Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 14 min ago
Peer-reviewedCC BY 4.0Frontiers in Neurology

Decoding glioblastoma recurrence: harnessing radiomics and machine learning for early prediction

  • Lijuan Gao1
  • Tao Yuan1
  • Yawu Liu2,3
  • Xiao Liu1
  • Bocong Gao1
  • Xiaoyun Yang4
  • Yiming Li5
  • Guanmin Quan1
5 affiliations
  1. 1Department of Medical Imaging, The Second Hospital of Hebei Medical University
  2. 2Department of Clinical Radiology, Kuopio University Hospital
  3. 3Department of Neurology, University of Eastern Finland
  4. 4Department of Ultrasound, The Second Hospital of Hebei Medical University
  5. 5Department of Experimental Center, College of Hebei Medical University
Open at sourceDOICite

Abstract

Objective: This study aimed to analyze postoperative periresidual FLAIR hyperintensity and assess radiomic features from periresidual enhancing and non-enhancing subregions for predicting early GBM recurrence (pre-CRT RANO criteria). We also evaluated the incremental prognostic value of multi-subregion radiomic signatures over conventional clinical and MRI features.

Methods: Adult patients with surgically confirmed GBM were retrospectively enrolled and randomly split into training ( n = 128) and test ( n = 56) cohorts at a 7:3 ratio. Postoperative pre-radiotherapy CE-T1WI and FLAIR images were fused to semi-automatically delineate periresidual enhancing (ROI-1) and non-enhancing hyperintense (ROI-2) regions using 3D Slicer. Radiomic features were extracted from both subregions and their fusion area. LASSO regression was used to select optimal features related to early recurrence from ROI-1, ROI-2, and combined subregion datasets. Five machine learning algorithms (DT, LR, NB, SVM, XGBoost) were applied to build radiomic prediction models. To evaluate the incremental value of radiomic signatures, a clinical/MRI-only baseline model was constructed using conventional clinical and morphological MRI features. Multivariate logistic regression was performed to identify independent clinical and MRI predictors. A quantitative Rad-score was generated based on the optimal combined radiomic features, and an integrated radiomics-clinical model with a predictive nomogram was established by incorporating the Rad-score and independent clinical/MRI variables. Ten-fold cross-validation was used for internal validation. Model performance was comprehensively assessed using ROC curves, calibration curves, and decision curve analysis in terms of discrimination, calibration, and clinical utility.

Results: A logistic regression analysis of 184 GBM cases found subventricular zone involvement [HR 4.868 (1.657–14.308), p = 0.004] and partial resection [HR 3.640 (1.341–9.883), p = 0.011] as predictors of early recurrence. The baseline model achieved an AUC of 0.701. Among five models using ROI-1 features, XGBoost performed best with validation AUC of 0.663. For ROI-2, the DT model excelled with 0.713. Combining ROI-1 and ROI-2, XGBoost achieved 0.752. Integrating radiomics with clinical and MRI data, XGBoost reached 0.817. DCA indicated the combined model had the highest clinical effectiveness. DCA showed that a threshold probability of 0.1 to 0.6 yields a net gain.

Conclusion: In-depth analysis of the enhanced and non-enhanced regions, within the FLAIR hyperintense surrounding the residual cavity of GBM before pre-CRT using ML, has revealed certain value for the early prediction of GBM recurrence. Furthermore, a combined model incorporating radiomic features, clinical and conventional MRI attributes enhances the predictive accuracy for survival prognosis.

Related

  1. Pixel-Wise Prediction of Glioblastoma Recurrence Using Mid-Treatment MRI and Deep Learning
    Sara Rezvanjou, Laurentius Oscar Osapoetra, Daniel Moore-Palhares +4
    CancersPeer-reviewedCC BY 4.0Medical imaging & radiologyCrossref
  2. Response to “radiomics of mandibular osteoradionecrosis with recurrence: The need for etiologic and temporal validation”
    Arnaud Beddok
    Physics and Imaging in Radiation OncologyPeer-reviewedCC BYFull textGeneral biologyGeneral medicineHAL
  3. Radiomics of mandibular osteoradionecrosis with recurrence: the need for etiologic and temporal validation
    Erkan Topkan, Efsun Somay, Ugur Selek
    Physics and Imaging in Radiation OncologyPeer-reviewedCC BYFull textOncologyDOAJ
  4. Neoplastic and non-neoplastic astrocyte states converge on mesenchymal and injury-response programs during glioblastoma recurrence
    David Lindgren, Rebecca Rosberg, Karolina I. Smolag +17
    Cell ReportsPeer-reviewedCC BY 4.0Human geneticsCrossref
  5. Explainable DSC Perfusion Radiomics for Post-Treatment Glioblastoma Assessment Using a Soft-Voting Machine-Learning Ensemble
    Rafail C. Christodoulou, Giorgos Christofi, Georgios Vamvouras +6
    CancersPeer-reviewedCC BY 4.0OncologyCrossref

Cite

BibTeXRIS
BibTeX
@article{gao2026decoding,
  title = {{Decoding glioblastoma recurrence: harnessing radiomics and machine learning for early prediction}},
  author = {Lijuan Gao and Tao Yuan and Yawu Liu and Xiao Liu and Bocong Gao and Xiaoyun Yang and Yiming Li and Guanmin Quan},
  journal = {Frontiers in Neurology},
  year = {2026},
  month = nov,
  doi = {10.3389/fneur.2026.1909375},
  url = {https://www.frontiersin.org/articles/10.3389/fneur.2026.1909375/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Decoding glioblastoma recurrence: harnessing radiomics and machine learning for early prediction
AU  - Lijuan Gao
AU  - Tao Yuan
AU  - Yawu Liu
AU  - Xiao Liu
AU  - Bocong Gao
AU  - Xiaoyun Yang
AU  - Yiming Li
AU  - Guanmin Quan
PY  - 2026
DA  - 2026/11/02
JO  - Frontiers in Neurology
DO  - 10.3389/fneur.2026.1909375
UR  - https://www.frontiersin.org/articles/10.3389/fneur.2026.1909375/full
AB  - Objective: This study aimed to analyze postoperative periresidual FLAIR hyperintensity and assess radiomic features from periresidual enhancing and non-enhancing subregions for predicting early GBM recurrence (pre-CRT RANO criteria). We also evaluated the incremental prognostic value of multi-subregion radiomic signatures over conventional clinical and MRI features.  Methods: Adult patients with surgically confirmed GBM were retrospectively enrolled and randomly split into training ( n = 128) and test ( n = 56) cohorts at a 7:3 ratio. Postoperative pre-radiotherapy CE-T1WI and FLAIR images were fused to semi-automatically delineate periresidual enhancing (ROI-1) and non-enhancing hyperintense (ROI-2) regions using 3D Slicer. Radiomic features were extracted from both subregions and their fusion area. LASSO regression was used to select optimal features related to early recurrence from ROI-1, ROI-2, and combined subregion datasets. Five machine learning algorithms (DT, LR, NB, SVM, XGBoost) were applied to build radiomic prediction models. To evaluate the incremental value of radiomic signatures, a clinical/MRI-only baseline model was constructed using conventional clinical and morphological MRI features. Multivariate logistic regression was performed to identify independent clinical and MRI predictors. A quantitative Rad-score was generated based on the optimal combined radiomic features, and an integrated radiomics-clinical model with a predictive nomogram was established by incorporating the Rad-score and independent clinical/MRI variables. Ten-fold cross-validation was used for internal validation. Model performance was comprehensively assessed using ROC curves, calibration curves, and decision curve analysis in terms of discrimination, calibration, and clinical utility.  Results: A logistic regression analysis of 184 GBM cases found subventricular zone involvement [HR 4.868 (1.657–14.308), p = 0.004] and partial resection [HR 3.640 (1.341–9.883), p = 0.011] as predictors of early recurrence. The baseline model achieved an AUC of 0.701. Among five models using ROI-1 features, XGBoost performed best with validation AUC of 0.663. For ROI-2, the DT model excelled with 0.713. Combining ROI-1 and ROI-2, XGBoost achieved 0.752. Integrating radiomics with clinical and MRI data, XGBoost reached 0.817. DCA indicated the combined model had the highest clinical effectiveness. DCA showed that a threshold probability of 0.1 to 0.6 yields a net gain.  Conclusion: In-depth analysis of the enhanced and non-enhanced regions, within the FLAIR hyperintense surrounding the residual cavity of GBM before pre-CRT using ML, has revealed certain value for the early prediction of GBM recurrence. Furthermore, a combined model incorporating radiomic features, clinical and conventional MRI attributes enhances the predictive accuracy for survival prognosis.
SN  - 1664-2295
ER  -