[HTML][HTML] Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics
There is significant interest in the development and application of deep neural networks
(DNNs) to neuroimaging data. A growing literature suggests that DNNs outperform their …
(DNNs) to neuroimaging data. A growing literature suggests that DNNs outperform their …
[HTML][HTML] Uncertainty modelling in deep learning for safer neuroimage enhancement: Demonstration in diffusion MRI
Deep learning (DL) has shown great potential in medical image enhancement problems,
such as super-resolution or image synthesis. However, to date, most existing approaches …
such as super-resolution or image synthesis. However, to date, most existing approaches …
Low-memory neural network training: A technical report
NS Sohoni, CR Aberger, M Leszczynski… - arXiv preprint arXiv …, 2019 - arxiv.org
Memory is increasingly often the bottleneck when training neural network models. Despite
this, techniques to lower the overall memory requirements of training have been less widely …
this, techniques to lower the overall memory requirements of training have been less widely …
A partially reversible U-Net for memory-efficient volumetric image segmentation
R Brügger, CF Baumgartner, E Konukoglu - Medical Image Computing …, 2019 - Springer
One of the key drawbacks of 3D convolutional neural networks for segmentation is their
memory footprint, which necessitates compromises in the network architecture in order to fit …
memory footprint, which necessitates compromises in the network architecture in order to fit …
Scanner invariant representations for diffusion MRI harmonization
Purpose In the present work, we describe the correction of diffusion‐weighted MRI for site
and scanner biases using a novel method based on invariant representation. Theory and …
and scanner biases using a novel method based on invariant representation. Theory and …
[HTML][HTML] Cross-scanner and cross-protocol multi-shell diffusion MRI data harmonization: Algorithms and results
Cross-scanner and cross-protocol variability of diffusion magnetic resonance imaging
(dMRI) data are known to be major obstacles in multi-site clinical studies since they limit the …
(dMRI) data are known to be major obstacles in multi-site clinical studies since they limit the …
Challenges in end-to-end neural scientific table recognition
In recent years, end-to-end trained neural models have been applied successfully to various
optical character recognition (OCR) tasks. However, the same level of success has not yet …
optical character recognition (OCR) tasks. However, the same level of success has not yet …
Reversible gans for memory-efficient image-to-image translation
TFA van der Ouderaa… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
The pix2pix and CycleGAN losses have vastly improved the qualitative and quantitative
visual quality of results in image-to-image translation tasks. We extend this framework by …
visual quality of results in image-to-image translation tasks. We extend this framework by …
Super-Resolved q-Space deep learning with uncertainty quantification
Y Qin, Z Liu, C Liu, Y Li, X Zeng, C Ye - Medical Image Analysis, 2021 - Elsevier
Diffusion magnetic resonance imaging (dMRI) provides a noninvasive method for measuring
brain tissue microstructure. q-Space deep learning (q-DL) methods have been developed to …
brain tissue microstructure. q-Space deep learning (q-DL) methods have been developed to …
Diffusion mri with machine learning
D Karimi, SK Warfield - Imaging Neuroscience, 2024 - direct.mit.edu
Diffusion-weighted magnetic resonance imaging (dMRI) of the brain offers unique
capabilities including noninvasive probing of tissue microstructure and structural …
capabilities including noninvasive probing of tissue microstructure and structural …