Andreas Kofler
YOU?
Author Swipe
View article: MRpro - open PyTorch-based MR reconstruction and processing package
MRpro - open PyTorch-based MR reconstruction and processing package Open
We introduce MRpro, an open-source image reconstruction package built upon PyTorch and open data formats. The framework comprises three main areas. First, it provides unified data structures for the consistent manipulation of MR datasets a…
View article: Deep unrolling for learning optimal spatially varying regularisation parameters for Total Generalised Variation
Deep unrolling for learning optimal spatially varying regularisation parameters for Total Generalised Variation Open
We extend a recently introduced deep unrolling framework for learning spatially varying regularisation parameters in inverse imaging problems to the case of Total Generalised Variation (TGV). The framework combines a deep convolutional neu…
View article: MR imaging in the low-field: Leveraging the power of machine learning
MR imaging in the low-field: Leveraging the power of machine learning Open
Recent innovations in Magnetic Resonance Imaging (MRI) hardware and software have reignited interest in low-field ($<1\,\mathrm{T}$) and ultra-low-field MRI ($<0.1\,\mathrm{T}$). These technologies offer advantages such as lower power cons…
View article: Metrology for artificial intelligence in medicine
Metrology for artificial intelligence in medicine Open
View article: Zero-Shot Unsupervised Motion Estimation for Motion-Corrected Cardiac T1 Mapping
Zero-Shot Unsupervised Motion Estimation for Motion-Corrected Cardiac T1 Mapping Open
As our method is individually optimized for each scan without the need for training on large datasets, it can easily be adapted to other cardiac qMRI approaches.
View article: Robust Myocardial Perfusion MRI Quantification With DeepFermi
Robust Myocardial Perfusion MRI Quantification With DeepFermi Open
Stress perfusion cardiac magnetic resonance is an important technique for examining and assessing the blood supply of the myocardium. Currently, the majority of clinical perfusion scans are evaluated based on visual assessment by experienc…
View article: Joint $\text{B}_{0}$ and Image Reconstruction in Low-Field MRI by Physics-Informed Deep-Learning
Joint $\text{B}_{0}$ and Image Reconstruction in Low-Field MRI by Physics-Informed Deep-Learning Open
low-field MRI is becoming increasingly more popular as it enables access to MR in challenging situations such as intensive care units or resource poor areas. Our method allows for fast and accurate image reconstruction in such low-field im…
View article: Joint reconstruction and segmentation in undersampled 3D knee MRI combining shape knowledge and deep learning
Joint reconstruction and segmentation in undersampled 3D knee MRI combining shape knowledge and deep learning Open
Objective. Task-adapted image reconstruction methods using end-to-end trainable neural networks (NNs) have been proposed to optimize reconstruction for subsequent processing tasks, such as segmentation. However, their training typically re…
View article: PINQI: An End-to-End Physics-Informed Approach to Learned Quantitative MRI Reconstruction
PINQI: An End-to-End Physics-Informed Approach to Learned Quantitative MRI Reconstruction Open
Quantitative Magnetic Resonance Imaging (qMRI) enables the reproducible measurement of biophysical parameters in tissue. The challenge lies in solving a nonlinear, ill-posed inverse problem to obtain the desired tissue parameter maps from …
View article: Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling
Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling Open
We introduce a method for the fast estimation of data-adapted, spatially and temporally dependent regularization parameter-maps for variational image reconstruction, focusing on total variation (TV) minimization. The proposed approach is i…
View article: NoSENSE: Learned unrolled cardiac MRI reconstruction without explicit sensitivity maps
NoSENSE: Learned unrolled cardiac MRI reconstruction without explicit sensitivity maps Open
We present a novel learned image reconstruction method for accelerated cardiac MRI with multiple receiver coils based on deep convolutional neural networks (CNNs) and algorithm unrolling. In contrast to many existing learned MR image recon…
View article: Quantitative MR Image Reconstruction Using Parameter-Specific Dictionary Learning With Adaptive Dictionary-Size and Sparsity-Level Choice
Quantitative MR Image Reconstruction Using Parameter-Specific Dictionary Learning With Adaptive Dictionary-Size and Sparsity-Level Choice Open
From a clinical perspective, the obtained T1-maps could be utilized to differentiate between healthy subjects and patients with Alzheimer's disease. From a technical perspective, the proposed unsupervised method could be employe…
View article: Data‐efficient Bayesian learning for radial dynamic MR reconstruction
Data‐efficient Bayesian learning for radial dynamic MR reconstruction Open
Background Cardiac MRI has become the gold‐standard imaging technique for assessing cardiovascular morphology and function. In spite of this, its slow data acquisition process presents imaging challenges due to the motion from heartbeats, …
View article: PINQI: An End-to-End Physics-Informed Approach to Learned Quantitative MRI Reconstruction
PINQI: An End-to-End Physics-Informed Approach to Learned Quantitative MRI Reconstruction Open
Quantitative Magnetic Resonance Imaging (qMRI) enables the reproducible measurement of biophysical parameters in tissue. The challenge lies in solving a nonlinear, ill-posed inverse problem to obtain the desired tissue parameter maps from …
View article: Unrolled three-operator splitting for parameter-map learning in Low Dose X-ray CT reconstruction
Unrolled three-operator splitting for parameter-map learning in Low Dose X-ray CT reconstruction Open
We propose a method for fast and automatic estimation of spatially dependent regularization maps for total variation-based (TV) tomography reconstruction. The estimation is based on two distinct sub-networks, with the first sub-network est…
View article: Learning Regularization Parameter-Maps for Variational Image Reconstruction using Deep Neural Networks and Algorithm Unrolling
Learning Regularization Parameter-Maps for Variational Image Reconstruction using Deep Neural Networks and Algorithm Unrolling Open
We introduce a method for fast estimation of data-adapted, spatio-temporally dependent regularization parameter-maps for variational image reconstruction, focusing on total variation (TV)-minimization. Our approach is inspired by recent de…
View article: A1.2 - Digital Testing Platform for Artificial Intelligence: A modular and scalable concept
A1.2 - Digital Testing Platform for Artificial Intelligence: A modular and scalable concept Open
View article: Deep supervised dictionary learning by algorithm unrolling—Application to fast 2D dynamic MR image reconstruction
Deep supervised dictionary learning by algorithm unrolling—Application to fast 2D dynamic MR image reconstruction Open
Background Unrolled neural networks (NNs) have been extensively applied to different image reconstruction problems across all imaging modalities. A key component of the latter is that they allow for physics‐informed learning of the regular…
View article: 3D model-based super-resolution motion-corrected cardiac T1 mapping
3D model-based super-resolution motion-corrected cardiac T1 mapping Open
Objective . To provide 3D high-resolution cardiac T1 maps using model-based super-resolution reconstruction (SRR). Approach . Due to signal-to-noise ratio limitations and the motion of the heart during imaging, often 2D T1 maps with only l…
View article: Convolutional Dictionary Learning by End-To-End Training of Iterative Neural Networks
Convolutional Dictionary Learning by End-To-End Training of Iterative Neural Networks Open
Sparsity-based methods have a long history in the field of signal processing and have been successfully applied to various image reconstruction problems. The involved sparsifying transformations or dictionaries are typically either pre-tra…
View article: Flow-Py v1.0: a customizable, open-source simulation tool to estimate runout and intensity of gravitational mass flows
Flow-Py v1.0: a customizable, open-source simulation tool to estimate runout and intensity of gravitational mass flows Open
Models and simulation tools for gravitational mass flows (GMFs) such as snow avalanches, rockfall, landslides, and debris flows are important for research, education, and practice. In addition to basic simulations and classic applications …
View article: Convolutional Analysis Operator Learning by End-To-End Training of Iterative Neural Networks
Convolutional Analysis Operator Learning by End-To-End Training of Iterative Neural Networks Open
The concept of sparsity has been extensively applied for regularization in image reconstruction. Typically, sparsifying transforms are either pre-trained on ground-truth images or adaptively trained during the reconstruction. Thereby, lear…
View article: Comment on gmd-2021-277
Comment on gmd-2021-277 Open
Abstract. Models and simulation tools for gravitational mass flows (GMFs) such as snow avalanches, rockfall, landslides, and debris flows are important for research, education, and practice. In addition to basic simulation…
View article: Comment on gmd-2021-277
Comment on gmd-2021-277 Open
Abstract. Models and simulation tools for gravitational mass flows (GMFs) such as snow avalanches, rockfall, landslides, and debris flows are important for research, education, and practice. In addition to basic simulation…
View article: Flow-Py v1.0: A customizable, open-source simulation tool to estimate runout and intensity of gravitational mass flows
Flow-Py v1.0: A customizable, open-source simulation tool to estimate runout and intensity of gravitational mass flows Open
Models and simulation tools for gravitational mass flows (GMF) such as snow avalanches, rockfall, landslides and debris flows are important for research, education and practice. In addition to basic simulations and classic applications (e.…
View article: Flow-Py: routing and stopping of gravitational mass flows
Flow-Py: routing and stopping of gravitational mass flows Open
Flow-Py is an open source gravitational mass flows (GMFs) run out model. The main objective of this tool is to compute the spatial extent of GMFs, which consists of the track/path and deposition areas of GMFs in three dimensional terrain. …
View article: Deep learning-based methods for image reconstruction in cardiac CT and cardiac cine MRI
Deep learning-based methods for image reconstruction in cardiac CT and cardiac cine MRI Open
Objective: Non-invasive medical imaging techniques such as computed tomography (CT) and magnetic resonance imaging (MRI) are nowadays essential tools for the assessment of cardiac diseases, e.g. coronary artery disease or cardiac dysfuncti…
View article: Adaptive sparsity level and dictionary size estimation for image reconstruction in accelerated 2D radial cine MRI
Adaptive sparsity level and dictionary size estimation for image reconstruction in accelerated 2D radial cine MRI Open
Purpose In the past, dictionary learning (DL) and sparse coding (SC) have been proposed for the regularization of image reconstruction problems. The regularization is given by a sparse approximation of all image patches using a learned dic…
View article: Rescue blankets hamper thermal imaging in search and rescue missions
Rescue blankets hamper thermal imaging in search and rescue missions Open
View article: Assessing the protective role of alpine forests against rockfall at regional scale
Assessing the protective role of alpine forests against rockfall at regional scale Open
Worldwide, mountain forests represent a significant factor in reducing rockfall risk over long periods of time on large potential disposition areas. While the economic value of technical protection measures against rockfall can be clearly …