237 Hits in 8.8 sec

MISPEL: A deep learning approach for harmonizing multi-scanner matched neuroimaging data [article]

Mahbaneh Eshaghzadeh Torbati, Davneet S Minhas, Charles M Laymon, Pauline Maillard, James D Wilson, Chang-Le Chen, Ciprian M Crainiceanu, Charles S DeCarli, Seong Jae Hwang, Dana L Tudorascu
2022 bioRxiv   pre-print
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]

Mengting Liu, Piyush Maiti, Sophia I Thomopoulos, Alyssa Zhu, Yaqiong Chai, Hosung Kim, Neda Jahanshad
2021 bioRxiv   pre-print
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 (which was not certified by peer review) is the author/funder.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]

surabhi sinha, Sophia I. Thomopoulos, Pradeep Lam, Alexandra Muir, Paul M. Thompson
2021 bioRxiv   pre-print
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

Guillem Simeon, Gemma Piella, Oscar Camara, Deborah Pareto
2022 Frontiers in Neuroinformatics  
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

Shruti Atul Mali, Abdalla Ibrahim, Henry C. Woodruff, Vincent Andrearczyk, Henning Müller, Sergey Primakov, Zohaib Salahuddin, Avishek Chatterjee, Philippe Lambin
2021 Journal of Personalized Medicine  
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]

Guillem Simeon, Gemma Piella, Oscar Camara, Deborah Pareto
2021 bioRxiv   pre-print
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

Guangming Zhu, Bin Jiang, Liz Tong, Yuan Xie, Greg Zaharchuk, Max Wintermark
2019 Frontiers in Neurology  
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]

Joan Rue-Queralt, Angus Stevner, Enzo Tagliazucchi, Helmut Laufs, Morten L Kringelbach, Gustavo Deco, Selen Atasoy
2021 bioRxiv   pre-print
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

Jennifer Stine Elam, Matthew F. Glasser, Michael P. Harms, Stamatios N. Sotiropoulos, Jesper L.R. Andersson, Gregory C. Burgess, Sandra W. Curtiss, Robert Oostenveld, Linda J. Larson-Prior, Jan-Mathijs Schoffelen, Michael R. Hodge, Eileen A. Cler (+6 others)
2021 NeuroImage  
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

Dominique Duncan, Paul Vespa, Asla Pitkänen, Adebayo Braimah, Niina Lapinlampi, Arthur W. Toga
2018 Neurobiology of Disease  
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]

S. Kevin Zhou, Hayit Greenspan, Christos Davatzikos, James S. Duncan, Bram van Ginneken, Anant Madabhushi, Jerry L. Prince, Daniel Rueckert, Ronald M. Summers
2020 arXiv   pre-print
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

Xiaofeng Zhu, Heung-Il Suk, Li Wang, Seong-Whan Lee, Dinggang Shen
2017 Medical Image Analysis  
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/ pmid:26674971 pmcid:PMC4862945 fatcat:xdqesmpifvbuhmsquumrdbouki

A multi-scale cortical wiring space links cellular architecture and functional dynamics in the human brain

Casey Paquola, Jakob Seidlitz, Oualid Benkarim, Jessica Royer, Petr Klimes, Richard A. I. Bethlehem, Sara Larivière, Reinder Vos de Wael, Raul Rodríguez-Cruces, Jeffery A. Hall, Birgit Frauscher, Jonathan Smallwood (+2 others)
2020 PLoS Biology  
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

Matthew F Glasser, Stephen M Smith, Daniel S Marcus, Jesper L R Andersson, Edward J Auerbach, Timothy E J Behrens, Timothy S Coalson, Michael P Harms, Mark Jenkinson, Steen Moeller, Emma C Robinson, Stamatios N Sotiropoulos (+4 others)
2016 Nature Neuroscience  
, 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]

Jiahao Huang, Yingying Fang, Yang Nan, Huanjun Wu, Yinzhe Wu, Zhifan Gao, Yang Li, Zidong Wang, Pietro Lio, Daniel Rueckert, Yonina C. Eldar, Guang Yang
2022 arXiv   pre-print
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