RESUMO
Background: Early detection of post-COVID-19-related lung fibrosis is very important for the early introduction of treatment and to minimize morbidity and mortality. The aim of this study is the early detection and evaluation of post-COVID-19 fibrosis by high-resolution computed tomography (HRCT). Methods: This prospective study included 115 patients irrespective of age and sex, who tested positive for the SARS-CoV-2 by nasopharyngeal swab (RT PCR), admitted to the Dhaka North City Corporation (DNCC) dedicated COVID-19 hospital, Dhaka, and discharged after recovery. Patients went through a chest HRCT scan at least once during their hospital stay and another scan during follow-up after hospital discharge and 8 to 12 weeks of negative RT-PCR report. Result: Among 100 patients 23 patients had >50% of total lung involvement by visual assessment. Thirty-three patients had 25% to 50% of total lung volume involvement. Twenty-seven patients had less than 25% of total lung involvement, whereas 17 patients had no visual fibrotic change on the follow-up HRCT scan. A statistical association was found between age, gender, smoking, and severe form of lung fibrosis (P < .05). Patients with mild CT severity score (⩽8) had a very good prognosis. Patients who were admitted to the hospital for more than 15 days were more prone to developing moderate and severe forms of fibrosis. Patients who received at least 2 doses of the COVID-19 vaccine had less severe forms of fibrosis as well as more cases of complete radiological recovery. On the HRCT scan, most of the patients had bilateral, peripheral (68%), and predominant mid & lower lobar parenchymal involvement. Conclusion: Early detection and HRCT evaluation of post-COVID-19 related lung fibrosis is very crucial for early management and introduction of anti-fibrotic drugs.
RESUMO
The COVID-19 pandemic has been adversely affecting the patient management systems in hospitals around the world. Radiological imaging, especially chest x-ray and lung Computed Tomography (CT) scans, plays a vital role in the severity analysis of hospitalized COVID-19 patients. However, with an increasing number of patients and a lack of skilled radiologists, automated assessment of COVID-19 severity using medical image analysis has become increasingly important. Chest x-ray (CXR) imaging plays a significant role in assessing the severity of pneumonia, especially in low-resource hospitals, and is the most frequently used diagnostic imaging in the world. Previous methods that automatically predict the severity of COVID-19 pneumonia mainly focus on feature pooling from pre-trained CXR models without explicitly considering the underlying human anatomical attributes. This paper proposes an anatomy-aware (AA) deep learning model that learns the generic features from x-ray images considering the underlying anatomical information. Utilizing a pre-trained model and lung segmentation masks, the model generates a feature vector including disease-level features and lung involvement scores. We have used four different open-source datasets, along with an in-house annotated test set for training and evaluation of the proposed method. The proposed method improves the geographical extent score by 11% in terms of mean squared error (MSE) while preserving the benchmark result in lung opacity score. The results demonstrate the effectiveness of the proposed AA model in COVID-19 severity prediction from chest X-ray images. The algorithm can be used in low-resource setting hospitals for COVID-19 severity prediction, especially where there is a lack of skilled radiologists.