深度学习在近距离放射治疗中的应用  

Application of deep learning in brachytherapy

作　　者：曹德政 倪昕晔 Cao Dezheng;Ni Xinye(Department of Radiotherapy,Changzhou Second Peope's Hospital,Nanjing Medical University/Jiangsu Province Engineering Research Center of Medical Physics/Center of Medical Physics,Nanjing Medical University/Changzhou Key Laboratory of Medical Physics,Changzhou 213003,China)

机构地区：[1]南京医科大学附属常州第二人民医院放疗科/江苏省医学物理工程研究中心/南京医科大学医学物理中心实验室/常州市医学物理重点实验室,常州213003

出　　处：《中华放射肿瘤学杂志》2024年第8期778-783,共6页Chinese Journal of Radiation Oncology

基　　金：国家自然科学基金面上项目(62371243);江苏省重点研发计划社会发展项目(BE2022720);江苏省自然科学基金面上项目(BK20231190);常州市社会发展项目(CE20235063)。

摘　　要：近距离放射治疗是与外部放射治疗相对应的一种放疗方式,因其可以对病灶区域实现更高的放射剂量并更好地保护危及器官而得到广泛应用。但近距离放射治疗工作流程耗时较长,可能会造成患者的不适、施源器或插值针的位移、器官的变化。近年来,深度学习技术在医学领域取得了巨大的成功,为实现近距离放射治疗自动化、提高放疗精度、确保放疗计划安全有效提供了新的思路。本文综述了深度学习在近距离放射治疗中的分割、图像配准、施源器重建、剂量预测和计划优化以及质量保证方面的研究进展,以供临床工作参考。Brachytherapy is a kind of radiation therapy corresponding to external radiation therapy,i.It has been widely used because it can achieve a higher radiation dose to the lesion area and better protect to the organs at risk.However,tThe workflow of brachytherapy is time-consuming and may lead to patient discomfort,displacement of the applicator or interstitial needle,and organ changes.In recent years,deep learning technology has achieved significant success in the medical field,offering new avenues for the automation of brachytherapy,improvement of radiotherapy precision,and ensuring the safety and effectiveness of radiotherapy plans.This review summarizes the research progress of deep learning in the context of brachytherapy segmentation,image registration,applicator reconstruction,dose prediction and planning optimization,and quality assurance for clinical research reference.

关 键 词：近距离放射疗法 深度学习 放射疗法 图像引导 人工智能 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] R730.55[自动化与计算机技术—控制科学与工程]