scholarly journals Neural Networks Implicated in Autobiographical Memory Training

2021 ◽  
Author(s):  
Dragoş Cȋrneci ◽  
Mihaela Onu ◽  
Claudiu C. Papasteri ◽  
Dana Georgescu ◽  
Catalina Poalelungi ◽  
...  
Keyword(s):  
Neural Networks ◽  
Autobiographical Memory ◽  
Resting State ◽  
Immune Modulation ◽  
Neural Substrates ◽  
Memory Training ◽  
Sensorimotor Network ◽  
Voluntary Recall ◽  
High Level ◽  
Resting State Connectivity

Abstract Training of autobiographical memory has been proposed as intervention to improve cognitive functions. The neural substrates for such improvements are poorly understood. Several brain networks have been previously linked to autobiographical recollections, including the default mode network (DMN) and the sensorimotor network. Here we tested the hypothesis that different neural networks support distinct aspects of memory improvement in response to training on a group of 59 subjects. We found that memory training using olfactory cues increases resting-state intra-network DMN connectivity, and this associates with improved recollection of cue-specific memories. On the contrary, training decreased resting-state connectivity within the sensorimotor network, a decrease that correlated with improved ability for voluntary recall. Moreover, only the decrease in sensorimotor connectivity associated with the training-induced decrease in the TNFα factor, an immune modulation previously linked to improved cognitive performance. We identified functional and biochemical factors that associate with distinct memory processes improved by autobiographical training. Pathways which connect autobiographical memory to both high level cognition and somatic physiology are discussed.

scholarly journals Neural networks implicated in autobiographical memory training

2021 ◽  
Author(s):  
Dragos Cirneci ◽  
Mihaela Onu ◽  
Claudiu C Papasteri ◽  
Dana P Georgescu ◽  
Catalina Poalelungi ◽  
...  
Keyword(s):  
Neural Networks ◽  
Autobiographical Memory ◽  
Cognitive Performance ◽  
Neural Substrates ◽  
Memory Training ◽  
Sensorimotor Network ◽  
Memory Improvement ◽  
Immunological Factor ◽  
Voluntary Recall ◽  
High Level

Training of autobiographical memory has been proposed as intervention to improve cognitive functions. The neural substrates for such improvements are poorly understood. Several brain networks have been previously linked to autobiographical recollections, including the default mode network (DMN) and the sensorimotor network. Here we tested the hypothesis that different neural networks support distinct aspects of memory improvement in response to training on a group of 59 subjects. We found that memory training increases DMN connectivity, and this associates with improved recollection of cue-specific memories. On the contrary, training decreased connectivity in the sensorimotor network, a decrease that correlated with improved ability for voluntary recall. Moreover, only decreased sensorimotor connectivity associated with training-induced decrease in the TNFalpha; immunological factor, which has been previously linked to improved cognitive performance. We identified functional and biochemical factors that associate with distinct memory processes improved by autobiographical training. Pathways which connect autobiographical memory to both high level cognition and somatic physiology are discussed.

scholarly journals Reduced Resting-State Connectivity in the Precuneus is correlated with Apathy in Patients with Schizophrenia

2018 ◽  
Author(s):  
Caroline Garcia Forlim ◽  
Leonie Klock ◽  
Johanna Bächle ◽  
Laura Stoll ◽  
Patrick Giemsa ◽  
...  
Keyword(s):  
Neural Networks ◽  
Resting State ◽  
Negative Symptoms ◽  
Magnetic Resonance Images ◽  
Healthy Controls ◽  
Resting State Networks ◽  
Healthy Individuals ◽  
Functional Magnetic Resonance ◽  
Resting State Connectivity ◽  
Positive And Negative Symptoms

AbstractA diagnosis of schizophrenia is associated with a heterogeneous psychopathology including positive and negative symptoms. The disconnection hypothesis, an early pathophysiological framework conceptualizes the diversity of symptoms as a result from disconnections in neural networks. In line with this hypothesis, previous neuroimaging studies of patients with schizophrenia reported alterations within the default mode network (DMN), the most prominent network at rest.Aim of the present study was to investigate the functional connectivity during rest in patients with schizophrenia and healthy individuals and explore whether observed functional alterations are related to the psychopathology of patients. Therefore, functional magnetic resonance images at rest were recorded of 35 patients with schizophrenia and 41 healthy individuals. Independent component analysis (ICA) was used to extract resting state networks.Comparing ICA results between groups indicated alterations only within the network of the DMN. More explicitly, reduced connectivity in the precuneus was observed in patients with schizophrenia compared to healthy controls. Connectivity in this area was negatively correlated with the severity of negative symptoms, more specifically with the domain of apathy.Taken together, the current results provide further evidence for a role DMN alterations might play in schizophrenia and especially in negative symptom such as apathy.

scholarly journals Learning Cortical Parcellations Using Graph Neural Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Kristian M. Eschenburg ◽  
Thomas J. Grabowski ◽  
David R. Haynor
Keyword(s):  
Neural Networks ◽  
Resting State ◽  
Network Architecture ◽  
Brain Connectivity ◽  
Model Performance ◽  
Disease Diagnosis ◽  
General Purpose ◽  
Tissue Segmentation ◽  
Graph Neural Networks ◽  
Resting State Connectivity

Deep learning has been applied to magnetic resonance imaging (MRI) for a variety of purposes, ranging from the acceleration of image acquisition and image denoising to tissue segmentation and disease diagnosis. Convolutional neural networks have been particularly useful for analyzing MRI data due to the regularly sampled spatial and temporal nature of the data. However, advances in the field of brain imaging have led to network- and surface-based analyses that are often better represented in the graph domain. In this analysis, we propose a general purpose cortical segmentation method that, given resting-state connectivity features readily computed during conventional MRI pre-processing and a set of corresponding training labels, can generate cortical parcellations for new MRI data. We applied recent advances in the field of graph neural networks to the problem of cortical surface segmentation, using resting-state connectivity to learn discrete maps of the human neocortex. We found that graph neural networks accurately learn low-dimensional representations of functional brain connectivity that can be naturally extended to map the cortices of new datasets. After optimizing over algorithm type, network architecture, and training features, our approach yielded mean classification accuracies of 79.91% relative to a previously published parcellation. We describe how some hyperparameter choices including training and testing data duration, network architecture, and algorithm choice affect model performance.

scholarly journals Predicting nonverbal intelligence level from resting-state connectivity: a neural networks approach

2021 ◽  
Vol 1727 ◽  
pp. 012010
Author(s):  
S A Ivanov ◽  
I M Zakharov ◽  
I V Feklicheva ◽  
V I Ismatullina ◽  
N A Chipeeva ◽  
...  
Keyword(s):  
Neural Networks ◽  
Resting State ◽  
Nonverbal Intelligence ◽  
Intelligence Level ◽  
Resting State Connectivity

scholarly journals Interpretation of Swedish Sign Language Using Convolutional Neural Networks and Transfer Learning

2021 ◽  
Vol 2 (3) ◽  
Author(s):  
Gustaf Halvardsson ◽  
Johanna Peterson ◽  
César Soto-Valero ◽  
Benoit Baudry
Keyword(s):  
Neural Networks ◽  
Sign Language ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Web Application ◽  
Training Dataset ◽  
Motion Processing ◽  
Image Perception ◽  
Sign Languages ◽  
High Level

AbstractThe automatic interpretation of sign languages is a challenging task, as it requires the usage of high-level vision and high-level motion processing systems for providing accurate image perception. In this paper, we use Convolutional Neural Networks (CNNs) and transfer learning to make computers able to interpret signs of the Swedish Sign Language (SSL) hand alphabet. Our model consists of the implementation of a pre-trained InceptionV3 network, and the usage of the mini-batch gradient descent optimization algorithm. We rely on transfer learning during the pre-training of the model and its data. The final accuracy of the model, based on 8 study subjects and 9400 images, is 85%. Our results indicate that the usage of CNNs is a promising approach to interpret sign languages, and transfer learning can be used to achieve high testing accuracy despite using a small training dataset. Furthermore, we describe the implementation details of our model to interpret signs as a user-friendly web application.

Sign in / Sign up

Export Citation Format

Share Document