EUVIMEDEUVIMED entdecken
Open Access

Patient-Specific Computational Framework to Spatiotemporally Forecast Treatment Response and Identify Biologically Informed Radiotherapy Targets in High-Grade Glioma

Sophia Ty iD, Jeanne Kowalski iD, Bikash Panthi, Maguy Farhat, Holly Langshaw, Mihir D Shanker iD, Wasif Talpur, Sara Thrower iD, Jodi Goldman, Calliope Custer, Thomas E Yankeelov iD, Caroline Chung iD und 1 weitere

JCO Clinical Cancer Informatics · 2026

DOI: 10.1200/cci-25-00336 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2026. Verfasst von Sophia Ty und 12 weiteren Autor:innen. Beteiligte Einrichtung: Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, TX. Hauptthemen laut MEDLINE: Glioma, Brain Neoplasms, Radiotherapy Planning, Computer-Assisted. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

High-grade gliomas exhibit substantial spatial and temporal heterogeneity, posing a challenge for radiotherapy (RT) target definition. Adaptive RT, which prospectively modifies treatment plans, may benefit from early identification of intratumoral regions likely to exhibit differential treatment response. Apparent diffusion coefficient ( ADC ), a marker associated with tumor cellularity and aggressiveness, is a promising imaging biomarker of RT response. We present a patient-specific computational framework that predicts treatment response and identifies candidate adaptive RT targets from anticipated spatiotemporal patterns of ADC changes (Δ ADC ).

Methods

Using longitudinal multiparametric magnetic resonance imaging (MRI) from 21 patients, the mathematical model was calibrated to spatiotemporally forecast tumor cell density immediately after and 1-month post-RT. Predictions of tumor cell density were converted to ADC maps. Δ ADC from baseline was analyzed using Pareto tail analysis. The lower Δ ADC distribution tail was used to classify tumor voxels as regions of increased diffusion restriction (IDR) or decreased/maintained diffusion restriction (DMDR). We compared agreement in categories between measured and predicted Δ ADC from MRI data. Classification performance was assessed using receiver operating characteristic (ROC) analysis across four scenarios combining two time points and two image inclusion strategies (± nonenhancing tumor volume).

Results

The framework achieved a median ROC AUC of 0.88 (0.80-0.93), indicating strong performance in distinguishing IDR from DMDR regions. No significant differences were observed between forecasting time points ( P value: .08) or image inclusion strategies ( P value: .50).

Conclusion

This framework can delineate IDR and DMDR regions, offering a potential strategy for prospectively defining candidate biologically informed adaptive RT targets. Future studies are needed to evaluate their role in adaptive RT planning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GliomaBrain NeoplasmsRadiotherapy Planning, Computer-AssistedHumansFemaleNeoplasm GradingMaleTreatment OutcomeMiddle AgedMagnetic Resonance ImagingDiffusion Magnetic Resonance ImagingAdult

Autor:innen und Institutionen

  • Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, TX.
  • UT Austin Cancer Research Institute, The University of Texas at Austin, Austin, TX.
  • Department of Medicine, The University of Texas at Austin, Austin, TX.
  • Department of Radiation Oncology, The M.D. Anderson Cancer Center, Houston, TX.
  • Faculty of Medicine, The University of Queensland, Brisbane, Queensland, Australia.
  • Department of Population Health, The University of Texas at Austin, Austin, TX.

ORCID-Profile: Sophia Ty, Jeanne Kowalski, Mihir D Shanker, Sara Thrower, Thomas E Yankeelov, Caroline Chung, David A Hormuth

Förderung

  • NCI NIH HHS

Zitieren

APA

Ty, S., Kowalski, J., Panthi, B., Farhat, M., Langshaw, H., Shanker, M. D., Talpur, W., Thrower, S., Goldman, J., Custer, C., Yankeelov, T. E., Chung, C., & Hormuth, D. A. (2026). Patient-Specific Computational Framework to Spatiotemporally Forecast Treatment Response and Identify Biologically Informed Radiotherapy Targets in High-Grade Glioma. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-25-00336

Vancouver

Ty S, Kowalski J, Panthi B, Farhat M, Langshaw H, Shanker MD, et al. Patient-Specific Computational Framework to Spatiotemporally Forecast Treatment Response and Identify Biologically Informed Radiotherapy Targets in High-Grade Glioma. JCO Clinical Cancer Informatics. 2026. doi:10.1200/cci-25-00336

BibTeX
@article{Ty2026,
  author = {Ty, Sophia and Kowalski, Jeanne and Panthi, Bikash and Farhat, Maguy and Langshaw, Holly and Shanker, Mihir D and Talpur, Wasif and Thrower, Sara and Goldman, Jodi and Custer, Calliope and Yankeelov, Thomas E and Chung, Caroline and Hormuth, David A},
  title = {Patient-Specific Computational Framework to Spatiotemporally Forecast Treatment Response and Identify Biologically Informed Radiotherapy Targets in High-Grade Glioma},
  journal = {JCO Clinical Cancer Informatics},
  year = {2026},
  doi = {10.1200/cci-25-00336}
}
Kostenlos starten →