Tüberküloz Hastalığının Tespiti için Derin Öğrenme Yöntemlerinin Karşılaştırılması

Yıl 2024, Cilt: 7 Sayı: 4, 1635 - 1665, 16.09.2024

Çiğdem Bakır , Mehmet Babalık

https://doi.org/10.47495/okufbed.1342465

Öz

Yapay zeka, sağlık alanında kanser gibi birçok hastalığın teşhis edilmesinde, doktorlar tarafından yapılan tetkiklerde, cihazlarla gerçekleştirilen tanı ve tedavilerde sıklıkla kullanılmaktadır. Çünkü doktorlar herhangi bir hastalığın doğru tanı ve doğru teşhisini manuel olarak ortaya koymak gerek zaman gerekse maliyet açısından oldukça zordur. Bu hastalıklardan en önemlisi olan tüberküloz (verem), dünyanın birçok yerinde sonu ölümle sonuçlanan bulaşıcı ve tehlikeli hastalıklardan biridir. Tüberküloz için uzman radyologlar göğüs röntgenlerine bakarak teşhis koyarlar. Fakat radyologlar bu teşhisi koyarken kimi zaman çok sayıda göğüs röntgeni inceledikleri için yanlış tanı ve teşhis koyabilmektedir. Bu durumda manuel bir teşhis yerine daha hızlı ve daha doğru kararlar verebilen bilgisayar destekli analizler gerekmektedir. Bu çalışmanın amacı yapay zekâ yöntemleri kullanılarak akciğer röntgen verilerinden tüberkülozlu ve sağlıklı görüntülerin otonom olarak tespiti ve sınıflandırılmasını yapacak bir model oluşturmaktır. Bu çalışmada tüberküloz hastalığının bilgisayar destekli analiz ve tespitini gerçekleştirmek amacıyla yapay zekanın bir alt kümesi olan derin öğrenme metotlarından Yapay Sinir Ağları (ANN), Evrişimsel Sinir Ağları (CNN) ve hibrit model (VGG19+CNN) kullanılmıştır. Önerilen modelinin ilk aşamasında akciğer röntgen filmlerinden elde edilen 1000 görüntü ön işlemeden geçirilerek, hastalıklı ve sağlıklı olarak etiketlenmiştir. Görüntülerin doğru, hızlı ve minimum maliyetle teşhisi için farklı ve yeni ağ yapısı oluşturularak verilerdeki önemli öznitelikler belirlenmiştir. Ayrıca önerilen CNN ve hibrit model ile literatürde birçok alanda yaygın bir şekilde kullanılan Yapay Sinir Ağları (Artificial Neural Network –ANN) modeli doğruluk, duyarlılık, kesinlik ve F1-Skor gibi farklı değerlendirme metrikleri kullanılarak detaylı bir şekilde karşılaştırılmıştır. Kullanılan her model için de performans analizleri gerçekleştirilmiştir. Bu çalışmada CNN ve ANN modelinin sınıflandırma başarısı sırasıyla %98,91 ve %90,41 olarak bulunmuştur. Önerilen CNN modeli ANN modeline göre tüberküloz hastalığının doğru teşhis ve sınıflandırılmasında daha başarılı sonuçlar vermiştir. Ayrıca tüberküloz görüntü verilerine önerilen VGG19+CNN model uygulanmıştır. Bu model özellik çıkarımı ve sınıflandırma aşamalarından oluşur. Hibrit model eğitim ve test görüntülerinde sırasıyla %100 ve %99.66 başarı vermiştir.

Anahtar Kelimeler

Derin Öğrenme, Evrişimsel Sinir Ağı, Hibrit Model, Tüberküloz, VGG19, Yapay Sinir Ağları, Yapay Zeka

Comparison of Deep Learning Methods for Detection of Tuberculosis Disease

Öz

Artificial intelligence is frequently used in the diagnosis of many diseases such as cancer in the field of health, in the examinations made by doctors, in the diagnosis and treatment performed with devices. Because it is very difficult for doctors to manually reveal the correct diagnosis and correct diagnosis of any disease in terms of both time and cost. Tuberculosis, the most important of these diseases, is one of the contagious and dangerous diseases that result in death in many parts of the world. For tuberculosis, specialist radiologists diagnose it by looking at chest X-rays. However, radiologists can sometimes misdiagnose and diagnose because they examine a large number of chest X-rays while making this diagnosis. In this case, computer-assisted analyzes that can make faster and more accurate decisions are required instead of a manual diagnosis. The aim of this study is to create a model that will autonomously detect and classify tuberculosis and healthy images from lung x-ray data using artificial intelligence methods. In this study, Artificial Neural Network (ANN), Convoluational Neural Network (CNN) and hybrid model (VGG19+CNN), which are deep learning methods, which are a subset of artificial intelligence, were used to perform computer-aided analysis and detection of tuberculosis disease. In the first stage of the proposed model, 1000 images obtained from lung x-ray films were preprocessed and labeled as diseased and healthy. In order to diagnose images accurately, quickly and with minimum cost, a different and new network structure was created and important features in the data were determined. In addition, the proposed CNN and hybrid model and the ANN model, which is widely used in many areas in the literature, were compared in detail using different evaluation metrics such as accuracy, sensitivity, precision and F1-Score. Performance analyzes were also performed for each model used. In this study, the classification success of the CNN and ANN model was found to be 98.91% and 90.41%, respectively. The proposed CNN model gave more successful results in the correct diagnosis and classification of tuberculosis disease compared to the ANN model. In addition, the suggested VGG19+CNN model was applied to the tuberculosis image data. This model consists of feature extraction and classification stages. The hybrid model gave 100% and 99.66% success in training and test images, respectively.

Anahtar Kelimeler

Deep Learning, Convolutional Neural Network, Hibrit Model, Tuberculosis, VGG19, Artificial Neural Networks, Artificial Intelligence

Kaynakça

• Abubakar MZ., Mustafa K., Sani, KJ. Automated tuberculosis classification with chest x-rays using deep neural networks-case study: Nigerian Public Health. Turkish Journal of Science and Technology 2024; 19(1): 55-64.
• Al-Shayea QK. Artificial neural networks in medical diagnosis. International Journal of Computer Science Issues 2011; 8(2): 150-154.
• Ammar LB., Gasmi K., Ltaifa IB. ViT-TB: Ensemble learning based ViT Model for tuberculosis recognition. Cybernetics and Systems 2022; 1-20.
• Angeli C. Diagnostic expert systems: From expert’s knowledge to real-time systems. Advanced knowledge-based systems: Model, applications & Research 2010; 1: 50-73.
• Asakawa T., Tsuneda R., Shimizu K., Aono M. Caverns detection and caverns report in tuberculosis: lesion detection based on image using YOLO-V3 and median based multi-label multi-class classification using SRGAN. In CLEF2022 Working Notes CEUR Workshop Proceedings 2022, Bologna, Italy.
• Ayas S., Ekinci M. Random forest-based tuberculosis bacteria classification in images of ZN-stained sputum smear samples. Signal, Image and Video Processing 2014; 8: 49-61.
• Bisht R., Mittal K., Prasad G. Evaluation of CNN models for accurate classification of COVID-19, pneumonia, tuberculosis in chest X-ray Images. In 2023 3rd Asian Conference on Innovation in Technology (ASIANCON) 2023, IEEE.
• Bozkurt F. Skin lesion classification on dermatoscopic images using effective data augmentation and pre-trained deep learning approach. Multimedia Tools and Applications 2023; 2(12): 18985-19003.
• Bozkurt F. Derin öğrenme tekniklerini kullanarak akciğer X-ray görüntülerinden COVID-19 tespiti. Avrupa Bilim ve Teknoloji Dergisi 2021; 24: 149-156.
• Bozkurt F. A deep and handcrafted features‐based framework for diagnosis of COVID‐19 from chest x‐ray images. Concurrency and Computation: Practice and Experience 2022; 34(5): 1-19.
• Bozkurt F., Yağanoğlu M. Derin evrişimli sinir ağları kullanarak akciğer X-Ray görüntülerinden COVID-19 tespiti. Veri Bilimi 2021; 4(2): 1-8.
• Breve, FA.. COVID-19 detection on Chest X-ray images: A comparison of CNN architectures and ensembles. Expert systems with applications 2022; 204: 117549.
• Cao K., Zhang J., Huang M., Deng T. X-ray classification of tuberculosis based on convolutional networks. In 2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) 2021, IEEE.
• Elveren E., Yumuşak N. Tuberculosis disease diagnosis using artificial neural network trained with genetic algorithm. Journal of Medical Systems 2011; 35: 329-332.
• Er O., Tanrikulu AÇ., Temurtas F. Tuberculosis disease diagnosis using artificial neural networks. Journal of Medical Systems 2010; 34(3): 299-302.
• Fatihah HA., Kurniawan I. Prediction of tuberculosis on HIV patients based on gene expression data using grey wolf optimization-support vector machine. In 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS) 2024, IEEE.
• Gasmi K., Kharrat A., Ammar LB., Ltaifa IB., Krichen M., Hrizi O. Classification of MRI brain tumors based on registration preprocessing and deep belief networks. AIMS Mathematics 2024; 9(2): 4604-4631.
• Gichuhi HW. A machine learning model to explore individual risk factors for tuberculosis treatment refill non-adherence in Mukono District. Makerere Üniversitesi, Yayınlanmış Doktora Tezi 2023.
• Gruson D. Data science, artificial intelligence, and machine learning: opportunities for laboratory medicine and the value of positive regulation. Clinical Biochemistry 2019; 69: 1-7.
• Hafeez U., Umer M., Hameed A., Mustafa H., Sohaib A., Nappi M., Madni HA. A CNN based coronavirus disease prediction system for chest X-rays. Journal of Ambient Intelligence and Humanized Computing 2023; 14(10): 13179-13193.
• Hrizi D., Tbarki K., Attia M., Elasmi S. Lung cancer detection and nodule type classification using image processing and machine learning. In 2023 International Wireless Communications and Mobile Computing (IWCMC) 2023, IEEE.
• Hrizi D., Tbarki K., Elasmi S. Lung cancer detection and classification using CNN and image segmentation. In 2023 IEEE Tenth International Conference on Communications and Networking (ComNet) 2023, IEEE.
• Hrizi O., Gasmi K., Ltaifa I., Alshammari H., Karamti H., Krichen M., Mahmood MA. Tuberculosis disease diagnosis based on an optimized machine learning model. Journal of Healthcare Engineering 2022; 2022:1-13.
• Hrizi O., Gasmi K., Ltaifa IB., Alshammari H., Karamti H., Krichen M., Mahmood MA. Tuberculosis disease diagnosis based on an optimized machine learning model. Journal of Healthcare Engineering, 2022.
• Iqbal A., Usman M. An efficient deep learning-based framework for tuberculosis detection using chest X-ray images. Tuberculosis 2022; 136, 102234.
• Iqbal A., Usman M., Ahmed Z. Tuberculosis chest X-ray detection using CNN-based hybrid segmentation and classification approach. Biomedical Signal Processing and Control 2023; 84: 104667.
• Iqbal A., Usman M., Ahmed Z.Tuberculosis chest X-ray detection using CNN-based hybrid segmentation and classification approach. Biomedical Signal Processing and Control 2023; 84, 104667.
• Kant S., Srivastava MM. Towards automated tuberculosis detection using deep learning. In 2018 IEEE Symposium Series on Computational Intelligence (SSCI) 18- 21 Kasım 2018 Bangalore, Hindistan.
• Karaddi SH., Sharma, LD. Automated multi-class classification of lung diseases from CXR-images using pre-trained convolutional neural networks. Expert Systems with Applications 2023; 211: 118650.
• Khatri A., Jain R., Vashista H., Mittal N., Ranjan P. Pneumonia ıdentification in chest x-ray ımages using EMD. In Internet of Things—Applications and Future; Springer Science and Business Media LLC 2020, Singapore.
• Lakhani P., Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 2017; 284(2): 574-582.
• Lestari V., Mawengkang H., Situmorang Z. Artificial Neural Network Backpropagation Method to Predict Tuberculosis Cases. Sinkron jurnal dan penelitian teknik informatika 2023; 8(1): 35-47.
• Li Z., Xu X., Cao X., Liu W., Zhang Y., Chen D., Dai H. Integrated CNN and federated learning for COVID-19 detection on chest X-ray images. IEEE/ACM Transactions on Computational Biology and Bioinformatics 2022.
• Liu C., Cao Y., Alcantara M., Liu B., Brunette M., Peinado J., Curioso W. TX-CNN: Detecting tuberculosis in chest X-ray images using convolutional neural network. In 2017 IEEE international conference on image processing (ICIP) 2017, IEEE.
• Lubis AR., Prayudani S., Fatmi Y.,Lase YY. Detection of HOG features on tuberculosis X-Ray results using SVM and KNN. In 2021 2nd International Conference on Innovative and Creative Information Technology (ICITech) 1-3 September 2021.
• Malik H., Anees T., Din M., Naeem A. CDC_Net: Multi-classification convolutional neural network model for detection of COVID-19, pneumothorax, pneumonia, lung Cancer, and tuberculosis using chest X-rays. Multimedia Tools and Applications 2023; 82(9): 13855-13880.
• Nafisah SI., Muhammad G. Tuberculosis detection in chest radiograph using convolutional neural network architecture and explainable artificial intelligence. Neural Computing and Applications 2022; 1-21.
• Rahman T., Akinbi A., Chowdhury ME., Rashid TA., Şengür A., Khandakar A., Ismael A. COV-ECGNET: COVID-19 detection using ECG trace images with deep convolutional neural network. Health Information Science and Systems 2022; 10(1): 1-10.
• Rahman T., Khandakar A., Kadir MA., Islam KR., Islam KF., Mazhar R. Reliable tuberculosis detection using chest X-ray with deep learning, segmentation and visualization. IEEE Access 2020; 8: 191586-191601.
• Shakya T., Jeyavathana RB., Kumar PK. Improved accuracy in automatic detection of tuberculosis disease from lung ct images using support vector machine classifier over K-nearest neighbours classifier. In 2022 International Conference on Cyber Resilience (ICCR) 1-3 October 2022.
• Singh M., Pujar GV., Kumar SA., Bhagyalalitha M., Akshatha HS., Abuhaija B., Gandomi, AH. Evolution of machine learning in tuberculosis diagnosis: a review of deep learning-based medical applications. Electronics 2022; 11(17): 2634.
• Sun M., Song Z., Jiang X., Pan J., Pang Y. Learning pooling for convolutional neural network. Neurocomputing 2017; 224: 96-104.
• Pannu A. Artificial intelligence and its application in different areas. Artificial Intelligence 2015; 4(10): 79-84. Pardue H., Schnipelsky P. Use of artificial intelligence in analytical systems for the clinical laboratory. Clinica Chimica Açta 1994; 231(2): S1-S34.
• Venkataramana L., Prasad DV., Saraswathi S., Mithumary CM., Karthikeyan R., Monika N. Classification of COVID-19 from tuberculosis and pneumonia using deep learning techniques. Medical & Biological Engineering & Computing 2022; 60(9): 2681-2691.
• Woolever DR. The impact of a patient safety program on medical error reporting. Journal of Medical Regulation 2005; 91(3): 16-21.