View in EDS HTML Full Text PDF Full Text

A data‐driven intravoxel mean diffusivities distribution approach for molecular classifications and MIB‐1 prediction of gliomas.

Saved in:
Bibliographic Details
Title: A data‐driven intravoxel mean diffusivities distribution approach for molecular classifications and MIB‐1 prediction of gliomas.
Authors: Xu, Junqi1 (AUTHOR), Sheng, Yaru2 (AUTHOR), Li, Hao1 (AUTHOR), Yang, Zidong3,4 (AUTHOR), Ren, Yan2 (AUTHOR) renyan_richard@aliyun.com, Wang, He1,5,6 (AUTHOR) hewang@fudan.edu.cn
Source: Medical Physics. Oct2024, Vol. 51 Issue 10, p7332-7344. 13p.
Subjects: Magnetic resonance imaging, Isocitrate dehydrogenase, Fuzzy algorithms, Regression analysis, Gliomas, Fuzzy clustering technique
Abstract: Background: Measuring non‐parametric intravoxel mean diffusivity distributions (MDDs) using magnetic resonance imaging (MRI) is a sensitive method for detecting intracellular diffusivity changes during physiological alterations. Histological and molecular glioma classifications are essential for prognosis and treatment, with distinct water diffusion dynamics among subtypes. Purpose: We developed a data‐driven approach using a fully connected network (FCN) to enhance the speed and stability of calculating MDDs across varying SNRs, enable tumor microstructural mapping, and test its reliability in identifying MIB‐1 labeling index (LI) levels and molecular status of gliomas. Methods: An FCN was trained to learn the mapping between the simulated diffusion decay curves and the ground truth MDDs. We performed 5 000 000 simulation curves with various diffusivity components and random SNR ∈[30,300]$ \in [ {30,\ 300} ]$. Eighty percent of simulation curves were used for the FCN training, 10% for validation, and the others were external tests for the FCN performance evaluation. In vivo data were collected to evaluate its clinical reliability. One hundred one patients (44 years ±$ \pm $ 14, 67 men) with gliomas and six healthy controls underwent a 3.0 T MRI examination with a spin echo–echo planar imaging (SE‐EPI) diffusion‐weighted imaging (DWI) sequence. The trained FCN was employed to calculate MDDs of each brain voxel by voxel. We used the Fuzzy C‐means algorithm to cluster the MDDs of tumor voxels, facilitating the characterization of distinct glioma tissues. Quantitative assessments were conducted through sectional integrals of the MDDs, demarcated by six bands to derive signal fractions (fn,n=1−6${{f}_n},\ n = 1 -6$) and diffusivities of the maximum peaks (Dpeak${{D}_{peak}}$). Cosine similarity scores (CSS) were used for MDD similarity. ANOVA and Mann–Whitney U test were used for difference analysis. Logistic regression and area under the receiver operator characteristic curve (AUC) were used for classification evaluation. Results: The simulation results showed that the FCN‐based MDD approach (FCN‐MDD) achieved higher CSS than non‐negative least squares‐based MDD (NNLS‐MDD). For in vivo data, the spectra of ET and NET obtained by FCN‐MDD are more distinguishable than NNLS‐MDD. Fraction maps delineate the characteristics of different tumor tissues (enhancing and non‐enhancing tumor, edema, and necrosis). f3,f4,Dpeak${{f}_3},\ {{f}_4},{{D}_{peak}}$ showed a positive and negative correlation with MIB‐1 respectively (r=0.568,r=−0.521,r=−0.654$r = 0.568,\ r = - 0.521,\ r = - 0.654$, all p<0.001$p < 0.001$). The AUC of Dpeak${{D}_{peak}}$ for predicting MIB‐1 LI levels was 0.900 (95% CI, 0.826–0.974), versus 0.781 (0.677–0.886) of ADC. The highest AUC of isocitrate dehydrogenase (IDH) mutation status, assessed by a logistic regression model (f1+f3${{f}_1} + {{f}_3}$) was 0.873 (95% CI, 0.802–0.944). Conclusion: The proposed FCN‐MDD method was more robust to variations in SNR and less reliant on empirically set regularization values than the NNLS‐MDD method. FCN‐MDD also enabled qualitative and quantitative evaluation of the composition of gliomas. [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: 180293778
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A data‐driven intravoxel mean diffusivities distribution approach for molecular classifications and MIB‐1 prediction of gliomas.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Xu%2C+Junqi%22&quot;&gt;Xu, Junqi&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Sheng%2C+Yaru%22&quot;&gt;Sheng, Yaru&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Li%2C+Hao%22&quot;&gt;Li, Hao&lt;/searchLink&gt;&lt;relatesTo&gt;1&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Yang%2C+Zidong%22&quot;&gt;Yang, Zidong&lt;/searchLink&gt;&lt;relatesTo&gt;3,4&lt;/relatesTo&gt; (AUTHOR)&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Ren%2C+Yan%22&quot;&gt;Ren, Yan&lt;/searchLink&gt;&lt;relatesTo&gt;2&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; renyan_richard@aliyun.com&lt;/i&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;AR&quot; term=&quot;%22Wang%2C+He%22&quot;&gt;Wang, He&lt;/searchLink&gt;&lt;relatesTo&gt;1,5,6&lt;/relatesTo&gt; (AUTHOR)&lt;i&gt; hewang@fudan.edu.cn&lt;/i&gt;
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22Medical+Physics%22&quot;&gt;Medical Physics&lt;/searchLink&gt;. Oct2024, Vol. 51 Issue 10, p7332-7344. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Magnetic+resonance+imaging%22&quot;&gt;Magnetic resonance imaging&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Isocitrate+dehydrogenase%22&quot;&gt;Isocitrate dehydrogenase&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Fuzzy+algorithms%22&quot;&gt;Fuzzy algorithms&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Regression+analysis%22&quot;&gt;Regression analysis&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Gliomas%22&quot;&gt;Gliomas&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;DE&quot; term=&quot;%22Fuzzy+clustering+technique%22&quot;&gt;Fuzzy clustering technique&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Measuring non‐parametric intravoxel mean diffusivity distributions (MDDs) using magnetic resonance imaging (MRI) is a sensitive method for detecting intracellular diffusivity changes during physiological alterations. Histological and molecular glioma classifications are essential for prognosis and treatment, with distinct water diffusion dynamics among subtypes. Purpose: We developed a data‐driven approach using a fully connected network (FCN) to enhance the speed and stability of calculating MDDs across varying SNRs, enable tumor microstructural mapping, and test its reliability in identifying MIB‐1 labeling index (LI) levels and molecular status of gliomas. Methods: An FCN was trained to learn the mapping between the simulated diffusion decay curves and the ground truth MDDs. We performed 5 000 000 simulation curves with various diffusivity components and random SNR ∈[30,300]$ \in [ {30,\ 300} ]$. Eighty percent of simulation curves were used for the FCN training, 10% for validation, and the others were external tests for the FCN performance evaluation. In vivo data were collected to evaluate its clinical reliability. One hundred one patients (44 years &#177;$ \pm $ 14, 67 men) with gliomas and six healthy controls underwent a 3.0 T MRI examination with a spin echo–echo planar imaging (SE‐EPI) diffusion‐weighted imaging (DWI) sequence. The trained FCN was employed to calculate MDDs of each brain voxel by voxel. We used the Fuzzy C‐means algorithm to cluster the MDDs of tumor voxels, facilitating the characterization of distinct glioma tissues. Quantitative assessments were conducted through sectional integrals of the MDDs, demarcated by six bands to derive signal fractions (fn,n=1−6${{f}_n},\ n = 1 -6$) and diffusivities of the maximum peaks (Dpeak${{D}_{peak}}$). Cosine similarity scores (CSS) were used for MDD similarity. ANOVA and Mann–Whitney U test were used for difference analysis. Logistic regression and area under the receiver operator characteristic curve (AUC) were used for classification evaluation. Results: The simulation results showed that the FCN‐based MDD approach (FCN‐MDD) achieved higher CSS than non‐negative least squares‐based MDD (NNLS‐MDD). For in vivo data, the spectra of ET and NET obtained by FCN‐MDD are more distinguishable than NNLS‐MDD. Fraction maps delineate the characteristics of different tumor tissues (enhancing and non‐enhancing tumor, edema, and necrosis). f3,f4,Dpeak${{f}_3},\ {{f}_4},{{D}_{peak}}$ showed a positive and negative correlation with MIB‐1 respectively (r=0.568,r=−0.521,r=−0.654$r = 0.568,\ r = - 0.521,\ r = - 0.654$, all p&lt;0.001$p &lt; 0.001$). The AUC of Dpeak${{D}_{peak}}$ for predicting MIB‐1 LI levels was 0.900 (95% CI, 0.826–0.974), versus 0.781 (0.677–0.886) of ADC. The highest AUC of isocitrate dehydrogenase (IDH) mutation status, assessed by a logistic regression model (f1+f3${{f}_1} + {{f}_3}$) was 0.873 (95% CI, 0.802–0.944). Conclusion: The proposed FCN‐MDD method was more robust to variations in SNR and less reliant on empirically set regularization values than the NNLS‐MDD method. FCN‐MDD also enabled qualitative and quantitative evaluation of the composition of gliomas. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: &lt;i&gt;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&#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=180293778
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/mp.17280
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 7332
    Subjects:
      – SubjectFull: Magnetic resonance imaging
        Type: general
      – SubjectFull: Isocitrate dehydrogenase
        Type: general
      – SubjectFull: Fuzzy algorithms
        Type: general
      – SubjectFull: Regression analysis
        Type: general
      – SubjectFull: Gliomas
        Type: general
      – SubjectFull: Fuzzy clustering technique
        Type: general
    Titles:
      – TitleFull: A data‐driven intravoxel mean diffusivities distribution approach for molecular classifications and MIB‐1 prediction of gliomas.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Xu, Junqi
      – PersonEntity:
          Name:
            NameFull: Sheng, Yaru
      – PersonEntity:
          Name:
            NameFull: Li, Hao
      – PersonEntity:
          Name:
            NameFull: Yang, Zidong
      – PersonEntity:
          Name:
            NameFull: Ren, Yan
      – PersonEntity:
          Name:
            NameFull: Wang, He
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 00942405
          Numbering:
            – Type: volume
              Value: 51
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Medical Physics
              Type: main
ResultId 1