arXiv research

Predicting MRI coil failures using image features and ensemble learning.

Predicting MRI coil failures using time series classification.

PC-RNN reconstructs MRI images from undersampled data with more details.

Study on helix curves and their Möbius energy asymptotics.

The paper studies Möbius energy gradient of helix pairs and finds limiting behavior as coiling ratio increases.

Study on the $L^p$ behavior of helix curves' energy density.

Ensembled neural networks improve MRI image quality.

In recent years, several families of hyperbolic knots have been shown to have both volume and $λ_1$ (first eigenvalue of the Laplacian) bounded in terms of the twist number of a diagram, while other families of knots have volume bounded by a generalized twist number. We show that for general knots, neither the twist nu…

Algorithms for Magnetic Resonance (MR) image reconstruction from undersampled measurements exploit prior information to compensate for missing k-space data. Deep learning (DL) provides a powerful framework for extracting such information from existing image datasets, through learning, and then using it for reconstructi…

We present simple reconstruction networks for multi-coil data by extending deep cascade of CNN's and exploiting the data consistency layer. In particular, we propose two variants, where one is inspired by POCSENSE and the other is calibration-less. We show that the proposed approaches are competitive relative to the st…

Time-resolved angiography with interleaved stochastic trajectories (TWIST) has been widely used for dynamic contrast enhanced MRI (DCE-MRI). To achieve highly accelerated acquisitions, TWIST combines the periphery of the k-space data from several adjacent frames to reconstruct one temporal frame. However, this view-sha…

XPDNet wins MRI reconstruction challenge with neural network.

A benchmarking framework for studying data geometry.

The U-net is a deep-learning network model that has been used to solve a number of inverse problems. In this work, the concatenation of two-element U-nets, termed the W-net, operating in k-space (K) and image (I) domains, were evaluated for multi-channel magnetic resonance (MR) image reconstruction. The two element net…

We introduce a new unsupervised representation learning and visualization using deep convolutional networks and self organizing maps called Deep Neural Maps (DNM). DNM jointly learns an embedding of the input data and a mapping from the embedding space to a two-dimensional lattice. We compare visualizations of DNM with…

New Bayesian method for joint sparse parameter inference.

The approximation of nonlinear kernels via linear feature maps has recently gained interest due to their applications in reducing the training and testing time of kernel-based learning algorithms. Current random projection methods avoid the curse of dimensionality by embedding the nonlinear feature space into a low dim…

Nyquist ghost artifacts in EPI are originated from phase mismatch between the even and odd echoes. However, conventional correction methods using reference scans often produce erroneous results especially in high-field MRI due to the non-linear and time-varying local magnetic field changes. Recently, it was shown that …

We present a graph-based variational algorithm for classification of high-dimensional data, generalizing the binary diffuse interface model to the case of multiple classes. Motivated by total variation techniques, the method involves minimizing an energy functional made up of three terms. The first two terms promote a …

This study uses CNN-IOs to estimate MRI image reconstruction performance bounds.

It is a well-known procedure for constructing a torus knot or link that first we prepare an unknotted torus and meridian disks in the complementary solid tori of it, and second smooth the intersections of the boundary of meridian disks uniformly. Then we obtain a torus knot or link on the unknotted torus and its Seifer…

We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters $k$, and for each $1 \leq k \leq k_\mathrm{max}$, a distribution over the individual cluster assignm…

Generative model learns object variability from MRI measurements.

This paper proposes a multi-channel image reconstruction method, named DeepcomplexMRI, to accelerate parallel MR imaging with residual complex convolutional neural network. Different from most existing works which rely on the utilization of the coil sensitivities or prior information of predefined transforms, Deepcompl…

We present two graph-based algorithms for multiclass segmentation of high-dimensional data. The algorithms use a diffuse interface model based on the Ginzburg-Landau functional, related to total variation compressed sensing and image processing. A multiclass extension is introduced using the Gibbs simplex, with the fun…

We present a numerical model for the dynamics of thin viscous threads based on a discrete, Lagrangian formulation of the smooth equations. The model makes use of a condensed set of coordinates, called the centerline/spin representation: the kinematical constraints linking the centerline's tangent to the orientation of …

Accelerated magnetic resonance (MR) scan acquisition with compressed sensing (CS) and parallel imaging is a powerful method to reduce MR imaging scan time. However, many reconstruction algorithms have high computational costs. To address this, we investigate deep residual learning networks to remove aliasing artifacts …

Jointly correct bias fields and reconstruct undersampled MRI images.

Unpaired deep learning reconstructs MRI images from accelerated data.

Explicitly or implicitly, most of dimensionality reduction methods need to determine which samples are neighbors and the similarity between the neighbors in the original highdimensional space. The projection matrix is then learned on the assumption that the neighborhood information (e.g., the similarity) is known and f…

Generative models improve MRI reconstruction by learning image structure.

Deep learning for TOF-MRA without matched training data.

The segmentation of the breast from the chest wall is an important first step in the analysis of breast magnetic resonance images. 3D U-nets have been shown to obtain high segmentation accuracy and appear to generalize well when trained on one scanner type and tested on another scanner, provided that a very similar T1-…

New algorithms for clustering and dimension reduction using relative von Neumann entropy.

MosaicMRI expands public datasets for musculoskeletal MRI, revealing cross-anatomical correlations.

A new diffusion sampling method combines Krylov subspace and diffusion models for faster and more efficient inverse problems.

Purpose: To introduce a combined machine learning (ML) and physics-based image reconstruction framework that enables navigator-free, highly accelerated multishot echo planar imaging (msEPI), and demonstrate its application in high-resolution structural and diffusion imaging. Methods: Singleshot EPI is an efficient enco…

Generates samples conditioned on labels using optimal transport.

The paper classifies Finsler surfaces satisfying the T-condition or σT-condition.

The paper develops a new approach to conditional risk measures using modular convex analysis.

Paper constructs solutions to Bogomolny equations with specific boundary and asymptotic conditions.

We extend probabilistic programming to handle conditioning on marginal distributions.

New tests for conditional copulas based on decision trees.

Paper finds necessary condition for logarithmic Minkowski problem in higher dimensions.

This paper introduces a neural operator for probabilistic conditioning.

CSI method learns conditional distributions by estimating flow equations.

New conditional risk measures called conditional generalized quantiles defined and characterized.

A new method for learning conditional distributions using ODEs and neural networks.