T2 MRI radiomics model stratifies prostate cancer aggressiveness with AUC 0.84

A T2-weighted MRI radiomics random forest model distinguished ISUP ≥3 prostate cancer from lower grades with an AUC of 0.84 (95% CI 0.63–0.98), sensitivity 85.7%, and specificity 78.6% in a retrospective 112-lesion cohort.

• Model calibration improved after isotonic regression (expected calibration error reduced from 0.168 to 0.099).
• First-order and grey-level size zone matrix features were the dominant predictors.

Automated summary

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