Automatic segmentation algorithm for single organ of CT images based on cascaded Vnet-S network

doi:10.11772/j.issn.1001-9081.2018122445

Abstract

Abstract: In order to realize fast and accurate segmentation of organs in Computed Tomography (CT) images, a automatic segmentation algorithm for single organ based on cascaded Vnet-S network was proposed. Firstly, the organ in the CT image was coarsely segmented by using the first Vnet-S network. Then, the maximum connection flux in the segmentation result was selected and expanded twice, and the organ boundary was determined and the organ area was extracted according to the maximum connection flux after expansion. Finally, the organ was finely segmented by using the second Vnet-S network. In order to verify the performance of the proposed algorithm, a liver segmentation experiment was carried out on the MICCAI 2017 Liver Tumor Segmentation Challenge (LiTS) dataset, and a lung segmentation experiment was carried out on the ISBI LUng Nodule Analysis 2016 (LUNA16) dataset. The cascaded Vnet-S algorithm has a Dice coefficient of 0.9600 on the online test data of 70 cases in LiTS and a Dice coefficient of 0.9810 on the 288 cases in LUNA16, which are higher than those of Vnet-S network and Vnet network. Experimental results show that the single organ segmentation algorithm based on cascaded Vnet-S network can accurately segment organs with lower computational complexity compared with Vnet and Unet networks.

Key words: organ segmentation, Vnet-S, deep learning, segmentation network, cascaded network structure

摘要： 为了快速准确地对计算机断层扫描（CT）影像中的器官进行分割，提出基于级联Vnet-S网络的单一器官自动分割算法。首先，使用第一个Vnet-S网络对CT影像中的器官进行粗分割；然后，选择分割结果中的最大连接通量做两次膨胀，根据膨胀后的最大连接通量确定器官边界并提取器官区域；最后，使用第二个Vnet-S网络对器官进行细分割。为了验证算法的性能，采用MICCAI 2017 Liver Tumor Segmentation Challenge （LiTS）数据集进行肝脏分割实验，采用ISBI LUng Nodule Analysis 2016（LUNA16）数据集进行肺分割实验。级联Vnet-S算法在LiTS的70例线上测试数据上的Dice系数为0.9600，在LUNA16的288例测试数据上的Dice系数为0.9810，均高于Vnet-S网络和Vnet网络。实验结果表明，基于级联Vnet-S网络的单一器官分割算法可以准确地对器官进行分割，而且级联Vnet-S算法的计算量小于Unet网络和Vnet网络。

关键词: 器官分割, Vnet-S, 深度学习, 分割网络, 级联网络结构

CLC Number:

TP391.4

XU Baoquan, LING Tonghui. Automatic segmentation algorithm for single organ of CT images based on cascaded Vnet-S network[J]. Journal of Computer Applications, 2019, 39(8): 2420-2425.

徐宝泉, 凌彤辉. 基于级联Vnet-S网络的CT影像单一器官自动分割算法[J]. 计算机应用, 2019, 39(8): 2420-2425.

References

[1] MORTELÉ K J, CANTISANI V, TROISI R, et al. Preoperative liver donor evaluation:imaging and pitfalls[J]. Liver Transplantation, 2003, 9(9):S6-S14.
[2] SUZUKI K, KOHLBRENNER R, EPSTEIN M L, et al. Computer-aided measurement of liver volumes in CT by means of geodesic active contour segmentation coupled with level-set algorithms[J]. Medical Physics, 2010, 37(5):2159-2166.
[3] ARMATO S G 3rd, SENSAKOVIC W F. Automated lung segmentation for thoracic CT:impact on computer-aided diagnosis[J]. Academic Radiology, 2004, 11(9):1011-1021.
[4] UKIL S, REINHARDT J M. Smoothing lung segmentation surfaces in three-dimensional x-ray CT images using anatomic guidance[J]. Academic Radiology, 2005, 12(12):1502-1511.
[5] ZHANG X, TIAN J, DENG K, et al. Automatic liver segmentation using a statistical shape model with optimal surface detection[J]. IEEE Transactions on Biomedical Engineering, 2010, 57(10):2622-2626.
[6] BADAKHSHANNOORY H, SAEEDI P. A model-based validation scheme for organ segmentation in CT scan volumes[J]. IEEE Transactions on Biomedical Engineering, 2011, 58(9):2681-2693.
[7] SUN SH, BAUER C, BEICHEL R. Automated 3-D segmentation of lungs with lung cancer in CT data using a novel robust active shape model approach[J]. IEEE Transactions on Medical Imaging, 2012, 31(2):449-460.
[8] JI H, HE J, YANG X, et al. ACM-based automatic liver segmentation from 3-D CT images by combining multiple atlases and improved mean-shift techniques[J]. IEEE Journal of Biomedical and Health Informatics, 2013, 17(3):690-698.
[9] ZHANG X, TIAN J, XIANG D, et al. Interactive liver tumor segmentation from CT scans using support vector classification with watershed[C]//Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway, NJ:IEEE, 2011:6005-6008.
[10] KORFIATIS P, KALOGEROPOULOU C, KARAHALIOU A, et al. Texture classification-based segmentation of lung affected by interstitial pneumonia in high-resolution CT[J]. Medical Physics, 2008, 35(12):5290-5302.
[11] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651.
[12] RONNEBERGER O, FISCHER P, BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Cham:Springer, 2015:234-241.
[13] ÇIEK Ç, ABDULKADIR A, LIENKAMP S S, et al. 3D U-Net:learning dense volumetric segmentation from sparse annotation[C]//Proceedings of the 2016 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9901. Cham:Springer, 2016:424-432.
[14] MILLETARI F, NAVAB N, AHMADI S. V-Net:fully convolutional neural networks for volumetric medical image segmentation[C]//Proceedings of the 4th International Conference on 3D Vision. Piscataway, NJ:IEEE, 2016:565-571.
[15] 郭树旭, 马树志, 李晶,等. 基于全卷积神经网络的肝脏CT影像分割研究[J]. 计算机工程与应用, 2017, 53(18):126-131. (GUO S X, MA S Z, LI J, et al. Fully convolutional neural network for liver segmentation in CT image[J]. Computer Engineering and Applications, 2017, 53(18):126-131.)
[16] NEGAHDAR M, BEYMER D, SYEDA-MAHMOOD T. Automated volumetric lung segmentation of thoracic CT images using fully convolutional neural network[C]//Proceedings of the Medical Imaging 2018:Computer-Aided Diagnosis, SPIE 10575. Bellingham, WA:SPIE, 2018:1-6.
[17] 孙明建, 徐军, 马伟,等. 基于新型深度全卷积网络的肝脏CT影像三维区域自动分割[J]. 中国生物医学工程学报, 2018, 37(4):385-393. (SUN M J, XU J, MA W, et al. A new fully convolutional network for 3D liver region segmentation on CT images[J]. Chinese Journal of Biomedical Engineering, 2018, 37(4):385-393.)
[18] JANSSENS R, ZENG G, ZHENG G. Fully automatic segmentation of lumbar vertebrae from CT images using cascaded 3D fully convolutional networks[C]//Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging. Piscataway, NJ:IEEE, 2018:893-897.
[19] ROTH H R, ODA H, HAYASHI Y, et al. Hierarchical 3D fully convolutional networks for multi-organ segmentation[J]. arXiv E-print, 2017:arXiv:1704.06382.
[20] IOFFE S, SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning.[S.l.]:JMLR, 2015:448-456.
[21] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2016:770-778.
[22] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout:a simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 2014, 15(1):1929-1958.
[23] KINGMA D P, BA J L. Adam:a method for stochastic optimization[J]. arXiv E-print, 2017:arXiv:1412.6980.
[24] KALUVA K C, KHENED M, KORI A,et al. 2D-densely connected convolution neural networks for automatic liver and tumor segmentation[J]. arXiv E-print, 2018:arXiv:1802.02182.
[25] VORONTSOV E, TANG A, PAL C, et al. Liver lesion segmentation informed by joint liver segmentation[C]//Proceedings of the IEEE 15th International Symposium on Biomedical Imaging. Piscataway, NJ:IEEE, 2018:1332-1335.
[26] LI X, CHEN, QI X, et al. H-DenseUNet:hybrid densely connected UNet for liver and tumor segmentation from CT volumes[J]. IEEE Transactions on Medical Imaging, 2018, 37(12):2663-2674.
[27] YUAN Y, BUCKSTEIN M, LO Y. Automatic liver and tumor segmentation using hierarchical convolutional-deconvolutional neural networks with jaccard distance[J]. Medical Physics, 2018, 45(6):E516.