Malte Hoffmann
YOU?
Author Swipe
View article: Domain-randomized deep learning for neuroimage analysis
Domain-randomized deep learning for neuroimage analysis Open
Deep learning has revolutionized neuroimage analysis by delivering unprecedented speed and accuracy. However, the narrow scope of many training datasets constrains model robustness and generalizability. This challenge is particularly acute…
View article: Domain-Randomized Deep Learning for Neuroimage Analysis: Selecting Training Strategies, Navigating Challenges, and Maximizing Benefits
Domain-Randomized Deep Learning for Neuroimage Analysis: Selecting Training Strategies, Navigating Challenges, and Maximizing Benefits Open
Deep learning has revolutionized neuroimage analysis by delivering unprecedented speed and accuracy. However, the narrow scope of many training datasets constrains model robustness and generalizability. This challenge is particularly acute…
View article: MindGrab for BrainChop: Fast and Accurate Skull Stripping for Command Line and Browser
MindGrab for BrainChop: Fast and Accurate Skull Stripping for Command Line and Browser Open
We developed MindGrab, a parameter- and memory-efficient deep fully-convolutional model for volumetric skull-stripping in head images of any modality. Its architecture, informed by a spectral interpretation of dilated convolutions, was tra…
View article: Learning Accurate Rigid Registration for Longitudinal Brain MRI from Synthetic Data
Learning Accurate Rigid Registration for Longitudinal Brain MRI from Synthetic Data Open
Rigid registration aims to determine the translations and rotations necessary to align features in a pair of images. While recent machine learning methods have become state-of-the-art for linear and deformable registration across subjects,…
View article: MultiMorph: On-demand Atlas Construction
MultiMorph: On-demand Atlas Construction Open
We present MultiMorph, a fast and efficient method for constructing anatomical atlases on the fly. Atlases capture the canonical structure of a collection of images and are essential for quantifying anatomical variability across population…
View article: Learning accurate rigid registration for longitudinal brain MRI from synthetic data
Learning accurate rigid registration for longitudinal brain MRI from synthetic data Open
Rigid registration aims to determine the translations and rotations necessary to align features in a pair of images. While recent machine learning methods have become state-of-the-art for linear and deformable registration across subjects,…
View article: WALINET: A water and lipid identification convolutional neural network for nuisance signal removal in 1H$$ {}^1\mathrm{H} $$ MR spectroscopic imaging
WALINET: A water and lipid identification convolutional neural network for nuisance signal removal in 1H$$ {}^1\mathrm{H} $$ MR spectroscopic imaging Open
Purpose Proton magnetic resonance spectroscopic imaging (‐MRSI) provides noninvasive spectral‐spatial mapping of metabolism. However, long‐standing problems in whole‐brain ‐MRSI are spectral overlap of metabolite peaks with large lipid sig…
View article: Search Wide, Focus Deep: Automated Fetal Brain Extraction with Sparse Training Data
Search Wide, Focus Deep: Automated Fetal Brain Extraction with Sparse Training Data Open
Automated fetal brain extraction from full-uterus MRI is a challenging task due to variable head sizes, orientations, complex anatomy, and prevalent artifacts. While deep-learning (DL) models trained on synthetic images have been successfu…
View article: Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging
Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging Open
Over recent years, deep learning based image registration has achieved impressive accuracy in many domains, including medical imaging and, specifically, human neuroimaging with magnetic resonance imaging (MRI). However, the uncertainty est…
View article: WALINET: A water and lipid identification convolutional Neural Network for nuisance signal removal in 1H MR Spectroscopic Imaging
WALINET: A water and lipid identification convolutional Neural Network for nuisance signal removal in 1H MR Spectroscopic Imaging Open
Purpose. Proton Magnetic Resonance Spectroscopic Imaging (1H-MRSI) provides non-invasive spectral-spatial mapping of metabolism. However, long-standing problems in whole-brain 1H-MRSI are spectral overlap of metabolite peaks with large lip…
View article: Deep-ER: Deep Learning ECCENTRIC Reconstruction for fast high-resolution neurometabolic imaging
Deep-ER: Deep Learning ECCENTRIC Reconstruction for fast high-resolution neurometabolic imaging Open
Introduction: Altered neurometabolism is an important pathological mechanism in many neurological diseases and brain cancer, which can be mapped non-invasively by Magnetic Resonance Spectroscopic Imaging (MRSI). Advanced MRSI using non-car…
View article: Clinical evaluation of k-space correlation informed motion artifact detection in segmented multi-slice MRI
Clinical evaluation of k-space correlation informed motion artifact detection in segmented multi-slice MRI Open
Motion artifacts can negatively impact diagnosis, patient experience, and radiology workflow especially when a patient recall is required. Detecting motion artifacts while the patient is still in the scanner could potentially improve workf…
View article: Can we predict motion artifacts in clinical MRI before the scan completes?
Can we predict motion artifacts in clinical MRI before the scan completes? Open
Subject motion remains the major source of artifacts in magnetic resonance imaging (MRI). Motion correction approaches have been successfully applied in research, but clinical MRI typically involves repeating corrupted acquisitions. To all…
View article: SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI
SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI Open
Rigid motion tracking is paramount in many medical imaging applications where movements need to be detected, corrected, or accounted for. Modern strategies rely on convolutional neural networks (CNN) and pose this problem as rigid registra…
View article: Boosting Skull-Stripping Performance for Pediatric Brain Images
Boosting Skull-Stripping Performance for Pediatric Brain Images Open
Skull-stripping is the removal of background and non-brain anatomical features from brain images. While many skull-stripping tools exist, few target pediatric populations. With the emergence of multi-institutional pediatric data acquisitio…
View article: Registration by Regression (RbR): a framework for interpretable and flexible atlas registration
Registration by Regression (RbR): a framework for interpretable and flexible atlas registration Open
In human neuroimaging studies, atlas registration enables mapping MRI scans to a common coordinate frame, which is necessary to aggregate data from multiple subjects. Machine learning registration methods have achieved excellent speed and …
View article: Synthetic data in generalizable, learning-based neuroimaging
Synthetic data in generalizable, learning-based neuroimaging Open
Synthetic data have emerged as an attractive option for developing machine-learning methods in human neuroimaging, particularly in magnetic resonance imaging (MRI)—a modality where image contrast depends enormously on acquisition hardware …
View article: Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
Anatomy-aware and acquisition-agnostic joint registration with SynthMorph Open
Affine image registration is a cornerstone of medical-image analysis. While classical algorithms can achieve excellent accuracy, they solve a time-consuming optimization for every image pair. Deep-learning (DL) methods learn a function tha…
View article: SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI
SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI Open
Rigid motion tracking is paramount in many medical imaging applications where movements need to be detected, corrected, or accounted for. Modern strategies rely on convolutional neural networks (CNN) and pose this problem as rigid registra…
View article: RnR-ExM Test Dataset
RnR-ExM Test Dataset Open
This dataset was released as part of the 2023 ISBI challenge, RnR-ExM. The organizers thank Ruihan Zhang (MIT), Margaret Elizabeth Schroeder (MIT) and Chi Zhang (MIT) for contributing data to this competition.
View article: RnR-ExM Test Dataset
RnR-ExM Test Dataset Open
This dataset was released as part of the 2023 ISBI challenge, RnR-ExM. The organizers thank Ruihan Zhang (MIT), Margaret Elizabeth Schroeder (MIT) and Chi Zhang (MIT) for contributing data to this competition.
View article: Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
Anatomy-aware and acquisition-agnostic joint registration with SynthMorph Open
Affine image registration is a cornerstone of medical image analysis. While classical algorithms can achieve excellent accuracy, they solve a time-consuming optimization for every image pair. Deep-learning (DL) methods learn a function tha…
View article: Data Consistent Deep Rigid MRI Motion Correction
Data Consistent Deep Rigid MRI Motion Correction Open
Motion artifacts are a pervasive problem in MRI, leading to misdiagnosis or mischaracterization in population-level imaging studies. Current retrospective rigid intra-slice motion correction techniques jointly optimize estimates of the ima…
View article: RnR-Exm Validation Dataset
RnR-Exm Validation Dataset Open
This dataset was released as part of the 2023 ISBI challenge, RnR-ExM. The organizers thank Ruihan Zhang (MIT), Margaret Elizabeth Schroeder (MIT) and Chi Zhang (MIT) for contributing data to this competition.
View article: RnR-Exm Validation Dataset
RnR-Exm Validation Dataset Open
This dataset was released as part of the 2023 ISBI challenge, RnR-ExM. The organizers thank Ruihan Zhang (MIT), Margaret Elizabeth Schroeder (MIT) and Chi Zhang (MIT) for contributing data to this competition.
View article: RnR-ExM Training Dataset
RnR-ExM Training Dataset Open
This dataset was released as part of the 2023 ISBI challenge, RnR-ExM. The organizers thank Ruihan Zhang (MIT), Margaret Elizabeth Schroeder (MIT) and Chi Zhang (MIT) for contributing data to this competition.
View article: RnR-ExM Training Dataset
RnR-ExM Training Dataset Open
This dataset was released as part of the 2023 ISBI challenge, RnR-ExM. The organizers thank Ruihan Zhang (MIT), Margaret Elizabeth Schroeder (MIT) and Chi Zhang (MIT) for contributing data to this competition.