Echocardiographic image segmentation using deep Res-U network

Abstract Cardiac function assessment using echocardiography is a crucial step in daily cardiology. However, cardiac boundary segmentation and in particular, ventricle segmentation is a challenging procedure due to shadows and speckle noise. Manual segmentation of the cardiac boundary is a time-consuming process which rules out conventional segmentation for many situations such as emergency cases and image-guided robotic interventions. Therefore, providing an efficient and robust autonomous segmentation method is crucial for such applications. In this paper, a fast and fully automatic deep learning framework for left ventricle segmentation is proposed. This model couples the advantages of ResNet and U-Net to provide reliable segmentation results. We propose a new encoder in the U-Net, defined as ResU which is a modified version of ResNet-50 and has a superiority over ResNet in data denoising. We trained this model on the dataset CAMUS (Cardiac Acquisitions for Multi-structure Ultrasound Segmentation) which is a large, publicly available and fully annotated dataset for 2D echocardiographic assessment. It is shown that this model outperforms other state-of-the-art methods in terms of accuracy with a Dice metric of 0.97 ± 0.01 .

[1]  Sander Dieleman,et al.  Rotation-invariant convolutional neural networks for galaxy morphology prediction , 2015, ArXiv.

[2]  Gustavo Carneiro,et al.  The Segmentation of the Left Ventricle of the Heart From Ultrasound Data Using Deep Learning Architectures and Derivative-Based Search Methods , 2012, IEEE Transactions on Image Processing.

[3]  Denis Friboulet,et al.  Fast and fully automatic 3-d echocardiographic segmentation using B-spline explicit active surfaces: feasibility study and validation in a clinical setting. , 2013, Ultrasound in medicine & biology.

[4]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[5]  Purang Abolmaesumi,et al.  Semi-Supervised Learning For Cardiac Left Ventricle Segmentation Using Conditional Deep Generative Models as Prior , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[6]  Wei Li,et al.  A fused deep learning architecture for viewpoint classification of echocardiography , 2017, Inf. Fusion.

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Baiying Lei,et al.  Fully Automatic Pediatric Echocardiography Segmentation Using Deep Convolutional Networks Based on BiSeNet , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[9]  Tanveer F. Syeda-Mahmood,et al.  Echocardiography segmentation based on a shape-guided deformable model driven by a fully convolutional network prior , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[10]  Carlos Alberto Silva,et al.  Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images. , 2016, IEEE transactions on medical imaging.

[11]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Ron Kikinis,et al.  Statistical validation of image segmentation quality based on a spatial overlap index. , 2004, Academic radiology.

[13]  Xujiong Ye,et al.  Segmentation of Left Ventricle in 2D Echocardiography Using Deep Learning , 2019, MIUA.

[14]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[15]  Henggui Zhang,et al.  VoxelAtlasGAN: 3D Left Ventricle Segmentation on Echocardiography with Atlas Guided Generation and Voxel-to-voxel Discrimination , 2018, MICCAI.

[16]  Leslie N. Smith,et al.  Cyclical Learning Rates for Training Neural Networks , 2015, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[17]  Kilian Q. Weinberger,et al.  Deep Networks with Stochastic Depth , 2016, ECCV.

[18]  Frederic Cervenansky,et al.  Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D Echocardiography , 2019, IEEE Transactions on Medical Imaging.

[19]  Lasse Lovstakken,et al.  2D left ventricle segmentation using deep learning , 2017, 2017 IEEE International Ultrasonics Symposium (IUS).

[20]  A. Skalski,et al.  Heart segmentation in echo images , 2011 .

[21]  J J Bax,et al.  Assessing right ventricular function: the role of echocardiography and complementary technologies , 2006, Heart.

[22]  Konstantinos Kamnitsas,et al.  Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation , 2017, IEEE Transactions on Medical Imaging.

[23]  Amir A. Amini,et al.  Tissue Doppler Imaging Optical Flow (TDIOF): A Combined B-Mode and Tissue Doppler Approach for Cardiac Motion Estimation in Echocardiographic Images , 2014, IEEE Transactions on Biomedical Engineering.

[24]  Nico de Jong,et al.  Left ventricular border tracking using cardiac motion models and optical flow. , 2011, Ultrasound in medicine & biology.

[25]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[26]  J. Alison Noble,et al.  Ultrasound image segmentation: a survey , 2006, IEEE Transactions on Medical Imaging.

[27]  Xiaohui Zhang,et al.  Real-Time Organ Tracking in Ultrasound Imaging Using Active Contours and Conditional Density Propagation , 2010, MIAR.

[28]  Gustavo Carneiro,et al.  Combining Multiple Dynamic Models and Deep Learning Architectures for Tracking the Left Ventricle Endocardium in Ultrasound Data , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..