A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
MISPEL: A deep learning approach for harmonizing multi-scanner matched neuroimaging data
[article]
2022
bioRxiv
pre-print
Preserved Fulltext
In this study, we propose MISPEL (Multi-scanner Image harmonization via Structure Preserving Embedding Learning), a supervised multi-scanner harmonization method. ...
Large-scale data obtained from the aggregation of already collected multi-site neuroimaging datasets has brought benefits such as higher statistical power, reliability, and robustness to the studies. ...
In this work, we present MISPEL (Multi-scanner Image harmonization via Structure Preserving Embedding Learning), which is a supervised multi-scanner harmonization method that maps images of scanners to ...
doi:10.1101/2022.07.27.501786
fatcat:jmf53eppc5eqtlcsskuufwgcd4
Style Transfer Using Generative Adversarial Networks for Multi-Site MRI Harmonization
[article]
2021
bioRxiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Large data initiatives and high-powered brain imaging analyses require the pooling of MR images acquired across multiple scanners, often using different protocols. ...
We trained our model using data from five large-scale multi-site datasets with varied demographics. ...
Acknowledgements: the NIMH Data Archive (NDA). (which was not certified by peer review) is the author/funder. All rights reserved. No reuse allowed without permission. ...
doi:10.1101/2021.03.17.435892
fatcat:gb2lpds5jnd6do4xlay4nfogcy
Alzheimer's Disease Classification Accuracy is Improved by MRI Harmonization based on Attention-Guided Generative Adversarial Networks
[article]
2021
bioRxiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To test this, we used an Attention-Guided Generative Adversarial Network (GAN) to harmonize images from three publicly available brain MRI datasets - ADNI, AIBL and OASIS - adjusting for scanner-dependent ...
Even so, MRI scanning protocols and scanners differ across studies. ...
harmonized data for any pair of individuals and scanners. 19 In this work, we examined whether adversarial domain adaptation can boost the performance of a CNN model that is designed to classify Alzheimer's ...
doi:10.1101/2021.07.26.453862
fatcat:aeroztllovgannlmgcz6w5wrla
Riemannian Geometry of Functional Connectivity Matrices for Multi-Site Attention-Deficit/Hyperactivity Disorder Data Harmonization
2022
Frontiers in Neuroinformatics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The use of multi-site datasets in neuroimaging provides neuroscientists with more statistical power to perform their analyses. ...
This represents an advance with respect to previous functional connectivity data harmonization approaches, which do not respect the geometric constraints imposed by the underlying structure of the manifold ...
Given the need for large cohorts to carry out statistical studies, together with the advent of big data and machine learning, neuroimaging datasets have increased their size usually by collecting data ...
doi:10.3389/fninf.2022.769274
pmid:35685944
pmcid:PMC9171428
fatcat:bubfgpzql5abhj7za7qgzweraq
Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods
2021
Journal of Personalized Medicine
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Radiomics converts medical images into mineable data via a high-throughput extraction of quantitative features used for clinical decision support. ...
We also reflect upon the importance of deep learning solutions for addressing variability across multi-centric radiomic studies especially using generative adversarial networks (GANs), neural style transfer ...
On the other hand, ComBat tries to get rid of the 'batch effects' (or scanner/protocol variability) by shifting data distributions while also preserving the biological variation in the data under analysis ...
doi:10.3390/jpm11090842
pmid:34575619
fatcat:2ngorzmaw5alrpj7deecvvf4au
Riemannian geometry of functional connectivity matrices for multi-site attention-deficit/hyperactivity disorder data harmonization
[article]
2021
bioRxiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The use of multi-site datasets in neuroimaging provides neuroscientists with more statistical power to perform their analyses. ...
This represents an advance with respect to previous functional connectivity data harmonization approaches, which do not respect the geometric constraints imposed by the underlying structure of the manifold ...
Given the need for large cohorts to carry out statistical studies, together with the advent of big data and machine learning, neuroimaging datasets have increased their size usually by collecting data ...
doi:10.1101/2021.09.01.458579
fatcat:5hvkthsbxndvhow47w3zyclary
Applications of Deep Learning to Neuro-Imaging Techniques
2019
Frontiers in Neurology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This article will address this topic and will seek to present an overview of deep learning applied to neuroimaging techniques. ...
/harmonizing images, improving image quality, lowering radiation and contrast dose, and shortening the duration of imaging studies. ...
It is a type of representation learning in which the algorithm learns a composition of features that reflect a hierarchy of structures in the data (18) . ...
doi:10.3389/fneur.2019.00869
pmid:31474928
pmcid:PMC6702308
fatcat:yki64mb57jhafduasd3hohfkgi
Decoding brain states on the intrinsic manifold of human brain dynamics across wakefulness and sleep
[article]
2021
bioRxiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Here we present a novel method to reveal the low dimensional intrinsic manifold underlying human brain dynamics, which is invariant of the high dimensional spatio-temporal representation of the neuroimaging ...
By applying this novel intrinsic manifold framework to fMRI data acquired in wakefulness and sleep, we reveal the nonlinear differences between wakefulness and three different sleep stages, and successfully ...
Acknowledgments J.R.Q. is funded by the Fundació Catalunya -La Pedrera Masters of Excellence ...
doi:10.1101/2021.03.23.436551
fatcat:ufhayvi67fhzxdv6nti2htx22e
The Human Connectome Project: A Retrospective
2021
NeuroImage
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
generation of neuroimagers. ...
multimodal MRI and MEG data of unprecedented quality together with behavioral measures from more than 1100 HCP participants, and 3) freely sharing the data (via the ConnectomeDB database) and associated ...
Acknowledgements We thank the many members of the WU-Minn-Ox HCP Consortium for their dedicated efforts on this project and the HCP-style projects that have followed. ...
doi:10.1016/j.neuroimage.2021.118543
pmid:34508893
fatcat:qzxs43vy7reavhdqkn2f5yhw6u
Big data sharing and analysis to advance research in post-traumatic epilepsy
2018
Neurobiology of Disease
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We describe the infrastructure and functionality for a centralized preclinical and clinical data repository and analytic platform to support importing heterogeneous multi-modal data, automatically and ...
Highlights: We have created the infrastructure for a centralized data repository for multi-modal data Innovative image and electrophysiology processing methods have been applied Novel analytic tools ...
., 2012) to be used on the clinical data in this study. DTI is used to extract connectivity between all pairs of gyral and sulcal structures in the presence of brain trauma. ...
doi:10.1016/j.nbd.2018.05.026
pmid:29864492
pmcid:PMC6274619
fatcat:hgn4qtkzhjag7oseeeqhz72pl4
A review of deep learning in medical imaging: Image traits, technology trends, case studies with progress highlights, and future promises
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
It is known that the success of AI is mostly attributed to the availability of big data with annotations for a single task and the advances in high performance computing. ...
We cover the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, etc. ...
In [46] , domain-invariant features are learned via an adversarial mechanism that attempts to classify the domain of the input data. Zhang et al. ...
arXiv:2008.09104v1
fatcat:z2gic7or4vgnnfcf4joimjha7i
A novel relational regularization feature selection method for joint regression and classification in AD diagnosis
2017
Medical Image Analysis
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
into a sparse multi-task learning framework. ...
Specifically, the relational information includes three kinds of relationships (such as feature-feature relation, response-response relation, and sample-sample relation), for preserving three kinds of ...
All structural MR images used in this work were acquired from 1.5T scanners. Data were collected across a variety of scanners with protocols individualized for each scanner. ...
doi:10.1016/j.media.2015.10.008
pmid:26674971
pmcid:PMC4862945
fatcat:xdqesmpifvbuhmsquumrdbouki
A multi-scale cortical wiring space links cellular architecture and functional dynamics in the human brain
2020
PLoS Biology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
machine learning. ...
Our approach is inspired by seminal, but so far largely neglected models of cortico–cortical wiring established by postmortem anatomical studies and capitalises on cutting-edge in vivo neuroimaging and ...
their gratitude to the open science initiatives that made this work possible, including the teams involved in the BigBrain project, the PsychEncode consortium, the Human Connectome Project, and Scikit-learn ...
doi:10.1371/journal.pbio.3000979
pmid:33253185
fatcat:wzpsh4og5vbnjjcdkczcwwpbbm
The Human Connectome Project's neuroimaging approach
2016
Nature Neuroscience
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
, blurring, and temporal artifacts; (4) represent data using the natural geometry of cortical and subcortical structures; (5) accurately align corresponding brain areas across subjects and studies; (6) ...
analyze data using neurobiologically accurate brain parcellations; and (7) share published data via user-friendly databases. ...
We thank the other investigators and staff members of the Human Connectome Project consortium for invaluable contributions to data acquisition, analysis, and sharing. ...
doi:10.1038/nn.4361
pmid:27571196
fatcat:wwg4h7gmw5eshc5bc3zsmt6zmy
Data and Physics Driven Learning Models for Fast MRI – Fundamentals and Methodologies from CNN, GAN to Attention and Transformers
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Finally, we will demonstrate through a few clinical applications, explain the importance of data harmonisation and explainable models for such fast MRI techniques in multicentre and multi-scanner studies ...
Recent studies have witnessed substantial growth in the development of deep learning techniques for propelling fast MRI. ...
In general digital healthcare settings, federated learning enables multi-centre and multi-scanner studies across different sites to develop accurate and robust deep learning models without revealing or ...
arXiv:2204.01706v1
fatcat:7vwd52c23faglm2c4zmcqwzjtu
« Previous
Showing results 1 — 15 out of 237 results