[1]蒋家良,罗勇,何奕松,等.特征区域再聚焦提升全卷积神经网络勾画较小靶区准确度[J].中国医学物理学杂志,2020,37(1):75-78.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.015]
 JIANG Jialiang,LUO Yong,HE Yisong,et al.Feature area refocusing for improving the accuracy of small target area segmentations by fully convolutional networks[J].Chinese Journal of Medical Physics,2020,37(1):75-78.[doi:DOI:10.3969/j.issn.1005-202X.2020.01.015]
点击复制

特征区域再聚焦提升全卷积神经网络勾画较小靶区准确度()
分享到:

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
37
期数:
2020年第1期
页码:
75-78
栏目:
医学影像物理
出版日期:
2020-01-25

文章信息/Info

Title:
Feature area refocusing for improving the accuracy of small target area segmentations by fully convolutional networks
文章编号:
1005-202X(2020)01-0075-04
作者:
蒋家良罗勇何奕松余行傅玉川
四川大学华西医院放疗科, 四川 成都 610041
Author(s):
JIANG Jialiang LUO Yong HE Yisong YU Hang FU Yuchuan
Department of Radiotherapy, West China Hospital, Sichuan University, Chengdu 610041, China
关键词:
鼻咽癌肿瘤体积靶区勾画卷积神经网络注意力机制
Keywords:
Keywords: nasopharyngeal carcinoma tumor volume segmentation of target area convolutional neural network attention mechanism
分类号:
R739.6;R319
DOI:
DOI:10.3969/j.issn.1005-202X.2020.01.015
文献标志码:
A
摘要:
在卷积神经网络基础之上介绍一种特征区域再聚焦的勾画方法。方法:利用端到端的全卷积神经网络,采用正常勾画及特征区域再聚焦勾画两种方法分别对鼻咽癌肿瘤体积(GTVnx)进行自动勾画。选取60例鼻咽癌患者数据,其中40例用于训练,20例用于测试。Dice相似系数(DSC)用于评估自动勾画准确度。结果:正常勾画方法DSC为0.352±0.084,特征区域再聚焦方法DSC为0.524±0.079。对20例测试例勾画结果进行统计学检验结果显示P<0.01。结论:相比正常勾画方法,特征再聚焦勾画方法能够提高对GTVnx的勾画效果,提升较小靶区的勾画精度。
Abstract:
Abstract: Objective To propose a feature area refocusing method based on convolutional neural networks (CNN) for improving the accuracy of small target area segmentations. Methods End-to-end fully convolutional networks (FCN) was used to automatically segment nasopharynx gross tumor volume (GTVnx) by conventional segmentation method and feature area refocusing method. Sixty cases of nasopharyngeal carcinoma were analyzed in the study, with 40 cases for training and 20 cases for testing. Dice similarity coefficient (DSC) was used to evaluate the accuracy of automatic segmentation. Results The DSC obtained by conventional segmentation method was 0.352±0.084, lower than 0.524±0.079 which was obtained by feature area refocusing method. Statistical analysis of 20 test cases showed that the P value was less than 0.01. Conclusion Compared with conventional segmentation method, the feature area refocusing method for segmentation can achieve a better GTVnx segmentation result and improve the accuracy of small target area segmentation.

相似文献/References:

[1]陈广涛,汪 淇,刘亚强,等.TrueBeam加速器射野准直器跟随功能在鼻咽癌固定野调强放疗和容积旋转调强放疗中的应用[J].中国医学物理学杂志,2014,31(03):4865.[doi:10.3969/j.issn.1005-202X.2014.03.005]
[2]潘宇辉,陈榕钦,柏朋刚,等.鼻咽癌调强放射治疗前后腮腺体积及空间几何位置变化研究[J].中国医学物理学杂志,2014,31(05):5120.[doi:10.3969/j.issn.1005-202X.2014.05.005]
[3]张俊俊,邱小平,李奇欣,等.ArcCheck系统在鼻咽癌容积旋转调强剂量验证中的应用[J].中国医学物理学杂志,2014,31(05):5136.[doi:10.3969/j.issn.1005-202X.2014.05.009]
[4]桑 勇,陈维军,狄小云,等.多叶光栅叶片宽度对鼻咽癌剂量学的影响[J].中国医学物理学杂志,2014,31(06):5240.[doi:10.3969/j.issn.1005-202X.2014.06.004]
[5]黄利生,庄婷婷,伍方财,等.鼻咽癌调强放疗Ib区剂量分析[J].中国医学物理学杂志,2014,31(06):5265.[doi:10.3969/j.issn.1005-202X.2014.06.010]
[6]易金玲,金献测,周永强,等.鼻咽癌IMRT与VMAT治疗的计划与剂量验证比较研究[J].中国医学物理学杂志,2013,30(01):3859.[doi:10.3969/j.issn.1005-202X.2013.01.006]
[7]金献测,易金玲,周永强,等.鼻咽癌同步加量调强放射治疗新的计划质量评估指标研究[J].中国医学物理学杂志,2013,30(02):3978.[doi:10.3969/j.issn.1005-202X.2013.02.004]
[8]蒋晓芹,段宝风,艾平,等.基于图谱库的自动轮廓勾画软件(ABAS)在鼻咽癌调强放疗中的应用[J].中国医学物理学杂志,2013,30(02):3997.[doi:10.3969/j.issn.1005-202X.2013.02.008]
[9]张达光,蒋胜鹏,李智华,等.鼻咽癌调强放疗中解剖结构改变及剂量分布变化的研究[J].中国医学物理学杂志,2013,30(04):4239.[doi:10.3969/j.issn.1005-202X.2013.04.006]
[10]杨海燕,王军良,周振山,等.AAA算法和PBC算法在鼻咽癌调强放疗中剂量分布的比较[J].中国医学物理学杂志,2013,30(04):4245.[doi:10.3969/j.issn.1005-202X.2013.04.008]

备注/Memo

备注/Memo:
【收稿日期】2019-06-15 【作者简介】蒋家良,在读硕士,研究方向:肿瘤放射治疗技术,E-mail: 2760663011@qq.com 【通信作者】傅玉川,博士,主任技师,研究方向:医学物理,E-mail: ychfu@hotmail.com
更新日期/Last Update: 2020-01-14