SVD-CLAHE boosting and balanced loss function for Covid-19 detection from an imbalanced Chest X-Ray dataset.

Covid-19 disease has had a disastrous effect on the health of the global population, for the last two years. Automatic early detection of Covid-19 disease from Chest X-Ray (CXR) images is a very crucial step for human survival against Covid-19. In this paper, we propose a novel data-augmentation technique, called SVD-CLAHE Boosting and a novel loss function Balanced Weighted Categorical Cross Entropy (BWCCE), in order to detect Covid 19 disease efficiently from a highly class-imbalanced Chest X-Ray image dataset. Our proposed SVD-CLAHE Boosting method is comprised of both oversampling and under-sampling methods. First, a novel Singular Value Decomposition (SVD) based contrast enhancement and Contrast Limited Adaptive Histogram Equalization (CLAHE) methods are employed for oversampling the data in minor classes. Simultaneously, a Random Under Sampling (RUS) method is incorporated in major classes, so that the number of images per class will be more balanced. Thereafter, Balanced Weighted Categorical Cross Entropy (BWCCE) loss function is proposed in order to further reduce small class imbalance after SVD-CLAHE Boosting. Experimental results reveal that ResNet-50 model on the augmented dataset (by SVD-CLAHE Boosting), along with BWCCE loss function, achieved 95% F1 score, 94% accuracy, 95% recall, 96% precision and 96% AUC, which is far better than the results by other conventional Convolutional Neural Network (CNN) models like InceptionV3, DenseNet-121, Xception etc. as well as other existing models like Covid-Lite and Covid-Net. Hence, our proposed framework outperforms other existing methods for Covid-19 detection. Furthermore, the same experiment is conducted on VGG-19 model in order to check the validity of our proposed framework. Both ResNet-50 and VGG-19 model are pre-trained on the ImageNet dataset. We publicly shared our proposed augmented dataset on Kaggle website (https://www.kaggle.com/tr1gg3rtrash/balanced-augmented-covid-cxr-dataset), so that any research community can widely utilize this dataset. Our code is available on GitHub website online (https://github.com/MrinalTyagi/SVD-CLAHE-and-BWCCE).

SVD-CLAHE boosting and balanced loss function for Covid-19 detection from an imbalanced Chest X-ray dataset

The covid-19 disease has had a disastrous effect on the global population’s health for the last two years. Automatic early detection of Covid-19 disease from Chest X-ray (CXR) images is a very crucial step for human survival against Covid-19. In this paper, we propose a novel data augmentation technique, called SVD-CLAHE (Singular Value Decomposition - Contrast Limited Adaptive Histogram Equalization) Boosting, and a novel loss function Balanced Weighted Categorical Cross-Entropy (BWCCE), in order to detect Covid 19 disease efficiently from a highly class-imbalanced Chest X-ray (CXR) image dataset. Our proposed SVD-CLAHE Boosting method is comprised of both oversampling and under-sampling methods. First, novel Singular Value Decomposition (SVD) based contrast enhancement and Contrast Limited Adaptive Histogram Equalization (CLAHE) methods are employed for oversampling the data in minor classes. Simultaneously, a Random Under Sampling (RUS) method is incorporated in major classes so that the number of images per class will be more balanced. After that, the BWCCE loss function is proposed to further reduce class imbalance after SVD-CLAHE Boosting. Experimental results reveal that the ResNet-50 model on the augmented dataset (by SVD-CLAHE Boosting), along with BWCCE loss function, achieved 95% F1 score, 94% accuracy, 96% recall, and 96% precision, which is far better than the results by other conventional CNN models like InceptionV3, DenseNet-121, Xception, etc. and other existing models like Covid-Lite and Covid-Net. Hence, our proposed framework outperforms other existing methods for Covid-19 detection. Furthermore, the same experiment is conducted on the VGG-19 model to check our proposed framework’s validity. Both ResNet-50 and VGG-19 models are pre-trained from the ImageNet dataset. We publicly share our proposed augmented dataset on the Kaggle site (https://www.kaggle.com/tr1gg3rtrash/balanced-augmented-covid-cxr-dataset) so that any research community can widely utilize this dataset. Our code is available on the GitHub website online (https://github.com/MrinalTyagi/SVD-CLAHE-and-BWCCE).

Children, comorbidities and COVID-19 - What tilts the balance?

Background: Data on the outcome of children with SARS-COV-2 infection (COVID-19) is still evolving as the pandemic unfolds. Aims and Objective: The present study aims at describing the clinical severity, course and outcome of COVID-19 in children who had underlying illnesses or co-infections. Materials and Methods: Retrospective, single center, observational study, conducted in a pediatric tertiary care center at Noida (National Capital Region, India). Results: We analyzed the data of 15 children with co-morbidities associated with COVID-19. Cancer (n=4, 26.6%), co-infections (n=5, 33.3%), Thalassemia major (n=2, 13.3%) and one child each with celiac disease, cholelithiasis, Duchenne muscular dystrophy and multiple rib fractures were diagnosed with COVID-19. None were asymptomatic. 9 children (60%) had mild symptoms and 4 had moderate symptoms (26.6%) with respiratory distress. 2 children had severe respiratory distress requiring high flow oxygen. Convalescent plasma, IVIG, Oseltamivir, Azithromycin, Hydroxychloroquine were given as treatment in varying combinations. All children recovered from COVID-19. Conclusion: Active malignancy, hypogammaglobinemia, underlying lung disease were associated with moderate to severe symptoms in this series of patients. Convalescent plasma helped in both children with severe hypoxia. [ABSTRACT FROM AUTHOR] Copyright of Asian Journal of Medical Sciences is the property of Manipal Colleges of Medical Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The use of telemedicine for the diagnosis and treatment of sleep disorders: an American Academy of Sleep Medicine update.

NONE: The COVID-19 pandemic led to widespread use of telemedicine and highlighted its importance in improving access to sleep care and advocating for sleep health. This update incorporates the lessons learned from such widespread utilization of telehealth to build on the American Academy of Sleep Medicine's 2015 position paper on the use of telemedicine for diagnosing and treating sleep disorders. Important key factors in this update include an emphasis on quality and value, privacy and safety, health advocacy through sleep telemedicine, and future directions.

Use of convalescent plasma for managing severe COVID-19 infection in 2-month-old infant

Abstract A 58-day-old female infant reported with complaints of fever, difficult breathing, loose stool, vomiting and refusal to feed for 4 days. Laboratory work showed anaemia, leucocytosis with elevated neutrophils and thrombocytopenia along with high C-reactive protein and D-dimer with bilateral patchy infiltrate on X-ray and positivity for COVID-19. Her blood culture was also positive for Gram-negative bacilli (acinetobacter lwoffii). Along with antibiotics, she was given 50 ml convalescent plasma. She was off oxygen within 2 days and showed improvement in lung lesions, and RT-PCR was negative by day 7 and discharged by day 10 of transfusion.