A Deep Neural Network to Distinguish COVID-19 from other Chest Diseases Using X-ray Images

Author(s): Saleh Albahli*

Journal Name: Current Medical Imaging
Formerly: Current Medical Imaging Reviews

Volume 17 , Issue 1 , 2021


Become EABM
Become Reviewer
Call for Editor

Graphical Abstract:


Abstract:

Background: Scanning a patient’s lungs to detect Coronavirus 2019 (COVID-19) may lead to similar imaging of other chest diseases. Thus, a multidisciplinary approach is strongly required to confirm the diagnosis. There are only a few works targeted at pathological x-ray images. Most of the works only target single disease detection which is not good enough. Some works have been provided for all classes. However, the results suffer due to lack of data for rare classes and data unbalancing problem.

Methods: Due to the rise in COVID-19 cases, medical facilities in many countries are overwhelmed and there is a need for an intelligent system to detect it. Few works have been done regarding the detection of the coronavirus but there are many cases where it can be misclassified as some techniques are not efficient and can only identify specific diseases. This work is a deep learning- based model to distinguish COVID-19 cases from other chest diseases.

Results: A Deep Neural Network model provides a significant contribution in terms of detecting COVID-19 and provides an effective analysis of chest-related diseases taking into account both age and gender. Our model achieves 87% accuracy in terms of GAN-based synthetic data and presents four different types of deep learning-based models that provide comparable results to other state-of-the-art techniques.

Conclusion: The healthcare industry may face unfavorable consequences if the gap in the identification of all types of pneumonia is not filled with effective automation.

Keywords: Deep learning, coronavirus, X-ray, chest diseases, resNet-152, inception-V3.

[2]
Rajpurkar P, Irvin J, Zhu K, Che XNet, et al. Radiologist-level Pneumonia detection on chest X-rays with deep learning. 2017. arxiv: 1711.052.25
[3]
Hoyler M, Finlayson SRG, McClain CD, Meara JG, Hagander L. Shortage of doctors, shortage of data: a review of the global surgery, obstetrics, and anesthesia workforce literature. World J Surg 2014; 38(2): 269-80.
[http://dx.doi.org/10.1007/s00268-013-2324-y] [PMID: 24218153]
[4]
Albahli S. A deep ensemble learning method for effort-aware just-in-time defect prediction. Future Internet 2019; 11(12): 246.
[http://dx.doi.org/10.3390/fi11120246]
[5]
Yang JX, Zhang M, Liu ZH, Ba L, Gan JX, Xu SW. Detection of lung at electasis/consolidation by ultrasound in multiple trauma patients with mechanical ventilation. Crit Ultrasound J 2009; 1(1): 13-6.
[http://dx.doi.org/10.1007/s13089-009-0003-x]
[6]
Gompelmann D, Eberhardt R, Slebos DJ, et al. Comparison between char- tis® pulmonary assessment system detection of collateral ventilation vs corelabct fissure analysis in predicting atelectasis in emphysema patients treated with endo- bronchial valves 2011.
[7]
Bar Y, Diamant I, Wolf L, Lieberman S, Konen E, Greenspan H. Chest pathology de- tection using deep learning with non-medical training 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI). IEEE. 2015; pp. 294-7.
[8]
Pietka E, Huang HK. Orientation correction for chest images. J Digit Imaging 1992; 5(3): 185-9.
[http://dx.doi.org/10.1007/BF03167768] [PMID: 1520745]
[9]
Boone JM, Seshagiri S, Steiner RM. Recognition of chest radiograph orientation for picture archiving and communications systems display using neural networks. J Digit Imaging 1992; 5(3): 190-3.
[http://dx.doi.org/10.1007/BF03167769] [PMID: 1520746]
[10]
Arimura H, Katsuragawa S, Li Q, Ishida T, Doi K. Development of a computerized method for identifying the posteroanterior and lateral views of chest radiographs by use of a template matching technique. Med Phys 2002; 29(7): 1556-61.
[http://dx.doi.org/10.1118/1.1487426] [PMID: 12148738]
[11]
Lehmann TM, Güld O, Keysers D, Schubert H, Kohnen M, Wein BB. Determining the view of chest radiographs. J Digit Imaging 2003; 16(3): 280-91.
[http://dx.doi.org/10.1007/s10278-003-1655-x] [PMID: 14669063]
[12]
Kao EF, Lee C, Jaw TS, Hsu JS, Liu GC. Projection profile analysis for identifying different views of chest radiographs. Acad Radiol 2006; 13(4): 518-25.
[http://dx.doi.org/10.1016/j.acra.2006.01.009] [PMID: 16554233]
[13]
Kao EF, Lin WC, Hsu JS, Chou MC, Jaw TS, Liu GC. A computerized method for automated identification of erect posteroanterior and supine anteroposterior chest radiographs. Phys Med Biol 2011; 56(24): 7737-53.
[http://dx.doi.org/10.1088/0031-9155/56/24/004] [PMID: 22094308]
[14]
Luo H, Hao W, Foos DH, Cornelius CW. Automatic image hanging protocol for chest radiographs in PACS. IEEE Trans Inf Technol Biomed 2006; 10(2): 302-11.
[http://dx.doi.org/10.1109/TITB.2005.859872] [PMID: 16617619]
[15]
Li L, Qin L, Xu Z, et al. Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT. Radiology 2020; 200905.
[http://dx.doi.org/10.1148/radiol.2020200905] [PMID: 32191588]
[16]
Li L, Qin L, Xu Z, et al. Radiology Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT lin 2020. 200905.
[17]
Shan F, Geo Y, Wang J. Lung Infection Quantificationof COVID-19 in CT Images with Deep Learning Author The journal of the Japan Societyfor Bronchology 2020. arxiv: 2003. 04665.
[18]
Song Y, Zheng S, Li L, et al. Deep learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) with CT images Rxiv 2020. preprint.
[19]
Xu X, Jiang X, Ma C, et al. Deep Learning System to Screen Coronavirus Disease Engineering 2020; 6(10): 1122-29.
[20]
Yan L, Zhang HT, Goncalves J, et al. A machine learning-based model for survival prediction in patients with severe COVID-19 infection. 2020. preprint.
[21]
Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. Chestx-ray8: Hospital-scale chest x-ray database and bench- marks on weakly-supervised classification and localization of common thorax diseases. Proceedings of the IEEE conference on computer vision and pattern recognition. 2097-106.
[http://dx.doi.org/10.1109/CVPR.2017.369]
[22]
Albahli S. Type 2 Machine Learning: An Effective Hybrid Prediction Model for Early Type 2 Diabetes Detection. J Med Imaging Health Inform 2020; 10(5): 1069-75.
[http://dx.doi.org/10.1166/jmihi.2020.3000]
[23]
Digital Pathology Classification Challenge. Available at.. https://www.kaggle.com/c/digitalpathology/data
[24]
Cohen JP, Morrison P, Dao L. COVID-19 image data collection arXiv:200311597 2020.
[25]
Bao J, Chen D, Wen F, Li H, Hua G. Cvae-gan: fine-grained image generation through asymmetric training. Proceedings of the IEEE International Conference on Computer Vision. 2745-54.
[http://dx.doi.org/10.1109/ICCV.2017.299]
[26]
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. Proceedings of the IEEE conference on computer vision and pattern recognition. 2818-26.
[http://dx.doi.org/10.1109/CVPR.2016.308]
[27]
Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition. 1-9.
[28]
Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift arXiv preprint arXiv:150203167 2015.
[29]
Zagoruyko S, Komodakis N. Wide residual networks arXiv preprint arXiv:160507146 2016.


Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 17
ISSUE: 1
Year: 2021
Published on: 04 June, 2020
Page: [109 - 119]
Pages: 11
DOI: 10.2174/1573405616666200604163954
Price: $65

Article Metrics

PDF: 28
HTML: 3