View in EDS HTML Full Text PDF Full Text

Robust contour propagation using deep learning and image registration for online adaptive proton therapy of prostate cancer.

Saved in:
Bibliographic Details
Title: Robust contour propagation using deep learning and image registration for online adaptive proton therapy of prostate cancer.
Authors: Elmahdy, Mohamed S.1 (AUTHOR) m.s.e.elmahdy@lumc.nl, Jagt, Thyrza2 (AUTHOR), Zinkstok, Roel Th.3 (AUTHOR), Qiao, Yuchuan1 (AUTHOR), Shahzad, Rahil1 (AUTHOR), Sokooti, Hessam1 (AUTHOR), Yousefi, Sahar1 (AUTHOR), Incrocci, Luca2 (AUTHOR), Marijnen, C.A.M.3 (AUTHOR), Hoogeman, Mischa2 (AUTHOR), Staring, Marius1,3,4 (AUTHOR)
Source: Medical Physics. Aug2019, Vol. 46 Issue 8, p3329-3343. 15p.
Subjects: Proton therapy, Deep learning, Image registration, Prostate cancer, Cancer treatment, Seminal vesicles, Computed tomography
Abstract: Purpose: To develop and validate a robust and accurate registration pipeline for automatic contour propagation for online adaptive Intensity‐Modulated Proton Therapy (IMPT) of prostate cancer using elastix software and deep learning. Methods: A three‐dimensional (3D) Convolutional Neural Network was trained for automatic bladder segmentation of the computed tomography (CT) scans. The automatic bladder segmentation alongside the computed tomography (CT) scan is jointly optimized to add explicit knowledge about the underlying anatomy to the registration algorithm. We included three datasets from different institutes and CT manufacturers. The first was used for training and testing the ConvNet, where the second and the third were used for evaluation of the proposed pipeline. The system performance was quantified geometrically using the dice similarity coefficient (DSC), the mean surface distance (MSD), and the 95% Hausdorff distance (HD). The propagated contours were validated clinically through generating the associated IMPT plans and compare it with the IMPT plans based on the manual delineations. Propagated contours were considered clinically acceptable if their treatment plans met the dosimetric coverage constraints on the manual contours. Results: The bladder segmentation network achieved a DSC of 88% and 82% on the test datasets. The proposed registration pipeline achieved a MSD of 1.29 ± 0.39, 1.48 ± 1.16, and 1.49 ± 0.44 mm for the prostate, seminal vesicles, and lymph nodes, respectively, on the second dataset and a MSD of 2.31 ± 1.92 and 1.76 ± 1.39 mm for the prostate and seminal vesicles on the third dataset. The automatically propagated contours met the dose coverage constraints in 86%, 91%, and 99% of the cases for the prostate, seminal vesicles, and lymph nodes, respectively. A Conservative Success Rate (CSR) of 80% was obtained, compared to 65% when only using intensity‐based registration. Conclusion: The proposed registration pipeline obtained highly promising results for generating treatment plans adapted to the daily anatomy. With 80% of the automatically generated treatment plans directly usable without manual correction, a substantial improvement in system robustness was reached compared to a previous approach. The proposed method therefore facilitates more precise proton therapy of prostate cancer, potentially leading to fewer treatment‐related adverse side effects. [ABSTRACT FROM AUTHOR]
Copyright of Medical Physics is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 138052913
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Robust contour propagation using deep learning and image registration for online adaptive proton therapy of prostate cancer.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Elmahdy%2C+Mohamed+S%2E%22">Elmahdy, Mohamed S.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> m.s.e.elmahdy@lumc.nl</i><br /><searchLink fieldCode="AR" term="%22Jagt%2C+Thyrza%22">Jagt, Thyrza</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zinkstok%2C+Roel+Th%2E%22">Zinkstok, Roel Th.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Qiao%2C+Yuchuan%22">Qiao, Yuchuan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Shahzad%2C+Rahil%22">Shahzad, Rahil</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sokooti%2C+Hessam%22">Sokooti, Hessam</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yousefi%2C+Sahar%22">Yousefi, Sahar</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Incrocci%2C+Luca%22">Incrocci, Luca</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Marijnen%2C+C%2EA%2EM%2E%22">Marijnen, C.A.M.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hoogeman%2C+Mischa%22">Hoogeman, Mischa</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Staring%2C+Marius%22">Staring, Marius</searchLink><relatesTo>1,3,4</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Medical+Physics%22">Medical Physics</searchLink>. Aug2019, Vol. 46 Issue 8, p3329-3343. 15p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Proton+therapy%22">Proton therapy</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Image+registration%22">Image registration</searchLink><br /><searchLink fieldCode="DE" term="%22Prostate+cancer%22">Prostate cancer</searchLink><br /><searchLink fieldCode="DE" term="%22Cancer+treatment%22">Cancer treatment</searchLink><br /><searchLink fieldCode="DE" term="%22Seminal+vesicles%22">Seminal vesicles</searchLink><br /><searchLink fieldCode="DE" term="%22Computed+tomography%22">Computed tomography</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Purpose: To develop and validate a robust and accurate registration pipeline for automatic contour propagation for online adaptive Intensity‐Modulated Proton Therapy (IMPT) of prostate cancer using elastix software and deep learning. Methods: A three‐dimensional (3D) Convolutional Neural Network was trained for automatic bladder segmentation of the computed tomography (CT) scans. The automatic bladder segmentation alongside the computed tomography (CT) scan is jointly optimized to add explicit knowledge about the underlying anatomy to the registration algorithm. We included three datasets from different institutes and CT manufacturers. The first was used for training and testing the ConvNet, where the second and the third were used for evaluation of the proposed pipeline. The system performance was quantified geometrically using the dice similarity coefficient (DSC), the mean surface distance (MSD), and the 95% Hausdorff distance (HD). The propagated contours were validated clinically through generating the associated IMPT plans and compare it with the IMPT plans based on the manual delineations. Propagated contours were considered clinically acceptable if their treatment plans met the dosimetric coverage constraints on the manual contours. Results: The bladder segmentation network achieved a DSC of 88% and 82% on the test datasets. The proposed registration pipeline achieved a MSD of 1.29 ± 0.39, 1.48 ± 1.16, and 1.49 ± 0.44 mm for the prostate, seminal vesicles, and lymph nodes, respectively, on the second dataset and a MSD of 2.31 ± 1.92 and 1.76 ± 1.39 mm for the prostate and seminal vesicles on the third dataset. The automatically propagated contours met the dose coverage constraints in 86%, 91%, and 99% of the cases for the prostate, seminal vesicles, and lymph nodes, respectively. A Conservative Success Rate (CSR) of 80% was obtained, compared to 65% when only using intensity‐based registration. Conclusion: The proposed registration pipeline obtained highly promising results for generating treatment plans adapted to the daily anatomy. With 80% of the automatically generated treatment plans directly usable without manual correction, a substantial improvement in system robustness was reached compared to a previous approach. The proposed method therefore facilitates more precise proton therapy of prostate cancer, potentially leading to fewer treatment‐related adverse side effects. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Medical Physics is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=138052913
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/mp.13620
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 3329
    Subjects:
      – SubjectFull: Proton therapy
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Image registration
        Type: general
      – SubjectFull: Prostate cancer
        Type: general
      – SubjectFull: Cancer treatment
        Type: general
      – SubjectFull: Seminal vesicles
        Type: general
      – SubjectFull: Computed tomography
        Type: general
    Titles:
      – TitleFull: Robust contour propagation using deep learning and image registration for online adaptive proton therapy of prostate cancer.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Elmahdy, Mohamed S.
      – PersonEntity:
          Name:
            NameFull: Jagt, Thyrza
      – PersonEntity:
          Name:
            NameFull: Zinkstok, Roel Th.
      – PersonEntity:
          Name:
            NameFull: Qiao, Yuchuan
      – PersonEntity:
          Name:
            NameFull: Shahzad, Rahil
      – PersonEntity:
          Name:
            NameFull: Sokooti, Hessam
      – PersonEntity:
          Name:
            NameFull: Yousefi, Sahar
      – PersonEntity:
          Name:
            NameFull: Incrocci, Luca
      – PersonEntity:
          Name:
            NameFull: Marijnen, C.A.M.
      – PersonEntity:
          Name:
            NameFull: Hoogeman, Mischa
      – PersonEntity:
          Name:
            NameFull: Staring, Marius
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2019
              Type: published
              Y: 2019
          Identifiers:
            – Type: issn-print
              Value: 00942405
          Numbering:
            – Type: volume
              Value: 46
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: Medical Physics
              Type: main
ResultId 1