Filters








8,819 Hits in 2.9 sec

Spectral Graph Transformer Networks for Brain Surface Parcellation [article]

Ran He, Karthik Gopinath, Christian Desrosiers, Herve Lombaert
2019 arXiv   pre-print
The analysis of the brain surface modeled as a graph mesh is a challenging task. Conventional deep learning approaches often rely on data lying in the Euclidean space.  ...  This paper presents a novel approach for learning the transformation matrix required for aligning brain meshes using a direct data-driven approach.  ...  Acknowledgment -This work was supported financially by the MITACS Globalink Internship Program, the Fonds de Recherche du Quebec (FQRNT), the Research Council of Canada (NSERC) and NVIDIA with the donation of a  ... 
arXiv:1911.10118v1 fatcat:lqmz45olabdddiqjx66fjcv76y

Deep Fiber Clustering: Anatomically Informed Unsupervised Deep Learning for Fast and Effective White Matter Parcellation [article]

Yuqian Chen, Chaoyi Zhang, Yang Song, Nikos Makris, Yogesh Rathi, Weidong Cai, Fan Zhang, Lauren J. O'Donnell
2021 arXiv   pre-print
We propose a novel WMFC framework based on unsupervised deep learning. We solve the unsupervised clustering problem as a self-supervised learning task.  ...  Specifically, we use a convolutional neural network to learn embeddings of input fibers, using pairwise fiber distances as pseudo annotations.  ...  Therefore, besides the classical autoencoder network, the self-supervised learning framework can also be a promising approach to learn deep embeddings of inputs.  ... 
arXiv:2107.04938v1 fatcat:3fwbqf2n7vdhvjd6o4ttslwzqu

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.  ...  We illustrate the benefits of this approach with an application to brain parcellation. We validate the algorithm over 101 manually labeled brain surfaces.  ...  We illustrate the learning capabilities of this approach with an application to brain parcellation.  ... 
arXiv:1803.10336v1 fatcat:mvcxhzeuqzcvdolw3j3n4t3lxm

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

Karthik Gopinath, Christian Desrosiers, Herve Lombaert
2020 arXiv   pre-print
This novel approach comprises a segmentator that uses a set of graph convolution layers to enable parcellation directly across brain surfaces in a source domain, and a discriminator that predicts a graph  ...  More precisely, the proposed adversarial network learns to generalize a parcellation across both, source and target domains.  ...  A recent work [19] proposed to use geometric deep learning for segmenting three cortical regions by relying on the spatial representation of the brain mesh.  ... 
arXiv:2004.00074v1 fatcat:fi5psaaorzarrgsix2aabuceni

Deep Learning Based Pipeline for Fingerprinting Using Brain Functional MRI Connectivity Data

Nicolás F. Lori, Ivo Ramalhosa, Paulo Marques, Victor Alves
2018 Procedia Computer Science  
In this work we describe an appropriate pipeline for using deep-learning as a form of improving the brain functional connectivitybased fingerprinting process which is based in functional Magnetic Resonance  ...  with a 50 Nodes parcellation which had an accuracy of 0.237.  ...  The major novelty in our approach is the use of Deep Neuronal Networks (DNN), which uses Artificial Neural Networks (ANN) for modelling, to these standard rs-fMRIbased FC data, to achieve a better classification  ... 
doi:10.1016/j.procs.2018.10.129 fatcat:3k3iswonhrcd3cogeuonmnv4i4

Computational neuroanatomy of baby brains: A review

Gang Li, Li Wang, Pew-Thian Yap, Fan Wang, Zhengwang Wu, Yu Meng, Pei Dong, Jaeil Kim, Feng Shi, Islem Rekik, Weili Lin, Dinggang Shen
2018 NeuroImage  
A comprehensive review of infant-dedicated computational methods and tools 2. A discussion of contributions to the understanding of infant brain development 3.  ...  To address these challenges, many infant-tailored computational methods have been proposed for computational neuroanatomy of infant brains.  ...  According to features used, we divided learning-based approaches into hand-crafted features based approaches and deep learning based approaches.  ... 
doi:10.1016/j.neuroimage.2018.03.042 pmid:29574033 pmcid:PMC6150852 fatcat:w2o27wt5afhktd7zoophmhnmi4

Harnessing networks and machine learning in neuropsychiatric care

Eli J Cornblath, David M Lydon-Staley, Danielle S Bassett
2019 Current Opinion in Neurobiology  
The development of next-generation therapies for neuropsychiatric illness will likely rely on a precise and accurate understanding of human brain dynamics.  ...  For simplicity, we will refer to large cross-sectional neuroimaging studies as broad studies and to intensive longitudinal studies as deep studies.  ...  Typical approaches for 'parcellation,' -obtaining representative signals within anatomically [52] or functionally [33] similar regions or 'parcels' -tend to rely on registering brain images to a common  ... 
doi:10.1016/j.conb.2018.12.010 pmid:30641443 pmcid:PMC6839408 fatcat:wzxhhmtu4bbotbiv44pps55ciq

Improving Individual Brain Age Prediction Using an Ensemble Deep Learning Framework

Chen-Yuan Kuo, Tsung-Ming Tai, Pei-Lin Lee, Chiu-Wang Tseng, Chieh-Yu Chen, Liang-Kung Chen, Cheng-Kuang Lee, Kun-Hsien Chou, Simon See, Ching-Po Lin
2021 Frontiers in Psychiatry  
Recently, several end-to-end deep learning (DL) analytical frameworks have been proposed as alternative approaches to predict individual brain age with higher accuracy.  ...  In summary, this study provides initial evidence of how-to efficiency for integrating ML and advanced DL approaches into a unified analytical framework for predicting individual brain age with higher accuracy  ...  The author would like to thank NVIDIA AI Technology Center (NVAITC) for discussing and training deep learning approaches.  ... 
doi:10.3389/fpsyt.2021.626677 pmid:33833699 pmcid:PMC8021919 fatcat:24pip26yrba3la4sxydbokjxhe

Brain Morphometry Estimation: From Hours to Seconds Using Deep Learning

Michael Rebsamen, Yannick Suter, Roland Wiest, Mauricio Reyes, Christian Rummel
2020 Frontiers in Neurology  
We propose a deep learning-based approach to predict the volumes of anatomically delineated subcortical regions of interest (ROI), and mean thicknesses and curvatures of cortical parcellations directly  ...  Conclusions: We demonstrate the general feasibility of using deep learning to estimate human brain morphometry directly from T1-weighted MRI within seconds.  ...  ACKNOWLEDGMENTS The authors thank the NVIDIA Corporation for the donation of a Titan Xp GPU. Calculations were partially performed on UBELIX, the HPC cluster at the University of Bern.  ... 
doi:10.3389/fneur.2020.00244 pmid:32322235 pmcid:PMC7156625 fatcat:x2d4ouztqbdjhp3pztlr3epppi

DFC: Anatomically Informed Fiber Clustering with Self-supervised Deep Learning for Fast and Effective Tractography Parcellation [article]

Yuqian Chen, Chaoyi Zhang, Tengfei Xue, Yang Song, Nikos Makris, Yogesh Rathi, Weidong Cai, Fan Zhang, Lauren J. O'Donnell
2022 arXiv   pre-print
While widely used WMFC approaches have shown good performance using classical machine learning techniques, recent advances in deep learning reveal a promising direction towards fast and effective WMFC.  ...  In this work, we propose a novel deep learning framework for WMFC, Deep Fiber Clustering (DFC), which solves the unsupervised clustering problem as a self-supervised learning task with a domain-specific  ...  Pretraining with Self-supervised Deep Embedding In the pretraining stage, we propose a novel self-supervised learning approach to obtain deep embeddings of fibers.  ... 
arXiv:2205.00627v1 fatcat:janyxulyqzepxcyk27r77vv7ua

Morphometric and Functional Brain Connectivity Differentiates Chess Masters from Amateur Players [article]

Harish RaviPrakash, Syed Muhammad Anwar, Nadia M. Biassou, Ulas Bagci
2020 bioRxiv   pre-print
Moreover, we quantitatively validate an existing neuroscience hypothesis that learning a certain skill could cause a change in the brain (functional connectivity and anatomy) and this can be tested via  ...  Towards this end, we look at a dataset of amateur and professional chess players, where we utilize resting-state functional magnetic resonance images to generate functional connectivity (FC) information  ...  It was hypothesized that even short-term skill acquisition, such as learning to juggle for three months, can lead towards detectable changes in the human brain 16 .  ... 
doi:10.1101/2020.09.18.303685 fatcat:vsw45uaepverdnti5fua472xw4

Automated brainstem parcellation using multi-atlas segmentation and deep neural network [article]

Magnus Magnusson, Askell Love, Lotta M. Ellingsen
2021 arXiv   pre-print
Here we present a joint multi-atlas-segmentation and deep-learning-based segmentation method for fast and robust parcellation of the brainstem into its four sub-structures, i.e., the midbrain, pons, medulla  ...  More detailed characterization of brain atrophy due to individual diseases is urgently required to select biomarkers and therapeutic targets that are meaningful to each disease.  ...  This first step provides a segmentation of the whole brain, including the brainstem as one unit. Then the brainstem module is run to get the separate brainstem parcellation.  ... 
arXiv:2102.03281v1 fatcat:jmxaw6sghjcddfak5lhdmsxgha

Morphometric and Functional Brain Connectivity Differentiates Chess Masters From Amateur Players

Harish RaviPrakash, Syed Muhammad Anwar, Nadia M. Biassou, Ulas Bagci
2021 Frontiers in Neuroscience  
Moreover, we quantitatively validate an existing neuroscience hypothesis that learning a certain skill could cause a change in the brain (functional connectivity and anatomy) and this can be tested via  ...  Toward this end, we look at a dataset of amateur and professional chess players, where we utilize resting-state functional magnetic resonance images to generate functional connectivity (FC) information  ...  All authors significantly contributed to the design, analysis, and evaluation of the proposed method and results. All authors reviewed the manuscript and agreed on the final version.  ... 
doi:10.3389/fnins.2021.629478 pmid:33679310 pmcid:PMC7933502 fatcat:ykxrfzamffb2zmpegoalzlean4

Learnable Pooling in Graph Convolution Networks for Brain Surface Analysis [article]

Karthik Gopinath, Christian Desrosiers, Herve Lombaert
2019 arXiv   pre-print
These facilitate the learning of surface data, yet pooling strategies often remain constrained to a single fixed-graph.  ...  Our experiments demonstrate the superiority of our learnable pooling approach compared to other pooling techniques for graph convolution networks, with results improving the state-of-the-art in brain surface  ...  Acknowledgment -This work is supported by the Research Council of Canada (NSERC), NVIDIA Corporation with the donation of a Titan Xp GPU.  ... 
arXiv:1911.10129v1 fatcat:gq6eekjux5b37jwekcrjjdieom

Functional connectivity-based parcellation of amygdala using self-organized mapping: A data driven approach

Arabinda Mishra, Baxter P. Rogers, Li Min Chen, John C. Gore
2013 Human Brain Mapping  
We hypothesize that similarity of functional connectivity of subregions with other parts of the brain can be a potential basis to segment and cluster voxels using data driven approaches.  ...  Although amygdala contains several nuclei whose distinct roles are implicated in various functions, our objective approach discerns at least two functionally distinct volumes comparable to previous parcellation  ...  The authors are thankful to Dr. Allen Newton and Kevin Wilson for their support in designing the software (SPM tool box) to perform the analysis.  ... 
doi:10.1002/hbm.22249 pmid:23418140 pmcid:PMC3919874 fatcat:dqyn5bxeffaztazbdfeu2kmks4
« Previous Showing results 1 — 15 out of 8,819 results