Fuzzy technique for microcalcifications clustering in digital mammograms

BMC Medical Imaging

Giuseppe Raso¹  Francesco Fauci¹  Donato Cascio¹  Letizia Vivona¹ 

[1] Dipartimento di Fisica e Chimica, Università Degli Studi di Palermo, Palermo, Italy

关键词: Segmentation;    Mammography;    C-means;    Fuzzy logic;    Clustering;    Spatial filters;    Microcalcifications;    Breast cancer;   

Others  :  1090258
DOI  :  10.1186/1471-2342-14-23

 received in 2012-12-18, accepted in 2014-06-09,  发布年份 2014

【 摘 要 】

Background

Mammography has established itself as the most efficient technique for the identification of the pathological breast lesions. Among the various types of lesions, microcalcifications are the most difficult to identify since they are quite small (0.1-1.0 mm) and often poorly contrasted against an images background. Within this context, the Computer Aided Detection (CAD) systems could turn out to be very useful in breast cancer control.

Methods

In this paper we present a potentially powerful microcalcifications cluster enhancement method applicable to digital mammograms. The segmentation phase employs a form filter, obtained from LoG filter, to overcome the dependence from target dimensions and to optimize the recognition efficiency. A clustering method, based on a Fuzzy C-means (FCM), has been developed. The described method, Fuzzy C-means with Features (FCM-WF), was tested on simulated clusters of microcalcifications, implying that the location of the cluster within the breast and the exact number of microcalcifications are known.

The proposed method has been also tested on a set of images from the mini-Mammographic database provided by Mammographic Image Analysis Society (MIAS) publicly available.

Results

The comparison between FCM-WF and standard FCM algorithms, applied on both databases, shows that the former produces better microcalcifications associations for clustering than the latter: with respect to the private and the public database we had a performance improvement of 10% and 5% with regard to the Merit Figure and a 22% and a 10% of reduction of false positives potentially identified in the images, both to the benefit of the FCM-WF. The method was also evaluated in terms of Sensitivity (93% and 82%), Accuracy (95% and 94%), FP/image (4% for both database) and Precision (62% and 65%).

Conclusions

Thanks to the private database and to the informations contained in it regarding every single microcalcification, we tested the developed clustering method with great accuracy. In particular we verified that 70% of the injected clusters of the private database remained unaffected if the reconstruction is performed with the FCM-WF. Testing the method on the MIAS databases allowed also to verify the segmentation properties of the algorithm, showing that 80% of pathological clusters remained unaffected.

【 授权许可】

   
2014 Vivona et al.; licensee BioMed Central Ltd.

【 图 表 】

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

Figure 12.

Figure 13.

Figure 14.

Figure 15.

Figure 16.

Figure 17.

Figure 18.

Figure 19.

Figure 20.

Figure 4.

【 参考文献 】

• [1]Ciatto S, Cascio D, Fauci F, Magro R, Raso G, Ienzi R, Martinelli F, Simone MV: Computer-Assisted Diagnosis (CAD) in Mammography: Comparison of Diagnostic Accuracy of a New Algorithm (Cyclopus®, Medicad) with Two Commercial Systems. Radiol Med 2009, 114:626-635. 10.1007/s11547-009-0396-4
• [2]Cascio D, Fauci F, Iacomi M, Raso G, Magro R, Castrogiovanni D, Filosto G, Ienzi R, Vasile MS: Computer-aided diagnosis in digital mammography: comparison of two commercial systems. Imaging in Medicine 2014, 6(1):13-20.
• [3]Karssemeijer N, Hendriks JHCL: Computer-assisted reading of mammograms. Eur Radiol 1997, 7:743-748.
• [4]McLoughlin KJ, Bones PJ, Karssemeijer N: Noise equalization for detection of microcalcification clusters in direct digital mammogram images. IEEE Trans Med Imag 2004, 23(3):313-320.
• [5]Fu JC, Lee SK, Wong STC, Yeh JY, Wang AH, Wu HK: Image segmentation feature selection and pattern classification for mammographic microcalcifications. Comput Med Imaging Graph 2005, 29:419-429.
• [6]Halkiotis S, Botsis T, Rangoussi M: Automatic detection of clustered microcalcifications in digital mammograms using mathematical morphology and neural networks. Signal Process 2007, 87:1559-1568.
• [7]Vedkamp WJH, Karssemeijer N: Automated classification of clustered microcalcifications into malignant and benign types. Med Phys 2000, 27(11):2600-2608.
• [8]Cascio D, Magro R, Fauci F, Iacomi M, Raso G: Automatic detection of lung nodules in CT datasets based on stable 3D mass-spring models. Comput Biol Med 2012, 42(11):1098-1109.
• [9]Cascio D, Magro R, Fauci F, Iacomi M, Raso G: Automatic detection of lung nodules in low-dose computed tomography. Comput Assist Radiol Surg 2007, 2(supplement 1):357-360.
• [10]Wei L, Yang Y, Nishikawa RN, Jiang Y: A study on several machine-learning methods for classification of malignant and benign clustered microcalcifications. IEEE Trans Med Imag 2005, 24(3):371-380.
• [11]Jain AK, Dubes RC: Algorithms for clustering data. Upper Saddle River, NJ, USA: Prentice Hall; 1988:55-143.
• [12]Nishikawa RM, Giger ML, Doi K, Vyborny CJ, Schmidt RA: Computer-aided detection of clustered microcalcifications: an improved method for grouping detected signals. Med Phys 1993, 20(6):1661-1666.
• [13]Estevez L, Kehtarnavaz N, Wendt R: Interactive selective and adaptive clustering for detection of microcalcifications in mammograms. Digit Signal Process 1996, 6:224-232.
• [14]Mao F, Zhang Y, Song D, Qian W, Clarke LP: An improved method of region grouping for microcalcification detection in digital mammograms”. Proc of IEEE 1998, 20(2):740-743.
• [15]Arodz T, Kurdziel M, Popiela TJ, Sevre E, Yuen D: Detection of clustered microcalcifications in small field digital mammography”. Comput Methods Prog Biomed 2006, 81:56-65.
• [16]Cihan IK, Senel HG: An application of topological median filter on detection and clustering of microcalcifications in digital mammograms. IEEE 2006, 10:1136-1139.
• [17]Riyahi-Alam N, Ahmadian A, Nasehi Tehrani J, Guiti M, Oghabian MA: Segmentation of suspicious clustered microcalcifications on digital mammograms: using fuzzy logic and wavelet. 7th International Conference on Signal Processing Proceedings, ICSP 2004, 3:2228-2230.
• [18]Cordella LP, Percannella G, Sansone C, Vento M: A graph-theoretical clustering method for detecting clusters of microcalcifications in mammographic images. Proceedings of the IEEE CBMS 2005, 15:20.
• [19]Wang Y, Shi H, Ma S: A new approach to the detection of lesions in mammography using fuzzy clustering. J Int Med Res 2011, 39:2256-2263.
• [20]Quintanilla-Dominguez J, Ojeda-Magana B, Marcano-Cedeno A, Barròn-Adame JM, Vega-Corona A, Andina D: Automatic detection of microcalcifications in ROI images based on PCFM And ANN. Int J Intell Comput Med Sci Image Process 2013, 5(2):161-174.
• [21]Malar E, Kandaswamy A, Chakravarthy D, Giri DA: A novel approach for detection and classification of mammographic microcalcifications using wavelet analysis and extreme learning machine. Comput Biol Med 2012, 42:898-905.
• [22]Cheng HD, Wang J, Shi X: Microcalcification detection using fuzzy logic and scale space approaches. Pattern Recogn 2004, 37:363-375.
• [23]Fauci F, Bagnasco S, Bellotti R, Cascio D, Cheran SC, De Carlo F, De Nunzio G, Fantacci ME, Forni G, Lauria A, Lopez Torres E, Magro R, Masala GL, Oliva P, Quarta M, Raso G, Retico A, Tangaro S: Mammogram segmentation by contour searching and massive lesion classification with neural network. IEEE Nucl Sci Symp Conf R 2004, 5:2695-2699.
• [24]Fauci F, Cascio D, La Manna A, Magro R, Raso G, Vasile M, Iacomi M: A fourier-based algorithm for micro-calcification enhancement in mammographic images. IEEE Nuclear Science Symposium Conference Record, article number 4774254 2008, 4388-4391.
• [25]Liu J, Chen J, Liu X, Chun L, Tang J, Deng Y: Mass segmentation using a combined method for cancer detection. BMC Syst Biol 2011., 5(SUPPL. 3) art. no. S6
• [26]Iacomi M, Cascio D, Fauci F, Raso G: Mammographic images segmentation based on chaotic map clustering algorithm. BMC Med Imaging 2014, 14(1):12.
• [27]Marr D: Vision: A computational investigation into the human representation and processing of visual information: San Francisco. 1982.
• [28]Tangaro S, Bellotti R, De Carlo F, Gargano G, Lattanzio E, Monno P, Massacra R, Delogu P, Fantacci ME, Retico A, Mazzocchi M, Bagnasco S, Cerello P, Cheran SC, Lopez Torres E, Zanon E, Lauria A, Sodano A, Cascio D, Fauci F, Magro R, Raso G, Ienzi R, Bottigli U, Masala GL, Oliva P, Meloni G, Caricato AP, Cataldo R: MAGIC-5: an Italian mammographic database of digitized images for research. La Radiologia Medica 2008, 113(4):477-485.
• [29]Youn H, Han Jong C, Cho Min K, Jang SY, Kim HK, Kim JH, Tanguay J, Cunningham IA: Numerical generation of digital mammograms considering imaging characteristics of an imager. Nucl Instrum Meth A 2011, 652:810-814.
• [30]Berthold M, Hand DJ: Intelligent data analysis. Book: Springer; 1999:321-351.
• [31]Vivona L, Cascio D, Magro R, Fauci F, Raso G: A fuzzy logic C-means clustering algorithm to enhance microcalcifications clusters in digital mammograms. IEEE Nucl Sci Symp Med Imaging Conf 2012, 3048-3050. art. No. 6152551
• [32]Bellotti R, De Carlo F, Gargano G, Tangaro S, Cascio D, Catanzariti E, Cerello P, Cheran SC, Delogu P, De Mitri I, Fulcheri C, Grosso D, Retico A, Squarcia S, Tommasi E, Golosio B: A CAD system for nodule detection in low-dose lung CTs based on region growing and a new active contour model. Med Phys 2007, 34(12):4901-4910.
• [33]Rusina R, Kukal J, Bělíček T, Buncová M, Matěj R: Use of fuzzy edge single-photon emission computed tomography analysis in definite Alzheimer's disease - a retrospective study. BMC Med Imaging 2010. 10 , art. no. 20
• [34]Masala GL, Golosio B, Oliva P, Cascio D, Fauci F, Tangaro S, Quarta M, Cheran SC, Lopez Torres E: Classifiers trained on dissimilarity representation of medical pattern: a comparative study”. Nuovo Cimento della Società Italiana di Fisica C 2005, 28(6):905-912.
• [35]Masala GL, Tangaro S, Golosio B, Oliva P, Stumbo S, Bellotti R, De Carlo F, Gargano G, Cascio D, Fauci F, Magro R, Raso G, Bottigli U, Cgincarini A, De Mitri I, De Nunzio G, Gori I, Retico A, Cerello P, Cheran SC, Fulcheri C, Lopez Torres E: Comparative study of feature classification methods for mass lesion recognition in digiteized mammograms”. Nuovo Cimento C, Geophysics and Space Physics 2007, 30(3):305-316.
• [36]McKeen-Polizzotti L, Henderson KM, Oztan B, Bilgin CC, Yener B, Plopper GE: Quantitative metric profiles capture three-dimensional temporospatial architecture to discriminate cellular functional states”. BMC Med Imaging 2011. 11, art. no. 11
• [37]Kim SY, Lee JW, Bae JS: Effect of data normalization on fuzzy clustering of DNA microarray data. BMC Bioinformatics 2006. 7, art. no. 134