Filters








54 Hits in 2.1 sec

Tractography filtering using autoencoders [article]

Jon Haitz Legarreta, Laurent Petit, François Rheault, Guillaume Theaud, Carl Lemaire, Maxime Descoteaux, Pierre-Marc Jodoin
2020 arXiv   pre-print
Our method, dubbed FINTA (Filtering in Tractography using Autoencoders) comes with several key advantages: training does not need labeled data, as it uses raw tractograms, it is fast and easily reproducible  ...  Together, this work brings forward a new deep learning framework in tractography based on autoencoders, and shows how it can be applied for filtering purposes.  ...  We have dubbed our method FINTA, Filtering in Tractography using Autoencoders.  ... 
arXiv:2010.04007v1 fatcat:3yn2r5oukbaovndjutr4ijokkm

Generative sampling in tractography using autoencoders (GESTA) [article]

Jon Haitz Legarreta and Laurent Petit and Pierre-Marc Jodoin and Maxime Descoteaux
2022 arXiv   pre-print
In this work, we propose a generative, autoencoder-based method, named GESTA (Generative Sampling in Tractography using Autoencoders), that produces streamlines with better spatial coverage.  ...  Current tractography methods use the local orientation information to propagate streamlines from seed locations.  ...  Figure 1 : Illustration of the GESTA (Generative Sampling in Tractography using Autoencoders) generative tractography pipeline using autoencoders.  ... 
arXiv:2204.10891v1 fatcat:knat37dg4zecrhbxpg4b24vqby

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
Specifically, we use a convolutional neural network to learn embeddings of input fibers, using pairwise fiber distances as pseudo annotations.  ...  White matter fiber clustering (WMFC) enables parcellation of white matter tractography for applications such as disease classification and anatomical tract segmentation.  ...  Tractography data were generated using a two-tensor unscented Kalman filter (UKF) method [19] , and tractography co-registration was performed using an affine followed by a nonrigid registration [24]  ... 
arXiv:2107.04938v1 fatcat:3fwbqf2n7vdhvjd6o4ttslwzqu

A Matrix Autoencoder Framework to Align the Functional and Structural Connectivity Manifolds as Guided by Behavioral Phenotypes [article]

Niharika Shimona D'Souza, Mary Beth Nebel, Deana Crocetti, Nicholas Wymbs, Joshua Robinson, Stewart Mostofsky, Archana Venkataraman
2021 arXiv   pre-print
The embedding is simultaneously used to reconstruct DTI tractography matrices via a second manifold alignment decoder and to predict inter-subject phenotypic variability via an artificial neural network  ...  Our specialized autoencoder infers a low dimensional manifold embedding for the rs-fMRI correlation matrices that mimics a canonical outer-product decomposition.  ...  DTI data was preprocessed using the FDT pipeline in FSL [18] , with tractography performed using the BEDPOSTx and PROBTRACKx functions in FSL [2] .  ... 
arXiv:2105.14409v2 fatcat:ra3xixhzjfdohg7tql624ql64a

StreamNet: A WAE for White Matter Streamline Analysis [article]

Andrew Lizarraga, Katherine L. Narr, Kristy A. Donald, Shantanu H. Joshi
2022 arXiv   pre-print
We present StreamNet, an autoencoder architecture for the analysis of the highly heterogeneous geometry of large collections of white matter streamlines.  ...  Experimental model performance is evaluated on white matter streamlines resulting from T1-weighted diffusion imaging of 40 healthy controls using recent state of the art bundle comparison metric that measures  ...  Whole brain tractography was performed using multi-shell multi-tissue constrained spherical deconvolution followed by filtering of the tractograms.  ... 
arXiv:2209.01498v1 fatcat:rhgzdq3h3rf7tbclajpzjmr5cu

Brain Network Constraints and Recurrent Neural Networks reproduce unique Trajectories and State Transitions seen over the span of minutes in resting state fMRI [article]

Amrit Kashyap, Shella Keilholz
2019 bioRxiv   pre-print
Moreover, it exhibits complex states and transitions as seen using k-Means analysis on windowed FC matrices.  ...  We believe that our technique will be useful in understanding the large-scale functional organization of the brain and how different BNMs recapitulate different aspects of the system dynamics.  ...  tractography.  ... 
doi:10.1101/798520 fatcat:rjympapiojb6bdxtovtrtcqqe4

Brain Network Constraints and Recurrent Neural Networks reproduce unique Trajectories and State Transitions seen over the span of minutes in resting state fMRI

Amrit Kashyap, Shella Keilholz
2020 Network Neuroscience  
Simulated data also contain unique repeating trajectories observed in rs-fMRI, called Quasi Periodic Patterns (QPP) that span 20 seconds and complex state transitions observed using k-Means analysis on  ...  The manuscript demonstrates that by using Recurrent Neural Networks, it can fit the BNM in a novel way to the rs-fMRI data and predict large amounts of variance between subsequent measures of rs-fMRI data  ...  Christopher Rozell for his insightful discussion on the interpretation of the autoencoder. AUTHOR CONTRIBUTIONS  ... 
doi:10.1162/netn_a_00129 pmid:32537536 pmcid:PMC7286308 fatcat:gkl5smssqratzoxjo36u46k7iu

FiberNeat: unsupervised streamline clustering and white matter tract filtering in latent space [article]

Bramsh Qamar Chandio, Tamoghna Chattopadhyay, Conor Owens-Walton, Julio E Villalon Reina, Leila Nabulsi, Sophia I Thomopoulos, Eleftherios Garyfallidis, Paul M Thompson
2021 bioRxiv   pre-print
This approach can be deployed as a filtering step after tracts are extracted.  ...  In addition, outlier streamline clusters are detected using DBSCAN and then removed from the data in streamline space.  ...  It does not depend on training data or an atlas as compared to recently proposed methods for tractography filtering using deep learning [24] , [25] .  ... 
doi:10.1101/2021.10.26.465991 fatcat:wodrdxeoujfgxpsnuaiwfljwgy

Unified Embeddings of Structural and Functional Connectome via a Function-Constrained Structural Graph Variational Auto-Encoder [article]

Carlo Amodeo, Igor Fortel, Olusola Ajilore, Liang Zhan, Alex Leow, Theja Tulabandhula
2022 arXiv   pre-print
With the advent of connectomics, the primary graphs or networks of interest are structural connectome (derived from DTI tractography) and functional connectome (derived from resting-state fMRI).  ...  To this end, we propose a function-constrained structural graph variational autoencoder (FCS-GVAE) capable of incorporating information from both functional and structural connectome in an unsupervised  ...  Graph Variational Autoencoder Variational Autoencoder (VAE) [7] is a variant of deep generative models used for learning latent representations from an unlabeled dataset by simultaneously training an  ... 
arXiv:2207.02328v1 fatcat:jtxrgdeajzga5mrikv5sacvub4

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
stereotactic body radiation therapy 638 A probabilistic model combining deep learning and multi-atlas segmentation for semi-automated labelling of histology Better Fiber ODFs From Suboptimal Data With Autoencoder  ...  Squeeze & Excitation in Fully Convolutional Networks 578 Learning Myelin Content in Multiple Sclerosis from Multimodal MRI through Adversarial Training 584 Edema-informed anatomically constrained particle filter  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Dynamic Oscillations Evoked by Subcallosal Cingulate Deep Brain Stimulation

Vineet Tiruvadi, Vineet Tiruvadi, Vineet Tiruvadi, Ki Sueng Choi, Robert E. Gross, Robert E. Gross, Robert Butera, Robert Butera, Viktor Jirsa, Helen Mayberg
2022 Frontiers in Neuroscience  
In this study we used novel intracranial recordings (LFP) in n = 6 depressed patients stimulated with DBS around the SCCwm target, observing a novel dynamic oscillation (DOs).  ...  SINDy uses an autoencoder architecture to build a generative model of the dynamics, or time evolution, of a set of timeseries.  ...  Mean tractography was then calculated across all VTA using NILearn (Abraham et al., 2014) , yielding an average map for OnTarget and OffTarget conditions in each patient.  ... 
doi:10.3389/fnins.2022.768355 pmid:35281513 pmcid:PMC8905359 doaj:a584c80ab94b4b6f95998062fee8abe4 fatcat:7jmv26octjcy3e44y6l7ugvo3u

Auto-encoded Latent Representations of White Matter Streamlines for Quantitative Distance Analysis [article]

Shenjun Zhong, Zhaolin Chen, Gary Egan
2021 bioRxiv   pre-print
To resolve these issues, we proposed a novel atlas-free method that learnt a latent space using a deep recurrent autoencoder which efficiently embedded any lengths of streamlines to fixed-size feature  ...  The method is evaluated on the ISMRM 2015 tractography challenge dataset, and shows the ability to discriminate major bundles with unsupervised clustering and query streamline based on similarity.  ...  This finding highlights that the proposed technique can filter false streamlines generated in the tractography process as embedded streamline are spatially separable in the latent space.  ... 
doi:10.1101/2021.10.06.463445 fatcat:2j5oj46llbdy7h4vkqizvpsko4

Visualization and Processing of Anisotropy in Imaging, Geometry, and Astronomy (Dagstuhl Seminar 18442)

Andrea Fuster, Evren Özarslan, Thomas Schultz, Eugene Zhang, Michael Wagner
2019 Dagstuhl Reports  
Crease Enhancement Using MAFOD Filter Diffusion magnetic resonance imaging (dMRI) provides the opportunity to non-invasively obtain measures that relate to the human brain tissue microstructure.  ...  For this purpose, we propose a multi-scale anisotropic fourth-order diffusion (MAFOD) filter that performs better than the other existing isotropic and anisotropic fourth-order filters.  ...  Algorithms for image deconvolution could be used for this purpose. Participants  ... 
doi:10.4230/dagrep.8.10.148 dblp:journals/dagstuhl-reports/FusterO0Z18 fatcat:mlcgmrzo5fexfikbsmtpt5wwzy

Equivariant Spherical Deconvolution: Learning Sparse Orientation Distribution Functions from Spherical Data [article]

Axel Elaldi, Neel Dey, Heejong Kim, Guido Gerig
2021 arXiv   pre-print
We then show improved downstream performance on fiber tractography measures on the Tractometer benchmark dataset.  ...  Finally, we show downstream improvements in terms of tractography and partial volume estimation on a multi-shell dataset of human subjects.  ...  Patel et al. use an autoencoder pretrained for fODF reconstruction as a regularizer for the MSMT-CSD optimization problem [13] .  ... 
arXiv:2102.09462v1 fatcat:d67bxm7jq5ch3p63k4s3q5dd3a

Computer Vision in Healthcare Applications

Junfeng Gao, Yong Yang, Pan Lin, Dong Sun Park
2018 Journal of Healthcare Engineering  
Gargiulo et al. in Iceland "New Directions in 3D Medical Modeling: 3D-Printing Anatomy and Functions in Neurosurgical Planning" combine CT and MRI images with DTI tractography and use image segmentation  ...  In addition, the extended neighborhood model is used to increase the filter denoising ability, which is based on von Neumann concept derived from cellular automata theory.  ... 
doi:10.1155/2018/5157020 pmid:29686826 pmcid:PMC5857319 fatcat:nouvaymmrbgircnal6irb2nynq
« Previous Showing results 1 — 15 out of 54 results