scholarly journals Interpretation of Frequency Channel-Based CNN on Depression Identification

2021 ◽  
Vol 15 ◽  
Author(s):  
Hengjin Ke ◽  
Cang Cai ◽  
Fengqin Wang ◽  
Fang Hu ◽  
Jiawei Tang ◽  
...  
Keyword(s):  
Neural Network ◽  
High Performance ◽  
Classification Performance ◽  
Brain Diseases ◽  
Control Group ◽  
Brain State ◽  
Frequency Channel ◽  
Brain Rhythm ◽  
Research Challenge ◽  
The Brain

Online end-to-end electroencephalogram (EEG) classification with high performance can assess the brain status of patients with Major Depression Disabled (MDD) and track their development status in time with minimizing the risk of falling into danger and suicide. However, it remains a grand research challenge due to (1) the embedded intensive noises and the intrinsic non-stationarity determined by the evolution of brain states, (2) the lack of effective decoupling of the complex relationship between neural network and brain state during the attack of brain diseases. This study designs a Frequency Channel-based convolutional neural network (CNN), namely FCCNN, to accurately and quickly identify depression, which fuses the brain rhythm to the attention mechanism of the classifier with aiming at focusing the most important parts of data and improving the classification performance. Furthermore, to understand the complexity of the classifier, this study proposes a calculation method of information entropy based on the affinity propagation (AP) clustering partition to measure the complexity of the classifier acting on each channel or brain region. We perform experiments on depression evaluation to identify healthy and MDD. Results report that the proposed solution can identify MDD with an accuracy of 99±0.08%, the sensitivity of 99.07±0.05%, and specificity of 98.90±0.14%. Furthermore, the experiments on the quantitative interpretation of FCCNN illustrate significant differences between the frontal, left, and right temporal lobes of depression patients and the healthy control group.

Relationship Between Exercise and 18-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography Imaging of Brain in the Elderly

2020 ◽  
Vol 10 (8) ◽  
pp. 1962-1966
Author(s):  
Pengfei Kang
Keyword(s):  
Vascular Occlusion ◽  
The Elderly ◽  
Exercise Group ◽  
Brain Diseases ◽  
Control Group ◽  
Computed Tomography Imaging ◽  
Positron Emission ◽  
Pet Scanning ◽  
Cerebral Vascular Occlusion ◽  
The Brain

CT were analyzed. The subjects were elderly people aged 55–75 who volunteered for brain 18F of the FDG CT and PET scanning. The elderly who maintained exercise were divided into exercise group and non-exercise group into control group. The images obtained by CT examination showed that the brain of the elderly who insisted on exercise showed a significant increase in glucose metabolism, which indicated that exercise had a preventive effect on brain diseases of the elderly, and reduced the risk of cerebral vascular occlusion and brain atrophy.

scholarly journals Norepinephrine Transporter Imaging in the Brain of a Rat Model of Depression Using Radioiodinated (2S, αS)-2-(α-(2-iodophenoxy)benzyl)morpholine

2012 ◽  
Vol 11 (4) ◽  
pp. 7290.2011.00049 ◽  
Author(s):  
Naoki Kanegawa ◽  
Yasushi Kiyono ◽  
Taku Sugitaa ◽  
Yuji Kuge ◽  
Yasushisa Fujibayasi ◽  
...  
Keyword(s):  
Rat Model ◽  
Thalamic Nucleus ◽  
Ex Vivo ◽  
Norepinephrine Transporter ◽  
Diagnostic Information ◽  
Brain Diseases ◽  
Imaging Biomarker ◽  
Control Group ◽  
The Brain

To visualize the norepinephrine transporters (NETs) in various brain diseases, we developed radioiodinated (2S,αS)-2-(α-(2-iodophenoxy)benzyl)morpholine ((S,S)-IPBM). This radioligand achieved the basic requirements for NET imaging. In this study, we assessed the potential of radioiodinated (S,S)-IPBM as an imaging biomarker of NET to obtain diagnostic information about depression in relation to NET expression in the brain using a rat depression model. The ex vivo autoradiographic experiments using the (S,S)-[125I]IPBM showed significantly lower accumulation of radioactivity in the locus coeruleus (LC) and the anteroventricular thalamic nucleus (AVTN) of the depression group than in those of the control group. Consequently, in vitro autoradiographic experiments showed that NET maximum binding (Bmax) values in the LC and AVTN, known as NET-rich regions, were significantly decreased in the rat model of depression when compared to those of the control rats. In addition, there was an extremely good correlation between NET Bmax and (S,S)-IPBM accumulation ( r = .98), an indication of radioiodinated IPBM as a quantitative NET imaging biomarker. The reduction in(S,S)-[125I]IPBM accumulation in the rat model of depression correlated with that of NET density. These results suggest that (S,S)-[123I]IPBM has potential as an imaging biomarker of NET to obtain diagnostic information about major depression.

Platelet Glutamate Uptake and Release in Migraine With and Without Aura

Cephalalgia ◽  
2007 ◽  
Vol 27 (1) ◽  
pp. 35-40 ◽  
Author(s):  
M Vaccaro ◽  
C Riva ◽  
L Tremolizzo ◽  
M Longoni ◽  
A Aliprandi ◽  
...  
Keyword(s):  
Amino Acid ◽  
High Performance ◽  
Spreading Depression ◽  
Glutamate Uptake ◽  
Glutamate Release ◽  
Plasma Concentrations ◽  
Control Group ◽  
Therapeutic Approaches ◽  
The Brain ◽  
Uptake And Release

Glutamate may play an important role in the pathogenesis of migraine: glutamate release in the brain may be involved in the development of spreading depression and increased concentrations of this amino acid have been reported in plasma and platelets from migraine patients. Here we assessed platelet glutamate uptake and release in 25 patients affected by migraine with aura (MA) and 25 patients affected by migraine without aura (MoA), comparing the results with a group of 20 healthy matched controls. Both glutamate release from stimulated platelets and plasma concentrations of the amino acid were assessed by high-performance liquid chromatography, and were increased in both types of migraine, although more markedly in MA. Platelet glutamate uptake, assessed as 3H-glutamate intake, was increased in MA, while it was reduced in MoA with respect to the control group. These results support the view that MA might involve different pathophysiological mechanisms from MoA and, specifically, up-regulation of the glutamatergic metabolism. Understanding these dysfunctional pathways could lead to new, possibly more successful therapeutic approaches to the management of migraine.

Diagnosis of Brain Tumor Using Artificial Neural Network

2021 ◽  
Vol 8 (1) ◽  
pp. 06-10
Author(s):  
R. Ganesh ◽  
Dr.R. Sivakumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Brain Tumor ◽  
Medical Image Analysis ◽  
Region Of Interest ◽  
Classification Performance ◽  
Feed Forward Neural Network ◽  
Classification Rate ◽  
Artificial Neural ◽  
The Brain

Accurate detection and diagnosis of brain tumor is one the crucial task of medical image analysis. Brain tumor classification system aids the physician to make accurate diagnosis and to provide effective treatment. Magnetic Resonance Imaging (MRI) is the gold standard imaging technique for brain tumor diagnosis. This paper proposes a method for brain tumor detection and classification using artificial neural network. The proposed method consists of four major processes such as preprocessing, region of interest segmentation, feature extraction and classification. Feed forward neural network is employed to classify the brain tumors. Classification performance of the proposed method is evaluated using 10-cross fold validation and compared with the previous methods. Empirical findings proved that the proposed method can efficiently classify the brain tumor with higher classification rate.

Brain MRI Intelligent Diagnostic Using an Improved Deep Convolutional Neural Network

2021 ◽  
Vol 11 (3) ◽  
pp. 836-845
Author(s):  
Xiangsheng Zhang ◽  
Feng Pan ◽  
Leyuan Zhou
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Brain Tissue ◽  
Brain Mri ◽  
Deep Convolutional Neural Network ◽  
Brain Diseases ◽  
Support Vector ◽  
Svm Classifier ◽  
Intelligent Diagnosis ◽  
The Brain

The diagnosis of brain diseases based on magnetic resonance imaging (MRI) is a mainstream practice. In the course of practical treatment, medical personnel observe and analyze the changes in the size, position, and shape of various brain tissues in the brain MRI image, thereby judging whether the brain tissue has been diseased, and formulating the corresponding medical plan. The conclusion drawn after observing the image will be influenced by the subjective experience of the experts and is not objective. Therefore, it has become necessary to try to avoid subjective factors interfering with the diagnosis. This paper proposes an intelligent diagnosis model based on improved deep convolutional neural network (IDCNN). This model introduces integrated support vector machine (SVM) into IDCNN. During image segmentation, if IDCNN has problems such as irrational layer settings, too many parameters, etc., it will make its segmentation accuracy low. This study made a slight adjustment to the structure of IDCNN. First, adjust the number of convolution layers and down-sampling layers in the DCNN network structure, adjust the network’s activation function, and optimize the parameters to improve IDCNN’s non-linear expression ability. Then, use the integrated SVM classifier to replace the original Softmax classifier in IDCNN to improve its classification ability. The simulation experiment results tell that compared with the model before improvement and other classic classifiers, IDCNN improves segmentation results and promote the intelligent diagnosis of brain tissue.

The Vegetative Status Correction in the Patients with Chronic Dyscirculatory Encephalopathy on the Sanatorium Rehabilitation Stage

10.12737/5760 ◽  
2014 ◽  
Vol 8 (1) ◽  
pp. 1-6
Author(s):  
Куликов ◽  
N. Kulikov ◽  
Череващенко ◽  
Lyubov Cherevashchenko ◽  
Череващенко ◽  
...  
Keyword(s):  
Laser Therapy ◽  
The State ◽  
The Body ◽  
Brain Diseases ◽  
Control Group ◽  
Autonomic Imbalance ◽  
Dyscirculatory Encephalopathy ◽  
Before And After ◽  
The Brain ◽  
Adaptive Reactions

Among vascular brain diseases a special place in its importance takes chronic cerebrovascular pathology in the form of dyscirculatory encephalopathy. The most frequently affected cerebral structures with discirculatory encephalopathy are those parts of the brain that are largely responsible for shaping over segmental vegetative disorders, which are characteristic of clinics chronic cerebrovascular insufficiency. The purpose of this work is to develop a new modern high technology of sanatorium rehabilitation of the patients with circulatory encephalopathy on stage I and to correct autonomic imbalance. The authors observed 60 patients who were divided into 2 groups. The control group received radon baths, the patients from the main group in addition to radon baths received laser therapy paravertebrally C1-Th3, according to scanning technique. In all patients before and after treatment the state of the autonomic nervous system studied. It was found that the initial manifestations of vascular encephalopathy accompanied by autonomic imbalance with a predominance of sympathetic tone, activation and inhibition effects of ergotrop activities segmental systems, primarily due to the parasympathetic division. The results of this study demonstrate feasibility of incorporating laser therapy in complex radon baths for rehabilitation of patients with circulatory encephalopathy autonomic imbalance. The findings suggest that improving the functional state mechanisms vegetative maintenance activities, which help to eliminate the state of surge and flow of adaptive reactions in the body.

EFFECTS OF PRENATAL PASSIVE SMOKING ON CHOLINERGIC MECHANISMS SIMULATION RESPIRATORY RHYTHM IN NEONATAL RATS (IN VITRO)

2020 ◽  
Vol 6(72) (2) ◽  
pp. 3-12
Author(s):  
S. E. Bolychevsky ◽  
E. A. Zinchenko ◽  
I. V. Miroshnichenko
Keyword(s):  
Neural Network ◽  
Tobacco Smoke ◽  
Passive Smoking ◽  
Respiratory Rhythm ◽  
Control Group ◽  
Newborn Rats ◽  
Pregnant Rats ◽  
Nicotinic Cholinergic Receptors ◽  
The Brain ◽  
Experimental Group

Both active and passive smoking increases the risk of sudden death of the newborn. Researchers are actively studying the effect of chronic nicotine infusion, as one of the leading neurogenic factors of tobacco smoke on cholinergic mechanisms of respiratory control. In this paper, using a fumigation model of passive smoking, tested the assumption that second-hand smoke that is transferred in the prenatal period, changes the expression mediated by nicotinic receptors activating influence of the cholinergic system of the brain stem to the processes of the respiratory activity of the neural network generation. It is found that the fumigation of tobacco smoke pregnant rats decreases their progeny respiratory sensitivity to the action of a neural network and exogenous nicotine increases cholinergic part tonic effect mediated by nicotinic cholinergic receptors in the modulation of respiratory rhythm. The study uses data obtained from 40 brain stem-spinal cord preparations (BSP) of the newborn rats. The experimental group was 22, and the control group was 18 newborn rats. In the processing of neurograms, the duration of the cycle of respiratory activity, duration, and the amplitude of inspiratory discharges were measured. To describe the peaks of the respiratory discharge spectrum, the following parameters were used: the peak frequency and the peak power spectral density of the peak. Analysis of the statistical differences was made using Student’s t-test for mean values. Differences were considered significant at p<0.05. Our results confirm the presence for exogenous nicotine of powerful activating effect on the generation frequency, amplitude and duration of inspiratory discharges of the BSP of newborn rats in the control group. It is established that an increase in the amplitude of the inspiratory discharges is accompanied by an increase in the spectral power density in the mid-frequency range of their spectrograms. In the BSP of the brain of newborn rats with prenatal exposure to tobacco smoke, exogenous nicotine increased only the frequency of inspiratory discharge generation. The amplitude of the inspiratory discharges and the power of the mid-frequency oscillations under the influence of exogenous nicotine in the BSP of the experimental group was significantly reduced. Mecamylamine, a selective blocker of nAChR, added to the perfusate of the BSP of the control group, caused a significant increase in the amplitude and duration of the inspiratory discharges, without significantly changing the duration of the respiratory cycle. At the same time, in BSP of newborn rats subjected to prenatal exposure to tobacco smoke, nAChR blockade resulted in an increase in the duration of the respiratory cycle. Thus, our study showed that fumigation of pregnant rats with tobacco smoke reduces the sensitivity of the respiratory neural network to the action of exogenous nicotine in early postnatal period and increases the involvement of tonic cholinergic effect mediated by nicotinic cholinergic receptors in modulating the respiratory rhythm.

scholarly journals Explainable Neural Network Ensembles

2021 ◽  
Author(s):  
Manomita Chakraborty ◽  
Saroj Kumar Biswas ◽  
Biswajit Purkayastha
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Performance ◽  
Decision Rules ◽  
Rule Extraction ◽  
Classification Performance ◽  
Classification Rules ◽  
Multiple Networks ◽  
Neural Network Ensembles ◽  
Network Ensembles

Abstract Neural networks are known for providing impressive classification performance, and the ensemble learning technique is further acting as a catalyst to enhance this performance by integrating multiple networks. But like neural networks, neural network ensembles are also considered as a black-box because they cannot explain their decision making process. So, despite having high classification performance, neural networks and their ensembles are not suited for some applications which require explainable decisions. However, the rule extraction technique can overcome this drawback by representing the knowledge learned by a neural network in the guise of interpretable decision rules. A rule extraction algorithm provides neural networks with the power to justify their classification responses through explainable classification rules. Several rule extraction algorithms exist to extract classification rules from neural networks, but only a few of them generates rules using neural network ensembles. So this paper proposes an algorithm named Rule Extraction using Ensemble of Neural Network Ensembles (RE-E-NNES) to demonstrate the high performance of neural network ensembles through rule extraction. RE-E-NNES extracts classification rules by ensembling several neural network ensembles. Results show the efficacy of the proposed RE-E-NNES algorithm compared to different existing rule extraction algorithms.

scholarly journals Neural classifiers with limited connectivity and recurrent readouts

2017 ◽  
Author(s):  
Lyudmila Kushnir ◽  
Stefano Fusi
Keyword(s):  
Neural Network ◽  
Long Range ◽  
Network Models ◽  
Classification Performance ◽  
Network Architectures ◽  
Huge Number ◽  
Neural Network Models ◽  
Random Patterns ◽  
Scalable Network ◽  
The Brain

AbstractFor many neural network models in which neurons are trained to classify inputs like perceptrons, the number of inputs that can be classified is limited by the connectivity of each neuron, even when the total number of neurons is very large. This poses the problem of how the biological brain can take advantage of its huge number of neurons given that the connectivity is sparse. One solution is to combine multiple perceptrons together, as in committee machines. The number of classifiable random patterns would then grow linearly with the number of perceptrons, even when each perceptron has limited connectivity. However, the problem is moved to the downstream readout neurons, which would need a number of connections that is as large as the number of perceptrons. Here we propose a different approach in which the readout is implemented by connecting multiple perceptrons in a recurrent attractor neural network. We prove analytically that the number of classifiable random patterns can grow unboundedly with the number of perceptrons, even when the connectivity of each perceptron remains finite. Most importantly, both the recurrent connectivity and the connectivity of downstream readouts also remain finite. Our study shows that feed-forward neural classifiers with numerous long range afferent connections can be replaced by recurrent networks with sparse long range connectivity without sacrificing the classification performance. Our strategy could be used to design more general scalable network architectures with limited connectivity, which resemble more closely the brain neural circuits which are dominated by recurrent connectivity.

scholarly journals CENNA: Cost-Effective Neural Network Accelerator

Electronics ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 134
Author(s):  
Sang-Soo Park ◽  
Ki-Seok Chung
Keyword(s):  
Neural Network ◽  
High Performance ◽  
Data Exchange ◽  
Matrix Multiplication ◽  
Cost Effective ◽  
Classification Performance ◽  
Memory Access ◽  
Control Logic ◽  
Silicon Area ◽  
Data Movement

Convolutional neural networks (CNNs) are widely adopted in various applications. State-of-the-art CNN models deliver excellent classification performance, but they require a large amount of computation and data exchange because they typically employ many processing layers. Among these processing layers, convolution layers, which carry out many multiplications and additions, account for a major portion of computation and memory access. Therefore, reducing the amount of computation and memory access is the key for high-performance CNNs. In this study, we propose a cost-effective neural network accelerator, named CENNA, whose hardware cost is reduced by employing a cost-centric matrix multiplication that employs both Strassen’s multiplication and a naïve multiplication. Furthermore, the convolution method using the proposed matrix multiplication can minimize data movement by reusing both the feature map and the convolution kernel without any additional control logic. In terms of throughput, power consumption, and silicon area, the efficiency of CENNA is up to 88 times higher than that of conventional designs for the CNN inference.

Sign in / Sign up

Export Citation Format

Share Document