Derin Sinir Ağları Kullanılarak Koyun-Keçi Çiçeği Hastalığının Tespiti ve Sınıflandırılması için Hibrit Bir Yaklaşım

Yıl 2022, , 1542 - 1554, 31.12.2022

Nilgün Şengöz

https://doi.org/10.31202/ecjse.1159621

Öz

Yapay zeka, ve bunun alt dalları olan makine öğrenimi ve derin öğrenme medikal görüntüleme sistemlerinden yüz tanıma, otonom sürüş gibi bir çok farklı alanlarda kendini ispat etmiştir. Özellikle derin öğrenme modelleri günümüzde çok popüler olmuştur. Derin öğrenme modelleri yapısı itibariyle çok karmaşık olduğundan ötürü doğası gereği kara-kutu modellerine en iyi örneklerden birisidir. Bu durum yorumlanabilirlik ve açıklanabilirlik bağlamında son kullanıcıyı şüphe içerisinde bırakmaktadır. Bu nedenle, bu tür sistemlerin anlaşılabilir metotların açıklanabilir yapay zeka (AYZ) ile yapılması ihtiyacı son yıllarda yaygın olarak geliştirilmiştir. Bu bağlamda, çalışma neticesinde hibrid bir metot geliştirilmiş olup farklı derin öğrenme algoritmaları üzerinden yeni ve orijinal veri kümesi üzerinde sınıflandırma çalışması gerçekleştirilmiştir. Sınıflandırma doğruluğu %99,643 ile VGG16 mimarisi üzerinden Grad-CAM uygulaması gerçekleştirilmiş ve CLAHE metodu ile ön işlenen görüntülerin ısı haritaları çıkarılmıştır.

Anahtar Kelimeler

derin öğrenme, CLAHE, açıklanabilir yapay zeka, koyun-keçi çiçek hastalığı

Teşekkür

Bu çalışmanın gerçekleştirilmesi için desteklerini esirgemeyen Prof. Dr. Özlem Özmen’e ve danışman hocam Prof. Dr. Tuncay Yiğit’e teşekkür ederim.

A Hybrid Approach for Detection and Classification of Sheep-Goat Pox Disease Using Deep Neural Networks

Öz

Artificial intelligence and its sub-branches, machine learning and deep learning, have proven themselves in many different areas such as medical imaging systems, face recognition, autonomous driving. Especially deep learning models have become very popular today. Because deep learning models are very complex in nature, they are one of the best examples of black-box models. This situation leaves the end user in doubt in terms of interpretability and explainability. Therefore, the need to make such systems understandable methods with explainable artificial intelligence (XAI) has been widely developed in recent years. In this context, a hybrid method has been developed as a result of the study, and classification study has been carried out on the new and original dataset over different deep learning algorithms. Grad-CAM application was performed on VGG16 architecture with classification accuracy of 99.643% and heat maps of pre-processed images were obtained by CLAHE method.

Anahtar Kelimeler

deep learning, CLAHE, explainable artificial intelligence, sheep-goat pox

Kaynakça

• Ayhan, V., Taşkın, T., İnce, D., Yılmaz, M., Boyar, S., Bardakçıoğlu, E. Damızlık koyun-keçi yetiştiricileri birliklerinin edinimleri. İLİK KONG, 68, (2010)
• Jiang, Y., Chan, C. K., Chan, R. C., Wang, X., Wong, N., To, K. F., Poon, C. C.. Identification of Tissue Types and Gene Mutations from Histopathology Images for Advancing Colorectal Cancer Biology, 2022, IEEE Open Journal of Engineering in Medicine and Biology
• Saldanha, O. L., Quirke, P., West, N. P., James, J. A., Loughrey, M. B., Grabsch, H. I., Kather, J. N., Swarm learning for decentralized artificial intelligence in cancer histopathology, 2022, Nature Medicine, 1-8
• Abdelsamea, M. M., Zidan, U., Senousy, Z., Gaber, M. M., Rakha, E., & Ilyas, M.,. A survey on artificial intelligence in histopathology image analysis, 2022, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, e1474
• Sauter, D., Lodde, G., Nensa, F., Schadendorf, D., Livingstone, E., & Kukuk, M. Validating Automatic Concept-Based Explanations for AI-Based Digital Histopathology, 2022, Sensors, 22(14), 5346
• K. Roy, D. Banik, D. Bhattacharjee, and M. Nasipuri, Patch-based system for Classification of Breast Histology images using deep learning ,2019, Comput. Med. Imaging Graph., vol. 71, 90–103
• S. Chakraborty, S. Aich, A. Kumar, S. Sarkar, J.-S. Sim, and H.-C. Kim, Detection of cancerous tissue in histopathological images using Dual-Channel Residual Convolutional Neural Networks (DCRCNN), 2020, 22nd International Conference on Advanced Communication Technology (ICACT), 197–202
• C. Wang, J. Shi, Q. Zhang, and S. Ying, Histopathological image classification with bilinear convolutional neural networks, 2017, 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 4050– 4053
• Şengöz, N., Yiğit, T., Özmen, Ö., Isik, A.H., Importance of Preprocessing in Histopathology Image Classification Using Deep Convolutional Neural Network, 2022, Advances in Artificial Intelligence Research, 2(1), 1-6
• Yiğit, T., Şengöz, N., Özmen, Ö., Hemanth, J., Işık, A.H., Diagnosis of Paratuberculosis in Histopathological Images Based on Explainable Artificial Intelligence and Deep Learning, 2022, Traitement du Signal, 39(3), 863-869
• V. Petsiuk, A. Das, K. Saenko, RISE: Randomized Input Sampling for Explanation of Black-box Models, Br. Mach. Vis. Conf. 2018
• Graziani, M., Andrearczyk, V., Müller, H., Visualizing and interpreting feature reuse of pretrained CNNs for histopathology. In Irish Machine Vision and Image Processing Conference (IMVIP 2019), Dublin, Ireland, (2019)
• Yoon, H., Han, .Y, Hahn, H., Image Contrast Enhancement based Sub-histogram Equalization Technique without Over-equalization Noise, 2009, International Journal of Computer Science and Engineering, 3 (2)
• Yadav, G., Maheshwari, S., Agarwal, A., Contrast limited adaptive histogram equalization based enhancement for real time video system, 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2014, 2392-2397
• Lodhi, B., Kang, J., Multipath-DenseNet: A Supervised ensemble architecture of densely connected convolutional networks, 2019, Information Sciences, 482,63-72
• Tan, M., Le, Q.,V., EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, 2019, Proceedings of the 36th International Conference on Machine Learning, PMLR 97,6105–6114
• Theckedath, D., Sedamkar, R. R., Detecting affect states using VGG16, ResNet50 and SE-ResNet50 networks, 2020, SN Computer Science, 1(2), 1-7
• Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Rabinovich, A., Going deeper with convolutions. 2015, In Proceedings of the IEEE conference on computer vision and pattern recognition, 1-9
• Li, J., Wang, P., Li, Y.Z., Zhou, Y., Liu, X.L., Luan, K., Transfer learning of pre-trained inception-V3 model for colorectal cancer lymph node metastasis classification, 2018, IEEE International Conference on Mechatronics and Automation, 10, 1650–1654
• Sinha, D., El-Sharkawy, M., Thin MobileNet: An Enhanced MobileNet Architecture, 2019, IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), 0280-0285
• Sahlol, A.T., Abd Elaziz, M., Tariq Jamal, A., Damaševičius, R., Farouk Hassan, O., A Novel Method for Detection of Tuberculosis in Chest Radiographs Using Artificial Ecosystem-Based Optimisation of Deep Neural Network Features, 2020, Symmetry, 12(7),1146
• Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D., Grad-CAM: Visual explanations from deep networks via gradient-based localization, 2017, IEEE International Conference on Computer Vision (ICCV), 618-626