Radiomics Features Measured with Multiparametric Magnetic Resonance Imaging Predict Prostate Cancer Aggressiveness

No AccessJournal of UrologyAdult Urology1 Sep 2019Radiomics Features Measured with Multiparametric Magnetic Resonance Imaging Predict Prostate Cancer AggressivenessThis article is commented on by the following:Editorial CommentEditorial Comment Stefanie J. Hectors, Mathew Cherny, Kamlesh K. Yadav, Alp Tuna Beksaç, Hari Thulasidass, Sara Lewis, Elai Davicioni, Pei Wang, Ashutosh K. Tewari, and Bachir Taouli Stefanie J. HectorsStefanie J. Hectors Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York Departments of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author , Mathew ChernyMathew Cherny Departments of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author , Kamlesh K. YadavKamlesh K. Yadav Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York SEMA4, A Mount Sinai Venture, Stamford, Connecticut More articles by this author , Alp Tuna BeksaçAlp Tuna Beksaç Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author , Hari ThulasidassHari Thulasidass Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author , Sara LewisSara Lewis Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York Departments of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author , Elai DavicioniElai Davicioni GenomeDx Biosciences Inc., Vancouver, British Columbia, Canada Financial interest and/or other relationship with GenomeDx Biosciences. More articles by this author , Pei WangPei Wang Genetics and Genomics Sciences, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author , Ashutosh K. TewariAshutosh K. Tewari ‡Correspondence: Department of Urology, Icahn School of Medicine at Mount Sinai, 1425 Madison Ave., New York, New York 10029 telephone: 212-876-3246; E-mail Address: [email protected] Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York Equal study contribution. More articles by this author , and Bachir TaouliBachir Taouli ‡Correspondence: Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai, 1470 Madison Ave., New York, New York 10029 telephone: 212-824-8453; E-mail Address: [email protected] Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York Departments of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York Equal study contribution. More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000000272AboutFull TextPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract Purpose: We sought to 1) assess the association of radiomics features based on multiparametric magnetic resonance imaging with histopathological Gleason score, gene signatures and gene expression levels in prostate cancer and 2) build machine learning models based on radiomics features to predict adverse histopathological scores and the Decipher® genomics metastasis risk score. Materials and Methods: We retrospectively analyzed the records of 64 patients with prostate cancer with a mean age of 64 years (range 41 to 76) who underwent magnetic resonance imaging between January 2016 and January 2017 before radical prostatectomy. A total of 226 magnetic resonance imaging radiomics features, including histogram and texture features in addition to lesion size and the PI-RADS™ (Prostate Imaging Reporting and Data System) score, were extracted from T2-weighted, apparent diffusion coefficient and diffusion kurtosis imaging maps. Radiomics features were correlated with the pathological Gleason score, 40 gene expression signatures, including Decipher, and 698 prostate cancer related gene expression levels. Cross-validated, lasso regularized, logistic regression machine learning models based on radiomics features were built and evaluated for the prediction of Gleason score 8 or greater and Decipher score 0.6 or greater. Results: A total of 14 radiomics features significantly correlated with the Gleason score (highest correlation r = 0.39, p = 0.001). A total of 31 texture and histogram features significantly correlated with 19 gene signatures, particularly with the PORTOS (Post-Operative Radiation Therapy Outcomes Score) signature (strongest correlation r = –0.481, p = 0.002). A total of 40 diffusion-weighted imaging features correlated significantly with 132 gene expression levels. Machine learning prediction models showed fair performance to predict a Gleason score of 8 or greater (AUC 0.72) and excellent performance to predict a Decipher score of 0.6 or greater (AUC 0.84). Conclusions: Magnetic resonance imaging radiomics features are promising markers of prostate cancer aggressiveness on the histopathological and genomics levels. References 1. : The complexity of prostate cancer: genomic alterations and heterogeneity. Nat Rev Urol 2012; 9: 652. Google Scholar 2. : Overdiagnosis and overtreatment of prostate cancer. Eur Urol 2014; 65: 1046. Google Scholar 3. : Prostate MRI: evaluating tumor volume and apparent diffusion coefficient as surrogate biomarkers for predicting tumor Gleason score. Clin Cancer Res 2014; 20: 3705. Google Scholar 4. : Preoperative evaluation of prostate cancer aggressiveness: using ADC and ADC ratio in determining Gleason score. AJR Am J Roentgenol 2016; 207: 114. Google Scholar 5. : Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images. Proc Natl Acad Sci U S A 2015; 112: E6265. Google Scholar 6. : Utility of diffusional kurtosis imaging as a marker of adverse pathologic outcomes among prostate cancer active surveillance candidates undergoing radical prostatectomy. AJR Am J Roentgenol 2013; 201: 840. Google Scholar 7. : Grading of prostatic adenocarcinoma: current state and prognostic implications. Diagn Pathol 2016; 11: 25. Google Scholar 8. : The present and future of biomarkers in prostate cancer: proteomics, genomics, and immunology advancements. Biomark Cancer 2016; 8: 15. Google Scholar 9. : Discovery and validation of a prostate cancer genomic classifier that predicts early metastasis following radical prostatectomy. PLoS One 2013; 8: e66855. Google Scholar 10. : Genomic classifier identifies men with adverse pathology after radical prostatectomy who benefit from adjuvant radiation therapy. J Clin Oncol 2015; 33: 944. Google Scholar 11. : Genomic markers in prostate cancer decision making. Eur Urol 2018; 73: 572. Google Scholar 12. : Association of multiparametric MRI quantitative imaging features with prostate cancer gene expression in MRI-targeted prostate biopsies. Oncotarget 2016; 7: 53362. Google Scholar 13. : Multiparametric MRI features identify aggressive prostate cancer at the phenotypic and transcriptomic level. J Urol 2018; 200: 1241. Link, Google Scholar 14. : Advanced diffusion-weighted imaging modeling for prostate cancer characterization: correlation with quantitative histopathologic tumor tissue composition–a hypothesis-generating study. Radiology 2018; 286: 918. Google Scholar 15. : PI-RADS Prostate Imaging-Reporting and Data System: 2015, version 2. Eur Urol 2016; 69: 16. Google Scholar 16. : Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3 1973; 3: 610. Google Scholar 17. : Texture analysis using gray level run lengths. Computer Graphics Image Process 1975; 4: 172. Google Scholar 18. : Influence of MRI acquisition protocols and image intensity normalization methods on texture classification. Magn Reson Imaging 2004; 22: 81. Google Scholar 19. : Decipher correlation patterns post prostatectomy: initial experience from 2 342 prospective patients. Prostate Cancer Prostatic Dis 2016; 19: 374. Google Scholar 20. : Exon array data analysis using Affymetrix power tools and R statistical software. Brief Bioinform 2011; 12: 634. Google Scholar 21. : A single-sample microarray normalization method to facilitate personalized-medicine workflows. Genomics 2012; 100: 337. Google Scholar 22. : ToppGene suite for gene list enrichment analysis and candidate gene prioritization. Nucleic Acids Res 2009; 37: W305. Google Scholar 23. : Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics 2006; 7: 91. Google Scholar 24. : Development and validation of a 24-gene predictor of response to postoperative radiotherapy in prostate cancer: a matched, retrospective analysis. Lancet Oncol 2016; 17: 1612. Google Scholar 25. : T2-weighted MRI-derived textural features reflect prostate cancer aggressiveness: preliminary results. Eur Radiol 2017; 27: 3050. Google Scholar 26. : Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores. Eur Radiol 2015; 25: 2840. Google Scholar 27. : Repeatability and reproducibility of radiomic features: a systematic review. Int J Radiat Oncol Biol Phys 2018; 102: 1143. Google Scholar The corresponding author certifies that, when applicable, a statement(s) has been included in the manuscript documenting institutional review board, ethics committee or ethical review board study approval; principles of Helsinki Declaration were followed in lieu of formal ethics committee approval; institutional animal care and use committee approval; all human subjects provided written informed consent with guarantees of confidentiality; IRB approved protocol number; animal approved project number. Supported by the 2017 Judy and Ronald Baron Prostate Cancer Foundation Young Investigator Award (SJH). No direct or indirect commercial, personal, academic, political, religious or ethical incentive is associated with publishing this article. © 2019 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetailsRelated articlesJournal of Urology8 Aug 2019Editorial CommentJournal of Urology8 Aug 2019Editorial Comment Volume 202Issue 3September 2019Page: 498-505Supplementary Materials Advertisement Copyright & Permissions© 2019 by American Urological Association Education and Research, Inc.Keywordsprostatectomygenomicsprostatic neoplasmsmachine learningmagnetic resonance imagingMetricsAuthor Information Stefanie J. Hectors Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York Departments of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author Mathew Cherny Departments of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author Kamlesh K. Yadav Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York SEMA4, A Mount Sinai Venture, Stamford, Connecticut More articles by this author Alp Tuna Beksaç Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author Hari Thulasidass Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author Sara Lewis Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York Departments of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author Elai Davicioni GenomeDx Biosciences Inc., Vancouver, British Columbia, Canada Financial interest and/or other relationship with GenomeDx Biosciences. More articles by this author Pei Wang Genetics and Genomics Sciences, Icahn School of Medicine at Mount Sinai, New York, New York More articles by this author Ashutosh K. Tewari Department of Urology, Icahn School of Medicine at Mount Sinai, New York, New York ‡Correspondence: Department of Urology, Icahn School of Medicine at Mount Sinai, 1425 Madison Ave., New York, New York 10029 telephone: 212-876-3246; E-mail Address: [email protected] Equal study contribution. More articles by this author Bachir Taouli Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York Departments of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York ‡Correspondence: Translational and Molecular Imaging Institute, Icahn School of Medicine at Mount Sinai, 1470 Madison Ave., New York, New York 10029 telephone: 212-824-8453; E-mail Address: [email protected] Equal study contribution. More articles by this author Expand All The corresponding author certifies that, when applicable, a statement(s) has been included in the manuscript documenting institutional review board, ethics committee or ethical review board study approval; principles of Helsinki Declaration were followed in lieu of formal ethics committee approval; institutional animal care and use committee approval; all human subjects provided written informed consent with guarantees of confidentiality; IRB approved protocol number; animal approved project number. Supported by the 2017 Judy and Ronald Baron Prostate Cancer Foundation Young Investigator Award (SJH). No direct or indirect commercial, personal, academic, political, religious or ethical incentive is associated with publishing this article. Advertisement PDF downloadLoading ...