Background: Tumour mutational burden (TMB) is an emerging biomarker for predicting the efficacy of immune checkpoint inhibitors (ICIs) in cancer therapy. While its role is well established in lung cancer and melanoma, its predictive value for breast and prostate cancers remains unclear. Objective: This systematic review aimed to assess the predictive value of TMB for ICI therapy across four major cancer types—lung, melanoma, breast, and prostate—and to explore factors contributing to the variability in its effectiveness as a biomarker. Methods: A systematic search and a review of the literature were conducted in accordance with PRISMA guidelines. Studies examining the relationship between TMB levels and clinical outcomes following ICI therapy in the specified cancers were analyzed. The data were synthesized to evaluate TMB’s predictive value and identify gaps in the current research. Results: High TMB consistently correlated with improved outcomes in lung cancer and melanoma, confirming its predictive utility in these cancers. Conversely, the findings for breast and prostate cancers were inconclusive. The variability in TMB’s predictive value for these cancers suggests the need for complementary biomarkers or refined criteria to enhance its reliability. Methodological inconsistencies in TMB evaluation were also noted as a significant limitation. Conclusions: TMB serves as a robust biomarker for predicting ICI response in lung cancer and melanoma, but demonstrates limited predictive utility in breast and prostate cancers. Future research should prioritize standardizing TMB assessment protocols and investigating additional biomarkers to improve treatment personalization for these cancer types.

Accurate distinction between non-muscle-invasive bladder cancer (NMIBC) and muscle-invasive bladder cancer (MIBC) remains the key local staging problem in bladder cancer because treatment intensity, timing of radical therapy, and suitability for bladder-preserving strategies all depend on it. Multiparametric magnetic resonance imaging (mpMRI) and the Vesical Imaging-Reporting and Data System (VI-RADS) now provide a standardized imaging framework for local staging and increasingly support MRI-first clinical pathways. Artificial intelligence (AI) has emerged as an additional decision-support layer, but the evidence base remains methodologically uneven. In this structured narrative review, we synthesized peer-reviewed literature from January 2020 to March 2026, while retaining foundational VI-RADS studies from 2018 to 2019, and prioritized guideline documents, meta-analyses, prospective cohorts, multicenter and externally validated AI studies, response-assessment studies, and papers addressing implementation and reporting quality. Current evidence shows that radiomics and deep learning models can achieve high discrimination for MIBC detection on MRI, and that the most plausible incremental value of AI lies in equivocal VI-RADS lesions, reader support outside high-volume expert settings, and multimodal risk stratification. However, most studies remain retrospective, highly selected, segmentation-dependent, and vulnerable to reference-standard bias, domain shift, and poor calibration. This review therefore emphasizes several translational issues that are often underreported: lesion-level versus patient-level inference, the distortive effect of TURBT-based labels, the need to evaluate false-negative consequences in VI-RADS 3 tumors, and the distinction between diagnostic support and broader pathway redesign. We also discuss response assessment, nacVI-RADS, segmentation automation, multicenter and federated infrastructure, workflow ownership, and the limits of imaging-only models in a biologically heterogeneous disease. The most credible near-term role of AI is not autonomous diagnosis, but augmentation of standardized mpMRI and VI-RADS within multidisciplinary care. Future progress will depend on prospective utility studies, site-held-out validation, transparent reporting, and the integration of imaging with molecular and cellular heterogeneity through radiogenomic and multi-omics approaches.