Matthew D Greer1, Nathan Lay2, Joanna H Shih3, Tristan Barrett4, Leonardo Kayat Bittencourt5, Samuel Borofsky6, Ismail Kabakus7, Yan Mee Law8, Jamie Marko9, Haytham Shebel10, Francesca V Mertan1, Maria J Merino11, Bradford J Wood12, Peter A Pinto13, Ronald M Summers2, Peter L Choyke1, Baris Turkbey14. 1. Molecular Imaging Program, NCI, NIH, 10 Center Drive, Room B3B85, Bethesda, MD, 20892, USA. 2. Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA. 3. Biometric Research Program, NCI, NIH, Bethesda, MD, USA. 4. Department of Radiology, University of Cambridge School of Medicine, Cambridge, UK. 5. Universidade Federal Fluminense and CDPI Clinics/DASA, Rio de Janeiro, RJ, Brazil. 6. George Washington University Hospital, Washington, DC, USA. 7. Hacettepe University, Ankara, Turkey. 8. Singapore General Hospital, Singapore, Singapore. 9. Radiology and Imaging Sciences Department, Clinical Center, NIH, Bethesda, MD, USA. 10. Department of Radiology, Nephrology Center, Mansoura University, Mansoura, 35516, Egypt. 11. Laboratory of Pathology, NCI, NIH, Bethesda, MD, USA. 12. Center for Interventional Oncology, NCI and Radiology Imaging Sciences, Clinical Center, NIH, Bethesda, MD, USA. 13. Urologic Oncology Branch, NCI, NIH, Bethesda, MD, USA. 14. Molecular Imaging Program, NCI, NIH, 10 Center Drive, Room B3B85, Bethesda, MD, 20892, USA. turkbeyi@mail.nih.gov.
Abstract
OBJECTIVES: To evaluate if computer-aided diagnosis (CAD) prior to prostate multi-parametric MRI (mpMRI) can improve sensitivity and agreement between radiologists. METHODS: 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). RESULTS: 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). CONCLUSIONS: CAD-assisted mpMRI improved sensitivity and agreement, but decreased specificity, between radiologists of varying experience. KEY POINTS: • 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.
OBJECTIVES: To evaluate if computer-aided diagnosis (CAD) prior to prostate multi-parametric MRI (mpMRI) can improve sensitivity and agreement between radiologists. METHODS: 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 cancerpatients 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). RESULTS: 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). CONCLUSIONS: CAD-assisted mpMRI improved sensitivity and agreement, but decreased specificity, between radiologists of varying experience. KEY POINTS: • 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.
Authors: Nathan Lay; Yohannes Tsehay; Matthew D Greer; Baris Turkbey; Jin Tae Kwak; Peter L Choyke; Peter Pinto; Bradford J Wood; Ronald M Summers Journal: J Med Imaging (Bellingham) Date: 2017-06-12
Authors: M Minhaj Siddiqui; Soroush Rais-Bahrami; Baris Turkbey; Arvin K George; Jason Rothwax; Nabeel Shakir; Chinonyerem Okoro; Dima Raskolnikov; Howard L Parnes; W Marston Linehan; Maria J Merino; Richard M Simon; Peter L Choyke; Bradford J Wood; Peter A Pinto Journal: JAMA Date: 2015-01-27 Impact factor: 56.272
Authors: Xiaosong Meng; Andrew B Rosenkrantz; Neil Mendhiratta; Michael Fenstermaker; Richard Huang; James S Wysock; Marc A Bjurlin; Susan Marshall; Fang-Ming Deng; Ming Zhou; Jonathan Melamed; William C Huang; Herbert Lepor; Samir S Taneja Journal: Eur Urol Date: 2015-06-22 Impact factor: 20.096
Authors: Berrend G Muller; Joanna H Shih; Sandeep Sankineni; Jamie Marko; Soroush Rais-Bahrami; Arvin Koruthu George; Jean J M C H de la Rosette; Maria J Merino; Bradford J Wood; Peter Pinto; Peter L Choyke; Baris Turkbey Journal: Radiology Date: 2015-06-18 Impact factor: 11.105
Authors: Ivo G Schoots; Monique J Roobol; Daan Nieboer; Chris H Bangma; Ewout W Steyerberg; M G Myriam Hunink Journal: Eur Urol Date: 2014-12-03 Impact factor: 20.096
Authors: Angelika Borkowetz; Ivan Platzek; Marieta Toma; Theresa Renner; Roman Herout; Martin Baunacke; Michael Laniado; Gustavo Baretton; Michael Froehner; Stefan Zastrow; Manfred Wirth Journal: BJU Int Date: 2016-04-02 Impact factor: 5.588
Authors: Samuel G Armato; Henkjan Huisman; Karen Drukker; Lubomir Hadjiiski; Justin S Kirby; Nicholas Petrick; George Redmond; Maryellen L Giger; Kenny Cha; Artem Mamonov; Jayashree Kalpathy-Cramer; Keyvan Farahani Journal: J Med Imaging (Bellingham) Date: 2018-11-10
Authors: Yohan Sumathipala; Nathan Lay; Baris Turkbey; Clayton Smith; Peter L Choyke; Ronald M Summers Journal: J Med Imaging (Bellingham) Date: 2018-12-15
Authors: Matthew D Greer; Joanna H Shih; Nathan Lay; Tristan Barrett; Leonardo Bittencourt; Samuel Borofsky; Ismail Kabakus; Yan Mee Law; Jamie Marko; Haytham Shebel; Maria J Merino; Bradford J Wood; Peter A Pinto; Ronald M Summers; Peter L Choyke; Baris Turkbey Journal: AJR Am J Roentgenol Date: 2019-03-27 Impact factor: 3.959
Authors: Armando Stabile; Francesco Giganti; Veeru Kasivisvanathan; Gianluca Giannarini; Caroline M Moore; Anwar R Padhani; Valeria Panebianco; Andrew B Rosenkrantz; Georg Salomon; Baris Turkbey; Geert Villeirs; Jelle O Barentsz Journal: Eur Urol Oncol Date: 2020-03-17