Explainable incremental-value analysis of apparent diffusion coefficient and arterial spin labeling radiomics for ATRX status prediction in glioblastoma - Takeaways - MDSpire

Explainable incremental-value analysis of apparent diffusion coefficient and arterial spin labeling radiomics for ATRX status prediction in glioblastoma

  • By

  • Rafail C. Christodoulou

  • Revati Natu

  • Georgios Vamvouras

  • Platon S. Papageorgiou

  • Evros Vassiliou

  • Elena E. Solomou

  • Sokratis G. Papageorgiou

  • Michalis F. Georgiou

  • June 19, 2026

  • 0 min

Share

  • 1

    ATRX mutation is a significant molecular feature in glioblastoma, linked to tumor heterogeneity and treatment-relevant biology.

  • 2

    The study analyzed 106 GBM patients to compare four radiomics models for predicting ATRX status using multiparametric MRI.

  • 3

    Model 1A, which included ADC and ASL-CBF features, showed statistically significant improvements in predicting ATRX status.

  • 4

    The best-performing model achieved an ROC-AUC of 0.753 and a sensitivity of 0.947, indicating improved discrimination.

  • 5

    Findings suggest that ADC and ASL-CBF radiomics provide modest incremental value for ATRX prediction in glioblastoma.

Original Source(s)

Explainable incremental-value analysis of apparent diffusion coefficient and arterial spin labeling radiomics for ATRX status prediction in glioblastoma

  • by Rafail C. Christodoulou, Revati Natu, Georgios Vamvouras, Platon S. Papageorgiou, Evros Vassiliou, Elena E. Solomou, Sokratis G. Papageorgiou, Michalis F. Georgiou

  • June 19, 2026

Related Content

A Case Report of follicular dendritic cell sarcoma

Radiomics and deep learning in upper tract urothelial carcinoma: advancing preoperative risk stratification and clinical decision-making

Beyond Visual Consensus: Tiered Reference Framework for AI Cystoscopy Studies