Derin Öğrenme Kullanarak Tiroid Kanseri Teşhisi

Year 2021, Issue: 29, 292 - 298, 01.12.2021

Zeynep Aytaç , İsmail Iseri , Beşir Dandıl

https://doi.org/10.31590/ejosat.1011166

Cited By: 2

Abstract

Geçmişten günümüze yapay zekanın kullanım alanları giderek artmaktadır ve en çok kullanılan alanlardan biri de sağlık sektörüdür. Özellikle tıbbi görüntülerin işlenmesinde oldukça başarılı sonuçlar vermesi ile bir yapay zekâ algoritması olan derin öğrenme, bu görüntülerin işlenmesi ve yorumlanması konusunda sıkça tercih edilmektedir. Son yıllarda dünya çapında artan kanser oranlarıyla birlikte gelişen görüntüleme teknikleri bu hastalıkların teşhisi ve tanısı konusunda uzmanlara oldukça faydalı hale gelmiştir. Bu çalışmanın temel amacı sitopatologlar tarafından manuel olarak yapılan teşhis etme biçiminden esinlenerek derin öğrenmeye dayalı bir çalışma gerçekleştirilmiştir. Bu algoritma bir derin öğrenme mimarisi olan evrişimsel sinir ağı kullanılmıştır Evrişimsel sinir ağı, tanısal olarak ilgili görüntü bölgelerini tanımlayarak önceden belirlenen malignite skolarlarını atar ve bu sayede malignite tahmini yapılır. Deneysel sonuçlar önerilen çalışmanın uzmanlarla karşılaştırılabilir bir performans elde ederek sitopatologlara ikinci bir görüş sağlayabildiğini ve iş yükünü azalttığını göstermektedir.

Keywords

Derin Öğrenme, Evrişimsel sinir ağı, yapay zeka, tiroid kanseri

Diagnosing Thyroid Cancer Using Deep Learning

Abstract

From past to present, the usage areas of artificial intelligence are increasing and one of the most used areas is the health sector. Deep learning, which is an artificial intelligence algorithm with its very successful results in the processing of medical images, is frequently preferred for the processing and interpretation of these images. Imaging techniques, which have developed with the increasing cancer rates worldwide in recent years, have become very useful to experts in the diagnosis and diagnosis of these diseases. The main purpose of this study is to carry out a deep learning-based study inspired by the manual diagnosis method by cytopathologists. This algorithm is used in convolutional neural network, which is a deep learning architecture. Convolutional neural network defines diagnostically relevant image regions and assigns predetermined malignancy scolars, and thus malignancy prediction is made. Experimental results show that the proposed study can achieve a performance comparable to that of experts, providing cytopathologists with a second opinion and reducing their workload.

Keywords

Deep Learning, Convolutional Neural Network, Artificial Intelligence, Thyroid Cancer., Deep Learning, Convolutional Neural Network, Artificial Intelligence, Thyroid Cancer.

References

• Du XL, Li WB, Hu BJ. Application of artificial intelligence in ophthalmology. Int J Ophthalmol. 2018;11(9):1555–61.
• McCorduck P. Machines who think: a personal inquiry into the his- tory and prospects of artificial intelligence. Natick: A.K. Peters, 2004.
• Russell SJ, Norvig P. Artificial intelligence: a modern approach. Upper Saddle River: Prentice Hall, 2003.
• Gupta, N., Sarkar, C., Singh, R. ve Karak, A. K. (2001). Evaluation of diagnostic efficiency of computerized image analysis based quantitative nuclear parameters in papillary and follicular thyroid tumors using paraffin-embedded tissue sections. Pathology Oncology Research, 7(1), 46-55.
• Daskalakis, A., Kostopoulos, S., Spyridonos, P., Glotsos, D., Ravazoula, P., Kardari, M., Kalatzis, I., Cavouras, D. ve Nikiforidis, G. (2008). Design of a multi-classifier system for discriminating benign from malignant thyroid nodules using routinely H&E-stained cytological images. Computers in biology and medicine, 38(2), 196-203.
• Selvathi, D. ve Sharnitha, V. S. (2011). Thyroid classification and segmentation in ultrasound images using machine learning algorithms. In 2011 International Conference on Signal Processing, Communication, Computing and Networking Technologies, 836-841. IEEE.
• Ding, J., Cheng, H. D., Huang, J. ve Zhang, Y. (2014). Multiple-instance learning with global and local features for thyroid ultrasound image classification. In 2014 7th International Conference on Biomedical Engineering and Informatics 66-70. IEEE.
• Ma, J., Wu, F., Jiang, T. A., Zhao, Q., ve Kong, D. (2017). Ultrasound image-based thyroid nodule automatic segmentation using convolutional neural networks. International journal of computer assisted radiology and surgery, 12(11), 1895-1910. Doi: 10.1007/s11548-017-1649-7
• Li, H., Weng, J., Shi, Y., Gu, W., Mao, Y., Wang, Y., Liu, W. ve Zhang, J. (2018). An improved deep learning approach for detection of thyroid papillary cancer in ultrasound images. Scientific reports, 8(1), 1-12. Doi:10.1038/s41598-018-25005-7
• Fukushima, K., Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36 (4), 193–202. doi: 10.10 07/BF0 0344251, 1980.
• Lo, S.-C., Lou, S.-L., Lin, J.-S., Freedman, M.T., Chien, M.V., Mun, S.K., Artificial convolution neural network techniques and applications for lung nodule detec- tion. IEEE Trans. Med. Imaging 14, 711–718. doi: 10.1109/42.476112, 1995.
• Sirinukunwattana, K., Raza, S. E. A., Tsang, Y. W., Snead, D. R., Cree, I. A. ve Rajpoot, N. M. (2016). Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images. IEEE transactions on medical imaging, 35(5), 1196-1206.
• Kraus, O. Z., Ba, J. L. ve Frey, B. J. (2016). Classifying and segmenting microscopy images with deep multiple instance learning. Bioinformatics, 32(12), 52-59.
• Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Hurst, R. T., Kendall, C. B., Gotway, M. B. ve Liang, J. (2016). Convolutional neural networks for medical image analysis: Full training or fine tuning?. IEEE transactions on medical imaging, 35(5), 1299-1312.
• Cruz-Roa, A., Gilmore, H., Basavanhally, A., Feldman, M., Ganesan, S., Shih, N. N., Tomaszewski, J., Gonzales, F. A. Ve Madabhushi, A. (2017). Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent. Scientific reports, 7, 46450. Doi: 10.1038/srep46450.
• Hou, L., Samaras, D., Kurc, T. M., Gao, Y., Davis, J. E. ve Saltz, J. H. (2016). Patch-based convolutional neural network for whole slide tissue image classification. In Proceedings of the ieee conference on computer vision and pattern recognition, 2424-2433.
• Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M. ve Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. nature, 542(7639), 115-118.
• Shi, G., Wang, J., Qiang, Y., Yang, X., Zhao, J., Hao, R., Yang, W., Du, Q. ve Kazihise, N. G. F. (2020). Knowledge-guided synthetic medical image adversarial augmentation for ultrasonography thyroid nodule classification. Computer Methods and Programs in Biomedicine, 196, 105611.
• Ravi, D., Wong, C., Deligianni, F., Berthelot, M., Andreu-Perez, J., Lo, B., et al. (2017). Deep learning for health informatics. IEEE Journal of Biomedical and Health Informatics, 21(1), 4–21.
• Nielsen, M. A. (2015). Neural networks and deep learning. Determination Press.
• Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In IEEE conference on, Computer vision and pattern recognition, 2009. CVPR. 2009 (pp. 248–255). IEEE.
• Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097–1105).
• Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013). Overfeat: Integrated recognition, localization and detection using convolutional networks. (pp. 1–16). arXiv preprint arXiv:13126229.
• Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., et al. (2015). Going deeper with convolutions. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1–9).
• Chandrakumar, T., & Kathirvel, R. (2016). Classifying diabetic retinopathy using deep learning architecture. International Journal of Engineering Research & Technology (IJERT), 5(6), 19–24.
• 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.
• Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., & Fergus, R. (2013) Regularization of neural networks using dropconnect. In International Conference on Machine Learning. (pp. 1058–1066).
• Pedraza l.,Vargas C., Narvaez F., Duran O., Munoz E., Romero E. (2015). An open access thyroid ultrasound-image Database. 10th International Symposium on Medical Information Processing and Analysis, doi: 10.1117/12.2073532