Classification of microcalcifications into BI-RADS™ morphologic categories - preliminary results

• Autorzy: Podsiadły-Marczykowska T. , Wróblewska A. , Przelaskowski A.
• Języki publikacji: EN

Abstrakty

EN

In the paper, preliminary results for the classification of microcalcifications (MCs) into the three BIRADSTM morphologic categories (punctate, pleomorphic and linear) are presented. To classify the microcalcifications into morphologic types the set of 27 shape descriptors was constructed. The morphology of the cluster was determined as the mean values of shape descriptors for single microcalcifications. SVM classifier was used to differentiate MCs clusters into BI-RADS morphologic types. Classification of the clustered MCs into linear or pleomorphic morphologic types obtained accuracy ranging from 84 to 88% depending on the MCs features and the SVM parameters. The most discriminate features for the classification of clustered linear and pleomorphic MCs are: inner compactness, major axis and first invariant shape moment calculated from binary image of segmented MCs.

Słowa kluczowe

EN

clustered microcalcifications; microcalcifications morphology; BI-RADS; classification; SVM (support vector machine)

PL

mikrozwapnienie; system BI-RADS; maszyna wektorów podpierających

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2009
• Tom: Vol. 29, no. 4
• Strony: 83--93
• Opis fizyczny: Bibliogr. 28 poz., rys., tab., wykr.

Twórcy

autor

Podsiadły-Marczykowska T.

autor

Wróblewska A.

autor

Przelaskowski A.

• Institute of Biomedical Engineering, Polish Academy of Sciences, ul. Ks. Trojdena 4, 02-109 Warszawa, Poland,

Bibliografia

• 1. Pijnappel R.M., Peeters P.H., Hendriks J.H., Mali W.P.: Reproducibility of mammographic classifications for nonpalpable suspect lesions with microcalcifications. The British Journal of Radiology, 2004, 77, 312–314.
• 2. U.S. Food and Drug Administration: Summary and Safety and Effectiveness Data: R2 Technologies, 1998, P970058.
• 3. U.S. Food and Drug Administration: Summary and Safety and Effectiveness Data: CADx Medical Systems, 2002, P010034.
• 4. Thangavel K., Karnan M., Sivakumar R., A. Kaja Mohideen A.K.: Automatic Detection of Microcalcification in Mammograms– A Review. ICGST-GVIP Journal, 2005, 5, 31–61.
• 5. American College of Radiology. Breast imaging reporting and data system (BI-RADS), 3rd ed. Reston, VA: American College of Radiology, 1998.
• 6. Berg W.A., Campassi C., Langenberg P., Sexton M.J.: Breast Imaging Reporting and Data System: inter- and intraobserver variability in feature analysis and final assessment. American Journal of Roentgenology 2000, 174, 1769–1777.
• 7. Kerlikowske K., Grady D., Barclay J., Frankel S.D., Ominsky S.H., Sickles E.A., Ernster V.: Variability and Accuracy in Mammographic Interpretation Using the American College of Radiology Breast Imaging Reporting and Data System. Journal of the National Cancer Institute, 1998, 90, 1801–1809.
• 8. Sameer A., Long L.R., Thoma G.R.: Bridging the Gap: Enabling CBIR in Medical Applications. 21st IEEE International Symposium on Computer-Based Medical Systems, 2008, 4–6.
• 9. Kulikowski J.L., Ngo Thi Lan A., Przytulska M., Wierzbicka D., Wiśniewska E.: Computer-Aided Analysis of Tumour Shapes and Dimensions in Mammographic RTG Images. European Medical & Biological Engineering Conference EMBEC, 1999, 2, 980–981.
• 10. Rangaraj M., Rangayyan T.M., et al.: Fractal Analysis of Contours of Breast Masses in Mammograms. Journal of Digital Imaging, 2007, 20, 223–237.
• 11. Mehul P., Sampat M.P., Bovik A.C., Markey M.K.: Classification of mammographic lesions into BI-RADS™ shape categories using the Beamlet Transform. Medical Imaging 2005, 5747, 438–447.
• 12. Shen L., Rangayyan R., Desautels J.: Shape analysis of mammographic calcifications, IEEE Trans. Med. Imag., 1994, 13, 263–274.
• 13. DDSM http://marathon.csee.usf.edu/Mammography/Database.html – last visited 01.09.2008
• 14. MammoViewer http://www.ire.pw.edu.pl/MammoViewer – last visited 01.09.2008
• 15. Hu, M.K.: Visual pattern recognition by moment invariants. IRE Transactions on Information Theory. 1962, 17, 197–187.
• 16. Costa L.F., Cesar R.M.: Shape Analysis and Classification. Boca Raton, Florida:CRC Press, 2000.
• 17. Lee S., Bulthoff H., Poggio T.: Biologically Motivated Computer Vision. Seoul:Springer 2003, 23, 446–456.
• 18. Yu S., Guan L.: A CAD system for the automatic detection of clustered microcalcifications in digitized mammogram films. IEEE Trans. Medical Imag. 2000, 19, 115–125.
• 19. Jiang Y.: Classification of breast lesions from mammograms. Handbook of Medical Imaging, Academic Press, New York, 2000, 341–357.
• 20. Cosgriff RL, “Identification of shape,” Res. Foundation, Ohio State Univ., Columbus, 1960.
• 21. Feature Selection and Classification Tool – last visited 01.09.2008, available at http://www.cs.huji.ac.il/~anavot/feature_selection_tool/fst.htm.
• 22. Guyon I., Elisseeff E.: An introduction to variable and feature selection. JMLR, 2003.
• 23. Kira K., Rendell L: A practical approach to feature selection. 9th International Workshop on Machine Learning, 1992, 249–256.
• 24. Vapnik V.: Statistical Learning Theory, Wiley, New York 1998.
• 25. Burges C.J.:A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 1998, 2, 121–167.
• 26. Singh S., Kumar V., Verma H.K., Singh D.: SVM based system for classification of microcalcifications in digital mammograms. IEEE Eng. Med. Biol. Soc. 2006, 1, 4747–4750.
• 27. Papadopoulos A., Fotiadis D., Likas A.: Characterization of clustered microcalcifications in digitized mammograms using neural networks and support vector machines. Artificial Intelligence in Medicine 2003, 34 , 141–150.
• 28. Mavroforakis M., Georgiou H., Dimitropoulos N., Cavouras D., Theodoridis S.: Significance analysis of qualitative mammographic features, using linear classifiers, neural networks and support vector machines. European Journal of Radiology 2005, 54, 80–89.