Meme Kanseri Histopatalojik Görüntülerinin Konvolüsyonal Sinir Ağları ile Sınıflandırılması

Yıl 2019, , 391 - 398, 27.09.2019

Muhammed Talo

https://doi.org/10.35234/fumbd.517939

Cited By: 5

Öz

Meme
kanseri, dünya çapında kadınlar arasında en fazla ölümün görüldüğü kanser
türüdür. Meme kanseri imgelerinin bilgisayar destekli sistemler yardımıyla
hızlı ve doğru bir şekilde sınıflandırılması hayati önem arz etmektedir. Bu
çalışmada, meme kanseri imgelerini iyi ve kötü huylu olarak sınıflandırmak için
ResNet-50 mimarisi önerilmiştir. Evrişimsel Sinir Ağı tabanlı ResNet-50
mimarisi kullanılarak, açık kaynak BreakHis veri setindeki, meme kanseri
imgelerinin ikili sınıflandırılması gerçekleştirilmiştir. ResNet-50 mimarisinin
eğitiminde transfer öğrenme yöntemi uygulanmıştır. Önerilen modelin
sınıflandırma başarısının, literatürdeki mevcut çalışmalara kıyasla daha yüksek
olduğu gözlemlenmiştir. Ayrıca önerilen model, meme kanseri imgeleri üzerinde
herhangi bir ön işleme yapmadan verileri otomatik olarak sınıflandırmaktadır.

Anahtar Kelimeler

Meme kanseri, Tıbbi görüntü analizi, Derin öğrenme, KSA

Classification of Histopathological Breast Cancer Images using Convolutional Neural Networks

Öz

Breast
cancer is the most common form of cancer that causes death among women
worldwide. The automated classification of breast cancer images with the help
of computer aided systems is significantly important for early intervention. In
this study, transfer learning method was used to classify breast cancer biopsy
images as benign and malignant. Binary classification of breast cancer images
from open source BreakHis data set was performed using the ResNet-50 convolutional
neural network (CNN) architecture. The classification accuracy of the proposed
model is higher than all existing studies on the BreakHis dataset. In addition,
the proposed model provides automatic classification of breast cancer images
without manual feature extraction or any pre-processing on images.

Anahtar Kelimeler

Breast cancer, Medical image analysis, Deep learning, CNN

Kaynakça

• https://www.who.int/cancer/prevention/diagnosis-screening/breast-cancer/en/ (son erişim traihi: 25.01.19).
• Loukas C, Kostopoulos S, Tanoglidi A, Glotsos D, Sfikas C, Cavouras D. “Breast cancer characterization based on image classification of tissue sections visualized under low magnification.” Computational and mathematical methods in medicine. 2013 Aug 31;2013.
• National Research Council, 2005. Saving women's lives: strategies for improving breast cancer detection and diagnosis. National Academies Press.
• Veta, M., Pluim, J.P., Van Diest, P.J. and Viergever, M.A., 2014. Breast cancer histopathology image analysis: A review. IEEE Transactions on Biomedical Engineering, 61(5), pp.1400-1411.
• Gupta, V. and Bhavsar, A., 2017, July. Breast cancer histopathological image classification: is magnification important?. In IEEE Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW).
• Spanhol, F.A., Oliveira, L.E., Petitjean, C., & Heutte, L. (2016). Breast cancer histopathological image classification using Convolutional Neural Networks. 2016 International Joint Conference on Neural Networks (IJCNN), 2560-2567.
• Kowal, M., Filipczuk, P., Obuchowicz, A., Korbicz, J. and Monczak, R., 2013. Computer-aided diagnosis of breast cancer based on fine needle biopsy microscopic images. Computers in biology and medicine, 43(10), pp.1563-1572.
• Zhang, Y., Zhang, B., Coenen, F., Xiao, J. and Lu, W., 2014. One-class kernel subspace ensemble for medical image classification. EURASIP Journal on Advances in Signal Processing, 2014(1), p.17.
• Zhang, Y., Zhang, B., Coenen, F. and Lu, W., 2013. Breast cancer diagnosis from biopsy images with highly reliable random subspace classifier ensembles. Machine vision and applications, 24(7), pp.1405-1420.
• George, Y.M., Zayed, H.H., Roushdy, M.I. and Elbagoury, B.M., 2014. Remote computer-aided breast cancer detection and diagnosis system based on cytological images. IEEE Systems Journal, 8(3), pp.949-964.
• Filipczuk, P., Fevens, T., Krzyzak, A. and Monczak, R., 2013. Computer-Aided Breast Cancer Diagnosis Based on the Analysis of Cytological Images of Fine Needle Biopsies. IEEE Trans. Med. Imaging, 32(12), pp.2169-2178.
• Gupta, V. and Bhavsar, A., 2017, July. Breast cancer histopathological image classification: is magnification important?. In IEEE Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW).
• Spanhol, F.A., Oliveira, L.S., Cavalin, P.R., Petitjean, C. and Heutte, L., 2017, October. Deep features for breast cancer histopathological image classification. In Systems, Man, and Cybernetics (SMC), 2017 IEEE International Conference on(pp. 1868-1873). IEEE.
• Araújo, T., Aresta, G., Castro, E., Rouco, J., Aguiar, P., Eloy, C., Polónia, A. and Campilho, A., 2017. Classification of breast cancer histology images using convolutional neural networks. PloS one, 12(6), p.e0177544.
• Bayramoglu, N., Kannala, J. and Heikkilä, J., 2016, December. Deep learning for magnification independent breast cancer histopathology image classification. In Pattern Recognition (ICPR), 2016 23rd International Conference on (pp. 2440-2445). IEEE.
• Alom, M.Z., Yakopcic, C., Taha, T.M. and Asari, V.K., 2018. Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural Network. arXiv preprint arXiv:1811.04241.
• Veta, M., Pluim, J.P., Van Diest, P.J. and Viergever, M.A., 2014. Breast cancer histopathology image analysis: A review. IEEE Transactions on Biomedical Engineering, 61(5), pp.1400-1411.
• K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, 2016.
• Yildirim, Ö., 2018. A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification. Computers in biology and medicine, 96, pp.189-202.
• Yildirim, O., San Tan, R. and Acharya, U.R., 2018. An efficient compression of ECG signals using deep convolutional autoencoders. Cognitive Systems Research, 52, pp.198-211.
• Yıldırım, Ö., Pławiak, P., Tan, R.S. and Acharya, U.R., 2018. Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Computers in biology and medicine, 102, pp.411-420.
• Talo, M., Baloglu, U.B., Yıldırım, Ö. and Acharya, U.R., 2018. Application Of Deep Transfer Learning For Automated Brain Abnormality Classification Using Mr Images. Cognitive Systems Research.
• http://imagenet.org/challenges/ilsvrc+mscoco2015 (son erişim tarihi:25.01.19).
• Kahya, M.A., Al-Hayani, W. and Algamal, Z.Y., 2017. Classification of breast cancer histopathology images based on adaptive sparse support vector machine. Journal of Applied Mathematics and Bioinformatics, 7(1), p.49.
• Han, Z., Wei, B., Zheng, Y., Yin, Y., Li, K. and Li, S., 2017. Breast cancer multi-classification from histopathological images with structured deep learning model. Scientific reports, 7(1), p.4172.
• Ketkar, N., 2017. Deep Learning with Python. Apress:2017.