Oncotarget

Research Papers:

Can computer-aided diagnosis assist in the identification of prostate cancer on prostate MRI? a multi-center, multi-reader investigation

Sonia Gaur, Nathan Lay, Stephanie A. Harmon, Sreya Doddakashi, Sherif Mehralivand, Burak Argun, Tristan Barrett, Sandra Bednarova, Rossanno Girometti, Ercan Karaarslan, Ali Riza Kural, Aytekin Oto, Andrei S. Purysko, Tatjana Antic, Cristina Magi-Galluzzi, Yesim Saglican, Stefano Sioletic, Anne Y. Warren, Leonardo Bittencourt, Jurgen J. Fütterer, Rajan T. Gupta, Ismail Kabakus, Yan Mee Law, Daniel J. Margolis, Haytham Shebel, Antonio C. Westphalen, Bradford J. Wood, Peter A. Pinto, Joanna H. Shih, Peter L. Choyke, Ronald M. Summers and Baris Turkbey _

PDF  |  HTML  |  Supplementary Files  |  How to cite  |  Press Release

Oncotarget. 2018; 9:33804-33817. https://doi.org/10.18632/oncotarget.26100

Metrics: PDF 2321 views  |   HTML 3723 views  |   ?  


Abstract

Sonia Gaur1, Nathan Lay2, Stephanie A. Harmon1,3, Sreya Doddakashi1, Sherif Mehralivand1,4,5, Burak Argun6, Tristan Barrett7, Sandra Bednarova8, Rossanno Girometti8, Ercan Karaarslan9, Ali Riza Kural6, Aytekin Oto10, Andrei S. Purysko11, Tatjana Antic12, Cristina Magi-Galluzzi13, Yesim Saglican14, Stefano Sioletic15, Anne Y. Warren16, Leonardo Bittencourt17, Jurgen J. Fütterer18, Rajan T. Gupta19, Ismail Kabakus20, Yan Mee Law21, Daniel J. Margolis22, Haytham Shebel23, Antonio C. Westphalen24, Bradford J. Wood25, Peter A. Pinto4, Joanna H. Shih26, Peter L. Choyke1, Ronald M. Summers2 and Baris Turkbey1

1Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA

2Imaging Biomarkers and Computer-aided Diagnosis Lab, Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA

3Clinical Research Directorate/ Clinical Monitoring Research Program, Leidos Biomedical Research, Inc., Frederick National Laboratory for Cancer Research, Frederick, MD, USA

4Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA

5Department of Urology and Pediatric Urology, University Medical Center Mainz, Mainz, Germany

6Department of Urology, Acibadem University, Istanbul, Turkey

7Department of Radiology, University of Cambridge, Cambridge, UK

8Department of Radiology, University of Udine, Udine, Italy

9Department of Radiology, Acibadem University, Istanbul, Turkey

10Department of Radiology, University of Chicago, Chicago, IL, USA

11Department of Radiology, Cleveland Clinic, Cleveland, OH, USA

12Department of Pathology, University of Chicago, Chicago, IL, USA

13Department of Pathology, Cleveland Clinic, Cleveland, OH, USA

14Department of Pathology, Acibadem University, Istanbul, Turkey

15Department of Pathology, University of Udine, Udine, Italy

16Department of Pathology, University of Cambridge, Cambridge, UK

17Department of Radiology, Federal Fluminense University, Rio de Janeiro, Brazil

18Department of Radiology, Radboud University, Nijmegen, The Netherlands

19Department of Radiology, Duke University, Durham, NC, USA

20Department of Radiology, Hacettepe University, Ankara, Turkey

21Department of Radiology, Singapore General Hospital, Singapore

22Weill Cornell Imaging, Cornell University, New York, NY, USA

23Department of Radiology, Mansoura University, Mansoura, Egypt

24UCSF Department of Radiology, University of California-San Francisco, San Francisco, CA, USA

25Center for Interventional Oncology, Clinical Center, National Institutes of Health, Bethesda, MD, USA

26Biometric Research Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA

Correspondence to:

Baris Turkbey, email: [email protected]

Keywords: computer-aided diagnosis; prostate cancer; multiparametric MRI; PI-RADSv2; tumor detection

Received: May 28, 2018     Accepted: August 23, 2018     Published: September 18, 2018

ABSTRACT

For prostate cancer detection on prostate multiparametric MRI (mpMRI), the Prostate Imaging-Reporting and Data System version 2 (PI-RADSv2) and computer-aided diagnosis (CAD) systems aim to widely improve standardization across radiologists and centers. Our goal was to evaluate CAD assistance in prostate cancer detection compared with conventional mpMRI interpretation in a diverse dataset acquired from five institutions tested by nine readers of varying experience levels, in total representing 14 globally spread institutions.

Index lesion sensitivities of mpMRI-alone were 79% (whole prostate (WP)), 84% (peripheral zone (PZ)), 71% (transition zone (TZ)), similar to CAD at 76% (WP, p=0.39), 77% (PZ, p=0.07), 79% (TZ, p=0.15). Greatest CAD benefit was in TZ for moderately-experienced readers at PI-RADSv2 <3 (84% vs mpMRI-alone 67%, p=0.055). Detection agreement was unchanged but CAD-assisted read times improved (4.6 vs 3.4 minutes, p<0.001). At PI-RADSv2 ≥ 3, CAD improved patient-level specificity (72%) compared to mpMRI-alone (45%, p<0.001).

PI-RADSv2 and CAD-assisted mpMRI interpretations have similar sensitivities across multiple sites and readers while CAD has potential to improve specificity and moderately-experienced radiologists’ detection of more difficult tumors in the center of the gland. The multi-institutional evidence provided is essential to future prostate MRI and CAD development.


Creative Commons License All site content, except where otherwise noted, is licensed under a Creative Commons Attribution 4.0 License.
PII: 26100