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

Authors

Matthew Truong, Department of Urology, University of Rochester Medical Center, Rochester, NY, USA.
Janet E. Baack Kukreja, Department of Urology, University of Texas MD Anderson Cancer Center, Houston, TX, USA.
Soroush Rais-Bahrami, Department of Urology, University of Alabama at Birmingham, Birmingham, AL, USA; Department of Radiology, University of Alabama at Birmingham, Birmingham, AL, USA.
Nimrod S. Barashi, Department of Urology, University of Chicago Medical Center, Chicago, IL, USA.
Bokai Wang, Department of Biostatistics and Computational Biology, University of Rochester School of Medicine and Dentistry, Rochester, NY, USA.
Zachary Nuffer, Department of Radiology and Imaging Sciences, University of Rochester Medical Center, Rochester, NY, USA.
Ji Hae Park, Department of Urology, University of Rochester Medical Center, Rochester, NY, USA.
Khoa Lam, Rochester Regional HealthFollow
Thomas P. Frye, Department of Urology, University of Rochester Medical Center, Rochester, NY, USA.
Jeffrey W. Nix, Department of Urology, University of Alabama at Birmingham, Birmingham, AL, USA.
John V. Thomas, Department of Radiology, University of Alabama at Birmingham, Birmingham, AL, USA.
Changyong Feng, Department of Biostatistics and Computational Biology, University of Rochester School of Medicine and Dentistry, Rochester, NY, USA.
Brian F. Chapin, Department of Urology, University of Texas MD Anderson Cancer Center, Houston, TX, USA.
John W. Davis, Department of Urology, University of Texas MD Anderson Cancer Center, Houston, TX, USA.
Gary Hollenberg, Department of Radiology and Imaging Sciences, University of Rochester Medical Center, Rochester, NY, USA.
Aytekin Oto, Department of Radiology, University of Chicago Medical Center, Chicago, IL, USA.
Scott E. Eggener, Department of Urology, University of Chicago Medical Center, Chicago, IL, USA.
Jean V. Joseph, Department of Urology, University of Rochester Medical Center, Rochester, NY, USA.
Eric Weinberg, Department of Radiology and Imaging Sciences, University of Rochester Medical Center, Rochester, NY, USA.
Edward M. Messing, Department of Urology, University of Rochester Medical Center, Rochester, NY, USA.

Department

Radiology

Document Type

Article

Publication Title

European Urology Oncology

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.

First Page

257

Last Page

264

DOI

10.1016/j.euo.2018.08.008

Volume

2

Issue

3

Publication Date

5-1-2019

Medical Subject Headings

Aged; Biopsy; Decision Support Techniques; Humans; Kallikreins (blood); Male; Middle Aged; Multiparametric Magnetic Resonance Imaging; Patient Selection; Prospective Studies; Prostate (blood supply, diagnostic imaging, pathology); Prostate-Specific Antigen (blood); Prostatic Neoplasms (blood, diagnostic imaging, pathology); Retrospective Studies; Risk Factors; Support Vector Machine; Unnecessary Procedures

PubMed ID

31200839

Recommended Citation

Truong, M., Baack Kukreja, J. E., Rais-Bahrami, S., Barashi, N. S., Wang, B., Nuffer, Z., Park, J. H., Lam, K., Frye, T. P., Nix, J. W., Thomas, J. V., Feng, C., Chapin, B. F., Davis, J. W., Hollenberg, G., Oto, A., Eggener, S. E., Joseph, J. V., Weinberg, E., & Messing, E. M. (2019). Multi-institutional Clinical Tool for Predicting High-risk Lesions on 3Tesla Multiparametric Prostate Magnetic Resonance Imaging. European Urology Oncology, 2 (3), 257-264. https://doi.org/10.1016/j.euo.2018.08.008