COVID-19 Detection Using Integration of Deep Learning Classifiers and Contrast-Enhanced Canny Edge Detected X-Ray Images

COVID-19 is a deadly disease, and should be efficiently detected. COVID-19 shares similar symptoms with pneumonia, another type of lung disease, which remains a cause of morbidity and mortality. This article aims to demonstrate an ensemble deep learning approach that can differentiate COVID-19 and pneumonia based on chest X-ray images. The original X-ray images were processed to produce two sets of images with different features. The first set was images enhanced with contrast limited adaptive histogram equalization. The second set was edge images produced by contrast-enhanced canny edge detection. Convolutional neural networks were used to extract features from the images and train classifiers, which were able to classify COVID-19, pneumonia, and healthy lungs cases. Results show that the classifiers were able to differentiate X-rays of different classes, where the best performing ensemble achieved an overall accuracy of 97.90%, with a sensitivity of 99.47%, and specificity of 98.94% for COVID-19 detection.

Adjunct low-dose ketamine infusion in critically ill patients at a Saudi Hospital (Attainment trial)

INTRODUCTION: A noticeable interest in ketamine infusion for sedation management has developed among critical care physicians for critically ill patients. The Analgo-sedative adjuncT keTAmine Infusion iN Mechanically vENTilated ICU patients (ATTAINMENT) trial aims to assess the effect and safety of adjunct low-dose continuous infusion of ketamine as an analgo-sedative compared to standard of care (SOC) in critically ill patients on mechanical ventilation (MV) for ≥ 24 h METHODS: This trial is a prospective, randomized, active controlled, open-label, pilot, feasibility study of adult intensive care unit (ICU) patients (> 14 years old) on MV at King Faisal Specialist Hospital and Research Center, Saudi Arabia, and will enroll 80 patients. Patients was randomized post-intubation into two groups: the intervention group received an adjunct lowdose ketamine infusion plus SOC administered over a period of 48 h at a fixed infusion rate of 2 μg/kg/min (0.12 mg/kg/h) in day 1 followed by 1 μg/kg/min (0.06 mg/kg/h) in day 2. The control group received SOC (propofol and/or fentanyl and/or midazolam) according to our sedation and analgesia protocol as clinically appropriate. The primary outcome is MV duration until ICU discharge, death, extubation, or 28 days post-randomization, whichever comes first RESULTS: As of 25 July 2020, a total of 65 patients had been enrolled. We expect to complete the recruitment by 31 December 2020. Recruitment rate has been slowed down due to COVID-19 pandemic. An Interim analysis was conducted and showed 45% were in medical ICU, 35 % in surgical ICU, and 20 % in transplant/oncology ICU, range SOFA 2-18, and APACHE II 7-39. About 70 % of the patients was extubated within 28 days post-randomization to ketamine compared to 50 % randomized to SOC. The percentage of the patient at goal RASS in 48 hours is 61.11 % in ketamine vs 57.89 % in SOC. No significant difference between the 2 arms in 28 days mortality CONCLUSIONS: The findings of this pilot trial will justify further investigation for the role of adjunct low-dose ketamine infusion as an analgo-sedative agent in a larger, multicenter, randomized controlled trial. The trial is registered at ClinicalTrials.gov: NCT04075006, Saudi Food and Drug Authority: SCTR #19063002, and Current controlled trials: ISRCTN14730035.

Enhanced Canny edge detection for Covid-19 and pneumonia X-Ray images

In image processing, one of the most fundamental technique is edge detection. It is a process to detect edges from images by identifying discontinuities in brightness. In this research, we present an enhanced Canny edge detection technique. This method integrates local morphological contrast enhancement and Canny edge detection. Furthermore, the proposed edge detection technique was also applied for pneumonia and COVID-19 detection in digital x-ray images by utilising convolutional neural networks. Results show that this enhanced Canny edge detection technique is better than the traditional Canny technique. Also, we were able to produce classifiers that can classify edge x-ray images into COVID-19, normal, and pneumonia classes with high accuracy, sensitivity, and specificity. © Published under licence by IOP Publishing Ltd.