A Two-Headed Deep Learning Framework for Predicting Severity of COVID-19 Disease

Year 2021, Volume: 1 Issue: 2, 19 - 28, 30.09.2021

Çoşku Öksüz Oğuzhan Urhan Mehmet Kemal Güllü

Abstract

Introduction-Objectives: The high contagiousness of the SARS-COV-2 virus has resulted in many people being infected worldwide. In many countries, the capacity of intensive care units has been insufficient and has become unable to accept new patients. Imaging-based non-invasive methods developed as an alternative to the RT-PCR technique to control the spread of the virus during the pandemic process generally focus on the presence or absence of the disease. However, these methods do not provide information about how severe the disease is and how it progresses. Therefore, in this study, a deep learning-based estimation framework with low computational load is proposed to predict severity scores using chest radiographs.

Materials-Methods: The pre-trained ImageNet models are used as feature extraction networks to extract generic features. A two-headed estimation subnetwork each with the same number of layers is created to learn taskspecific features. Eventually, an end-to-end trainable lightweight deep model is created by connecting the estimation subnetwork to the feature extraction
network.

Results: The proposed model is evaluated on a publicly available Cohen’s covid-chestxray-data set. The best cross-validation performance in terms of RMSE, MAE, and R2 in the prediction of lung involvement and opacity is obtained as 1.39/0.98, 1.1/0.81, 0.65/0.66, respectively.

Conclusions: Although the model has been trained with limited data, promising results are achieved with an end-to-end framework for estimating the severity of the COVID-19 disease.

Keywords

lung involvement, opacity, deep learning, feature extraction, X-Ray

References

• [1] ‘WHO Coronavirus (COVID-19) Dashboard’. https://covid19.who.int (accessed Apr. 03, 2021).
• [2] K. R. Peck, ‘Early diagnosis and rapid isolation: response to COVID-19 outbreak in Korea’, Clin. Microbiol. Infect., vol. 26, no. 7, pp. 805–807, Jul. 2020, doi: 10.1016/j.cmi.2020.04.025.
• [3] D. Cozzi et al., ‘Chest X-ray in new Coronavirus Disease 2019 (COVID-19) infection: findings and correlation with clinical outcome’, Radiol. Med. (Torino), vol. 125, no. 8, pp. 730–737, Aug. 2020, doi: 10.1007/s11547-020-01232-9.
• [4] A. M. Ismael and A. Şengür, ‘Deep learning approaches for COVID-19 detection based on chest X-ray images’, Expert Syst. Appl., vol. 164, p. 114054, Feb. 2021, doi: 10.1016/j.eswa.2020.114054. [5] K. Shankar and E. Perumal, ‘A novel hand-crafted with deep learning features based fusion model for COVID-19 diagnosis and classification using chest X-ray images’, Complex Intell. Syst., Nov. 2020, doi:10.1007/s40747-020-00216-6.
• [6] Ş. Öztürk, U. Özkaya, and M. Barstuğan, ‘Classification of Coronavirus (COVID-19) from X-ray and CT images using shrunken features’, Int. J. Imaging Syst. Technol., vol. 31, no. 1, pp. 5–15, 2021, doi: https://doi.org/10.1002/ima.22469.
• [7] C. Öksüz, O. Urhan, and M. K. Güllü, ‘Ensemble-CVDNet: A Deep Learning based End-to-End Classification Framework for COVID-19 Detection using Ensembles of Networks’, ArXiv201209132 Eess, Dec. 2020, Accessed: Dec. 20, 2020. [Online]. Available: http://arxiv.org/abs/2012.09132.
• [8] L. Wang, Z. Q. Lin, and A. Wong, ‘COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images’, Sci. Rep., vol. 10, no. 1, Art. no. 1, Nov. 2020, doi: 10.1038/s41598-020-76550-z.
• [9] M. K. Hasan, M. T. Jawad, K. N. I. Hasan, S. B. Partha, and M. M. A. Masba, ‘COVID-19 identification from volumetric chest CT scans using a progressively resized 3D-CNN incorporating segmentation, augmentation, and class-rebalancing’, ArXiv210206169 Cs Eess, Feb. 2021, Accessed: Apr. 04, 2021. [Online]. Available: http://arxiv.org/abs/2102.06169.
• [10] C. Zhang et al., ‘A Novel Scoring System for Prediction of Disease Severity in COVID-19’, Front. Cell. Infect. Microbiol., vol. 10, p. 318, Jun. 2020, doi: 10.3389/fcimb.2020.00318.
• [11] Z. Tang et al., ‘Severity assessment of COVID-19 using CT image features and laboratory indices’, Phys. Med. Biol., vol. 66, no. 3, p. 035015, Jan. 2021, doi: 10.1088/1361-6560/abbf9e.
• [12] C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, ‘A Survey on Deep Transfer Learning’, in Artificial Neural Networks and Machine Learning – ICANN 2018, Cham, 2018, pp. 270–279, doi: 10.1007/978-3-030-01424-7_27.
• [13] O. Russakovsky et al., ‘ImageNet Large Scale Visual Recognition Challenge’, ArXiv14090575 Cs, Jan. 2015, Accessed: Nov. 17, 2020. [Online]. Available: http://arxiv.org/abs/1409.0575.
• [14] K. He, X. Zhang, S. Ren, and J. Sun, ‘Deep Residual Learning for Image Recognition’, 2016, pp. 770–778, Accessed: Mar. 26, 2021. [Online]. Available: https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html.
• [15] F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, ‘SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size’, ArXiv160207360 Cs, Nov. 2016, Accessed: Nov. 17, 2020. [Online]. Available: http://arxiv.org/abs/1602.07360.
• [16] C. Szegedy et al., ‘Going Deeper With Convolutions’, 2015, pp. 1–9, Accessed: Mar. 26, 2021. [Online]. Available: https://www.cvfoundation.org/openaccess/content_cvpr_2015/html/Szegedy_Going_Deeper_With_2015_CVPR_paper.html.
• [17] X. Zhang, X. Zhou, M. Lin, and J. Sun, ‘ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices’, ArXiv170701083 Cs, Dec. 2017, Accessed: Nov. 17, 2020. [Online]. Available: http://arxiv.org/abs/1707.01083.
• [18] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, ‘MobileNetV2: Inverted Residuals and Linear Bottlenecks’, ArXiv180104381 Cs, Mar. 2019, Accessed: Nov. 18, 2020. [Online]. Available: http://arxiv.org/abs/1801.04381.
• [19] M. Tan and Q. V. Le, ‘EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks’, ArXiv190511946 Cs Stat, Sep. 2020, Accessed: Nov. 17, 2020. [Online]. Available: http://arxiv.org/abs/1905.11946.
• [20] J. P. Cohen, P. Morrison, L. Dao, K. Roth, T. Q. Duong, and M. Ghassemi, ‘COVID-19 Image Data Collection: Prospective Predictions Are the Future’, ArXiv200611988 Cs Eess Q-Bio, Dec. 2020, Accessed: Mar. 26, 2021. [Online]. Available: http://arxiv.org/abs/2006.11988.
• [21] H. Y. F. Wong et al., ‘Frequency and Distribution of Chest Radiographic Findings in Patients Positive for COVID-19’, Radiology, vol. 296, no. 2, pp. E72–E78, Aug. 2020, doi: 10.1148/radiol.2020201160.
• [22] J. P. Cohen et al., ‘Predicting COVID-19 Pneumonia Severity on Chest X-ray With Deep Learning’, Cureus, Jul. 2020, doi: 10.7759/cureus.9448.
• [23] G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, ‘Densely Connected Convolutional Networks’, ArXiv160806993 Cs, Jan. 2018, Accessed: Apr. 05, 2021. [Online]. Available: http://arxiv.org/abs/1608.06993.
• [24] R. Amer, M. Frid-Adar, O. Gozes, J. Nassar, and H. Greenspan, ‘COVID-19 in CXR: from Detection and Severity Scoring to Patient Disease Monitoring’, IEEE J. Biomed. Health Inform., pp. 1–1, 2021, doi:10.1109/JBHI.2021.3069169.