Breast Cancer Detection on Histopathological Images Using Deep Neural Networks

Abstract

In this study, a model is proposed using deep neural network on histopathological images for the detection of breast cancer, which is one of the most dangerous diseases of our age and is very difficult to treat in case of late diagnosis. Within the study, computer-aided diagnosis systems are used as an assistant diagnostic method in the detection of breast cancer by reaching high accuracy values. The dataset has magnification ratios of 40X, 100X, 200X and 400X and contains a total of 7909 histopathological images. In the proposed deep neural network model, more successful results are obtained using four different pre-trained networks such as DenseNet201, Inception V3, ResNet50 and Xception. In order to further increase the performance of the models, dropout and data augmentation techniques are used. These networks are compared among themselves and the results obtained with the Xception network are performed to be more successful than other networks. In experimental studies carried out with the Xception network at the ratio of 200X magnification the most successful results are achieved with an accuracy score of 98.01, a precision value of 97.89 and recall value of 97.47 when comparing to other networks and other magnification ratios. The area value of under the ROC curve for the Xception network at 200X zoom ratio is 0.975. 

Keywords

• Breast cancer
• Histopathological image
• Classification
• Deep neural network
• pre-trained networks
• Xception

Derin Sinir Ağları Kullanarak Histopatolojik Görüntülerde Meme Kanseri Tespiti

Öz

Bu çalışmada çağımızın en tehlikeli hastalıklarından birisi olan ve geç teşhis durumunda tedavisi oldukça zor bir hal alan meme kanserinin histopatolojik görüntülerde tespiti için derin sinir ağları kullanılarak bir model önerilmiştir. Çalışma ile bilgisayar destekli teşhis sistemlerinin yüksek doğruluk değerlerine ulaşarak meme kanserinin tespitinde yardımcı bir teşhis metodu kullanılması sağlanmıştır. Kullanılan veriseti 40X, 100X, 200X ve 400X yakınlaştırma oranlarına sahip ve toplamda 7909 adet histopatolojik görüntü içermektedir. Önerilen derin sinir ağı modelinde DenseNet201, Inception V3, ResNet50 ve Xception olmak üzere dört farklı ön-eğitimli (pre-trained) ağ kullanılarak daha başarılı sonuçlar elde edilmiştir. Modellerin başarımlarını daha da artırmak amacıyla bırakma (dropout) ve veri artırma (data augmentation) yöntemleri kullanılmıştır. Kullanılan bu ağlar kendi arasında karşılaştırılmış ve Xception ağı ile elde edilen sonuçların diğer ağlara oranla daha başarılı olduğu görülmüştür. Xception ağı ile 200X yakınlaştırma oranında gerçekleştirilen deneysel çalışmalarda, hem diğer ağlara göre hem de diğer yakınlaştırma oranlarına göre en başarılı sonuçlara ulaşılmış ve 98.01’lik bir doğruluk (Accuracy) skoru, 97.89’luk bir hassasiyet (Precision) değeri ve 97.47’lik bir hatırlama (Recall) değeri elde edilmiştir. Xception ağının 200X yakınlaştırma oranındaki ROC eğrisi altındaki alan değeri ise 0.975 olarak hesaplanmıştır.

Anahtar Kelimeler

• Meme kanseri
• Histopatolojik görüntü
• Sınıflandırma
• Derin sinir ağları
• Xception
• ön-eğitimli ağlar

Kaynakça

1. Abdel-Zaher, A. M., & Eldeib, A. M. (2016). Breast cancer classification using deep belief networks. Expert Systems with Applications, 46, 139-144.
2. Azar, A. T., & El-Said, S. A. (2013). Probabilistic neural network for breast cancer classification. Neural Computing and Applications, 23(6), 1737-1751.
3. Behera, B., & Kumaravelan, G. (2019). Performance Evaluation of Deep Learning Algorithms in Biomedical Document Classification. Paper presented at the 2019 11th International Conference on Advanced Computing (ICoAC).
4. Bradley, A. P. (1997). The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern recognition, 30(7), 1145-1159.
5. Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
6. Collis, J. (2017). Glossary of Deep Learning: Batch Normalisation: Jun.
7. Davis, J., & Goadrich, M. (2006). The relationship between Precision-Recall and ROC curves. Paper presented at the Proceedings of the 23rd international conference on Machine learning.
8. Dogan, B. E., Gonzalez-Angulo, A. M., Gilcrease, M., Dryden, M. J., & Yang, W. T. (2010). Multimodality imaging of triple receptor–negative tumors with mammography, ultrasound, and MRI. American Journal of Roentgenology, 194(4), 1160-1166.

9. Goutte, C., & Gaussier, E. (2005). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. Paper presented at the European Conference on Information Retrieval.
10. Hajian-Tilaki, K. (2013). Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Caspian journal of internal medicine, 4(2), 627.
11. Han, Z., Wei, B., Zheng, Y., Yin, Y., Li, K., & Li, S. (2017). Breast cancer multi-classification from histopathological images with structured deep learning model. Scientific reports, 7(1), 1-10.
12. Hashemi, M. (2019). Enlarging smaller images before inputting into convolutional neural network: zero-padding vs. interpolation. Journal of Big Data, 6(1), 98.
13. Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
14. Huang, J., & Ling, C. X. (2005). Using AUC and accuracy in evaluating learning algorithms. IEEE Transactions on knowledge and Data Engineering, 17(3), 299-310.
15. Ide, H., & Kurita, T. (2017). Improvement of learning for CNN with ReLU activation by sparse regularization. Paper presented at the 2017 International Joint Conference on Neural Networks (IJCNN).
16. Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167.
17. Kalchbrenner, N., Grefenstette, E., & Blunsom, P. (2014). A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188.
18. Kumar, A., Singh, S. K., Saxena, S., Lakshmanan, K., Sangaiah, A. K., Chauhan, H., . . . Singh, R. K. (2020). Deep feature learning for histopathological image classification of canine mammary tumors and human breast cancer. Information Sciences, 508, 405-421.
19. Ling, C. X., Huang, J., & Zhang, H. (2003). AUC: a better measure than accuracy in comparing learning algorithms. Paper presented at the Conference of the canadian society for computational studies of intelligence.
20. Ma, X., Dai, Z., He, Z., Ma, J., Wang, Y., & Wang, Y. (2017). Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction. Sensors, 17(4), 818.
21. Mohammed, M. A., Al-Khateeb, B., Rashid, A. N., Ibrahim, D. A., Ghani, M. K. A., & Mostafa, S. A. (2018). Neural network and multi-fractal dimension features for breast cancer classification from ultrasound images. Computers & Electrical Engineering, 70, 871-882.
22. Moshkov, N., Mathe, B., Kertesz-Farkas, A., Hollandi, R., & Horvath, P. (2020). Test-time augmentation for deep learning-based cell segmentation on microscopy images. Scientific reports, 10(1), 1-7.
23. Nahid, A.-A., Mehrabi, M. A., & Kong, Y. (2018). Histopathological breast cancer image classification by deep neural network techniques guided by local clustering. BioMed research international, 2018.
24. Öztürk, Ş., & Akdemir, B. (2019). HIC-net: A deep convolutional neural network model for classification of histopathological breast images. Computers & Electrical Engineering, 76, 299-310.
25. Paasio, A., & Dawidziuk, A. (1999). CNN template robustness with different output nonlinearities. International Journal of Circuit Theory and Applications, 27(1), 87-102.
26. Perez, L., & Wang, J. (2017). The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621.
27. Powers, D. M. (2011). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation.
28. Powers, D. M. (2015). What the F-measure doesn't measure: Features, Flaws, Fallacies and Fixes. arXiv preprint arXiv:1503.06410.
29. Rakhlin, A., Shvets, A., Iglovikov, V., & Kalinin, A. A. (2018). Deep convolutional neural networks for breast cancer histology image analysis. Paper presented at the International Conference Image Analysis and Recognition.
30. Siegel, R. L., Miller, K. D., & Jemal, A. (2015). Cancer statistics, 2015. CA: a cancer journal for clinicians, 65(1), 5-29.
31. Siegel, R. L., Miller, K. D., & Jemal, A. (2019). Cancer statistics, 2019. CA: a cancer journal for clinicians, 69(1), 7-34.
32. Spanhol, F. A., Oliveira, L. S., Cavalin, P. R., Petitjean, C., & Heutte, L. (2017). Deep features for breast cancer histopathological image classification. Paper presented at the 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC).
33. Spanhol, F. A., Oliveira, L. S., Petitjean, C., & Heutte, L. (2015). A dataset for breast cancer histopathological image classification. IEEE Transactions on Biomedical Engineering, 63(7), 1455-1462.
34. Spanhol, F. A., Oliveira, L. S., Petitjean, C., & Heutte, L. (2016). Breast cancer histopathological image classification using convolutional neural networks. Paper presented at the 2016 international joint conference on neural networks (IJCNN).
35. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1), 1929-1958.
36. Stewart, B., & Wild, C. P. (2014). World cancer report 2014.
37. Sudharshan, P., Petitjean, C., Spanhol, F., Oliveira, L. E., Heutte, L., & Honeine, P. (2019). Multiple instance learning for histopathological breast cancer image classification. Expert Systems with Applications, 117, 103-111.
38. Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. Paper presented at the Thirty-first AAAI conference on artificial intelligence.
39. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
40. Tai, Y., Yang, J., & Liu, X. (2017). Image super-resolution via deep recursive residual network. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.
41. Taylor, L., & Nitschke, G. (2017). Improving deep learning using generic data augmentation. arXiv preprint arXiv:1708.06020.
42. Vani, S., & Rao, T. M. (2019). An Experimental Approach towards the Performance Assessment of Various Optimizers on Convolutional Neural Network. Paper presented at the 2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI).
43. Wang, D., Khosla, A., Gargeya, R., Irshad, H., & Beck, A. H. (2016). Deep learning for identifying metastatic breast cancer. arXiv preprint arXiv:1606.05718.