Stochastic region competition algorithm for Doppler sonography segmentation.

PURPOSE A probabilistic image segmentation algorithm called stochastic region competition is proposed for performing Doppler sonography segmentation. METHODS The image segmentation is conducted by maximizing a posteriori that models histogram likelihood, gradient likelihood, and a spatial prior. The optimization is done by a modified expectation and maximization (EM) method that aims to improve computation efficiency and avoid local optima. RESULTS The algorithm was tested on 155 color Doppler sonograms and compared with manual delineations. The qualitative assessment shows that our algorithm is able to segment mass lesions under the condition of low image quality and the interference of the color-encoded Doppler information. The quantitative assessment analysis shows that the average distance between the algorithm-generated boundaries and manual delineations is statistically comparable to the variability of manual delineations. The ratio of the overlapping area between the algorithm-generated boundaries and manual delineations is also comparable to that between different sets of manual delineations. A reproductivity test was conducted to confirm that the result is statistically reproducible. CONCLUSIONS The algorithm can be used to perform Doppler sonography segmentation and to replace the tedious manual delineation task in clinical application.

[1]  Yongmin Kim,et al.  A methodology for evaluation of boundary detection algorithms on medical images , 1997, IEEE Transactions on Medical Imaging.

[2]  C. Sehgal,et al.  Renal blood flow changes induced with endothelin-1 and fenoldopam mesylate at quantitative Doppler US: initial results in a canine study. , 2001, Radiology.

[3]  Berkman Sahiner,et al.  A new automated method for the segmentation and characterization of breast masses on ultrasound images. , 2009, Medical physics.

[4]  King-Jen Chang,et al.  Association of Color Doppler Vascularity Index and Microvessel Density With Survival in Patients with Gastric Cancer , 2002, Annals of surgery.

[5]  Woo Kyung Moon,et al.  Segmentation of breast tumor in three-dimensional ultrasound images using three-dimensional discrete active contour model. , 2003, Ultrasound in medicine & biology.

[6]  Jun Xie,et al.  Segmentation of kidney from ultrasound images based on texture and shape priors , 2005, IEEE Transactions on Medical Imaging.

[7]  Ruey-Feng Chang,et al.  Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors , 2004, Breast Cancer Research and Treatment.

[8]  D. Adler,et al.  Doppler ultrasound color flow imaging in the study of breast cancer: preliminary findings. , 1990, Ultrasound in medicine & biology.

[9]  F. Hsieh,et al.  Clinical significance of intratumoral blood flow in cervical carcinoma assessed by color doppler ultrasound , 1995, Cancer.

[10]  E. Conant,et al.  Quantitative vascularity of breast masses by Doppler imaging: regional variations and diagnostic implications. , 2000, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[11]  D. S. Bell,et al.  Segmentation and analysis of colour Doppler images of tumour vasculature. , 1995, Ultrasound in medicine & biology.

[12]  U. Hamper,et al.  Transvaginal color Doppler sonography of adnexal masses: differences in blood flow impedance in benign and malignant lesions. , 1993, AJR. American journal of roentgenology.

[13]  K. Badr,et al.  Role for Doppler ultrasound in the assessment of renal circulation: effects of dopamine and dobutamine on renal hemodynamics in humans. , 1995, Nephron.

[14]  H Ermert,et al.  Segmentation of 3D intravascular ultrasonic images based on a random field model. , 2000, Ultrasound in medicine & biology.

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

[16]  Zoran B Popović,et al.  Assessment of left ventricular function by cardiac ultrasound. , 2006, Journal of the American College of Cardiology.

[17]  J. Folkman.  Role of angiogenesis in tumor growth and metastasis. , 2002, Seminars in oncology.

[18]  Milan Sonka,et al.  Automatic segmentation of echocardiographic sequences by active appearance motion models , 2002, IEEE Transactions on Medical Imaging.

[19]  H. Markus,et al.  Asymptomatic Embolization Detected by Doppler Ultrasound Predicts Stroke Risk in Symptomatic Carotid Artery Stenosis , 2005, Stroke.

[20]  Sheng-Fang Huang,et al.  Solid Breast Masses: Neural Network Analysis of Vascular Features at Three-dimensional Power Doppler Us for Benign or Malignant Classification Materials and Methods , 2006 .

[21]  Jie-Zhi Cheng,et al.  Cell-based two-region competition algorithm with a map framework for boundary delineation of a series of 2D ultrasound images. , 2007, Ultrasound in medicine & biology.

[22]  Ralph M Bunte,et al.  The antivascular action of physiotherapy ultrasound on a murine tumor: role of a microbubble contrast agent. , 2007, Ultrasound in medicine & biology.

[23]  A. Yuan,et al.  Differentiation of benign and malignant cervical lymph nodes with color Doppler sonography. , 1994, AJR. American journal of roentgenology.

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

[25]  M. Fujita,et al.  Color Doppler flow imaging of liver tumors. , 1990, AJR. American journal of roentgenology.

[26]  D. Fraker,et al.  An integrated approach to measuring tumor oxygen status using human melanoma xenografts as a model. , 2003, Cancer research.

[27]  Dar-Ren Chen,et al.  Watershed segmentation for breast tumor in 2-D sonography. , 2004, Ultrasound in medicine & biology.

[28]  J. Folkman.  Angiogenesis in cancer, vascular, rheumatoid and other disease , 1995, Nature Medicine.

[29]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[30]  J. Chang,et al.  Patients with Breast Cancer: Differences in Color Doppler Flow and Gray-Scale US Features of Benign and Malignant Axillary Lymph Nodes , 2000, Radiology.

[31]  Lubomir M. Hadjiiski,et al.  Computerized characterization of breast masses on three-dimensional ultrasound volumes. , 2004, Medical physics.

[32]  R. Shukla,et al.  Color doppler ultrasound as an objective assessment tool for chemotherapeutic response in advanced breast cancer , 2005, Breast cancer.

[33]  D. M. Titterington,et al.  t -Tests, F -Tests and Otsu's Methods for Image Thresholding , 2011, IEEE Trans. Image Process..

[34]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[35]  Giancarlo Pennati,et al.  Computational Patient-Specific Models Based on 3-D Ultrasound Data to Quantify Uterine Arterial Flow During Pregnancy , 2008, IEEE Transactions on Medical Imaging.

[36]  Dinggang Shen,et al.  Deformable segmentation of 3-D ultrasound prostate images using statistical texture matching method , 2006, IEEE Transactions on Medical Imaging.

[37]  Stefano Forti,et al.  Novel methods for the determination of the angiogenic activity of human tumors , 2004, Breast Cancer Research and Treatment.

[38]  Chiun-Sheng Huang,et al.  Breast cancer vascularity: Color Doppler sonography and histopathology study , 1996, Breast Cancer Research and Treatment.

[39]  Ming-Yang Chang,et al.  Tumor Vascular Pattern and Blood Flow Impedance in the Differential Diagnosis of Leiomyoma and Adenomyosis by Color Doppler Sonography , 1999, Journal of Assisted Reproduction and Genetics.

[40]  F. Hsieh,et al.  Color Doppler vascularity index can predict distant metastasis and survival in colon cancer patients. , 2000, Cancer research.

[41]  M. Friedman.  A Comparison of Alternative Tests of Significance for the Problem of $m$ Rankings , 1940 .

[42]  S M Evans,et al.  Doppler ultrasound imaging detects changes in tumor perfusion during antivascular therapy associated with vascular anatomic alterations. , 2001, Cancer research.