Next-generation imaging in prostate cancer.

Background: Early detection of clinically significant prostate cancer (csPCa) remains a major challenge in urologic oncology. Although prostate-specific antigen (PSA) screening and systematic transrectal ultrasound- guided biopsy has historically been the main diagnostic approaches, these strategies are associated with both overdiagnosis of indolent disease and underdetection of clinically significant tumors. Recent advances in imaging technologies-including multiparametric magnetic resonance imaging (mpMRI), high-resolution micro-ultrasound (MUS), and prostate-specific membrane antigen positron emission tomography (PSMA PET)-have significantly improved the diagnostic pathway for prostate cancer. In parallel, artificial intelligence (AI)-based algorithms have emerged as promising tools for enhancing image interpretation and reducing diagnostic variability. Objective: This review aims to summarize current evidence regarding the diagnostic performance of micro- ultrasound, mpMRI, and PSMA PET in prostate cancer detection and to explore the potential role of artificial intelligence in integrating these imaging modalities to improve diagnostic accuracy. Methods: A systematic literature search was performed using PubMed and MEDLINE databases for articles published between January 2013 and December 2024. The following search strategy was employed using combinations of MeSH terms and keywords: ('prostate cancer' OR 'prostate neoplasm' OR 'prostatic carcinoma') AND ('micro-ultrasound' OR 'high-resolution micro-ultrasound' OR 'micro-US' OR 'PRI-MUS' OR 'ExactVu') OR ('multiparametric MRI' OR 'mpMRI' OR 'multi-parametric magnetic resonance imaging' OR 'PI-RADS') OR ('PSMA PET' OR 'prostate-specific membrane antigen' OR '68Ga-PSMA' OR '18F-DCFPyL' OR 'PSMA-11') OR ('artificial intelligence' OR 'machine learning' OR 'deep learning' OR 'radiomics' OR 'neural network'). Only English-language, peer-reviewed original research articles, systematic reviews, meta-analyses, and major consensus guidelines were included. Case reports, editorials, conference abstracts, and non-peer-reviewed publications were excluded. Two authors (A.R. and O.Z.) independently screened titles and abstracts for relevance. Full texts of potentially eligible articles were retrieved and assessed against predefined inclusion criteria: (1) evaluation of mpMRI, micro-ultrasound, or PSMA PET for prostate cancer detection, localization, or staging; (2) reported diagnostic accuracy metrics (sensitivity, specificity, AUC) or biopsy outcomes; (3) sample size ≥20 patients for original studies. Disagreements were resolved by consensus with a third author (M.B.). Reference lists of included articles were hand-searched for additional relevant studies. A narrative synthesis was conducted due to heterogeneity in study designs, populations, and outcome measures. Results: Multiparametric MRI has become a cornerstone in prostate cancer diagnosis due to its high sensitivity for detecting clinically significant diseases and its role in guiding targeted biopsies. Micro-ultrasound, offering substantially higher spatial resolution than conventional ultrasound, has demonstrated promising diagnostic performance and may represent a cost-effective alternative or complement to in review mpMRI. Meanwhile, PSMA PET imaging has shown high sensitivity for identifying both intraprostatic lesions and metastatic disease. Emerging evidence suggests that combining these imaging modalities may significantly enhance detection rates. Furthermore, artificial intelligence techniques-including machine learning and deep learning algorithms-have shown potential in improving lesion detection, segmentation, and risk stratification in prostate imaging. Conclusion: The integration of multimodal imaging approaches with artificial intelligence represents a promising investigational strategy that may, following prospective validation, improve prostate cancer detection and characterization. Future prospective studies are needed to validate these technologies and define their optimal role in clinical practice.