Prostate cancer (PCa) is the second most common malignancy diagnosed in men worldwide, with approximately 1.47 million new cases reported in 2022. Biochemical recurrence (BCR), defined as a rising prostate-specific antigen (PSA) after radical treatment, is the first clinical sign of disease relapse and a harbinger of metastasis and cancer-specific mortality. Accurate, non-invasive prediction of BCR is essential for guiding individualized treatment decisions and optimizing long-term outcomes. This narrative review critically evaluates the current evidence on artificial intelligence (AI)-based approaches—encompassing radiomics, machine learning (ML), and deep learning (DL)—applied to multiparametric magnetic resonance imaging (mpMRI) for the prediction of BCR in PCa following radical prostatectomy (RP) or radiation therapy (RT). The review further examines multimodal AI approaches integrating mpMRI with prostate-specific membrane antigen positron emission tomography (PSMA-PET), digital pathology, and genomic data. This manuscript is a narrative review; no systematic protocol was registered. Among the reviewed studies, mpMRI-based radiomics models achieved area under the receiver operating characteristic curve (AUC) values ranging from 0.72 to 0.97 for BCR prediction, though this wide range reflects substantial methodological and population heterogeneity. Deep learning models, particularly those combining mpMRI features with clinical parameters, demonstrated C-index values up to 0.83. Because the area under the receiver operating characteristic curve (a discrimination metric for binary classification) and the C-index (for time-to-event survival analysis) are distinct statistical measures, radiomics AUC and deep-learning C-index values are reported separately here and are not directly comparable or interchangeable. AI-powered mpMRI analysis holds substantial promise for non-invasive, accurate BCR prediction in PCa. Integration of radiomics and DL with clinical and multi-omics data within standardized, multi-center frameworks represents the most promising future direction. Regulatory-compliant, externally validated models with demonstrated calibration are required before routine clinical implementation.
N. Narimani, M. Atarod, Ehsan Zolfi et al.· African Journal of Urology· 0 citations
Background Inherited ocular disorders are a leading cause of early-onset visual impairment, particularly in populations with high consanguinity such as Iran, where a substantial proportion of affected individuals remain without a molecular diagnosis after conventional evaluation. We aimed to determine the diagnostic yield and variant spectrum of whole-exome sequencing (WES) in Iranian probands with congenital or early-onset ocular disorders that were genetically unresolved by prior testing. Methods Thirty unrelated probands were recruited consecutively (July–September 2024). Genomic DNA underwent exome capture (Agilent SureSelect V7) and paired-end sequencing (Illumina NovaSeq 6000). Reads were cleaned with SOAPnuke, aligned with BWA-MEM, and variants were called with GATK HaplotypeCaller and DeepVariant, filtered by GATK VQSR, and annotated against public and Iranian-specific databases (GEMIRAN, IRANOM). Variants were classified per ACMG/AMP criteria. Diagnostic yield was defined as the proportion of probands with a causative or candidate variant concordant with phenotype. Results A causative or strong candidate variant concordant with the phenotype was identified in 21 of 30 probands (diagnostic yield 70.0%; 95% CI 50.6–85.3%). Pathogenic or likely-pathogenic variants were found in established genes including ABCA4, USH2A, RP1, CRB1, CEP290, GUCY2D, CYP1B1 and TYR. Among the identified genotypes, 54% were homozygous and 12% hemizygous (X-linked), consistent with consanguinity in 11/30 (36.7%) families; 35% were single heterozygous findings in autosomal-recessive genes, interpreted as incomplete genotypes pending detection of a second allele. Onset was infantile in 73% of probands. Conclusions WES is an effective first-tier test for congenital and early-onset ocular disorders in the Iranian population, resolving roughly 70% of previously undiagnosed probands. Single-allele findings in recessive genes indicate that complementary copy-number and structural-variant analysis, deep-intronic assessment, periodic reanalysis, and reflex whole-genome sequencing are needed to maximise yield and support accurate genetic counselling.
Ali Asadi, Seyed Ataollah Sadat Shandiz, Amirhossein Ebrahimi et al.· Molecular Genetics and Metab...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
