View in EDS HTML Full Text PDF Full Text

A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics.

Saved in:
Bibliographic Details
Title: A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics.
Authors: Bleker, Jeroen1 (AUTHOR) j.bleker@umcg.nl, Kwee, Thomas C.1 (AUTHOR), Rouw, Dennis2 (AUTHOR), Roest, Christian1 (AUTHOR), Borstlap, Jaap3 (AUTHOR), de Jong, Igle Jan4 (AUTHOR), Dierckx, Rudi A. J. O.1 (AUTHOR), Huisman, Henkjan5 (AUTHOR), Yakar, Derya1 (AUTHOR)
Source: European Radiology. Sep2022, Vol. 32 Issue 9, p6526-6535. 10p. 3 Color Photographs, 1 Diagram, 2 Graphs.
Abstract: Objectives: To determine the value of a deep learning masked (DLM) auto-fixed volume of interest (VOI) segmentation method as an alternative to manual segmentation for radiomics-based diagnosis of clinically significant (CS) prostate cancer (PCa) on biparametric magnetic resonance imaging (bpMRI).Materials and Methods: This study included a retrospective multi-center dataset of 524 PCa lesions (of which 204 are CS PCa) on bpMRI. All lesions were both semi-automatically segmented with a DLM auto-fixed VOI method (averaging < 10 s per lesion) and manually segmented by an expert uroradiologist (averaging 5 min per lesion). The DLM auto-fixed VOI method uses a spherical VOI (with its center at the location of the lowest apparent diffusion coefficient of the prostate lesion as indicated with a single mouse click) from which non-prostate voxels are removed using a deep learning-based prostate segmentation algorithm. Thirteen different DLM auto-fixed VOI diameters (ranging from 6 to 30 mm) were explored. Extracted radiomics data were split into training and test sets (4:1 ratio). Performance was assessed with receiver operating characteristic (ROC) analysis.Results: In the test set, the area under the ROC curve (AUCs) of the DLM auto-fixed VOI method with a VOI diameter of 18 mm (0.76 [95% CI: 0.66-0.85]) was significantly higher (p = 0.0198) than that of the manual segmentation method (0.62 [95% CI: 0.52-0.73]).Conclusions: A DLM auto-fixed VOI segmentation can provide a potentially more accurate radiomics diagnosis of CS PCa than expert manual segmentation while also reducing expert time investment by more than 97%.Key Points: • Compared to traditional expert-based segmentation, a deep learning mask (DLM) auto-fixed VOI placement is more accurate at detecting CS PCa. • Compared to traditional expert-based segmentation, a DLM auto-fixed VOI placement is faster and can result in a 97% time reduction. • Applying deep learning to an auto-fixed VOI radiomics approach can be valuable. [ABSTRACT FROM AUTHOR]
Copyright of European Radiology is the property of Springer Nature 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: 158547004
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Bleker%2C+Jeroen%22&quot;&gt;Bleker, Jeroen&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; j.bleker@umcg.nl&lt;/i&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Kwee%2C+Thomas+C%2E%22&quot;&gt;Kwee, Thomas C.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Rouw%2C+Dennis%22&quot;&gt;Rouw, Dennis&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Roest%2C+Christian%22&quot;&gt;Roest, Christian&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Borstlap%2C+Jaap%22&quot;&gt;Borstlap, Jaap&lt;/searchLink&gt;&lt;relatesTo&gt;3&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22de+Jong%2C+Igle+Jan%22&quot;&gt;de Jong, Igle Jan&lt;/searchLink&gt;&lt;relatesTo&gt;4&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Dierckx%2C+Rudi+A%2E+J%2E+O%2E%22&quot;&gt;Dierckx, Rudi A. J. O.&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Huisman%2C+Henkjan%22&quot;&gt;Huisman, Henkjan&lt;/searchLink&gt;&lt;relatesTo&gt;5&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Yakar%2C+Derya%22&quot;&gt;Yakar, Derya&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22European+Radiology%22&quot;&gt;European Radiology&lt;/searchLink&gt;. Sep2022, Vol. 32 Issue 9, p6526-6535. 10p. 3 Color Photographs, 1 Diagram, 2 Graphs.
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: &lt;bold&gt;Objectives: &lt;/bold&gt;To determine the value of a deep learning masked (DLM) auto-fixed volume of interest (VOI) segmentation method as an alternative to manual segmentation for radiomics-based diagnosis of clinically significant (CS) prostate cancer (PCa) on biparametric magnetic resonance imaging (bpMRI).&lt;bold&gt;Materials and Methods: &lt;/bold&gt;This study included a retrospective multi-center dataset of 524 PCa lesions (of which 204 are CS PCa) on bpMRI. All lesions were both semi-automatically segmented with a DLM auto-fixed VOI method (averaging &lt; 10 s per lesion) and manually segmented by an expert uroradiologist (averaging 5 min per lesion). The DLM auto-fixed VOI method uses a spherical VOI (with its center at the location of the lowest apparent diffusion coefficient of the prostate lesion as indicated with a single mouse click) from which non-prostate voxels are removed using a deep learning-based prostate segmentation algorithm. Thirteen different DLM auto-fixed VOI diameters (ranging from 6 to 30 mm) were explored. Extracted radiomics data were split into training and test sets (4:1 ratio). Performance was assessed with receiver operating characteristic (ROC) analysis.&lt;bold&gt;Results: &lt;/bold&gt;In the test set, the area under the ROC curve (AUCs) of the DLM auto-fixed VOI method with a VOI diameter of 18 mm (0.76 [95% CI: 0.66-0.85]) was significantly higher (p = 0.0198) than that of the manual segmentation method (0.62 [95% CI: 0.52-0.73]).&lt;bold&gt;Conclusions: &lt;/bold&gt;A DLM auto-fixed VOI segmentation can provide a potentially more accurate radiomics diagnosis of CS PCa than expert manual segmentation while also reducing expert time investment by more than 97%.&lt;bold&gt;Key Points: &lt;/bold&gt;• Compared to traditional expert-based segmentation, a deep learning mask (DLM) auto-fixed VOI placement is more accurate at detecting CS PCa. • Compared to traditional expert-based segmentation, a DLM auto-fixed VOI placement is faster and can result in a 97% time reduction. • Applying deep learning to an auto-fixed VOI radiomics approach can be valuable. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;Copyright of European Radiology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder&#39;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.&lt;/i&gt; (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=158547004
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00330-022-08712-8
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 6526
    Titles:
      – TitleFull: A deep learning masked segmentation alternative to manual segmentation in biparametric MRI prostate cancer radiomics.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Bleker, Jeroen
      – PersonEntity:
          Name:
            NameFull: Kwee, Thomas C.
      – PersonEntity:
          Name:
            NameFull: Rouw, Dennis
      – PersonEntity:
          Name:
            NameFull: Roest, Christian
      – PersonEntity:
          Name:
            NameFull: Borstlap, Jaap
      – PersonEntity:
          Name:
            NameFull: de Jong, Igle Jan
      – PersonEntity:
          Name:
            NameFull: Dierckx, Rudi A. J. O.
      – PersonEntity:
          Name:
            NameFull: Huisman, Henkjan
      – PersonEntity:
          Name:
            NameFull: Yakar, Derya
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: Sep2022
              Type: published
              Y: 2022
          Identifiers:
            – Type: issn-print
              Value: 09387994
          Numbering:
            – Type: volume
              Value: 32
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: European Radiology
              Type: main
ResultId 1