Advertisement

Classifying Breast Masses in Volumetric Whole Breast Ultrasound Data: A 2.5-Dimensional Approach

  • Gobert N. Lee
  • Toshiaki Okada
  • Daisuke Fukuoka
  • Chisako Muramatsu
  • Takeshi Hara
  • Takako Morita
  • Etsuo Takada
  • Tokiko Endo
  • Hiroshi Fujita
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6136)

Abstract

The aim of this paper is to investigate a 2.5-dimensional approach in classifying masses as benign or malignant in volumetric anisotropic voxel whole breast ultrasound data. In this paper, the term 2.5-dimensional refers to the use of a series of 2-dimensional images. While mammography is very effective in breast cancer screening in general, it is less sensitivity in detecting breast cancer in younger women or women with dense breasts. Breast ultrasonography does not have the same limitation and is a valuable adjunct in breast cancer detection. We have previously reported on the clinical value of volumetric data collected from a prototype whole breast ultrasound scanner. The current study focuses on a new 2.5-dimensional approach in analyzing the volumetric whole breast ultrasound data for mass classification. Sixty-three mass lesions were studied. Of them 33 were malignant and 30 benign. Features based on compactness, orientation, shape, depth-to-width ratio, homogeneity and posterior echo were measured. Linear discriminant analysis and receiver operating characteristic (ROC) analysis were employed for classification and performance evaluation. The area under the ROC curve (AUC) was 0.91 using all breast masses for training and testing and 0.87 using the leave-one-mass-out cross-validation method. Clinically significance of the results will be evaluated using a larger dataset from multi-clinics.

Keywords

ultrasound breast mass classification geometric feature echo feature 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Takada, E., Ikedo, Y., Fukuoka, D., Hara, T., Fujita, H., Endo, T., Morita, T.: Semi-Automatic Ultrasonic Full-Breast Scanner and Computer-Assisted Detection System for Breast Cancer Mass Screening. In: Proc. of SPIE Medical Imaging 2007: Ultrasonic Imaging and Signal Processing, vol. 6513, pp. 651310-1–651310-8. SPIE, Bellingham (2007)Google Scholar
  2. 2.
    Lee, G.N., Morita, T., Fukuoka, D., Ikedo, Y., Hara, T., Fujita, H., Takada, E., Endo, T.: Differentiation of Mass Lesions in Whole Breast Ultrasound Images: Volumetric Analysis. In: Radiological Society of North America, 94th Scientific Assembly and Annual Meeting Program, p. 456 (2008)Google Scholar
  3. 3.
    Lee, G.N., Fukuoka, D., Ikedo, Y., Hara, T., Fujita, H., Takada, E., Endo, T., Morita, T.: Classification of Benign and Malignant Masses in Ultrasound Breast Image Based on Geometric and Echo Features. In: Krupinski, E.A. (ed.) IWDM 2008. LNCS, vol. 5116, pp. 433–440. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  4. 4.
    Fukuoka, D., Hara, T., Fujita, H., Endo, T., Kato, Y.: Automated Detection and Classification of Masses on Breast Ultrsonograms and its 3D Imaging Technique. In: Yaffe, M.J. (ed.) IWDM 2000: 5th International Workshop on Digital Mammography, pp. 182–188. Medical Physics, Madison (2001)Google Scholar
  5. 5.
    Fukuoka, D., Hara, T., Fujita, H.: Detection, Characterization, and Visualization of Breast Cancer Using 3D Ultrasound Images. In: Suri, J.S., Rangayyan, R.M. (eds.) Recent Advances in Breast Imaging, Mammography, and Computer-Aided Diagnosis of Breast Cancer, pp. 557–567. SPIE, Bellingham (2006)CrossRefGoogle Scholar
  6. 6.
    Ikedo, Y., Fukuoka, D., Hara, T., Fujita, H., Takada, E., Endo, T., Morita, T.: Development of a Fully Automatic Scheme for Detection of Masses in Whole Breast Ultrasound Images. Med. Phys. 34(11), 4378–4388 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Gobert N. Lee
    • 1
  • Toshiaki Okada
    • 2
  • Daisuke Fukuoka
    • 3
  • Chisako Muramatsu
    • 2
  • Takeshi Hara
    • 2
  • Takako Morita
    • 4
  • Etsuo Takada
    • 5
  • Tokiko Endo
    • 6
  • Hiroshi Fujita
    • 2
  1. 1.School of Computer Science, Engineering and MathematicsFlinders UniversityAdelaideAustralia
  2. 2.Department of Intelligent Image Information, Division of Regeneration and, Advanced Medical Sciences, Graduate School of MedicineGifu UniversityGifuJapan
  3. 3.Technology Education, Faculty of EducationGifu UniversityGifuJapan
  4. 4.Department of Mammary GlandChunichi HospitalNagoyaJapan
  5. 5.Division of Medical Ultrasonics, Center of Optical MedicineDokkyo Medical, UniversityTochigiJapan
  6. 6.Department of RadiologyNational Hospital Organization Nagoya Medical, CenterNagoyaJapan

Personalised recommendations