Objective:

To evaluate the incremental value of physiologic MRI features (ADC and ASL-CBF) in predicting ATRX status in glioblastoma beyond conventional structural MRI.

Approach:

Key Findings:

• The best structural model achieved an ROC-AUC of 0.721, a PR-AUC of 0.322, and a sensitivity of 0.737.
• Model 1A (including ADC and ASL-CBF) improved prediction with an ROC-AUC of 0.753, a PR-AUC of 0.364, and a sensitivity of 0.947.
• ADC and ASL features improved discrimination in five of six classifiers.

Interpretation:

ADC and ASL-CBF radiomics provide a modest but statistically significant incremental value for predicting ATRX status in glioblastoma.

Limitations:

• The study is limited to a specific patient cohort and may not generalize to all glioblastoma cases, potentially affecting the applicability of the findings.
• The reliance on machine learning models may introduce variability based on the selected algorithms and parameters.

Conclusion:

Further validation of functional MRI sequences as complementary radiogenomic markers for ATRX status in glioblastoma is needed.

Attribution Notice

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.