Automatic scoring of COVID-19 severity in X-ray imaging based on a novel deep learning workflow

• Published in: Scientific reports Vol. 12; no. 1; pp. 12791 - 22
• Main Authors: Danilov, Viacheslav V., Litmanovich, Diana, Proutski, Alex, Kirpich, Alexander, Nefaridze, Dato, Karpovsky, Alex, Gankin, Yuriy
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 27.07.2022; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/1041; 639/705/1042; 639/705/1046; 639/705/117; 639/705/258; 692/308/409; 692/699/255/1318; 692/699/255/1856; 692/699/255/2514; 692/700/1421; 692/700/1421/1770; Algorithms; Coronaviruses; COVID-19; COVID-19 - diagnostic imaging; Deep Learning; Humanities and Social Sciences; Humans; Image Processing, Computer-Assisted - methods; Lung - diagnostic imaging; Lung diseases; multidisciplinary; Pneumothorax; Science; Science (multidisciplinary); Segmentation; Tuberculosis; X-Rays
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-022-15013-z

In this study, we propose a two-stage workflow used for the segmentation and scoring of lung diseases. The workflow inherits quantification, qualification, and visual assessment of lung diseases on X-ray images estimated by radiologists and clinicians. It requires the fulfillment of two core stages devoted to lung and disease segmentation as well as an additional post-processing stage devoted to scoring. The latter integrated block is utilized, mainly, for the estimation of segment scores and computes the overall severity score of a patient. The models of the proposed workflow were trained and tested on four publicly available X-ray datasets of COVID-19 patients and two X-ray datasets of patients with no pulmonary pathology. Based on a combined dataset consisting of 580 COVID-19 patients and 784 patients with no disorders, our best-performing algorithm is based on a combination of DeepLabV3 + , for lung segmentation, and MA-Net, for disease segmentation. The proposed algorithms’ mean absolute error (MAE) of 0.30 is significantly reduced in comparison to established COVID-19 algorithms; BS-net and COVID-Net-S, possessing MAEs of 2.52 and 1.83 respectively. Moreover, the proposed two-stage workflow was not only more accurate but also computationally efficient, it was approximately 11 times faster than the mentioned methods. In summary, we proposed an accurate, time-efficient, and versatile approach for segmentation and scoring of lung diseases illustrated for COVID-19 and with broader future applications for pneumonia, tuberculosis, pneumothorax, amongst others.