生物医学工程学杂志

生物医学工程学杂志

基于自适应均值漂移的超声心动图左心室分割方法

查看全文

利用超声心动图进行心室分割能够获得心室容积参数,对评价心功能有重要意义。但超声图像有噪声大、难以分割等特点,仅仅靠人工对目标区域进行手动分割工作量巨大,且目前自动分割技术尚无法保证分割精度。针对这些问题,本文提出了一种全新的算法框架对心室结构进行了分割提取。首先,采用更快速的基于区域的卷积神经网络目标检测算法对目标区域进行定位,得到感兴趣区域;然后使用 K 均值(K-means)算法对目标区域进行初始聚类;接着使用一种自适应核函数带宽的均值漂移(mean shift)算法进行分割;最后采用种子填充算法提取目标区域。该算法结构实现了自动提取分割目标区域,免去了人工定位的过程。实验表明,在定量评价标准下,这种分割框架能够对目标区域进行精确的提取,同时提出的自适应均值漂移算法较传统固定带宽均值漂移算法更稳定,且分割效果更好。研究结果显示,本文所述方法有助于实现超声心动图左心室切面的自动分割。

The use of echocardiography ventricle segmentation can obtain ventricular volume parameters, and it is helpful to evaluate cardiac function. However, the ultrasound images have the characteristics of high noise and difficulty in segmentation, bringing huge workload to segment the object region manually. Meanwhile, the automatic segmentation technology cannot guarantee the segmentation accuracy. In order to solve this problem, a novel algorithm framework is proposed to segment the ventricle. Firstly, faster region-based convolutional neural network is used to locate the object to get the region of interest. Secondly, K-means is used to pre-segment the image; then a mean shift with adaptive bandwidth of kernel function is proposed to segment the region of interest. Finally, the region growing algorithm is used to get the object region. By this framework, ventricle is obtained automatically without manual localization. Experiments prove that this framework can segment the object accurately, and the algorithm of adaptive mean shift is more stable and accurate than the mean shift with fixed bandwidth on quantitative evaluation. These results show that the method in this paper is helpful for automatic segmentation of left ventricle in echocardiography.

关键词: 左心室分割; 左心室定位; 像素聚类; 均值漂移分割; 自适应核函数带宽

Key words: left ventricle segmentation; left ventricle localization; pixel clustering; mean shift segmentation; adaptive bandwidth

引用本文: 朱锴, 付忠良, 陶攀, 朱硕. 基于自适应均值漂移的超声心动图左心室分割方法. 生物医学工程学杂志, 2018, 35(2): 273-279. doi: 10.7507/1001-5515.201702037 复制

登录后 ,请手动点击刷新查看全文内容。 没有账号,
登录后 ,请手动点击刷新查看图表内容。 没有账号,
1. 纪祥虎, 高思聪, 黄志标, 等. 基于 Centripetal Catmull-Rom 曲线的经食道超声心动图左心室分割方法. 四川大学学报: 工程科学版, 2016, 48(5): 84-90.
2. 孙申申, 范立南, 康雁, 等. 基于改进主动形状模型的含胸壁粘连型肿块的肺区分割方法研究. 生物医学工程学杂志, 2016(5): 879-884.
3. Carneiro G, Nascimento J C, Freitas A. The segmentation of the left ventricle of the heart from ultrasound data using deep learning architectures and derivative-based search methods. IEEE Transactions on Image Processing, 2012, 21(3): 968-982.
4. Milletari F, Ahmadi S A, Kroll C A, et al. Hough-CNN: deep learning for segmentation of deep brain regions in MRI and ultrasound. Computer Vision and Image Understanding, 2017, 164(SI): 92-102.
5. Gao Mingchen, Xu Ziyue, Lu Le, et al. Segmentation label propagation using deep convolutional neural networks and dense conditional random field//2016 IEEE 13th international symposium on biomedical imaging (ISBI), 2016: 1265-1268.
6. Mignotte M, Meunier J, Tardif J C. Endocardial boundary e timation and tracking in echocardiographic images using deformable template and markov random fields. Pattern Analysis Applications, 2001, 4(4): 256-271.
7. Mishra A, Dutta P K, Ghosh M K. A GA based approach for boundary detection of left ventricle with echocardiographic image sequences. Image Vis Comput, 2003, 21(11): 967-976.
8. Sadek I, Elawady M, Stefanovski V. Automated breast lesion segmentation in ultrasound images. arXiv preprint. 2016. arXiv: 1609.08364.
9. McClymont D, Mehnert A, Trakic A, et al. Fully automatic lesion segmentation in breast MRI using Mean-shift and graph-cuts on a region adjacency graph. Journal of Magnetic Resonance Imaging, 2014, 39(4): 795-804.
10. ZHOU Zhuhuang, WU Weiwei, WU Shuicai, et al. Semi-automatic breast ultrasound image segmentation based on mean shift and graph cuts. Ultrason Imaging, 2014, 36(4): 256-276.
11. Kim J H, Lee S, Lee G S, et al. Using a method based on a modified K-Means clustering and mean shift segmentation to reduce file sizes and detect brain tumors from magnetic resonance (MRI) images. Wireless Personal Communications, 2016, 89(3, SI): 993-1008.
12. Mayer A, Greenspan H. An adaptive Mean-Shift framework for MRI brain segmentation. IEEE Trans Med Imaging, 2009, 28(8): 1238-1250.
13. Comaniciu D, Meer P. Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell, 2002, 24(5): 603-619.
14. Ren Shaoqing, He Kaiming, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks//Computer Vision and Pattern Recognition, 2015: 91-99.
15. Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation//Proceedings of the IEEE conference on computer vision and pattern recognition, 2014: 580-587.
16. Girshick R. Fast R-CNN//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
17. Zeiler M D, Fergus R. Visualizing and understanding convolutional networks//Computer Vision–ECCV 2014, Zurich, 2014: 818-833.
18. Deng Jia, Dong Wei, Socher R, et al. Imagenet: a large-scale hierarchical image database//Computer Vision and Pattern Recognition, Miami, 2009: 248-255.