Artificial intelligence(AI)is transforming the diagnostic landscape of malignant tumors in the urinary system,including prostate cancer,bladder cancer,and renal cell carcinoma(RCC).By integrating imaging,pathology,and...Artificial intelligence(AI)is transforming the diagnostic landscape of malignant tumors in the urinary system,including prostate cancer,bladder cancer,and renal cell carcinoma(RCC).By integrating imaging,pathology,and molecular data,AI enhances the precision and reproducibility of tumor detection,grading,and risk stratification.In prostate cancer,AI-assisted multiparametric Magnetic resonance imaging(MRI)and digital pathology systems improve lesion localization and Gleason scoring.For bladder cancer,deep learning-based cystoscopy and radiomics models from Computed tomography/magnetic resonance imaging(CT/MRI)enable real-time lesion segmentation and non-invasive biomarker prediction,such as Programmed Cell Death-Ligand 1(PD-L1)expression.In RCC,AI,combined with CT/MRI and multi-omics data,aids in subtype classification and prognostic prediction,supporting personalized therapy.However,despite these promising advances,challenges such as data standardization,model generalizability,interpretability,and regulatory compliance hinder AI’s clinical translation.This review outlines the current state of AI in urological cancer diagnosis and prognosis,its technological innovations,and the clinical challenges and opportunities that lie ahead.展开更多
Prostate cancer(PCa)remains a major cause of cancer-related mortality in men,largely due to therapy resistance and metastatic progression.Increasing evidence highlights the tumor microenvironment(TME),particularly can...Prostate cancer(PCa)remains a major cause of cancer-related mortality in men,largely due to therapy resistance and metastatic progression.Increasing evidence highlights the tumor microenvironment(TME),particularly cancer-associated fibroblasts(CAFs),as a critical determinant of disease behavior.CAFs constitute a heterogeneous population originating from fibroblasts,mesenchymal stem cells,endothelial cells,epithelial cells undergoing epithelial-mesenchymal transition(EMT),and adipose tissue.Through dynamic crosstalk with tumor,immune,endothelial,and adipocyte compartments,CAFs orchestrate oncogenic processes including tumor proliferation,invasion,immune evasion,extracellular matrix remodeling,angiogenesis,and metabolic reprogramming.This review comprehensively summarizes the cellular origins,phenotypic and functional heterogeneity,and spatial distribution of CAFs within the prostate TME.We further elucidate the molecular mechanisms by which CAFs regulate PCa progression and therapeutic resistance,and critically evaluate emerging strategies to therapeutically target CAFmediated signaling,metabolic,and immune pathways.By integrating recent advances from single-cell and spatial transcriptomics(ST),our objective is to provide a holistic framework for understanding CAF biology and to highlight potential avenues for stromal reprogramming as an adjunct to current PCa therapies.展开更多
基金supported by grants from the Hangzhou Key Project for Agricultural and Social Development under Grant No.20231203A12(JZ)the General Program of the Scientific Research Special Project for Post-Marketing Clinical Research of Innovative Drugs,Development Center for Medical Science&Technology,National Health Commission of the People’s Republic of China under Grant No.WKZX2024CX104202(JZ).
文摘Artificial intelligence(AI)is transforming the diagnostic landscape of malignant tumors in the urinary system,including prostate cancer,bladder cancer,and renal cell carcinoma(RCC).By integrating imaging,pathology,and molecular data,AI enhances the precision and reproducibility of tumor detection,grading,and risk stratification.In prostate cancer,AI-assisted multiparametric Magnetic resonance imaging(MRI)and digital pathology systems improve lesion localization and Gleason scoring.For bladder cancer,deep learning-based cystoscopy and radiomics models from Computed tomography/magnetic resonance imaging(CT/MRI)enable real-time lesion segmentation and non-invasive biomarker prediction,such as Programmed Cell Death-Ligand 1(PD-L1)expression.In RCC,AI,combined with CT/MRI and multi-omics data,aids in subtype classification and prognostic prediction,supporting personalized therapy.However,despite these promising advances,challenges such as data standardization,model generalizability,interpretability,and regulatory compliance hinder AI’s clinical translation.This review outlines the current state of AI in urological cancer diagnosis and prognosis,its technological innovations,and the clinical challenges and opportunities that lie ahead.
文摘Prostate cancer(PCa)remains a major cause of cancer-related mortality in men,largely due to therapy resistance and metastatic progression.Increasing evidence highlights the tumor microenvironment(TME),particularly cancer-associated fibroblasts(CAFs),as a critical determinant of disease behavior.CAFs constitute a heterogeneous population originating from fibroblasts,mesenchymal stem cells,endothelial cells,epithelial cells undergoing epithelial-mesenchymal transition(EMT),and adipose tissue.Through dynamic crosstalk with tumor,immune,endothelial,and adipocyte compartments,CAFs orchestrate oncogenic processes including tumor proliferation,invasion,immune evasion,extracellular matrix remodeling,angiogenesis,and metabolic reprogramming.This review comprehensively summarizes the cellular origins,phenotypic and functional heterogeneity,and spatial distribution of CAFs within the prostate TME.We further elucidate the molecular mechanisms by which CAFs regulate PCa progression and therapeutic resistance,and critically evaluate emerging strategies to therapeutically target CAFmediated signaling,metabolic,and immune pathways.By integrating recent advances from single-cell and spatial transcriptomics(ST),our objective is to provide a holistic framework for understanding CAF biology and to highlight potential avenues for stromal reprogramming as an adjunct to current PCa therapies.
