View in EDS HTML Full Text PDF Full Text

Knowledge‐based automated planning with three‐dimensional generative adversarial networks.

Saved in:
Bibliographic Details
Title: Knowledge‐based automated planning with three‐dimensional generative adversarial networks.
Authors: Babier, Aaron1 (AUTHOR) ababier@mie.utoronto.ca, Mahmood, Rafid1 (AUTHOR), McNiven, Andrea L.2,3 (AUTHOR), Diamant, Adam4 (AUTHOR), Chan, Timothy C.Y.1,5 (AUTHOR)
Source: Medical Physics. Feb2020, Vol. 47 Issue 2, p297-306. 10p.
Subjects: Deep learning, Generating functions, Oropharyngeal cancer, Computed tomography, Three-dimensional imaging, Digital image correlation, Geometric tomography
Abstract: Purpose: To develop a knowledge‐based automated planning pipeline that generates treatment plans without feature engineering, using deep neural network architectures for predicting three‐dimensional (3D) dose. Methods: Our knowledge‐based automated planning (KBAP) pipeline consisted of a knowledge‐based planning (KBP) method that predicts dose for a contoured computed tomography (CT) image followed by two optimization models that learn objective function weights and generate fluence‐based plans, respectively. We developed a novel generative adversarial network (GAN)‐based KBP approach, a 3D GAN model, which predicts dose for the full 3D CT image at once and accounts for correlations between adjacent CT slices. Baseline comparisons were made against two state‐of‐the‐art deep learning–based KBP methods from the literature. We also developed an additional benchmark, a two‐dimensional (2D) GAN model which predicts dose to each axial slice independently. For all models, we investigated the impact of multiplicatively scaling the predictions before optimization, such that the predicted dose distributions achieved all target clinical criteria. Each KBP model was trained on 130 previously delivered oropharyngeal treatment plans. Performance was tested on 87 out‐of‐sample previously delivered treatment plans. All KBAP plans were evaluated using clinical planning criteria and compared to their corresponding clinical plans. KBP prediction quality was assessed using dose‐volume histogram (DVH) differences from the corresponding clinical plans. Results: The best performing KBAP plans were generated using predictions from the 3D GAN model that were multiplicatively scaled. These plans satisfied 77% of all clinical criteria, compared to the clinical plans, which satisfied 67% of all criteria. In general, multiplicatively scaling predictions prior to optimization increased the fraction of clinical criteria satisfaction by 11% relative to the plans generated with nonscaled predictions. Additionally, these KBAP plans satisfied the same criteria as the clinical plans 84% and 8% more frequently as compared to the two benchmark methods, respectively. Conclusions: We developed the first knowledge‐based automated planning framework using a 3D generative adversarial network for prediction. Our results, based on 217 oropharyngeal cancer treatment plans, demonstrated superior performance in satisfying clinical criteria and generated more realistic plans as compared to the previous state‐of‐the‐art approaches. [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: 141676966
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Knowledge‐based automated planning with three‐dimensional generative adversarial networks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Babier%2C+Aaron%22">Babier, Aaron</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> ababier@mie.utoronto.ca</i><br /><searchLink fieldCode="AR" term="%22Mahmood%2C+Rafid%22">Mahmood, Rafid</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22McNiven%2C+Andrea+L%2E%22">McNiven, Andrea L.</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Diamant%2C+Adam%22">Diamant, Adam</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chan%2C+Timothy+C%2EY%2E%22">Chan, Timothy C.Y.</searchLink><relatesTo>1,5</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Medical+Physics%22">Medical Physics</searchLink>. Feb2020, Vol. 47 Issue 2, p297-306. 10p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Generating+functions%22">Generating functions</searchLink><br /><searchLink fieldCode="DE" term="%22Oropharyngeal+cancer%22">Oropharyngeal cancer</searchLink><br /><searchLink fieldCode="DE" term="%22Computed+tomography%22">Computed tomography</searchLink><br /><searchLink fieldCode="DE" term="%22Three-dimensional+imaging%22">Three-dimensional imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Digital+image+correlation%22">Digital image correlation</searchLink><br /><searchLink fieldCode="DE" term="%22Geometric+tomography%22">Geometric tomography</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Purpose: To develop a knowledge‐based automated planning pipeline that generates treatment plans without feature engineering, using deep neural network architectures for predicting three‐dimensional (3D) dose. Methods: Our knowledge‐based automated planning (KBAP) pipeline consisted of a knowledge‐based planning (KBP) method that predicts dose for a contoured computed tomography (CT) image followed by two optimization models that learn objective function weights and generate fluence‐based plans, respectively. We developed a novel generative adversarial network (GAN)‐based KBP approach, a 3D GAN model, which predicts dose for the full 3D CT image at once and accounts for correlations between adjacent CT slices. Baseline comparisons were made against two state‐of‐the‐art deep learning–based KBP methods from the literature. We also developed an additional benchmark, a two‐dimensional (2D) GAN model which predicts dose to each axial slice independently. For all models, we investigated the impact of multiplicatively scaling the predictions before optimization, such that the predicted dose distributions achieved all target clinical criteria. Each KBP model was trained on 130 previously delivered oropharyngeal treatment plans. Performance was tested on 87 out‐of‐sample previously delivered treatment plans. All KBAP plans were evaluated using clinical planning criteria and compared to their corresponding clinical plans. KBP prediction quality was assessed using dose‐volume histogram (DVH) differences from the corresponding clinical plans. Results: The best performing KBAP plans were generated using predictions from the 3D GAN model that were multiplicatively scaled. These plans satisfied 77% of all clinical criteria, compared to the clinical plans, which satisfied 67% of all criteria. In general, multiplicatively scaling predictions prior to optimization increased the fraction of clinical criteria satisfaction by 11% relative to the plans generated with nonscaled predictions. Additionally, these KBAP plans satisfied the same criteria as the clinical plans 84% and 8% more frequently as compared to the two benchmark methods, respectively. Conclusions: We developed the first knowledge‐based automated planning framework using a 3D generative adversarial network for prediction. Our results, based on 217 oropharyngeal cancer treatment plans, demonstrated superior performance in satisfying clinical criteria and generated more realistic plans as compared to the previous state‐of‐the‐art approaches. [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=141676966
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/mp.13896
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 297
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Generating functions
        Type: general
      – SubjectFull: Oropharyngeal cancer
        Type: general
      – SubjectFull: Computed tomography
        Type: general
      – SubjectFull: Three-dimensional imaging
        Type: general
      – SubjectFull: Digital image correlation
        Type: general
      – SubjectFull: Geometric tomography
        Type: general
    Titles:
      – TitleFull: Knowledge‐based automated planning with three‐dimensional generative adversarial networks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Babier, Aaron
      – PersonEntity:
          Name:
            NameFull: Mahmood, Rafid
      – PersonEntity:
          Name:
            NameFull: McNiven, Andrea L.
      – PersonEntity:
          Name:
            NameFull: Diamant, Adam
      – PersonEntity:
          Name:
            NameFull: Chan, Timothy C.Y.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 02
              Text: Feb2020
              Type: published
              Y: 2020
          Identifiers:
            – Type: issn-print
              Value: 00942405
          Numbering:
            – Type: volume
              Value: 47
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Medical Physics
              Type: main
ResultId 1