View in EDS PDF Full Text

Radiomics of high-resolution computed tomography for the differentiation between cholesteatoma and middle ear inflammation: effects of post-reconstruction methods in a dual-center study.

Saved in:
Bibliographic Details
Title: Radiomics of high-resolution computed tomography for the differentiation between cholesteatoma and middle ear inflammation: effects of post-reconstruction methods in a dual-center study.
Authors: Arendt, Christophe T.1 (AUTHOR), Leithner, Doris1,2 (AUTHOR), Mayerhoefer, Marius E.2,3 (AUTHOR) marius.mayerhoefer@meduniwien.ac.at, Gibbs, Peter2 (AUTHOR), Czerny, Christian3 (AUTHOR), Arnoldner, Christoph4 (AUTHOR), Burck, Iris1 (AUTHOR), Leinung, Martin5 (AUTHOR), Tanyildizi, Yasemin6 (AUTHOR), Lenga, Lukas1 (AUTHOR), Martin, Simon S.1 (AUTHOR), Vogl, Thomas J.1 (AUTHOR), Schernthaner, Ruediger E.3 (AUTHOR)
Source: European Radiology. Jun2021, Vol. 31 Issue 6, p4071-4078. 8p. 1 Color Photograph, 1 Black and White Photograph, 1 Chart, 1 Graph.
Subjects: Otitis media, Radiomics, Cholesteatoma, Receiver operating characteristic curves, Tomography, Retrospective studies, Impact of Event Scale, Computed tomography
Abstract: Objectives: To evaluate the performance of radiomic features extracted from high-resolution computed tomography (HRCT) for the differentiation between cholesteatoma and middle ear inflammation (MEI), and to investigate the impact of post-reconstruction harmonization and data resampling.Methods: One hundred patients were included in this retrospective dual-center study: 48 with histology-proven cholesteatoma (center A: 23; center B: 25) and 52 with MEI (A: 27; B: 25). Radiomic features (co-occurrence and run-length matrix, absolute gradient, autoregressive model, Haar wavelet transform) were extracted from manually defined 2D-ROIs. The ten best features for lesion differentiation were selected using probability of error and average correlation coefficients. A multi-layer perceptron feed-forward artificial neural network (MLP-ANN) was used for radiomics-based classification, with histopathology serving as the reference standard (70% of cases for training, 30% for validation). The analysis was performed five times each on (a) unmodified data and on data that were (b) resampled to the same matrix size, and (c) corrected for acquisition protocol differences using ComBat harmonization.Results: Using unmodified data, the MLP-ANN classification yielded an overall median area under the receiver operating characteristic curve (AUC) of 0.78 (0.72-0.84). Using original data from center A and resampled data from center B, an overall median AUC of 0.88 (0.82-0.99) was yielded, while using ComBat harmonized data, an overall median AUC of 0.89 (0.79-0.92) was revealed.Conclusion: Radiomic features extracted from HRCT differentiate between cholesteatoma and MEI. When using multi-centric data obtained with differences in CT acquisition parameters, data resampling and ComBat post-reconstruction harmonization clearly improve radiomics-based lesion classification.Key Points: • Unenhanced high-resolution CT coupled with radiomics analysis may be useful for the differentiation between cholesteatoma and middle ear inflammation. • Pooling of data extracted from inhomogeneous CT datasets does not appear meaningful without further post-processing. • When using multi-centric CT data obtained with differences in acquisition parameters, post-reconstruction harmonization and data resampling clearly improve radiomics-based soft-tissue differentiation. [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
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 150343664
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Radiomics of high-resolution computed tomography for the differentiation between cholesteatoma and middle ear inflammation: effects of post-reconstruction methods in a dual-center study.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Arendt%2C+Christophe+T%2E%22">Arendt, Christophe T.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Leithner%2C+Doris%22">Leithner, Doris</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Mayerhoefer%2C+Marius+E%2E%22">Mayerhoefer, Marius E.</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<i> marius.mayerhoefer@meduniwien.ac.at</i><br /><searchLink fieldCode="AR" term="%22Gibbs%2C+Peter%22">Gibbs, Peter</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Czerny%2C+Christian%22">Czerny, Christian</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Arnoldner%2C+Christoph%22">Arnoldner, Christoph</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Burck%2C+Iris%22">Burck, Iris</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Leinung%2C+Martin%22">Leinung, Martin</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tanyildizi%2C+Yasemin%22">Tanyildizi, Yasemin</searchLink><relatesTo>6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lenga%2C+Lukas%22">Lenga, Lukas</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Martin%2C+Simon+S%2E%22">Martin, Simon S.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Vogl%2C+Thomas+J%2E%22">Vogl, Thomas J.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Schernthaner%2C+Ruediger+E%2E%22">Schernthaner, Ruediger E.</searchLink><relatesTo>3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22European+Radiology%22">European Radiology</searchLink>. Jun2021, Vol. 31 Issue 6, p4071-4078. 8p. 1 Color Photograph, 1 Black and White Photograph, 1 Chart, 1 Graph.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Otitis+media%22">Otitis media</searchLink><br /><searchLink fieldCode="DE" term="%22Radiomics%22">Radiomics</searchLink><br /><searchLink fieldCode="DE" term="%22Cholesteatoma%22">Cholesteatoma</searchLink><br /><searchLink fieldCode="DE" term="%22Receiver+operating+characteristic+curves%22">Receiver operating characteristic curves</searchLink><br /><searchLink fieldCode="DE" term="%22Tomography%22">Tomography</searchLink><br /><searchLink fieldCode="DE" term="%22Retrospective+studies%22">Retrospective studies</searchLink><br /><searchLink fieldCode="DE" term="%22Impact+of+Event+Scale%22">Impact of Event Scale</searchLink><br /><searchLink fieldCode="DE" term="%22Computed+tomography%22">Computed tomography</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: <bold>Objectives: </bold>To evaluate the performance of radiomic features extracted from high-resolution computed tomography (HRCT) for the differentiation between cholesteatoma and middle ear inflammation (MEI), and to investigate the impact of post-reconstruction harmonization and data resampling.<bold>Methods: </bold>One hundred patients were included in this retrospective dual-center study: 48 with histology-proven cholesteatoma (center A: 23; center B: 25) and 52 with MEI (A: 27; B: 25). Radiomic features (co-occurrence and run-length matrix, absolute gradient, autoregressive model, Haar wavelet transform) were extracted from manually defined 2D-ROIs. The ten best features for lesion differentiation were selected using probability of error and average correlation coefficients. A multi-layer perceptron feed-forward artificial neural network (MLP-ANN) was used for radiomics-based classification, with histopathology serving as the reference standard (70% of cases for training, 30% for validation). The analysis was performed five times each on (a) unmodified data and on data that were (b) resampled to the same matrix size, and (c) corrected for acquisition protocol differences using ComBat harmonization.<bold>Results: </bold>Using unmodified data, the MLP-ANN classification yielded an overall median area under the receiver operating characteristic curve (AUC) of 0.78 (0.72-0.84). Using original data from center A and resampled data from center B, an overall median AUC of 0.88 (0.82-0.99) was yielded, while using ComBat harmonized data, an overall median AUC of 0.89 (0.79-0.92) was revealed.<bold>Conclusion: </bold>Radiomic features extracted from HRCT differentiate between cholesteatoma and MEI. When using multi-centric data obtained with differences in CT acquisition parameters, data resampling and ComBat post-reconstruction harmonization clearly improve radiomics-based lesion classification.<bold>Key Points: </bold>• Unenhanced high-resolution CT coupled with radiomics analysis may be useful for the differentiation between cholesteatoma and middle ear inflammation. • Pooling of data extracted from inhomogeneous CT datasets does not appear meaningful without further post-processing. • When using multi-centric CT data obtained with differences in acquisition parameters, post-reconstruction harmonization and data resampling clearly improve radiomics-based soft-tissue differentiation. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>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.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=150343664
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00330-020-07564-4
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 8
        StartPage: 4071
    Subjects:
      – SubjectFull: Otitis media
        Type: general
      – SubjectFull: Radiomics
        Type: general
      – SubjectFull: Cholesteatoma
        Type: general
      – SubjectFull: Receiver operating characteristic curves
        Type: general
      – SubjectFull: Tomography
        Type: general
      – SubjectFull: Retrospective studies
        Type: general
      – SubjectFull: Impact of Event Scale
        Type: general
      – SubjectFull: Computed tomography
        Type: general
    Titles:
      – TitleFull: Radiomics of high-resolution computed tomography for the differentiation between cholesteatoma and middle ear inflammation: effects of post-reconstruction methods in a dual-center study.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Arendt, Christophe T.
      – PersonEntity:
          Name:
            NameFull: Leithner, Doris
      – PersonEntity:
          Name:
            NameFull: Mayerhoefer, Marius E.
      – PersonEntity:
          Name:
            NameFull: Gibbs, Peter
      – PersonEntity:
          Name:
            NameFull: Czerny, Christian
      – PersonEntity:
          Name:
            NameFull: Arnoldner, Christoph
      – PersonEntity:
          Name:
            NameFull: Burck, Iris
      – PersonEntity:
          Name:
            NameFull: Leinung, Martin
      – PersonEntity:
          Name:
            NameFull: Tanyildizi, Yasemin
      – PersonEntity:
          Name:
            NameFull: Lenga, Lukas
      – PersonEntity:
          Name:
            NameFull: Martin, Simon S.
      – PersonEntity:
          Name:
            NameFull: Vogl, Thomas J.
      – PersonEntity:
          Name:
            NameFull: Schernthaner, Ruediger E.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2021
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-print
              Value: 09387994
          Numbering:
            – Type: volume
              Value: 31
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: European Radiology
              Type: main
ResultId 1