Filters








65 Hits in 12.0 sec

Graph Saliency Maps through Spectral Convolutional Networks: Application to Sex Classification with Brain Connectivity [article]

Salim Arslan, Sofia Ira Ktena, Ben Glocker, Daniel Rueckert
2018 arXiv   pre-print
Graph convolutional networks (GCNs) allow to apply traditional convolution operations in non-Euclidean domains, where data are commonly modelled as irregular graphs.  ...  Medical imaging and, in particular, neuroscience studies often rely on such graph representations, with brain connectivity networks being a characteristic example, while ultimately seeking the locus of  ...  This research has been conducted using the UK Biobank Resource under Application Number 12579 and funded by the EPSRC Doctoral Prize Fellowship funding scheme.  ... 
arXiv:1806.01764v1 fatcat:orqgczzaxzg75b4tup2dca5epq

Metric learning with spectral graph convolutions on brain connectivity networks

Sofia Ira Ktena, Sarah Parisot, Enzo Ferrante, Martin Rajchl, Matthew Lee, Ben Glocker, Daniel Rueckert
2018 NeuroImage  
Evaluating similarity between these brain connectivity networks in a manner that accounts for the graph structure and is tailored for a particular application is, however, non-trivial.  ...  traditional convolutions to irregular graphs and operates in the graph spectral domain.  ...  To the best of our knowledge, this has been 125 the first application of metric learning with spectral graph convolutions on brain connectivity networks.  ... 
doi:10.1016/j.neuroimage.2017.12.052 pmid:29278772 fatcat:ihthm266gbclpcm3eqq3tu2zmm

A Deep Graph Neural Network Architecture for Modelling Spatio-temporal Dynamics in resting-stating functional MRI Data [article]

Tiago Azevedo, Alexander Campbell, Rafael Romero-Garcia, Luca Passamonti, Richard A.I. Bethlehem, Pietro Lio, Nicola Toschi
2020 bioRxiv   pre-print
Herein we present a novel deep neural network architecture, combining both GNNs and temporal convolutional networks (TCNs), which is able to learn from the spatial and temporal components of rs-fMRI data  ...  Recently, graph neural networks (GNNs) have seen a surge in popularity due to their successes in modelling unstructured relational data.  ...  Rueckert, Graph saliency maps 577 through spectral convolutional networks: Application to sex classifica-578 tion with brain connectivity, in: Lecture Notes in Computer Science, 579 Springer International  ... 
doi:10.1101/2020.11.08.370288 fatcat:aogq724mrfholnzpoedqfwy7fu

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future [article]

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 arXiv   pre-print
As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interactive nodes connected by edges whose weights can be  ...  In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare.  ...  [199] introduced a spectral graph transformer (SGT) network to learn this transformation function across multiple brain surfaces directly in the spectral domain, mapping input spectral coordinates to  ... 
arXiv:2105.13137v1 fatcat:gm7d2ziagba7bj3g34u4t3k43y

Structure Can Predict Function in the Human Brain: A Graph Neural Network Deep Learning Model of Functional Connectivity and Centrality based on Structural Connectivity [article]

Josh Neudorf, Shaylyn Kress, Ron Borowsky
2021 bioRxiv   pre-print
Although functional connectivity and associated graph theory measures (e.g., centrality; how centrally important to the network a region is) are widely used in brain research, the full extent to which  ...  Graph neural network deep learning methods have not yet been applied for this purpose, and offer an ideal model architecture for working with connectivity data given their ability to capture and maintain  ...  Graph Saliency Maps Through Spectral 395 Convolutional Networks: Application to Sex Classification with Brain Connectivity, in: 396 Stoyanov, D., Taylor, Z., Ferrante, E., Dalca, A.V., Martel, A., Maier-Hein  ... 
doi:10.1101/2021.03.15.435531 fatcat:xbo5f4s5tjczzdaagwtnppbe2y

A Unified Framework for Personalized Regions Selection and Functional Relation Modeling for Early MCI Identification

Jiyeon Lee, Wonjun Ko, Eunsong Kang, Heung-Il Suk
2021 NeuroImage  
Furthermore, our method allows us to capture the functional relations of a subject-specific ROI subset through the use of a graph-based neural network.  ...  Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely adopted to investigate functional abnormalities in brain diseases.  ...  We implemented the network using two edge-to-edge layers with 10 output feature maps, one edge-to-node layer with 20 output feature maps, and one node-to-graph layer with 40 output feature maps, to train  ... 
doi:10.1016/j.neuroimage.2021.118048 pmid:33878379 fatcat:djdqfurbxfc4nmdk3ghefiwwum

Cyclic multiplex fluorescent immunohistochemistry and machine learning reveal distinct states of astrocytes and microglia in normal aging and Alzheimer's disease

Clara Muñoz-Castro, Ayush Noori, Colin G. Magdamo, Zhaozhi Li, Jordan D. Marks, Matthew P. Frosch, Sudeshna Das, Bradley T. Hyman, Alberto Serrano-Pozo
2022 Journal of Neuroinflammation  
Three distinct phenotypes emerged with our combination of markers, thus expanding the classic binary "homeostatic vs. reactive" classification to a third state, which could represent "transitional" or  ...  Machine learning models applied on either high-plex signal intensity data (gradient boosting machines) or directly on image features (convolutional neural networks) accurately discriminated control vs.  ...  Mezlini, PhD for helpful discussions on spectral clustering, and Tessa Connors, Angelica Gaona, and Patrick Dooley for technical support from the MADRC Brain Bank.  ... 
doi:10.1186/s12974-022-02383-4 pmid:35109872 pmcid:PMC8808995 fatcat:ambflhlltng2lk5pbrqqqohvdu

Deep learning-based electroencephalography analysis: a systematic review

Yannick Roy, Hubert Banville, Isabela Albuquerque, Alexandre Gramfort, Tiago H Falk, Jocelyn Faubert
2019 Journal of Neural Engineering  
Recently, deep learning (DL) has shown great promise in helping make sense of EEG signals due to its capacity to learn good feature representations from raw data.  ...  Whether DL truly presents advantages as compared to more traditional EEG processing approaches, however, remains an open question.  ...  Other techniques include Deeplift [97] , saliency maps [209] , input-feature unit-output correlation maps [167] , retrieval of closest examples [41] , analysis of performance with transferred layers  ... 
doi:10.1088/1741-2552/ab260c pmid:31151119 fatcat:tgb2o34h2zbx7jft2d6bqbkvlu

Artificial intelligence for the echocardiographic assessment of valvular heart disease

Rashmi Nedadur, Bo Wang, Wendy Tsang
2022 Heart  
Developments in artificial intelligence (AI) have led to an explosion of studies exploring its application to cardiovascular medicine.  ...  Measurements obtained during echocardiographic valvular assessment have been integrated with other clinical data to identify novel aortic valve disease subgroups and describe new predictors of aortic valve  ...  Measures such as saliency maps, which show which parts of the images are analysed for classification, can help the user understand how the algorithm functions. 43 Widespread AI implementation has also  ... 
doi:10.1136/heartjnl-2021-319725 pmid:35144983 fatcat:xu652vr2qncflppp5htd42zehm

2022 Roadmap on Neuromorphic Computing and Engineering [article]

Dennis V. Christensen, Regina Dittmann, Bernabé Linares-Barranco, Abu Sebastian, Manuel Le Gallo, Andrea Redaelli, Stefan Slesazeck, Thomas Mikolajick, Sabina Spiga, Stephan Menzel, Ilia Valov, Gianluca Milano (+47 others)
2022 arXiv   pre-print
learn or deal with complex data as our brain does.  ...  Among their potential future applications, an important niche is moving the control from data centers to edge devices.  ...  Concluding Remarks Integrating event-based vision sensing and processing with neuromorphic computation techniques is expected to yield solutions that will be able to penetrate the artificial vision market  ... 
arXiv:2105.05956v3 fatcat:pqir5infojfpvdzdwgmwdhsdi4

Neuroimaging-based biomarkers for pain

Maite M. van der Miesen, Martin A. Lindquist, Tor D. Wager
2019 PAIN Reports  
In particular, brain pathophysiology may be diagnosable with human brain imaging, particularly when imaging is combined with machine learning techniques designed to identify predictive measures embedded  ...  With the realization that biomarkers can reveal pain-causing mechanisms of disease in brain circuits and in the periphery, this situation is poised to change.  ...  connectivity across a set of regions, graph theoretic properties such as global network efficiency, and more.  ... 
doi:10.1097/pr9.0000000000000751 pmid:31579847 pmcid:PMC6727991 fatcat:dj4o5h2vtvcyvjchkjhgbhkzsq

Deep learning-based electroencephalography analysis: a systematic review [article]

Yannick Roy, Hubert Banville, Isabela Albuquerque, Alexandre Gramfort, Tiago H. Falk, Jocelyn Faubert
2019 arXiv   pre-print
As for the model, 40% of the studies used convolutional neural networks (CNNs), while 14% used recurrent neural networks (RNNs), most often with a total of 3 to 10 layers.  ...  In this work, we review 156 papers that apply DL to EEG, published between January 2010 and July 2018, and spanning different application domains such as epilepsy, sleep, brain-computer interfacing, and  ...  Other techniques include Deeplift [87] , saliency maps [190] , input-feature unit-output correlation maps [150] , retrieval of closest examples [34] , analysis of performance with transferred layers  ... 
arXiv:1901.05498v2 fatcat:5ugb4i3oerdrvarwozxvepbzxe

29th Annual Computational Neuroscience Meeting: CNS*2020

2020 BMC Neuroscience  
Selection starts in the primary visual cortex (V1), which creates a bottom-up saliency map to guide the fovea to selected visual locations via gaze shifts.  ...  Investigations of this question have, to date, focused largely on deep neural networks trained using supervised learning, in tasks such as image classification.  ...  Institute (Challenge grants to SJ), the Research Corporation for Science Advancement (a Cottrell SEED Award to TV), and the German Research Foundation (DFG grant #ME 1535/7-1 to RM), and the Foundation  ... 
doi:10.1186/s12868-020-00593-1 pmid:33342424 fatcat:edosycf35zfifm552a2aogis7a

25th Annual Computational Neuroscience Meeting: CNS-2016

Tatyana O. Sharpee, Alain Destexhe, Mitsuo Kawato, Vladislav Sekulić, Frances K. Skinner, Daniel K. Wójcik, Chaitanya Chintaluri, Dorottya Cserpán, Zoltán Somogyvári, Jae Kyoung Kim, Zachary P. Kilpatrick, Matthew R. Bennett (+597 others)
2016 BMC Neuroscience  
I will discuss theoretical results that point to functional advantages of splitting neural populations into subtypes, both in feedforward and recurrent networks.  ...  Such classification scheme could augment classification schemes based on molecular, anatomical, and electrophysiological properties.  ...  The funders had no role in study design, data collection and analysis, the decision to publish, or the preparation of the manuscript.  ... 
doi:10.1186/s12868-016-0283-6 pmid:27534393 pmcid:PMC5001212 fatcat:bt45etzj2bbolfcxlxo7hlv6ju

19th biennial IPEG Meeting

Igor Timofeev, Leon Kenemans, P. F. Fabene, A. Ahnaou, Sebastian Olbrich, Robert Oostenveld, Martijn Arns, Nash Boutros, Fernando Lopes da Silva, Igor Timofeev, Ole Jensen, Sandra K. Loo (+404 others)
2016 Neuropsychiatric Electrophysiology  
We implemented a convolutional neural network (CNN) in python with TensorFlow on a CentOS system with the NVIDIA GTX-1080 as GPU.  ...  Source estimates and connectivity measures were mapped using Low Resolution Brain Tomography (LORETA).  ...  Stimulation of α2A noradrenergic receptors on PFC spines by clonidine leads to strengthening of network connectivity, increase in neuronal PFC firing, and thus improves PFC regulation of sensory gating  ... 
doi:10.1186/s40810-016-0021-4 fatcat:iynffofbojdx3nspgskpizfwt4
« Previous Showing results 1 — 15 out of 65 results