浏览全部资源
扫码关注微信
收稿：2017-11-14，
修回：2018-1-24，
纸质出版：2018-08-16
移动端阅览
目的
2
精确的肝脏分割是计算机辅助肝脏疾病诊断和手术规划的必要步骤，但由于肝脏解剖学的复杂性、邻近器官的低对比度和病态等原因，使得肝脏分割在医学图像处理领域仍然是具有挑战性的任务。针对腹部图像器官边界模糊及传统U-Net模型实现端到端的分割时精确度不高等问题，设计了一种基于改进的U-Net（IU-Net）和Morphsnakes算法的增强CT图像肝脏分割方法。
方法
2
首先根据CT图像头文件信息对原始数据进行预处理并构建数据集，然后使用构建好的数据集训练IU-Net，训练过程中使用自定义的Dice层评测图像分割结果的准确率，最后通过OpenCV和Morphsnakes对初始分割结果进行精细分割，最终实现增强CT图像中肝脏的精确分割。
结果
2
实验数据包括200组增强CT，160组用于训练，40组用于测试。本文算法分割准确率达到了94.8%，与U-Net、FCN-8s模型相比，具有更好的分割效果。
结论
2
本文算法可以准确分割增强CT图像中各种形状的肝脏，能够为临床诊断提供可靠依据。
Objective
2
Precise liver segmentation is necessary in the computer-aided diagnosis and surgical planning of liver disease. However
liver segmentation remains challenging in medical image processing task due to the complexity of the liver anatomy and low contrast and morbidity of neighboring organs. To solve the problem of the fuzzy boundary of abdominal image organs and low accuracy of traditional U-Net model in end-to-end segmentation
this study presents an enhanced CT liver segmentation method based on improved U-Net and Morphsnakes algorithm.
Method
2
First
we proposed a method for medical image preprocessing. Medical image is different from natural image. The CT images we obtained from a hospital cannot be used directly because the original format of CT images is not rectangular. Pixel padding value (0028
0120) is used to pad grayscale images (those with a photometric interpretation of MONOCHROME1 or MONOCHROME2) to rectangular format. The first step of image preprocessing is to set the pixel padding value to 0. The second step is converting pixel values to CT values. We then used the processed images to create a dataset. Thereafter
IU-Net is trained with the constructed dataset. IU-Net is a U-Net-like convolution neural network that can achieve end-to-end segmentation. IU-Net contains two paths:downsample path to extract features from images and upsample path to resume image resolution. Between these two paths
the skip connections that can provide additional features for upsample path are available. IU-Net is deeper than U-Net but with less skip connections. While training segmentation neural network
only seeing the loss is insufficient. Often
the loss has good performance
but the segmentation accuracy is low. Therefore
IU-Net has an additional dice layer to evaluate segmentation accuracy during the training epoch. When training loss is stable at low levels
and dice accuracy is stable at high levels
training ends. Finally
OpenCV and Morphsnakes are used to refine the segmentation results generated by IU-Net. OpenCV is used to fill the hole and remove the redundant part of the segmented liver. Morphsnakes is a morphological approach to contour evolution on the basis of a new curvature morphological operator valid for surfaces of any dimension. Morphsnakes approximates the numerical solution of the curve evolution PDE by the successive application of a set of morphological operators defined on a binary level set and with equivalent infinitesimal behavior. The binary segmentation mask optimized by OpenCV also serves as the binary level set. Through the processing of Morphsnakes
we obtained the final segmentation mask and liver contour. In this study
we trained IU-Net
U-Net
and FCN-8s
and all of them were trained in two kinds of processed data. One kind of data is Hounsfield windows
which we used to set the CT value to[-100
400]. The other one has nothing to do with CT value. IU-Net and U-Net were both trained from scratch. FCN-8s was trained using a fine-tuning strategy
because this strategy did not merge when we trained FCN-8s from scratch. We also compared the performance of rectified linear units and parametric rectified linear units on IU-Net.
Result
2
The experimental data include 200 sets of enhanced CT
160 sets for training
and 40 sets for testing. The segmentation accuracy of our proposed method is 94.8%
which is better than that of the U-Net and FCN-8s models. Fine-tuning can make neural network training easy because it takes an already learned model and adapts the architecture. When building a neural network model completely different from a previous one
fine-tuning is no longer useful.
Conclusion
2
Our proposed method can accurately segment liver from enhanced CT images in various shapes and provide a reliable basis for clinical diagnosis.
Selver M A, Kocaoǧlu A, Demir G K, et al. Patient oriented and robust automatic liver segmentation for pre-evaluation of liver transplantation[J]. Computers in Biology and Medicine, 2008, 38(7):765-784.[DOI:10.1016/j.compbiomed.2008.04.006]
Lu X Q, Wu J S, Ren X Y, et al. The study and application of the improved region growing algorithm for liver segmentation[J]. Optik-International Journal for Light and Electron Optics, 2014, 125(9):2142-2147.[DOI:10.1016/j.ijleo.2013.10.049]
Zhang X Q, Xiong B L, Kuang G Y. A ship target discrimination method based on change detection in SAR imagery[J]. Journal of Electronics&Information Technology, 2015, 37(1):63-70.
张小强, 熊博莅, 匡纲要.一种基于变化检测技术的SAR图像舰船目标鉴别方法[J].电子与信息学报, 2015, 37(1):63-70. [DOI:10.11999/JEIT140143]
Zhao Y Q, Yan G X, Xu X W, et al. Automatic segmentation of livers from CT series based on level set method with prior knowledge[J]. Journal of Central South University:Science and Technology, 2015, 46(4):1310-1317.
赵于前, 闫桂霞, 徐效文, 等.基于先验信息水平集方法的肝脏CT序列图像自动分割[J].中南大学学报:自然科学版, 2015, 46(4):1310-1317. [DOI:10.11817/j.issn.1672-7207.2015.04.020]
Ji H W, He J P, Yang X. Three-dimensional CT liver image segmentation based on hierarchical contextual active contour[J]. Journal of Biomedical Engineering, 2014, 31(2):405-412.
吉宏伟, 何江萍, 杨新.基于层次上下文活动轮廓的三维CT肝脏图像分割[J].生物医学工程学杂志, 2014, 31(2):405-412. [DOI:10.7507/1001-5515.20140076.]
Han M, Liu J M, Meng J Y, et al. Local energy information combined with improved signed distance regularization term for image target segmentation algorithm[J]. Journal of Electronics&Information Technology, 2015, 37(9):2047-2054.
韩明, 刘教民, 孟军英, 等.结合局部能量与改进的符号距离正则项的图像目标分割算法[J].电子与信息学报, 2015, 37(9):2047-2054.[DOI:10.11999/JEIT141473]
Peng J L, Wang Y, Kong D X. Liver segmentation with constrained convex variational model[J]. Pattern Recognition Letters, 2014, 43:81-88.[DOI:10.1016/j.patrec.2013.07.010]
Afifi A, Nakaguchi T. Liver segmentation a pproach using graph cuts and iteratively estimated shape and intensity constrains[M ] //Ayache N, Delingette H, Golland P, et al. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2012. Berlin, Heidelberg: Springer, 2012, 7511: 395-403. [ DOI: 10.1007/978-3-642-33418-4_49 http://dx.doi.org/10.1007/978-3-642-33418-4_49 ]
Chen X J, Udupa J K, Bagci U, et al. Medical image segmentation by combining graph cuts and oriented active appearance models[J]. IEEE Transactions on Image Processing, 2012, 21(4):2035-2046.[DOI:10.1109/TIP.2012.2186306]
Liao M, Zhao Y Q, Zeng Y Z, et al. Liver segmentation from abdominal CT volumes based on graph cuts and border marching[J]. Journal of Electronics&Information Technology, 2016, 38(6):1152-1156.
廖苗, 赵于前, 曾业战, 等.基于图割和边缘行进的肝脏CT序列图像分割[J].电子与信息学报, 2016, 38(6):1552-1556.[DOI:10.11999/JEIT151005]
Heimann T, Meinzer H P, Wolf I. A statistical deformable model for the segmentation of liver CT volumes[C]//MICCAI Workshop 3D Segmentation Clinic: A Grand Challenge. Brisbane: MICCAI, 2007: 161-166.
Kainmüller D, Lange T, Lamecker H. Shape constrained automatic segmentation of the liver based on a heuristic intensity model[C]//MICCAI Workshop 3D Segmentation Clinic: A Grand Challenge. Brisbane: MICCAI, 2007: 109-116.
Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C ] //Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA: IEEE, 2015: 3431-3440. [ DOI: 10.1109/CVPR.2015.7298965 http://dx.doi.org/10.1109/CVPR.2015.7298965 ]
Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation[C ] //Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241. [ DOI: 10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28 ]
Christ P F, Ettlinger F, Grün F, et al. Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields[C ] //Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2016: 415-423. [ DOI: 10.1007/978-3-319-46723-8_48 http://dx.doi.org/10.1007/978-3-319-46723-8_48 ]
Ben-Cohen A, Diamant I, Klang E, et al. Fully convolutional network for liver segmentation and lesions detection[C ] //Proceedings of the First International Workshop on Lar ge-Scale Annotation of Biomedical Data and Expert Label Synthesis. Cham: Springer, 2016: 77-85. [ DOI: 10.1007/978-3-319-46976-8_9 http://dx.doi.org/10.1007/978-3-319-46976-8_9 ]
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C]//International Conference on Learning Representations, 2015.
Marquez-Neila P, Baumela L, Alvarez L. A morphological approach to curvature-based evolution of curves and surfaces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(1):2-17.[DOI:10.1109/TPAMI.2013.106]
Glorot X, Bordes A, Bengio Y. Deep sparse rectifier neural networks[C]//Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. Fort Lauderdale: PMLR, 2011: 315-323.
Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision[C ] //Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, United States: IEEE, 2016: 2818-2826. [ DOI: 10.1109/CVPR.2016.308 http://dx.doi.org/10.1109/CVPR.2016.308 ]
Jia Y Q, Shelhamer E, Donahue J, et al. Caffe: convolutional architecture for fast feature embedding[C ] //Proceedings of the 22nd ACM international conference on Multimedia (MM'14). New York, NY, USA: ACM, 2014: 675-678. [ DOI: 10.1145/2647868.2654889 http://dx.doi.org/10.1145/2647868.2654889 ]
相关作者
相关机构
京公网安备11010802024621
