Objective:

To determine whether radiomic features extracted from the peritumoral zone capture biologically relevant invasion-associated imaging phenotypes, using membrane-bound Hsp70 (mHsp70) as a molecular correlate.

Approach:

Key Findings:

• The SVM classifier achieved an AUC of 0.875 in the independent test cohort.
• Higher-order texture features were identified as major contributors to model predictions.
• The radiomics-derived Invasion Burden Index (IBI) showed a significant positive correlation with mHsp70 expression (Spearman ρ = 0.67, p = 0.0004).
• Regions with elevated invasion-associated radiomic signatures often extended beyond conventional MRI-defined tumor margins.

Interpretation:

Voxel-wise radiomic analysis identifies invasion-associated imaging phenotypes that correlate with membrane Hsp70 expression, a biological marker associated with aggressive tumor behavior.

Limitations:

• The study is retrospective and may be subject to biases inherent in such designs.
• Further prospective studies with spatially matched biological validation are needed.

Conclusion:

Radiomic invasion mapping may serve as a non-invasive tool for characterizing infiltrative glioma biology.

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.