MRI Habitat Imaging Predicts Meningioma Ki-67 Proliferation Index Across Four Centers

A multiparametric MRI habitat imaging model predicted Ki-67 proliferation index ≥5% in meningiomas with AUCs of 0.929 in training and 0.903–0.914 in two external validation sets, outperforming whole-tumor radiomics.

• Habitat-derived features, especially textural heterogeneity in the strongly enhancing subregion, comprised 9 of the 15 selected features.
• Across cohorts, sensitivities ranged 0.651–0.843, specificities 0.874–0.911, and standardized net benefit peaked at a threshold probability range of 15%–35%.

Evidence grade: 2

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.