Radiomic Machine Learning for Characterization of Prostate Lesions with MRI: Comparison to ADC Values.

Purpose To compare biparametric contrast-free radiomic machine learning (RML), mean apparent diffusion coefficient (ADC), and radiologist assessment for characterization of prostate lesions detected during prospective MRI interpretation. Materials and Methods This single-institution study included 316 men (mean age ± standard deviation, 64.0 years ± 7.8) with an indication for MRI-transrectal US fusion biopsy between May 2015 and September 2016 (training cohort, 183 patients; test cohort, 133 patients). Lesions identified by prospective clinical readings were manually segmented for mean ADC and radiomics analysis. Global and zone-specific random forest RML and mean ADC models for classification of clinically significant prostate cancer (Gleason grade group ≥ 2) were developed on the training set and the fixed models tested on an independent test set. Clinical readings, mean ADC, and radiomics were compared by using the McNemar test and receiver operating characteristic (ROC) analysis. Results In the test set, radiologist interpretation had a per-lesion sensitivity of 88% (53 of 60) and specificity of 50% (79 of 159). Quantitative measurement of the mean ADC (cut-off 732 mm2/sec) significantly reduced false-positive (FP) lesions from 80 to 60 (specificity 62% [99 of 159]) and false-negative (FN) lesions from seven to six (sensitivity 90% [54 of 60]) (P = .048). Radiologist interpretation had a per-patient sensitivity of 89% (40 of 45) and specificity of 43% (38 of 88). Quantitative measurement of the mean ADC reduced the number of patients with FP lesions from 50 to 43 (specificity 51% [45 of 88]) and the number of patients with FN lesions from five to three (sensitivity 93% [42 of 45]) (P = .496). Comparison of the area under the ROC curve (AUC) for the mean ADC (AUCglobal = 0.84; AUCzone-specific ≤ 0.87) vs the RML (AUCglobal = 0.88, P = .176; AUCzone-specific ≤ 0.89, P ≥ .493) showed no significantly different performance. Conclusion Quantitative measurement of the mean apparent diffusion coefficient (ADC) improved differentiation of benign versus malignant prostate lesions, compared with clinical assessment. Radiomic machine learning had comparable but not better performance than mean ADC assessment. © RSNA, 2018 Online supplemental material is available for this article.

[1]  Seung Hyup Kim,et al.  Diagnostic Performance of Prostate Imaging Reporting and Data System Version 2 for Detection of Prostate Cancer: A Systematic Review and Diagnostic Meta-analysis. , 2017, European urology.

[2]  Yousef Mazaheri,et al.  Prostate cancer aggressiveness: assessment with whole-lesion histogram analysis of the apparent diffusion coefficient. , 2014, Radiology.

[3]  Simone Schrading,et al.  Abbreviated Biparametric Prostate MR Imaging in Men with Elevated Prostate-specific Antigen. , 2017, Radiology.

[4]  Jin Tae Kwak,et al.  Prostate Cancer: A Correlative Study of Multiparametric MR Imaging and Digital Histopathology. , 2017, Radiology.

[5]  Mark McEntee,et al.  Changes in Epithelium, Stroma, and Lumen Space Correlate More Strongly with Gleason Pattern and Are Stronger Predictors of Prostate ADC Changes than Cellularity Metrics. , 2015, Radiology.

[6]  M. Stasi,et al.  Texture features on T2-weighted magnetic resonance imaging: new potential biomarkers for prostate cancer aggressiveness , 2015, Physics in medicine and biology.

[7]  A. Warren,et al.  Sub-differentiating equivocal PI-RADS-3 lesions in multiparametric magnetic resonance imaging of the prostate to improve cancer detection. , 2017, European journal of radiology.

[8]  Jing Wang,et al.  Machine learning-based analysis of MR radiomics can help to improve the diagnostic performance of PI-RADS v2 in clinically relevant prostate cancer , 2017, European Radiology.

[9]  Klaus H. Maier-Hein,et al.  The Medical Imaging Interaction Toolkit: challenges and advances , 2013, International Journal of Computer Assisted Radiology and Surgery.

[10]  H. G. van der Poel,et al.  What Is the Negative Predictive Value of Multiparametric Magnetic Resonance Imaging in Excluding Prostate Cancer at Biopsy? A Systematic Review and Meta-analysis from the European Association of Urology Prostate Cancer Guidelines Panel. , 2017, European urology.

[11]  H. Hricak,et al.  Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores , 2015, European Radiology.

[12]  J. Fütterer,et al.  ESUR prostate MR guidelines 2012 , 2012, European Radiology.

[13]  Pär Stattin,et al.  Evaluation of the 2015 Gleason Grade Groups in a Nationwide Population-based Cohort. , 2016, European urology.

[14]  M. Roethke,et al.  Improved detection of anterior fibromuscular stroma and transition zone prostate cancer using biparametric and multiparametric MRI with MRI-targeted biopsy and MRI-US fusion guidance , 2015, Prostate Cancer and Prostatic Disease.

[15]  Yousef Mazaheri,et al.  Prostate MRI: Evaluating Tumor Volume and Apparent Diffusion Coefficient as Surrogate Biomarkers for Predicting Tumor Gleason Score , 2014, Clinical Cancer Research.

[16]  A. Madabhushi,et al.  Radiomic features for prostate cancer detection on MRI differ between the transition and peripheral zones: Preliminary findings from a multi‐institutional study , 2017, Journal of magnetic resonance imaging : JMRI.

[17]  P. Lambin,et al.  Machine Learning methods for Quantitative Radiomic Biomarkers , 2015, Scientific Reports.

[18]  Baris Turkbey,et al.  Accuracy and agreement of PIRADSv2 for prostate cancer mpMRI: A multireader study , 2017, Journal of magnetic resonance imaging : JMRI.

[19]  M. Cooperberg,et al.  Trends in Management for Patients With Localized Prostate Cancer, 1990-2013. , 2015, JAMA.

[20]  H. Hricak,et al.  Updated prostate imaging reporting and data system (PIRADS v2) recommendations for the detection of clinically significant prostate cancer using multiparametric MRI: critical evaluation using whole-mount pathology as standard of reference , 2016, European Radiology.

[21]  F. Beuvon,et al.  Diffusion-weighted imaging of the prostate: should we use quantitative metrics to better characterize focal lesions originating in the peripheral zone? , 2018, European Radiology.

[22]  Joseph O. Deasy,et al.  Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images , 2015, Proceedings of the National Academy of Sciences.

[23]  M. Roethke,et al.  Multiparametric Magnetic Resonance Imaging (MRI) and MRI-Transrectal Ultrasound Fusion Biopsy for Index Tumor Detection: Correlation with Radical Prostatectomy Specimen. , 2016, European urology.

[24]  Masoom A. Haider,et al.  Automated prostate cancer detection via comprehensive multi-parametric magnetic resonance imaging texture feature models , 2015, BMC Medical Imaging.

[25]  James S. Babb,et al.  Proposed Adjustments to PI-RADS Version 2 Decision Rules: Impact on Prostate Cancer Detection. , 2017, Radiology.

[26]  Baris Turkbey,et al.  What Are We Missing? False-Negative Cancers at Multiparametric MR Imaging of the Prostate. , 2018, Radiology.

[27]  Tone F. Bathen,et al.  T2-weighted MRI-derived textural features reflect prostate cancer aggressiveness: preliminary results , 2017, European Radiology.

[28]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[29]  D. Margolis,et al.  PI-RADS Prostate Imaging - Reporting and Data System: 2015, Version 2. , 2016, European urology.