Segmentation and feature extraction for reliable classification of microcalcifications in digital mammograms

• Autorzy: Wróblewska A. , Boniński P. , Przelaskowski A. , Kazubek M.
• Konferencja: The Fourth Scientific Symposium on Image Processing Technology. TPO 2002 ; (21.11-23.11.2002 ; Serock, Poland)
• Języki publikacji: EN

Abstrakty

EN

Microcalcifications are one of more important signs enabling detection of breast cancer at an early stage. The main goal of the research was designing and realization of a system for automatic detection and classification of microcalcifications, taking advantage of the proposed automatic feature selection algorithm. The first step of the detection algorithm is to segment the individual objects : potential microcalcifications. This is achieved by applying opening by reconstruction top-hat technique and image thresholding based on approximation of an image local histogram with a probability density function of Gauss distribution. Selected features of the segmented objects are used as inputs to neural networks. The first classifier verifies the initial detection and the others assess a diagnosis of the input objects. The algorithm results are locations of suggested microcalcifications and optionally automatic diagnosis. The presented form of the system was verified in clinical tests using diagnosed databases (DDSM from the University of South Florida and own digitised database of mammograms). The achieved results are promising and comparable with other known systems. Efficiency of microcalcifications detection was up to 90%.

Słowa kluczowe

EN

computer-aided diagnosis; microcalcification detection; digital mammography

• Wydawca: Stowarzyszenie Elektryków Polskich ; Polska Akademia Nauk ; Wojskowa Akademia Techniczna im. Jarosława Dąbrowskiego
• Czasopismo: Opto-Electronics Review
• Rocznik: 2003
• Tom: Vol. 11, No. 3
• Strony: 227--235
• Opis fizyczny: Bibliogr. 22 poz., rys., tab.

Twórcy

autor

Wróblewska A.

• Institute of Radioelectronics, Warsaw University of Technology, 15/19 Nowowiejska Str., 00-665 Warsaw, Poland

autor

Boniński P.

• Institute of Radioelectronics, Warsaw University of Technology, 15/19 Nowowiejska Str., 00-665 Warsaw, Poland

autor

Przelaskowski A.

• Institute of Radioelectronics, Warsaw University of Technology, 15/19 Nowowiejska Str., 00-665 Warsaw, Poland

autor

Kazubek M.

• Institute of Radioelectronics, Warsaw University of Technology, 15/19 Nowowiejska Str., 00-665 Warsaw, Poland

Bibliografia

• 1. Mammography in Breast Cancer Diagnosis, Bel Corp, Warsaw, 1998. (in Polish).
• 2. A. Przelaskowski and P. Surowski, "Methods of medical image data optimisation applied to archiving and telemedical transmission", Research Project of the State Committee for Scientific Research No. 7T11E03920 (2002). (in Polish).
• 3. http://www.r2tech.com
• 4. http://www.lorad.com/selenia.html
• 5. http://www.cadxmed.com/productslsecond_look_ad/
• 6. http://www.scanis.com/products/index.html
• 7. S. Yu and L. Guan, " A CAD system for the automatic detection of clustered microcalcifications in digitized mammogram films", IEEE Trans. Medical Imag. 19, 115-125 (2000).
• 8. http://www.marathon.csee.usf.edu/Mammography/Data-base.html
• 9. S. Quadrades and A. Sacristan, "Automated extraction of microcalcifications BI-RADS numbers in mammograms", Proc. IEEE ICIP, 289-292 (2001).
• 10. J. Dengler, S. Behrens, and J. Desaga, "Segmentation of microcalcification in mammograms", IEEE Trans. Medical Imag. 12, 231-238 (1993).
• 11. D. Betal, N. Roberts, and G. Whitehouse, "Segmentation and numerical analysis of microcalcifications on mammograms using mathematical morphology", British J. Radiology 70, 903-917 (1997).
• 12. J. Kim and H. Park, "Statistical textural features for detection of microcalcifications in digitized mammograms", IEEE Trans. Medical Imag. 18, 231-238 (1999).
• 13. H. Chany, B. Sahiner, N. Petrick, M. Helvie, K. Lam, D. Adler, and M. Goodsitt, "Computerized classification of malignant and benign microcalcifications on mammogram: texture analysis using an artificial neural network", Phys. Med. Biol. 42, 549-567 (1997).
• 14. Y. Jiang, "Classification of breast lesions from mammograms", in Handbook of Medical Imaging, pp. 341-357, Academic Press, New York, 2000.
• 15. M. Hu, "Visual pattern recognition by moment invariants", IRE Transactions on Information Theory IT-8, 179-187 (1964).
• 16. L. Shen, R. Rangayyan, and J. Desautels, "Shape analysis of mammographic calcifications", Proc. 5th Annual IEEE Symposium on Computer-Based Medical Systems, 123-128 (1992).
• 17. W. Pratt, Digital Image Processing, A Wiley - Interscience Publication, John Wiley & Sons, New York, 1991.
• 18. M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis and Machine Vision, PWS Publishing, 2nd edition.
• 19. S. Raudys and V. Pikelis, "On dimensionality, sample size, classification error, and complexity of classification algorithm in pattern recognition", IEEE Trans. Pattern Anal. Machine Intel. 2, 242-252 (1980).
• 20. T. Kohonen, "Self-organizing maps in information sciences", in Sprinter Series in information Sciences, p. 30, 1995.
• 21. T. Kohonen, "The self-organizing map", Proc. IEEE 18, 1464-1480 (1990).
• 22. Y. Jiang and R. Nishikawa, "Malignant and benign clustered microcalcifications: automated feature analysis and classification", Radiology 198, 671-678 (1996).