基于深度学习的超声图像左心耳自动分割方法

doi:10.11772/j.issn.1001-9081.2019040771

计算机应用 ›› 2019, Vol. 39 ›› Issue (11): 3361-3365.DOI: 10.11772/j.issn.1001-9081.2019040771

• 虚拟现实与多媒体计算 • 上一篇下一篇

基于深度学习的超声图像左心耳自动分割方法

韩路易¹, 黄韫栀^1,2, 窦浩然³, 白文娟⁴, 刘奇¹

1. 四川大学电气工程学院, 成都 610065;
2. 四川大学材料科学与工程学院, 成都 610065;
3. 深圳大学生物医学工程学院, 广东深圳 518060;
4. 四川大学华西医院超声心内科, 成都 610065

收稿日期:2019-05-07 修回日期:2019-08-16 发布日期:2019-08-26 出版日期:2019-11-10
通讯作者: 刘奇
作者简介:韩路易(1995-),男,四川成都人,硕士研究生,主要研究方向:医学图像处理;黄韫栀(1989-),女,江苏靖江人,博士研究生,主要研究方向:医学信号处理、医学图像处理;窦浩然(1995-),男,河北邢台人,硕士研究生,主要研究方向:医学图像分析;白文娟(1982-),山西广灵人,副主任医师,博士研究生,主要研究方向:心脏瓣膜病的动态评估;刘奇(1966-),男,四川内江人,教授,博士,主要研究方向:机器视觉、医学图像处理、医学信息。
基金资助:
成都市科技局项目（2015-HM01-00525-SF）。

Automatic method for left atrial appendage segmentation from ultrasound images based on deep learning

HAN Luyi¹, HUANG Yunzhi^1,2, DOU Haoran³, BAI Wenjuan⁴, LIU Qi¹

1. College of Electrical Engineering, Sichuan University, Chengdu Sichuan 610065, China;
2. College of Materials Science and Engineering, Sichuan University, Chengdu Sichuan 610065, China;
3. School of Biomedical Engineering, Shenzhen University, Shenzhen Guangdong 518060, China;
4. Department of Cardiology, West China Hospital of Sichuan University, Chengdu Sichuan 610000, China

Received:2019-05-07 Revised:2019-08-16 Online:2019-08-26 Published:2019-11-10
Supported by:
This work is partially supported by the Project of Chengdu Science and Technology Bureau (2015-HM01-00525-SF).

摘要/Abstract

摘要： 从超声图像中分割出左心耳（LAA）是得出临床诊断指标的重要步骤，而准确自动分割的首要步骤和难点就是实现目标的自动定位。针对这一问题，提出了一种结合基于深度学习框架的自动定位和基于模型的分割算法的方法来实现超声图像中LAA的自动分割。首先，训练YOLO模型作为LAA自动定位的网络架构；其次，通过验证集确定最优的权重文件，并预测出LAA的最小包围盒；最后，在正确定位的基础上，将YOLO预测的最小包围盒放大1.5倍作为初始轮廓，利用C-V模型完成LAA的自动分割。分割结果用5项指标加以评价：正确性、敏感性、特异性、阴性、阳性。实验结果表明，所提方法能够实现不同分辨率条件和不同显示模式下LAA的自动定位，小样本数据在1000次迭代时已经达到最优的定位效果，正确定位率达到72.25%，并且在正确定位的基础上，C-V模型的分割准确率能够达到98.09%。因此，深度学习技术在实现LAA超声图像的自动分割上具备较大的潜力，能够为基于轮廓的分割算法提供良好的初始轮廓。

关键词: 自动分割, 深度学习, C-V模型, 左心耳, 超声图像

Abstract: Segmenting Left Atrial Appendage (LAA) from ultrasound image is an essential step for obtaining the clinical indicators, and the prerequisite and difficulty for automatic and accurate segmentation is locating the target accurately. Therefore, a method combining with automatic location based on deep learning and segmenting algorithm based on model was proposed to accomplish the automatic segmentation of LAA from ultrasound images. Firstly, You Only Look Once (YOLO) model was trained as the network structure for the automatic location of LAA. Secondly, the optimal weight files were determined by the validation set and the bounding box of LAA was predicted. Finally, based on the correct location, the bounding box was magnified 1.5 times as the initial contour, and C-V (Chan-Vese) model was utilized to realize the automatic segmentation of LAA. The performance of automatic segmentation was evaluated by 5 metrics, including accuracy, sensitivity, specificity, positive, and negative. The experimental results show that the proposed method can achieve a good automatic segmentation in different resolutions and visual modes, small samples data achieve the optimal location performance at 1000 iterations with a correct position rate of 72.25%, and C-V model can reach the accuracy of 98.09% based on the correct location. Therefore, deep learning is a rather promising technique in the automatic segmentation of LAA from ultrasound images, and it can provide a good initial contour for the segmentation algorithm based on contour.

Key words: automatic segmentation, deep learning, C-V (Chan-Vese) model, Left Atrial Appendage (LAA), ultrasound image

中图分类号:

TP391.1

韩路易, 黄韫栀, 窦浩然, 白文娟, 刘奇. 基于深度学习的超声图像左心耳自动分割方法[J]. 计算机应用, 2019, 39(11): 3361-3365.

HAN Luyi, HUANG Yunzhi, DOU Haoran, BAI Wenjuan, LIU Qi. Automatic method for left atrial appendage segmentation from ultrasound images based on deep learning[J]. Journal of Computer Applications, 2019, 39(11): 3361-3365.

参考文献

[1] AL-SAADY N M, OBEL O A, CAMM A J. Left atrial appendage:structure, function, and role in thrombo-embolism[J]. Heart, 1999, 82(5):547-554.
[2] KONG B, LIU Y, HUANG H, et al. Left atrial appendage closure for thrombo-embolism prevention in patients with atrial fibrillation:advances and perspectives[J]. Journal of Thoracic Disease. 2015, 7(2):199-203.
[3] LEAL S, MORENO R, de SOUSA ALMEIDA M, et al. Evidence-based percutaneous closure of the left atrial appendage in patients with atrial fibrillation[J]. Current Cardiology Reviews. 2012, 8(1):37-42.
[4] WHITLOCK R P, HEALEY J S, CONNOLLY S J. Left atrial appendage occlusion does not eliminate the need for warfarin[J]. Circulation, 2009, 120(19):1927-1932.
[5] ABDELMONEIM S S, MULVAGH S L. Techniques to improve left atrial appendage imaging[J]. Journal of Atrial Fibrillation, 2014, 7(1):No.1059.
[6] CHAN T F, VESE L A. Active contours without edges[J]. IEEE Transactions on Image Processing, 2001, 10(2):266-277.
[7] LI C, KAO C Y, GORE J C, et al. Implicit active contours driven by local binary fitting energy[C]//Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2007:1-7.
[8] LI C, KAO C Y, GORE J C, et al. Minimization of region-scalable fitting energy for image segmentation[J]. IEEE Transactions on Image Processing, 2008, 17(10):1940-1949.
[9] LeCUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436-444.
[10] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2014:580-587.
[11] GIRSHICK R. Fast R-CNN[EB/OL].[2019-04-20]. https://arxiv.org/pdf/1504.08083.pdf.
[12] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[13] GOULD S, GAO T, KOLLER D. Region-based segmentation and object detection[C]//Advances in Neural Information Processing Systems 22. Cambridge, MA:MIT Press, 2009:655-663.
[14] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified, real-time object detection[EB/OL].[2019-04-20]. https://arxiv.org/pdf/1506.02640.pdf.
[15] REDMON J, FARHADI A. YOLO9000:better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:6517-6525.
[16] REDMON J, FARHADI A. YOLOv3:an incremental improvement[EB/OL].[2018-05-25]. https://arxiv.org/pdf/1804.02767.pdf.
[17] MAŠKA M, DANĚK O, GARASA S, et al. Segmentation and shape tracking of whole fluorescent cells based on the Chan-Vese model[J]. IEEE Transactions on Medical Imaging, 2013, 32(6):995-1006.
[18] WANG X, ZHENG C, LI C. Automated CT liver segmentation using improved Chan-Vese model with global shape constrained energy[C]//Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway:IEEE, 2011:3415-3418.
[19] MAAS A L, HANNUN A Y, NG A Y, et al. Rectifier nonlinearities improve neural network acoustic models[EB/OL].[2018-05-28].http://robotics.stanford.edu/~amaas/papers/relu_hybrid_icml2013_final.pdf

基于深度学习的超声图像左心耳自动分割方法

Automatic method for left atrial appendage segmentation from ultrasound images based on deep learning

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]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[2]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[3]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[4]	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.
[5]	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.
[6]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[7]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[8]	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.
[9]	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.
[10]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.
[11]	李亚芳, 梁烨, 冯韦玮, 祖宝开, 康玉健. 基于社区优化的深度网络嵌入方法[J]. 计算机应用, 2021, 41(7): 1956-1963.
[12]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.
[13]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[14]	侯笑晗, 金国栋, 谭力宁, 薛远亮. 基于自适应和最优特征的合成孔径雷达舰船检测方法[J]. 计算机应用, 2021, 41(7): 2150-2155.
[15]	史杨潇, 章军, 陈鹏, 王兵. 基于轻量级网络的钢铁表面缺陷分类[J]. 计算机应用, 2021, 41(6): 1836-1841.