Liang Zi-Chun, Sun Chao, Chen Ming
Department of Urology, Zhongda Hospital Affiliated to Southeast University, Nanjing, Jiangsu 210096, China.
Zhonghua Nan Ke Xue. 2024 Jan;30(1):60-65.
Prostate cancer (PCa) is the second most common cancer worldwide and the fifth leading cause of cancer deaths in men. Magnetic resonance imaging (MRI), with its high sensitivity and specificity in detecting PCa, is currently the most widely used imaging technique for tumor localization and staging. MRI plays a significant role in risk stratification of patients with neoplasm, surveillance of low-risk patients, and monitoring of recurrence after treatment. Radiomics is an emerging and promising tool that allows quantitative assessment of tumors in images by converting digital images into mineable high-dimensional data. Imaging histology aims to increase the number of features that can be used to detect PCa, avoid unnecessary biopsies, determine tumor aggressiveness and monitor recurrence after treatment. Artificial intelligence integration of imaging histology data, including those of different imaging modalities (e.g., PET-CT) as well as other clinical and histopathological data, can improve the prediction of tumor aggressiveness and guide clinical decision-making and patient management. The aim of this review is to present current research applications of AI-assisted radiomics in PCa MRI images.
前列腺癌（PCa）是全球第二常见的癌症，也是男性癌症死亡的第五大主要原因。磁共振成像（MRI）在检测PCa方面具有高灵敏度和特异性，是目前用于肿瘤定位和分期的最广泛使用的成像技术。MRI在肿瘤患者的风险分层、低风险患者的监测以及治疗后复发的监测中发挥着重要作用。放射组学是一种新兴且有前景的工具，它通过将数字图像转换为可挖掘的高维数据，实现对图像中肿瘤的定量评估。影像组织学旨在增加可用于检测PCa的特征数量，避免不必要的活检，确定肿瘤侵袭性并监测治疗后的复发情况。将影像组织学数据与人工智能相结合，包括不同成像模态（如PET-CT）的数据以及其他临床和组织病理学数据，可以改善对肿瘤侵袭性的预测，并指导临床决策和患者管理。本综述的目的是介绍人工智能辅助放射组学在PCa MRI图像中的当前研究应用。
