[1]吴传锋,金鑫妍,白司悦,等.基于U-Net结合改进算法对放疗危及器官自动勾画研究[J].中国医学物理学杂志,2023,40(3):303-312.[doi:DOI:10.3969/j.issn.1005-202X.2023.03.008]
　WU Chuanfeng,JIN Xinyan,BAI Siyue,et al.Auto-segmentation of organs-at-risk for radiotherapy using U-Net combined with improved algorithms[J].Chinese Journal of Medical Physics,2023,40(3):303-312.[doi:DOI:10.3969/j.issn.1005-202X.2023.03.008]
点击复制

基于U-Net结合改进算法对放疗危及器官自动勾画研究()
分享到：

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

卷:
40卷
期数:
2023年第3期
页码:
303-312
栏目:
医学放射物理
出版日期:
2023-03-29

文章信息/Info

Title:
Auto-segmentation of organs-at-risk for radiotherapy using U-Net combined with improved algorithms
文章编号:
1005-202X（2023）03-0303-10
作者:
吴传锋1; 金鑫妍2; 白司悦2; 葛云2; 周俊东1; 胡睿1; 陈颖2; 王东燕1
1.南京医科大学附属苏州医院放疗科， 江苏 苏州 215000； 2.南京大学电子科学与工程学院， 江苏 南京 210023
Author(s):
WU Chuanfeng1;  JIN Xinyan2;  BAI Siyue2;  GE Yun2;  ZHOU Jundong1;  HU Rui1;  CHEN Ying2;  WANG Dongyan1
1. Department of Radiation Oncology, the Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou 215000, China 2. School of Electronic Science and Engineering, Nanjing University, Nanjing 210023, China
关键词:
深度学习; 自动勾画; 肝脏; 危及器官; U-Net
Keywords:
Keywords: deep learning auto-segmentation liver organs-at-risk U-Net
分类号:
R318；R811.1
DOI:
DOI:10.3969/j.issn.1005-202X.2023.03.008
文献标志码:
A
摘要:
目的：面向放疗危及器官自动勾画构建基于U-Net的模型并针对肝脏分割构建3种改进模型。方法：采集共计184例肝癌患者和183例头部放疗患者的计算机断层扫描（CT）图像及组织结构信息，并结合公开数据集Sliver07用于模型的训练与评估。通过搭建U-Net模型并针对肝脏分割分别结合空洞卷积、SLIC超像素算法、区域生长算法进行训练并得到预测模型，利用预测模型对自动勾画结果进行预测。采用交并比（IoU）和平均交并比（MIoU）评价预测结果的精确性。结果：测试集头部放疗危及器官自动勾画预测结果MIoU为0.795~0.970，肝脏分割使用U-Net预测结果MIoU约为0.876，使用改进后模型预测结果MIoU约为0.888，并很好地约束了预测偏差较大结果的出现，使得测试样本中IoU结果小于0.8的数量占比从16.67%降至7.5%。直观勾画方面结合改进算法的模型比U-Net更能捕捉到复杂、混淆性的边界区域。结论：构建U-Net模型能够在头部放疗危及器官和肝脏自动勾画上表现良好，3种改进的模型能够在肝脏分割上具有更优的表现。
Abstract:
Abstract: Objective To develop a model based on U-Net for the auto-segmentation of organs-at-risk, and to propose 3 improved models for automated liver segmentation. Methods The CT images and tissue structure data of 184 patients with liver cancer and 183 patients receiving head radiotherapy were collected and combined with the public dataset Sliver07 for the training and evaluation of the models. The established U-Net model and 3 models combined with dilated convolution, SLIC super-pixel algorithm and region growing algorithm, respectively, were trained for obtaining prediction models which were then used for the prediction of auto-segmentation results. The segmentation accuracy was evaluated using intersection over union (IoU) and mean intersection over union (MIoU). Results For the test set, the MIoU of the U-Net model for OAR segmentation in head radiotherapy ranged from 0.795 to 0.970 and for the liver segmentation was around 0.876. The improved model for automated liver segmentation improved the MIoU to 0.888 and restricted the occurrence of large prediction deviations, which reduced the proportion of IoU less than 0.8 in the test samples from 16.67% to 7.50%. Visually, the models combined with improved algorithms could capture more complex and confusing boundary areas than U-Net. Conclusion The established U-Net performed well in the auto-segmentations of liver and organs-at-risk for head radiotherapy, and the 3 improved models can obtain better results in liver segmentation.

相似文献/References:

[1]张艺宝,吴昊,李莎,等.临床前验证与几何对比分析基于图谱库的危及器官自动勾画[J].中国医学物理学杂志,2015,32(06):761.[doi:doi:10.3969/j.issn.1005-202X.2015.06.001]
　[J].Chinese Journal of Medical Physics,2015,32(3):761.[doi:doi:10.3969/j.issn.1005-202X.2015.06.001]
[2]陶源,王佳飞,杜俊龙,等.基于卷积神经网络的细胞识别[J].中国医学物理学杂志,2017,34(1):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
　[J].Chinese Journal of Medical Physics,2017,34(3):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
[3]门阔,戴建荣. 利用深度反卷积神经网络自动勾画放疗危及器官[J].中国医学物理学杂志,2018,35(3):256.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.002]
　MEN Kuo,DAI Jianrong. Automatic segmentation of organs at risk in radiotherapy using deep deconvolutional neural network[J].Chinese Journal of Medical Physics,2018,35(3):256.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.002]
[4]邓金城,彭应林,刘常春,等. 深度卷积神经网络在放射治疗计划图像分割中的应用[J].中国医学物理学杂志,2018,35(6):621.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.001]
　DENG Jincheng,PENG Yinglin,LIU Changchun,et al. Application of deep convolution neural network in radiotherapy planning image segmentation[J].Chinese Journal of Medical Physics,2018,35(3):621.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.001]
[5]查雪帆,杨丰,吴俣南,等. 结合迁移学习与深度卷积网络的心电分类研究[J].中国医学物理学杂志,2018,35(11):1307.[doi:DOI:10.3969/j.issn.1005-202X.2018.11.013]
　ZHA Xuefan,YANG Feng,WU Yunan,et al. ECG classification based on transfer learning and deep convolution neural network[J].Chinese Journal of Medical Physics,2018,35(3):1307.[doi:DOI:10.3969/j.issn.1005-202X.2018.11.013]
[6]宫进昌,赵尚义,王远军. 基于深度学习的医学图像分割研究进展[J].中国医学物理学杂志,2019,36(4):420.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.010]
　GONG Jinchang,ZHAO Shangyi,WANG Yuanjun.Research progress on deep learning-based medical image segmentation[J].Chinese Journal of Medical Physics,2019,36(3):420.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.010]
[7]安莹,黄能军,杨荣,等. 基于深度学习的心血管疾病风险预测模型[J].中国医学物理学杂志,2019,36(9):1103.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.021]
　AN Ying,HUANG Nengjun,YANG Rong,et al. Deep learning-based model for risk prediction of cardiovascular diseases[J].Chinese Journal of Medical Physics,2019,36(3):1103.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.021]
[8]王金媛,徐寿平,杨微,等.算法和匹配数目对宫颈癌危及器官自动勾画的影响[J].中国医学物理学杂志,2019,36(11):1243.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.001]
　WANG Jinyuan,XU Shouping,YANG Wei,et al.Effects of algorithm and matching number on the auto-segmentation of organs-at-risk in patients with cervical cancer[J].Chinese Journal of Medical Physics,2019,36(3):1243.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.001]
[9]徐航,随力,张靖雯,等.卷积神经网络在医学图像分割中的研究进展[J].中国医学物理学杂志,2019,36(11):1302.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.011]
　XU Hang,SUI Li,ZHANG Jingwen,et al.Progress on convolutional neural network in medical image segmentation[J].Chinese Journal of Medical Physics,2019,36(3):1302.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.011]
[10]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.[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(3):1346.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.019]
[11]张富利,崔德琪,王秋生,等.基于深度学习和图谱库方法自动勾画肿瘤放疗中危及器官的比较[J].中国医学物理学杂志,2019,36(12):1486.[doi:DOI:10.3969/j.issn.1005-202X.2019.12.024]
　ZHANG Fuli,CUI Deqi,WANG Qiusheng,et al.Comparative study of deep learning- versus Atlas-based auto-segmentation of organs-at-risk in tumor radiotherapy[J].Chinese Journal of Medical Physics,2019,36(3):1486.[doi:DOI:10.3969/j.issn.1005-202X.2019.12.024]
[12]汪志,常艳奎,吴昊天,等.基于深度学习的危及器官自动勾画软件系统DeepViewer在放疗中的应用及评估[J].中国医学物理学杂志,2020,37(8):1071.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.025]
　WANG Zhi,CHANG Yankui,et al.Application and evaluation of deep learning-based DeepViewer system for automatic segmentation of organs-at-risk[J].Chinese Journal of Medical Physics,2020,37(3):1071.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.025]
[13]时飞跃,王敏,赵紫婷,等.基于深度学习的rtStation软件自动勾画乳腺癌术后患者心脏结构的应用分析[J].中国医学物理学杂志,2021,38(6):661.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.001]
　SHI Feiyue,WANG Min,et al.Application analysis of deep learning-based rtStation software in automatic delineation of the heart in patients after surgery for breast cancer[J].Chinese Journal of Medical Physics,2021,38(3):661.[doi:DOI:10.3969/j.issn.1005-202X.2021.06.001]
[14]宋威,鹿红,马珺,等.金属伪影对鼻咽癌放疗危及器官自动勾画的影响[J].中国医学物理学杂志,2021,38(10):1185.[doi:DOI:10.3969/j.issn.1005-202X.2021.10.001]
　SONG Wei,LU Hong,MA Jun,et al.Effects of metal artifacts on automatic segmentation of organs-at-risk in patients receiving radiotherapy for nasopharyngeal carcinoma[J].Chinese Journal of Medical Physics,2021,38(3):1185.[doi:DOI:10.3969/j.issn.1005-202X.2021.10.001]
[15]张瑞萍,刘应龙,张文静,等.基于人工智能的多模态影像辅助海马体自动勾画研究[J].中国医学物理学杂志,2022,39(3):390.[doi:DOI:10.3969/j.issn.1005-202X.2022.03.021]
　ZHANG Ruiping,LIU Yinglong,ZHANG Wenjing,et al.Auto-segmentation of the hippocampus in multimodal image using artificial intelligence[J].Chinese Journal of Medical Physics,2022,39(3):390.[doi:DOI:10.3969/j.issn.1005-202X.2022.03.021]
[16]张丹凤,蒋俊,吴昊天,等.基于nnU-Net的宫颈癌近距离治疗中高危临床靶区及危及器官的自动勾画[J].中国医学物理学杂志,2023,40(12):1463.[doi:DOI:10.3969/j.issn.1005-202X.2023.12.003]
　ZHANG Danfeng,JIANG Jun,WU Haotian,et al.Auto-segmentation of high-risk clinical target volume and organs-at-risk for brachytherapy of cervical cancer based on nnUNet[J].Chinese Journal of Medical Physics,2023,40(3):1463.[doi:DOI:10.3969/j.issn.1005-202X.2023.12.003]
[17]胡兴刚,王娴,张扬,等.基于深度学习算法的自动勾画系统在头颈部危及器官勾画精度的研究[J].中国医学物理学杂志,2024,41(5):548.[doi:DOI:10.3969/j.issn.1005-202X.2024.05.004]
　HU Xinggang,WANG Xian,ZHANG Yang,et al.Deep learning based software solutions for automatic segmentation of head and neck organs at risk[J].Chinese Journal of Medical Physics,2024,41(3):548.[doi:DOI:10.3969/j.issn.1005-202X.2024.05.004]
[18]王云祥,杨碧凝,刘宇翔,等.利用基于图像配准的深度学习方法提高磁共振引导前列腺癌放疗自动勾画精度[J].中国医学物理学杂志,2024,41(6):667.[doi:DOI:10.3969/j.issn.1005-202X.2024.06.002]
　WANG Yunxiang,YANG Bining,LIU Yuxiang,et al.Improving auto-segmentation accuracy for online magnetic resonance imaging-guided prostate radiotherapy by registration-based deep learning method[J].Chinese Journal of Medical Physics,2024,41(3):667.[doi:DOI:10.3969/j.issn.1005-202X.2024.06.002]

备注/Memo

备注/Memo:
【收稿日期】2022-08-12 【基金项目】南京医科大学科技发展基金一般项目（NMUB2020271）；姑苏卫生人才计划人才科研项目（GSWS2020063） 【作者简介】吴传锋，副主任技师，主要研究方向：肿瘤放射治疗，E-mail:wuchuanfeng.2008@163.com 【通信作者】王东燕，副主任技师，主要研究方向：肿瘤放射治疗，E-mail: wsdongdong1015@aliyun.com
更新日期/Last Update: 2023-03-29