基于深度学习方法的伪CT图像合成技术研究及在放疗中的应用进展  

Research on pseudo CT image synthesis technology based on deep learning method and its application in radiotherapy

作　　者：孙鸿飞 倪昕晔 杨建华[1] Sun Hongfei;Ni Xinye;Yang Jianhua(School of Automation,Northwest Polytechnic University,Xi'an 710072,China;Department of Radiation Oncology,Affiliated Changzhou No.2 People's Hospital of Nanjing Medical University,Center for Medical Physics,Nanjing Medical University,Changzhou 213003,China)

机构地区：[1]西北工业大学自动化学院,西安710072 [2]南京医科大学附属常州第二人民医院放疗科南京医科大学医学物理研究中心,213003

出　　处：《中华放射医学与防护杂志》2021年第3期222-228,共7页Chinese Journal of Radiological Medicine and Protection

摘　　要：随着医学图像合成任务复杂度的提高和对临床放疗精度的需求,深度学习算法在伪CT图像合成与分析中的角色越发重要。本文根据图像的模态种类对基于深度学习方法下的伪CT图像合成技术进行归类与分析,并介绍其在放疗应用中的最新进展。With the improvement of the complexity of medical image synthesis and the demand for the accuracy of clinical radiotherapy,deep learning algorithm plays an increasingly important role in pseudo CT image synthesis and analysis.This paper classifies and analyzes the pseudo CT image synthesis technology based on deep learning method in terms of the types of image modes,and describes the ongoing application in radiotherapy.

关 键 词：深度学习 伪CT 图像引导放疗 

分 类 号：R730.55[医药卫生—肿瘤] TP18[医药卫生—临床医学] TP391.41[自动化与计算机技术—控制理论与控制工程]