Abstract: Prostate cancer (PCa) is one of the most common malignant tumors in men, and the precise diagnosis and treatment of PCa urgently need to address the challenges of tumor heterogeneity and prognostic variability. Radiomics, by extracting high-throughput features from medical imaging and integrating artificial intelligence technologies, provides new tools for lesion detection, Gleason score prediction, and treatment response monitoring. This article systematically reviews the latest advancements in the technical processes, diagnostic efficacy, prognostic assessment, and treatment monitoring of radiomics in PCa. It highlights breakthrough achievements in non-invasive grading, metastatic risk prediction, and personalized radiotherapy planning, with a focus on integrating multimodal imaging technologies and deep learning methods. Addressing current technical limitations, it proposes future development directions, including the establishment of multicenter collaborative databases, multimodal omics, integrative omics, and the development of standardized validation models. Through a balanced approach of technological innovation and clinical practice, radiomics is expected to drive the transition of PCa diagnosis and treatment towards a paradigm of dynamic precision medicine, ultimately enhancing patient survival benefits.

Key words:

Prostate cancer, Radiomics, MRI, Deep learning, Precision diagnosis and treatment, Progress

摘要： 前列腺癌（prostate cancer，PCa）是男性常见的恶性肿瘤之一，PCa的精准诊疗亟需克服肿瘤异质性及预后差异的挑战。影像组学通过提取医学影像的高通量特征并融合人工智能技术，为病灶检测、Gleason评分预测及治疗反应监测提供了新工具。本文系统综述了影像组学在PCa中的技术流程、诊断效能、预后评估及治疗监测中的最新进展，梳理影像组学在无创分级、转移风险预测及个体化放疗规划中的突破性成果，重点整合了多模态影像技术与深度学习方法；针对当前技术局限性，提出建立多中心协作数据库、多模态组学、多组学融合、开发标准化验证模型的未来发展方向。通过技术创新与临床实践并重，影像组学有望推动PCa诊疗向动态精准医学范式转变，最终实现患者生存获益的全面提升。

关键词: 前列腺癌, 影像组学, MRI, 深度学习, 精准诊疗, 进展