OBJECTIVES: Radical prostatectomy (RP) is a common intervention in patients with localized prostate cancer (PCa), with nerve-sparing RP recommended to reduce adverse effects on patient quality of life. Accurate pre-operative detection of extraprostatic extension (EPE) remains challenging, often leading to the application of suboptimal treatment. The aim of this study was to enhance pre-operative EPE detection through multimodal data integration using explainable machine learning (ML). METHODS: Patients with newly diagnosed PCa who underwent [68Ga]Ga-PSMA-11 PET/MRI and subsequent RP were recruited retrospectively from two time ranges for training, cross-validation, and independent validation. The presence of EPE was measured from post-surgical histopathology and predicted using ML and pre-operative parameters, including PET/MRI-derived features, blood-based markers, histology-derived parameters, and demographic parameters. ML models were subsequently compared with conventional PET/MRI-based image readings. RESULTS: The study involved 107 patients, 59 (55%) of whom were affected by EPE according to postoperative findings for the initial training and cross-validation. The ML models demonstrated superior diagnostic performance over conventional PET/MRI image readings, with the explainable boosting machine model achieving an AUC of 0.88 (95% CI 0.87-0.89) during cross-validation and an AUC of 0.88 (95% CI 0.75-0.97) during independent validation. The ML approach integrating invasive features demonstrated better predictive capabilities for EPE compared to visual clinical read-outs (Cross-validation AUC 0.88 versus 0.71, p = 0.02). CONCLUSION: ML based on routinely acquired clinical data can significantly improve the pre-operative detection of EPE in PCa patients, potentially enabling more accurate clinical staging and decision-making, thereby improving patient outcomes. CRITICAL RELEVANCE STATEMENT: This study demonstrates that integrating multimodal data with machine learning significantly improves the pre-operative detection of extraprostatic extension in prostate cancer patients, outperforming conventional imaging methods and potentially leading to more accurate clinical staging and better treatment decisions. KEY POINTS: Extraprostatic extension is an important indicator guiding treatment approaches. Current assessment of extraprostatic extension is difficult and lacks accuracy. Machine learning improves detection of extraprostatic extension using PSMA-PET/MRI and histopathology.

Center for Biomarker Research in Medicine Graz Austria

Center for Medical Physics and Biomedical Engineering Medical University of Vienna Vienna Austria

Christian Doppler Laboratory for Applied Metabolomics Vienna Austria

Department of Biomedical Imaging and Image Guided Therapy Division of General and Pediatric Radiology Medical University of Vienna Vienna Austria

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

Department of Pathology Medical University of Vienna Vienna Austria

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

Department of Urology and Andrology University Hospital Krems Krems Austria

Department of Urology Medical University of Vienna Vienna Austria

Department of Urology University of Texas Southwestern Medical Center Dallas USA

Department of Urology Weill Cornell Medical College New York USA

Division of Urology Department of Special Surgery The University of Jordan Amman Jordan

Karl Landsteiner Institute of Urology and Andrology Vienna Austria

Karl Landsteiner University of Health Sciences Krems Austria

Unit for Pathology of Laboratory Animals University of Veterinary Medicine Vienna Vienna Austria

Zobrazit více v PubMed

Mottet N, van den Bergh RCN, Briers E et al (2021) EAU-EANM-ESTRO-ESUR-SIOG guidelines on prostate cancer—2020 update. Part 1: Screening, diagnosis, and local treatment with curative intent. Eur Urol 79:243–262 PubMed

Costello AJ (2020) Considering the role of radical prostatectomy in 21st century prostate cancer care. Nat Rev Urol 17:177–188 PubMed

Reeves F, Preece P, Kapoor J et al (2015) Preservation of the neurovascular bundles is associated with improved time to continence after radical prostatectomy but not long-term continence rates: results of a systematic review and meta-analysis. Eur Urol 68:692–704 PubMed

Potter SR, Epstein JI, Partin AW (2000) Seminal vesicle invasion by prostate cancer: prognostic significance and therapeutic implications. Rev Urol 2:190–195 PubMed PMC

de Rooij M, Hamoen EHJ, Witjes JA, Barentsz JO, Rovers MM (2016) Accuracy of magnetic resonance imaging for local staging of prostate cancer: a diagnostic meta-analysis. Eur Urol 70:233–245 PubMed

Muehlematter UJ, Burger IA, Becker AS et al (2019) Diagnostic accuracy of multiparametric MRI versus 68Ga-PSMA-11 PET/MRI for extracapsular extension and seminal vesicle invasion in patients with prostate cancer. Radiology 293:350–358 PubMed

Jia Y, McDermid J, Lawton T, Habli I (2022) The role of explainability in assuring safety of machine learning in healthcare. IEEE Trans Emerg Top Comput 10:1746–1760

Spielvogel CP, Stoiber S, Papp L et al (2022) Radiogenomic markers enable risk stratification and inference of mutational pathway states in head and neck cancer. Eur J Nucl Med Mol Imaging. 10.1007/s00259-022-05973-9 PubMed PMC

Saux P, Bauvin P, Raverdy V et al (2023) Development and validation of an interpretable machine learning-based calculator for predicting 5-year weight trajectories after bariatric surgery: a multinational retrospective cohort SOPHIA study. Lancet Digit Health 5:e692–e702 PubMed

Mongan J, Moy L, Kahn CE Jr (2020) Checklist for artificial intelligence in medical imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell 2:e200029 PubMed PMC

Sobin Leslie H, Gospodarowicz MK, Wittekind C (2009) TNM classification of malignant tumours. Wiley-Blackwell, Oxford

Bloch BN, Furman-Haran E, Helbich TH et al (2007) Prostate cancer: accurate determination of extracapsular extension with high-spatial-resolution dynamic contrast-enhanced and T2-weighted MR imaging—initial results. Radiology 245:176–185 PubMed

Nori H, Jenkins S, Koch P, Caruana R (2019) InterpretML: a unified framework for machine learning interpretability. Preprint at http://arxiv.org/abs/1909.09223

Lundberg SM, Erion GG, Lee S-I (2018) Consistent individualized feature attribution for tree ensembles. Preprint at arXiv http://arxiv.org/abs/1802.03888

Becht E, McInnes L, Healy J et al (2018) Dimensionality reduction for visualizing single-cell data using UMAP. Nat Biotechnol. 10.1038/nbt.4314 PubMed

Luining WI, Oprea-Lager DE, Vis AN et al (2023) Optimization and validation of 18F-DCFPyL PET radiomics-based machine learning models in intermediate- to high-risk primary prostate cancer. PLoS ONE 18:e0293672 PubMed PMC

Cysouw MCF, Jansen BHE, van de Brug T et al (2021) Machine learning-based analysis of [18F]DCFPyL PET radiomics for risk stratification in primary prostate cancer. Eur J Nucl Med Mol Imaging 48:340–349 PubMed PMC

Yao F, Bian S, Zhu D et al (2022) Machine learning-based radiomics for multiple primary prostate cancer biological characteristics prediction with 18F-PSMA-1007 PET: comparison among different volume segmentation thresholds. Radiol Med 127:1170–1178 PubMed

Brembilla G, Lavalle S, Parry T et al (2023) Impact of prostate imaging quality (PI-QUAL) score on the detection of clinically significant prostate cancer at biopsy. Eur J Radiol 164:110849 PubMed

Ponsiglione A, Stanzione A, Califano G et al (2023) MR image quality in local staging of prostate cancer: role of PI-QUAL in the detection of extraprostatic extension. Eur J Radiol 166:110973 PubMed

de Rooij M, Allen C, Twilt JJ et al (2024) PI-QUAL version 2: an update of a standardised scoring system for the assessment of image quality of prostate MRI. Eur Radiol 34:7068–7079 PubMed PMC

Zwanenburg A, Vallières M, Abdalah MA et al (2020) The Image Biomarker Standardization Initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328–338 PubMed PMC

Mayerhoefer ME, Materka A, Langs G et al (2020) Introduction to radiomics. J Nucl Med 61:488–495 PubMed PMC

Werner RA, Habacha B, Lütje S et al (2023) Lack of repeatability of radiomic features derived from PET scans: results from a 18F-DCFPyL test-retest cohort. Prostate 83:547–554 PubMed

Ponsiglione A, Gambardella M, Stanzione A et al (2024) Radiomics for the identification of extraprostatic extension with prostate MRI: a systematic review and meta-analysis. Eur Radiol 34:3981–3991 PubMed PMC

Uprimny C, Kroiss AS, Decristoforo C et al (2017) 68Ga-PSMA-11 PET/CT in primary staging of prostate cancer: PSA and Gleason score predict the intensity of tracer accumulation in the primary tumour. Eur J Nucl Med Mol Imaging 44:941–949 PubMed