Search · four archives
Search · four archives
21 papers · ranked by Valyu relevance
Samo Lasič, Nathalie Just, Markus Nilsson, Filip Szczepankiewicz + 2 more
'Matthew Budde' 'Henrik Lundell'] Title: Abstract Tensor-valued encoding in diffusion MRI allows probing of microscopic anisotropy in tissue, however, time-dependent diffusion (TDD) can bias results unless b-tensors are carefully tuned to account for TDD. We propose two novel strategies for tuning b-tensors to enable…
Alexandru V. Avram, Kadharbatcha S. Saleem, Peter J. Basser
Diffusion MRI studies with resolutions of a few hundred micrometers have consistently shown that in the cortex water diffusion occurs preferentially along radial and tangential orientations with respect to the cortical surface, in agreement with histology. These dominant orientations do not change significantly even if…
Filip Szczepankiewicz, Malwina Molendowska, Samo Lasič, Marcella E. Safi + 7 more
Tensor-valued diffusion encoding employs gradient waveforms that enable unique sensitivity to microstructural features of tissue, but the interpretation of signal and parameters may be confounded by diffusion-time dependence. We introduce a framework for restriction-weighted q-space trajectory imaging (ResQ) that…
Filip Szczepankiewicz, Malwina Molendowska, Samo Lasič, Marcella E Safi + 7 more
Tensor-valued diffusion encoding employs gradient waveforms that enable unique sensitivity to microstructural features of tissue, but the interpretation of signal and parameters may be confounded by diffusion-time dependence. We introduce a framework for restriction-weighted q-space trajectory imaging (ResQ) that…
Yiang Pan, Yuanjing Feng, Jianzhong He, William Consagra + 3 more
Diffusion MRI (dMRI) enables noninvasive characterization of white-matter fiber orientations and tissue microstructure, but widely used approaches, such as constrained spherical deconvolution (CSD) and parametric multicompartment models, typically address these features separately. The diffusion tensor distribution…
Maxime Yon, Omar Narvaez, Daniel Topgaard, Alejandra Sierra
Massively multidimensional diffusion magnetic resonance imaging combines tensor-valued encoding, oscillating gradients, and diffusion-relaxation correlation to provide multicomponent subvoxel parameters depicting some tissue microstructural features. This method was successfully implemented ex vivo in microimaging…
Hong Jiang, Leo Svenningsson, Daniel Topgaard
Diffusion NMR and MRI methods building on the classic pulsed gradient spin-echo sequence are sensitive to many aspects of translational motion, including time and frequency dependence (“restriction”), anisotropy, and flow, leading to ambiguities when interpreting experimental data from complex heterogeneous materials…
Maxime Yon, Omar Narvaez, Daniel Topgaard, Alejandra Sierra
Massively Multidimensional Diffusion MRI combines tensor-valued encoding, oscillating gradients, and diffusion-relaxation correlation to provide multicomponent sub-voxel parameters depicting the tissue microstructure. This method was successfully implemented ex vivo in micro-imaging systems and in clinical conditions…
Junhyeok Lee, Kyu Sung Choi
Reconstructing diffusion tensors from sparse DWIs is critical for accelerating Diffusion Tensor Imaging (DTI) in clinical settings, yet current deep learning approaches frequently yield anatomically inconsistent or physically implausible tensors. We introduce TensorLDM, a component-wise latent diffusion model that…
Maxime Yon, Omar Narvaez, Jan Martin, Hong Jiang + 5 more
Time- or frequency-dependent (“restricted”) diffusion potentially provides useful information about cellular-scale structures in the brain but is challenging to interpret because of the intravoxel tissue heterogeneity. Frequency-dependence was recently incorporated in a multidimensional diffusion-relaxation correlation…
Zejun Wu, Jiechao Wang, Zunquan Chen, Qinqin Yang + 3 more
'Zhong Chen' 'Congbo Cai'] Abstract. Objective: Most deep neural network-based diffusion tensor imaging methods require the diffusion gradients' number and directions in the data to be reconstructed to match those in the training data. This work aims to develop and evaluate a novel dynamic-convolution-based method…
Maryam Afzali, Sam Coveney, Lars Mueller, Sarah Jones + 7 more
Diffusion tensor imaging (DTI) is commonly used in cardiac diffusion magnetic resonance imaging (dMRI). However, the tissue’s microstructure (cells, membranes, etc.) restricts the movement of the water molecules, making the spin displacements deviate from Gaussian behaviour. This effect may be observed with diffusion…
Benoit Anctil-Robitaille, Antoine Théberge, Pierre-Marc Jodoin, Maxime Descoteaux + 2 more
'Maxime Descoteaux' 'Christian Desrosiers' 'Hervé Lombaert'] The physical and clinical constraints surrounding diffusion-weighted imaging (DWI) often limit the spatial resolution of the produced images to voxels up to eight times larger than those of T1w images. The detailed information contained in accessible…
Tobias Alt, Karl Schrader, Joachim Weickert, Pascal Peter + 1 more
'Matthias Augustin'] Partial differential equation models and their associated variational energy formulations are often rotationally invariant by design. This ensures that a rotation of the input results in a corresponding rotation of the output, which is desirable in applications such as image analysis. Convolutional…
Lucas Relic, Roberto Gerson de Albuquerque Azevedo, Markus Groß, Christopher Schroers
'Christopher Schroers'] Abstract. Incorporating diffusion models in the image compression domain has the potential to produce realistic and detailed reconstructions, especially at extremely low bitrates. Previous methods focus on using diffusion models as expressive decoders robust to quantization errors in the…
Authors not listed
Real-world datasets in chemical engineering and bioengineering processes--such as those from catalytic reactors, multiphase flows, polymerization reactors, bioreactors, and clinical trials--can often be unlabelled or disorganized, rendering the training of existing supervised learning models ineffective at learning the…
Jeremy Vonderfecht, Feng Liu
We apply the DiffC algorithm (Theis et al., 2022) to Stable Diffusion 1.5, 2.1, XL, and Flux-dev, and demonstrate that these pretrained models are remarkably capable lossy image compressors. A principled algorithm for lossy compression using pretrained diffusion models has been understood since at least Ho et al.…
Angela F Harper, Simone S Köcher, Karsten Reuter, Christoph Scheurer
Machine learning (ML) surrogate modeling is a powerful approach to reduce the computational cost of first-principles calculations. While well established for the prediction of scalar observables like energetics or band gaps, performance metrics for the learning of tensor-based observables have not yet been formalized.…
Anton Obukhov, Mikhail Usvyatsov, Christos Sakaridis, Konrad Schindler + 1 more
'Konrad Schindler' 'Luc Van Gool'] Learning neural fields has been an active topic in deep learning research, focusing, among other issues, on finding more compact and easy-to-fit representations. In this paper, we introduce a novel low-rank representation termed Tensor Train Neural Fields (TT-NF) for learning neural…
Tae-Hyung Kwon, Jihoon Ko, Jinhong Jung, Kijung Shin
In this work, we propose TENSORCODEC, a lossy compression algorithm for general tensors that do not necessarily adhere to strong input data assumptions. TENSORCODEC incorporates three key ideas. The first idea is Neural Tensor-Train Decomposition (NTTD) where we integrate a recurrent neural network into Tensor-Train…
Maxwell Venetos, Mingjian Wen, Kristin Persson
The nuclear magnetic resonance (NMR) chemical shift tensor is a highly sensitive probe of the electronic structure of an atom and furthermore its local structure. Re- cently, machine learning has been applied to NMR in the prediction of isotropic chemi- cal shifts from a structure. Current machine learning models…