Frontiers in Oncology (Jan 2023)

Pilot study for generating and assessing nomograms and decision curves analysis to predict clinically significant prostate cancer using only spatially registered multi-parametric MRI

  • Rulon Mayer,
  • Rulon Mayer,
  • Baris Turkbey,
  • Peter Choyke,
  • Charles B. Simone

DOI
https://doi.org/10.3389/fonc.2023.1066498
Journal volume & issue
Vol. 13

Abstract

Read online

BackgroundCurrent prostate cancer evaluation can be inaccurate and burdensome. To help non-invasive prostate tumor assessment, recent algorithms applied to spatially registered multi-parametric (SRMP) MRI extracted novel clinically relevant metrics, namely the tumor’s eccentricity (shape), signal-to-clutter ratio (SCR), and volume.PurposeConduct a pilot study to predict the risk of developing clinically significant prostate cancer using nomograms and employing Decision Curves Analysis (DCA) from the SRMP MRI-based features to help clinicians non-invasively manage prostate cancer.MethodsThis study retrospectively analyzed 25 prostate cancer patients. MP-MRI (T1, T2, diffusion, dynamic contrast-enhanced) were resized, translated, and stitched to form SRMP MRI. Target detection algorithm [adaptive cosine estimator (ACE)] applied to SRMP MRI determines tumor’s eccentricity, noise reduced SCR (by regularizing or eliminating principal components (PC) from the covariance matrix), and volume. Pathology assessed wholemount prostatectomy for Gleason score (GS). Tumors with GS >=4+3 (<=3+4) were judged as “Clinically Significant” (“Insignificant”). Logistic regression combined eccentricity, SCR, volume to generate probability distribution. Nomograms, DCA used all patients plus training (13 patients) and test (12 patients) sets. Area Under the Curves for (AUC) for Receiver Operator Curves (ROC) and p-values evaluated the performance.ResultsCombining eccentricity (0.45 ACE threshold), SCR (3, 4 PCs), SCR (regularized, modified regularization) with tumor volume (0.65 ACE threshold) improved AUC (>0.70) for ROC curves and p-values (<0.05) for logistic fit. DCA showed greater net benefit from model fit than univariate analysis, treating “all,” or “none.” Training/test sets achieved comparable AUC but with higher p-values.ConclusionsPerformance of nomograms and DCA based on metrics derived from SRMP-MRI in this pilot study were comparable to those using prostate serum antigen, age, and PI-RADS.

Keywords