Filters








26 Hits in 15.8 sec

Predicting motor outcome in preterm infants from very early brain diffusion MRI using a deep learning convolutional neural network (CNN) model

Susmita Saha, Alex Pagnozzi, Pierrick Bourgeat, Joanne M. George, DanaKai Bradford, Paul B. Colditz, Roslyn N. Boyd, Stephen E. Rose, Jurgen Fripp, Kerstin Pannek
2020 NeuroImage  
convolutional neural network (CNN) model.  ...  This study established the potential of an early brain MRI-based deep learning CNN model to identify preterm infants at risk of a later motor impairment and to identify brain regions predictive of adverse  ...  Acknowledgements We would like to acknowledge the families of preterm infants who participated in this study and all the associated medical, nursing and administrative staff.  ... 
doi:10.1016/j.neuroimage.2020.116807 pmid:32278897 fatcat:nf4knnadzzcsdliw7a7wr6pro4

Early Prediction of Cognitive Deficit in Very Preterm Infants Using Brain Structural Connectome With Transfer Learning Enhanced Deep Convolutional Neural Networks

Ming Chen, Hailong Li, Jinghua Wang, Weihong Yuan, Mekbib Altaye, Nehal A Parikh, Lili He
2020 Frontiers in Neuroscience  
As such, we developed a transfer learning enhanced convolutional neural network (TL-CNN) model for early prediction of cognitive assessment at 2 years of age in very preterm infants using brain structural  ...  The results suggest that deep learning models may facilitate early prediction of later neurodevelopmental outcomes in very preterm infants at term-equivalent age.  ...  In this study, we proposed a TL-enhanced deep CNN (TL-CNN) model for early prediction of cognitive deficit at 2 years of age in very preterm infants using brain structural connectome derived from at term  ... 
doi:10.3389/fnins.2020.00858 pmid:33041749 pmcid:PMC7530168 fatcat:ufmstu6kqvcmrimzgzvmyfocfa

A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants

Lili He, Hailong Li, Jinghua Wang, Ming Chen, Elveda Gozdas, Jonathan R. Dillman, Nehal A. Parikh
2020 Scientific Reports  
early interventions to improve clinical outcomes in very preterm infants.  ...  (cognitive, language and motor) outcomes at 2 years corrected age in very preterm infants.  ...  Acknowledgements This study was supported by the National Institutes of Health Grants R21-HD094085, R01-NS094200 and R01-NS096037 and a Trustee grant from Cincinnati Children's Hospital Medical Center.  ... 
doi:10.1038/s41598-020-71914-x pmid:32934282 fatcat:mqllg23b5nbjbdneyl43gazi6e

BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment

Jeremy Kawahara, Colin J. Brown, Steven P. Miller, Brian G. Booth, Vann Chau, Ruth E. Grunau, Jill G. Zwicker, Ghassan Hamarneh
2017 NeuroImage  
Abstract We propose BrainNetCNN, a convolutional neural network (CNN) framework to predict clinical neurodevelopmental outcomes from brain networks.  ...  We apply the BrainNetCNN framework to predict cognitive and motor developmental outcome scores from structural brain networks of infants born preterm.  ...  S.P.M. is currently the Bloorview Children's Hospital Chair in Pediatric Neuroscience. R.E.G. is supported by a Senior Scientist Award from the Child & Family Research Institute.  ... 
doi:10.1016/j.neuroimage.2016.09.046 pmid:27693612 fatcat:7orxb5grqzdh5mi3k6337kdoi4

Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants

Lili He, Hailong Li, Ming Chen, Jinghua Wang, Mekibib Altaye, Jonathan R. Dillman, Nehal A. Parikh
2021 Frontiers in Neuroscience  
Thus, analyzing quantitative multimodal MRI features affords unique opportunities to study early postnatal brain development and neurodevelopmental outcome prediction in VPIs.  ...  These survivors, especially, very preterm infants (VPIs), born ≤ 32 weeks gestational age, are at high risk for neurodevelopmental impairments.  ...  In another study, Saha et al. (2020) achieved a mean accuracy of 73% on predicting motor outcome in preterm infants by applying a CNN model on DTI data.  ... 
doi:10.3389/fnins.2021.753033 pmid:34675773 pmcid:PMC8525883 fatcat:w2iwwvfyubfrbnymdronjxrbxy

Brain age predicted using graph convolutional neural network explains developmental trajectory in preterm neonates [article]

Mengting Liu, Sharon Kim, Ben A. Duffy, Shiyu Yuan, James H. Cole, Arthur W. Toga, Neda Jahanshad, Anthony James Barkovich, Duan Xu, Hosung Kim
2021 bioRxiv   pre-print
Here, we investigated the ability of the graph convolutional network (GCN) to predict brain age for preterm neonates by accounting for morphometrics measured on the cortical surface and the surface mesh  ...  Our findings demonstrate that GCN-based age prediction of preterm neonates (n=170; mean absolute error [MAE]: 1.06 weeks) outperformed conventional machine learning algorithms and deep learning methods  ...  For instance, in aging brains, the PBA has been investigated using standard deep learning approaches (Ning et al., 2020) where an image volume is inputted into a convolutional neural network (CNN) and  ... 
doi:10.1101/2021.05.15.444320 fatcat:p2hhvgtyp5fejgqnagphfukvzm

Prospects of deep learning for medical imaging

Jonghoon Kim, Jisu Hong, Hyunjin Park
2018 Precision and Future Medicine  
First, an overview of how traditional machine learning evolved to deep learning is provided. Second, a survey of the application of deep learning in medical imaging research is given.  ...  Recently, a highly flexible machine learning approach known as deep learning has emerged as a disruptive technology to enhance the performance of existing machine learning techniques and to solve previously  ...  predict a cognitive and motor developmental outcome score by using structural brain networks of diffusion tensor imag- ing.  ... 
doi:10.23838/pfm.2018.00030 fatcat:2bclzigfijadzcdoqhhzniqwdy

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

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 arXiv   pre-print
With the advances of data-driven machine learning research, a wide variety of prediction problems have been tackled.  ...  As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interactive nodes connected by edges whose weights can be  ...  DCRNN model: Diffusion convolutional recurrent neural networks (DCRNN) [56] introduce the diffusion graph convolutional layer to capture spatial dependencies, and uses a sequence-to-sequence architecture  ... 
arXiv:2105.13137v1 fatcat:gm7d2ziagba7bj3g34u4t3k43y

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  
With the advances of data-driven machine learning research, a wide variety of prediction problems have been tackled.  ...  As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interacting nodes connected by edges whose weights can be  ...  DCRNN model: Diffusion convolutional recurrent neural networks (DCRNNs) [51] introduce the diffusion graph convolutional layer to capture spatial dependencies, and uses a sequence-to-sequence architecture  ... 
doi:10.3390/s21144758 fatcat:jytyt4u2pjgvhnhcto3vcvd3a4

Brain microstructure and morphology of very preterm-born infants at term equivalent age: associations with motor and cognitive outcomes at 1 and 2 years

Kerstin Pannek, Joanne M. George, Roslyn N. Boyd, Paul B. Colditz, Stephen E. Rose, Jurgen Fripp
2020 NeuroImage  
Very preterm-born infants are at risk of adverse neurodevelopmental outcomes.  ...  Brain magnetic resonance imaging (MRI) at term equivalent age (TEA) can probe tissue microstructure and morphology, and demonstrates potential in the early prediction of outcomes.  ...  Rose, Jurgen Fripp, and Kerstin Pannek. 2020. 31 "Predicting Motor Outcome in Preterm Infants from Very Early Brain Diffusion MRI 32 Using a Deep Learning Convolutional Neural Network (CNN) Model."  ... 
doi:10.1016/j.neuroimage.2020.117163 pmid:32663645 fatcat:wco2lcwnjre7fmb4l6qwssoqra

Machine Learning on Human Connectome Data from MRI [article]

Colin J Brown, Ghassan Hamarneh
2016 arXiv   pre-print
Functional MRI (fMRI) and diffusion MRI (dMRI) are non-invasive imaging modalities that allow in-vivo analysis of a patient's brain network (known as a connectome).  ...  Recently, researchers have been exploring the application of machine learning models to connectome data in order to predict clinical outcomes and analyze the importance of subnetworks in the brain.  ...  190] and delayed motor and cognitive development in preterm infants [24, 25, 92] since early intervention of these conditions can improve patient outcomes [14, 190] .  ... 
arXiv:1611.08699v1 fatcat:opmtmr3eejbjjm4swfmg54g4q4

Fusing autonomy and sociality via embodied emergence and development of behaviour and cognition from fetal period

Yasuo Kuniyoshi
2019 Philosophical Transactions of the Royal Society of London. Biological Sciences  
This work is important because it models very early autonomous development in realistic detailed human embodiment.  ...  We present a hypothetical early developmental scenario that fills in the very beginning part of the comprehensive scenarios proposed in developmental robotics.  ...  Other collaborators and (former) students who contributed to our work reviewed in this paper are gratefully acknowledged.  ... 
doi:10.1098/rstb.2018.0031 pmid:30852992 pmcid:PMC6452254 fatcat:ebmqbqydf5gypntxakyy2yhgxu

Diffusion Kurtosis Imaging of the neonatal Spinal Cord: design and application of the first processing pipeline implemented in Spinal Cord Toolbox [article]

Rosella Denise Tro', Monica Roascio, Domenico Tortora, Mariasavina Severino, Andrea Rossi, Julien Cohen-Adad, Marco Massimo Fato, Gabriele Arnulfo
2021 medRxiv   pre-print
packages widely adopted in brain imaging domain.  ...  Due to its extreme sensitivity to non-gaussian diffusion, DKI proves particularly suitable for detecting complex, subtle, fast microstructural changes occurring in this area at this early and critical  ...  It is composed of a cascade of two convolutional neural networks (CNN), specifically designed to deal with spinal cord morphometry: the first detects the cord centerline and reduces the space around the  ... 
doi:10.1101/2021.03.12.21253413 fatcat:yaytyxwblnfvzht5shsqjaxcey

28th Annual Computational Neuroscience Meeting: CNS*2019

2019 BMC Neuroscience  
Activity from both the LP and PD neurons of the stomatogastric ganglion of a crab was recorded using intracellular electrodes and sent to a computer through a DAQ device.  ...  A hexapod robotic platform was built using printable parts from the BQ DIWO PrintBot Crab, whose schematics are open-source.  ...  Deep Convolutional Neural Networks (CNNs) excel at object recognition and classification, with accuracy levels that now exceed humans [1] .  ... 
doi:10.1186/s12868-019-0538-0 fatcat:3pt5qvsh45awzbpwhqwbzrg4su

SPR 2020

2020 Pediatric Radiology  
A convolutional neural network with the U-Net architecture was used to train the segmentation model.  ...  Paper #: 014 Free-Breathing Highly Accelerated 2D Cine Cardiac MRI Using Deep Convolutional Neural Network (DCNN) Reconstruction: Clinical Validation Evan J.  ...  Methods & Materials: Cases of IHA seen on brain MRIs at a single tertiary paediatric centre on 1.5T and 3T performed from September 2001 and September 2019 were compiled from a search of MRI reports on  ... 
doi:10.1007/s00247-020-04679-0 pmid:32435980 fatcat:y6da6d4blvaxlkus6w6zahpwlu
« Previous Showing results 1 — 15 out of 26 results