SU‐E‐J‐168: Automated Pancreas Segmentation Based On Dynamic MRI

Purpose: MRI guided radiotherapy is particularly attractive for abdominal targets with low CT contrast. To fully utilize this modality for pancreas tracking, automated segmentation tools are needed. A hybrid gradient, region growth and shape constraint (hGReS) method to segment 2D upper abdominal dy...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Medical physics (Lancaster) Ročník 41; číslo 6Part9; s. 195
Hlavní autoři: Gou, S, Rapacchi, S, Hu, P, Sheng, K
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States American Association of Physicists in Medicine 01.06.2014
Témata:
ISSN:0094-2405, 2473-4209
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Purpose: MRI guided radiotherapy is particularly attractive for abdominal targets with low CT contrast. To fully utilize this modality for pancreas tracking, automated segmentation tools are needed. A hybrid gradient, region growth and shape constraint (hGReS) method to segment 2D upper abdominal dynamic MRI is developed for this purpose. Methods: 2D coronal dynamic MR images of 2 healthy volunteers were acquired with a frame rate of 5 f/second. The regions of interest (ROIs) included the liver, pancreas and stomach. The first frame was used as the source where the centers of the ROIs were annotated. These center locations were propagated to the next dynamic MRI frame. 4‐neighborhood region transfer growth was performed from these initial seeds for rough segmentation. To improve the results, gradient, edge and shape constraints were applied to the ROIs before final refinement using morphological operations. Results from hGReS and 3 other automated segmentation methods using edge detection, region growth and level set were compared to manual contouring. Results: For the first patient, hGReS resulted in the organ segmentation accuracy as measure by the Dices index (0.77) for the pancreas. The accuracy was slightly superior to the level set method (0.72), and both are significantly more accurate than the edge detection (0.53) and region growth methods (0.42). For the second healthy volunteer, hGReS reliably segmented the pancreatic region, achieving a Dices index of 0.82, 0.92 and 0.93 for the pancreas, stomach and liver, respectively, comparing to manual segmentation. Motion trajectories derived from the hGReS, level set and manual segmentation methods showed high correlation to respiratory motion calculated using a lung blood vessel as the reference while the other two methods showed substantial motion tracking errors. hGReS was 10 times faster than level set. Conclusion: We have shown the feasibility of automated segmentation of the pancreas anatomy based on dynamic MRI.
AbstractList Purpose: MRI guided radiotherapy is particularly attractive for abdominal targets with low CT contrast. To fully utilize this modality for pancreas tracking, automated segmentation tools are needed. A hybrid gradient, region growth and shape constraint (hGReS) method to segment 2D upper abdominal dynamic MRI is developed for this purpose. Methods: 2D coronal dynamic MR images of 2 healthy volunteers were acquired with a frame rate of 5 f/second. The regions of interest (ROIs) included the liver, pancreas and stomach. The first frame was used as the source where the centers of the ROIs were annotated. These center locations were propagated to the next dynamic MRI frame. 4-neighborhood region transfer growth was performed from these initial seeds for rough segmentation. To improve the results, gradient, edge and shape constraints were applied to the ROIs before final refinement using morphological operations. Results from hGReS and 3 other automated segmentation methods using edge detection, region growth and level set were compared to manual contouring. Results: For the first patient, hGReS resulted in the organ segmentation accuracy as measure by the Dices index (0.77) for the pancreas. The accuracy was slightly superior to the level set method (0.72), and both are significantly more accurate than the edge detection (0.53) and region growth methods (0.42). For the second healthy volunteer, hGReS reliably segmented the pancreatic region, achieving a Dices index of 0.82, 0.92 and 0.93 for the pancreas, stomach and liver, respectively, comparing to manual segmentation. Motion trajectories derived from the hGReS, level set and manual segmentation methods showed high correlation to respiratory motion calculated using a lung blood vessel as the reference while the other two methods showed substantial motion tracking errors. hGReS was 10 times faster than level set. Conclusion: We have shown the feasibility of automated segmentation of the pancreas anatomy based on dynamic MRI.
Purpose: MRI guided radiotherapy is particularly attractive for abdominal targets with low CT contrast. To fully utilize this modality for pancreas tracking, automated segmentation tools are needed. A hybrid gradient, region growth and shape constraint (hGReS) method to segment 2D upper abdominal dynamic MRI is developed for this purpose. Methods: 2D coronal dynamic MR images of 2 healthy volunteers were acquired with a frame rate of 5 f/second. The regions of interest (ROIs) included the liver, pancreas and stomach. The first frame was used as the source where the centers of the ROIs were annotated. These center locations were propagated to the next dynamic MRI frame. 4‐neighborhood region transfer growth was performed from these initial seeds for rough segmentation. To improve the results, gradient, edge and shape constraints were applied to the ROIs before final refinement using morphological operations. Results from hGReS and 3 other automated segmentation methods using edge detection, region growth and level set were compared to manual contouring. Results: For the first patient, hGReS resulted in the organ segmentation accuracy as measure by the Dices index (0.77) for the pancreas. The accuracy was slightly superior to the level set method (0.72), and both are significantly more accurate than the edge detection (0.53) and region growth methods (0.42). For the second healthy volunteer, hGReS reliably segmented the pancreatic region, achieving a Dices index of 0.82, 0.92 and 0.93 for the pancreas, stomach and liver, respectively, comparing to manual segmentation. Motion trajectories derived from the hGReS, level set and manual segmentation methods showed high correlation to respiratory motion calculated using a lung blood vessel as the reference while the other two methods showed substantial motion tracking errors. hGReS was 10 times faster than level set. Conclusion: We have shown the feasibility of automated segmentation of the pancreas anatomy based on dynamic MRI.
Abstract only
Author Gou, S
Hu, P
Rapacchi, S
Sheng, K
Author_xml – sequence: 1
  givenname: S
  surname: Gou
  fullname: Gou, S
– sequence: 2
  givenname: S
  surname: Rapacchi
  fullname: Rapacchi, S
– sequence: 3
  givenname: P
  surname: Hu
  fullname: Hu, P
– sequence: 4
  givenname: K
  surname: Sheng
  fullname: Sheng, K
BackLink https://www.osti.gov/biblio/22334057$$D View this record in Osti.gov
BookMark eNp1kM1OAjEUhRuDiYAufINJXLkY6N-UjjtEUAwEIrJuStvRGqZjpjVmdj6Cz-iTWIGV0cXJXdzvnNx7OqDlKmcAOEewhxDifdSjnHOM0RFoYzogKcUwb4E2hDlNMYXZCeh4_wIhZCSDbTBZrb8-PsdR91GI8atk-BaqUgajk6V0qjbSJyvzVBoXZLCVS66lj7uFS24aJ0urkvnD9BQcF3LrzdlhdsF6Mn4c3aWzxe10NJylClGIUs6kzilnRaFMjjXkFBI9IDmRWUY10YhrLgkzmVEblhFkGCRYxlMx41pvNqQLLva5lQ9WeGWDUc-qcs6oIDAmJH44iNTlnlJ15X1tCvFa21LWjUBQ_NQkkDjUFNn-LzaG7h4NtbTbPx3p3vFut6b5P1rMlzv-G-eyeAc
CitedBy_id crossref_primary_10_1088_1361_6560_ad3e5c
ContentType Journal Article
Copyright 2014 American Association of Physicists in Medicine
Copyright_xml – notice: 2014 American Association of Physicists in Medicine
DBID AAYXX
CITATION
OTOTI
DOI 10.1118/1.4888221
DatabaseName CrossRef
OSTI.GOV
DatabaseTitle CrossRef
DatabaseTitleList

CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Physics
EISSN 2473-4209
EndPage 195
ExternalDocumentID 22334057
10_1118_1_4888221
MP8221
Genre miscellaneous
GroupedDBID ---
--Z
-DZ
.GJ
0R~
1OB
1OC
29M
2WC
33P
36B
3O-
4.4
53G
5GY
5RE
5VS
AAHQN
AAIPD
AAMMB
AAMNL
AANLZ
AAQQT
AASGY
AAXRX
AAYCA
AAZKR
ABCUV
ABDPE
ABEFU
ABJNI
ABLJU
ABQWH
ABXGK
ACAHQ
ACBEA
ACCZN
ACGFO
ACGFS
ACGOF
ACPOU
ACXBN
ACXQS
ADBBV
ADBTR
ADKYN
ADMLS
ADOZA
ADXAS
ADZMN
AEFGJ
AEGXH
AEIGN
AENEX
AEUYR
AEYWJ
AFBPY
AFFPM
AFWVQ
AGHNM
AGXDD
AGYGG
AHBTC
AIACR
AIAGR
AIDQK
AIDYY
AIQQE
AITYG
AIURR
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
LH4
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
AAYXX
ABUFD
CITATION
476
AAHHS
AAJUZ
AAPBV
ABCVL
ABFTF
ABPTK
ABTAH
ACCFJ
ACSMX
ADDAD
AEEZP
AEQDE
AEUQT
AIWBW
AJBDE
OTOTI
ID FETCH-LOGICAL-c1401-86ad9486ffce92d08403d7393a554d3d18d8a36e5ecb6531e6032a063268ddbb3
IEDL.DBID DRFUL
ISSN 0094-2405
IngestDate Thu May 18 22:30:05 EDT 2023
Sat Nov 29 01:32:35 EST 2025
Tue Nov 18 22:06:05 EST 2025
Sun Sep 21 06:20:34 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 6Part9
Language English
License http://onlinelibrary.wiley.com/termsAndConditions#vor
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c1401-86ad9486ffce92d08403d7393a554d3d18d8a36e5ecb6531e6032a063268ddbb3
PageCount 1
ParticipantIDs osti_scitechconnect_22334057
crossref_primary_10_1118_1_4888221
crossref_citationtrail_10_1118_1_4888221
wiley_primary_10_1118_1_4888221_MP8221
PublicationCentury 2000
PublicationDate June 2014
2014-06-00
2014-06-01
PublicationDateYYYYMMDD 2014-06-01
PublicationDate_xml – month: 06
  year: 2014
  text: June 2014
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Medical physics (Lancaster)
PublicationYear 2014
Publisher American Association of Physicists in Medicine
Publisher_xml – name: American Association of Physicists in Medicine
SSID ssj0006350
Score 2.0894914
Snippet Purpose: MRI guided radiotherapy is particularly attractive for abdominal targets with low CT contrast. To fully utilize this modality for pancreas tracking,...
Abstract only
Purpose: MRI guided radiotherapy is particularly attractive for abdominal targets with low CT contrast. To fully utilize this modality for pancreas tracking,...
SourceID osti
crossref
wiley
SourceType Open Access Repository
Enrichment Source
Index Database
Publisher
StartPage 195
SubjectTerms 60 APPLIED LIFE SCIENCES
ACCURACY
ANATOMY
BLOOD VESSELS
COMPARATIVE EVALUATIONS
Computed tomography
Edge detection
GROWTH
HYBRIDIZATION
INDEXES
LIMITING VALUES
LIVER
LUNGS
Medical image contrast
Medical image segmentation
Medical magnetic resonance imaging
NMR IMAGING
PANCREAS
PATIENTS
Radiation therapy
RADIOTHERAPY
SEEDS
STOMACH
Title SU‐E‐J‐168: Automated Pancreas Segmentation Based On Dynamic MRI
URI https://onlinelibrary.wiley.com/doi/abs/10.1118%2F1.4888221
https://www.osti.gov/biblio/22334057
Volume 41
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/eLvHCXMwpV1LSwMxEB5Kq-LFt1hfBBHxstpttjHRk6-iYrWoBW9LNsmKoFtpq2d_gr_RX-LMbloQFAQPYS_JskxmMt9sZr4B2OREocKNC4R0IkAEXg-0VC5ICW7IWuR0mObNJvauruT9vWqX4GBYC1PwQ4x-uJFl5Oc1GbhOfBeSkBLXwx3UPXRvGPpUqKgKI6_KyU2zczk6iNGXFhUoKqJLhIYnFsLlu6PF39xRuYtm9R2l5m6mOf2vD5yBKY8u2WGhDrNQctkcTLT8_fkcjOcJn6Y_D83bzuf7xymOCxyhkPvs8HXQRfzqLGujKlCyOrt1D8--OCljR-jwLLvO2EnRxZ61bs4XoNM8vTs-C3xPhcBQKBVIoa2KpEhT41Td1jC-45ZY8TTiCsttKK3UXLiGM4lA-3SixusaRVkX0tok4YtQzrqZWwImG-ke10pK6xpRlCqpbE0rqqxNrLWGV2F7KNrYeMJx6nvxFBeBh4zD2EuoChujqS8Fy8ZPk1Zpf2KEBsRvaygRyAxixDecUGcVtvLd-P0FcatNj-W_TlyBSYRHUZEYtgrlQe_VrcGYeRs89nvrXtu-AD0R0nA
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEB6kPi8-qmJ9BhHxstpttmkiXtS2-GhrUQu9LdskK4JuRatnf4K_0V_izG4sFBQED2EvSViSmcw3ycw3ADucKFS4tp6QVniIwEteJJX1YoIbshjYyI_TYhOVVkt2u6o9BkffuTAZP8Twwo00Iz2vScHpQtppOUWu-_sofGjf0PcZDwSvyByMV6_rncbwJEZjmqWgqIBeEcqOWQiHHwwHj9ijXB_1ahSmpnamPve_P5yHWYcv2XEmEAswZpM8TDXdC3oeJtOQT_2yCPWbzuf7Rw3bBTZfyEN2_DroI4K1hrVRGChcnd3Yu0eXnpSwEzR5hl0lrJrVsWfN6_Ml6NRrt6dnnquq4GlypjwpIqMCKeJYW1UyRfTwuCFevAiRheHGl0ZGXNiy1T2BGmpFkZciXMuSkMb0enwZckk_sSvAZDmu8EhJaWw5CGIllSlGinJre8YYzQuw9722oXaU41T54iHMXA8Z-qFboQJsD7s-ZTwbP3Vapw0KERwQw62mUCA9CBHhcMKdBdhNt-P3CcJmmz6rf-24BdNnt81G2DhvXa7BDIKlIAsTW4fc4PnVbsCEfhvcvzxvOtH7Au7k1mA
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=SU-E-J-168%3A+Automated+Pancreas+Segmentation+Based+On+Dynamic+MRI&rft.jtitle=Medical+physics+%28Lancaster%29&rft.au=Gou%2C+S&rft.au=Rapacchi%2C+S&rft.au=Hu%2C+P&rft.au=Sheng%2C+K&rft.date=2014-06-01&rft.issn=0094-2405&rft.eissn=2473-4209&rft.volume=41&rft.issue=6&rft_id=info:doi/10.1118%2F1.4888221&rft.externalDocID=22334057
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