EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Pixel-Wise Prediction of Glioblastoma Recurrence Using Mid-Treatment MRI and Deep Learning

Sara Rezvanjou, Laurentius Oscar Osapoetra, Daniel Moore-Palhares, Liam S P Lawrence iD, Angus Z Lau iD, Arjun Sahgal, Gregory J Czarnota

Cancers · 27.10.2026 · 18 (21) · 3465

DOI: 10.3390/cancers18213465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 27.10.2026. Verfasst von Sara Rezvanjou und 6 weiteren Autor:innen. Beteiligte Einrichtung: Physical Sciences, Sunnybrook Research Institute, Toronto, ON M4N 3M5, Canada. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, Terry Fox Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Glioblastoma (GBM) commonly recurs close to the original gross tumor volume (GTV), suggesting treatment-resistant subregions may be present before radiologically visible progression. This study investigated whether deep learning on apparent diffusion coefficient (ADC) maps could generate pixel-wise probability maps of treatment-resistant regions within the GTV.

Methods

The training/validation set included images of 64 in-house patients after radiation fraction 10 (Fx10) and 40 external patients before treatment used as an auxiliary cross-domain training cohort; the held-out test set included 16 in-house Fx10 patients. Resistant regions were defined as the overlap between the GTV from scans acquired at radiation fraction 10 and subsequent recurrence after finishing treatment. Models were trained on 2D GTV-cropped slices with patient-level separation to prevent data leakage. Single- and multimodal MRI inputs were compared, and ADC-based models (including baseline UNet, pretrained ResNet34, BiomedCLIP-assisted UNet, and a BLIP image-text UNet) were later evaluated. Performance was evaluated using conventional metrics, including ROC AUC, PR AUC, F1-score, recall, specificity, and precision.

Results

ADC was the most informative single modality, achieving 69% and 80% for Receiver Operating Characteristic (ROC)- and Precision-Recall (PR)-Area Under the Curve (AUC), respectively. In the ADC-based architecture comparison, no model was consistently superior across all metrics. The baseline UNet achieved the highest accuracy, F1-score, and recall, whereas pretrained ResNet34 and BLIP-assisted models showed slightly higher ROC AUC than the baseline UNet (both 70%). Error analysis showed that performance decreased substantially for small or sparse resistant regions, and false-negative errors were enriched near resistant-region and GTV boundaries.

Conclusions

ADC-based deep learning showed feasibility for pixel-wise spatial mapping of treatment-resistant glioblastoma regions within the GTV. A UNet trained from scratch provided the strongest sensitivity/F1 trade-off, whereas pretrained and VLM-assisted models provided only metric-specific benefits. Model comparisons showed that BiomedCLIP-assisted and BLIP image-text UNet models did not clearly improve fine spatial segmentation performance over the baseline UNet.

Schlagwörter

Stichwörter der Autor:innen

apparent diffusion coefficient (ADC)deep learningglioblastomagross tumor volume (GTV)recurrence-risk mappingtreatment resistancevision–language model

Autor:innen und Institutionen

  • Physical Sciences, Sunnybrook Research Institute, Toronto, ON M4N 3M5, Canada.
  • Department of Radiation Oncology, Odette Cancer Centre, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, Canada.
  • Department of Medical Biophysics, University of Toronto, Toronto, ON M5G 2C4, Canada.
  • Department of Radiation Oncology, University of Toronto, Toronto, ON M4N 3M5, Canada.

ORCID-Profile: Liam S P Lawrence, Angus Z Lau

Förderung

  • Natural Sciences and Engineering Research Council of Canada
  • Terry Fox Foundation

Zitieren

APA

Rezvanjou, S., Osapoetra, L. O., Moore-Palhares, D., Lawrence, L. S. P., Lau, A. Z., Sahgal, A., & Czarnota, G. J. (2026). Pixel-Wise Prediction of Glioblastoma Recurrence Using Mid-Treatment MRI and Deep Learning. Cancers, 18(21), 3465. https://doi.org/10.3390/cancers18213465

Vancouver

Rezvanjou S, Osapoetra LO, Moore-Palhares D, Lawrence LSP, Lau AZ, Sahgal A, et al. Pixel-Wise Prediction of Glioblastoma Recurrence Using Mid-Treatment MRI and Deep Learning. Cancers. 2026;18(21):3465. doi:10.3390/cancers18213465

BibTeX
@article{Rezvanjou2026,
  author = {Rezvanjou, Sara and Osapoetra, Laurentius Oscar and Moore-Palhares, Daniel and Lawrence, Liam S P and Lau, Angus Z and Sahgal, Arjun and Czarnota, Gregory J},
  title = {Pixel-Wise Prediction of Glioblastoma Recurrence Using Mid-Treatment MRI and Deep Learning},
  journal = {Cancers},
  year = {2026},
  volume = {18},
  number = {21},
  pages = {3465},
  doi = {10.3390/cancers18213465}
}
Kostenlos starten →