基于卷积神经网络的超声图像左心室分割方法

doi:10.11772/j.issn.1001-9081.2018112321

计算机应用 ›› 2019, Vol. 39 ›› Issue (7): 2121-2124.DOI: 10.11772/j.issn.1001-9081.2018112321

• 虚拟现实与多媒体计算 • 上一篇下一篇

基于卷积神经网络的超声图像左心室分割方法

朱锴^1,2, 付忠良^1,2, 陈晓清^1,2

1. 中国科学院成都计算机应用研究所, 成都 610041;
2. 中国科学院大学, 北京 100049

收稿日期:2018-11-23 修回日期:2018-12-28 出版日期:2019-07-10 发布日期:2019-07-15
通讯作者: 朱锴
作者简介:朱锴(1991-),男,贵州安顺人,博士研究生,主要研究方向:机器视觉、机器学习;付忠良(1967-),男,重庆合川人,研究员,博士生导师,主要研究方向:机器学习;陈晓清(1989-),男,四川凉山人,博士研究生,主要研究方向:机器学习、机器视觉。
基金资助:
四川省科技厅重点研发项目（2017SZ0010）；四川省科技支撑计划项目（2016JZ0035）。

Left ventricular segmentation method of ultrasound image based on convolutional neural network

ZHU Kai^1,2, FU Zhongliang^1,2, CHEN Xiaoqing^1,2

1. Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu Sichuan 610041, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2018-11-23 Revised:2018-12-28 Online:2019-07-10 Published:2019-07-15
Supported by:
This work is partially supported by the Key Research and Development Project of Sichuan Science and Technology Department (2017SZ0010), the Science and Technology Support Program of Sichuan Province (2016JZ0035).

摘要/Abstract

摘要：

超声图像左心室的分割在临床上对医生的作用巨大。由于超声图像含有大量噪声，轮廓特征不明显，目前的卷积神经网络（CNN）方法对左心室分割容易得到不必要的区域，并且分割目标不完整。为了解决上述问题，在全卷积神经网络（FCN）基础上加入了关键点定位和求取图像凸包方法对分割结果进行优化。首先采用FCN获取初步的分割结果；然后为了去除分割结果中的错误区域，提出一种CNN定位左心室三个关键点的位置，通过关键点筛选掉分割结果中不必要的区域；最后为保证剩余区域能够组合成一个完整的心室，利用求取图像凸包算法将所有有效区域进行合并。实验结果表明，在超声图像左心室分割效果上，所提方法能够在普通FCN的基础上获得很大的提升，在交并比评价标准下，该方法获取的左心室结果能够比传统CNN方法提升近15%。

关键词: 超声图像, 分割, 关键点定位, 卷积神经网络, 凸包

Abstract:

Ultrasound image segmentation of left ventricle is very important for doctors in clinical practice. As the ultrasound images contain a lot of noise and the contour features are not obvious, current Convolutional Neural Network (CNN) method is easy to obtain unnecessary regions in left ventricular segmentation, and the segmentation regions are incomplete. In order to solve these problems, keypoint location and image convex hull method were used to optimize segmentation results based on Fully Convolutional neural Network (FCN). Firstly, FCN was used to obtain preliminary segmentation results. Then, in order to remove erroneous regions in segmentation results, a CNN was proposed to locate three keypoints of left ventricle, by which erroneous regions were filtered out. Finally, in order to ensure that the remained area were able to be a complete ventricle, image convex hull algorithm was used to merge all the effective areas together. The experimental results show that the proposed method can greatly improve left ventricular segmentation results of ultrasound images based on FCN. Under the evaluation standard, the accuracy of results obtained by this method can be increased by nearly 15% compared with traditional CNN method.

Key words: ultrasound image, segmentation, keypoint location, Convolutional Neural Network (CNN), convex hull

中图分类号:

朱锴, 付忠良, 陈晓清. 基于卷积神经网络的超声图像左心室分割方法[J]. 计算机应用, 2019, 39(7): 2121-2124.

ZHU Kai, FU Zhongliang, CHEN Xiaoqing. Left ventricular segmentation method of ultrasound image based on convolutional neural network[J]. Journal of Computer Applications, 2019, 39(7): 2121-2124.

参考文献

[1] 朱锴,付忠良,陶攀,等.基于自适应均值漂移的超声心动图左心室分割方法[J].生物医学工程学杂志,2018,35(2):273-279.(ZHU K, FU Z, TAO P, et al. Left ventricle segmentation in echocardiography based on adaptive mean shift[J]. Journal of Biomedical Engineering, 2018, 35(2):273-279.)
[2] SADEK I, ELAWADY M, STEFANOVSKI V. Automated breast lesion segmentation in ultrasound images[J]. ArXiv Preprint, 2016, 2016:1609.08364.
[3] 朱永杰,邱天爽.基于改进LGDF模型的超声图像自动分割方法[J].大连理工大学学报,2016,56(1):28-34.(ZHU Y J, QIU T S. Automated segmentation method for ultrasound image based on improved LGDF model[J]. Journal of Dalian University of Technology, 2016, 56(1):28-34.)
[4] JIANG P, PENG J, ZHANG G, et al. Learning-based automatic breast tumor detection and segmentation in ultrasound images[C]//Proceedings of the 2012 IEEE International Symposium on Biomedical Imaging. Piscataway, NJ:IEEE, 2012:1587-1590.
[5] NGO T A, LU Z, CARNEIRO G. Combining deep learning and level set for the automated segmentation of the left ventricle of the heart from cardiac cine magnetic resonance[J]. Medical Image Analysis, 2017, 35:159-171.
[6] 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[J]. 四川大学学报(工程科学版),2016,48(5):84-90.(JI X H, GAO S C, HUANG Z B, et al. Left ventricle segmentation in transesophageal echocardiography based on Centripetal Catmull-Rom curve[J]. Journal of Sichuan University (Engineering Science Edition), 2016, 48(5):84-90.)
[7] VARGAS-QUINTERO L, ESCALANTE-RAMÍREZ B, CAMARGO M L, et al. Left ventricle segmentation in fetal echocardiography using a multi-texture active appearance model based on the steered Hermite transform[J]. Computer Methods and Programs in Biomedicine, 2016, 137:231-245.
[8] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651.
[9] ZHENG S, JAYASUMANA S, ROMERA-PAREDES B, et al. Conditional random fields as recurrent neural networks[C]//ICCV'15:Proceedings of the 2015 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2015:1529-1537.
[10] HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//ICCV 2017:Proceedings of the 2017 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2017:2961-2969.
[11] RONNEBERGER O, FISCHER P, BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//MICCAI 2015:Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Berlin:Springer, 2015:234-241.
[12] GAO M, XU Z, LU L, et al. Segmentation label propagation using deep convolutional neural networks and dense conditional random field[C]//Proceedings of the 2016 IEEE International Symposium on Biomedical Imaging. Piscataway, NJ:IEEE, 2016:1265-1268.
[13] LI Y, YI G, WANG Y, et al. Segmentation of fetal left ventricle in echocardiographic sequences based on dynamic convolutional neural networks[J]. IEEE Transactions on Biomedical Engineering, 2017, 64(8):1886-1895.
[14] 詹曙,梁植程,谢栋栋.前列腺磁共振图像分割的反卷积神经网络方法[J].中国图象图形学报,2017,22(4):516-522.(ZHAN S, LIANG Z C, XIE D D. Deconvolutional neural network for prostate MRI segmentation[J]. Journal of Image and Graphics, 2017, 22(4):516-522.)
[15] JAFARI M H, GIRGIS H, LIAO Z, et al. A unified framework integrating recurrent fully-convolutional networks and optical flow for segmentation of the left ventricle in echocardiography data[C]//Proceedings of the 2018 International Workshop on Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Berlin:Springer, 2018:29-37.
[16] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. ArXiv Preprint, 2014, 2014:1409.1556.
[17] GRAHAM R L. An efficient algorithm for determining the convex hull of a finite planar set[J]. Information Processing Letters, 1978, 7(1):53-55.

基于卷积神经网络的超声图像左心室分割方法

Left ventricular segmentation method of ultrasound image based on convolutional neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	马佳良, 陈斌, 孙晓飞. 基于改进的Faster R-CNN的通用目标检测框架[J]. 计算机应用, 2021, 41(9): 2712-2719.
[2]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[3]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[4]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[5]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[6]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[7]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[8]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[9]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[10]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[11]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[12]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[13]	杨瑞, 钱晓军, 孙振强, 许振. 自然场景下多区域特征融合的混合航拍图像分割算法[J]. 计算机应用, 2021, 41(8): 2445-2452.
[14]	樊玮, 李晨炫, 邢艳, 黄睿, 彭洪健. 航空发动机损伤图像的二分类到多分类递进式检测网络[J]. 计算机应用, 2021, 41(8): 2352-2357.
[15]	吴则举, 焦翠娟, 陈亮. 基于改进Faster R-CNN的轮胎缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1939-1946.