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

Sonia Gaur¹, Nathan Lay², Stephanie A Harmon^{1

3}, Sreya Doddakashi¹, Sherif Mehralivand^{1

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, Baris Turkbey¹

Affiliations

¹ Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
² Imaging Biomarkers and Computer-aided Diagnosis Lab, Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA.
³ Clinical Research Directorate/ Clinical Monitoring Research Program, Leidos Biomedical Research, Inc., Frederick National Laboratory for Cancer Research, Frederick, MD, USA.
⁴ Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
⁵ Department of Urology and Pediatric Urology, University Medical Center Mainz, Mainz, Germany.
⁶ Department of Urology, Acibadem University, Istanbul, Turkey.
⁷ Department of Radiology, University of Cambridge, Cambridge, UK.
⁸ Department of Radiology, University of Udine, Udine, Italy.
⁹ Department of Radiology, Acibadem University, Istanbul, Turkey.
¹⁰ Department of Radiology, University of Chicago, Chicago, IL, USA.
¹¹ Department of Radiology, Cleveland Clinic, Cleveland, OH, USA.
¹² Department of Pathology, University of Chicago, Chicago, IL, USA.
¹³ Department of Pathology, Cleveland Clinic, Cleveland, OH, USA.
¹⁴ Department of Pathology, Acibadem University, Istanbul, Turkey.
¹⁵ Department of Pathology, University of Udine, Udine, Italy.
¹⁶ Department of Pathology, University of Cambridge, Cambridge, UK.
¹⁷ Department of Radiology, Federal Fluminense University, Rio de Janeiro, Brazil.
¹⁸ Department of Radiology, Radboud University, Nijmegen, The Netherlands.
¹⁹ Department of Radiology, Duke University, Durham, NC, USA.
²⁰ Department of Radiology, Hacettepe University, Ankara, Turkey.
²¹ Department of Radiology, Singapore General Hospital, Singapore.
²² Weill Cornell Imaging, Cornell University, New York, NY, USA.
²³ Department of Radiology, Mansoura University, Mansoura, Egypt.
²⁴ UCSF Department of Radiology, University of California-San Francisco, San Francisco, CA, USA.
²⁵ Center for Interventional Oncology, Clinical Center, National Institutes of Health, Bethesda, MD, USA.
²⁶ Biometric Research Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.

PMID: 30333911
PMCID: PMC6173466
DOI: 10.18632/oncotarget.26100

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

Sonia Gaur et al. Oncotarget. 2018.

. 2018 Sep 18;9(73):33804-33817.

doi: 10.18632/oncotarget.26100.

Authors

Affiliations

¹ Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
² Imaging Biomarkers and Computer-aided Diagnosis Lab, Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA.
³ Clinical Research Directorate/ Clinical Monitoring Research Program, Leidos Biomedical Research, Inc., Frederick National Laboratory for Cancer Research, Frederick, MD, USA.
⁴ Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
⁵ Department of Urology and Pediatric Urology, University Medical Center Mainz, Mainz, Germany.
⁶ Department of Urology, Acibadem University, Istanbul, Turkey.
⁷ Department of Radiology, University of Cambridge, Cambridge, UK.
⁸ Department of Radiology, University of Udine, Udine, Italy.
⁹ Department of Radiology, Acibadem University, Istanbul, Turkey.
¹⁰ Department of Radiology, University of Chicago, Chicago, IL, USA.
¹¹ Department of Radiology, Cleveland Clinic, Cleveland, OH, USA.
¹² Department of Pathology, University of Chicago, Chicago, IL, USA.
¹³ Department of Pathology, Cleveland Clinic, Cleveland, OH, USA.
¹⁴ Department of Pathology, Acibadem University, Istanbul, Turkey.
¹⁵ Department of Pathology, University of Udine, Udine, Italy.
¹⁶ Department of Pathology, University of Cambridge, Cambridge, UK.
¹⁷ Department of Radiology, Federal Fluminense University, Rio de Janeiro, Brazil.
¹⁸ Department of Radiology, Radboud University, Nijmegen, The Netherlands.
¹⁹ Department of Radiology, Duke University, Durham, NC, USA.
²⁰ Department of Radiology, Hacettepe University, Ankara, Turkey.
²¹ Department of Radiology, Singapore General Hospital, Singapore.
²² Weill Cornell Imaging, Cornell University, New York, NY, USA.
²³ Department of Radiology, Mansoura University, Mansoura, Egypt.
²⁴ UCSF Department of Radiology, University of California-San Francisco, San Francisco, CA, USA.
²⁵ Center for Interventional Oncology, Clinical Center, National Institutes of Health, Bethesda, MD, USA.
²⁶ Biometric Research Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.

PMID: 30333911
PMCID: PMC6173466
DOI: 10.18632/oncotarget.26100

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.

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

PubMed Disclaimer

Conflict of interest statement

CONFLICTS OF INTEREST Dr. Ronald M. Summers: Patent royalties from iCAD & ScanMed, Research support from Ping An & NVidia, Software licenses to Philips & Ping An. Dr. Bradford J. Wood reports grants from NIH Intramural Research Program , during the conduct of the study; grants and non-financial support from CRADA with Philips, grants and non-financial support from CRADA with Celsion Corp, grants and non-financial support from CRADA with Siemens, grants and non-financial support from CRADA with Biocompatibles BTG, grants and non-financial support from CRADA with NVIDIA, grants and non-financial support from CRADA with Profound Medical, grants and non-financial support from CRADA with XAct Robotics, outside the submitted work; In addition, Dr. Wood has a patent Fusion Patents with royalties paid to NIH and to Dr. Wood by Philips, but this is unrelated to this work.

Figures

**Figure 1**
Index lesion sensitivity in WP, PZ, TZ for MRI-only **(A)** and CAD-assisted **(B)** reads. Sensitivities are plotted for all readers as well as by experience level at each PI-RADSv2 category threshold. PI-RADSv2 category ≥1 threshold used for all lesions detected on MRI and CAD, while PI-RADSv2 category ≥3 threshold used to represent all lesions considered cumulatively suspicious on MRI and CAD. WP = whole prostate, PZ = peripheral zone, TZ = transition zone.

**Figure 2. Benefit of CAD in TZ tumor identification**
CAD (top left) picked up a tumor (arrows) in the right apical anterior TZ, identified by more readers on MRI (T2W top right, ADC map bottom left, b-1500 bottom right) with CAD assistance. ND = not detected, D = detected; the tumor was found by 5 readers with CAD assistance versus 1 reader with mpMRI alone. Radical prostatectomy histopathology mapping revealed Gleason 4+5 prostatic adenocarcinoma within this lesion.

**Figure 3. Study design**
The large multi-institutional framework is shown starting with image acquisition and ending with image interpretation across multiple institutions and readers.

See this image and copyright information in PMC

References

1. Siddiqui MM, Rais-Bahrami S, Turkbey B, George AK, Rothwax J, Shakir N, Okoro C, Raskolnikov D, Parnes HL, Linehan WM, Merino MJ, Simon RM, Choyke PL, et al. Comparison of MR/ultrasound fusion-guided biopsy with ultrasound-guided biopsy for the diagnosis of prostate cancer. JAMA. 2015;313:390–7. doi: 10.1001/jama.2014.17942. - DOI - PMC - PubMed
1. Rais-Bahrami S, Siddiqui MM, Turkbey B, Stamatakis L, Logan J, Hoang AN, Walton-Diaz A, Vourganti S, Truong H, Kruecker J, Merino MJ, Wood BJ, Choyke PL, et al. Utility of multiparametric magnetic resonance imaging suspicion levels for detecting prostate cancer. J Urol. 2013;190:1721–7. doi: 10.1016/j.juro.2013.05.052. - DOI - PMC - PubMed
1. Kasivisvanathan V, Rannikko AS, Borghi M, Panebianco V, Mynderse LA, Vaarala MH, Briganti A, Budaus L, Hellawell G, Hindley RG, Roobol MJ, Eggener S, Ghei M, et al. MRI-Targeted or Standard Biopsy for Prostate-Cancer Diagnosis. N Engl J Med. 2018;378:1767–1777. doi: 10.1056/NEJMoa1801993. - DOI - PMC - PubMed
1. Mehralivand S, Shih JH, Rais-Bahrami S, Oto A, Bednarova S, Nix JW, Thomas JV, Gordetsky JB, Gaur S, Harmon SA, Siddiqui MM, Merino MJ, Parnes HL, et al. A Magnetic Resonance Imaging-Based Prediction Model for Prostate Biopsy Risk Stratification. JAMA Oncol. 2018;4:678–685. doi: 10.1001/jamaoncol.2017.5667. - DOI - PMC - PubMed
1. Weinreb JC, Barentsz JO, Choyke PL, Cornud F, Haider MA, Macura KJ, Margolis D, Schnall MD, Shtern F, Tempany CM, Thoeny HC, Verma S. PI-RADS Prostate Imaging - Reporting and Data System: 2015, Version 2. Eur Urol. 2016;69:16–40. doi: 10.1016/j.eururo.2015.08.052. - DOI - PMC - PubMed

Grants and funding

LinkOut - more resources

Full Text Sources
Other Literature Sources
- The Lens - Patent Citations Database
Research Materials
- NCI CPTC Antibody Characterization Program
Miscellaneous
- NCI CPTAC Assay Portal

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

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

Affiliations

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

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

References

Grants and funding

LinkOut - more resources

Full Text Sources

Other Literature Sources

Research Materials

Miscellaneous