Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지

Computer-Aided Detection of Clustered Microcalcifications using Texture Analysis and Neural Network in Digitized X-ray Mammograms

X-선 유방영상에서 텍스처 분석과 신경망을 이용한 군집성 미세석회화의 컴퓨터 보조검출

  • 김종국 (삼성전자 기술총괄 소프트웨어센타) ;
  • 박정미 (울산대학교 의과대학, 한국과학기술원 정보 및 통신공학과)
  • Published : 1998.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

Clustered microcalcifications on X-ray mammograms are an important sign for early detection of breast cancer. This paper proposes a computer-aided diagnosis method for the detection of clustered microcalcifications and marking their locations on digitized mammograms. The proposed detection method consists of the region of interest (ROI) selection, the film-artifact removal, the surrounding texture analysis method for the detection of clustered microcalcifications, which is based on the second-order histogram in two nested surrounding regions on the current pixel. This paper also describes the effectiveness of the proposed film-artifact removal filter in terms of the classification performance with the receiver operating-characteristics(ROC) analysis. A three-layer backpropagation neural network is employed as a classifier. The appropriate marking for the locations of clustered microcalcifications can be used to alert radiologists to locations of suspicious lesions.

X-선 유방영상에서 군집성 미세석회화는 유방암의 조기 검출에 중요한 징후로 이용된다. 본 논문은 X-선 유방영상에서 군집성 미세석회를 검출하여 그것의 위치를 표시하는 컴퓨터 보조 검출 방법을 제안한다. 제안된 검출방법의 구성도는 ROI9region of interest)선택, 필름흠제거, srdm(surrounding region dependence method), 분류기, 그리고 위치 표시로 구성되어 있다. SRDM은 이미 저자들에 의해 제안되었으며, 이것은 현재의 픽셀을 둘러싸고 있는 두 개의 영역에서의 2차 히스토그램에 근거한 통계적인 텍스처(texture)분석 방법이며 X-선 유방영상에서 군집성 미세석회화의 검출을 위해 제안되었다. 또한, 본 논문에서 제안된 필름흠 제거 필터의 효과는 ROC (receiver operating-characteristics) 분석에 의한 분류 성능 측면에서 평가되어진다. 정상조직(normal tissue)과 군집성 미세석회화를 포함한 조직을 분류하기 위해 3계층 backpropagation 신경망이 분류기로 이용되었다. 검출된 군집성 미세석회화의 위치와 적절한 표시를 함으로써 진단방사선의사에게 더 많은 주의를 상기시킬 수 있다

Keywords

References

  1. Radioloy v.184 Analysis of cancers missed at screening mammography R. G. Bird;R. G. Wallace;B. C. Yankaskas
  2. Phys. in Med. and Biol. v.32 X-ray characterization of normal and neoplastic breat tissues P. C. Johns;M. J. Yaffe
  3. Radiology v.167 Nonpalpable breast lesions: Recommendations for biopsy based on suspicion of caracinoma at mammography F. M. Hall;J. M. Storella;D. Z. Silverstone et al.
  4. Breast Imaging D. B. Kopans
  5. Med. Phys. v.14 Image feature analysis and computer-aided diagnosis in digital radipgraphy. I. Automated detection of micro calcifications in mammography H. P. Chan;K. Doi;S. Galhotra(et al.)
  6. J. of VLSI Signal Processing Systems for Signal, Image, and Video Technology v.18 no.3 Detection of clustered microcalcifications on mammograms using artificial neural network and surrounding region dependence method J. K. Kim;J. M. Park;K. S. Song;H. W. Park
  7. submitted to IEEE Trand. on Medical Imaging Textural features for detection of the microcalcifications on digitized mammograms J. K. Kim;H. W. Park
  8. IEEE Trans. on Medical Imaging v.16 no.5 Adaptive mammographic image enhancement using first derivatice and local statistics J. K. Kim;J. M. Park;K . S. Song;H. W. Park
  9. Med. Phys. v.19 no.3 Computerizde detection of clustered microcalcifications in digital mammograms: Application of artificial neural network Y. Wu;K. Doi;M. L. Giger;R. M. Nishikawa
  10. Phys. Med. Biol. v.35 no.8 Automatic computer detection of clustered calcifications in digital mammograms D. H. Davies;D. R. Dance
  11. Fundamentals of neural networks L. Fausett
  12. Digital Image Processing K. R. Castleman
  13. Fundamentals of digital image processing A. K. Jain
  14. Pattern Recognition Engineering M. Nadler;E. P. Smith
  15. Investigative Radiology v.21 ROC methodology in radiology imaging C. E. Metz
  16. present at the 1990 Annual Meeting of the American Statistical Association no.August 7 New methods for estimating a binormal ROC curve from continuously-distributed test result C. E. Metz;J. H. Shen;B. A. Herman