Mamografide Meme Mikrokalsifikasyonları için Otomatik Bilgisayar Destekli Tespit (CADe) ve Tanı (CADx) Sistemi

Öz

Mamografide mikrokalsifikasyon (MC) kümelerinin saptanması için otomatik bir bilgisayar destekli

tanı sistemi önerilmiştir. Önerilen sistem şüpheli bölgelerin tanımlanması, MC'lerin tespiti, yanlış pozitif

indirgeme ve iyi huylu/kötü huylu sınıflamayı içeren bütün bir sistemdir. Şüpheli mikrokalsifikasyon

bölgelerinin sınıflandırılması için, gri seviye eş-oluşum matrisi (GLCM) ve istatistiksel özellikler ile çok

tabakalı bir perceptron (MLP) sinir ağı kullanıldı. Daha sonra, yanlış pozitif sınıflandırma oranını

azaltmak için, gri seviye çalışma uzunluğu matrisi (GLRLM) özellikli kademeli korelasyon sinir ağı

(CCNN) kullanılmıştır. Son adımda, tespit edilen MC kümelerinin iyi huylu/kötü huylu sınıflandırması

için GLRLM özellikleri ile hibrid yapıda diskriminant analizi ve destek vektör makinesi (SVM)

yöntemleri kullanıldı. Çalışma için açık erişimli Mamografik Görüntü Analizi Derneği (MIAS) veri

tabanı kullanılmıştır. Deneysel sonuçlar, önerilen algoritmanın meme kanseri tespiti için %86 duyarlılık,

%98.3 özgüllük ve 1.163 FPpI oranları elde ettiğini ve meme kanseri tanısı için elde edilen duyarlılık ve

özgüllük değerlerinin sırasıyla %100 ve %100 olduğunu ortaya koymuştur. MC kümelenmelerinin

görme zorluğu olsa da, önerilen sistem çok tatmin edici sonuçlar vermektedir. Bununla birlikte, gelişmiş

sistem; çıktıları yüzdeler ve dönüştürülmüş değerlendirme kategorileri olarak veren tam otomatik bir

bütün sistemdir.

Anahtar Kelimeler

• Meme kanseri
• Bilgisayar destekli tanı
• Kademeli korelasyon sinir ağı (CCNN)
• Gri seviye eş-oluşu matrisi (GLCM)
• Gri seviye çalışma uzunluğu matrisi (GLRLM)
• Mamografi

AN AUTOMATED COMPUTER-AIDED DETECTION (CADe) AND DIAGNOSIS (CADx) SYSTEM FOR BREAST MICROCALCIFICATIONS IN MAMMOGRAMS

Öz

An automated computer aided diagnosis system has been proposed for detection of

microcalcification (MC) clusters in mammograms. The proposed system is a whole system including

suspicious regions identification, MCs detection, false positive reduction and benign/malign

classification. For classification of suspicious microcalcification regions, a multilayer perceptron (MLP)

neural network was used with grey level co-occurrence matrix (GLCM) and statistical features. Then to

decrease the false positive classification ratio, we used cascade correlation neural network (CCNN) with

grey level run length matrix (GLRLM) features. In the last step, hybrid form of discriminant analysis and

support vector machine (SVM) methods were used with GLRLM features for benign/malign

classification of detected MC clusters. The open access Mammographic Image Analysis Society (MIAS)

database was used for the study. Experimental results show that the proposed algorithm obtained 86%

sensitivity, 98.3% specificity and 1.163 FPpI rates for detection an for diagnosis of breast cancer, the

obtained sensitivity and specificity values are 100% and 100% respectively. Despite the vision difficulty

of MC clusters, the novel system provides very satisfactory results. Furthermore, the developed system

is fully automatic whole system which gives outputs as percentages and transformed assessment

categories.

Anahtar Kelimeler

• Breast cancer
• Computer aided diagnosis
• Cascade correlation neural network (CCNN)
• Grey level cooccurrence matrix (GLCM)
• Grey level run length matrix (GLRLM)
• Mammograms

Kaynakça

1. Albregsten, F., 2008, “Statistical Texture Measures Computed from Gray Level Cooccurrence Matrices”, Technical Note, Department of Informatics, University of Oslo.
2. Bird, R.G., Wallace, T.W., Yankaskas, B.C., 1992, “Analysis of Cancers Missed at Screening Mammography”, Radiology, Vol. 184, pp. 613-617.
3. Bria, A., Karssemeijer, N., Tortorella, F., 2014, “Learning from Unbalanced Data: A Cascade-Based Approach for Detecting Clustered Microcalcifications”, Medical Image Analysis, Vol. 18, pp. 241-252.
4. Chandra, B., Varghese, P.P., 2007, “Applications of Cascade Correlation Neural Networks for Cipher System Identification”, International Journal of Computer, Information, Systems and Control Engineering, Vol. 1, No. 2, pp. 343-346.
5. Cheng, H.D., Shi, X.J., Min, R., Hu, L.M., Cai, X.P., Du, H.N., 2006, “Approaches for Automated Detection and Classification of Masses in Mammograms”, Pattern Recognition, Vol. 39, pp. 646 – 668.
6. Dennis, J.E., Schnabel, R.B., 1996, Numerical Methods for Unconstrained Optimization and Nonlinear Equations, Siam Press, Philadelphia, A.B.D.
7. Dheeba, S., Singh, N.A., Selvi, S.T., 2014, “Computer-Aided Detection of Breast Cancer on Mammograms: A Swarm Intelligence Optimized Wavelet Neural Network Approach”, Journal of Biomedical Informatics, Vol. 49, pp. 45-52.
8. Diaz-Huerta, C.C., Felipe-Riveron, E.M., Montaño-Zetina, L.M., 2014, “Quantitative Analysis of Morphological Techniques for Automatic Classification of Micro-Calcifications in Digitized Mammograms”, Expert Systems with Applications, Vol. 41, pp. 7361–7369.

9. Ergen, B., Baykara, M., 2011, “İstatistiksel Uzaysal Alan Metotlarının Içerik Tabanlı Tıbbi Görüntü Erişimi için Bir Uygulama”, Fırat University Mühendislik Bilimleri Dergisi, Vol. 23, No. 2, pp. 87-93.
10. Fahlman, S.E., Lebiere, C., “The Cascade-Correlation Learning Architecture”, Advances in Neural Information Processing Systems 2, San Francisco, 1990.
11. Gao, X.Z., Wang, X., Ovaska, S.J., 2009, “Fusion of Clonal Selection Algorithm and Differential Evolution Method in Training Cascade–Correlation Neural Network”, Neurocomputing, Vol. 72, pp. 2483–2490.
12. Halkiotis, S., Botsis, T., Rangoussi, M., 2007, “Automatic Detection of Clustered Microcalcifications in Digital Mammograms Using Mathematical Morphology and Neural Networks”, Signal Processing, Vol. 87, pp. 1559–1568.
13. Haralick, R.M., Shanmugam, K., Dinstein, I., 1973, “Texture Feature for Image Classification”, IEEE Transaction on System, Man and Cybernetics, Vol. 3, No. 6, pp. 610-621.
14. Herwanto, D., Arymurthy, A.M., 2013, “Association Technique Based on Classification for Classifying Microcalcification and Mass in Mammogram”, International Journal of Computer Science, Vol. 10, No. 2, pp. 252-259.
15. Jasmine, J.S.L., Baskaran, S., Govardhan, A.A., 2013, “Robust Approach to Classify Microcalcification in Digital Mammograms Using Contourlet Transform and Support Vector Machine”, American Journal of Engineering and Applied Sciences, Vol. 6, No. 1, pp. 57-68.
16. Jasmine, J.S.L., Govardhan, A., Baskaran, S., “Microcalcification Detection in Digital Mammograms Based on Wavelet Analysis and Neural Networks”, International Conference on Control, Automation, Communication and Energy Conservation, Perundurai, 1-6, 4-6 June 2009.
17. Jelvehfard, E., Faez, K., Laluie, A., 2013, “Microcalcification Detection in Mamography Images Using 2D Wavelet Coefficients Histogram”, Computer Science and Information Technology, Vol. 1, No. 3, pp. 178-184.
18. Karahaliou, A., Skiadopoulos, S., Boniatis, I., Sakellaropoulos, P., Likaki, E., Panayiotakis, G., Costaridou, L., 2007, “Texture Analysis of Tissue Surrounding Microcalcifications on Mammograms for Breast Cancer Diagnosis”, The British Journal of Radiology, Vol. 80, pp. 648-656.
19. Kovalishyn, V.V., Tetko, I.V., Luik, A.I., Kholodovych, V.V., Villa, A.E.P., Livingstone, D.J., 1998, “Neural Network Studies. 3. Variable Selection in The Cascade-Correlation Learning Architecture”, Journal of Chemical Information and Computer Sciences, Vol. 38, pp. 651-659.
20. Kurt, B., Nabiyev, V.V., Turhan, K., 2015, “A Novel Algorithm for Segmentation of Suspicious Microcalcification Regions on Mammograms”, Lecture Notes in Computer Science, Vol. 9043, pp. 222-230.
21. Martins, L.O., Santos, A.M., Silva, A.C., Paiva, A.C., “Classification of Normal, Benign And Malignant Tissues Using Co-Occurrence Matrix and Bayesian Neural Network in Mammographic Images”, Proceedings of the 9th Brazilian Symposium on Neural Networks, Ribeirao Preto, 24-29, 23-27 October 2006,.
22. Mazurowskia, M.A., Habasa, P.A., Zuradaa, J.M., Lob, J.Y., Bakerb, J.A., Tourassib, G.D., 2008, “Training Neural Network Classifiers for Medical Decision Making: The Effects of Imbalanced Datasets on Classification Performance”, Neural Networks, Vol. 21, pp. 427-436.
23. Medcalc Statistical Software, http://www.medcalc.org/ ( last modified 2013), last accessed 22 April 2014.
24. Mohamed, H., Mabrouk, M.S., Sharawy, A., 2014, “Computer Aided Detection System for Micro Calcifications in Digital Mammograms”, Computer Methods and Programs in Biomedicine, Vol. 116, pp. 226-235.
25. Mohanalin, J., Beenamol, M., Kalra, P.K., Kumar, N., 2010, “A Novel Automatic Microcalcification Detection Technique Using Tsallis Entropy & Type II Fuzzy Index”, Computers and Mathematics with Applications, Vol. 60, pp. 2426–2432.
26. Mohanty, A.K., Beberta, S., Lenka, S.K., 2011, “Classifying Benign and Malignant Mass Using GLCM and GLRLM Based Texture Features From Mammogram”, International Journal of Engineering Research and Applications, Vol. 1, pp. 687-693.
27. Nocedal, G., Wright, S., 2006, Numerical Optimization, Springer, New York, A.B.D.
28. Pal, N.R., Bhowmick, B., Patel, S.K., Pal, S., Das, J., 2008, “A Multi-Stage Neural Network Aided System for Detection of Microcalcifications in Digitized Mammograms”, Neurocomputing, Vol. 71, pp. 2625– 2634.
29. Phadke, A.C., Rege, P.P., 2013, “Detection and Classification of Microcalcifications Using Discrete Wavelet Transform”, International Journal of Emerging Trends&Technology in Computer Science, Vol. 2, No. 4, pp. 130-134.
30. Radhakrishnan, M., Kuttiannan, T., 2012, “Comparative Analysis of Feature Extraction Methods for The Classification of Prostate Cancer From TRUS Medical Images”, International Journal of Computer Science, Vol. 9, No. 2, pp. 171-179.
31. Rajesh, A., Ellappan, M., 2014, “Classification of Microcalcification Based on Wave Atom Transform”, Journal of Computer Science, Vol. 10, No. 8, pp. 1543-1547.
32. Rizzi, M., D’Aloia, M., Castagnolo, B., 2012, “Review: Health Care CAD Systems for Breast Microcalcification Cluster Detection”, Journal of Medical and Biological Engineering, Vol. 32, No. 3, pp. 147-156.
33. Sabu, M.A., Ponraj, D.N., Poongodi, R., 2012, “Textural Features Based Breast Cancer Detection: A Survey”, Journal of Emerging Trends in Computing and Information Sciences, Vol. 3, No. 9, pp. 1329-1334.
34. Sharma, N., Om, H., 2014, “Cascade Correlation Neural Network Model for Classification of Oral Cancer”, Wseas Transactions on Biology And Biomedicine, Vol. 11, pp. 45-51.
35. Stewart, B.W., Wild, C.P., 2014, World Cancer Report 2014, World Health Organization Press, Swiss.
36. Strange, H., Chen, Z., Denton, E.R.E., Zwiggelaar, R., 2014, “Modelling Mammographic Microcalcification Clusters Using Persistent Mereotopology”, Pattern Recognition Letters, Vol. 47, pp. 157–163.
37. Suba, C., Nirmala, K., 2015, “An Automated Classification of Microcalcification Clusters in Mammograms Using Dual Tree M-Band Wavelet Transform and Support Vector Machine”, International Journal of Computer Applications, Vol. 115, No. 20, pp. 24-29.
38. Thangavel, K., Mohideen, A.K., 2009, “Classification of Microcalcifications Using Multi-Dimensional Genetic Association Rule Miner”, International Journal of Recent Trends in Engineering, Vol. 2, No. 2, pp. 233-235.
39. The American College of Radiology (ACR), ACR BI-RADS® Atlas — Mammography, Frequently Asked Questions, https://www.acr.org/-/media/ACR/Files/RADS/BI-RADS/Mammography-FAQ.pdf, last accessed 22 October 2015.
40. University of Essec, Mamographic Image Analysis Society, http://peipa.essex.ac.uk/info/mias.html, last accessed 22 December 2014.
41. Vivona, L., Cascio, D., Fauci, F., Raso, G., 2014, “Fuzzy Technique for Microcalcifications Clustering in Digital Mammograms”, BMC Medical Imaging, Vol. 14, No.23, pp. 1-18.
42. Xu, D., Kurani, A.S., Furst, J.D., Raicu, D.S., “Run-Length Encoding for Volumetric Texture”, The IASTED International Conference on Visualization, Imaging, and Image Processing, Marbella, Spain, 131-136, 6-8 September 2004.
43. Zyout, I., Czajkowska, J., Grzegorzek, M., 2015, “Multi-Scale Textural Feature Extraction and Particle Swarm Optimization Based Model Selection for False Positive Reduction in Mammography”, Computirized Medical Imaging and Graphics, Vol. 46, No. 2, pp. 95-107.