Journals / Konya Journal of Engineering Sciences / 2018 / Cilt: 6 Sayı: 3

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

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

Pages
355–376
Publication Date
2018-09-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

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, theobtained sensitivity and specificity values are 100% and 100% respectively.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:An automated computer aided diagnosis system has been proposed for detection ofmicrocalcification (MC) clusters in mammograms.
📊
Key Findings & Data:Then todecrease the false positive classification ratio, we used cascade correlation neural network (CCNN) withgrey level run length matrix (GLRLM) features.
💡
Conclusion & Impact: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, theobtained sensitivity and specificity values are 100% and 100% respectively.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Meme kanseri · Bilgisayar destekli tanı · Kademeli korelasyon sinir ağı (CCNN)

Abstract

An automated computer aided diagnosis system has been proposed for detection ofmicrocalcification (MC) clusters in mammograms. The proposed system is a whole system includingsuspicious regions identification, MCs detection, false positive reduction and benign/malignclassification. 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 todecrease the false positive classification ratio, we used cascade correlation neural network (CCNN) withgrey level run length matrix (GLRLM) features. In the last step, hybrid form of discriminant analysis andsupport vector machine (SVM) methods were used with GLRLM features for benign/malignclassification 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, theobtained sensitivity and specificity values are 100% and 100% respectively. Despite the vision difficultyof MC clusters, the novel system provides very satisfactory results. Furthermore, the developed systemis fully automatic whole system which gives outputs as percentages and transformed assessmentcategories.

Özet

Mamografide mikrokalsifikasyon (MC) kümelerinin saptanması için otomatik bir bilgisayar desteklitanı sistemi önerilmiştir. Önerilen sistem şüpheli bölgelerin tanımlanması, MC'lerin tespiti, yanlış pozitifindirgeme ve iyi huylu/kötü huylu sınıflamayı içeren bütün bir sistemdir. Şüpheli mikrokalsifikasyonbölgelerinin sınıflandırılması için, gri seviye eş-oluşum matrisi (GLCM) ve istatistiksel özellikler ile çoktabakalı bir perceptron (MLP) sinir ağı kullanıldı. Daha sonra, yanlış pozitif sınıflandırma oranınıazaltmak için, gri seviye çalışma uzunluğu matrisi (GLRLM) özellikli kademeli korelasyon sinir ağı(CCNN) kullanılmıştır. Son adımda, tespit edilen MC kümelerinin iyi huylu/kötü huylu sınıflandırmasıiçin GLRLM özellikleri ile hibrid yapıda diskriminant analizi ve destek vektör makinesi (SVM)yöntemleri kullanıldı. Çalışma için açık erişimli Mamografik Görüntü Analizi Derneği (MIAS) veritabanı 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 veözgüllük değerlerinin sırasıyla %100 ve %100 olduğunu ortaya koymuştur. MC kümelenmeleriningörme zorluğu olsa da, önerilen sistem çok tatmin edici sonuçlar vermektedir. Bununla birlikte, gelişmişsistem; çıktıları yüzdeler ve dönüştürülmüş değerlendirme kategorileri olarak veren tam otomatik birbütün sistemdir.

🔖

Cite This Article

KURT, B., NABİYEV, V. V., TURHAN, K. (2018). AN AUTOMATED COMPUTER-AIDED DETECTION (CADe) AND DIAGNOSIS (CADx) SYSTEM FOR BREAST MICROCALCIFICATIONS IN MAMMOGRAMS. Konya Journal of Engineering Sciences, Cilt: 6 Sayı: 3, 355–376. https://ajindex.com/articles/909296

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (11)

  1. Albregsten, F., 2008, “Statistical Texture Measures Computed from Gray Level Cooccurrence Matrices”, Technical Note, Department of Informatics, University of Oslo. Bird, R.G., Wallace, T.W., Yankaskas, B.C., 1992, “Analysis of Cancers Missed at Screening Mammography”, Radiology, Vol. 184, pp. 613-617.
  2. 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.
  3. 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.
  4. 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. Dennis, J.E., Schnabel, R.B., 1996, Numerical Methods for Unconstrained Optimization and Nonlinear Equations, Siam Press,
  5. Philadelphia, A.B.D. 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.
  6. 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.
  7. 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.
  8. Fahlman, S.E., Lebiere, C., “The Cascade-Correlation Learning Architecture”, Advances in Neural Information Processing Systems 2, San Francisco, 1990.
  9. 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.
  10. 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.
  11. 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. H