22 papers · ranked by Valyu relevance
Filip Szczepankiewicz, Carl‐Fredrik Westin, Markus Nilsson
- Diffusion encoding along multiple spatial directions per signal acquisition can be described in terms of a b-tensor. The benefit of tensor-valued diffusion encoding is that it unlocks the 'shape of the b-tensor' as a new encoding dimension. By modulating the b-tensor shape, we can control the sensitivity to…
Filip Szczepankiewicz, Jens Sjölund, Freddy Ståhlberg, Jimmy Lätt + 2 more
'Markus Nilsson' 'Xi Chen'] Microstructure imaging techniques based on tensor-valued diffusion encoding have gained popularity within the MRI research community. Unlike conventional diffusion encoding-applied along a single direction in each shot-tensor-valued encoding employs diffusion encoding along multiple…
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…
Filip Szczepankiewicz, Jens Sjölund, Erica Dall’Armellina, Sven Plein + 3 more
1## INTRODUCTION Tissue movement during diffusion encoding can lead to phase dispersion that is erroneously attributed to diffusion or cause gross signal dropout. For example, the relatively slow and incoherent movement of blood in capillaries has a measurable impact on the diffusion-weighted signal at low b-values and…
Alexis Reymbaut, Alex Valcourt Caron, Guillaume Gilbert, Filip Szczepankiewicz + 4 more
'Filip Szczepankiewicz' 'Markus Nilsson' 'Simon K. Warfield' 'Maxime Descoteaux' 'Benoît Scherrer'] Diffusion tensor imaging provides increased sensitivity to microstructural tissue changes compared to conventional anatomical imaging but also presents limited specificity. To tackle this problem, the DIAMOND model…
Philippe Karan, Alexis Reymbaut, Guillaume Gilbert, Maxime Descoteaux
Diffusion tensor imaging (DTI) is widely used to extract valuable tissue measurements and white matter (WM) fiber orientations, even though its lack of specificity is now well-known, especially for WM fiber crossings. Models such as constrained spherical deconvolution (CSD) take advantage of high angular resolution…
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…
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…
Benjamin Bourassa, Maxime Tremblay, David Poulin
Arikan's recursive code construction is designed to polarize a collection of memoryless channels into a set of good and a set of bad channels, and it can be efficiently decoded using successive cancellation [1]. It was recently shown that the same construction also polarizes channels with memory [2], and a…
Maryam Afzali, Santiago Aja-Fernández, Derek K Jones
It has been shown previously that for a very specific form of diffusion-encoding, i.e., the conventional Stejskal-Tanner pulsed gradient, or ‘linear tensor encoding’ (LTE), and in tissue in which diffusion exhibits a ‘stick-like’ geometry, the diffusion-weighted MRI signal at extremely high b-values follows a power…
Miaoyan Wang, Lexin Li
We consider the problem of decomposing a higher-order tensor with binary entries. Such data problems arise frequently in applications such as neuroimaging, recommendation system, topic modeling, and sensor network localization. We propose a multilinear Bernoulli model, develop a rank-constrained likelihood-based…
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…
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.…
Michele Gallo
Tensors provide a robust framework for managing high-dimensional data. Consequently, tensor analysis has emerged as an active research area in various domains, including machine learning, signal processing, computer vision, graph analysis, and data mining. This study introduces an efficient image storage approach…
Laura Sainz Villalba, P. Michael Furlong, Madeleine Bartlett, Nicole Sandra-Yaffa Dumont
The brain faces the feature binding problem: how are multiple stimulus features and variables combined into coherent representations that support flexible behavior? A key finding from neuroscience is that some brain regions employ factorized representations, where distinct features are encoded in neural state space in…
Gian Marco Visani, Michael N. Pun, Armita Nourmohammad
Group-equivariant neural networks have emerged as a data-efficient approach to solve classification and regression tasks, while respecting the relevant symmetries of the data. However, little work has been done to extend this paradigm to the unsupervised and generative domains. Here, we present Holographic-(V)AE…
Qingzhu Wang, Xiaoming Chen, Mengying Wei, Zhuang Miao
Background The existing techniques for simultaneous encryption and compression of images refer lossy compression. Their reconstruction performances did not meet the accuracy of medical images because most of them have not been applicable to three-dimensional (3D) medical image volumes intrinsically represented by…
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…
Ivan Lopez-Arevalo, Edwin Aldana-Bobadilla, Alejandro Molina-Villegas, Hiram Galeana-Zapién + 2 more
'Hiram Galeana-Zapién' 'Victor Muñiz-Sanchez' 'Saul Gausin-Valle'] The most common machine-learning methods solve supervised and unsupervised problems based on datasets where the problem’s features belong to a numerical space. However, many problems often include data where numerical and categorical data coexist, which…
Michalis Giannopoulos, Anastasia Aidini, Anastasia Pentari, Konstantina Fotiadou + 1 more
'Konstantina Fotiadou' 'Panagiotis Tsakalides'] Multispectral sensors constitute a core Earth observation image technology generating massive high-dimensional observations. To address the communication and storage constraints of remote sensing platforms, lossy data compression becomes necessary, but it unavoidably…
Authors not listed
Elucidating Collective Variables (CVs) for biomolecular dynamics is crucial for understanding numerous biological processes. By leveraging the tensor-train data structure, a multilinear version of the AMUSE (Algorithm for Multiple Unknown Signals) algorithm for Koopman approximation (AMUSEt) was recently developed to…
Chen-Hsiu Huang, Ja-Ling Wu, Jun Chen
End-to-end learned image compression codecs have notably emerged in recent years. These codecs have demonstrated superiority over conventional methods, showcasing remarkable flexibility and adaptability across diverse data domains while supporting new distortion losses. Despite challenges such as computational…