EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-based pathomics model predicts regulatory T cell infiltration and radiotherapy response in IDH-wild-type glioblastoma

Shaoli Peng, Jialei Chen, Xuezhen Wang, Xingfu Wang, Qiuyuan Yue, Hailin Lan, Jingru Zhang, Yuqi Xie, Meiyan Yang, Jiayu Xiao, Chenyan Guo, Yang Wang und 3 weitere

Frontiers in Immunology · 21.05.2026 · 17

DOI: 10.3389/fimmu.2026.1817892 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Immunology, online erschienen am 21.05.2026. Verfasst von Shaoli Peng und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiotherapy, Cancer Center, The First Affiliated Hospital of Fujian Medical University, Fuzhou, China. Hauptthemen laut MEDLINE: Glioblastoma, T-Lymphocytes, Regulatory, Brain Neoplasms, Artificial Intelligence. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Regulatory T cells (Tregs) contribute significantly to immune suppression and therapy resistance in isocitrate dehydrogenase (IDH)-wild-type glioblastoma (GBM), a highly aggressive brain tumor with poor prognosis.

Methods

In this study, we developed an artificial intelligence (AI)-powered pathomics model to predict Treg infiltration and stratify prognosis in GBM patients undergoing radiotherapy. Using high-dimensional features extracted from hematoxylin and eosin-stained biopsies, we constructed a pathomics score (PS) via gradient boosting after feature selection with Minimum Redundancy Maximum Relevance (mRMR) and Relief algorithms.

Results

The model demonstrated strong predictive performance across multi-center cohorts (n > 300), where high PS was significantly associated with elevated Treg levels and reduced overall survival (TCGA: HR = 2.16; validation cohort: HR = 1.706). Gene set enrichment analysis linked high PS to immune-evasive pathways, including Notch and IL-6/JAK/STAT3 signaling, along with increased expression of DNA repair gene RAD50, suggesting a potential association with radiotherapy response.

Conclusion

This AI-based pathomics framework offers a robust and interpretable tool for immunoprofiling and outcome prediction, paving the way for precision radiotherapy and Treg-targeted therapeutic strategies in glioblastoma.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GlioblastomaT-Lymphocytes, RegulatoryBrain NeoplasmsArtificial IntelligenceLymphocytes, Tumor-InfiltratingHumansIsocitrate DehydrogenaseTumor MicroenvironmentPrognosis

Stichwörter der Autor:innen

artificial intelligenceglioblastomaimmunotherapy biomarkersmachine learningpathomicsradiotherapy responseregulatory T celltumor microenvironment

Substanzen

Isocitrate Dehydrogenase

Autor:innen und Institutionen

  • Department of Radiotherapy, Cancer Center, The First Affiliated Hospital of Fujian Medical University, Fuzhou, China.
  • Key Laboratory of Radiation Biology of Fujian Higher Education Institutions, The First Affiliated Hospital, Fujian Medical University, Fuzhou, China.
  • Department of Pathology, The First Affiliated Hospital of Fujian Medical University, Fuzhou, China.
  • Department of Radiology, Fujian Cancer Hospital and Fujian Medical University Cancer Hospital, Fuzhou, China.
  • School of Medical Imaging, Fujian Medical University, Fuzhou, China.
  • School of Basic Medical Sciences, Fujian Medical University, Fuzhou, China.

Zitieren

APA

Peng, S., Chen, J., Wang, X., Wang, X., Yue, Q., Lan, H., Zhang, J., Xie, Y., Yang, M., Xiao, J., Guo, C., Wang, Y., Wu, Z., Hong, J., & Zhang, M. (2026). AI-based pathomics model predicts regulatory T cell infiltration and radiotherapy response in IDH-wild-type glioblastoma. Frontiers in Immunology, 17. https://doi.org/10.3389/fimmu.2026.1817892

Vancouver

Peng S, Chen J, Wang X, Wang X, Yue Q, Lan H, et al. AI-based pathomics model predicts regulatory T cell infiltration and radiotherapy response in IDH-wild-type glioblastoma. Frontiers in Immunology. 2026;17. doi:10.3389/fimmu.2026.1817892

BibTeX
@article{Peng2026,
  author = {Peng, Shaoli and Chen, Jialei and Wang, Xuezhen and Wang, Xingfu and Yue, Qiuyuan and Lan, Hailin and Zhang, Jingru and Xie, Yuqi and Yang, Meiyan and Xiao, Jiayu and Guo, Chenyan and Wang, Yang and Wu, Zanyi and Hong, Jinsheng and Zhang, Mingwei},
  title = {AI-based pathomics model predicts regulatory T cell infiltration and radiotherapy response in IDH-wild-type glioblastoma},
  journal = {Frontiers in Immunology},
  year = {2026},
  volume = {17},
  doi = {10.3389/fimmu.2026.1817892}
}
Kostenlos starten →