Multi-institutional Clinical Tool for Predicting High-risk Lesions on 3 Tesla Multiparametric Prostate Magnetic Resonance Imaging

Matthew Truong, Janet E. Baack Kukreja, Soroush Rais-Bahrami, Nimrod S. Barashi, Bokai Wang, Zachary Nuffer, Ji Hae Park, Khoa Lam, Thomas P. Frye, Jeffrey W. Nix, John V. Thomas, Changyong Feng, Brian F. Chapin, John W. Davis, Gary Hollenberg, Aytekin Oto, Scott E. Eggener, Jean V. Joseph, Eric Weinberg, Edward M. Messing

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Background: Multiparametric magnetic resonance imaging (mpMRI) for prostate cancer detection without careful patient selection may lead to excessive resource utilization and costs. Objective: To develop and validate a clinical tool for predicting the presence of high-risk lesions on mpMRI. Design, setting, and participants: Four tertiary care centers were included in this retrospective and prospective study (BiRCH Study Collaborative). Statistical models were generated using 1269 biopsy-naive, prior negative biopsy, and active surveillance patients who underwent mpMRI. Using age, prostate-specific antigen, and prostate volume, a support vector machine model was developed for predicting the probability of harboring Prostate Imaging Reporting and Data System 4 or 5 lesions. The accuracy of future predictions was then prospectively assessed in 214 consecutive patients. Outcome measurements and statistical analysis: Receiver operating characteristic, calibration, and decision curves were generated to assess model performance. Results and limitations: For biopsy-naïve and prior negative biopsy patients (n = 811), the area under the curve (AUC) was 0.730 on internal validation. Excellent calibration and high net clinical benefit were observed. On prospective external validation at two separate institutions (n = 88 and n = 126), the machine learning model discriminated with AUCs of 0.740 and 0.744, respectively. The final model was developed on the Microsoft Azure Machine Learning platform (birch.azurewebsites.net). This model requires a prostate volume measurement as input. Conclusions: In patients who are naïve to biopsy or those with a prior negative biopsy, BiRCH models can be used to select patients for mpMRI. Patient summary: In this multicenter study, we developed and prospectively validated a calculator that can be used to predict prostate magnetic resonance imaging (MRI) results using patient age, prostate-specific antigen, and prostate volume as input. This tool can aid health care professionals and patients to make an informed decision regarding whether to get an MRI. Previously, there were no clinical tools to predict Prostate Imaging Reporting and Data System 4–5 before magnetic resonance imaging (MRI). BiRCH models were developed to predict the MRI result using logistic regression and machine learning, and can be used to select patients for multiparametric MRI.

Original languageEnglish (US)
Pages (from-to)257-264
Number of pages8
JournalEuropean Urology Oncology
Volume2
Issue number3
DOIs
StatePublished - May 2019

Keywords

  • Early detection of cancer
  • Machine learning
  • Magnetic resonance imaging
  • Prostatic neoplasm

ASJC Scopus subject areas

  • Surgery
  • Oncology
  • Radiology Nuclear Medicine and imaging
  • Urology

Fingerprint

Dive into the research topics of 'Multi-institutional Clinical Tool for Predicting High-risk Lesions on 3 Tesla Multiparametric Prostate Magnetic Resonance Imaging'. Together they form a unique fingerprint.

Cite this