17,887 Hits in 4.7 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
Driven by this, we explore GCNs for the task of ROI identification and propose a visual attribution method based on class activation mapping.  ...  By undertaking a sex classification task as proof of concept, we show that this method can be used to identify salient nodes (brain regions) without prior node labels.  ...  As proof of concept, we undertake a sex classification task on functional connectivity networks, since there is previous evidence for sex-related differences in brain connectivity [3] .  ... 
arXiv:1806.01764v1 fatcat:orqgczzaxzg75b4tup2dca5epq

Graph Domain Adaptation for Alignment-Invariant Brain Surface Segmentation [article]

Karthik Gopinath, Christian Desrosiers, Herve Lombaert
2020 arXiv   pre-print
The varying cortical geometry of the brain creates numerous challenges for its analysis.  ...  Adversarial training is widely used for domain adaptation to improve the segmentation performance across domains.  ...  We gratefully acknowledge the support of NVIDIA Corporation for the donation of the Titan X Pascal GPU used for this research.  ... 
arXiv:2004.00074v1 fatcat:fi5psaaorzarrgsix2aabuceni

4D Attention-based Neural Network for EEG Emotion Recognition [article]

Guowen Xiao, Mengwen Ye, Bowen Xu, Zhendi Chen, Quansheng Ren
2021 arXiv   pre-print
The experimental results have shown the effectiveness of the attention mechanisms in different domains for EEG emotion recognition.  ...  Then, the proposed 4D-aNN adopts spectral and spatial attention mechanisms to adaptively assign the weights of different brain regions and frequency bands, and a convolutional neural network (CNN) is utilized  ...  RGNN considers the biological topology among different brain regions, reaching 94.24% on classification accuracy. 4D-CRNN takes 4D DE feature maps containing spatial, spectral, and temporal information  ... 
arXiv:2101.05484v1 fatcat:kdqrfcvlhjc4zfupjhg2woktgq

Graph Convolutions on Spectral Embeddings: Learning of Cortical Surface Data [article]

Karthik Gopinath, Christian Desrosiers, Herve Lombaert
2018 arXiv   pre-print
For instance, the widely used FreeSurfer takes about 3 hours to parcellate brain surfaces on a standard machine.  ...  Surface bases are indeed incompatible between brain geometries. This paper leverages recent advances in spectral graph matching to transfer surface data across aligned spectral domains.  ...  To do so, we compare the classification accuracy on 32 cortical parcels when running our algorithm, respectively, in the Euclidean and Spectral domains.  ... 
arXiv:1803.10336v1 fatcat:mvcxhzeuqzcvdolw3j3n4t3lxm

An automatic unsupervised classification of MR images in Alzheimer's disease

Xiaojing Long, Chris Wyatt
2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
The spectral embedding algorithm is performed based on the Riemannian distance matrix to project images onto a low-dimensional space where each image is represented as a point and its neighboring points  ...  In this paper, we propose an automatic unsupervised classification approach to distinguish brain magnetic resonance (MR) images of AD patients from those of elderly normal controls.  ...  Figure 1 . 1 Classification on dataset using the whole-brain distances.  ... 
doi:10.1109/cvpr.2010.5540031 dblp:conf/cvpr/LongW10 fatcat:6kphx7nuhve67andshzekf2xda

Automatic Response Assessment in Regions of Language Cortex in Epilepsy Patients Using ECoG-based Functional Mapping and Machine Learning [article]

Harish RaviPrakash, Milena Korostenskaja, Eduardo Castillo, Ki Lee, James Baumgartner, Ulas Bagci
2017 arXiv   pre-print
Accurate localization of brain regions responsible for language and cognitive functions in Epilepsy patients should be carefully determined prior to surgery.  ...  Electrocorticography (ECoG)-based Real Time Functional Mapping (RTFM) has been shown to be a safer alternative to the electrical cortical stimulation mapping (ESM), which is currently the clinical/gold  ...  Brunner for providing their in-house built version of BCI2000-based software for ECoG recording and for their continued support of our ECoG-related studies.  ... 
arXiv:1706.01380v2 fatcat:icucma3v3zc7dhkraci7ituu44

Cognitive state classification using transformed fMRI data [article]

Hariharan Ramasangu, Neelam Sinha
2016 arXiv   pre-print
One approach, for understanding human brain functioning, is to analyze the changes in the brain while performing cognitive tasks.  ...  The corresponding classification accuracy stands at 96.8% and 97.5% for Fourier transformed data. For Hilbert transformed data, it is 93.7% and 99%, for 6 subjects, on 2 cognitive tasks.  ...  The raw voxel data has been transformed by random sieve function before mapped to Fourier and Hilbert domains.  ... 
arXiv:1604.05413v1 fatcat:i2pc3iunz5fmljf2mmy26ql57i

Spectral Graph Transformer Networks for Brain Surface Parcellation [article]

Ran He, Karthik Gopinath, Christian Desrosiers, Herve Lombaert
2019 arXiv   pre-print
The novel Spectral Graph Transformer (SGT) network proposed in this paper uses very few randomly sub-sampled nodes in the spectral domain to learn the alignment matrix for multiple brain surfaces.  ...  However, the spectral decomposition across different brain graphs causes inconsistencies between the eigenvectors of individual spectral domains, causing the graph learning algorithm to fail.  ...  These methods, however, involve an explicit computation of a transformation map for each brain towards one reference template.  ... 
arXiv:1911.10118v1 fatcat:lqmz45olabdddiqjx66fjcv76y

Inferring Brain Dynamics via Multimodal Joint Graph Representation EEG-fMRI [article]

Jalal Mirakhorli
2022 arXiv   pre-print
Determining overlaps can provide a new perspective for diagnosing functional changes in neuroplasticity studies.  ...  Graph-based analyzes, which have many similarities to brain structure, can overcome the complexities of brain mapping analysis.  ...  The spectral analysis of the graph signals relies on the graph Laplacian, which maps the signal distributions from the spatial domain to the graph spectral domain and decomposes the signals into a series  ... 
arXiv:2201.08747v1 fatcat:ia72xmqjrraj3h6pjt2iyf372e

Lesion detection using Gabor-based saliency field mapping

Marc Macenko, Rutao Luo, Mehmet Celenk, Limin Ma, Qiang Zhou, Josien P. W. Pluim, Joseph M. Reinhardt
2007 Medical Imaging 2007: Image Processing  
The proposed algorithm was tested on different images of "The Whole Brain Atlas" database. 8 The experimental results have produced 93% classification accuracy in processing 100 arbitrary images, representing  ...  different kinds of brain lesion.  ...  The spectrally estimated 2D signal is then converted to the spatial domain to find the abnormalities present in the brain. Sections 2.1 and 2.2 provide further discussion on this process.  ... 
doi:10.1117/12.706431 dblp:conf/miip/MacenkoLCMZ07 fatcat:wbb4bh2ryjdtfcx7jpzxhamv4q

Signal processing techniques for motor imagery brain computer interface: A review

Swati Aggarwal, Nupur Chugh
2019 Array  
This paper provides a comprehensive review of dominant feature extraction methods and classification algorithms in brain-computer interface for motor imagery tasks.  ...  Authors discuss existing challenges in the domain of motor imagery brain-computer interface and suggest possible research directions.  ...  In feature extraction phase the EEG signal acquired for MI BCI reveals task-specific features in both spectral domain and spatial domain [20] .  ... 
doi:10.1016/j.array.2019.100003 fatcat:tlkzqreshzgfpeusxub3f5h4bq

Tensor-driven extraction of developmental features from varying paediatric EEG datasets [article]

Eli Kinney-Lang, Loukianos Spyrou, Ahmed Ebied, Richard FM Chin, Javier Escudero
2017 arXiv   pre-print
SVM classification accuracy and misclassification costs were improved significantly for both healthy and impaired paediatric populations. t-SNE maps revealed suitable tensor factorization was key in extracting  ...  (t-SNE) maps complemented classification analysis through visualization of the high-dimensional feature structures.  ...  The authors also thank Ephrem Zewdie for his comments and suggestions on figures.  ... 
arXiv:1712.07443v1 fatcat:s4bpd622ojffjeu66e54mll77u

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

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 Sensors  
We provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure, and electrical-based analysis.  ...  We also outline the limitations of existing techniques and discuss potential directions for future research.  ...  [154] 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  ... 
doi:10.3390/s21144758 fatcat:jytyt4u2pjgvhnhcto3vcvd3a4

Distance Metric Learning Using Graph Convolutional Networks: Application to Functional Brain Networks [chapter]

Sofia Ira Ktena, Sarah Parisot, Enzo Ferrante, Martin Rajchl, Matthew Lee, Ben Glocker, Daniel Rueckert
2017 Lecture Notes in Computer Science  
In this problem, the definition of an appropriate graph similarity function is critical to unveil patterns of disruptions associated with certain brain disorders.  ...  We demonstrate the potential of our method in the field of connectomics, where neuronal pathways or functional connections between brain regions are commonly modelled as graphs.  ...  Spectral graph theory makes this generalisation feasible by defining filters in the graph spectral domain.  ... 
doi:10.1007/978-3-319-66182-7_54 fatcat:ydvxdnwacjf5vdoa4dbnfavp7e

On the Spatial Distribution of Temporal Complexity in Resting State and Task Functional MRI

Amir Omidvarnia, Raphaël Liégeois, Enrico Amico, Maria Giulia Preti, Andrew Zalesky, Dimitri Van De Van De Ville
2022 Entropy  
For the significance thresholding of brain complexity maps, we used a statistical framework based on graph signal processing that incorporates the structural connectome to develop the null distributions  ...  Measuring the temporal complexity of functional MRI (fMRI) time series is one approach to assess how brain activity changes over time.  ...  Acknowledgments: A.O. would like to thank Simon Eickhoff and Kaustubh Patil for their support. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/e24081148 pmid:36010812 pmcid:PMC9407401 fatcat:djxlwmzpdbcnlf4gowyl224w2i
« Previous Showing results 1 — 15 out of 17,887 results