|
|
|
| Pediatric Left Cardiac Echocardiography Segmentation via BiSeNet |
| Hu Yujin1, Lei Baiying1, Guo Libao1, Mao Muyi2, Jin Zelong2, Chen Siping1, Xia Bei2*, Wang Tianfu1* |
1(School of Biomedical Engineering, Health Science Center, Shenzhen University, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, Shenzhen 518071, Guangdong, China)
2(Department of Ultrasound, Shenzhen Children Hospital, Hospital of Shantou University, Shenzhen 518038, Guangdong, China) |
|
|
|
|
Abstract Accurate segmentation of pediatric echocardiography is an essential step for the later biomedical measurement and diagnose. Currently, it relies on sonographer′s manual segmentation, which is time consuming and redundant, and therefore may lead to mistakes. Deep learning methods have achieved remarkable results in the field of computer vision. Therefore, we proposed to extract features from pediatric echocardiography images via deep convolutional neural networks and segment key anatomical structures of the heart. Specifically, we used BiSeNet consisting of two components, spatial path and context path, to extract low and high level features, respectively, and then fused them via a feature fusion module to get the most important features, for accurate segmentation. We conducted experiments on a dataset consisting of 87 echocardiography videos (2216 images) collected from Shenzhen Children Hospital, and compared our prediction with sonographers′ ground truth. Results showed that BiSeNet was able to capture the structure feature of echocardiography images, and achieved 0.914 and 0.887 in term of Dice index in left ventricle and left atrium segmentation task, respectively. The proposed method could help with accurate pediatric echocardiography segmentation, and released sonographers from redundant work.
|
|
Received: 27 January 2019
|
|
|
|
|
|
[1] Mendis S, Puska P, Norrving B. Global atlas on cardiovascular disease prevention and control [M]. Geneva: World Health Organization, 2011: 1-57.
[2] Hoffman JIE, Kaplan S. The incidence of congenital heart disease [J]. Journal of the American College of Cardiology, 2002, 39(12): 1890-1900.
[3] Krasuski RA, Bashore TM. Congenital heart disease epidemiology in the United States: blindly feeling for the charging elephant [J]. Circulation, 2016, 134(2): 110-113.
[4] Chen Xinlin. A national survey of fetal congenital heart diseases in China [J]. Ultrasound in Obstetrics & Gynecology, 2015, 46(S1): 26-26.
[5] Badrinarayanan V, Kendall A, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
[6] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition [C] // the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[7] Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks [C] // Advances in Neural Information Processing Systems. Lake Tahoe: 2012: 1097-1105.
[8] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation [C] // the IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 3431-3440.
[9] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition [J]. arXiv, 2014, 1409: 1556.
[10] Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation [C] // Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
[11] Veni G, Moradi M, Bulu H, et al. Echocardiography segmentation based on a shape-guided deformable model driven by a fully convolutional network prior [C] // 2018 IEEE 15th International Symposium on Biomedical Imaging. Washington: IEEE, 2018: 898-902.
[12] Zheng Qiao, Delingette H, Duchateau N, et al. 3-D consistent and robust segmentation of cardiac images by deep learning with spatial propagation [J]. IEEE Transactions on Medical Imaging, 2018, 37(9): 2137-2148.
[13] Vigneault DM, Xie Weidi, Ho CY, et al. Ω-Net (Omega-Net): fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks [J]. Medical Image Analysis, 2018, 48: 95-106.
[14] Lopez L, Colan SD, Frommelt PC, et al. Recommendations for quantification methods during the performance of a pediatric echocardiogram: a report from the pediatric measurements writing group of the American Society of Echocardiography Pediatric and Congenital Heart Disease Council [J]. Journal of the American Society of Echocardiography, 2010, 23(5): 465-495.
[15] 夏焙. 小儿超声心动图定量分析的标准化 [J]. 中华医学超声杂志, 2014, 11(7): 525-528.
[16] Yu Changqian, Wang Jingbo, Peng Chao, et al. BiSeNet: bilateral segmentation network for real-time semantic segmentation [C] // the 15th European Conference on Computer Vision. Munich: 2018: 1-17.
[17] Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions [J]. arXiv, 2015, 1511: 07122.
[18] Peng Chao, Zhang Xiangyu, Yu Gang, et al. Large kernel matters—improve semantic segmentation by global convolutional network [C] // the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 1743-1751.
[19] Zhao Hengshuang, Shi Jianping, Qi Xiaojuan, et al. Pyramid scene parsing network [C] // the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 2881-2890.
[20] Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift [C] // International Conference on Machine Learning. Lille: 2015: 448-456.
[21] Hu Jie, Shen Li, Sun Gang. Squeeze-and-excitation networks [C] // The IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2017: 7132-7141.
[22] Xie Saining, Tu Zhuowen. Holistically-nested edge detection [J]. International Journal of Computer Vision, 2017, 125(1-3): 3-18.
[23] Paszke A, Gross S, Chintala S, et al. Automatic differentiation in PyTorch [C] // the 31st Conference on Neural Information Processing Systems. Long Beach: NIPS, 2017: 1-4.
[24] Graves A. Generating sequences with recurrent neural networks [J]. arXiv, 2013, 1308: 0850.
[25] Chen Liang-Chieh, Papandreou G, Schroff F, et al. Rethinking atrous convolution for semantic image segmentation [J]. arXiv, 2017, 1706: 05587.
[26] He Kaiming, Girshick R, Dollár P. Rethinking ImageNet pre-training [J]. arXiv, 2018, 1811: 08883.
[27] Geng Qichuan, Zhou Zhong, Cao Xiaochun. Survey of recent progress in semantic image segmentation with CNNs [J]. Science (China Information Sciences), 2018, 61(5): 1-18. |
|
|
|
