[an error occurred while processing this directive]
中华放射肿瘤学杂志
   2025年4月7日 星期一     首 页 |  期刊介绍  |  编 委 会  |  投稿指南  |  期刊订阅  |  广告合作  |  学术影响  |  收录情况  |  联系我们  |  English
中华放射肿瘤学杂志  2020, Vol. 29 Issue (5): 374-368    DOI: 10.3760/cma.j.cn113030-20190102-00011
物理·生物·技术 最新目录| 下期目录| 过刊浏览| 高级检索 [an error occurred while processing this directive]|[an error occurred while processing this directive]
基于卷积神经网络的直肠癌靶区及危及器官自动勾画
夏祥, 王佳舟, 杨立峰, 章真, 胡伟刚
复旦大学附属肿瘤医院放射治疗科 复旦大学上海医学院肿瘤学系 200032
Automatic delineation of rectal cancer target volume and organs at risk based on convolutional neural network
Xia Xiang, Wang Jiazhou, Yang Lifeng, Zhang Zhen, Hu Weigang
Department of Radiotherapy, Cancer Hospital, Fudan University;Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, China
全文: PDF (0 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      背景资料
摘要 目的 实现直肠癌靶区和正常组织的自动勾画,提高临床工作效率。 方法 采用基于卷积神经网络的深度学习方法,架构神经网络,学习并实现自动勾画,比较自动勾画与人工勾画的差异。结果 210例直肠癌患者随机分组为190例训练集,20例验证集。测量单个患者完整勾画耗时约10s,CTV的平均Dice为0.87±0.04,其余正常组织的平均Dice均>0.8,CTV的HD指数为25.33±16.05,MDA指数为3.07±1.49,JSC指数为0.77±0.07。结论 使用基于全卷积神经网络的深度学习方法可以实现直肠癌靶区的自动勾画,提高工作效率。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
夏祥
王佳舟
杨立峰
章真
胡伟刚
关键词 自动勾画全卷积神经网络直肠癌    
AbstractObjective To realize automatic delineation of rectal cancer target volume and normal tissues and improve clinical work efficiency. Methods The deep learning method based on convolutional neural network was adopted to construct neural network, learn and realize automatic delineation, and compare the differences between automatic delineation and manual delineation. Results Two hundred and ten caseswith rectal cancer were randomly assigned to a training set of 190 and a validation set of 20. The complete delineation of a single case took about 10s;the average Dice of CTV was 0.87±0.04;the average Dice of other normal tissues was bigger than 0.8;the Hausdorff distance (HD) index of CTV was 25.33±16.05;the mean distance to agreement (MDA) index was 3.07±1.49, and the Jaccard similarity coefficient (JSC) index was 0.77±0.07. Conclusion The deep learning method based on full convolutional neural network can realize the automatic delineation of rectal cancer target volume and improve work efficiency.
Key wordsAutomatic delineation    Full convolutional neural networks    Rectal cancer   
收稿日期: 2019-01-02     
通讯作者: 王佳舟,Email:wjiazhou@126.com   
引用本文:   
夏祥,王佳舟,杨立峰等. 基于卷积神经网络的直肠癌靶区及危及器官自动勾画[J]. 中华放射肿瘤学杂志, 2020, 29(5): 374-368.
Xia Xiang,Wang Jiazhou,Yang Lifeng et al. Automatic delineation of rectal cancer target volume and organs at risk based on convolutional neural network[J]. Chinese Journal of Radiation Oncology, 2020, 29(5): 374-368.
链接本文:  
http://journal12.magtechjournal.com/Jweb_fszlx/CN/10.3760/cma.j.cn113030-20190102-00011     或     http://journal12.magtechjournal.com/Jweb_fszlx/CN/Y2020/V29/I5/374
京公网安备11010502022167号
版权所有 © 2010《中华放射肿瘤学杂志》编辑部
地址:北京朝阳区潘学园南里17号 中国医学科学院肿瘤医院(100021)
电话:010-67700737,87788294 Email: cjron@cmaph.org
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:Support@magtech.com.cn