This paper addresses issues of brain tumor subtype classification using Magnetic Resonance Images (MRIs) from different scanner modalities like T1 weighted, weighted with contrast-enhanced, T2 and FLAIR images. Currently most available glioma datasets are relatively moderate in size, often accompanied incomplete MRIs modalities. To tackle the commonly encountered problems insufficiently large modality image for deep learning, we propose to add augmented MR images enlarge training dataset by...

This paper addresses issues of brain tumor, glioma, grading from multi-sensor images. Different types scanners (or sensors) like enhanced T1-MRI, T2-MRI and FLAIR, show different contrast are sensitive to tissues fluid regions. Most existing works use 3D images single sensor. In this paper, we propose a novel multistream deep Convolutional Neural Network (CNN) architecture that extracts fuses the features multiple sensors for glioma tumor grading/subcategory grading. The main contributions...

Abstract Background This paper addresses issues of brain tumor, glioma, classification from four modalities Magnetic Resonance Image (MRI) scans (i.e., T1 weighted MRI, MRI with contrast-enhanced, T2 and FLAIR). Currently, many available glioma datasets often contain some unlabeled scans, are moderate in size. Methods We propose to exploit deep semi-supervised learning make full use the data. Deep CNN features were incorporated into a new graph-based framework for labels data, where 3D-2D...

Depression is a common psychiatric disorder with limited effective treatments. Research suggests that depression involves apoptosis mechanisms. Quercetin (QUE) has been reported to have anti-apoptotic activities. In this study, we aimed investigate the effects and mechanisms of QUE in chronic unpredictable mild stress (CUMS)-induced depression. After establishing mouse models CUMS-induced depression, mice were randomly assigned into four groups: control, CUMS, CUMS+QUE, CUMS+Fluoxetine...

This paper addresses issues of grading brain tumor, glioma, from Magnetic Resonance Images (MRIs). Although feature pyramid is shown to be useful extract multi -scale features for object recognition, it rarely explored in MRI images glioma classification/grading. For grading, existing deep learning methods often use convolutional neural networks (CNN s) single-scale without considering that the scales tumor vary depending on structure/shape, size, tissue smoothness, and locations. In this...

This article proposes a novel scheme for analyzing power system measurement data. The main question that we seek answers in this study is on "whether one can find some important patterns are hidden the large data of measurements such as variational data." proposed uses an unsupervised deep feature learning approach by first employing autoencoder (DAE) followed clustering. An analysis performed examining clusters and reconstructing representative sequence clustering centers. illustrated...

Brain Magnetic Resonance Images (MRIs) are commonly used for tumor diagnosis. Machine learning brain characterization often uses MRIs from many modalities (e.g., T1-MRI, Enhanced-T1-MRI, T2-MRI and FLAIR). This paper tackles two issues that may impact performance deep learning: insufficiently large training dataset, incomplete collection of different modalities. We propose a novel pairwise generative adversarial network (GAN) architecture generating synthetic in missing by using existing...

This paper addresses the issues of Alzheimer's disease (AD) characterization and detection from Magnetic Resonance Images (MRIs). Many existing AD methods use single-scale feature learning brain scans. In this paper, we propose a multiscale deep architecture for features. The main contributions include: (a) novel 3D CNN dedicated task detection; (b) fusion enhancement strategy features; (c) empirical study on impact several settings, including two dataset partitioning approaches,...

This paper addresses issues in human fall detection from videos. Unlike using handcrafted features the conventional machine learning, we extract Convolutional Neural Networks (CNNs) for detection. Similar to many existing work two stream inputs, use a spatial CNN with raw image difference and temporal optical flow as inputs of CNN. Different action recognition work, exploit sparse representation residual-based pooling on extracted features, obtaining more discriminative feature codes. For...

This paper addresses the issue of fall detection from videos for e-healthcare and assisted-living. Instead using conventional hand-crafted features videos, we propose a scheme based on co-saliency-enhanced recurrent convolutional network (RCN) architecture videos. In proposed scheme, deep learning method RCN is realized by set Convolutional Neural Networks (CNNs) in segment-levels followed Recurrent Network (RNN), Long Short-Term Memory (LSTM), to handle time-dependent video frames. The...

Brain ischemia is an independent risk factor for Alzheimer's disease (AD); however, the mechanisms underlining ischemic stroke and AD remain unclear. The present study aimed to investigate function of ε isoform protein kinase C (PKCε) in brain ischemia-induced dendritic spine dysfunction elucidate how causes AD. In study, primary hippocampus cortical neurons were cultured while oxygen-glucose deprivation (OGD) model was used simulate ischemia. OGD cell model, vitro activity assay performed...

In this paper, we present a method for discovering the common salient objects from set of images. We treat co-saliency detection as pairwise saliency propagation problem, which utilizes similarity between each pair images to measure property with guidance single map image. Given co-salient foreground maps, is optimized by combining initial background cues. Pairwise maps are then fused according novel fusion strategy based on focus human attention. Finally adopt an integrated multi-scale...

Tongue temperature perception abnormality typically refers to an alteration in the tongue's ability sense temperature, which may manifest as diminished or lost of heat cold, abnormal sensations absence significant changes. This case report describes a 60-year-old female who developed tongue following use agomelatine. The patient had history good health, with no surgical chronic disease history, and family mental illness. She presented symptoms emotional depression, irritability, insomnia,...