M. G. Mini
ABSTRACT
In this paper, we present a novel approach to the classification of digital mammograms into normal and abnormal classes for breast cancer detection. First, the structures in mammograms produced by normal glandular tissue of varying density are eliminated using a Wavelet Transform (WT) based local average subtraction. Then the linear markings formed by the normal connective tissue are identified and removed. Any abnormality that may exist in the mammogram is therefore enhanced in the residual image, which makes the decision regarding the normality of the mammogram much easier. Features derived from the residual images are applied to a Probabilistic Neural Network (PNN) for classification.
- C. J. Baines, D. V. McFarlane and A. B. Miller, 1990, The role of the reference radiologist: Estimates of interobserver agreement and potential delay in cancer detection in the national screening study, Investigat. Radiol, 971--976Google Scholar
- R. N. Strickland and H. I. Hahn, 1996, Wavelet transforms for detecting microcalcifications in mammograms, IEEE Transactions on Medical Imaging, vol 15, No.2, 218--229Google ScholarCross Ref
- M. L. Giger, F. F. Yin, K. Doi, C. E. Metz, R. A. Schmidt, and C. J. Vyborny, 1990, Investigation of methods for the computerized detection and analysis of mammographic masses Proc. of SPIE, Bellingham, 183--184Google Scholar
- S. Liu and E. J. Delp, Multiresolution detection of stellate lesions in mammograms Proceedings of the IEEE International Conference on Image Processing, October 26--29 1997, Santa Barbara, California, 109--112.Google Scholar
- L. Tabar and P. B. Dean, 1985, Teaching Atlas of Mammography: 2
nd
edition, Thieme, NY,Google Scholar
- J. J. Heine, S. R. Deans, D. K. Cullers, R. Stauduhar, and L. P. Clarke, 1997, Multiresolution statistical analysis of high-resolution digital mammograms, IEEE Transactions on Medical Imaging, vol.16, No. 5, 503--515Google ScholarCross Ref
- Z. Huo, M. Giger, C. Vyborny, D. Wolverton, R. Schmidt, K. Doi, 1996, Computer-Aided Diagnosis: Automated Classification of Mammographic Mass Lesions, Proc. of the 3
rd
Int. Workshop on Digital Mammography, Chicago, IL, 207--211Google Scholar
- D. Brzakovic, X. M. Luo, and P. Brzakovic, 1990 An approach to automated detection of tumors in mammograms, IEEE Trans. on Medical Imaging, vol.9, No.3, 233--241Google ScholarCross Ref
- D. B. Kopans: 1989, Breast Imaging: J. B. Lippincott Company,Google Scholar
- I. Daubechies: 1992. Ten lectures on wavelets: SIAM, Philadelphia, Google ScholarDigital Library
- S. Liu, 1999. The analysis of digital mammograms: Spiculated tumour detection and normal mammogram characterization Ph.D.Thesis, School of Electrical and Computer Engineering, Purdue University, Google ScholarDigital Library
- Haralick R, 1979, Statistical and Structural approaches to Texture, Proc. IEEE, vol.67, No.4, 786--804.Google Scholar
- J. Suckling et al, 1994 The Mammographic Image Analysis Society Digital Mammogram Database Exerpta Medica: International Congress Series 1069, 375--378Google Scholar
- Xiong, M., Fang, X., and Zhao, J2001, Biomarker Identification by Feature Wrappers, Genome Res., vol11, 1878--1887Google ScholarCross Ref
Index Terms
- Neural network based classification of digitized mammograms
Recommendations
Classification of Benign and Malignant Breast Mass in Digital Mammograms with Convolutional Neural Networks
ISICDM 2018: Proceedings of the 2nd International Symposium on Image Computing and Digital MedicineBreast cancer is one of the most common cancers affecting women lives worldwide. It is usually quite difficult for radiologists to accurately distinguish between malignant and benign tumor in digital mammograms. An intelligent classifier based on ...
Probabilistic Neural Network for Breast Biopsy Classification
DESE '09: Proceedings of the 2009 Second International Conference on Developments in eSystems EngineeringThis paper presents the classification of benign and malignant breast tumor based on Fine Needle Aspiration Cytology (FNAC) and Probabilistic Neural Network (PNN). Five hundred and sixty nine sets of cell nuclei characteristics obtained by applying ...
Comments