Purpose: This study aims to assess whole-mount Gleason grading (GG) in prostate cancer (PCa) accurately using a multiomics machine learning (ML) model and to compare its performance with biopsy-proven GG (bxGG) assessment. Materials and Methods: A total of 146 patients with PCa recruited in a pilot study of a prospective clinical trial (NCT02659527) were retrospectively included in the side study, all of whom underwent 68Ga-PSMA-11 integrated positron emission tomography (PET) / magnetic resonance (MR) before radical prostatectomy (RP) between May 2014 and April 2020. To establish a multiomics ML model, we quantified PET radiomics features, pathway-level genomics features from whole exome sequencing, and pathomics features derived from immunohistochemical staining of 11 biomarkers. Based on the multiomics dataset, five ML models were established and validated using 100-fold Monte Carlo cross-validation. Results: Among five ML models, the random forest (RF) model performed best in terms of the area under the curve (AUC). Compared to bxGG assessment alone, the RF model was superior in terms of AUC (0.87 vs 0.75), specificity (0.72 vs 0.61), positive predictive value (0.79 vs 0.75), and accuracy (0.78 vs 0.77) and showed slightly decreased sensitivity (0.83 vs 0.89) and negative predictive value (0.80 vs 0.81). Among the feature categories, bxGG was identified as the most important feature, followed by pathomics, clinical, radiomics and genomics features. The three important individual features were bxGG, PSA staining and one intensity-related radiomics feature. Conclusion: The findings demonstrate a superior assessment of the developed multiomics-based ML model in whole-mount GG compared to the current clinical baseline of bxGG. This enables personalized patient management by identifying high-risk PCa patients for RP.

Center for Biomarker Research in Medicine Graz Styria Austria

Center for Cancer Research Medical University of Vienna 1090 Vienna Austria

Center for Medical Physics and Biomedical Engineering Vienna Austria

Central European Institute of Technology Masaryk University Brno 62500 Czech Republic

Christian Doppler Laboratory for Applied Metabolomics 1090 Vienna Austria

Clinical Institute of Pathology Department for Experimental and Laboratory Animal Pathology Medical University of Vienna Vienna Austria

Comprehensive Cancer Center Medical University Vienna Vienna Austria

Department of Biomedical Imaging and Image guided Therapy Division of Molecular and Gender Imaging Medical University of Vienna 1090 Vienna Austria

Department of Urology 2nd Faculty of Medicine Charles University Prague Czech Republic

Department of Urology Medical University of Vienna Vienna Austria

Department of Urology University of Texas Southwestern Dallas Texas

Division of Medical Oncology Department of Urology Weill Medical College of Cornell University New York New York

Division of Nuclear Medicine Department of Biomedical Imaging and Image Guided Therapy Medical University of Vienna 1090 Vienna Austria

Institute for Urology and Reproductive Health 1 M Sechenov 1st Moscow State Medical University Moscow Russia

Karl Landsteiner Institute of Urology and Andrology Vienna Austria

Unit of Laboratory Animal Pathology University of Veterinary Medicine Vienna 1210 Vienna Austria

Working Group of Diagnostic Imaging in Urology Austrian Society of Urology Vienna Austria

Zobrazit více v PubMed

McGuire S. World Cancer Report 2014. Geneva, Switzerland: World Health Organization, International Agency for Research on Cancer, WHO Press, 2015. Adv Nutr. 2016;7:418–9. PubMed PMC

Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022. CA Cancer J Clin. 2022;72:7–33. PubMed

Bill-Axelson A, Holmberg L, Garmo H. et al. Radical Prostatectomy or Watchful Waiting in Prostate Cancer - 29-Year Follow-up. N Engl J Med. 2018;379:2319–29. PubMed

Castellan P, Ferretti S, Litterio G, Marchioni M, Schips L. Management of Urinary Incontinence Following Radical Prostatectomy: Challenges and Solutions. Ther Clin Risk Manag. 2023;19:43–56. PubMed PMC

Bratu O, Oprea I, Marcu D. et al. Erectile dysfunction post-radical prostatectomy - a challenge for both patient and physician. J Med Life. 2017;10:13–8. PubMed PMC

Costello AJ. Considering the role of radical prostatectomy in 21st century prostate cancer care. Nat Rev Urol. 2020;17:177–88. PubMed

Mottet N, van den Bergh RCN, Briers E. et al. EAU-EANM-ESTRO-ESUR-SIOG Guidelines on Prostate Cancer-2020 Update. Part 1: Screening, Diagnosis, and Local Treatment with Curative Intent. Eur Urol. 2021;79:243–62. PubMed

Yeldir N, Yildiz E, Dündar G. Gleason Score Correlation Between Prostate Needle Biopsy and Radical Prostatectomy Materials. Turk Patoloji Derg. 2019;35:185–92. PubMed

Mansouri N, Msakni I, Gargouri F, Khiari R, Bouziani A, Laabidi B. Evaluation of concordance of Gleason score between prostate biopsy and radical prostatectomy. Tunis Med. 2018;96:430–6. PubMed

Abedi AR, Basiri A, Shakhssalim N. et al. The Discrepancy between Needle Biopsy and Radical Prostatectomy Gleason Score in Patients with Prostate Cancer. Urol J. 2020;18:395–9. PubMed

Li QK, Lih T-SM, Wang Y. et al. Improving the detection of aggressive prostate cancer using immunohistochemical staining of protein marker panels. Am J Cancer Res. 2022;12:1323–36. PubMed PMC

Swanson GP, Trevathan S, Hammonds KAP, Speights VO, Hermans MR. Gleason score evolution and the effect on prostate cancer outcomes. Am J Clin Pathol. 2021;155:711–7. PubMed

Vollmer RT. Gleason grading, biochemical failure, and prostate cancer-specific death. Am J Clin Pathol. 2017;147:273–7. PubMed

Canzler S, Schor J, Busch W. et al. Prospects and challenges of multi-omics data integration in toxicology. Arch Toxicol. 2020;94:371–88. PubMed

Loeb S, Ross AE. Genomic testing for localized prostate cancer: where do we go from here? Curr Opin Urol. 2017;27:495–9. PubMed PMC

Yip SSF, Aerts HJWL. Applications and limitations of radiomics. Phys Med Biol. 2016;61:R150–66. PubMed PMC

Norris JM, Simpson BS, Parry MA. et al. Genetic Landscape of Prostate Cancer Conspicuity on Multiparametric Magnetic Resonance Imaging: A Systematic Review and Bioinformatic Analysis. Eur Urol Open Sci. 2020;20:37–47. PubMed PMC

Ferro M, de Cobelli O, Vartolomei MD, Prostate Cancer Radiogenomics-From Imaging to Molecular Characterization. Int J Mol Sci [Internet] 2021. 22. Available at: http://dx.doi.org/10.3390/ijms22189971. PubMed PMC

Gupta R, Kurc T, Sharma A, Almeida JS, Saltz J. The Emergence of Pathomics. Curr Pathobiol Rep. 2019;7:73–84.

Schuettfort VM, Pradere B, Rink M, Comperat E, Shariat SF. Pathomics in urology. Curr Opin Urol. 2020;30:823–31. PubMed

McGarry SD, Hurrell SL, Iczkowski KA. et al. Radio-pathomic Maps of Epithelium and Lumen Density Predict the Location of High-Grade Prostate Cancer. Int J Radiat Oncol Biol Phys. 2018;101:1179–87. PubMed PMC

Fang LT. SomaticSeq: An Ensemble and Machine Learning Method to Detect Somatic Mutations. In: Boegel S, Ed. Bioinformatics for Cancer Immunotherapy: Methods and Protocols. New York, NY: Springer US. 2020. pp. 47–70. PubMed

Frazer J, Notin P, Dias M. et al. Disease variant prediction with deep generative models of evolutionary data. Nature. 2021;599:91–5. PubMed

Rentzsch P, Witten D, Cooper GM, Shendure J, Kircher M. CADD: predicting the deleteriousness of variants throughout the human genome. Nucleic Acids Res. 2019;47:D886–94. PubMed PMC

Adzhubei I, Jordan DM, Sunyaev SR. Predicting functional effect of human missense mutations using PolyPhen-2. Curr Protoc Hum Genet. 2013. Chapter 7: Unit7.20. PubMed PMC

Talevich E, Shain AH, Botton T, Bastian BC. CNVkit: Genome-Wide Copy Number Detection and Visualization from Targeted DNA Sequencing. PLoS Comput Biol. 2016;12:e1004873. PubMed PMC

Grubmüller B, Baltzer P, Hartenbach S. et al. PSMA Ligand PET/MRI for Primary Prostate Cancer: Staging Performance and Clinical Impact. Clin Cancer Res. 2018;24:6300–7. PubMed

Schmuck S, von Klot CA, Henkenberens C. et al. Initial Experience with Volumetric 68Ga-PSMA I&T PET/CT for Assessment of Whole-Body Tumor Burden as a Quantitative Imaging Biomarker in Patients with Prostate Cancer. J Nucl Med. 2017;58:1962–8. PubMed

van Griethuysen JJM, Fedorov A, Parmar C. et al. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017;77:e104–7. PubMed PMC

Zwanenburg A, Vallières M, Abdalah MA. et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology. 2020;295:328–38. PubMed PMC

Kristiansen G, Epstein JI. IHC Prostate Pathology [Internet] [cited July 18, 2023]. Available at: https://www.patologi.com/DAKO%20immun%20-prostate-pathology.pdf.

Maia R, Santos GADOS, Reis S, Can we use Ki67 expression to predict prostate cancer aggressiveness? Revista do Colégio Brasileiro de Cirurgiões [Internet] 2022. 49. Available at: https://www.scielo.br/j/rcbc/a/pYjPndLW69VXczN94GMrwqk/?format=pdf&lang=en. PubMed PMC

Zhang J, Gan Y, Li H. et al. Inhibition of the CDK2 and Cyclin A complex leads to autophagic degradation of CDK2 in cancer cells. Nat Commun. 2022;13:1–16. PubMed PMC

Yin X, Yu J, Zhou Y. et al. Identification of CDK2 as a novel target in treatment of prostate cancer. Future Oncol. 2018;14:709–18. PubMed

Glud EN, Rasmussen M, Zhang Y. et al. Identification of a high-risk immunogenic prostate cancer patient subset as candidates for T-cell engager immunotherapy and the introduction of a novel albumin-fused anti-CD3 × anti-PSMA bispecific design. Br J Cancer. 2022;127:2186–97. PubMed PMC

Pencik J, Schlederer M, Gruber W. et al. STAT3 regulated ARF expression suppresses prostate cancer metastasis. Nat Commun. 2015;6:7736. PubMed PMC

Aksoy O, Pencik J, Hartenbach M. et al. Thyroid and androgen receptor signaling are antagonized by μ-Crystallin in prostate cancer. Int J Cancer. 2021;148:731–47. PubMed PMC

Shariat SF, Chromecki TF, Hoefer J. et al. Soluble gp130 regulates prostate cancer invasion and progression in an interleukin-6 dependent and independent manner. J Urol. 2011;186:2107–14. PubMed

Glinsmann-Gibson B, Wisner L, Stanton M, Larsen B, Rimsza L, Maguire A. Recommendations for Tissue Microarray Construction and Quality Assurance. Appl Immunohistochem Mol Morphol. 2020;28:325–30. PubMed PMC

Das CJ, Netaji A, Razik A, Verma S. MRI-Targeted Prostate Biopsy: What Radiologists Should Know. Korean J Radiol. 2020;21:1087–94. PubMed PMC

Purdie CA, Quinlan P, Jordan LB. et al. Progesterone receptor expression is an independent prognostic variable in early breast cancer: a population-based study. Br J Cancer. 2014;110:565–72. PubMed PMC

Detre S, Saclani Jotti G, Dowsett M. A “quickscore” method for immunohistochemical semiquantitation: validation for oestrogen receptor in breast carcinomas. J Clin Pathol. 1995;48:876–8. PubMed PMC

Sowalsky AG, Figueiredo I, Lis RT. et al. Assessment of Androgen Receptor Splice Variant-7 as a Biomarker of Clinical Response in Castration-Sensitive Prostate Cancer. Clin Cancer Res. 2022;28:3509–25. PubMed PMC

Epstein JI, Egevad L, Amin MB. et al. The 2014 International Society of Urological Pathology (ISUP) Consensus Conference on Gleason Grading of Prostatic Carcinoma: Definition of Grading Patterns and Proposal for a New Grading System. Am J Surg Pathol. 2016;40:244–52. PubMed

Epstein JI, Zelefsky MJ, Sjoberg DD. et al. A Contemporary Prostate Cancer Grading System: A Validated Alternative to the Gleason Score. Eur Urol. 2016;69:428–35. PubMed PMC

van Leenders GJLH, van der Kwast TH, Grignon DJ. et al. The 2019 International Society of Urological Pathology (ISUP) Consensus Conference on Grading of Prostatic Carcinoma. Am J Surg Pathol. 2020;44:e87–99. PubMed PMC

Zelic R, Giunchi F, Fridfeldt J. et al. Prognostic Utility of the Gleason Grading System Revisions and Histopathological Factors Beyond Gleason Grade. Clin Epidemiol. 2022;14:59–70. PubMed PMC

Beretta L, Santaniello A. Nearest neighbor imputation algorithms: a critical evaluation. BMC Med Inform Decis Mak [Internet] 2016. 16. Available at: http://dx.doi.org/10.1186/s12911-016-0318-z. PubMed PMC

Peng H, Long F, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell. 2005;27:1226–38. PubMed

Altmann A, Toloşi L, Sander O, Lengauer T. Permutation importance: a corrected feature importance measure. Bioinformatics. 2010;26:1340–7. PubMed

Pumplun L, Fecho M, Wahl N, Peters F, Buxmann P. Adoption of Machine Learning Systems for Medical Diagnostics in Clinics: Qualitative Interview Study. J Med Internet Res. 2021;23:e29301. PubMed PMC

Sandhu S, Lin AL, Brajer N. et al. Integrating a Machine Learning System Into Clinical Workflows: Qualitative Study. J Med Internet Res. 2020;22:e22421. PubMed PMC

Gómez-Cebrián N, Poveda JL, Pineda-Lucena A, Puchades-Carrasco L. Metabolic Phenotyping in Prostate Cancer Using Multi-Omics Approaches. Cancers [Internet] 2022. 14. Available at: http://dx.doi.org/10.3390/cancers14030596. PubMed PMC

Wei Z, Han D, Zhang C. et al. Deep Learning-Based Multi-Omics Integration Robustly Predicts Relapse in Prostate Cancer. Front Oncol. 2022;12:893424. PubMed PMC

Wu L, Yang Y, Guo X. et al. An integrative multi-omics analysis to identify candidate DNA methylation biomarkers related to prostate cancer risk. Nat Commun. 2020;11:3905. PubMed PMC

Kiebish MA, Cullen J, Mishra P. et al. Multi-omic serum biomarkers for prognosis of disease progression in prostate cancer. J Transl Med. 2020;18:10. PubMed PMC

Abdollahi H, Mofid B, Shiri I. et al. Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer. Radiol Med. 2019;124:555–67. PubMed

Chaddad A, Kucharczyk MJ, Niazi T. Multimodal Radiomic Features for the Predicting Gleason Score of Prostate Cancer. Cancers [Internet] 2018. 10. Available at: http://dx.doi.org/10.3390/cancers10080249. PubMed PMC

Papp L, Spielvogel CP, Grubmüller B. et al. Supervised machine learning enables non-invasive lesion characterization in primary prostate cancer with [68Ga]Ga-PSMA-11 PET/MRI. Eur J Nucl Med Mol Imaging. 2021;48:1795–805. PubMed PMC

Bonk S, Kluth M, Hube-Magg C. et al. Prognostic and diagnostic role of PSA immunohistochemistry: A tissue microarray study on 21,000 normal and cancerous tissues. Oncotarget. 2019;10:5439–53. PubMed PMC

Zschaeck S, Andela SB, Amthauer H. et al. Correlation Between Quantitative PSMA PET Parameters and Clinical Risk Factors in Non-Metastatic Primary Prostate Cancer Patients. Front Oncol. 2022;12:879089. PubMed PMC

Kishan AU, Romero T, Alshalalfa M. et al. Transcriptomic Heterogeneity of Gleason Grade Group 5 Prostate Cancer. Eur Urol. 2020;78:327–32. PubMed PMC

Leithner D, Schöder H, Haug A. et al. Impact of ComBat Harmonization on PET Radiomics-Based Tissue Classification: A Dual-Center PET/MRI and PET/CT Study. J Nucl Med. 2022;63:1611–6. PubMed PMC

Da-Ano R, Visvikis D, Hatt M. Harmonization strategies for multicenter radiomics investigations. Phys Med Biol. 2020;65:24TR02. PubMed

Orlhac F, Frouin F, Nioche C, Ayache N, Buvat I. Validation of A Method to Compensate Multicenter Effects Affecting CT Radiomics. Radiology. 2019;291:53–9. PubMed

Zobrazit více v PubMed

ClinicalTrials.gov
NCT02659527