北京生物医学工程2025，Vol.44Issue(5)：524-531,8.DOI:10.3969/j.issn.1002-3208.2025.05.012
基于多参数磁共振成像和深度学习的前列腺癌辅助诊断研究进展
Advancements in prostate cancer assisted diagnosis based on MP-MRI and deep learning
摘要
Abstract
Prostate cancer is a common malignant tumor in the male reproductive system.The complex structure of the prostate makes the diagnosis of prostate cancer extremely challenging.In recent years,scholars at home and abroad have conducted a number of studies on the auxiliary diagnosis methods of prostate cancer based on deep learning,aiming to improve the accuracy and efficiency of prostate cancer diagnosis.Therefore,this article reviews the related studies in order to provide reference for further research on the auxiliary diagnosis of prostate cancer.Firstly,the common multi-parametric magnetic resonance imaging(MP-MRI)sequences are summarized,and the application value of different sequence combinations in the auxiliary diagnosis of prostate cancer is discussed.Secondly,this paper focuses on the deep learning-assisted prostate cancer diagnosis algorithms,including prostate segmentation and prostate cancer detection,segmentation and grading.Finally,the deep learning models in the relevant literature were summarized and the future research directions were prospected.Studies have shown that deep learning has shown great advantages in the auxiliary diagnosis of prostate cancer and has certain clinical practicability.In the future,we should continue to study higher order deep learning algorithms to fully explore its potential and clinical application value in the auxiliary diagnosis of prostate cancer,and provide a basis for the realization of integrated treatment.关键词
多参数磁共振成像/深度学习/前列腺癌辅助诊断/前列腺癌Key words
multiparametric magnetic resonance imaging/deep learning/prostate cancer auxiliary diagnosis/prostate cancer分类
医药卫生引用本文复制引用
王蕾,孙榕,贾守强,聂生东..基于多参数磁共振成像和深度学习的前列腺癌辅助诊断研究进展[J].北京生物医学工程,2025,44(5):524-531,8.基金项目
国家自然科学基金重点项目(81830052)、上海市自然科学基金(20ZR1438300)资助 （81830052）
