Computer-aided diagnosis prior to conventional interpretation of prostate mpMRI: an international multi-reader study
To evaluate if computer-aided diagnosis (CAD) prior to prostate multi-parametric MRI (mpMRI) can improve sensitivity and agreement between radiologists.
Nine radiologists (three each high, intermediate, low experience) from eight institutions participated. A total of 163 patients with 3-T mpMRI from 4/2012 to 6/2015 were included: 110 cancer patients with prostatectomy after mpMRI, 53 patients with no lesions on mpMRI and negative TRUS-guided biopsy. Readers were blinded to all outcomes and detected lesions per PI-RADSv2 on mpMRI. After 5 weeks, readers re-evaluated patients using CAD to detect lesions. Prostatectomy specimens registered to MRI were ground truth with index lesions defined on pathology. Sensitivity, specificity and agreement were calculated per patient, lesion level and zone—peripheral (PZ) and transition (TZ).
Index lesion sensitivity was 78.2% for mpMRI alone and 86.3% for CAD-assisted mpMRI (p = 0.013). Sensitivity was comparable for TZ lesions (78.7% vs 78.1%; p = 0.929); CAD improved PZ lesion sensitivity (84% vs 94%; p = 0.003). Improved sensitivity came from lesions scored PI-RADS < 3 as index lesion sensitivity was comparable at PI-RADS ≥ 3 (77.6% vs 78.1%; p = 0.859). Per patient specificity was 57.1% for CAD and 70.4% for mpMRI (p = 0.003). CAD improved agreement between all readers (56.9% vs 71.8%; p < 0.001).
CAD-assisted mpMRI improved sensitivity and agreement, but decreased specificity, between radiologists of varying experience.
• Computer-aided diagnosis (CAD) assists clinicians in detecting prostate cancer on MRI.
• CAD assistance improves agreement between radiologists in detecting prostate cancer lesions.
• However, this CAD system induces more false positives, particularly for less-experienced clinicians and in the transition zone.
• CAD assists radiologists in detecting cancer missed on MRI, suggesting a path for improved diagnostic confidence.
KeywordsProstate cancer MRI scans Image interpretation computer assisted Computer-assisted diagnosis
area under the curve
dynamic contrast-enhanced imaging
index of specific agreement
Prostate Imaging Reporting and Data System
Compliance with ethical standards
The scientific guarantor of this publication is Baris Turkbey, MD.
Conflict of interest
The authors of this manuscript declare relationships with the following companies: Bradford Wood, Philips and InVivo; Ronald Summers, Ping An and iCAD.
Statistics and biometry
One of the authors, Dr. Joanna Shih, has significant statistical expertise.
Institutional review board approval was obtained.
Written informed consent was obtained from all patients in this study.
Study subjects or cohorts overlap
Some study subjects or cohorts have been previously reported in Greer MD, Shih JH, Lay N, et al. Validation of the dominant sequence paradigm and role of dynamic contrast-enhanced imaging in PI-RADS Version 2. Radiology. 2017;285:859–869.
• diagnostic study
• multicentre study
- 1.Society AC (2016) Cancer facts & figures 2016. American Cancer Society, AtlantaGoogle Scholar
- 7.Schoots IG, Roobol MJ, Nieboer D, Bangma CH, Steyerberg EW, Hunink MG (2015) Magnetic resonance imaging-targeted biopsy may enhance the diagnostic accuracy of significant prostate cancer detection compared to standard transrectal ultrasound-guided biopsy: a systematic review and meta-analysis. Eur Urol 68:438–450CrossRefPubMedGoogle Scholar
- 8.Borkowetz A, Platzek I, Toma M et al (2016) Direct comparison of multiparametric MRI and final histopathology in patients with proven prostate cancer in MRI/ultrasound-fusion biopsy. BJU Int. https://doi.org/10.1111/bju.13461
- 10.Borofsky S, George AK, Gaur S et al (2017) What are we missing? False-negative cancers at multiparametric MR imaging of the prostate. Radiology. https://doi.org/10.1148/radiol.2017152877:152877
- 14.Liu L, Tian Z, Zhang Z, Fei B (2016) Computer-aided detection of prostate cancer with MRI: technology and applications. Acad Radiol. https://doi.org/10.1016/j.acra.2016.03.010
- 15.Litjens GJ, Elliott R, Shih NN et al (2015) Computer-extracted features can distinguish noncancerous confounding disease from prostatic adenocarcinoma at multiparametric MR imaging. Radiology. https://doi.org/10.1148/radiol.2015142856:142856
- 24.Medixant (2015) RadiAnt DICOM Viewer, 22.214.171.12428. http://www.radiantviewer.com/
- 25.Radiology ACo (2015) MR Prostate Imaging Reporting and Data System version 2.0.Google Scholar
- 28.Muller BG, Shih JH, Sankineni S et al (2015) Prostate cancer: interobserver agreement and accuracy with the revised Prostate Imaging Reporting and Data System at multiparametric MR imaging. Radiology. https://doi.org/10.1148/radiol.2015142818:142818
- 29.Rosenkrantz AB, Ginocchio LA, Cornfeld D et al (2016) Interobserver reproducibility of the PI-RADS Version 2 Lexicon: a multicenter study of six experienced prostate radiologists. Radiology. https://doi.org/10.1148/radiol.2016152542:152542
- 31.Hansen NL, Koo BC, Gallagher FA et al (2016) Comparison of initial and tertiary centre second opinion reads of multiparametric magnetic resonance imaging of the prostate prior to repeat biopsy. Eur Radiol. https://doi.org/10.1007/s00330-016-4635-5