Christopher S Lim1, Jorge Abreu-Gomez2,3, Rebecca Thornhill4, Nick James5, Ahmed Al Kindi6, Andrew S Lim7, Nicola Schieda4. 1. Department of Medical Imaging, Sunnybrook Health Sciences Centre, University of Toronto, 2075 Bayview Avenue, Rm AB 279, Toronto, ON, M4N 3M5, Canada. cs.lim@utoronto.ca. 2. Department of Medical Imaging, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, ON, Canada. 3. Department of Medical Imaging, Joint Department of Medical Imaging, University of Toronto, 585 University Avenue PMB-298, Toronto, ON, M5G2N2, Canada. 4. Department of Medical Imaging, The Ottawa Hospital, The University of Ottawa, 1053 Carling Ave, Civic Campus C1, Ottawa, ON, K1Y 4E9, Canada. 5. Software Solutions, The Ottawa Hospital, Ottawa, Canada. 6. Department of Medical Imaging, Sunnybrook Health Sciences Centre, University of Toronto, 2075 Bayview Avenue, Rm AB 279, Toronto, ON, M4N 3M5, Canada. 7. Department of Radiation Oncology, Seattle Cancer Care Alliance, University of Washington, 825 Eastlake Ave. E, Seattle Washington, 98109-1023, USA.
Abstract
PURPOSE: To evaluate if machine learning (ML) of radiomic features extracted from apparent diffusion coefficient (ADC) and T2-weighted (T2W) MRI can predict prostate cancer (PCa) diagnosis in Prostate Imaging-Reporting and Data System (PI-RADS) version 2.1 category 3 lesions. METHODS: This multi-institutional review board-approved retrospective case-control study evaluated 158 men with 160 PI-RADS category 3 lesions (79 peripheral zone, 81 transition zone) diagnosed at 3-Tesla MRI with histopathology diagnosis by MRI-TRUS-guided targeted biopsy. A blinded radiologist confirmed PI-RADS v2.1 score and segmented lesions on axial T2W and ADC images using 3D Slicer, extracting radiomic features with an open-source software (Pyradiomics). Diagnostic accuracy for (1) any PCa and (2) clinically significant (CS; International Society of Urogenital Pathology Grade Group ≥ 2) PCa was assessed using XGBoost with tenfold cross -validation. RESULTS: From 160 PI-RADS 3 lesions, there were 50.0% (80/160) PCa, including 36.3% (29/80) CS-PCa (63.8% [51/80] ISUP 1, 23.8% [19/80] ISUP 2, 8.8% [7/80] ISUP 3, 3.8% [3/80] ISUP 4). The remaining 50.0% (80/160) lesions were benign. ML of all radiomic features from T2W and ADC achieved area under receiver operating characteristic curve (AUC) for diagnosis of (1) CS-PCa 0.547 (95% Confidence Intervals 0.510-0.584) for T2W and 0.684 (CI 0.652-0.715) for ADC and (2) any PCa 0.608 (CI 0.579-0.636) for T2W and 0.642 (CI 0.614-0.0.670) for ADC. CONCLUSION: Our results indicate ML of radiomic features extracted from T2W and ADC achieved at best moderate accuracy for determining which PI-RADS category 3 lesions represent PCa.
PURPOSE: To evaluate if machine learning (ML) of radiomic features extracted from apparent diffusion coefficient (ADC) and T2-weighted (T2W) MRI can predict prostate cancer (PCa) diagnosis in Prostate Imaging-Reporting and Data System (PI-RADS) version 2.1 category 3 lesions. METHODS: This multi-institutional review board-approved retrospective case-control study evaluated 158 men with 160 PI-RADS category 3 lesions (79 peripheral zone, 81 transition zone) diagnosed at 3-Tesla MRI with histopathology diagnosis by MRI-TRUS-guided targeted biopsy. A blinded radiologist confirmed PI-RADS v2.1 score and segmented lesions on axial T2W and ADC images using 3D Slicer, extracting radiomic features with an open-source software (Pyradiomics). Diagnostic accuracy for (1) any PCa and (2) clinically significant (CS; International Society of Urogenital Pathology Grade Group ≥ 2) PCa was assessed using XGBoost with tenfold cross -validation. RESULTS: From 160 PI-RADS 3 lesions, there were 50.0% (80/160) PCa, including 36.3% (29/80) CS-PCa (63.8% [51/80] ISUP 1, 23.8% [19/80] ISUP 2, 8.8% [7/80] ISUP 3, 3.8% [3/80] ISUP 4). The remaining 50.0% (80/160) lesions were benign. ML of all radiomic features from T2W and ADC achieved area under receiver operating characteristic curve (AUC) for diagnosis of (1) CS-PCa 0.547 (95% Confidence Intervals 0.510-0.584) for T2W and 0.684 (CI 0.652-0.715) for ADC and (2) any PCa 0.608 (CI 0.579-0.636) for T2W and 0.642 (CI 0.614-0.0.670) for ADC. CONCLUSION: Our results indicate ML of radiomic features extracted from T2W and ADC achieved at best moderate accuracy for determining which PI-RADS category 3 lesions represent PCa.
Authors: Stefanie J Hectors; Christine Chen; Johnson Chen; Jade Wang; Sharon Gordon; Miko Yu; Bashir Al Hussein Al Awamlh; Mert R Sabuncu; Daniel J A Margolis; Jim C Hu Journal: J Magn Reson Imaging Date: 2021-05-10 Impact factor: 4.813
Authors: Faraz Ahmad; Lee Treanor; Trevor A McGrath; Daniel Walker; Matthew D F McInnes; Nicola Schieda Journal: J Magn Reson Imaging Date: 2020-10-24 Impact factor: 4.813