Browse > Article
http://dx.doi.org/10.9728/dcs.2014.15.6.675

Detecting the Prostate Contour in TRUS Image using Support Vector Machine and Rotation-invariant Textures  

Park, Jae Heung (Gyeongsang Nat'l Univ. Dept. of Computer Science)
Seo, Yeong Geon (Gyeongsang Nat'l Univ. Dept. of Computer Science, Graduate school of Cultural Convergence)
Publication Information
Journal of Digital Contents Society / v.15, no.6, 2014 , pp. 675-682 More about this Journal
Abstract
Prostate is only an organ of men. To diagnose the disease of the prostate, generally transrectal ultrasound(TRUS) images are used. Detecting its boundary is a challenging and difficult task due to weak prostate boundaries, speckle noise and the short range of gray levels. In this paper a method for automatic prostate segmentation in TRUS images using Support Vector Machine(SVM) is presented. This method involves preprocessing, extracting Gabor feature, training, and prostate segmentation. The speckle reduction for preprocessing step has been achieved by using stick filter and top-hat transform has been implemented for smoothing. Gabor filter bank for extraction of rotation-invariant texture features has been implemented. SVM for training step has been used to get each feature of prostate and nonprostate. Finally, the boundary of prostate is extracted. A number of experiments are conducted to validate this method and results shows that the proposed algorithm extracted the prostate boundary with less than 10% relative to boundary provided manually by doctors.
Keywords
Gabor feature; Prostate Cancer; Prostate Contour; SVM;
Citations & Related Records
연도 인용수 순위
  • Reference
1 http://www.cancer.org/Research/CancerFactsFigures/ CancerFactsFigures/cancer-facts-figures-2011.
2 Cancer Facts and Figures. American Cancer Society. http://www.cancer.org.
3 Mettlin C: American society national cancer detection project. Cancer 1995, 75:1790-1794.   DOI
4 A. Chakraborty, and etc, "Deformable boundary finding in medical images by integrating gradient and region information," IEEE Trans. Med. Imag., Vol. 15, No. 6, Dec. 1996, pp. 859-870.   DOI   ScienceOn
5 P. D. Grimm, , and etc, "Ultrasound guided transperineal implantation of iodine 125 and palladium 103 for the treatment of early stage prostate cancer," Atlas Urol. Clin. No. Amer., Vol. 2, 1994, pp. 113-125.
6 Y.Zhan and D. Shen , "Deformable Segmentation of 3-D Ultrasound Prostate Images Using Statistical Texture Matching Method", IEEE Trans. on Medical Imaging, Vol. 25, March 2006, pp.245-255.   DOI   ScienceOn
7 A. Rafiee, , and etc, "A Novel Prostate Segmentation Algorithm in TRUS Images", World Academy of Science, Eng. and Tech. 45, 2008, pp. 120-124.
8 S. Pathak, and etc, "Edge-guided boundary delineati on in prostate ultrasound images", IEEE Trans. Med. Imag., Vol. 19, No. 12, Dec. 2000, pp. 1211-1219.   DOI   ScienceOn
9 D. Shen, Y. Zhan, and C. Davatzikos, "Segmentation prostate boundaries from ultrasound images using statistical shape model," IEEE Trans. Med. Imag., Vol. 22, No. 4, Apr. 2003, pp. 539-551.   DOI   ScienceOn
10 F. Shao, K. Ling, and W. Ng, "3-D prostate surface detection from ultrasound images based on level set method," in Proc. MICCAI 2003, 2003, pp. 389-396.
11 P. Yan, and etc, "Adaptively Learning Local Shape Statistics for Prostate Segmentation in Ultrasound", IEEE Trans. On Biomedical Engineering, Vol. 58, No. 3, Mar. 2011, pp.633-641.   DOI   ScienceOn
12 H. Akbari, and etc,"3D segmentation of prostate US images using wavelet transform", Proc. of SPIE 7962, 2011
13 B. E. Boser, and etc,."A training algorithm for optim al margin classifiers", In D. Haussler, editor, 5th Annual ACM Workshop on COLT, 1992, pp. 144-152.