EUVIMEDEUVIMED entdecken
MetaanalyseSystematische ÜbersichtOpen Access · CC BY 4.0

Diagnostic performance of deep learning for predicting glioma isocitrate dehydrogenase and 1p/19q co-deletion in MRI: a systematic review and meta-analysis

Somayeh Farahani, Marjaneh Hejazi, Mehnaz Tabassum, Antonio Di Ieva, Neda Mahdavifar, Sidong Liu

European Radiology · 16.08.2025 · 36 (2) · 1562-1591

DOI: 10.1007/s00330-025-11898-2 ↗

Kurz gefasst

Metaanalyse in der Zeitschrift European Radiology, online erschienen am 16.08.2025. Verfasst von Somayeh Farahani und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Physics and Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran. somayeh.farahani@h…. Hauptthemen laut MEDLINE: Glioma, Isocitrate Dehydrogenase, Deep Learning, Magnetic Resonance Imaging. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 150 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHMRC Ideas Grant.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

We aimed to evaluate the diagnostic performance of deep learning (DL)-based radiomics models for the noninvasive prediction of isocitrate dehydrogenase (IDH) mutation and 1p/19q co-deletion status in glioma patients using MRI sequences, and to identify methodological factors influencing accuracy and generalizability. Materials and methods Following PRISMA guidelines, we systematically searched major databases (PubMed, Scopus, Embase, Web of Science, and Google Scholar) up to March 2025, screening studies that utilized DL to predict IDH and 1p/19q co-deletion status from MRI data. We assessed study quality and risk of bias using the Radiomics Quality Score and the QUADAS-2 tool. Our meta-analysis employed a bivariate model to compute pooled sensitivity and specificity, and meta-regression to assess interstudy heterogeneity.

Results

Among the 1517 unique publications, 104 were included in the qualitative synthesis, and 72 underwent meta-analysis. Pooled estimates for IDH prediction in test cohorts yielded a sensitivity of 0.80 (95% CI: 0.77–0.83) and specificity of 0.85 (95% CI: 0.81–0.87). For 1p/19q co-deletion, sensitivity was 0.75 (95% CI: 0.65–0.82) and specificity was 0.82 (95% CI: 0.75–0.88). Meta-regression identified the tumor segmentation method and the extent of DL integration into the radiomics pipeline as significant contributors to interstudy variability.

Conclusion

Although DL models demonstrate strong potential for noninvasive molecular classification of gliomas, clinical translation requires several critical steps: harmonization of multi-center MRI data using techniques such as histogram matching and DL-based style transfer; adoption of standardized and automated segmentation protocols; extensive multi-center external validation; and prospective clinical validation. Key Points Question Can DL based radiomics using routine MRI noninvasively predict IDH mutation and 1p/19q co-deletion status in gliomas, and what factors affect diagnostic accuracy?

Findings

Meta-analysis showed 80% sensitivity and 85% specificity for predicting IDH mutation, and 75% sensitivity and 82% specificity for 1p/19q co-deletion status . Clinical relevance MRI-based DL models demonstrate clinically useful accuracy for noninvasive glioma molecular classification, but data harmonization, standardized automated segmentation, and rigorous multi-center external validation are essential for clinical adoption . Graphical Abstract

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GliomaIsocitrate DehydrogenaseDeep LearningMagnetic Resonance ImagingBrain NeoplasmsChromosome DeletionHumansChromosomes, Human, Pair 1Chromosomes, Human, Pair 19Sensitivity and Specificity

Stichwörter der Autor:innen

Deep learningGliomaIsocitrate dehydrogenaseMagnetic resonance imagingRadiomics

Substanzen

Isocitrate Dehydrogenase

Autor:innen und Institutionen

  • Department of Medical Physics and Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran. somayeh.farahani@hdr.mq.edu.au.
  • Centre for Health Informatics, Australian Institute of Health Innovation, Macquarie University, Sydney, NSW, Australia. somayeh.farahani@hdr.mq.edu.au.
  • Computational NeuroSurgery (CNS) Lab, Faculty of Medicine, Health and Human Sciences, Macquarie Medical School, Macquarie University, Sydney, NSW, Australia. somayeh.farahani@hdr.mq.edu.au.
  • Department of Medical Physics and Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
  • Centre for Health Informatics, Australian Institute of Health Innovation, Macquarie University, Sydney, NSW, Australia.
  • Computational NeuroSurgery (CNS) Lab, Faculty of Medicine, Health and Human Sciences, Macquarie Medical School, Macquarie University, Sydney, NSW, Australia.

Förderung

  • NHMRC Ideas Grant

Zitieren

APA

Farahani, S., Hejazi, M., Tabassum, M., Di Ieva, A., Mahdavifar, N., & Liu, S. (2025). Diagnostic performance of deep learning for predicting glioma isocitrate dehydrogenase and 1p/19q co-deletion in MRI: a systematic review and meta-analysis. European Radiology, 36(2), 1562-1591. https://doi.org/10.1007/s00330-025-11898-2

Vancouver

Farahani S, Hejazi M, Tabassum M, Di Ieva A, Mahdavifar N, Liu S. Diagnostic performance of deep learning for predicting glioma isocitrate dehydrogenase and 1p/19q co-deletion in MRI: a systematic review and meta-analysis. European Radiology. 2025;36(2):1562-1591. doi:10.1007/s00330-025-11898-2

BibTeX
@article{Farahani2025,
  author = {Farahani, Somayeh and Hejazi, Marjaneh and Tabassum, Mehnaz and Di Ieva, Antonio and Mahdavifar, Neda and Liu, Sidong},
  title = {Diagnostic performance of deep learning for predicting glioma isocitrate dehydrogenase and 1p/19q co-deletion in MRI: a systematic review and meta-analysis},
  journal = {European Radiology},
  year = {2025},
  volume = {36},
  number = {2},
  pages = {1562--1591},
  doi = {10.1007/s00330-025-11898-2}
}
Kostenlos starten →