Emerging Feature Extraction Techniques for Machine Learning-Based Classification of Carotid Artery Ultrasound Images.

Plaque deposits in the carotid artery are the major cause of stroke and atherosclerosis. Ultrasound imaging is used as an early indicator of disease progression. Classification of the images to identify plaque presence and intima-media thickness (IMT) by machine learning algorithms requires features extracted from the images. A total of 361 images were used for feature extraction, which will assist in further classification of the carotid artery. This study presents the extraction of 65 features, which constitute of shape, texture, histogram, correlogram, and morphology features. Principal component analysis (PCA)-based feature selection is performed, and the 22 most significant features, which will improve the classification accuracy, are selected. Naive Bayes algorithm and dynamic learning vector quantization (DLVQ)-based machine learning classifications are performed with the extracted and selected features, and analysis is performed.

Discernment on assistive technology for the care and support requirements of older adults and differently-abled individuals.

Assistive technology for the differently abled and older adults has made remarkable achievements in providing rehabilitative, adaptive, and assistive devices. It provides huge assistance for people with physical impairments to lead a better self-reliant daily life, in terms of mobility, education, rehabilitation, etc. This technology ranges from simple hand-held devices to complex robotic accessories which promote the individual's independence. This study aimed at identifying the assistance required by differently-abled individuals, and the solutions proposed by different researchers, and reviewed their merits and demerits. It provides a detailed discussion on the state of art assistive technologies, their applications, challenges, types, and their usage for rehabilitation. The study also identifies different unexplored research areas related to assistive technology that can improve the daily life of individuals and advance the field. Despite their high usage, assistive technologies have some limitations which have been briefly described in the study. This review, therefore, can help understand the utilization, and pros and cons of assistive devices in rehabilitation engineering and assistive technologies.

Smart access development for classifying lung disease with chest x-ray images using deep learning.

Recently the world has come across a pandemic disease known as covid-19. The presence of symptoms of covid-19 and pneumonia may be alike to other types of lung illnesses. So, because of this, it is difficult for the affected person or medical experts to identify the condition. Chest x-ray provides general orientation which can be an initial investigative study in the analysis of lung diseases. Information from retenogram studies help the finding of covid-19 and pneumonia affecting the lungs. We use a Convolution Neural Network (CNN) in Tensor Flow and Keras based covid-19, pneumonia classification. The best fit model of CNN is then deployed in the Django framework for providing a better user interface and predicting the output.

Performance Analysis of Machine Learning and Deep Learning Architectures on Early Stroke Detection Using Carotid Artery Ultrasound Images.

Atherosclerotic plaque deposit in the carotid artery is used as an early estimate to identify the presence of cardiovascular diseases. Ultrasound images of the carotid artery are used to provide the extent of stenosis by examining the intima-media thickness and plaque diameter. A total of 361 images were classified using machine learning and deep learning approaches to recognize whether the person is symptomatic or asymptomatic. CART decision tree, random forest, and logistic regression machine learning algorithms, convolutional neural network (CNN), Mobilenet, and Capsulenet deep learning algorithms were applied in 202 normal images and 159 images with carotid plaque. Random forest provided a competitive accuracy of 91.41% and Capsulenet transfer learning approach gave 96.7% accuracy in classifying the carotid artery ultrasound image database.

Field Effect Transistor Based on Layered NiPS 3.

Layered metal phosphochalcogenides of molecular formula, MPX3 (M = Mn, Fe, Co, Ni, etc and X = S, Se) have been emerging as new class of semiconductors towards various catalytic and optoelectronic applications. The low cleavage energy associated with these layered chalcogenides may lead to devices with very thin semiconductor channels. Herein, we report the first successful fabrication of field effect transistor (FET) using layered NiPS3 that reveals n-type semiconducting behavior. Devices using bulk and few-layer NiPS3 with gold contacts show on/off ratios of ~103-105 at 25 °C. The device characteristics reveal an increase in on-state current with decrease in threshold voltage and the Schottky barrier height is extracted to be 112 meV. Density functional theory calculations reveal various parameters that affect electron/hole doping in the layered phosphochalcogenide material.

Amla (Emblica officinalis) improves hepatic and renal oxidative stress and the inflammatory response in hypothyroid female wistar rats fed with a high-fat diet.

BACKGROUND: We investigated the protective effects of amla (Emblica officinalis) on the pathogenesis of oxidative stress (OS) and inflammatory response in hypothyroid rats fed with a high-fat diet (HFD) as an experimental model of hypothyroidism (HT) with obesity. METHODS: A total of 80 female wistar rats (5-months-old) were divided into eight different groups. Propylthiouracil (PTU) and HFD were used to induce the experimental HT and obesity, respectively. The euthyroid and hypothyroid rats were fed either normal chow or HFD with and without amla extract (AE, 100 mg/kg bw/day) for 6 weeks. The blood and tissues, liver and kidney OS and inflammatory parameters were studied using appropriate biochemical and molecular techniques. RESULTS: PTU and HFD per se caused OS and inflammatory response as evidenced by increased plasma MDA, TNF-α, CRP and GPx in association with decreased levels of TAS and reduced glutathione (GSH). The proteomic analysis revealed that the expressions of pERK, pP38, TNF-α, IL6, COX2 and NOX-4 were up-regulated in the liver and kidney of these rats. In addition, all these metabolic derangements were further augmented when HT was followed by the addition of HFD. This suggested that there was a synergism between HT and the intake of HFD on the development of OS and inflammatory response. CONCLUSIONS: The treatment with amla fruit extract significantly restored the redox imbalance and inflammatory signaling and ameliorated OS and inflammatory response, suggesting the use of this natural compound as an alternative remedy or adjuvant for the management of metabolic complications concomitant with HT.

Myosin cross-bridges do not form precise rigor bonds in hypertrophic heart muscle carrying troponin T mutations.

Distribution of orientations of myosin was examined in ex-vivo myofibrils from hearts of transgenic (Tg) mice expressing Familial Hypertrophic Cardiomyopathy (FHC) troponin T (TnT) mutations I79N, F110I and R278C. Humans are heterozygous for sarcomeric FHC mutations and so hypertrophic myocardium contains a mixture of the wild-type (WT) and mutated (MUT) TnT. If mutations are expressed at a low level there may not be a significant change in the global properties of heart muscle. In contrast, measurements from a few molecules avoid averaging inherent in the global measurements. It is thus important to examine the properties of only a few molecules of muscle. To this end, the lever arm of one out of every 60,000 myosin molecules was labeled with a fluorescent dye and a small volume within the A-band (~1 fL) was observed by confocal microscopy. This volume contained on average 5 fluorescent myosin molecules. The lever arm assumes different orientations reflecting different stages of acto-myosin enzymatic cycle. We measured the distribution of these orientations by recording polarization of fluorescent light emitted by myosin-bound fluorophore during rigor and contraction. The distribution of orientations of rigor WT and MUT myofibrils was significantly different. There was a large difference in the width and of skewness and kurtosis of rigor distributions. These findings suggest that the hypertrophic phenotype associated with the TnT mutations can be characterized by a significant increase in disorder of rigor cross-bridges.

Familial hypertrophic cardiomyopathy can be characterized by a specific pattern of orientation fluctuations of actin molecules .

A single-point mutation in the gene encoding the ventricular myosin regulatory light chain (RLC) is sufficient to cause familial hypertrophic cardiomyopathy (FHC). Most likely, the underlying cause of this disease is an inefficient energy utilization by the mutated cardiac muscle. We set out to devise a simple method to characterize two FHC phenotypes caused by the R58Q and D166V mutations in RLC. The method is based on the ability to observe a few molecules of actin in working ex vivo heart myofibril. Actin is labeled with extremely diluted fluorescent dye, and a small volume within the I-band ( approximately 10(-16) L), containing on average three actin molecules, is observed by confocal microscopy. During muscle contraction, myosin cross-bridges deliver cyclic impulses to actin. As a result, actin molecules undergo periodic fluctuations of orientation. We measured these fluctuations by recording the parallel and perpendicular components of fluorescent light emitted by an actin-bound fluorophore. The histograms of fluctuations of fluorescent actin molecules in wild-type (WT) hearts in rigor were represented by perfect Gaussian curves. In contrast, histograms of contracting heart muscle were peaked and asymmetric, suggesting that contraction occurred in at least two steps. Furthermore, the differences between histograms of contracting FHC R58Q and D166V hearts versus corresponding contracting WT hearts were statistically significant. On the basis of our results, we suggest a simple new method of distinguishing between healthy and FHC R58Q and D166V hearts by analyzing the probability distribution of polarized fluorescence intensity fluctuations of sparsely labeled actin molecules.

Fluorescence correlation spectroscopy in a reverse Kretchmann surface plasmon assisted microscope.

Fluorescence Correlation Spectroscopy (FCS) demands a high rate of photon detection per molecule, low background, and large fluctuations of fluorescence associated with translational motion. The new approach presented here, Surface Plasmon Assisted Microscope (SPAM), meets these requirements by drastically limiting the observation volume. In this method, the observational layer is made so thin that fluctuations are mostly due to the axial motion of molecules. This is conveniently realized by placing a sample on a thin metal film and illuminating it with a laser beam through an aqueous medium. The excited fluorophores close to the surface couple (via near-field interactions) to surface plasmons in the metal. Propagated surface plasmons decouple on opposite side of the metal film as a far-field radiation and emit in directional manner. Fluorescence is collected with a high Numerical Aperture objective. A confocal aperture inserted in its conjugate image plane reduces lateral dimensions of the detection volume to a diffraction limit. The thickness of the detection layer is reduced further by metal quenching of excited fluorophores at a close proximity (about 30 nm) to the surface. We used a suspension of fluorescent microspheres to show that FCS-SPAM is an efficient method to measure molecular diffusion.