Journal of Digital Contents Society (디지털콘텐츠학회 논문지)

Digital Contents Society (한국디지털콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

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

SVM과 회전 불변 텍스처 특징을 이용한 TRUS 영상의 전립선 윤곽선 검출

  • 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)
  • Received : 2014.10.15
  • Accepted : 2014.12.20
  • Published : 2014.12.31
Download PDF
⟨ Previous Next ⟩

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.

전립선은 남자에게만 있는 장기이다. 전립선의 질병을 진단하기 위하여 일반적으로 TRUS 영상이 사용되는데, 희미한 전립선 경계나 잡음, 좁은 그레이 레벨 분포 때문에, 전립선의 경계를 검출하는 것은 상당히 어려운 작업 중의 하나이다. 본 논문에서는 SVM을 사용하여 TRUS 영상에서 자동적으로 전립선 분할을 하는 방법을 제안한다. 이 방법은 전처리, 가버 특징 추출, 훈련, 전립선 분할 과정으로 진행된다. 전처리 과정에서 잡음 제거는 스틱 필터와 top-hat 변환이 적용된다. 회전 불변 텍스처 추출을 위하여 가버 필터 뱅크가 사용된다. 훈련과정에서 SVM은 전립선과 비전립선의 각 특징을 얻기 위해 사용되며, 마지막으로 전립선 경계가 추출된다. 여러 실험 결과로 제안 방법은 충분히 유효하고, 의사의 수동 추출 방법과 비교했을 때 10%미만의 경계 차이를 보였다.

Keywords

References

  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. https://doi.org/10.1002/1097-0142(19950401)75:7+<1790::AID-CNCR2820751607>3.0.CO;2-Z
  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. https://doi.org/10.1109/42.544503
  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. https://doi.org/10.1109/TMI.2005.862743
  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. https://doi.org/10.1109/42.897813
  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. https://doi.org/10.1109/TMI.2003.809057
  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. https://doi.org/10.1109/TBME.2010.2094195
  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.

Cited by

  1. Extracting The Prostate Boundary Using Direction Features of Prostate Boundary On Ultrasound Prostate Image vol.21, pp.11, 2016, https://doi.org/10.9708/jksci.2016.21.11.103