A GAN-Augmented And Bio-Inspired Deep Learning Framework For Comprehensive Multi-Disease Detection In Chest Radio-graphs
DOI:
https://doi.org/10.29284/jwqek344Keywords:
Deep Learning · Chest X-ray (CXR) Analysis · Pulmonary Disease Classification · Artificial Intelligence (AI) in Medical Imaging · Automated DiagnosisAbstract
This research presents DNN_AO, a specialized deep learning architecture that leverages the Aquila Optimizer to automate the identification of various pulmonary conditions via chest X-rays. Deviating from traditional single-diagnosis approaches, DNN_AO employs a multi-faceted design to overcome data limitations. Specifically, the framework utilizes Generative Adversarial Networks (GANs) to synthesize data for underrepresented classes, ensuring a balanced dataset. It further optimizes performance by using the bio-inspired Aquila algorithm for hyperparameter tuning, paired with a hybrid feature extraction method that integrates a ResNet50 backbone with custom dense layers. Testing on the ChestX-ray14 dataset—comprising 5,606 images across 14 distinct pathologies—yielded an accuracy of 89%. This result consistently outperforms standard classifiers, including CNNs, Random Forests, and KNN. Notably, the model demonstrates high sensitivity for rare conditions such as hernias, marking a significant advancement toward holistic, multi-disease clinical screening.
References
[1] Ozturk, T., Talo, M., Yildirim, E.A., Baloglu, U.B., Yildirim, O., Acharya, U.R.: Automat-ed detection of COVID-19 cases using deep neural networks with X-ray images. Comput-ers in Biology and Medicine 121, 103792 (2020). https://doi.org/10.1016/j.compbiomed.2020.103792
[2] Alshazly, H., Linse, C., Abdalla, M., Sayed, A., et al.: Explainable COVID-19 detection using chest CT and X-ray images with deep learning. Computers in Biology and Medicine 132, 104336 (2021). https://doi.org/10.1016/j.compbiomed.2021.104336
[3] Chandra, R., Jain, S.: Pneumonia detection on chest X-ray using machine learning paradigm. Materials Today: Proceedings 61, 284–288 (2022). https://doi.org/10.1016/j.matpr.2022.05.223
[4] Sahlol, A.T., Abdeldaim, A.M., Hassanien, A.E.: VDSNet: A deep learning architecture to improve lung disease detection and classification. Multimedia Tools and Applications 81, 19133–19152 (2022). https://doi.org/10.1007/s11042-021-11444-1
[5] Pramanik, S., Bhattacharya, K., Bhattacharyya, R.: COVNet: A deep learning model for COVID-19 detection. Applied Soft Computing 108, 107433 (2021). https://doi.org/10.1016/j.asoc.2021.107433
[6] Khan, M.A., Tariq, U., Zhang, Y.D., Akram, T., Sharif, M.: A study of deep learning-based COVID-19 classification using chest X-ray images. Neural Computing and Applica-tions 33, 13505–13521 (2021). https://doi.org/10.1007/s00521-021-06074-6
[7] Apostolopoulos, I.D., Mpesiana, T.A.: COVID-19: automatic detection from X-ray im-ages using transfer learning with convolutional neural networks. Physical and Engineer-ing Sciences in Medicine 43, 635–640 (2020). https://doi.org/10.1007/s13246-020-00865-4
[8] Khan, A.I., Shah, J.L., Bhat, M.M.: 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). https://doi.org/10.1016/j.cmpb.2020.105581
[9] Hemdan, E.E.D., Shouman, M.A., Karar, M.E.: COVIDX-Net: A framework of deep learning classifiers to diagnose COVID-19 in X-ray images. arXiv preprint arXiv:2003.11055 (2020)
[10] Al-Waisy, A.S., Al-Fahdawi, S., Abdulkareem, K.H., Mohammed, M.A., et al.: COVID-CheXNet: hybrid deep learning framework for identifying COVID-19 virus in chest X-ray images. Soft Computing 25, 11431–11450 (2021). https://doi.org/10.1007/s00500-021-05896-0
[11] El-Shafai, W., Abd El-Samie, F.E., Khairy, A.: Detection of COVID-19 in chest X-ray images using FFNN and transfer learning. Multimedia Tools and Applications 80, 19921–19937 (2021). https://doi.org/10.1007/s11042-021-10589-z
[12] Mahmud, T., Rahman, M., Rahman, M.F.: CovXNet: A multi-dilation convolutional neural network for automatic COVID-19 and other pneumonia detection from chest X-ray images. Applied Sciences 10(11), 3725 (2020). https://doi.org/10.3390/app10113725
[13] Ghoshal, B., Opulencia, M.J.C.: Estimating uncertainty and interpretability in deep learning for coronavirus (COVID-19) detection. arXiv preprint arXiv:2003.10769 (2020)
[14] Mukherjee, H., Ghosh, S., Dhar, K.: COVID-19 detection using EfficientNetV2L with transfer learning and data augmentation. In: Proceedings of the International Confer-ence on Smart Technologies in Sustainable Energy (ICSTSE), pp. 1–5 (2021). https://doi.org/10.1109/ICSTSE52398.2021.9780352
[15] Islam, M.Z., Islam, M.M., Asraf, A.: A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images. Informatics in Medicine Unlocked 20, 100412 (2020). https://doi.org/10.1016/j.imu.2020.100412
[16] Rahman, A., Monira, A.M., Akhter, S.: Transfer learning with CNNs for pneumonia detection in chest X-rays. In: Proceedings of the IEEE International Conference on Com-puter and Communication Engineering (ICCCE), pp. 265–270 (2020). https://doi.org/10.1109/ICCCE50164.2020.9239023
[17] Wang, L., Wong, A.: COVID-Net: A tailored deep convolutional neural network de-sign for detection of COVID-19 cases from chest X-ray images. Scientific Reports 10, 19549 (2020). https://doi.org/10.1038/s41598-020-76550-z
[18] Narin, A., Kaya, C., Pamuk, Z.: Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks. Pattern Analysis and Applications 24, 1207–1220 (2021). https://doi.org/10.1007/s10044-021-00984-y
[19] Tahir, A., Soares, F., do Nascimento, E., Ferreira, A., et al.: COVID-19 detection using convolutional neural networks. Computers in Biology and Medicine 132, 104004 (2021). https://doi.org/10.1016/j.compbiomed.2021.104004
[20] Abbas, A., Abdelsamea, M.M., Gaber, M.M.: Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network. Applied Intelligence 51, 854–864 (2021). https://doi.org/10.1007/s10489-020-01829-7
[21] Panwar, H., Gupta, P.K., Siddiqui, M.K., Morales-Menendez, R., Bhardwaj, P., Singh, V.: A deep learning and grad-CAM based color visualization approach for fast detection of COVID-19 cases using chest X-ray and CT-scan images. Chaos, Solitons & Fractals 140, 110190 (2020). https://doi.org/10.1016/j.chaos.2020.110190
[22] Chowdhury, M.E.H., Rahman, T., Khandakar, A., Mazhar, R., et al.: Can AI help in screening viral and COVID-19 pneumonia? IEEE Access 8, 132665–132676 (2020). https://doi.org/10.1109/ACCESS.2020.3010287
[23] Wang, L., Qiao, Z., Yao, A.: PneuNet: Attention-based deep neural network for pneumonia detection from chest radiographs. Computers in Biology and Medicine 135, 104537 (2021). https://doi.org/10.1016/j.compbiomed.2021.104537
[24] Ucar, F., Korkmaz, D.: COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images. Medical Hypotheses 140, 109761 (2020). https://doi.org/10.1016/j.mehy.2020.109761
[25] Li, L., Qin, L., Xu, Z., Yin, Y., et al.: Artificial intelligence distinguishes COVID-19 from community-acquired pneumonia on chest CT. Radiology 296, E65–E71 (2020). https://doi.org/10.1148/radiol.2020200905
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
