A dynamic texture based segmentation method for ultrasound images with Surfacelet, HMT and parallel computing
- 73 Downloads
To segment regions of interest (ROIs) from ultrasound images, one novel dynamic texture based algorithm is presented with surfacelet transform, hidden Markov tree (HMT) model and parallel computing. During surfacelet transform, the image sequence is decomposed by pyramid model, and the 3D signals with high frequency are decomposed by directional filter banks. During HMT modeling, distribution of coefficients is described with Gaussian mixture model (GMM), and relationship of scales is described with scale continuity model. From HMT parameters estimated through expectation maximization, the joint probability density is calculated and taken as feature value of image sequence. Then ROIs and non-ROIs in collected sample videos are used to train the support vector machine (SVM) classifier, which is employed to identify the divided 3D blocks from input video. To improve the computational efficiency, parallel computing is implemented with multi-processor CPU. Our algorithm has been compared with the existing texture based approaches, including gray level co-occurrence matrix (GLCM), local binary pattern (LBP), Wavelet, for ultrasound images, and the experimental results prove its advantages of processing noisy ultrasound images and segmenting higher accurate ROIs.
KeywordsDynamic texture Surfacelet transform HMT model Parallel computing Ultrasound images
This work was supported by National Basic Research Program of China (973 Program, No. 2011CB707904).
- 13.Loizou CP, Pattichis CS, Pantziaris M, Kyriacou E, Nicolaides A (2017) Texture feature variability in ultrasound video of the atherosclerotic carotid plaque. IEEE J Translat Eng Health Med 5(99):1800509Google Scholar
- 22.Rezaeifar B, Saadatmand-Tarzjan M (2017) A new algorithm for multimodal medical image fusion based on the surfacelet transform. 7th Int Conf Comput Knowledge Eng (ICCKE): 396–400Google Scholar
- 23.Rueda S, Fathima S, Knight CL, Yaqub M, Papageorghiou AT, Rahmatullah B, Foi A, Maggioni M, Pepe A, Tohka J, Stebbing RV, McManigle JE, Ciurte A, Bresson X, Cuadra MB, Sun C, Ponomarev GV, Gelfand MS, Kazanov MD, Wang CW, Chen HC, Peng CW, Hung CM, Noble JA (2014) Evaluation and comparison of current fetal ultrasound image segmentation methods for biometric measurements: a grand challenge. IEEE Trans Med Imaging 33(4):797–813CrossRefGoogle Scholar
- 25.Sridar P, Kumar A, Li C, Woo J, Quinton A, Benzie R, Peek MJ, Feng D, Kumar RK, Nanan R, Kim J (2017) Automatic measurement of thalamic diameter in 2-D fetal ultrasound brain images using shape prior constrained regularized level sets. IEEE J Biomed Health Inform 21(4):1069–1078CrossRefGoogle Scholar
- 31.Yang X, Jin J, Xu M, Wu H, He W, Chi MY, Ding M (2013) Ultrasound common carotid artery segmentation based on active shape model. Comput Math Methods Med 2013:1–11Google Scholar