Detecting clusters of microcalcifications in high-resolution mammograms using support vector machines

Kurdziel, M.; Boryczko, K.; Yuen, D. A.

Artykuł - szczegóły

Tytuł artykułu

Detecting clusters of microcalcifications in high-resolution mammograms using support vector machines

Autorzy

Kurdziel M. , Boryczko K. , Yuen D. A.

Wybrane pełne teksty z tego czasopisma

Identyfikatory

Warianty tytułu

Języki publikacji

Abstrakty

This paper presents a new method for detecting clusters of microcalcifications in high-resolution digital mammograms. Using cluster analysis, we have designed a descriptive set of mammogram image features which enables precise recognition of microcalcifications. These features are fed into the Support Vector Machine classifier trained to discriminate between normal image occlusions and deposits of calcium in breast tissue. Initial candidates for microcalcifications, i.e. suspicious regions on a mammogram image, are selected by means of a discrete wavelet transform, image filtering and morphological operations. Once microcalcifications are detected, our algorithm assesses whether they form groups (clusters) and for each such group verifies its diagnostic significance. This verification is performed by employing another, appropriately trained, Support Vector Machine classifier. Accuracy of our system has been evaluated on the Breast Cancer Research Program (BCRP) volumes of the DDSM database. On this largest publicly available databases of mammograms our system achieved a sensitivity of 85.1% with average number of 5.0 false positive detections per image. Such an accuracy is competitive with other published results obtained on the same dataset.

W artykule przedstawiono nową metodę wykrywania skupisk mikrozwapnień na cyfrowych zdjęciach mammograficznych wysokiej rozdzielczości. Zaproponowana metoda korzysta ze zbioru statystycznych cech obszarów zdjęć mammograficznych, zaprojektowanego za pomocą technik analizy skupisk. Tak skonstruowany zbiór cechy umożliwia precyzyjne rozpoznawania mikrozwapnień. Cechy statystyczne obszarów zdjęć mammografi cznych są wykorzystywane przez klasyfikator SVM (od ang. Support Vector Machine) wyuczony do rozróżniania pomiędzy normalnymi strukturami na zdjęciach, a okluzjami sugerującymi obecność mikrozwapnień. Pierwotna selekcja podejrzanych obszarów na zdjęciach mammograficznych prowadzona jest za pomocą dyskretnej transformaty falkowej, szeregu operacji fi ltrowania i morfologicznych przekształceń obrazu. Po wykryciu mikrozwapnień, algorytm ustala, czy tworzą one skupiska. Następnie każde wykryte skupisko oceniane jest pod kątem wartości diagnostycznej. Oceny tej dokonuje kolejny klasyfikator SVM. Skuteczność proponowanej metody została oszacowana na podzbiorze Breast Cancer Research Program (BCRP) bazy danych DDSM. Na tej największej publicznie dostępnej bazie danych zdjęć mammograficznych zaproponowana metoda wykazuje czułość na poziomie 85.1% przy średniej liczbie 5.0 wskazań fałszywie dodatnich na jedno zdjęcie. Wynik ten jest konkurencyjny w stosunku do innych opublikowanych rezultatów uzyskanych dla tego samego zbioru zdjęć mammograficznych.

Słowa kluczowe

microcalcification detection clustering feature selection support vector machine

detekcja mikrozwapnienie analiza skupisko selekcja cecha Support Vector Machines

Wydawca

Uniwersytet Jagielloński - Collegium Medicum
Index Copernicus Sp. z o.o.

Czasopismo

Bio-Algorithms and Med-Systems

Rocznik

2007

Tom

Vol. 3, no. 6

Strony

11--22

Opis fizyczny

Bibliogr. 51 poz., rys., tab., wykr.

Twórcy

autor

Kurdziel M.

kurdziel@agh.edu.pl

Institute of Computer Science, AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Boryczko K.

boryczko@agh.edu.pl

Institute of Computer Science, AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Yuen D. A.

davey@krissy.geo.umn.edu

Minnesota Supercomputing Institute, University of Minnesota Minneapolis, MN 55455, USA

Bibliografia

1. L. J. Warren-Burhenne, S. A. Wood, C. J. D’Orsi, S. A. Feig, D. B. Kopans, K. F. O’Shaughnessy, E. A. Sickles, L. Tabar, C. J. Vyborny, R. A. Castellino, Potential contribution of computer-aided detection to the sensitivity of screening mammography, Radiology 215 (2000) 554–562.
2. S. M. Astley, F. J. Gilbert, Computer-aided detection in mammography, Clinical Radiology 59 (2004) 390–399.
3. J. A. Baker, J. Y. Lo, D. M. Delong, C. E. Floyd, Computeraided detection in screening mammography: Variability in cues, Radiology 233 (2004) 411–417.
4. M. Heath, K. Bowyer, D. Kopans, R. Moore, P. Kegelmeyer, The digital database for screening mammography, in: The Proceedings of the Fifth International Workshop on Digital Mammography, Medical Physics Publishing, Madison, WI, 2000, pp. 662–671.
5. C. Cortes, V. Vapnik, Support vector networks, Machine Learning 20 (1995) 273–297.
6. H. Cheng, X. Cai, X. Chen, L. Hu, X. Lou, Computer-aided detection and classification of microcalcifications in mammograms: a survey, Pattern Recognition 36 (2003) 2967–2991.
7. B. Zheng, W. Qian, L. P. Clarke, Digital mammography: Mixed feature neural network with spectral entropy decision for detection of microcalcifications, IEEE Transactions on Medical Imaging 15 (1996) 589–587.
8. I. El-Naqa, Y. Yang, M. Wernick, N. Galatsanos, R. Nishikawa, A support vector machine approach for detection of microcalcifications, IEEE Transactions on Medical Imaging 21 (12) (2002) 1552–1563.
9. L. Wei, Y. Yang, R. M. N. and Y. Jiang, A study on several machine-learning methods for classifi cation of malignant and benign clustered microcalcificationsi, IEEE Transactions on Medical Imaging 24 (2005) 371–380.
10. T. Arodz, M. Kurdziel, E. O. D. Sevre, D. A. Yuen, Pattern recognition techniques for automatic detection of suspicious-looking anomalies in mammograms, Computer Methods and Programs in Biomedicine 79 (2005) 135–149.
11. G. Lemaur, K. D. J. DeConinck, Highly regular wavelets for the detection of clustered microcalcifications in mammograms, IEEE Transactions on Medical Imaging 22 (2003) 393–401.
12. P. Heinlein, J. Drexl, W. Schneider, Integrated wavelets for enhancement of microcalcifications in digital mammography, IEEE Transactions on Medical Imaging 22 (2003) 402–413.
13. T. C. Wang, N. B. Karayiannis, Detection of microcalcifications in digital mammograms using wavelets, IEEE Transactions on Medical Imaging 17 (1998) 498–509.
14. T. Netsch, H. O. Peitgen, Scale-space signatures for the detection of clustered microcalcifications in digital mammograms, IEEE Transactions on Medical Imaging 18 (1999) 774–786.
15. W. J. Veldkamp, N. Karssemeijer, Normalization of local contrast in mammograms, IEEE Transactions on Medical Imaging 19 (7) (2000) 731–738.
16. M. Poissonier, J. M. Brady, Noise equalization, film screen artifacts and density representation, in: M. Yaffe (Ed.), Proceedings of the Fifth International Workshop on Digital Mammography, Medical Physics Publishing, Madison, WI, 2001, pp. 605–611.
17. R. Highnam, M. Brady, B. Shepstone, A representation for mammographic image processing, Medical Image Analysis 1 (1996) 1–18.
18. R. Zwiggelaar, S. M. Astley, C. R. Boggis, C. J. Taylor, Linear structures in mammographic images: Detection and classification, IEEE Transactions on Medical Imaging 23 (2004) 1077–1086.
19. C.-M. Chang, A. Laine, Coherence of multiscale features for enhancement of digital mammograms, IEEE Transactions on Information Technology in Biomedicine 3 (1999) 32–46.
20. N. Pandey, Z. Salcic, J. Sivaswamy, Fuzzy logic based microcalcification detection, in: B. W. et. al (Ed.), Proceedings of the IEEE Neural Networks for Signal Processing Workshop X, IEEE Press, 2000, pp. 662–671.
21. H. Li, K. Liu, S. Lo, Fractal modeling and segmentation for the enhancement of microcalcifications in digital mammograms, IEEE Transactions on Medical Imaging 16 (1997) 785–798.
22. T. Arodz, M. Kurdziel, T. Popiela, E. O. D. Sevre, D. A. Yuen, Detection of clustered microcalcifications in small field digital mammography, Computer Methods and Programs in Biomedicine 81 (2006) 56–65.
23. J. Drexi, P. Heinlein, W. Schneider, Mammolnsight computer assisted detection: Performance study with large database, in: Bildverarbeitung fur die Medizin: Algorithmen, Systeme, Anwendungen. Proceedings des Workshops vom 9.-11. Marz 2003 in Erlangen, Springer, 2003, pp. 101–105.
24. S. Sentelle, C. Sentelle, M. Sutton, Multiresolution-based segmentation of calcifications for the early detection of breast cancer, Real-Time Imaging 8 (3) (2002) 237–252.
25. J. Jiang, B. Yao, A. Wason, A genetic algorithm design for microcalcification detection and classification in digital mammograms, Computerized Medical Imaging and Graphics 31 (1) (2007) 49–61.
26. C. Garcia-Orellana, R. Gallardo-Caballero, M. Macias-Macias, H. Gonzalez-Velasco, Svm and neural networks comparison in mammographic cad, in: 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2007, pp. 3204–3207.
27. Y. Sun, C. Babbs, E. Delp, Full-field mammogram analysis based on the identification of normal regions, 2004, pp. 1131–1134.
28. J. Lo, M. Gavrielides, M. Markey, J. Jesneck, Computeraided classification of breast microcalcification clusters: Merging of features from image processing and radiologists, in: Medical Imaging 2003: Image Processing, Vol. 5032 of Proceedings of SPIE, SPIE, 2003, pp. 882–889.
29. P. Zhang, B. Verma, K. Kumar, A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography, in: IEEE International Joint Conference on Neural Networks, 2004, pp. 2303–2307.
30. R. Panchal, B. Verma, Classification of breast abnormalities in digital mammograms using image and bi-rads features in conjunction with neural network, EEE International Joint Conference on Neural Networks (2005) 2487–2492.
31. S. Mallat, A theory for multiresolution signal decomposition: The wavelet representation, IEEE Transactions on Pattern Analysis and Machine Intelligence 11 (1989) 674–693.
32. A. Cohen, Biorthogonal wavelets, in: C. K. Chui (Ed.), Wavelets: A Tutorial in Theory and Applications, Academic Press, San Diego, CA, 1992, pp. 123–152.
33. R. M. Haralick, Textural features for image classification, IEEE Transactions on Systems, Man, and Cybernetics SMC-3 (1973) 610–621.
34. S. Mitra, T. Acharya, Data Mining: Multimedia, Soft Computing and Bioinformatics, Wiley-Interscience, Hoboken, NJ, 2003.
35. J. MacQueen, Some methods for classification and analysis of multivariate observations, in: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, University of California Press, Berkeley, 1967, pp. 281–297.
36. K. Boryczko, M. Kurdziel, Approximate clustering of noisy biomedical data, to appear in: Proceedings of the International Conference on Computational Science 2008 (ICCS 2008), Krakow, PL, 2008.
37. D. B. Kopans, Breast Imaging 2nd edn., Lippincott Williams & Wilkins, Philadelphia, 1998.
38. A. P. Dhawan, Y. Chitre, C. Kaiser-Bonasso, M. Moskowitz, Analysis of mammographic microcalcifications using graylevel image structure features, IEEE Transactions on Medical Imaging 15 (1996) 246–259.
39. H.-P. Chan, B. Sahiner, K. L. Lam, N. Petrick, M. A. Helvie, M. M. Goodsitt, D. D. Adler, Analysis of mammographic microcalcifications using gray-level image structure features, Medical Physics 25 (1999) 2007–2019.
40. F. Schmidt, E. Sorantin, C. Szepesvari, E. Graif, M. Becker, H. Mayer, K. Hartwagner, An automatic method for the identification and interpretation of clustered microcalcifications in mammograms, Physics in Medicine and Biology 44 (1999) 1231–1243.
41. D. P. Chakraborty, Maximum likelihood analysis of free-response receiver operating characteristic (froc) data, Medical Physics 16 (4) (1989) 561–568.
42. N. Karssemeijer, Adaptive noise equalization and recognition of microcalcification clusters in mammograms, International Journal of Pattern Recognition and Artificial Intelligence 7 (1993) 1357–1376.
43. N. C. Yarlagadda, K. W. Bowyer, R. Li, Baseline comparison of microcalcification detection algorithms, in: M. Yaffe (Ed.), Proceedings of the Fifth International Workshop on Digital Mammography, Medical Physics Publishing, Madison, WI, 2001.
44. L. Ries, M. Eisner, C. Kosary, B. Hankey, B. Miller, L. Clegg, A. Mariotto, E. Feuer, E. B., SEER Cancer Statistics Review, 1975–2002, National Cancer Institute, Bethesda, MD, 2004.
45. T. W. Freer, J. M. Ulissey, Screening mammography with computer-aided detection: Prospective study of 12,860 patients in a community breast center, Radiology 220 (3) (2001) 781–786.
46. H.-P. Chan, L. T. Niklason, D. M. Ikeda, K. L. Lam, D. D. Adler, Digitization requirements in mammography: Effects on computer-aided detection of microcalcifications, Medical Physics 21 (1994) 1203–1211.
47. K. J. McLoughlin, P. J. Bones, N. Karssemeijer, Noise equalization for detection of microcalcification clusters in direct digital mammogram images, IEEE Transactions on Medical Imaging 23 (3) (2004) 313–320.
48. S. Yu, L. Guan, A cad system for the automatic detection of clustered microcalcifications in digitized mammogram films, IEEE Transactions on Medical Imaging 19 (2000) 115–126.
49. R. N. Strickland, H. I. Hahn, Wavelet transforms for detecting microcalcifications in mammograms, IEEE Transactions on Medical Imaging 15 (1996) 218–229.
50. K.-R. Muller, S. Mika, G. R. K. Tsuda, B. Scholkopf, An introduction to kernel-based learning algorithms, IEEE Transactions on Neural Networks 12 (2001) 181–201.
51. C. Burges, A tutorial on support vector machines for pattern recognition, Knowledge Discovery and Data Mining 2 (1998) 121–167.

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-40e0f33e-a0d8-4365-8888-e8c2917fccf7