EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

AI radiomics predicts spatial glioma recurrence on preoperative MRI: a systematic review

Sebastiaan Bijlsma, Thomas Maal, Christian Rubbert, Manoj Mannil, Anton Meijer, Anja van der Kolk, Guido de Jong, Dylan Henssen

European Journal of Radiology · 2025-12 · 193 · 112412

DOI: 10.1016/j.ejrad.2025.112412 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift European Journal of Radiology, 2025-12. Verfasst von Sebastiaan Bijlsma und 7 weiteren Autor:innen. Beteiligte Einrichtung: 3D Lab Radboudumc, Department of Medical Imaging Radboudumc, Nijmegen, the Netherlands. Electronic address: sebastiaan.bijlsma@radboudumc.nl. Hauptthemen laut MEDLINE: Glioma, Magnetic Resonance Imaging, Brain Neoplasms, Neoplasm Recurrence, Local. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Adult-type diffuse gliomas are highly infiltrative primary brain tumors in which, after a combination of surgery and chemoradiation therapy, tumor recurrence is inevitable. Artificial Intelligence (AI) models have been found capable to predict local and distant tumor recurrence at baseline, with the potential to guide surgical margins and enable focal dose escalation in radiotherapy. This study systematically reviews the literature on the performance of AI models in predicting local or distant tumor recurrence in glioma patients using preoperative MRI data. METHODS: A systematic literature search was conducted across PubMed, EMBASE, and the Cochrane Library. Studies evaluating AI-based models for spatial recurrence prediction in gliomas using preoperative MRI were included. Study quality and methodological rigor were assessed using the PROBAST + AI tool. FINDINGS: Eight studies, comprising 1004 high grade glioma patients, were included. A variety of machine learning and deep learning model architectures (e.g., Random Forest classifiers, Support Vector Machines and custom Convolutional Neural Networks) were employed. Input data were a heterogeneous combination of conventional MRI (e.g., T1CE, FLAIR) and more advanced imaging modalities (e.g., diffusion-weighted imaging). Considerable variability was reported with regard to sensitivity and specificity rates (ranging between 40 %-97 % and 29 %-98 %, respectively) for predicting tumor recurrence. The odds ratios for predicting regions of tumor recurrence, however, were generally high (ranging between 8.13-19.48). External validation was performed in 4 studies with one study using a multicenter cohort of 6 different institutions, demonstrating high generalizability in predictive performance. Risk of bias analysis was performed using the recently published PROBAST + AI tool and revealed generally low to unclear concern for risk of bias and low concern for applicability. INTERPRETATION: AI models have been shown capable of predicting local and distant tumor recurrence in glioma patients from baseline MRI data. While the high odds ratios reported from the multicenter study are encouraging, the evidence comes mainly from small, single-center, retrospective cohorts, so larger prospective multicenter studies are needed before clinical adoption.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GliomaMagnetic Resonance ImagingBrain NeoplasmsNeoplasm Recurrence, LocalArtificial IntelligenceHumansPreoperative CareSensitivity and SpecificityRadiomics

Stichwörter der Autor:innen

Artificial IntelligenceDeep LearningGliomaMagnetic resonance imagingRadiomicsSpatial predictionTumor recurrence

Autor:innen und Institutionen

  • 3D Lab Radboudumc, Department of Medical Imaging Radboudumc, Nijmegen, the Netherlands. Electronic address: sebastiaan.bijlsma@radboudumc.nl.
  • 3D Lab Radboudumc, Department of Medical Imaging Radboudumc, Nijmegen, the Netherlands.
  • Institute for Diagnostic and Interventional Radiology, University Hospital and Medical Faculty University Hospital Düsseldorf, Düsseldorf, Germany.
  • Clinic of Radiology, University Hospital Münster, Münster, Germany.
  • Department of Medical Imaging, Radboudumc, Nijmegen, the Netherlands.
  • Department of Medical Imaging, Radboudumc, Nijmegen, the Netherlands; Department of Nuclear Medicine, University Hospital Leipzig, Leipzig, Germany.

Zitieren

APA

Bijlsma, S., Maal, T., Rubbert, C., Mannil, M., Meijer, A., van der Kolk, A., de Jong, G., & Henssen, D. (2025). AI radiomics predicts spatial glioma recurrence on preoperative MRI: a systematic review. European Journal of Radiology, 193, 112412. https://doi.org/10.1016/j.ejrad.2025.112412

Vancouver

Bijlsma S, Maal T, Rubbert C, Mannil M, Meijer A, van der Kolk A, et al. AI radiomics predicts spatial glioma recurrence on preoperative MRI: a systematic review. European Journal of Radiology. 2025;193:112412. doi:10.1016/j.ejrad.2025.112412

BibTeX
@article{Bijlsma2025,
  author = {Bijlsma, Sebastiaan and Maal, Thomas and Rubbert, Christian and Mannil, Manoj and Meijer, Anton and van der Kolk, Anja and de Jong, Guido and Henssen, Dylan},
  title = {AI radiomics predicts spatial glioma recurrence on preoperative MRI: a systematic review},
  journal = {European Journal of Radiology},
  year = {2025},
  volume = {193},
  pages = {112412},
  doi = {10.1016/j.ejrad.2025.112412}
}
Kostenlos starten →