Tabita Catalán

Time-dependent Deep Image Prior for TR-resolved cine MRI at 0.55T

Tabita Catalán, Claudia Prieto, Rafael I. De la Sotta, Rene Botnar et autres

cl, gb (code pays fourni par la source)

Self-supervised Super-resolution based on Implicit Neural Representation for 3D whole-heart CMRA at 0.55T

Matías Paredes, Claudia Prieto, Sofía E. Farfán, Tabita Catalán et autres

cl (code pays fourni par la source)

PISCO: Self-supervised k-space regularization for improved neural implicit k-space representations of dynamic MRI

Veronika Spieker, Hannah Eichhorn, Wenqi Huang, Jonathan Stelter et autres

Neural implicit k-space representations (NIK) have shown promising results for dynamic magnetic resonance imaging (MRI) at high temporal resolutions. Yet, reducing acquisition time, and thereby available training data, results in severe performance drops due to overfitting. To address this, we introduce a …

de, cl, ch (code pays fourni par la source)

Multi-Slice Single-Breath-Hold Cardiac CINE with Slice and Time-Dependent Deep Image Prior at 1.5T and 0.55T

Rafael De la Sotta, Tabita Catalán, Francisco Sahli Costabal, René M. Botnar et autres

Motivation: Conventional cardiac CINE MRI requires multiple slices and breath-holds, leading to long scans and potential slice misalignment. Goal(s): We aim to perform an efficient multi-slice single-breath-hold cardiac CINE at 1.5T and 0.55T. Approach: Multi-slice single-breath-hold cardiac CINE at 1.5T and 0.55T …

Self-supervised motion-corrected reconstruction for single heartbeat cardiac cine MRI at 1.5T and 0.55T using PINNs and Deep Image Prior

Tabita Catalán, Rafael De la Sotta, René M. Botnar, Francisco Sahli Costabal et autres

Motivation: Long scan times can limit the spatial and temporal resolution of cardiac cine, especially at low field. Goal(s): To propose a novel self-supervised motion estimation and motion corrected deep learning reconstruction to single heartbeat TR-resolved cardiac cine at 1.5T and 0.55T. …

PISCO: Self-Supervised k-Space Regularization for Improved Neural Implicit k-Space Representations of Dynamic MRI

Veronika Spieker, Hannah Eichhorn, Wenqi Huang, Jonathan Stelter et autres

Neural implicit k-space representations (NIK) have shown promising results for dynamic magnetic resonance imaging (MRI) at high temporal resolutions. Yet, reducing acquisition time, and thereby available training data, results in severe performance drops due to overfitting. To address this, we introduce a …

Self-supervised motion-corrected reconstruction for single heartbeat cardiac cine MRI using neural fields and deep image prior

Tabita Catalán, René Michael Botnar, Francisco Sahli, Claudia Prieto

cl (code pays fourni par la source)

Unsupervised reconstruction of accelerated cardiac cine MRI using neural fields

Tabita Catalán, Matías Courdurier, Axel Osses, Anastasia Fotaki et autres

cl, gb (code pays fourni par la source)

Unsupervised reconstruction of undersampled 3D whole-heart Cartesian MRimaging using neural fields

Tabita Catalán, Francisco Sahli, René Michael Botnar, Claudia Prieto

Motivation: 3D MRI is fundamental for the assessment of cardiovascular disease but suffers from long scan times. Undersampled reconstruction techniques have been proposed to accelerate the acquisition, but require long computational times for training. Goal(s): To develop an unsupervised undersampled reconstruction approach …

One-Heartbeat Cine MRI with Implicit Neural Representations Reconstruction

Tabita Catalán, Matías Courdurier, Axel Osses, René Michael Botnar et autres

Motivation: Cardiac cine MRI is the gold standard for cardiac functional assessment but requires acquiring several slices under multiple breath-holds, leading to limited number of cardiac phases, patient fatigue and misregistration between slices. Goal(s): To develop a novel undersampled reconstruction based on …

Highly accelerated Cardiac CINE MRI using Neural Fields

Tabita Catalán, Matías Courdurier, Axel Osses, René Michael Botnar et autres

Neural fields cardiac MRI (NF-cMRI), a method for highly accelerated CINE reconstruction using deep learning, is proposed. NF-cMRI relies on an intensity network, based on neural fields with Fourier features to encode a continuous reconstruction. The network is trained with one undersampled …

CConnect: Synergistic Convolutional Regularization for Cartesian T2* Mapping

J.L. Molina, Alexandre Bousse, Tabita Catalán, Zhihan Wang et autres

Magnetic resonance imaging (MRI) is fundamental for the assessment of many diseases, due to its excellent tissue contrast characterization. This is based on quantitative techniques, such as T1 , T2 , and T2* mapping. Quantitative MRI requires the acquisition of several contrast-weighed …

fr (code pays fourni par la source)