[1]王沛沛,李金凯,李彩虹,等.基于人工智能技术的危及器官自动勾画在胸部肿瘤中的应用[J].中国医学物理学杂志,2019,36(11):1346-1349.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.019]
　WANG Peipei,LI Jinkai,LI Caihong,et al.Application of automatic organs-at-risk segmentation based on artificial intelligence technology in thoracic tumors[J].Chinese Journal of Medical Physics,2019,36(11):1346-1349.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.019]
点击复制

基于人工智能技术的危及器官自动勾画在胸部肿瘤中的应用()
分享到：

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

卷:
36卷
期数:
2019年第11期
页码:
1346-1349
栏目:
其他（激光医学等）
出版日期:
2019-11-25

文章信息/Info

Title:
Application of automatic organs-at-risk segmentation based on artificial intelligence technology in thoracic tumors
文章编号:
1005-202X（2019）11-1346-04
作者:
王沛沛; 李金凯; 李彩虹; 昌志刚; 顾宵寰; 曹远东
江苏省人民医院放射治疗中心， 江苏 南京 210029
Author(s):
WANG Peipei;  LI Jinkai;  LI Caihong;  CHANG Zhigang;  GU Xiaohuan;  CAO Yuandong
Center of Radiation Oncology, Jiangsu Province Hospital, Nanjing 210029, China
关键词:
胸部肿瘤; 人工智能; 危及器官; 自动勾画; 放射治疗
Keywords:
thoracic tumor;  artificial intelligence;  organs-at-risk;  automatic segmentation;  radiotherapy
分类号:
R312；R811.1
DOI:
DOI:10.3969/j.issn.1005-202X.2019.11.019
文献标志码:
A
摘要:
目的：评估基于人工智能技术的自动勾画软件勾画胸部危及器官轮廓的几何学精度，为临床应用提供依据。方法：选择30例胸部肿瘤患者的CT图像，分别使用基于人工智能技术的自动勾画软件勾画和医师手动勾画胸部危及器官。采用Hausdorff距离、形状相似性指数及Jaccard系数这3个指标评价自动勾画与手动勾画危及器官的几何学一致性。结果：在肺、心脏和脊髓的Hausdorff距离中，最大为右肺的（22.31±4.50） mm，最小为脊髓的（3.17±0.80） mm。危及器官的形状相似性指数值均≥0.91。Jaccard系数中左肺和右肺的均值≥0.95，脊髓的为0.84±0.02，心脏的略低为0.83±0.04。结论：基于人工智能技术的危及器官自动勾画软件对于胸部危及器官勾画能够达到较高的准确性和精度，可以满足临床工作。 【关键词】胸部肿瘤；人工智能；危及器官；自动勾画；放射治疗
Abstract:
Objective To evaluate the geometric accuracy of automatic segmentation software based on artificial intelligence technology for segmenting the organs-at-risk (OAR) in patients with thoracic tumors, so as to provide a basis for its clinical application. Methods A total of 30 patients with thoracic tumors were enrolled in the study, and the thoracic OAR was automatically delineated by segmentation software and manually segmented by physicians. Three evaluation indexes, namely Hausdorff distance, Dice similarity coefficient and Jaccard coefficient, were used to evaluate the geometric consistency between automatic segmentation and manual segmentation. Results Among the Hausdorff distances of lung-L, lung-R, heart and spinal cord, the maximum Hausdorff distance was (22.31±4.50) mm in lung-R, and the minimum was (3.17±0.80) mm in spinal cord. The Dice similarity coefficient of all OAR (lung-L, lung-R, heart, spinal cord) was not less than 0.91. The mean value of Jaccard coefficient in lung-L and lung-R were greater than or equal to 0.95, while that in spinal cord and heart was 0.84±0.02 and 0.83±0.04, respectively. Conclusion The automatic segmentation software based on artificial intelligence technology can achieve a high accuracy and precision in thoracic OAR segmentation, which can meet the needs of clinical practices.

相似文献/References:

[1]王弈,李传富.人工智能方法在医学图像处理中的研究新进展[J].中国医学物理学杂志,2013,30(03):4138.[doi:10.3969/j.issn.1005-202X.2013.03.013]
[2]李桢,洪文松,周凌宏.CT定位增强扫描对胸部肿瘤放疗剂量分布的影响[J].中国医学物理学杂志,2015,32(04):563.[doi:10.3969/j.issn.1005-202X.2015.04.024]
　[J].Chinese Journal of Medical Physics,2015,32(11):563.[doi:10.3969/j.issn.1005-202X.2015.04.024]
[3]王亚,李永欣,黄文华.人类脑计划的研究进展[J].中国医学物理学杂志,2016,33(2):109.[doi:10.3969/j.issn.1005-202X.2016.02.001]
　[J].Chinese Journal of Medical Physics,2016,33(11):109.[doi:10.3969/j.issn.1005-202X.2016.02.001]
[4]柏晗,等.基于四维CT下胸部肿瘤调强计划中心脏和食道的剂量评估[J].中国医学物理学杂志,2016,33(3):293.[doi:DOI:10.3969/j.issn.1005-202X.2016.03.015]
　[J].Chinese Journal of Medical Physics,2016,33(11):293.[doi:DOI:10.3969/j.issn.1005-202X.2016.03.015]
[5]张广鹏,杨波,庞皓文,等. 胸部肿瘤内外照射方式的靶区剂量分布和肺受照剂量[J].中国医学物理学杂志,2017,34(6):570.[doi:DOI:10.3969/j.issn.1005-202X.2017.06.006]
　[J].Chinese Journal of Medical Physics,2017,34(11):570.[doi:DOI:10.3969/j.issn.1005-202X.2017.06.006]
[6]祁红琳,胡先玲,李传明,等. 基于MRI纹理特征的早期肝癌术后复发预测[J].中国医学物理学杂志,2017,34(9):908.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.010]
　[J].Chinese Journal of Medical Physics,2017,34(11):908.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.010]
[7]邵凯南,翁邓胡,李玉成,等. 基于Python脚本的RayStation治疗计划系统逆向调强放疗计划半自动设计[J].中国医学物理学杂志,2018,35(2):156.[doi:DOI:10.3969/j.issn.1005-202X.2018.02.007]
　SHAO Kainan,WENG Denghu,LI Yucheng,et al. Semi-automatic design of inverse intensity-modulated radiotherapy treatment plans based on Python scripts in RayStation treatment planning system[J].Chinese Journal of Medical Physics,2018,35(11):156.[doi:DOI:10.3969/j.issn.1005-202X.2018.02.007]
[8]何亚男,罗焕丽,靳富,等. 不同重建方式下CT层厚对胸部肿瘤体积和剂量的影响[J].中国医学物理学杂志,2018,35(3):249.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.001]
　HE Yanan,LUO Huanli,JIN Fu,et al. Effects of computed tomography slice thickness on clinical target volume and dose in intensity-modulated radiotherapy for chest cancer based on different reconstruction methods[J].Chinese Journal of Medical Physics,2018,35(11):249.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.001]
[9]姚雷,夏兵,曾程,等. 不同计划系统胸部肿瘤物理剂量参数比较与分析[J].中国医学物理学杂志,2018,35(5):526.[doi:DOI:10.3969/j.issn.1005-202X.2018.05.006]
　YAO Lei,XIA Bing,ZENG Cheng,et al. Comparison and analysis of physical dose parameters between two different planning systems for radiotherapy in thoracic cancer[J].Chinese Journal of Medical Physics,2018,35(11):526.[doi:DOI:10.3969/j.issn.1005-202X.2018.05.006]
[10]纪春阳,徐秀林,王燕. 深度神经网络技术在肿瘤细胞识别中的应用[J].中国医学物理学杂志,2019,36(9):1113.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.022]
　JI Chunyang,XU Xiulin,WANG Yan. Application of deep neural network in tumor cell recognition[J].Chinese Journal of Medical Physics,2019,36(11):1113.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.022]

备注/Memo

备注/Memo:
【收稿日期】2019-06-19 【基金项目】国家自然科学基金（81672983） 【作者简介】王沛沛，研究生，主管技师，研究方向：医学物理，E-mail: wangpeipei5650@163.com 【通信作者】曹远东，博士，主任医师，研究方向：放射肿瘤学，E-mail: caoyuandong@jsph.org.cn
更新日期/Last Update: 2019-11-28