| 摘要: |
| 前列腺癌（PCa）是世界上最常见的肿瘤之一。多参数磁共振成像（mpMRI）作为一种非侵入性工具，可以改善前列腺病变的检测、分类和体积量化。机器学习是人工智能（AI）的一个分支，能够快速、准确地分析mpMRI图像，在识别前列腺病变方面有较好的一致性，能够加强PCa的标准化管理，已经成为提高放射科医师诊断效率和准确度的工具。本文总结了AI在前列腺mpMRI中的应用，主要包括前列腺分割，病变检测、分割，以及病变分类表征等，并对未来发展进行了展望。 |
| 关键词: 前列腺肿瘤 多参数磁共振成像 机器学习 人工智能 神经网络 |
| DOI：10.16781/j.CN31-2187/R.20210040 |
| 投稿时间：2021-01-15修订日期：2021-05-07 |
| 基金项目:国家临床重点专科军队建设项目（总后卫生部），上海市卫生和计划生育委员会面上项目（M20140149）. |
|
| Artificial intelligence in multi-parameter magnetic resonance imaging of the prostate:application and prospect |
| XING Peng-yi,MENG Ying-hao,YANG Qing-song,CHEN Wei* |
(Department of Radiology, The First Affiliated Hospital of Naval Medical University (Second Military Medical University), Shanghai 200433, China
*Corresponding author) |
| Abstract: |
| Prostate cancer is one of the most common tumors in the world. Multi-parameter magnetic resonance imaging (mpMRI) as a non-invasive tool, can improve the detection, classification and volume quantification of prostate lesions. Machine learning is a branch of artificial intelligence (AI). It can quickly and accurately analyze mpMRI images, has good consistency in identifying prostate lesions, and can strengthen the standardized management of prostate cancer. It has become a tool for improving the diagnostic efficiency and accuracy of radiologists. This review summarizes the application of AI in mpMRI of the prostate (mainly including prostate segmentation, lesion detection and segmentation, and lesion feature description) and its development in the future. |
| Key words: prostatic neoplasms multi-parameter magnetic resonance imaging machine learning artificial intelligence neural network |
