Showing papers by "National University of Malaysia published in 2020"

Can AI Help in Screening Viral and COVID-19 Pneumonia?

Abstract: Coronavirus disease (COVID-19) is a pandemic disease, which has already caused thousands of causalities and infected several millions of people worldwide. Any technological tool enabling rapid screening of the COVID-19 infection with high accuracy can be crucially helpful to the healthcare professionals. The main clinical tool currently in use for the diagnosis of COVID-19 is the Reverse transcription polymerase chain reaction (RT-PCR), which is expensive, less-sensitive and requires specialized medical personnel. X-ray imaging is an easily accessible tool that can be an excellent alternative in the COVID-19 diagnosis. This research was taken to investigate the utility of artificial intelligence (AI) in the rapid and accurate detection of COVID-19 from chest X-ray images. The aim of this paper is to propose a robust technique for automatic detection of COVID-19 pneumonia from digital chest X-ray images applying pre-trained deep-learning algorithms while maximizing the detection accuracy. A public database was created by the authors combining several public databases and also by collecting images from recently published articles. The database contains a mixture of 423 COVID-19, 1485 viral pneumonia, and 1579 normal chest X-ray images. Transfer learning technique was used with the help of image augmentation to train and validate several pre-trained deep Convolutional Neural Networks (CNNs). The networks were trained to classify two different schemes: i) normal and COVID-19 pneumonia; ii) normal, viral and COVID-19 pneumonia with and without image augmentation. The classification accuracy, precision, sensitivity, and specificity for both the schemes were 99.7%, 99.7%, 99.7% and 99.55% and 97.9%, 97.95%, 97.9%, and 98.8%, respectively. The high accuracy of this computer-aided diagnostic tool can significantly improve the speed and accuracy of COVID-19 diagnosis. This would be extremely useful in this pandemic where disease burden and need for preventive measures are at odds with available resources.

Public knowledge, attitudes and practices towards COVID-19: A cross-sectional study in Malaysia.

Abstract: In an effort to mitigate the outbreak of COVID-19, many countries have imposed drastic lockdown, movement control or shelter in place orders on their residents. The effectiveness of these mitigation measures is highly dependent on cooperation and compliance of all members of society. The knowledge, attitudes and practices people hold toward the disease play an integral role in determining a society's readiness to accept behavioural change measures from health authorities. The aim of this study was to determine the knowledge levels, attitudes and practices toward COVID-19 among the Malaysian public. A cross-sectional online survey of 4,850 Malaysian residents was conducted between 27th March and 3rd April 2020. The survey instrument consisted of demographic characteristics, 13 items on knowledge, 3 items on attitudes and 3 items on practices, modified from a previously published questionnaire on COVID-19. Descriptive statistics, chi-square tests, t-tests and one-way analysis of variance (ANOVA) were conducted. The overall correct rate of the knowledge questionnaire was 80.5%. Most participants held positive attitudes toward the successful control of COVID-19 (83.1%), the ability of Malaysia to conquer the disease (95.9%) and the way the Malaysian government was handling the crisis (89.9%). Most participants were also taking precautions such as avoiding crowds (83.4%) and practising proper hand hygiene (87.8%) in the week before the movement control order started. However, the wearing of face masks was less common (51.2%). This survey is among the first to assess knowledge, attitudes and practice in response to the COVID-19 pandemic in Malaysia. The results highlight the importance of consistent messaging from health authorities and the government as well as the need for tailored health education programs to improve levels of knowledge, attitudes and practices.

Spinal Cord Injury: Pathophysiology, Multimolecular Interactions, and Underlying Recovery Mechanisms.

Abstract: Spinal cord injury (SCI) is a destructive neurological and pathological state that causes major motor, sensory and autonomic dysfunctions. Its pathophysiology comprises acute and chronic phases and incorporates a cascade of destructive events such as ischemia, oxidative stress, inflammatory events, apoptotic pathways and locomotor dysfunctions. Many therapeutic strategies have been proposed to overcome neurodegenerative events and reduce secondary neuronal damage. Efforts have also been devoted in developing neuroprotective and neuro-regenerative therapies that promote neuronal recovery and outcome. Although varying degrees of success have been achieved, curative accomplishment is still elusive probably due to the complex healing and protective mechanisms involved. Thus, current understanding in this area must be assessed to formulate appropriate treatment modalities to improve SCI recovery. This review aims to promote the understanding of SCI pathophysiology, interrelated or interlinked multimolecular interactions and various methods of neuronal recovery i.e., neuroprotective, immunomodulatory and neuro-regenerative pathways and relevant approaches.

The Potential of Silver Nanoparticles for Antiviral and Antibacterial Applications: A Mechanism of Action

Abstract: Rapid development of nanotechnology has been in high demand, especially for silver nanoparticles (AgNPs) since they have been proven to be useful in various fields such as medicine, textiles, and household appliances. AgNPs are very important because of their unique physicochemical and antimicrobial properties, with a myriad of activities that are applicable in various fields, including wound care management. This review aimed to elucidate the underlying mechanisms of AgNPs that are responsible for their antiviral properties and their antibacterial activity towards the microorganisms. AgNPs can be synthesized through three different methods—physical, chemical, and biological synthesis—as indicated in this review. The applications and limitations of the AgNPs such as their cytotoxicity towards humans and the environment, will be discussed. Based on the literature search obtained, the properties of AgNPs scrutinizing the antibacterial or antiviral effect shown different interaction towards bacteria which dependent on the synthesis processes followed by the morphological structure of AgNPs.

The Role of Inflammation in the Pathogenesis of Osteoarthritis.

Abstract: A joint is the point of connection between two bones in our body. Inflammation of the joint leads to several diseases, including osteoarthritis, which is the concern of this review. Osteoarthritis is a common chronic debilitating joint disease mainly affecting the elderly. Several studies showed that inflammation triggered by factors like biomechanical stress is involved in the development of osteoarthritis. This stimulates the release of early-stage inflammatory cytokines like interleukin-1 beta (IL-1β), which in turn induces the activation of signaling pathways, such as nuclear factor kappa-light-chain-enhancer of activated B cells (NF-κB), phosphoinositide 3-kinase/protein kinase B (PI3K/AKT), and mitogen-activated protein kinase (MAPK). These events, in turn, generate more inflammatory molecules. Subsequently, collagenase like matrix metalloproteinases-13 (MMP-13) will degrade the extracellular matrix. As a result, anatomical and physiological functions of the joint are altered. This review is aimed at summarizing the previous studies highlighting the involvement of inflammation in the pathogenesis of osteoarthritis.

ROS Homeostasis in Abiotic Stress Tolerance in Plants

Abstract: Climate change-induced abiotic stress results in crop yield and production losses. These stresses result in changes at the physiological and molecular level that affect the development and growth of the plant. Reactive oxygen species (ROS) is formed at high levels due to abiotic stress within different organelles, leading to cellular damage. Plants have evolved mechanisms to control the production and scavenging of ROS through enzymatic and non-enzymatic antioxidative processes. However, ROS has a dual function in abiotic stresses where, at high levels, they are toxic to cells while the same molecule can function as a signal transducer that activates a local and systemic plant defense response against stress. The effects, perception, signaling, and activation of ROS and their antioxidative responses are elaborated in this review. This review aims to provide a purview of processes involved in ROS homeostasis in plants and to identify genes that are triggered in response to abiotic-induced oxidative stress. This review articulates the importance of these genes and pathways in understanding the mechanism of resistance in plants and the importance of this information in breeding and genetically developing crops for resistance against abiotic stress in plants.

Future global meteorological drought hot spots: A study based on CORDEX data

Abstract: Two questions motivated this study: 1) Will meteorological droughts become more frequent and severe during the twenty-first century? 2) Given the projected global temperature rise, to what ...

Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization

Abstract: Tuberculosis (TB) is a chronic lung disease that occurs due to bacterial infection and is one of the top 10 leading causes of death. Accurate and early detection of TB is very important, otherwise, it could be life-threatening. In this work, we have detected TB reliably from the chest X-ray images using image pre-processing, data augmentation, image segmentation, and deep-learning classification techniques. Several public databases were used to create a database of 3500 TB infected and 3500 normal chest X-ray images for this study. Nine different deep CNNs (ResNet18, ResNet50, ResNet101, ChexNet, InceptionV3, Vgg19, DenseNet201, SqueezeNet, and MobileNet) were used for transfer learning from their pre-trained initial weights and were trained, validated and tested for classifying TB and non-TB normal cases. Three different experiments were carried out in this work: segmentation of X-ray images using two different U-net models, classification using X-ray images and that using segmented lung images. The accuracy, precision, sensitivity, F1-score and specificity of best performing model, ChexNet in the detection of tuberculosis using X-ray images were 96.47%, 96.62%, 96.47%, 96.47%, and 96.51% respectively. However, classification using segmented lung images outperformed that with whole X-ray images; the accuracy, precision, sensitivity, F1-score and specificity of DenseNet201 were 98.6%, 98.57%, 98.56%, 98.56%, and 98.54% respectively for the segmented lung images. The paper also used a visualization technique to confirm that CNN learns dominantly from the segmented lung regions that resulted in higher detection accuracy. The proposed method with state-of-the-art performance can be useful in the computer-aided faster diagnosis of tuberculosis.

Environmental impact of food packaging materials: a review of contemporary development from conventional plastics to polylactic acid based materials

Abstract: Plastics have remained the material of choice, and after serving their intended purpose, a large proportion ends up in the environment where they persist for centuries. The packaging industry is the largest and growing consumer of synthetic plastics derived from fossil fuels. Food packaging plastics account for the bulk of plastic waste that are polluting the environment. Additionally, given the fact that petroleum reserves are finite and facing depletion, there is a need for the development of alternative materials that can serve the same purpose as conventional plastics. This paper reviews the function of packaging materials and highlights the future potential of the adoption of green materials. Biopolymers have emerged as promising green materials although they still have very low market uptake. Polylactic acid (PLA) has emerged as the most favoured bioplastic. However, it is limited by its high cost and some performance drawbacks. Blending with agricultural waste and natural fillers can result in green composites at low cost, low greenhouse gas emissions, and with improved performance for food packaging applications. The continent of Africa is proposed as a rich source of fibres and fillers that can be sustainably exploited to fabricate green composites in a bid to achieve a circular economy.

State of the art of solid-state transformers: Advanced topologies, implementation issues, recent progress and improvements

Abstract: Solid-state transformer (SST) is an emerging technology integrating with a transformer power electronics converters and control circuitry. This paper comprehensively reviews the SST topologies suitable for different voltage levels and with varied stages, their control operation, and different trends in applications. The paper discusses various SST configurations with their design and characteristics to convert the input to output under unipolar and bipolar operation. A comparison between the topologies, control operation and applications are included. Different control models and schemes are explained. Potential benefits of SST in many applications in terms of controllability and the synergy of AC and DC systems are highlighted to appreciate the importance of SST technologies. This review highlights many factors including existing issues and challenges and provides recommendations for the improvement of future SST configuration and development.

Elicitor and Receptor Molecules: Orchestrators of Plant Defense and Immunity.

Abstract: Pathogen-associated molecular patterns (PAMPs), microbe-associated molecular patterns (MAMPs), herbivore-associated molecular patterns (HAMPs), and damage-associated molecular patterns (DAMPs) are molecules produced by microorganisms and insects in the event of infection, microbial priming, and insect predation. These molecules are then recognized by receptor molecules on or within the plant, which activates the defense signaling pathways, resulting in plant’s ability to overcome pathogenic invasion, induce systemic resistance, and protect against insect predation and damage. These small molecular motifs are conserved in all organisms. Fungi, bacteria, and insects have their own specific molecular patterns that induce defenses in plants. Most of the molecular patterns are either present as part of the pathogen’s structure or exudates (in bacteria and fungi), or insect saliva and honeydew. Since biotic stresses such as pathogens and insects can impair crop yield and production, understanding the interaction between these organisms and the host via the elicitor–receptor interaction is essential to equip us with the knowledge necessary to design durable resistance in plants. In addition, it is also important to look into the role played by beneficial microbes and synthetic elicitors in activating plants’ defense and protection against disease and predation. This review addresses receptors, elicitors, and the receptor–elicitor interactions where these components in fungi, bacteria, and insects will be elaborated, giving special emphasis to the molecules, responses, and mechanisms at play, variations between organisms where applicable, and applications and prospects.

A review of biological drinking water treatment technologies for contaminants removal from polluted water resources

Abstract: This paper is the first critical review of the technology of water treatment via biological process for contaminants removal from water resources. The biological process is considered the future for drinking water treatment, especially for developing countries. The main focus of the review is on single and integrated treatment technologies that have been studied for all types of drinking water resources, including surface water and ground water. These treatment technologies have the capability to treat contaminants in polluted drinking water resources, such as heavy metals, natural organic matter, inorganic non-metallic matter, disinfection by-products, endocrine disrupting chemicals and microbial contaminants. The potential threats and challenges of using the biological process for safe drinking water production also have been discussed, as this technology is a relatively new concept for safe drinking water production, and there have been very limited studies performed in developing countries.

Effects of agriculture, renewable energy, and economic growth on carbon dioxide emissions: Evidence of the environmental Kuznets curve

Abstract: This study contributes to (1) discovering that carbon dioxide (CO2) emissions are not directly influenced by modernisation; (2) attaining sustainable agriculture by incorporating renewable energy into the agriculture sector as an effective CO2 emissions mitigation measure; and (3) applying the environmental Kuznets curve (EKC) to test the relationships among attributes in Malaysia. Prior studies have not addressed the associations between the release of CO2 and economic development, renewable energy, urbanisation, and agriculture in Malaysia. Hence, the objective of the study is to investigate the relationships of the emissions of CO2 and economic development, renewable energy, urbanisation, and agricultural subsectors, such as crops, livestock, and fisheries, in Malaysia for the period 1978 to 2016. By the utilisation of the autoregressive distributed lag test for cointegration, CO2 emissions significantly increased due to economic growth and urbanisation but insignificantly increased due to livestock in the long term. Crops, fisheries, and renewable energy significantly reduced emissions in this period. Moreover, this study reveals that the association between emissions of CO2 and economic development is an inverted U. This finding indicates that CO2 emissions eventually decrease despite the increase in CO2 emissions and economic development in the long term upon reaching a specific level of growth. These findings are consistent for Malaysia in terms of the EKC hypothesis.

Deep Learning for Stock Market Prediction

Abstract: The prediction of stock groups values has always been attractive and challenging for shareholders due to its inherent dynamics, non-linearity, and complex nature. This paper concentrates on the future prediction of stock market groups. Four groups named diversified financials, petroleum, non-metallic minerals, and basic metals from Tehran stock exchange were chosen for experimental evaluations. Data were collected for the groups based on 10 years of historical records. The value predictions are created for 1, 2, 5, 10, 15, 20, and 30 days in advance. Various machine learning algorithms were utilized for prediction of future values of stock market groups. We employed decision tree, bagging, random forest, adaptive boosting (Adaboost), gradient boosting, and eXtreme gradient boosting (XGBoost), and artificial neural networks (ANN), recurrent neural network (RNN) and long short-term memory (LSTM). Ten technical indicators were selected as the inputs into each of the prediction models. Finally, the results of the predictions were presented for each technique based on four metrics. Among all algorithms used in this paper, LSTM shows more accurate results with the highest model fitting ability. In addition, for tree-based models, there is often an intense competition between Adaboost, Gradient Boosting, and XGBoost.

Deep learning-based breast cancer classification through medical imaging modalities: state of the art and research challenges

Abstract: Breast cancer is a common and fatal disease among women worldwide. Therefore, the early and precise diagnosis of breast cancer plays a pivotal role to improve the prognosis of patients with this disease. Several studies have developed automated techniques using different medical imaging modalities to predict breast cancer development. However, few review studies are available to recapitulate the existing literature on breast cancer classification. These studies provide an overview of the classification, segmentation, or grading of many cancer types, including breast cancer, by using traditional machine learning approaches through hand-engineered features. This review focuses on breast cancer classification by using medical imaging multimodalities through state-of-the-art artificial deep neural network approaches. It is anticipated to maximize the procedural decision analysis in five aspects, such as types of imaging modalities, datasets and their categories, pre-processing techniques, types of deep neural network, and performance metrics used for breast cancer classification. Forty-nine journal and conference publications from eight academic repositories were methodically selected and carefully reviewed from the perspective of the five aforementioned aspects. In addition, this study provided quantitative, qualitative, and critical analyses of the five aspects. This review showed that mammograms and histopathologic images were mostly used to classify breast cancer. Moreover, about 55% of the selected studies used public datasets, and the remaining used exclusive datasets. Several studies employed augmentation, scaling, and image normalization pre-processing techniques to minimize inconsistencies in breast cancer images. Several types of shallow and deep neural network architecture were employed to classify breast cancer using images. The convolutional neural network was utilized frequently to construct an effective breast cancer classification model. Some of the selected studies employed a pre-trained network or developed new deep neural networks to classify breast cancer. Most of the selected studies used accuracy and area-under-the-curve metrics followed by sensitivity, precision, and F-measure metrics to evaluate the performance of the developed breast cancer classification models. Finally, this review presented 10 open research challenges for future scholars who are interested to develop breast cancer classification models through various imaging modalities. This review could serve as a valuable resource for beginners on medical image classification and for advanced scientists focusing on deep learning-based breast cancer classification through different medical imaging modalities.

Colorectal Cancer Immunotherapy: Options and Strategies.

Abstract: Colorectal cancer is the third most common cancer in the world with increasing incidence and mortality rates globally. Standard treatments for colorectal cancer have always been surgery, chemotherapy and radiotherapy which may be used in combination to treat patients. However, these treatments have many side effects due to their non-specificity and cytotoxicity toward any cells including normal cells that are growing and dividing. Furthermore, many patients succumb to relapse even after a series of treatments. Thus, it is crucial to have more alternative and effective treatments to treat CRC patients. Immunotherapy is one of the new alternatives in cancer treatment. The strategy is to utilize patients' own immune systems in combating the cancer cells. Cancer immunotherapy overcomes the issue of specificity which is the major problem in chemotherapy and radiotherapy. The normal cells with no cancer antigens are not affected. The outcomes of some cancer immunotherapy have been astonishing in some cases, but some which rely on the status of patients' own immune systems are not. Those patients who responded well to cancer immunotherapy have a better prognostic and better quality of life.

Diagnostic performance of COVID-19 serology assays.

Abstract: INTRODUCTION: The World Health Organization (WHO) declared COVID-19 outbreak as a world pandemic on 12th March 2020. Diagnosis of suspected cases is confirmed by nucleic acid assays with real-time PCR, using respiratory samples. Serology tests are comparatively easier to perform, but their utility may be limited by the performance and the fact that antibodies appear later during the disease course. We aimed to describe the performance data on serological assays for COVID-19. MATERIALS AND METHODS: A review of multiple reports and kit inserts on the diagnostic performance of rapid tests from various manufacturers that are commercially available were performed. Only preliminary data are available currently. RESULTS: From a total of nine rapid detection test (RDT) kits, three kits offer total antibody detection, while six kits offer combination SARS-CoV-2 IgM and IgG detection in two separate test lines. All kits are based on colloidal gold-labeled immunochromatography principle and one-step method with results obtained within 15 minutes, using whole blood, serum or plasma samples. The sensitivity for both IgM and IgG tests ranges between 72.7% and 100%, while specificity ranges between 98.7% to 100%. Two immunochromatography using nasopharyngeal or throat swab for detection of COVID-19 specific antigen are also reviewed. CONCLUSIONS: There is much to determine regarding the value of serological testing in COVID-19 diagnosis and monitoring. More comprehensive evaluations of their performance are rapidly underway. The use of serology methods requires appropriate interpretations of the results and understanding the strengths and limitations of such tests.