Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

A Diagnostic Feature Subset Selection of Breast Tumor Based on Neighborhood Rough Set Model

Neighborhood 러프집합 모델을 활용한 유방 종양의 진단적 특징 선택

  • 손창식 (DGIST 웰니스융합연구센터) ;
  • 최락현 (DGIST 웰니스융합연구센터) ;
  • 강원석 (DGIST 웰니스융합연구센터) ;
  • 이종하 (계명대학교 의과대학 의용공학과)
  • Received : 2016.11.24
  • Accepted : 2016.12.12
  • Published : 2016.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

Feature selection is the one of important issue in the field of data mining and machine learning. It is the technique to find a subset of features which provides the best classification performance, from the source data. We propose a feature subset selection method using the neighborhood rough set model based on information granularity. To demonstrate the effectiveness of proposed method, it was applied to select the useful features associated with breast tumor diagnosis of 298 shape features extracted from 5,252 breast ultrasound images, which include 2,745 benign and 2,507 malignant cases. Experimental results showed that 19 diagnostic features were strong predictors of breast cancer diagnosis and then average classification accuracy was 97.6%.

특징선택은 데이터 마이닝, 기계학습 분야에서 가장 중요한 이슈 중 하나로, 원본 데이터에서 가장 좋은 분류 성능을 보여줄 수 있는 특징들을 찾아내는 방법이다. 본 논문에서는 정보 입자성을 기반으로 한 neighborhood 러프집합 모델을 이용한 특징선택 방법을 제안한다. 제안된 방법의 효과성은 5,252명의 유방 초음파 영상으로부터 추출된 298가지의 특징들 중에서 유방 종양의 진단과 관련된 유용한 특징들을 선택하는 문제에 적용되었다. 실험결과 19가지의 진단적 특징을 찾을 수 있었고, 이때에 평균 분류 정확성은 97.6%를 보였다.

Keywords

References

  1. F. Bessaoud, J. P. Daures, “Dietary Factors and Breast Cancer Risk: A Case Control Study Among a Population in Southern France,” Nutrition and Cancer, Vol. 60, No. 2, pp. 177-187, 2008. https://doi.org/10.1080/01635580701649651
  2. Yoo, Y. G., Choi, S. K., Hwang, S. J., and Kim, H. S., “Risk Factors of Breast Cancer According to Life Style,” Journal of The Korea Contents Association, Vol. 13, No. 4, pp. 262-272, 2013.
  3. Nam, S. J., “Screening and Diagnosis for Breast Cancers,” Journal of The Korean Medical Association, Vol. 52, No. 10, pp. 946-951, 2013. https://doi.org/10.5124/jkma.2009.52.10.946
  4. Chung, S. Y. and Han. B. K., "Breast Diagnostic Imaging," Seoul, Ilchokak, 2006.
  5. Bae, J. M., “On the Benefits and Harms of Mammography for Breast Cancer Screening in Korean Woman,” Korean Journal of Family Practice, Vol. 4, No. 1, pp. 1-6, 2014.
  6. Berg, W. A., “Rationale for a Trial of Screening Breast Ultrasound: American College of Radiology Imaging Network (ACRIN) 6666,” American Journal of Roentgenology, Vol. 180, No. 5, pp. 1225-1228, 2003. https://doi.org/10.2214/ajr.180.5.1801225
  7. Berg, W. A., “Supplemental Screening Sonography in Dense Breasts,” Radiologic Clinics of North America, Vol. 42, No. 5, pp. 845-851, 2004. https://doi.org/10.1016/j.rcl.2004.04.003
  8. Berg, W. A., “Beyond Standard Mammographic Screening: Mammography at Age Extremes, Ultrasound, and MR Imaging,” Radiologic Clinics of North America, Vol. 45, No. 5, pp. 895-906, 2007. https://doi.org/10.1016/j.rcl.2007.06.001
  9. Lim, S. Y., Lee, S. J., Shin, Y. K., Lee, S. N., Choi, J. Y., and Kang, D. R., “Comparison of the Diagnostic Value Between Mammography and Mammography with Breast Ultrasonography in Diagnosing Breast Cancer,” Korean Journal of Family Medicine, Vol. 24, No. 10, pp. 925-933, 2003.
  10. Berg, W. A., Blume, J. D., and Cormack, J. B., “Combined Screening with Ultrasound and Mammography vs. Mammography Alone in Women at Elevated Risk of Breast Cancer,” JAMA, Vol. 299, No. 18, pp. 2151-2163, 2008. https://doi.org/10.1001/jama.299.18.2151
  11. Jang, J. M., Yi, A., and Koo, H. R., “Differentiation of Breast Mass Using Automated Breast US: Application of US BI-RADS lexicon,” Journal of The Korean Society for Breast Screening, Vol. 8, No. 2, pp. 115-120, 2011.
  12. Giger, M. L., Chan, H. P., and Boone, J. "Anniversary Paper: History and Status of CAD and Quantitative Image Analysis: The Role of Medical Physics and AAPM," Medical Physics, Vol. 35, No. 12, pp. 5799-5820, 2008. https://doi.org/10.1118/1.3013555
  13. Guo, Y. H., Cheng, H. D., Huang, J. H., Tai, J. W., Zhao, W., and Sun, L., “Breast Ultrasound Image Enhancement Using Fuzzy Logic,” Ultrasound in Medicine and Biology, Vol. 32, No. 2, pp. 237-247, 2006. https://doi.org/10.1016/j.ultrasmedbio.2005.10.007
  14. Cheng, J. Z., Chou, Y. H., C. S., Huang, Chang, Y. C., Tiu, C. M., and Chen, K. W., "Computer-Aided US Diagnosis of Breast Lesions by Using Cell-Based Contour Grouping," Radiology, Vol. 255, No. 3 pp. 746-754, 2010.
  15. Sahiner, B., “Computer-Aided Characterization of Mammographic Masses: Accuracy of Mass Segmentation and its Effects on Characterization,” IEEE Transactions on Medical Imaging, Vol. 20, No. 12, pp. 1275-1284, 2001. https://doi.org/10.1109/42.974922
  16. Joo, S., Yang, Y. S., Moon, W. K., and Kim, H. C., “Computer-Aided Diagnosis of Solid Breast Nodules: Use of an Artificial Neural Network Based on Multiple Sonographic Feature,” IEEE Transactions on Medical Imaging, Vol. 23, No. 10, pp. 1292-1300, 2004. https://doi.org/10.1109/TMI.2004.834617
  17. Lee, J. H., Seong, Y. K., Chang, C. H., Park, J. M., Park, M. H., and Woo, K. G., "Fourier-Based Shape Feature Extraction Technique for Computer-Aided B-Mode Ultrasound Diagnosis of Breast Tumor," 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), August 28-September 1, San Diego, California, USA, pp. 6551-6554, 2012.
  18. Abonyi, J. and Szeifert, F., “Supervised Fuzzy Clustering for the Identification of Fuzzy Classifiers,” Pattern Recognition Letters, Vol. 14, No. 24, pp. 2195-2207, 2003.
  19. Goodman, D. E., Boggess, L., and Watkins, A. "Artificial Immune System Classification of Multiple-Class Problems," In Proceedings of Intelligent Engineering Systems, pp. 179-184, 2002.
  20. Setiono, R., "Generating Concise and Accurate Classification Rules for Breast Cancer Diagnosis," Artificial Intelligence in Medicine, Vol 18, No.3, pp. 205-217, 2000. https://doi.org/10.1016/S0933-3657(99)00041-X
  21. Akay, M. F., “Support Vector Machines Combined with Feature Selection for Breast Cancer Diagnosis,” Expert Systems with Applications, Vol. 36, No. 2, pp. 3240-3247, 2009. https://doi.org/10.1016/j.eswa.2008.01.009
  22. Lee, J. H., Seong, Y. K., Chang, C. H., Ko, E. Y., Cho, B. H., and Ku, J. H., "Computer-Aided Lesion Diagnosis in B-Mode Ultrasound by Border Irregularity and Multiple Sonographic Features," Proceedings of SPIE, Medical Imaging 2013, February 2013.
  23. Hu, Q. H., Yu, D. R., and Xie, Z. X., “Neighborhood Classifiers,” Expert Systems with Applications, Vol. 34, No. 2, pp. 866-876, 2008. https://doi.org/10.1016/j.eswa.2006.10.043
  24. Hu, Q. H., Yu, D. R., Liu, J. F., and Wu, C. X., “Neighborhood Rough Set Based Heterogeneous Feature Subset Selection,” Information Sciences, Vol. 178, No. 18, pp. 3577-3594, 2008. https://doi.org/10.1016/j.ins.2008.05.024
  25. Son, C. S., Kang, W. S., Choi, R. H., Park, H. S., Han, S. W., and Kim, Y. N., “A Probabilistic Knowledge Model for Analyzing Heart Rate Variability,” Journal of the Korea Industrial Systems Research, Vol. 20, No. 3, pp. 61-69, 2015.
  26. Ha, S. H. and Zhang, Z. Y., “Empirical Evaluation of Ensemble Approach for Diagnostic Knowledge Management,” The Journal of Information Systems, Vol. 20, No. 3, pp. 237-255, 2011. https://doi.org/10.5859/KAIS.2011.20.3.237