Abstract：This study attempted to accurately segment the mammographic masses and distinguish malignant from benign tumors. An adaptive region growing algorithm with hybrid assessment function combined with maximum likelihood analysis and maximum gradient analysis was developed in this paper. In order to accommodate different situations of masses, the likelihood and the edge gradients of segmented masses were weighted adaptively by the use of information entropy. 106 benign and 110 malignant tumors were included in this study. We found that the proposed algorithm obtained segmentation contour more accurately and delineated the tumor body as well as tumor peripheral regions covering typical mass boundaries and some spiculation patterns. Then the segmented results were evaluated by the classification accuracy. 42 features including age, intensity, shape and texture were extracted from each segmented mass and support vector machine (SVM) was used as a classifier. The classification accuracy was evaluated using the area (Az) under the receiver operating characteristic (ROC) curve. It was found that the maximum likelihood analysis achieved an Az value of 0.835, the maximum gradient analysis got an Az value of 0.932 and the hybrid assessment function performed the best classification result where the value of Az was 0.948. In addition, compared with traditional region growing algorithm, our proposed algorithm is more adaptive and provides a better performance for future works.
. An adaptive region growing algorithm for breast
masses in mammograms[J]. Front. Electr. Electron. Eng., 2010, 5(2): 128-136.
Ying CAO, Xin HAO, Xiaoen ZHU, Shunren XIA, . An adaptive region growing algorithm for breast
masses in mammograms. Front. Electr. Electron. Eng., 2010, 5(2): 128-136.
Hao X, Cao Y, Xia S R. Computer-aided diagnosis technique onmammograms using content-based medical image retrieval. Chinese Journal of Biomedical Engineering, 2009, 28(6): 922―930 (in Chinese)
Tang J S, Rangayyan R M, Xu J, EI Naqa I, Yang Y Y. Computer-aideddetection and diagnosis of breast cancer with mammography: recentadvances. IEEE Transactions on Informationon Technology in Biomedicine, 2009, 13(2): 236―251 doi: 10.1109/TITB.2008.2009441
Shen Y, Xia S R, Li M D. A survey on relevance feedback techniquesin content based medical image retrieval. Chinese Journal of Biomedical Engineering, 2009, 28(1): 128―136 (in Chinese)
Cheng H D, Shi X J, Min R, Hu L M, Cai X P, Du H N. Approaches for automated detection and classificationof masses in mammograms. Pattern Recognition, 2006, 39(4): 646―668 doi: 10.1016/j.patcog.2005.07.006
Brzakovic D, Luo X M, Brzakovic P. An approach to automated detection oftumors in mammograms. IEEE Transactionson Medical Imaging, 1990, 9(3): 233―241 doi: 10.1109/42.57760
Li L, Qian W, Clarke L P, Clark R A, Thomas C J. Improving mass detectionby adaptive and multi-scale processing in digitized mammograms. Proceedings of SPIE, 1999, 3661: 490―498 doi: 10.1117/12.348604
Petrick N, Chan H P, Sahiner B, Wei D, Helvie M A, Goodsitt M M, Adler D D. Automateddetection of breast masses on digital mammograms using adaptive density-weightedcontrast-enhancement filtering. Proceedingsof SPIE, 1995, 2434: 590―597 doi: 10.1117/12.208731
Pappas T N. An adaptive clustering algorithm for image segmentation. IEEE Transactions on Signal Processing, 1992, 40(4): 901―914 doi: 10.1109/78.127962
Xu W D, Xia S R, Duan H L, Xiao M. Segmentationof mass in mammograms using a novel intelligent algorithm. International Journal of Pattern Recognition andArtificial Intelligence, 2006, 20(2): 255―270 doi: 10.1142/S0218001406004648
Kinnard L M, Lo S B, Wang P C, Freedman M T, Chouikha M F. Separation of malignant andbenign masses using maximum-likelihood modeling and neural networks. Proceedings of SPIE, 2002, 4684: 733―741 doi: 10.1117/12.467216
Pal S K, King R A. Image enhancementusing fuzzy set. Electronics Letters, 1980, 16(10): 376―378 doi: 10.1049/el:19800267
Laine A F, Schuler S, Fan J, Huda W. Mammographic feature enhancement by multiscale analysis. IEEE Transactions on Medical Imaging, 1994, 13(4): 725―740 doi: 10.1109/42.363095
Kinnard L, Lo S C B, Wang P, Freedman M T, Chouikha M F. Automatic segmentation ofmammographic masses using fuzzy shadow and maximum-likelihood analysis. In: Proceedings of IEEE International Symposiumon Biomedical Imaging. 2002, 241―244
Kallergi M. Computer-aided diagnosis of mammographic microcalcificationclusters. Medical Physics, 2004, 31(2): 314―326 doi: 10.1118/1.1637972
Jesneck J L, Nolte L W, Baker J A, Floyd C E, Lo J Y. Optimized approach to decisionfusion of heterogeneous data for breast cancer diagnosis. Medical Physics, 2006, 33(8): 2945―2954 doi: 10.1118/1.2208934
Mavroforakis M E, Georgiou H V, Dimitropoulos N, Cavouras D, Theodoridis S. Mammographicmasses characterization based on localized texture and dataset fractalanalysis using linear, neural and support vector machine classifiers. Artificial Intelligence in Medicine, 2006, 37(2): 145―162 doi: 10.1016/j.artmed.2006.03.002
Rangayyan R M, EI-Faramawy N M, Desautels J E L, Alim O A. Measures of acutance and shape for classification ofbreast tumors. IEEE Transactions on MedicalImaging, 1997, 16(6): 799―810 doi: 10.1109/42.650876
Rangayyan R M, Nguyen T M. Fractal analysis of contours of breast masses in mammograms. Journal of Digital Imaging, 2007, 20(3): 223―237 doi: 10.1007/s10278-006-0860-9
Rangayyan R M, Nguyen T M. Pattern classification of breast masses via fractal analysis of theircontours. International Congress Series, 2005, 1281(4): 1041―1046 doi: 10.1016/j.ics.2005.03.329
Haralick R M, Shanmugam K, Dinstein I. Textural features for imageclassification. IEEE Transactions on Systems,Man, and Cybernetics, 1973, SMC-3(6): 610―621 doi: 10.1109/TSMC.1973.4309314
Zhou M Q, Geng G H, Wei N. Content-Based ImageRetrieval. Beijing: Tsinghua University Press, 2007 (in Chinese)
Vapnik V N. The Nature of Statistical Learning Theory. New York: Springer-Verlag, 1995
Campanini R, Dongiovanni D, Iampieri E, Lanconelli N, Masotti M, Palermo G, Riccardi A, Roffilli M. Anovel featureless approach to mass detection in digital mammogramsbased on support vector machines. Physicsin Medicine and Biology, 2004, 49(6): 961―975 doi: 10.1088/0031-9155/49/6/007
Mu T, Nandi A K, Rangayyan R M. Classification of breastmasses using selected shape, edge-sharpness, and texture featureswith linear and kernel-based classifiers. Journal of Digital Imaging, 2008, 21(2): 153―169 doi: 10.1007/s10278-007-9102-z
Yu S, Yang X W, Hao Z F, Liang Y C. An adaptive support vector machine learning algorithm for large classificationproblem. Lecture Notes in Computer Science, 2006, 3971: 981―990 doi: 10.1007/11759966_144
Heath M, Bowyer K, Kopans D, Moore R, Kegelmeyer P. Thedigital database for screening mammography. In: Proceedings of the 5th International Workshop on Digital Mammography. 2000, 212―218
American College of Radiology(ACR). Breast imaging reporting and datasystem atlas (BI-RADS atlas). Reston: AmericanCollege of Radiology, 2003
