Convolutional Neural Network for Segmentation and Measurement of Intima Media Thickness

The measurement of Carotid Intima Media Thickness (IMT) on Common Carotid Artery (CCA) is a principle marker of risk of cardiovascular disease. This paper presents a novel method of using deep Convolutional Neural Network (CNN) for identification and measurement of IMT on the far wall of the artery. The Region of Interest (ROI) is extracted using CNN architecture with 8 layers. 110 subjects are taken for the study. Each subject is recorded with one Right Common Carotid Artery (RCCA) and Left Common Carotid Artery (LCCA) frame resulting in 220 recordings. Patch based segmentation with 2640 patches are given to the training network for ROI localization. Intima Media Complex (IMC) is the area where IMT is measured. This region is extracted after defining the ROI. Keeping in mind the end objective of measurement of IMT values binary threshold with snake algorithm is applied to extract the lumen-intima and media-adventitia boundary. IMT values are measured for 20 cases and mean difference is found to be 0.08 mm.

[1]  Guang-Zhong Yang,et al.  Deep Learning for Health Informatics , 2017, IEEE Journal of Biomedical and Health Informatics.

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

[3]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[4]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[5]  Xuelong Li,et al.  A Novel Segmentation Approach Combining Region- and Edge-Based Information for Ultrasound Images , 2017, BioMed research international.

[6]  José-Luis Sancho-Gómez,et al.  Fully automatic segmentation of ultrasound common carotid artery images based on machine learning , 2015, Neurocomputing.

[7]  A. Govardhan,et al.  Active Contours and Image Segmentation: The Current State Of the Art , 2012 .

[8]  Leonid Karlinsky,et al.  A Region Based Convolutional Network for Tumor Detection and Classification in Breast Mammography , 2016, LABELS/DLMIA@MICCAI.

[9]  N. Santhiyakumari,et al.  Non-invasive evaluation of carotid artery wall thickness using improved dynamic programming technique , 2008, Signal Image Video Process..

[10]  Raymond Chan,et al.  Anisotropic edge-preserving smoothing in carotid B-mode ultrasound for improved segmentation and intima-media thickness (IMT) measurement , 2000, Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163).

[11]  Pierre Baldi,et al.  The dropout learning algorithm , 2014, Artif. Intell..

[12]  Tomas Gustavsson,et al.  A multiscale dynamic programming procedure for boundary detection in ultrasonic artery images , 2000, IEEE Transactions on Medical Imaging.

[13]  Christos P. Loizou,et al.  Snakes based segmentation of the common carotid artery intima media , 2007, Medical & Biological Engineering & Computing.

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

[15]  Hayit Greenspan,et al.  Fully Convolutional Network for Liver Segmentation and Lesions Detection , 2016, LABELS/DLMIA@MICCAI.

[16]  F. Faita,et al.  Real‐time Measurement System for Evaluation of the Carotid Intima‐Media Thickness With a Robust Edge Operator , 2008, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[19]  T Gustavsson,et al.  A new automated computerized analyzing system simplifies readings and reduces the variability in ultrasound measurement of intima-media thickness. , 1997, Stroke.

[20]  K. Jayanthi,et al.  Analysis on various segmentation techniques – IMT measurement of common carotid artery , 2017, TENCON 2017 - 2017 IEEE Region 10 Conference.

[21]  Jeny Rajan,et al.  Segmentation of intima media complex from carotid ultrasound images using wind driven optimization technique , 2018, Biomed. Signal Process. Control..

[22]  Arno W. Hoes,et al.  Common carotid intima-media thickness and risk of stroke and myocardial infarction: the Rotterdam Study. , 1997, Circulation.

[23]  Xiaoyi Jiang,et al.  Detections of Arterial Wall in Sonographic Artery Images Using Dual Dynamic Programming , 2008, IEEE Transactions on Information Technology in Biomedicine.

[24]  R H Selzer,et al.  Improved common carotid elasticity and intima-media thickness measurements from computer analysis of sequential ultrasound frames. , 2001, Atherosclerosis.

[25]  Christos P. Loizou,et al.  Segmentation of the Common Carotid Intima-Media Complex in Ultrasound Images Using Active Contours , 2012, IEEE Transactions on Biomedical Engineering.

[26]  Michele Ceccarelli,et al.  An Active Contour Approach To Automatic Detection Of The Intima-Media Thickness , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[27]  Ronald M. Summers,et al.  An analysis of robust cost functions for CNN in computer-aided diagnosis , 2018, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[28]  U. Rajendra Acharya,et al.  Constrained snake vs. conventional snake for carotid ultrasound automated IMT measurements on multi-center data sets. , 2012, Ultrasonics.

[29]  K. B. Jayanthi,et al.  Automated lumen segmentation and estimation of numerical attributes of common carotid artery using longitudinal B-mode ultrasound images , 2013, 2013 IEEE Point-of-Care Healthcare Technologies (PHT).

[30]  M. A. Aswathy,et al.  Analysis of the performance of various algorithms for the segmentation of the carotid artery , 2012, 2013 IEEE Point-of-Care Healthcare Technologies (PHT).

[31]  Yu Bai,et al.  Automated Measurement Method of Common Carotid Artery Intima-Media Thickness in Ultrasound Image Based on Markov Random Field Models , 2015 .

[32]  R. S. D. Wahida Banu,et al.  A non-invasive study of alterations of the carotid artery with age using ultrasound images , 2006, Medical and Biological Engineering and Computing.

[33]  Jasjit S. Suri,et al.  Characterization of a Completely User-Independent Algorithm for Carotid Artery Segmentation in 2-D Ultrasound Images , 2007, IEEE Transactions on Instrumentation and Measurement.

[34]  Liexiang Fan,et al.  A semiautomated ultrasound border detection program that facilitates clinical measurement of ultrasound carotid intima-media thickness. , 2005, Journal of the American Society of Echocardiography : official publication of the American Society of Echocardiography.

[35]  Jasjit S. Suri,et al.  User-independent Plaque Characterization and Accurate IMT Measurement of Carotid Artery Wall using Ultrasound , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[36]  Faouzi Benzarti,et al.  Speckle Noise Reduction in Medical Ultrasound Images , 2013, ArXiv.

[37]  Myoung-Hee Kim,et al.  Boundary detection in carotid ultrasound images using dynamic programming and a directional Haar-like filter , 2010, Comput. Biol. Medicine.

[38]  P. Pignoli,et al.  Evaluation of atherosclerosis with B-mode ultrasound imaging. , 1988, The Journal of nuclear medicine and allied sciences.

[39]  C Yamini,et al.  Classification using Convolutional Neural Network for Heart and Diabetics Datasets , 2016 .

[40]  A. Pietrosanto,et al.  An automatic measurement system for the evaluation of carotid intima-media thickness , 2000, Proceedings of the 17th IEEE Instrumentation and Measurement Technology Conference [Cat. No. 00CH37066].

[41]  Sergio Shiguemi Furuie,et al.  Automatic measurement of carotid diameter and wall thickness in ultrasound images , 2002, Computers in Cardiology.

[42]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[43]  Vibha Vyas,et al.  A novel training algorithm for convolutional neural network , 2016, Complex & Intelligent Systems.

[44]  Quan Liang,et al.  A dynamic programming procedure for automated ultrasonic measurement of the carotid artery , 1994, Computers in Cardiology 1994.

[45]  Rafael Verdú,et al.  Frequency-domain active contours solution to evaluate intima-media thickness of the common carotid artery , 2015, Biomed. Signal Process. Control..

[46]  João Manuel R. S. Tavares,et al.  Automatic segmentation of the lumen of the carotid artery in ultrasound B-mode images , 2013, Medical Imaging.

[47]  Hans Burkhardt,et al.  Using snakes to detect the intimal and adventitial layers of the common carotid artery wall in sonographic images , 2002, Comput. Methods Programs Biomed..