BREAST STRAIN IMAGING: A CAD FRAMEWORK - Deformable Models - page 284

6. CONCLUSION
In this chapter, the level set segmentation framework plays an important role
in extracting a tumor contour. All follow-up lesion analyses were based on credible
segmentation results. If the adopted segmentation method is not robust, the corre-
sponding tumor analyses will become suspect. In order to increase the accuracy of
level set segmentation, some image preprocessing techniques were adopted to re-
duce the effects from noise and speckle on ultrasound images. In the experiments,
the sufficient results proved that the performance of the proposed CAD system
was significant.
However, there are some disadvantages of the level set method, the major
one being that if some objects are embedded in another object, the level set will
not capture all objects of interest. This is especially true if embedded objects are
asymmetrically situated. Fortunately, most of the cases from our breast ultrasound
sources involved only one tumor. Nevertheless, the above-mentioned problem
must be solved in the future if we are to study the level set technique in depth.
7. REFERENCES
1. American Cancer Society. 2004. Cancer facts and figures 2004 . Arlington, VA: American
Cancer Society.
2. Ganott MA, Harris KM, Klaman HM, Keeling TL. 1999. Analysis of false-negative cancer
cases identified with a mammography audit. Breast J. 5 (3):166-175.
3. Crystal P, SD Strano, Shcharynski S, Koretz MJ. 2003. Using sonography to screen women
with mammographically dense breasts. AJR 181 (1):177-182.
4. Bassett LW, Ysrael M, Gold RH, Ysrael C. 1991. Usefulness of mammography and sonography
in women less than 35 years of age. Radiology 180 (3):831-835.
5. Jackson VP. 1990. The role of the US in breast imaging. Radiology 177 (2):305-311.
6. Stavros AT, Thickman D, Rapp CL, Dennis MA, Parker SH, Sisney GA. 1995. Solid breast
nodules: use of sonography to distinguish between benign and malignant lesions. Radiology
196 (no. 1):123-134.
7. Drukker K, Giger ML, Horsch K, Kupinski MA, Vyborny CJ, Mendelson EB. 2002. Comput-
erized lesion detection on breast ultrasound. Med Phys 29 (7):1438-1446.
8. Horsch K, Giger ML, Venta LA, Vyborny CJ. 2002. Computerized diagnosis of breast lesions
on ultrasound. Med Phys 29 (2):157-164.
9. Chang RF, Kuo WJ, Chen DR, Huang YL, Lee JH, Chou YH. 2000. Computer-aided diagnosis
for surgical office-based breast ultrasound. Arch Surg 135 (6):696-699.
10. Kuo WJ, Chang RF, Moon WK, Lee CC, Chen DR. 2002. Computer-aided diagnosis of breast
tumors with different US systems. Acad Radiol 9 (7):793-799.
11. ChenDR, ChangRF, ChenWM, MoonWK. 2003. Computer-aided diagnosis for 3-dimensional
breast ultrasonography. Arch Surg 138 (3):296-302.
12. Chen DR, Kuo WJ, Chang RF, Moon WK, Lee CC. 2002. Use of the bootstrap technique with
small training sets for computer-aided diagnosis in breast ultrasound. Ultrasound Med Biol
28 (7):897-902.
13. Chang RF, Wu WJ, Moon WK, Chen DR. 2003. Improvement in breast tumor discrimina-
tion by support vector machines and speckle-emphasis texture analysis. Ultrasound Med Biol
29 (5):679-686.