China 
Africa 
Explore chapters and articles related to this topic
Automated COVID-19 Detection from CT Images Using Deep Learning
Published in Varun Bajaj, G.R. Sinha, Computer-aided Design and Diagnosis Methods for Biomedical Applications, 2021
Abdulhamit Subasi, Arka Mitra, Fatih Ozyurt, Turker Tuncer
Li et al. [31] used a COVID-19 detection neural network to obtain visual features from volumetric chest CT scans for COVID-19 detection. They added CT scans of community-acquired pneumonia and other non-pneumonia irregularities to make the model even more robust. The final dataset consisted of 4352 CT scans from 3322 patients, and it had an area under the receiver operating characteristic curve (AUC) of 0.96. Zhang et al. [32] extracted the features from the CT scans and compared them against the clinical evidence of disease severity based on other organ systems’ parameters. They found a strong correlation between lung lesions as compared to other organs, and highlighted the importance of lung damage on the overall prognostic implications. Also, they were able to show that there is a strong association between age and a low mortality rate due to COVID-19. It also showed that there was a correlation among other organs as well that proved that multi-organ failure occurs in COVID-19.
Bronchiolitis obliterans organizing pneumonia induced by drugs or radiotherapy
Published in Philippe Camus, Edward C Rosenow, Drug-induced and Iatrogenic Respiratory Disease, 2010
Carbamazepine is an established anticonvulsant medication used for treatment of epilepsy. A 72-year-old man was treated with cabamazepine for focal seizures and admitted to the hospital with fever, unproductive cough and progressive shortness of breath after 7 weeks of treatment.50 He had bilateral crackles. The chest radiograph showed right upper lung consolidation. There was no eosinophilia. He was treated with antibiotics for community acquired pneumonia with worsening of symptoms. Transbronchial biopsy showed organizing tissue filling small bronchioles and alveolar spaces consistent with BOOP. Treatment with oral prednisolone at 60 mg daily was begun and the carbamazepine discontinued. He had a dramatic improvement and after 2 weeks was asymptomatic and the chest radiograph was normal.
Clinical Applications of Immunoassays
Published in Richard O’Kennedy, Caroline Murphy, Immunoassays, 2017
Pneumonia is an inflammatory condition of the lung, which causes serious morbidity and mortality worldwide. The laboratory investigation of pneumonia includes microscopy, culture, bacterial identification, antibiotic susceptibility, serology and molecular techniques [32]. Sputum sampling is a quick and efficient way to culture specific strains of bacteria and is a non-invasive and relatively low-cost technique. However, it has a low sensitivity (35–60%), with high variability between readers. In addition, about 30–40% of community-acquired pneumonia patients do not produce sputum and hence identifying the infective bacterial strain is more problematic.
War Snake Optimisation Algorithm with deep Q-Net for COVID-19 classification
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023
G. Venkata Rami Reddy, Abboju Niranjan
For detecting COVID-19 Zhao et al. (2021) developed transfer learning based on images from CT. This method reduced the possibility of able to diagnose COVID-19-(-) cases as (+) cases and reduced the saddle on the medical system. But, this method failed to access large datasets in real-time. To detect and classify the COVID-19 established CNN using CT Images. It effectively reduced the manual labelling CT images requirements. However, this method was not effective in separating Community-Acquired Pneumonia (CAP) from COVID-19 disease. Castiglione et al. (2021) established the Automatic Detection of Coronavirus using an optimised CNN model (ADECO-CNN) from CT images Hu et al. (2022). This method was more efficient in the real-time classification of disease from chest-CT images at anywhere for controlling earlier disease outbreaks, however this method took much time for training the network. Wang et al. (2021) introduced CNN to screen coronavirus using CT images. Here, high accuracy was obtained by the inclusion of more CT images in the training process. However, the task of classification was difficult, because of a relatively huge number of variable objects.
Identification of COVID-19 using chest X-Ray images
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023
Vijaya Patnaik, Monalisa Mohanty, Asit Kumar Subudhi
A revised ResNet50V2 design was implemented and investigated by Ahamed et al. (2021). The database was developed to train the design assembled from various public databases. The gathered images were again pre-processed over a filter that is sharpened and fed to the projected system. This system assures accuracy of about 96.452% for various instances like (COVID-19/Bacterial pneumonia/Normal/Viral pneumonia), 97.242% for the other three cases (COVID-19/Bacterial pneumonia/Normal), and 98.954% for the cases (of COVID-19/Viral pneumonia) using chest X-ray images. The network promises an accuracy of 99.012% for cases like (COVID-19/Community-acquired pneumonia/Normal) and 99.99% approximately for cases like (Normal/COVID-19) utilising chest scans of CT. This high accuracy provides an improved and potentially essential resource that encourages medical experts to identify and rapidly diagnose COVID-19 by utilising widely available equipment.
A mask-guided attention deep learning model for COVID-19 diagnosis based on an integrated CT scan images database
Published in IISE Transactions on Healthcare Systems Engineering, 2023
Maede Maftouni, Bo Shen, Andrew Chung Chee Law, Niloofar Ayoobi Yazdi, Fahimeh Hadavand, Fereshte Ghiasvand, Zhenyu (James) Kong
Despite the promising learning ability of deep models, the generalization power of the trained network depends on the size, distribution, and quality of the training dataset. Inadequate training datasets can easily lead to over-fitted deep learning models that cannot generalize well on a new dataset. Some COVID-19 datasets have been made publicly available (Afshar et al., 2021; Cohen et al., 2020; He et al., 2020; Jun et al., 2020; MedSeg, 2020; Morozov et al., 2020; Rahimzadeh et al., 2021; Zhao et al., 2020). Zhao et al. (2020) introduced the COVID-CT dataset, which includes 349 COVID-19 CT images from 216 patients and 463 non-COVID-19 (a mix of normal cases and patients with other diseases). Misztal et al. (2020) reported improving classification performance by categorizing negative COVID-19 cases into specific groups and creating the COVID-19 CT Radiograph Image Data Stock dataset with careful data split. Afshar et al. (2021) built an open-sourced dataset named COVID-CT-MD, comprising COVID-19, Normal, and community-acquired pneumonia (CAP) cases. The COVID-CT-MD is accompanied by lobe-level, slice-level, and patient-level labels to aid in developing deep learning methods. Notwithstanding, researchers continue to require more data for deep learning models’ training in order to provide better insights and generalization performance. To this end, our COVID-19 lung CT-scan dataset is curated from seven open-source datasets.