Efficient Classification Model of Pneumonia Infection Based on Deep Transfer Learning and Chest X-Ray Images

  • Muhannad Kassem College of Engineering, Al-Iraqia University, Saba’a Abkar Complex, Baghdad, Iraq
  • Baraa M. Albaker College of Engineering, Al-Iraqia University, Saba’a Abkar Complex, Baghdad, Iraq
الكلمات المفتاحية: Computer-aided diagnosis; Pneumonia, CNN; X-ray, EfficientNetV2B0, Deep learning, Transfer learning


Chest X-ray radiographic (CXR) imaging facilitates the early and precise diagnosis of lung disease. Combining CXR imaging with CNN and other artificial intelligence tools can expedite the diagnosis process. Because there are only a small number of clinical images that have been categorized, the most difficult challenge to overcome before these images can be reliably used in disease progression diagnosis is the automated classification of these images as positive or negative cases. A deep-learning approach was proposed to classify lung diseases on CXR images using a transfer learning technique based on the EfficientNetV2 model as the backbone to boost computer-aided diagnosis (CAD) performance reliability and efficiency. The proposed model is trained and tested on the two classifications, normal and pneumonia, based on images from three publicly available chest X-ray datasets. Using the curated dataset of posteroanterior (PA) chest view radiography images, the implemented model achieves an outstanding performance on the tested data represented by an average accuracy of 99.92%. Consequently, it outperforms the most recent classification techniques de-scribed in the literature.


[1] S. Levine et al., “The Global Impact of Respiratory Disease THIRD EDITION 2 WRITING COMMITTEE.” Accessed: May 30, 2022. [Online]. Available: https://www.firsnet.org/images/publications/FIRS_Master_09202021.pdf
[2] S. H. Wang, V. V. Govindaraj, J. M. Górriz, X. Zhang, and Y. D. Zhang, “Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network,” Information Fusion, vol. 67, pp. 208–229, Mar. 2021, doi: 10.1016/J.INFFUS.2020.10.004.
[3] D. A. Moses, D. Moses MBBS, and F. A. Correspondence Daniel Moses, “Deep learning applied to automatic disease detection using chest X-rays,” Journal of Medical Imaging and Radiation Oncology, vol. 65, no. 5, pp. 498–517, Aug. 2021, doi: 10.1111/1754-9485.13273.
[4] F. Shi et al., “Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19,” IEEE Reviews in Biomedical Engineering, vol. 14, pp. 4–15, 2021, doi: 10.1109/RBME.2020.2987975.
[5] “CT Scan Versus MRI Versus X-Ray: What Type of Imaging Do I Need? | Johns Hopkins Medicine.” https://www.hopkinsmedicine.org/health/treatment-tests-and-therapies/ct-vs-mri-vs-xray (accessed May 30, 2022).
[6] F. Pasa, V. Golkov, F. Pfeiffer, D. Cremers, and D. Pfeiffer, “Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and Visualization,” Scientific Reports 2019 9:1, vol. 9, no. 1, pp. 1–9, Apr. 2019, doi: 10.1038/s41598-019-42557-4.
[7] O. Stephen, M. Sain, U. J. Maduh, and D. U. Jeong, “An Efficient Deep Learning Approach to Pneumonia Classification in Healthcare,” Journal of Healthcare Engineering, vol. 2019, 2019, doi: 10.1155/2019/4180949.
[8] T. W. Kwon et al., “Diagnostic performance of artificial intelligence model for pneumonia from chest radiography,” PLOS ONE, vol. 16, no. 4, p. e0249399, Apr. 2021, doi: 10.1371/JOURNAL.PONE.0249399.
[9] D. M. Ibrahim, N. M. Elshennawy, and A. M. Sarhan, “Deep-chest: Multi-classification deep learning model for diagnosing COVID-19, pneumonia, and lung cancer chest diseases,” Computers in Biology and Medicine, vol. 132, p. 104348, May 2021, doi: 10.1016/J.COMPBIOMED.2021.104348.
[10] M. Hong, B. Rim, H. C. Lee, H. U. Jang, J. Oh, and S. Choi, “Multi-Class Classification of Lung Diseases Using CNN Models,” Applied Sciences 2021, Vol. 11, Page 9289, vol. 11, no. 19, p. 9289, Oct. 2021, doi: 10.3390/APP11199289.
[11] A. T. G. S. FS Yimer, “Multiple Lung Diseases Classification from Chest X- Ray Images using Deep Learning approach,” International Journal of Advanced Trends in Computer Science and Engineering, vol. 10, no. 5, pp. 2936–2946, Oct. 2021, doi: 10.30534/ijatcse/2021/021052021.
[12] K. el Asnaoui and Y. Chawki, “Using X-ray images and deep learning for automated detection of coronavirus disease,” https://doi.org/10.1080/07391102.2020.1767212, pp. 1–12, 2020, doi: 10.1080/07391102.2020.1767212.
[13] C. Sun, Y. Yang, C. Wen, K. Xie, and F. Wen, “Voiceprint Identification for Limited Dataset Using the Deep Migration Hybrid Model Based on Transfer Learning,” Sensors 2018, Vol. 18, Page 2399, vol. 18, no. 7, p. 2399, Jul. 2018, doi: 10.3390/S18072399.
[14] Y. Wang, C. Wang, and H. Zhang, “Ship Classification in High-Resolution SAR Images Using Deep Learning of Small Datasets,” Sensors 2018, Vol. 18, Page 2929, vol. 18, no. 9, p. 2929, Sep. 2018, doi: 10.3390/S18092929.
[15] Y. Zhang, G. Wang, M. Li, and S. Han, “Automated Classification Analysis of Geological Structures Based on Images Data and Deep Learning Model,” Applied Sciences 2018, Vol. 8, Page 2493, vol. 8, no. 12, p. 2493, Dec. 2018, doi: 10.3390/APP8122493.
[16] C. Douarre, R. Schielein, C. Frindel, S. Gerth, and D. Rousseau, “Transfer Learning from Synthetic Data Applied to Soil–Root Segmentation in X-Ray Tomography Images,” Journal of Imaging 2018, Vol. 4, Page 65, vol. 4, no. 5, p. 65, May 2018, doi: 10.3390/JIMAGING4050065.
[17] M. I. Razzak, S. Naz, and A. Zaib, “Deep Learning for Medical Image Processing: Overview, Challenges and the Future BT - Classification in BioApps: Automation of Decision Making,” Springer, vol. 26, pp. 323–350, 2018, Accessed: Jun. 19, 2022. [Online]. Available: https://doi.org/10.1007/978-3-319-65981-7_12
[18] D. Shen, G. Wu, and H. il Suk, “Deep Learning in Medical Image Analysis,” https://doi.org/10.1146/annurev-bioeng-071516-044442, vol. 19, pp. 221–248, Jun. 2017, doi: 10.1146/ANNUREV-BIOENG-071516-044442.
[19] A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature 2017 542:7639, vol. 542, no. 7639, pp. 115–118, Jan. 2017, doi: 10.1038/nature21056.
[20] F. Milletari, N. Navab, and S. A. Ahmadi, “V-Net: Fully convolutional neural networks for volumetric medical image segmentation,” Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016, pp. 565–571, Dec. 2016, doi: 10.1109/3DV.2016.79.
[21] V. Gulshan et al., “Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs,” JAMA, vol. 316, no. 22, pp. 2402–2410, Dec. 2016, doi: 10.1001/JAMA.2016.17216.
[22] U. Avni, H. Greenspan, E. Konen, M. Sharon, and J. Goldberger, “X-ray categorization and retrieval on the organ and pathology level, using patch-based visual words,” IEEE Transactions on Medical Imaging, vol. 30, no. 3, pp. 733–746, Mar. 2011, doi: 10.1109/TMI.2010.2095026.
[23] S. Jaeger et al., “Automatic tuberculosis screening using chest radiographs,” IEEE Transactions on Medical Imaging, vol. 33, no. 2, pp. 233–245, Feb. 2014, doi: 10.1109/TMI.2013.2284099.
[24] J. Melendez et al., “A novel multiple-instance learning-based approach to computer-aided detection of tuberculosis on chest X-rays,” IEEE Transactions on Medical Imaging, vol. 34, no. 1, pp. 179–192, Jan. 2015, doi: 10.1109/TMI.2014.2350539.
[25] S. Rajaraman, S. Candemir, I. Kim, G. Thoma, and S. Antani, “Visualization and Interpretation of Convolutional Neural Network Predictions in Detecting Pneumonia in Pediatric Chest Radiographs,” Applied Sciences 2018, Vol. 8, Page 1715, vol. 8, no. 10, p. 1715, Sep. 2018, doi: 10.3390/APP8101715.
[26] I. Sirazitdinov, M. Kholiavchenko, T. Mustafaev, Y. Yixuan, R. Kuleev, and B. Ibragimov, “Deep neural network ensemble for pneumonia localization from a large-scale chest x-ray database,” Computers & Electrical Engineering, vol. 78, pp. 388–399, Sep. 2019, doi: 10.1016/J.COMPELECENG.2019.08.004.
[27] P. Rajpurkar et al., “Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists,” PLOS Medicine, vol. 15, no. 11, p. e1002686, Nov. 2018, doi: 10.1371/JOURNAL.PMED.1002686.
[28] T. K. K. Ho and J. Gwak, “Multiple Feature Integration for Classification of Thoracic Disease in Chest Radiography,” Applied Sciences 2019, Vol. 9, Page 4130, vol. 9, no. 19, p. 4130, Oct. 2019, doi: 10.3390/APP9194130.
[29] E. Ayan and H. M. Ünver, “Diagnosis of pneumonia from chest X-ray images using deep learning,” 2019 Scientific Meeting on Electrical-Electronics and Biomedical Engineering and Computer Science, EBBT 2019, Apr. 2019, doi: 10.1109/EBBT.2019.8741582.
[30] T. Rahman et al., “Transfer Learning with Deep Convolutional Neural Network (CNN) for Pneumonia Detection Using Chest X-ray,” Applied Sciences 2020, Vol. 10, Page 3233, vol. 10, no. 9, p. 3233, May 2020, doi: 10.3390/APP10093233.
[31] A. K. Jaiswal, P. Tiwari, S. Kumar, D. Gupta, A. Khanna, and J. J. P. C. Rodrigues, “Identifying pneumonia in chest X-rays: A deep learning approach,” Measurement, vol. 145, pp. 511–518, Oct. 2019, doi: 10.1016/J.MEASUREMENT.2019.05.076.
[32] V. Chouhan et al., “A Novel Transfer Learning Based Approach for Pneumonia Detection in Chest X-ray Images,” Applied Sciences 2020, Vol. 10, Page 559, vol. 10, no. 2, p. 559, Jan. 2020, doi: 10.3390/APP10020559.
[33] R. Karthik, R. Menaka, and M. Hariharan, “Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN,” Applied Soft Computing, vol. 99, p. 106744, Feb. 2021, doi: 10.1016/J.ASOC.2020.106744.
[34] E. E.-D. Hemdan, M. A. Shouman, and M. E. Karar, “COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images,” Mar. 2020, Accessed: Feb. 08, 2022. [Online]. Available: https://arxiv.org/abs/2003.11055v1
[35] B. Antin, J. Kravitz, and E. Martayan, “Detecting Pneumonia in Chest X-Rays with Supervised Learning.”
[36] P. K. Sethy and S. K. Behera, “Detection of Coronavirus Disease (COVID-19) Based on Deep Features,” Mar. 2020, doi: 10.20944/PREPRINTS202003.0300.V1.
[37] K. Zrar et al., “Diagnosing COVID-19 pneumonia from x-ray and CT images using deep learning and transfer learning algorithms,” https://doi.org/10.1117/12.2588672, vol. 11734, no. 12, pp. 99–110, Apr. 2021, doi: 10.1117/12.2588672.
[38] R. Kundu, P. K. Singh, M. Ferrara, A. Ahmadian, and R. Sarkar, “ET-NET: an ensemble of transfer learning models for prediction of COVID-19 infection through chest CT-scan images,” Multimedia Tools and Applications, vol. 81, no. 1, pp. 31–50, Jan. 2022, doi: 10.1007/S11042-021-11319-8/TABLES/9.
[39] E. H. Houssein, Z. Abohashima, M. Elhoseny, and W. M. Mohamed, “Hybrid quantum-classical convolutional neural network model for COVID-19 prediction using chest X-ray images,” Journal of Computational Design and Engineering, vol. 9, no. 2, pp. 343–363, Apr. 2022, doi: 10.1093/JCDE/QWAC003.
[40] U. Sait et al., “Curated Dataset for COVID-19 Posterior-Anterior Chest Radiography Images (X-Rays).,” vol. 3, 2021, doi: 10.17632/9XKHGTS2S6.3.
[41] “NIH Chest X-ray dataset | Cloud Healthcare API | Google Cloud.” https://cloud.google.com/healthcare-api/docs/resources/public-datasets/nih-chest (accessed May 30, 2022).
[42] “TBX 11 | Kaggle.” https://www.kaggle.com/datasets/usmanshams/tbx-11 (accessed May 30, 2022).
[43] “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.” http://proceedings.mlr.press/v97/tan19a.html (accessed May 30, 2022).
[44] “EfficientNetV2: Smaller Models and Faster Training.” http://proceedings.mlr.press/v139/tan21a.html (accessed May 30, 2022).
[45] “Transfer learning and fine-tuning | TensorFlow Core.” https://www.tensorflow.org/guide/keras/transfer_learning (accessed May 30, 2022).
[46] “Lookahead Optimizer: k steps forward, 1 step back.” https://proceedings.neurips.cc/paper/2019/hash/90fd4f88f588ae64038134f1eeaa023f-Abstract.html (accessed May 30, 2022).
[47] L. Liu et al., “On the Variance of the Adaptive Learning Rate and Beyond,” Aug. 2019, doi: 10.48550/arxiv.1908.03265.