COVID-19 detection from chest X-ray images using CLAHE-YCrCb, LBP, and machine learning algorithms.

BACKGROUND: COVID-19 is a disease that caused a contagious respiratory ailment that killed and infected hundreds of millions. It is necessary to develop a computer-based tool that is fast, precise, and inexpensive to detect COVID-19 efficiently. Recent studies revealed that machine learning and deep learning models accurately detect COVID-19 using chest X-ray (CXR) images. However, they exhibit notable limitations, such as a large amount of data to train, larger feature vector sizes, enormous trainable parameters, expensive computational resources (GPUs), and longer run-time. RESULTS: In this study, we proposed a new approach to address some of the above-mentioned limitations. The proposed model involves the following steps: First, we use contrast limited adaptive histogram equalization (CLAHE) to enhance the contrast of CXR images. The resulting images are converted from CLAHE to YCrCb color space. We estimate reflectance from chrominance using the Illumination-Reflectance model. Finally, we use a normalized local binary patterns histogram generated from reflectance (Cr) and YCb as the classification feature vector. Decision tree, Naive Bayes, support vector machine, K-nearest neighbor, and logistic regression were used as the classification algorithms. The performance evaluation on the test set indicates that the proposed approach is superior, with accuracy rates of 99.01%, 100%, and 98.46% across three different datasets, respectively. Naive Bayes, a probabilistic machine learning algorithm, emerged as the most resilient. CONCLUSION: Our proposed method uses fewer handcrafted features, affordable computational resources, and less runtime than existing state-of-the-art approaches. Emerging nations where radiologists are in short supply can adopt this prototype. We made both coding materials and datasets accessible to the general public for further improvement. Check the manuscript's availability of the data and materials under the declaration section for access.

In silico identification of novel stilbenes analogs for potential multi-targeted drugs against Alzheimer's disease.

CONTEXT: Alzheimer's disease (AD) is a chronic progressive neurodegenerative syndrome, which adversely disturbs cognitive abilities as well as intellectual processes and frequently occurs in the elderly. Inhibition of cholinesterase is a valuable approach to upsurge acetylcholine concentrations in the brain and persuades the development of multi-targeted ligands against cholinesterases. METHODS: The current study aims to determine the binding potential accompanied by antioxidant and anti-inflammatory activities of stilbenes-designed analogs against both cholinesterases (Acetylcholinesterase and butyrylcholinesterase) and neurotrophin targets for effective AD therapeutics. Docking results have shown that the WS6 compound exhibited the least binding energy - 10.1 kcal/mol with Acetylcholinesterase and - 7.8 kcal/mol with butyrylcholinesterase. The WS6 also showed a better binding potential with neurotrophin targets that are Brain-derived Neurotrophic Factor, Neurotrophin 4, Nerve Growth Factor, and Neurotrophin 3. The tested compounds particularly WS6 revealed significant antioxidant and anti-inflammatory activities through the comparative docking analysis with Fluorouracil and Melatonin as control drugs of antioxidants while Celecoxib and Anakinra as anti-inflammatory. The bioinformatics approaches including molecular docking calculations followed by the pharmacokinetics analysis and molecular dynamic simulations were accomplished to explore the capabilities of designed stilbenes as effective and potential leads. Root mean square deviation, root mean square fluctuations, and MM-GBSA calculations were performed through molecular dynamic simulations to extract the structural and residual variations and binding free energies through the 50-ns time scale.