View in EDS HTML Full Text PDF Full Text

Risk classification of thymoma based on multi‐feature fusion in dynamic enhanced CT.

Saved in:
Bibliographic Details
Title: Risk classification of thymoma based on multi‐feature fusion in dynamic enhanced CT.
Authors: Peng, Xiayan1 (AUTHOR), Liu, Yifei2 (AUTHOR), He, Xiaodong3 (AUTHOR), Lin, Yi3 (AUTHOR), Wu, Yongshun4 (AUTHOR), Chen, Wanyuan5 (AUTHOR), Luo, Chao2 (AUTHOR), Zhou, Shumin2 (AUTHOR), Ruan, Guangying2 (AUTHOR), Li, Haojiang2 (AUTHOR), Chen, Shuchao1 (AUTHOR), Zhou, Haoyang1,6 (AUTHOR), Liu, Lizhi2 (AUTHOR) liulizh@sysucc.org.cn, Chen, Hongbo1,7,8,9 (AUTHOR) hongbochen@163.com
Source: Medical Physics. Jul2025, Vol. 52 Issue 7, p1-13. 13p.
Subjects: Thymoma, Computed tomography, Risk assessment, Radiomics, Noninvasive diagnostic tests, Therapeutics, Deep learning
Abstract: Background: Accurate classification of high‐risk and low‐risk thymomas is critical for guiding treatment strategies and assessing prognosis. Thymoma is the most common primary tumor of the anterior mediastinum. However, previous studies have limitations in comprehensively utilizing imaging data, particularly in combining radiomics and deep learning (DL) features for preoperative classification. Purpose: This study aimed to develop and validate a comprehensive model based on computed tomography (CT) imaging data (CSRT, Clinical Semantic, Radiomics, and Vision Transformer) to enhance the accuracy of preoperative high‐risk and low‐risk classification of thymomas and evaluate its application in non‐invasive diagnosis. Methods: This retrospective study included 360 patients with pathologically confirmed thymomas from three centers, with 274 cases (Centers A and B) used for model training and 86 cases (Center C) serving as an external validation set. CT images, including non‐contrast enhanced CT (NECT) and contrast‐enhanced CT (CECT), were used to extract radiomics features and ViT‐based DL features, along with calculated Delta features (NECT minus CECT). Clinical semantic features were integrated, and key features were selected using t‐tests and least absolute shrinkage and selection operator (LASSO) regression to construct the fusion model. Results: The CSRT model demonstrated excellent performance in the independent validation cohort, achieving an area under the receiver operating characteristic curve (AUC) of 0.835, an accuracy of 77.9%, a sensitivity of 78.4%, and a specificity of 77.1%. Calibration curves indicated high consistency between predictions and actual classifications. Through decision curve analysis, the model exhibited a high net benefit when the threshold probability exceeded 30%, confirming its clinical utility. Conclusions: The CSRT model effectively differentiates between high‐risk and low‐risk thymomas preoperatively using CT imaging data. This non‐invasive diagnostic tool supports individualized treatment strategies and enhances clinical decision‐making, offering significant value for thymoma management by providing reliable classification above clinically relevant risk thresholds. [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: 186809982
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Risk classification of thymoma based on multi‐feature fusion in dynamic enhanced CT.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Peng%2C+Xiayan%22">Peng, Xiayan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Yifei%22">Liu, Yifei</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22He%2C+Xiaodong%22">He, Xiaodong</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lin%2C+Yi%22">Lin, Yi</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wu%2C+Yongshun%22">Wu, Yongshun</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Wanyuan%22">Chen, Wanyuan</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Luo%2C+Chao%22">Luo, Chao</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhou%2C+Shumin%22">Zhou, Shumin</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ruan%2C+Guangying%22">Ruan, Guangying</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Haojiang%22">Li, Haojiang</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Shuchao%22">Chen, Shuchao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhou%2C+Haoyang%22">Zhou, Haoyang</searchLink><relatesTo>1,6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Lizhi%22">Liu, Lizhi</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> liulizh@sysucc.org.cn</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Hongbo%22">Chen, Hongbo</searchLink><relatesTo>1,7,8,9</relatesTo> (AUTHOR)<i> hongbochen@163.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Medical+Physics%22">Medical Physics</searchLink>. Jul2025, Vol. 52 Issue 7, p1-13. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Thymoma%22">Thymoma</searchLink><br /><searchLink fieldCode="DE" term="%22Computed+tomography%22">Computed tomography</searchLink><br /><searchLink fieldCode="DE" term="%22Risk+assessment%22">Risk assessment</searchLink><br /><searchLink fieldCode="DE" term="%22Radiomics%22">Radiomics</searchLink><br /><searchLink fieldCode="DE" term="%22Noninvasive+diagnostic+tests%22">Noninvasive diagnostic tests</searchLink><br /><searchLink fieldCode="DE" term="%22Therapeutics%22">Therapeutics</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Accurate classification of high‐risk and low‐risk thymomas is critical for guiding treatment strategies and assessing prognosis. Thymoma is the most common primary tumor of the anterior mediastinum. However, previous studies have limitations in comprehensively utilizing imaging data, particularly in combining radiomics and deep learning (DL) features for preoperative classification. Purpose: This study aimed to develop and validate a comprehensive model based on computed tomography (CT) imaging data (CSRT, Clinical Semantic, Radiomics, and Vision Transformer) to enhance the accuracy of preoperative high‐risk and low‐risk classification of thymomas and evaluate its application in non‐invasive diagnosis. Methods: This retrospective study included 360 patients with pathologically confirmed thymomas from three centers, with 274 cases (Centers A and B) used for model training and 86 cases (Center C) serving as an external validation set. CT images, including non‐contrast enhanced CT (NECT) and contrast‐enhanced CT (CECT), were used to extract radiomics features and ViT‐based DL features, along with calculated Delta features (NECT minus CECT). Clinical semantic features were integrated, and key features were selected using t‐tests and least absolute shrinkage and selection operator (LASSO) regression to construct the fusion model. Results: The CSRT model demonstrated excellent performance in the independent validation cohort, achieving an area under the receiver operating characteristic curve (AUC) of 0.835, an accuracy of 77.9%, a sensitivity of 78.4%, and a specificity of 77.1%. Calibration curves indicated high consistency between predictions and actual classifications. Through decision curve analysis, the model exhibited a high net benefit when the threshold probability exceeded 30%, confirming its clinical utility. Conclusions: The CSRT model effectively differentiates between high‐risk and low‐risk thymomas preoperatively using CT imaging data. This non‐invasive diagnostic tool supports individualized treatment strategies and enhances clinical decision‐making, offering significant value for thymoma management by providing reliable classification above clinically relevant risk thresholds. [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=186809982
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/mp.17968
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 1
    Subjects:
      – SubjectFull: Thymoma
        Type: general
      – SubjectFull: Computed tomography
        Type: general
      – SubjectFull: Risk assessment
        Type: general
      – SubjectFull: Radiomics
        Type: general
      – SubjectFull: Noninvasive diagnostic tests
        Type: general
      – SubjectFull: Therapeutics
        Type: general
      – SubjectFull: Deep learning
        Type: general
    Titles:
      – TitleFull: Risk classification of thymoma based on multi‐feature fusion in dynamic enhanced CT.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Peng, Xiayan
      – PersonEntity:
          Name:
            NameFull: Liu, Yifei
      – PersonEntity:
          Name:
            NameFull: He, Xiaodong
      – PersonEntity:
          Name:
            NameFull: Lin, Yi
      – PersonEntity:
          Name:
            NameFull: Wu, Yongshun
      – PersonEntity:
          Name:
            NameFull: Chen, Wanyuan
      – PersonEntity:
          Name:
            NameFull: Luo, Chao
      – PersonEntity:
          Name:
            NameFull: Zhou, Shumin
      – PersonEntity:
          Name:
            NameFull: Ruan, Guangying
      – PersonEntity:
          Name:
            NameFull: Li, Haojiang
      – PersonEntity:
          Name:
            NameFull: Chen, Shuchao
      – PersonEntity:
          Name:
            NameFull: Zhou, Haoyang
      – PersonEntity:
          Name:
            NameFull: Liu, Lizhi
      – PersonEntity:
          Name:
            NameFull: Chen, Hongbo
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 00942405
          Numbering:
            – Type: volume
              Value: 52
            – Type: issue
              Value: 7
          Titles:
            – TitleFull: Medical Physics
              Type: main
ResultId 1