Support Vector Machine Fed with Different Deep Features for Classification of Lung Diseases from Chest X-Ray Images

Yıl 2024, , 11 - 21, 31.01.2024

Hüseyin Üzen , Hüseyin Fırat

https://doi.org/10.17671/gazibtd.1366846

Öz

COVID-19, tuberculosis, and pneumonia, three of the most deadly lung diseases, are routinely detected using chest X-ray (CXR) scans. Recent technological advancements are ushering in a new era of computer-assisted systems for automated diagnosis, offering significant benefits. This study proposes a three-stage deep learning model designed to differentiate these diseases from CXRs. In the initial phase of the model, a Convolutional Neural Network (CNN) is used to extract deep features, including depthwise separable convolution, conventional convolution, and fully connected layers. In the second phase, a Support Vector Machine (SVM) classifier is employed for retraining to achieve higher classification accuracy, maximizing the utilization of deep features from different layers. The third stage involves testing the model. Experimental tests were conducted on a CXR dataset comprising four classes: COVID-19, Pneumonia, Normal, and Tuberculosis. Following comprehensive experimental studies, the proposed model achieved an average accuracy of 99.30%. Moreover, in class-specific results, it reached 100% accuracy for COVID-19 and Tuberculosis, and 98.60% accuracy for Normal and Pneumonia cases, indicating the high effectiveness of the proposed model in classifying COVID-19 and Tuberculosis. Furthermore, in the second part of the experimental studies, the outcomes of the proposed model were compared with existing models, demonstrating superior achievements.

Anahtar Kelimeler

COVID-19, pneumonia, tuberculosis, deep learning, support vector machine

Göğüs Röntgeni Görüntülerinden Akciğer Hastalıklarının Sınıflandırılması için Farklı Derin Öznitelikler ile Beslenen Destek Vektör Makinesi

Öz

En ölümcül akciğer hastalıklarından üçü olan COVID-19, tüberküloz ve zatürre, rutin olarak göğüs röntgeni (GR) taramaları kullanılarak tespit edilmektedir. Son teknolojik gelişmeler, otomatik teşhis için bilgisayar destekli sistemlerde yeni bir çağ başlatmakta ve önemli faydalar sunmaktadır. Bu çalışma, bu hastalıkları GR'lerden ayırt etmek için tasarlanmış üç aşamalı yeni bir derin öğrenme modeli önermektedir. Modelin ilk aşamasında, derinlemesine ayrılabilir evrişim, geleneksel evrişim ve tam bağlı katmanlar dahil olmak üzere derin özellikleri çıkarmak için bir Evrişimsel Sinir Ağı (ESA) kullanılmaktadır. İkinci aşamada, daha yüksek sınıflandırma başarısı elde etmek için Destek Vektör Makineleri (DVM) sınıflandırıcısı kullanılarak tekrar bir eğitim sürecinden geçirilmektedir. Bu sayede farklı katmanlardan alınan derin özelliklerden daha fazla yararlanılmaktadır. Üçüncü aşamada ise model test edilmektedir. Deneysel çalışmalarda dört sınıftan oluşan GR veri kümesi üzerinde testler gerçekleştirilmiştir. Bu veri kümesi COVID-19, Pnömoni, Normal ve Tüberküloz sınıflarını içermektedir. Kapsamlı deneysel çalışmalar sonucunda önerilen model %99,30 ortalama doğruluk sonucuna ulaşmıştır. Diğer yandan sınıf bazlı sonuçlarda COVID-19 ve Tüberküloz için %100, Normal ve Pnömoni vakaları için ise %98,60 doğruluk oranına ulaşmıştır. Bu sonuçlar COVID-19 ve Tüberküloz sınıflandırması için önerilen modelin çok etkili olduğu görülmektedir. Ayrıca deneysel çalışmaların ikinci bölümünde, önerilen model sonuçları, mevcut modeller ile karşılaştırılmış ve üstün başarılar elde ettiği görülmüştür.

Anahtar Kelimeler

COVID19, pnömoni, tüberküloz, derin öğrenme, destek vektör makinesi

Kaynakça

• D. Visca, C. W. M. Ong, S. Tiberi et al., “Tuberculosis and COVID-19 interaction: A review of biological, clinical and public health effects”, Pulmonology, 27(2), 151–165, 2021.
• A. E. Gorbalenya, S. C. Baker, R. S. Baric et al., “The species Severe acute respiratory syndrome-related coronavirus: classifying 2019-nCoV and naming it SARS-CoV-2”, Nature Microbiology, 5(4), 536–544, 2020.
• S. R. Islam, S. P. Maity, A. K. Ray, and M. Mandal, “Deep learning on compressed sensing measurements in pneumonia detection”, International Journal of Imaging Systems and Technology (IMA), 32(1), 41–54, 2022.
• A. H. van’t Hoog, H. K. Meme, K. F. Laserson et al., “Screening strategies for tuberculosis prevalence surveys: The value of chest radiography and symptoms”, PLoS One, 7(7), 1–9, 2012.
• H. Abdul, S. Hashmi, and H. M. Asif, “Early detection of COVID-19”, Frontiers in Medicine, 2020.
• M. Mamalakis, A. J. Swift, B. Vorselaars et al., “DenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and tuberculosis from X-rays”, Computerized Medical Imaging and Graphics, 94(October), 102008, 2021.
• A. A. Soltan, S. Kouchaki, T. Zhu et al., “Artificial intelligence driven assessment of routinely collected healthcare data is an effective screening test for COVID-19 in patients presenting to hospital”, medRxiv, 2020.
• G. J. Williams, P. Macaskill, M. Kerr et al., “Variability and accuracy in interpretation of consolidation on chest radiography for diagnosing pneumonia in children under 5 years of age”, Pediatric Pulmonology, 48(12), 1195–1200, 2013.
• D. Stacey, F. Legare, K. Lewis et al., “Decision aids for people facing health treatment or screening decisions”, Cochrane Database of Systematic Reviews., 2017(4), 14651858, 2017.
• H. Greenspan, R. San José Estépar, W. J. Niessen, E. Siegel, and M. Nielsen, “Position paper on COVID-19 imaging and AI: From the clinical needs and technological challenges to initial AI solutions at the lab and national level towards a new era for AI in healthcare”, Medical Image Analysis, 66(April), 101800, 2020.
• S. Lalmuanawma, J. Hussain, and L. Chhakchhuak, “Applications of machine learning and artificial intelligence for Covid-19 (SARS-CoV-2) pandemic: A review”, Chaos, Solitons and Fractals, 139, 110059, 2020.
• M. S. Ahmed, A. Rahman, F. AlGhamdi et al., “Joint Diagnosis of Pneumonia, COVID-19, and Tuberculosis from Chest X-ray Images: A Deep Learning Approach”, Diagnostics, 13(15), 2023.
• N. N. Qaqos and O. S. Kareem, “COVID-19 Diagnosis from Chest X-ray Images Using Deep Learning Approach”, 3rd International Conference on Advanced Science and Engineering (ICOASE 2020), Duhok, 110–116, 23-24 Aralık, 2020.
• M. Bhandari, T. B. Shahi, B. Siku, and A. Neupane, “Explanatory classification of CXR images into COVID-19, Pneumonia and Tuberculosis using deep learning and XAI”, Computers in Biology and Medicine, 150(September), 106156, 2022.
• C. Sitaula and M. B. Hossain, “Attention-based VGG-16 model for COVID-19 chest X-ray image classification”, Applied Intelligence, 51(5), 2850–2863, 2021.
• A. Bashar, G. Latif, G. Ben Brahim, N. Mohammad, and J. Alghazo, “COVID-19 pneumonia detection using optimized deep learning techniques”, Diagnostics, 11(11), 1–18, 2021.
• P. Szepesi and L. Szilágyi, “Detection of pneumonia using convolutional neural networks and deep learning”, Biocybernetics and Biomedical Engineering, 42(3), 1012–1022, 2022.
• S. K. T. Hwa, M. H. A. Hijazi, A. Bade, R. Yaakob, and M. S. Jeffree, “Ensemble deep learning for tuberculosis detection using chest X-ray and canny edge detected images”, IAES International Journal of Artificial Intelligence, 8(4), 429–435, 2019.
• B. Ibrokhimov and J.-Y. Kang, “Deep Learning Model for COVID-19-Infected Pneumonia Diagnosis Using Chest Radiography Images”, BioMedInformatics, 2(4), 654–670, 2022.
• Internet: JTIPTJ, Chest X-Ray (Pneumonia,Covid-19,Tuberculosis), Kaggle. [Online]. Available: https://www.kaggle.com/datasets/jtiptj/chest-xray-pneumoniacovid19tuberculosis?select=train, 20.09.2023.
• H. Üzen, M. Turkoglu, M. Aslan, and D. Hanbay, “Depth-wise Squeeze and Excitation Block-based Efficient-Unet model for surface defect detection”, The Visual Computer, 2022.
• H. Fırat, M. E. Asker, and D. Hanbay, “Depthwise Separable Convolution Based Residual Network Architecture for Hyperspectral Image Classification”, Gazi Üniversitesi Fen Bilim. Derg. Part C Tasarım ve Teknoloji, 10(2), 242–258, 2022.
• O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation”, in Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015, 234–241, 2015.
• S. Seferbekov, V. Iglovikov, A. Buslaev, and A. Shvets, “Feature pyramid network for multi-class land segmentation”, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18-22 June, 272–275, 2018.
• F. Meng, X. Wang, F. Shao, D. Wang, and X. Hua, “Energy-efficient gabor kernels in neural networks with genetic algorithm training method”, Electronics, 8(1), 2019.
• A. Mahendran and A. Vedaldi, “Visualizing Deep Convolutional Neural Networks Using Natural Pre-images”, International Journal of Computer Vision, 120(3), 233–255, 2016.
• A. Trockman and J. Z. Kolter, “Patches Are All You Need?”, 1–16, 2022.
• A. G. Howard, M. Zhu, B. Chen et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”, 2017.
• M. E. Asker, “Hyperspectral image classification method based on squeeze-and-excitation networks, depthwise separable convolution and multibranch feature fusion”, Earth Science Informatics, 1427–1448, 2023.
• M. Türkoğlu, K. Hanbay, I. S. Sivrikaya, and D. Hanbay, “Derin Evrişimsel Sinir Ağı Kullanılarak Kayısı Hastalıklarının Sınıflandırılması”, BEÜ Fen Bilimleri. Dergisi, 9(1), 334–345, 2020.
• M. F. Özdemir and D. Hanbay, “A Novel Covid-19 Detection System Based on PSO and Hybrid Feature Using Support Vector Machines”, Journal of Computer Science, IDAP-2022, 120–129, 2022.
• Y. Ha, Z. Du, and J. Tian, “Fine-grained interactive attention learning for semi-supervised white blood cell classification”, Biomedical Signal Processing and Control, 75(September), 103611, 2022.
• A. Naseri and A. Rezaei Nasab, “Automatic identification of minerals in thin sections using image processing”, Journal of Ambient Intelligence and Humanized Computing, 2021.
• H. Fırat, “Classification of microscopic peripheral blood cell images using multibranch lightweight CNN-based model”, Neural Computing and Application, 2023.
• C. Liu, Y. Cao, M. Alcantara et al., “TX-CNN: Detecting tuberculosis in chest X-ray images using convolutional neural network”, 2018 25th IEEE International Conference on Image Processing (ICIP), 7-10 Ekim, Atina, 2314–2318, 7-10 Ekim, 2018.
• M. Rahimzadeh and A. Attar, “A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2”, Informatics in Medicine Unlocked, 19, 100360, 2020.
• A. I. Khan, J. L. Shah, and M. M. Bhat, “CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images”, Computer Methods and Programs in Biomedicine, 196, 105581, 2020.
• S. Shastri, I. Kansal, S. Kumar, K. Singh, R. Popli, and V. Mansotra, “CheXImageNet: a novel architecture for accurate classification of Covid-19 with chest x-ray digital images using deep convolutional neural networks”, Health and Technology, 12(1), 193–204, 2022.
• A. H. Al-Timemy, R. N. Khushaba, Z. M. Mosa, and J. Escudero, “An Efficient Mixture of Deep and Machine Learning Models for COVID-19 and Tuberculosis Detection Using X-Ray Images in Resource Limited Settings”, Studies in System, Decision and Control, 358(December), 77–100, 2021.
• S. Asif, Y. Wenhui, H. Jin, and S. Jinhai, “Classification of COVID-19 from Chest X-ray images using Deep Convolutional Neural Network”, 2020 IEEE 6th International Conference on Computer and Communications (ICCC), Chengdu, 426–433, 11-14 Aralık, 2020.
• M. A. H. Metwally, Automatic Detection and Multi-Class Classification of COVID-19, Pneumonia, and Tuberculosis Diseases in Chest X-ray Images Using Deep Learning Techniques, Yüksek Lisans Tezi, University of Victoria, 2022.