Medical imaging datasets are inherently high dimensional with large variability and low sample sizes that limit the effectiveness of deep learning algorithms. Recently, generative adversarial networks (GANs) with the ability to synthesize realist images have shown great potential as an alternative to standard data augmentation techniques. Our work focuses on cross-modality synthesis of fluorodeoxyglucose (FDG) Positron Emission Tomography (PET) scans from structural Magnetic Resonance (MR) images using generative models to facilitate multi-modal diagnosis of Alzheimer's disease (AD). Specifically, we propose a novel end-to-end, globally and locally aware imageto-image translation GAN (GLA-GAN) with a multi-path architecture that enforces both global structural integrity and fidelity to local details. We further supplement the standard adversarial loss with voxel-level intensity, multiscale structural similarity (MS-SSIM) and region-of-interest (ROI) based loss components that reduce reconstruction error, enforce structural consistency at different scales and perceive variation in regional sensitivity to AD respectively. Experimental results demonstrate that our GLA-GAN not only generates synthesized FDG-PET scans with enhanced image quality but also superior clinical utility in improving AD diagnosis compared to state-of-the-art models. Finally, we attempt to interpret some of the internal units of the GAN that are closely related to this specific cross-modality generation task.

Background: India is the second-largest population in the world, and it is not well equipped, hitherto, in the scenario of the global pandemic, SARS-CoV-2 could impart a devastating impact on the Indian population. Only way to respond against this critical condition is by practicing large-scale social distancing. India lock down for 21 days, however, till 7 April 2020, SARS-CoV-2 positive cases were growing exponentially, which raises the concerns if the number of reported and actual cases are similar. Methods: We use Lasso Regression withand Polynomial features of degree 2 to predict the growth factor. Also, we predicted Logistic curve using the Prophet Python. Further, using the growth rate to logistic, and carrying capacity is 20000 allowed us to calculate the maximum cases and new cases per day. Results:We found the predicted growth factor with a standard deviation of 0.3443 for the upcoming days. When the growth factor becomes 1.0, which is known as Inflection point, it will be safe to state that the rate is no longer exponential. The estimated time to reach the inflection point is between 15-20 April. At that time, the estimated number of total positive cases will be over 12500, if lockdown remains continue. Conclusions:Our analysis suggests that there is an urgent need to take action to extend the period of lockdown and allocate enough resources, including personnel, beds, and intensive care facilities, to manage the situation in the next few days and weeks. Otherwise, the outbreak in India can reach the level of the USA or Italy or could be worse than these countries within a few days or weeks, given the size of the population and lack of resources.

Most of the people who do not take required sleep are prone to sleep-deprived mental fatigue. This mental fatigue due to sleep deprivation is very harmful to persons involved in critical jobs like Pilots, Surgeons, Air traffic controllers and others. The present research paper proposes an intelligent method based on re-enforced learning, followed by classification supported by the adaptive threshold. Moreover, the method proposed by us is non-intrusive, in which the subject is unaware of being monitored during the test; it helps prevent biased results. The novelty lies in the use of the Inter-frame interval of an open and close eye for feature extraction that leads to the detection of “Alertness” or “Fatigue” based on the adaptive threshold. The proposed self-learning framework is real-time in nature and has a detection accuracy of 97.5 %. Since the method is self-learning, as the size of the data set increases, its accuracy and sensitivity are likely to increase further.

No abstract

No abstract

No abstract

Sleep-deprived fatigued person is likely to commit more errors that may even prove to be fatal. Thus, it is necessary to recognize this fatigue. The novelty of the proposed research work for the detection of this fatigue is that it is nonintrusive and based on multimodal feature fusion. In the proposed methodology, fatigue is detected by obtaining features from four domains: visual images, thermal images, keystroke dynamics, and voice features. In the proposed methodology, the samples of a volunteer (subject) are obtained from all four domains for feature extraction, and empirical weights are assigned to the four different domains. Young, healthy volunteers (n = 60) between the age group of 20 to 30 years participated in the experimental study. Further, they abstained from the consumption of alcohol, caffeine, or other drugs impacting their sleep pattern during the study. Through this multimodal technique, appropriate weights are given to the features obtained from the four domains. The results are compared with k-nearest neighbors (kNN), support vector machines (SVM), random tree, random forest, and multilayer perceptron classifiers. The proposed nonintrusive technique has obtained an average detection accuracy of 93.33% in 3-fold cross-validation.

No abstract