Echocardiogram segmentation using active shape model and mean squared eigenvalue error

Abstract Cardiac function assessment using echocardiography is an essential step in daily cardiology. For this purpose, segmentation of images and, in particular, ventricle boundary segmentation poses several challenges due to shadows and speckle noise. Currently, the segmentation is done manually which is time-consuming and subjective. Therefore, providing an efficient and autonomous segmentation method could improve the evaluation efficiency and outcome. The focus of this paper is on active shape models (ASMs) to handle speckle noise, shadows, and dropouts in echocardiograms effectively, without the need for large training data. In this paper, an echocardiogram segmentation method using ASM, Nakagami and mean squared eigenvalues error (MSEE) is proposed. We propose the use of Nakagami distribution in providing a preprocess classification and hence improving the system performance. Additionally, we depart from the current practice in using (and manually entering) a percentage of eigenvalues in an appearance model of ASM. We show that the higher the percentage does not necessarily mean the better the performance. By integrating a mean squared error (MSE) evaluation method, we automate the choice of that percentage to warrant the minimum MSE. The simulation results are provided to show the effectiveness of the approach. In particular, we illustrate that using Nakagami would reduce the segmentation error. Also mean squared eigenvalues error (MSEE) will reduce the required total variance per landmark, and hence, the memory requirement will be decreased. Also, the proposed technique will provide the optimal total variance for each landmark, resulting in improved accuracy. The final results from segmentation ASM with Nakagami and MSEE illustrate a considerable reduction of the MSE error from 14.521 ± 7.36 in original ASM to 9.21 ± 3.85 pixels, and produced an average of 0.93 ± 0.02 DSI with insignificant additional processing time.

[1]  Huazhong Shu,et al.  Fast segmentation of ultrasound images by incorporating spatial information into Rayleigh mixture model , 2017, IET Image Process..

[2]  Nicholas Ayache,et al.  Features extraction and analysis methods for sequences of ultrasound Images , 1992, Image Vis. Comput..

[3]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[4]  David Rowlands,et al.  Segmentation of the Left Ventricle from Ultrasound Using Random Forest with Active Shape Model , 2013, 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation.

[5]  Curtis P. Langlotz,et al.  Video-based AI for beat-to-beat assessment of cardiac function , 2020, Nature.

[6]  W D Richard,et al.  Automated texture-based segmentation of ultrasound images of the prostate. , 1996, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[7]  Bram van Ginneken,et al.  Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks , 2016, IEEE Transactions on Medical Imaging.

[8]  C. Goodall.  Procrustes methods in the statistical analysis of shape , 1991 .

[9]  P. Shankar.  A general statistical model for ultrasonic backscattering from tissues , 2000 .

[10]  Dhanjoo N. Ghista,et al.  Unified model for interpreting multi-view echocardiographic sequences without temporal information , 2020, Appl. Soft Comput..

[11]  Ronald M. Summers,et al.  Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique , 2016 .

[12]  Huazhong Shu,et al.  Fast and accurate segmentation method of active shape model with Rayleigh mixture model clustering for prostate ultrasound images , 2020, Comput. Methods Programs Biomed..

[13]  Tim Cootes,et al.  An Introduction to Active Shape Models , 2000 .

[14]  Boudewijn P. F. Lelieveldt,et al.  Left Ventricle Segmentation from Contrast Enhanced Fast Rotating Ultrasound Images Using Three Dimensional Active Shape Models , 2009, FIMH.

[15]  Meng-Xing Tang,et al.  Fully Automatic Myocardial Segmentation of Contrast Echocardiography Sequence Using Random Forests Guided by Shape Model , 2018, IEEE Transactions on Medical Imaging.

[16]  A. Novell,et al.  Linear and nonlinear characterization of microbubbles and tissue using the Nakagami statistical model , 2017, Ultrasonics.

[17]  R. F. Wagner,et al.  Statistics of Speckle in Ultrasound B-Scans , 1983, IEEE Transactions on Sonics and Ultrasonics.

[18]  Frits Mastik,et al.  Fully automatic luminal contour segmentation in intracoronary ultrasound imaging-a statistical approach , 2004, IEEE Transactions on Medical Imaging.

[19]  Dinggang Shen,et al.  Segmentation of prostate boundaries from ultrasound images using statistical shape model , 2003, IEEE Transactions on Medical Imaging.

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

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

[22]  Ramy Arnaout,et al.  Fast and accurate view classification of echocardiograms using deep learning , 2018, npj Digital Medicine.

[23]  Jae Y. Shin,et al.  Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? , 2016, IEEE transactions on medical imaging.

[24]  Yongmin Kim,et al.  Parametric shape modeling using deformable superellipses for prostate segmentation , 2004, IEEE Transactions on Medical Imaging.

[25]  Nima Tajbakhsh,et al.  Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? , 2016, IEEE Transactions on Medical Imaging.

[26]  Tri Harsono,et al.  Improved echocardiography segmentation using active shape model and optical flow , 2019, TELKOMNIKA (Telecommunication Computing Electronics and Control).

[27]  Soosan Beheshti,et al.  Echocardiographic image segmentation using deep Res-U network , 2021, Biomed. Signal Process. Control..

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

[29]  Wei Zheng,et al.  Recurrent Aggregation Learning for Multi-View Echocardiographic Sequences Segmentation , 2019, MICCAI.

[30]  TianGe Zhuang,et al.  Applying improved fast marching method to endocardial boundary detection in echocardiographic images , 2003, Pattern Recognit. Lett..

[31]  Wei-Yen Hsu,et al.  Automatic Left Ventricle Recognition, Segmentation and Tracking in Cardiac Ultrasound Image Sequences , 2019, IEEE Access.

[32]  Ruzena Bajcsy,et al.  Fully Automated Echocardiogram Interpretation in Clinical Practice , 2018, Circulation.

[33]  J A Noble,et al.  Ultrasound image segmentation and tissue characterization , 2010, Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine.

[34]  Jesse S. Jin,et al.  Morphological image analysis of left-ventricular endocardial borders in 2D echocardiograms , 1996, Medical Imaging.

[35]  Carole Lartizien,et al.  RU-Net: A refining segmentation network for 2D echocardiography , 2019, 2019 IEEE International Ultrasonics Symposium (IUS).

[36]  Soosan Beheshti,et al.  Number of Source Signal Estimation by the Mean Squared Eigenvalue Error , 2018, IEEE Transactions on Signal Processing.

[37]  Boris Escalante-Ramírez,et al.  Left ventricle segmentation in fetal echocardiography using a multi-texture active appearance model based on the steered Hermite transform , 2016, Comput. Methods Programs Biomed..