电子密度模体插件自动定位方法
|
摘要
目的探讨基于深度卷积神经网络(DCNN)对电子密度模体(CIRS 062)插件自动定位的方法。方法首先基于DCNN模型分割CIRS 062的吸气态肺、呼气态肺、松质骨和密质骨4个插件;之后采用摩尔邻域追踪算法处理插件边缘;最后根据几何特征定位其他4个插件。结果基于DCNN分割结果的戴斯相似性系数均>0.85,精确度均>0.81,综合评价指标均>0.61。结论基于DCNN方法可实现插件自动定位。
Objective To investigate automatic location of inserts in the electron density phantom (CIRS 062) based on deep neural network(DCNN).Methods Firstly,four inserts in CIRS 062 were segmented with DCNN model,namely the inhaled lung,the exhaled lung,the solid trabecular bone and the solid dense bone.Then Moore-neighbor tracking algorithm was used to process the segmentation results to obtain the precise segmentation edges.Finally,the other four inserts were located based on the geometric features.Results The results of Dice similarity coefficient were all>0.85,the precision were all>0.81,and F1-measure were all>0.61 based on DCNN.Conclusion The method based on DCNN can realize the automatic positioning of the inserts.
Objective To investigate automatic location of inserts in the electron density phantom (CIRS 062) based on deep neural network(DCNN).Methods Firstly,four inserts in CIRS 062 were segmented with DCNN model,namely the inhaled lung,the exhaled lung,the solid trabecular bone and the solid dense bone.Then Moore-neighbor tracking algorithm was used to process the segmentation results to obtain the precise segmentation edges.Finally,the other four inserts were located based on the geometric features.Results The results of Dice similarity coefficient were all>0.85,the precision were all>0.81,and F1-measure were all>0.61 based on DCNN.Conclusion The method based on DCNN can realize the automatic positioning of the inserts.
引文
[1] 王为,聂生东,吴国华.锥形束CT在放射治疗中的应用.中国医学影像技术,2011,27(5):1074-1077.
[2] Annkah JK, Rosenberg I, Hindocha N, et al. Assessment of the dosimetric accuracies of CATPhan 504 and CIRS 062 using kV-CBCT for performing direct calculations. J Med Phys, 2014,39(3):133-141.
[3] 张基永,陆佳扬,洪丹丽,等.宫颈癌患者锥形束CT影像剂量计算的算法修正.中国医学影像技术,2017,33(1):114-118.
[4] Reeves TE, Mah P, Mcdavid WD. Deriving hounsfield units using grey levels in cone beam CT: A clinical application. Dentomaxillofac Radiol, 2012,41(6):500-508.
[5] Razi T, Niknami M, Alavi Ghazani F. Relationship between hounsfield unit in CT scan and gray scale in CBCT. J Dent Res Dent Clin Dent Prospects, 2014,8(2):107-110.
[6] Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis, 2015,115(3):211-252.
[7] Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell, 2017,39(4):640-651.
[8] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation//Springer. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. German: Springer, 2015,234-241.
[9] Gray L. A mathematician looks at S. Wolfram's new kind of science. Review of: A new kind of science. Not Am Math Soc, 2003,50(2):200-211.
[10] Hussain S, Anwar SM, Majid M. Brain tumor segmentation using cascaded deep convolutional neural network. Conf Proc IEEE Eng Med Biol Soc, 2017,2017:1998-2001 .
[11] Gonzalez RC, Wintz P. Digital image processing. Prentice Hall International, 2010,28(4):484-486.
[12] Ioffe S, Szegedy C. Batch Normalization: Accelerating deep network training by reducing internal covariate shift//JMLR. ICML'15 Proceedings of the 32nd International Conference on International Conference on Machine Learning. USA: JMLR, 2015,448-456.
[13] Hara K, Saito D, Shouno H. Analysis of function of rectified linear unit used in deep learning//IEEE. Proceedings of the International Joint Conference on Neural Networks. Killarney: IEEE, 2015:1-8.
[14] Wu HB, Gu XD. Max-pooling dropout for regularization of convolutional neural networks//Springer. International Conference on Neural Information Processing. German: Springer, 2015:46-54.
[15] Kingma D, Ba J. Adam: A Method for Stochastic Optimization. [2017-01-30] https://www.arxiv.org/pdf/1412.6980.
[16] Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell, 2017,39(12):2481-2495.
[17] 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.中国医学物理学杂志,2018,35(3):256-259.
[18] Fowlkes C, Martin K, Malik J. Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans Pattern Anal Mach Intell, 2004:530-549.
[19] 梁晓坤,牛田野,周勤煊,等.直线加速器机载锥形束CT图像散射的修正方法.中国医学影像技术,2016,32(4):619-622.
[2] Annkah JK, Rosenberg I, Hindocha N, et al. Assessment of the dosimetric accuracies of CATPhan 504 and CIRS 062 using kV-CBCT for performing direct calculations. J Med Phys, 2014,39(3):133-141.
[3] 张基永,陆佳扬,洪丹丽,等.宫颈癌患者锥形束CT影像剂量计算的算法修正.中国医学影像技术,2017,33(1):114-118.
[4] Reeves TE, Mah P, Mcdavid WD. Deriving hounsfield units using grey levels in cone beam CT: A clinical application. Dentomaxillofac Radiol, 2012,41(6):500-508.
[5] Razi T, Niknami M, Alavi Ghazani F. Relationship between hounsfield unit in CT scan and gray scale in CBCT. J Dent Res Dent Clin Dent Prospects, 2014,8(2):107-110.
[6] Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis, 2015,115(3):211-252.
[7] Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell, 2017,39(4):640-651.
[8] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation//Springer. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. German: Springer, 2015,234-241.
[9] Gray L. A mathematician looks at S. Wolfram's new kind of science. Review of: A new kind of science. Not Am Math Soc, 2003,50(2):200-211.
[10] Hussain S, Anwar SM, Majid M. Brain tumor segmentation using cascaded deep convolutional neural network. Conf Proc IEEE Eng Med Biol Soc, 2017,2017:1998-2001 .
[11] Gonzalez RC, Wintz P. Digital image processing. Prentice Hall International, 2010,28(4):484-486.
[12] Ioffe S, Szegedy C. Batch Normalization: Accelerating deep network training by reducing internal covariate shift//JMLR. ICML'15 Proceedings of the 32nd International Conference on International Conference on Machine Learning. USA: JMLR, 2015,448-456.
[13] Hara K, Saito D, Shouno H. Analysis of function of rectified linear unit used in deep learning//IEEE. Proceedings of the International Joint Conference on Neural Networks. Killarney: IEEE, 2015:1-8.
[14] Wu HB, Gu XD. Max-pooling dropout for regularization of convolutional neural networks//Springer. International Conference on Neural Information Processing. German: Springer, 2015:46-54.
[15] Kingma D, Ba J. Adam: A Method for Stochastic Optimization. [2017-01-30] https://www.arxiv.org/pdf/1412.6980.
[16] Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell, 2017,39(12):2481-2495.
[17] 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.中国医学物理学杂志,2018,35(3):256-259.
[18] Fowlkes C, Martin K, Malik J. Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans Pattern Anal Mach Intell, 2004:530-549.
[19] 梁晓坤,牛田野,周勤煊,等.直线加速器机载锥形束CT图像散射的修正方法.中国医学影像技术,2016,32(4):619-622.