicationDate October 2019
2019-10-00
2019-Oct
20191001
PublicationDateYYYYMMDD 2019-10-01
PublicationDate_xml – month: 10
  year: 2019
  text: October 2019
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Medical physics (Lancaster)
PublicationTitleAlternate Med Phys
PublicationYear 2019
References 2002; 17
2002; 15
2005; 174
2017; 44
2016; 32
2016; 102
2008; 5
2003; 18
2005; 61
2009; 5762
2016; 35
2001
2002; 223
2006; 28
2004; 37
2008; 27
2012; 29
2010; 195
2005; 1281
2012; 22
2001; 4322
2007; 26
1994; 32
2010; 33
2015; 15
2007; 19
2015; 6
2012
2011
2017; 25
2010
2013; 40
2017; 21
2008; 16
2017; 23
2008
1997
2007
2006
2011; 78
2011; 34
2004
2003
2012; 36
2015; 7
2006; 354
2007; 57
2015; 24
2009; 33
2012; 199
2013; 31
2017
2016
2015
2009; 1
2016; 25
e_1_2_8_28_1
Farid H (e_1_2_8_49_1) 1997
e_1_2_8_24_1
e_1_2_8_47_1
e_1_2_8_26_1
e_1_2_8_3_1
e_1_2_8_5_1
e_1_2_8_7_1
e_1_2_8_9_1
e_1_2_8_20_1
e_1_2_8_43_1
e_1_2_8_66_1
e_1_2_8_22_1
e_1_2_8_45_1
e_1_2_8_64_1
e_1_2_8_62_1
e_1_2_8_41_1
e_1_2_8_60_1
e_1_2_8_17_1
e_1_2_8_19_1
Panchal G (e_1_2_8_31_1) 2015; 6
e_1_2_8_13_1
e_1_2_8_36_1
e_1_2_8_59_1
e_1_2_8_15_1
e_1_2_8_38_1
e_1_2_8_57_1
e_1_2_8_32_1
e_1_2_8_55_1
e_1_2_8_11_1
e_1_2_8_34_1
e_1_2_8_53_1
e_1_2_8_51_1
e_1_2_8_30_1
e_1_2_8_29_1
e_1_2_8_25_1
e_1_2_8_46_1
e_1_2_8_27_1
e_1_2_8_48_1
e_1_2_8_2_1
e_1_2_8_4_1
e_1_2_8_6_1
e_1_2_8_8_1
e_1_2_8_21_1
e_1_2_8_42_1
e_1_2_8_23_1
e_1_2_8_44_1
e_1_2_8_65_1
e_1_2_8_63_1
e_1_2_8_40_1
e_1_2_8_61_1
e_1_2_8_18_1
e_1_2_8_39_1
e_1_2_8_14_1
e_1_2_8_35_1
e_1_2_8_16_1
e_1_2_8_37_1
e_1_2_8_58_1
e_1_2_8_10_1
e_1_2_8_56_1
e_1_2_8_12_1
e_1_2_8_33_1
e_1_2_8_54_1
e_1_2_8_52_1
e_1_2_8_50_1
References_xml – volume: 26
  start-page: 1564
  year: 2007
  end-page: 1571
  article-title: Different strategies for MRI measurements of renal cortical volume
  publication-title: J Magn Reson Imaging
– year: 2011
– volume: 195
  start-page: W146
  year: 2010
  end-page: W149
  article-title: Renal cortical thickness measured at ultrasound: is it better than renal length as an indicator of renal function in chronic kidney disease?
  publication-title: Am J Roentgenol
– volume: 44
  start-page: 6353
  year: 2017
  end-page: 6363
  article-title: Fast segmentation of kidney components using random forests and ferns
  publication-title: Med Phys
– volume: 174
  start-page: 303
  year: 2005
  end-page: 307
  article-title: Renal pelvis volume during diuresis in children with hydronephrosis: Implications for diagnosing obstruction with diuretic renography
  publication-title: J Urology
– start-page: 4474‐+
  year: 2006
– volume: 354
  start-page: 2473
  year: 2006
  end-page: 2483
  article-title: Medical progress – assessing kidney function – measured and estimated glomerular filtration rate
  publication-title: New Engl J Med
– volume: 5
  start-page: 21
  year: 2008
  end-page: 25
  article-title: A context‐sensitive clustering technique based on graph‐cut initialization and expectation‐maximization algorithm
  publication-title: IEEE Geosci Remote S
– volume: 24
  start-page: 5854
  year: 2015
  end-page: 5867
  article-title: walk and graph cut for co‐segmentation of lung tumor on PET‐CT images
  publication-title: IEEE Trans Image Process
– volume: 21
  start-page: 1124
  year: 2017
  end-page: 1130
  article-title: Automated renal cortical volume measurement for assessment of renal function in patients undergoing radical nephrectomy
  publication-title: Clin Exp Nephrol
– volume: 19
  start-page: 1498
  year: 2007
  end-page: 1507
  article-title: Open access series of imaging studies (OASIS): cross‐sectional MRI data in young, middle aged, nondemented, and demented older adults
  publication-title: J Cognitive Neurosci
– volume: 199
  start-page: 1060
  year: 2012
  end-page: 1069
  article-title: Assessment of kidney volumes from MRI: acquisition and segmentation techniques
  publication-title: Am J Roentgenol
– volume: 32
  start-page: 269
  year: 2016
  end-page: 280
  article-title: Renal compartment segmentation in DCE‐MRI images
  publication-title: Med Image Anal
– volume: 25
  start-page: 150
  year: 2017
  end-page: 158
  article-title: An improved automated type‐based method for area assessment of wound surface
  publication-title: Wound Repair Regen
– volume: 23
  start-page: 29
  year: 2017
  end-page: 36
  article-title: Automatic segmentation of lesion from breast DCE‐MR image using artificial fish swarm optimization algorithm
  publication-title: Pol J Med Phys Eng
– volume: 78
  start-page: 151
  year: 2011
  end-page: 156
  article-title: Renal cortical volume measured using automatic contouring software for computed tomography and its relationship with BMI, age and renal function
  publication-title: Eur J Radiol
– start-page: TR2007‐605,
  year: 1997
– start-page: 778‐+
  year: 2007
– volume: 32
  start-page: 100
  year: 1994
  end-page: 109
  article-title: Application of neural networks to radar image classification
  publication-title: IEEE T Geosci Remote
– start-page: 1183
  year: 2010
  end-page: 1189
– year: 2008
– volume: 36
  start-page: 108
  year: 2012
  end-page: 118
  article-title: Wavelet‐based segmentation of renal compartments in DCE‐MRI of human kidney: Initial results in patients and healthy volunteers
  publication-title: Comput Med Imag Grap
– volume: 102
  start-page: 317
  year: 2016
  end-page: 324
  article-title: Review of MRI‐based brain tumor image segmentation using deep learning methods
  publication-title: Procedia Comput Sci
– volume: 6
  start-page: 1828
  year: 2015
  end-page: 1831
  article-title: Efficient attribute evaluation, extraction and selection techniques for data classification
  publication-title: Int J Comput Sci Inf Technol
– year: 2004
– start-page: 69
  year: 2016
  end-page: 84
– volume: 35
  start-page: 1395
  year: 2016
  end-page: 1407
  article-title: 3D fast automatic segmentation of kidney based on modified AAM and random forest
  publication-title: IEEE Trans Med Imaging
– start-page: 2017
  year: 2017
  end-page: 2026
– volume: 5762
  start-page: 1108
  year: 2009
  end-page: 1115
  article-title: A fully automatic random walker segmentation for skin lesions in a supervised setting
  publication-title: Lect Notes Comput Sc
– year: 2015
– volume: 25
  start-page: 516
  year: 2016
  end-page: 527
  article-title: Sub‐markov random walk for image segmentation
  publication-title: IEEE Trans Image Process
– volume: 61
  start-page: 954
  year: 2005
  end-page: 960
  article-title: Comparison of human and automatic segmentations of kidneys from CT images
  publication-title: Int J Radiat Oncol
– start-page: 566‐+
  year: 2008
– volume: 29
  start-page: 277
  year: 2012
  end-page: 297
  article-title: Self‐supervised learning to visually detect terrain surfaces for autonomous robots operating in forested terrain
  publication-title: J Field Robot
– volume: 16
  start-page: 597
  year: 2008
  article-title: Assessment of renal function with dynamic contrast‐enhanced
  publication-title: MR Imaging. Magn Reson Imaging C
– year: 2003
– volume: 40
  start-page: 081905
  year: 2013
  article-title: Kidney segmentation in CT sequences using graph cuts based active contours model and contextual continuity
  publication-title: Med Phys
– start-page: 744
  year: 2011
  end-page: 748
– volume: 33
  start-page: 171
  year: 2009
  end-page: 181
  article-title: Assessment of 3D DCE‐MRI of the kidneys using non‐rigid image registration and segmentation of voxel time courses
  publication-title: Comput Med Imag Grap
– volume: 1
  start-page: 1257
  year: 2009
  end-page: 1272
  article-title: Improving landsat and IRS image classification: evaluation of unsupervised and supervised classification through band ratios and DEM in a mountainous landscape in Nepal
  publication-title: Remote Sens‐Basel
– volume: 31
  start-page: 1426
  year: 2013
  end-page: 1438
  article-title: State of the art survey on MRI brain tumor segmentation
  publication-title: Magn Reson Imaging
– volume: 7
  start-page: 2171
  year: 2015
  end-page: 2192
  article-title: Unsupervised global urban area mapping via automatic labeling from ASTER and PALSAR satellite images
  publication-title: Remote Sens‐Basel
– volume: 37
  start-page: 2323
  year: 2004
  end-page: 2335
  article-title: Unsupervised image segmentation using a simple MRF model with a new implementation scheme
  publication-title: Pattern Recogn
– volume: 15
  start-page: 29
  year: 2015
  article-title: Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool
  publication-title: Bmc Med Imaging
– volume: 223
  start-page: 76
  year: 2002
  end-page: 82
  article-title: Noninvasive measurement of extraction fraction and single‐kidney glomerular filtration rate with MR imaging in swine with surgically created renal artery stenoses
  publication-title: Radiology
– year: 2010
– volume: 15
  start-page: 174
  year: 2002
  end-page: 179
  article-title: Measurement of renal volumes with contrast‐enhanced MRI
  publication-title: J Magn Reson Imaging
– start-page: 1059
  year: 2001
  end-page: 1062
– year: 2012
– volume: 29
  start-page: 445
  year: 2012
  end-page: 468
  article-title: Self‐supervised terrain classification for planetary surface exploration rovers
  publication-title: J Field Robot
– volume: 22
  start-page: 1320
  year: 2012
  end-page: 1330
  article-title: Precise measurement of renal filtration and vascular parameters using a two‐compartment model for dynamic contrast‐enhanced MRI of the kidney gives realistic normal values
  publication-title: Eur Radiol
– volume: 57
  start-page: 1159
  year: 2007
  end-page: 1167
  article-title: Performance of an automated segmentation algorithm for 3D MR renography
  publication-title: Magn Reson Med
– volume: 1281
  start-page: 773
  year: 2005
  end-page: 778
  article-title: Automatic detection of renal rejection after kidney transplantation
  publication-title: Int Congr Ser
– start-page: 1422
  year: 2015
  end-page: 1430
– volume: 18
  start-page: 714
  year: 2003
  end-page: 725
  article-title: Measurement of single‐kidney glomerular filtration rate using a contrast‐enhanced dynamic gradient‐echo sequence and the Rutland‐Patlak plot technique
  publication-title: J Magn Reson Imaging
– year: 2006
– volume: 28
  start-page: 1768
  year: 2006
  end-page: 1783
  article-title: Random walks for image segmentation
  publication-title: IEEE T Pattern Anal
– volume: 33
  start-page: 261
  year: 2010
  end-page: 274
  article-title: Review of brain MRI image segmentation methods
  publication-title: Artif Intell Rev
– start-page: 525‐+
  year: 2008
– volume: 27
  start-page: 36
  year: 2008
  end-page: 41
  article-title: Dynamic contrast‐enhanced magnetic resonance images of the kidney ‐ A processing study
  publication-title: Ieee Eng Med Biol
– volume: 34
  start-page: 71
  year: 2011
  end-page: 85
  article-title: Functional segmentation of renal DCE‐MRI sequences using vector quantization algorithms
  publication-title: Neural Process Lett
– volume: 17
  start-page: 2
  year: 2002
  end-page: 7
  article-title: The importance of early detection of chronic kidney disease
  publication-title: Nephrol Dial Transpl
– volume: 4322
  start-page: 1337
  year: 2001
  end-page: 1346
  article-title: Segmentation of medical images using adaptive region growing
  publication-title: Proc SPIE
– ident: e_1_2_8_23_1
  doi: 10.1016/j.mri.2013.05.002
– ident: e_1_2_8_25_1
  doi: 10.1118/1.4812428
– ident: e_1_2_8_58_1
  doi: 10.1186/s12880-015-0068-x
– ident: e_1_2_8_36_1
  doi: 10.1109/LGRS.2007.905119
– ident: e_1_2_8_60_1
  doi: 10.1007/s00330-012-2382-9
– ident: e_1_2_8_61_1
  doi: 10.1145/1014052.1014118
– ident: e_1_2_8_37_1
  doi: 10.1016/j.procs.2016.09.407
– ident: e_1_2_8_59_1
  doi: 10.1002/jmri.10410
– ident: e_1_2_8_28_1
  doi: 10.1016/j.compmedimag.2008.11.004
– ident: e_1_2_8_19_1
  doi: 10.1016/j.media.2016.05.006
– ident: e_1_2_8_51_1
  doi: 10.1109/ICCV.2007.4408927
– ident: e_1_2_8_48_1
  doi: 10.2214/AJR.12.8657
– ident: e_1_2_8_10_1
  doi: 10.1148/radiol.2231010420
– ident: e_1_2_8_16_1
  doi: 10.1016/j.ics.2005.03.146
– ident: e_1_2_8_6_1
  doi: 10.1007/s10157-017-1404-y
– ident: e_1_2_8_38_1
  doi: 10.1109/ICCV.2015.167
– ident: e_1_2_8_27_1
  doi: 10.1016/j.compmedimag.2011.06.005
– ident: e_1_2_8_3_1
  doi: 10.2214/AJR.09.4104
– ident: e_1_2_8_7_1
  doi: 10.1097/01.ju.0000161217.47446.0b
– ident: e_1_2_8_55_1
  doi: 10.1109/CVPR.2012.6247859
– ident: e_1_2_8_62_1
  doi: 10.1162/jocn.2007.19.9.1498
– ident: e_1_2_8_9_1
  doi: 10.1016/j.mric.2008.07.001
– ident: e_1_2_8_66_1
  doi: 10.1016/S0031-3203(04)00195-5
– ident: e_1_2_8_54_1
  doi: 10.1109/TIP.2015.2488902
– ident: e_1_2_8_15_1
  doi: 10.1109/MEMB.2008.923949
– ident: e_1_2_8_42_1
– ident: e_1_2_8_47_1
  doi: 10.1109/ICRA.2011.5980157
– ident: e_1_2_8_22_1
  doi: 10.1016/j.ijrobp.2004.11.014
– ident: e_1_2_8_57_1
  doi: 10.1109/ICASSP.2016.7471989
– ident: e_1_2_8_12_1
  doi: 10.1109/ICASSP.2008.4517662
– ident: e_1_2_8_20_1
– ident: e_1_2_8_17_1
  doi: 10.1109/CVPRW.2008.4563025
– ident: e_1_2_8_18_1
  doi: 10.1007/s11063-011-9184-y
– ident: e_1_2_8_8_1
  doi: 10.1056/NEJMra054415
– ident: e_1_2_8_13_1
  doi: 10.1002/jmri.10058
– ident: e_1_2_8_29_1
  doi: 10.1109/IEMBS.2006.260178
– ident: e_1_2_8_21_1
– ident: e_1_2_8_24_1
  doi: 10.1109/TMI.2015.2512606
– ident: e_1_2_8_39_1
  doi: 10.1007/978-3-319-46466-4_5
– ident: e_1_2_8_63_1
  doi: 10.1515/pjmpe-2017-0006
– ident: e_1_2_8_33_1
  doi: 10.3390/rs70202171
– ident: e_1_2_8_26_1
  doi: 10.1002/mp.12594
– ident: e_1_2_8_2_1
  doi: 10.1093/ndt/17.suppl_11.2
– ident: e_1_2_8_65_1
  doi: 10.1111/wrr.12495
– ident: e_1_2_8_34_1
  doi: 10.1109/36.285193
– ident: e_1_2_8_56_1
  doi: 10.1109/CVPR.2015.7299008
– ident: e_1_2_8_43_1
  doi: 10.1002/rob.21417
– ident: e_1_2_8_45_1
  doi: 10.1002/rob.21408
– volume: 6
  start-page: 1828
  year: 2015
  ident: e_1_2_8_31_1
  article-title: Efficient attribute evaluation, extraction and selection techniques for data classification
  publication-title: Int J Comput Sci Inf Technol
– ident: e_1_2_8_35_1
– ident: e_1_2_8_41_1
– ident: e_1_2_8_5_1
  doi: 10.1002/jmri.21121
– ident: e_1_2_8_30_1
– ident: e_1_2_8_44_1
  doi: 10.15607/RSS.2006.II.005
– start-page: TR2007‐605,
  volume-title: Video stabilization and enhancement
  year: 1997
  ident: e_1_2_8_49_1
– ident: e_1_2_8_53_1
  doi: 10.1109/TIP.2015.2505184
– ident: e_1_2_8_46_1
  doi: 10.1109/CVPR.2017.218
– ident: e_1_2_8_4_1
  doi: 10.1016/j.ejrad.2009.10.005
– ident: e_1_2_8_52_1
  doi: 10.1007/978-3-642-04271-3_134
– ident: e_1_2_8_11_1
  doi: 10.1002/mrm.21240
– ident: e_1_2_8_40_1
  doi: 10.1145/1718487.1718501
– ident: e_1_2_8_14_1
  doi: 10.1117/12.431013
– ident: e_1_2_8_50_1
  doi: 10.1109/TPAMI.2006.233
– ident: e_1_2_8_64_1
  doi: 10.1007/s10462-010-9155-0
– ident: e_1_2_8_32_1
  doi: 10.3390/rs1041257
SSID ssj0006350
Score 2.3505397
Snippet Purpose An automated accurate segmentation for dynamic contrast‐enhanced magnetic resonance (DCE‐MR) image sequences is essential for quantification of renal...
An automated accurate segmentation for dynamic contrast-enhanced magnetic resonance (DCE-MR) image sequences is essential for quantification of renal function....
SourceID proquest
pubmed
crossref
wiley
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 4417
SubjectTerms automatic kidney segmentation
Automation
Contrast Media
DCE‐MRI
Female
Humans
Image Processing, Computer-Assisted - methods
Kidney - diagnostic imaging
Magnetic Resonance Imaging
Male
Middle Aged
random walker
self‐supervised algorithm
Supervised Machine Learning
unsupervised algorithm
Title A self‐supervised strategy for fully automatic segmentation of renal dynamic contrast‐enhanced magnetic resonance images
URI https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmp.13715
https://www.ncbi.nlm.nih.gov/pubmed/31306492
https://www.proquest.com/docview/2258733522
Volume 46
WOSCitedRecordID wos000481396000001&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/eLvHCXMwpV3NatwwEB7aTVty6U_aptufoEJpT05sybLkY2i79JCEUBrYm5FkKQ1kvctqNxDoIY-QZ8yTdCR5t4S2UOjJII9l45FmvpFmPgG8E9RwJlyRoavkWUk1z7SURabzshCt046rSOJ6II6O5HhcH_dZlaEWJvFDrBfcwsyI9jpMcKX93i_S0Mlst2Ai1JdvUBy25QA2Pn0dnRys7TC60lSAUpdhD4GvqGdzurd69rYz-g1h3gas0eOMHv3Ptz6Ghz3OJPtpYDyBO7bbggeH_U76FtyPqZ_GP4Uf-8Tbc3dzde2Xs2A5vG2JT6S1lwQxLQlL9JdELRfTyO-K4qeTvmSpI1NH5ja8qk1n25OY_K78Aju03feYYEAm6rQL1ZIoGqA_tpEzbLP-GZyMPn_7-CXrz2TIDEN0kFFTVKakpUO_nstWsoq5VtDclJVTuavrVim0AoVmucupEpJzZSUGLVZx3QrFnsOgm3b2BZDcVNZJzXNbaIximdIVyjEtW8QcVVkN4cNKOY3pCcvDuRnnTaJaps1k1sTfOoS3a8lZIun4k8xKvw3OoLAtojo7XfoGLZoUofSMDmE7KX7dCytChFbjnfdRv3_tvjk8jteX_yr4CjYRe9UpL_A1DBbzpX0D98zF4szPd-CuGMudfkT_BKH3-bU
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1La9wwEB7Cpq9LH-lr-1ShtCcnsmRZMj2FtktKd5dQEsjNSLaUBrLeZb1bCPTQn9Df2F_SkWRvCW2h0JNBHkvCI818kmY-AbyUrBJcujRBVymSjBmRGKXSxNAslbUzTuhA4jqW06k6OSkOt-BNnwsT-SE2G25-ZgR77Se435De-8UaOlvsplz6BPPtDEeRGMD2u0-j4_HGEKMvjRkoReYPEUTPPUvZXv_tZW_0G8S8jFiDyxnd-q_O3oabHdIk-3Fo3IEt2-zAtUl3lr4DV0PwZ9Xeha_7pLXn7se37-164W1Ha2vSRtraC4KolvhmLoher-aB4RXFT2dd0lJD5o4srW-qjrfbkxD-rtsVVmibzyHEgMz0aePzJVHUg38sI2dYZtt7cDx6f_T2IOluZUgqjvggYVWaVxnLHHp2qmrFc-5qyWiV5U5TVxS11mgHUsOpo0xLJYS2CpctVgtTS83vw6CZN_YhEFrl1ikjqE0NrmO5NjnKcaNqRB15lg_hda-dsuooy_3NGedlJFtm5WxRht86hBcbyUWk6fiTTK_gEueQPxjRjZ2v2xJtmpI--YwN4UHU_KYWnvo1WoFvXgUF_7X6cnIYno_-VfA5XD84mozL8Yfpx8dwA5FYEaMEn8BgtVzbp3Cl-rI6a5fPuoH9E6oi_L0
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bi9QwFA7Lri6-eFlv4zWC6FPdNGmaFJ8W10FxdhjEhX0rSZOsCzudMpkRFnzwJ_gb_SWeJO3IooLgUyE9TUtPzjlfknO-IPRc0IYz4fIMQiXPCqp5pqXMM02KXBinHVeRxHUiplN5clLNttDroRYm8UNsFtyCZUR_HQzcdsbt_2INnXevciZCgflOwasSrHLn8OP4eLJxxBBLUwVKVYRNBD5wzxK6Pzx7ORr9BjEvI9YYcsY3_utjb6LrPdLEB2lo3EJbtt1Du0f9XvoeuhqTPxt_G309wN6eux_fvvt1F3yHtwb7RFt7gQHV4rBIf4HVerWIDK8gfjrvi5ZavHB4acOrTDrdHsf0d-VX0KFtP8cUAzxXp22olwTRAP6hDZ9Bm_V30PH47ac377L-VIasYYAPMtrkZVPQwkFkJ9JIVjJnBCVNUTpFXFUZpcAP5JoRR6gSknNlJUxbrOLaCMXuou120dr7CJOmtE5qTmyuYR7LlC5BjmlpAHWURTlCLwft1E1PWR5OzjivE9kyreddHX_rCD3bSHaJpuNPMoOCa7ChsDGiWrtY-xp8mhSh-IyO0L2k-U0vLA9ztAruvIgK_mv39dEsXh_8q-BTtDs7HNeT99MPD9E1AGJVShJ8hLZXy7V9jK40X1ZnfvmkH9c_ATsj_Dg
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=A+self%E2%80%90supervised+strategy+for+fully+automatic+segmentation+of+renal+dynamic+contrast%E2%80%90enhanced+magnetic+resonance+images&rft.jtitle=Medical+physics+%28Lancaster%29&rft.au=Huang%2C+Wenjian&rft.au=Li%2C+Hao&rft.au=Wang%2C+Rui&rft.au=Zhang%2C+Xiaodong&rft.date=2019-10-01&rft.issn=0094-2405&rft.eissn=2473-4209&rft.volume=46&rft.issue=10&rft.spage=4417&rft.epage=4430&rft_id=info:doi/10.1002%2Fmp.13715&rft.externalDBID=10.1002%252Fmp.13715&rft.externalDocID=MP13715
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