Beyond hand-crafted features for pretherapeutic molecular status identification of pediatric low-grade gliomas.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
    • Publication Information:
      Original Publication: London : Nature Publishing Group, copyright 2011-
    • Subject Terms:
      Glioma*/genetics ; Glioma*/diagnostic imaging ; Glioma*/pathology ; Magnetic Resonance Imaging*/methods ; Brain Neoplasms*/genetics ; Brain Neoplasms*/diagnostic imaging ; Brain Neoplasms*/pathology ; Neural Networks, Computer*; Humans ; Child ; Female ; Retrospective Studies ; Male ; Adolescent ; Child, Preschool ; Neoplasm Grading ; Infant
    • Abstract:
      The use of targeted agents in the treatment of pediatric low-grade gliomas (pLGGs) relies on the determination of molecular status. It has been shown that genetic alterations in pLGG can be identified non-invasively using MRI-based radiomic features or convolutional neural networks (CNNs). We aimed to build and assess a combined radiomics and CNN non-invasive pLGG molecular status identification model. This retrospective study used the tumor regions, manually segmented from T2-FLAIR MR images, of 336 patients treated for pLGG between 1999 and 2018. We designed a CNN and Random Forest radiomics model, along with a model relying on a combination of CNN and radiomic features, to predict the genetic status of pLGG. Additionally, we investigated whether CNNs could predict radiomic feature values from MR images. The combined model (mean AUC: 0.824) outperformed the radiomics model (0.802) and CNN (0.764). The differences in model performance were statistically significant (p-values < 0.05). The CNN was able to learn predictive radiomic features such as surface-to-volume ratio (average correlation: 0.864), and difference matrix dependence non-uniformity normalized (0.924) well but was unable to learn others such as run-length matrix variance (- 0.017) and non-uniformity normalized (- 0.042). Our results show that a model relying on both CNN and radiomic-based features performs better than either approach separately in differentiating the genetic status of pLGGs, and that CNNs are unable to express all handcrafted features.
      (© 2024. The Author(s).)
    • References:
      IEEE Signal Process Mag. 2019 Jan;36(1):164-173. (PMID: 31543691)
      Med Phys. 2017 Oct;44(10):5162-5171. (PMID: 28681390)
      Eur Radiol. 2024 Apr;34(4):2772-2781. (PMID: 37803212)
      Magn Reson Imaging. 2012 Nov;30(9):1323-41. (PMID: 22770690)
      BMC Cancer. 2023 Sep 11;23(1):848. (PMID: 37697238)
      Can Assoc Radiol J. 2024 Feb;75(1):153-160. (PMID: 37401906)
      Neuro Oncol. 2020 Oct 30;22(12 Suppl 2):iv1-iv96. (PMID: 33123732)
      Proc IEEE Inst Electr Electron Eng. 2020 Jan;108(1):163-177. (PMID: 34045769)
      Front Oncol. 2020 Jan 31;10:53. (PMID: 32083007)
      Sci Rep. 2021 Jan 14;11(1):1378. (PMID: 33446870)
      Clin Neurol Neurosurg. 2022 Nov;222:107478. (PMID: 36244075)
      Nat Commun. 2014 Jun 03;5:4006. (PMID: 24892406)
      Cancer Cell. 2020 Apr 13;37(4):569-583.e5. (PMID: 32289278)
      Neuro Oncol. 2021 Feb 25;23(2):304-313. (PMID: 32706862)
      Insights Imaging. 2018 Aug;9(4):611-629. (PMID: 29934920)
      Nat Rev Clin Oncol. 2017 Dec;14(12):749-762. (PMID: 28975929)
      Radiology. 2019 Feb;290(2):290-297. (PMID: 30422086)
      Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:1742-1745. (PMID: 33018334)
      Radiol Artif Intell. 2024 May;6(3):e230333. (PMID: 38446044)
      J Child Neurol. 2009 Nov;24(11):1397-408. (PMID: 19841428)
      PET Clin. 2021 Oct;16(4):597-612. (PMID: 34537132)
      Sci Data. 2017 Sep 05;4:170117. (PMID: 28872634)
      IEEE Trans Med Imaging. 2015 Oct;34(10):1993-2024. (PMID: 25494501)
      Neural Comput. 1998 Sep 15;10(7):1895-1923. (PMID: 9744903)
      Cancer Res. 2017 Nov 1;77(21):e104-e107. (PMID: 29092951)
      Sci Rep. 2019 Apr 5;9(1):5746. (PMID: 30952930)
      Evol Intell. 2022;15(1):1-22. (PMID: 33425040)
      NPJ Digit Med. 2021 Feb 22;4(1):33. (PMID: 33619361)
      JAMA Oncol. 2016 Dec 01;2(12):1636-1642. (PMID: 27541161)
      Insights Imaging. 2020 Jan 03;11(1):1. (PMID: 31901171)
      Hum Brain Mapp. 2010 May;31(5):798-819. (PMID: 20017133)
      AJNR Am J Neuroradiol. 2022 Jun;43(6):792-801. (PMID: 34649914)
      Front Oncol. 2020 Dec 22;10:593192. (PMID: 33415075)
      Phys Med Biol. 2021 Mar 04;66(6):065015. (PMID: 33596552)
      AJNR Am J Neuroradiol. 2021 Apr;42(4):759-765. (PMID: 33574103)
      Comput Methods Programs Biomed. 2022 Jun;219:106750. (PMID: 35381490)
      Neuro Oncol. 2011 Feb;13(2):223-34. (PMID: 21177781)
      Acta Neuropathol Commun. 2020 Mar 12;8(1):30. (PMID: 32164789)
      Front Oncol. 2021 Jan 26;10:570465. (PMID: 33575207)
    • Grant Information:
      184015 Canada CIHR; 184015 Canada CIHR
    • Publication Date:
      Date Created: 20240817 Date Completed: 20240817 Latest Revision: 20240922
    • Publication Date:
      20240922
    • Accession Number:
      PMC11330469
    • Accession Number:
      10.1038/s41598-024-69870-x
    • Accession Number:
      39154039