A5071613278- Advanced MRI Techniques and Applications
- Functional Brain Connectivity Studies
- Transcranial Magnetic Stimulation Studies
- Medical Image Segmentation Techniques
- Advanced Neuroimaging Techniques and Applications
- Neurological disorders and treatments
- Advanced Neural Network Applications
- EEG and Brain-Computer Interfaces
- Brain Tumor Detection and Classification
- Neural and Behavioral Psychology Studies
- Generative Adversarial Networks and Image Synthesis
- Neural dynamics and brain function
- Machine Learning in Healthcare
- Neuroscience and Neural Engineering
- Radiomics and Machine Learning in Medical Imaging
- Electrical and Bioimpedance Tomography
- Neural Networks and Applications
- Neonatal and fetal brain pathology
- Ultrasound and Hyperthermia Applications
- Atomic and Subatomic Physics Research
- Domain Adaptation and Few-Shot Learning
- Traumatic Brain Injury and Neurovascular Disturbances
- Photoacoustic and Ultrasonic Imaging
- Medical Imaging Techniques and Applications
- Multiple Sclerosis Research Studies
Copenhagen University Hospital
2017-2025
Massachusetts General Hospital
2023-2025
Athinoula A. Martinos Center for Biomedical Imaging
2023-2025
Hvidovre Hospital
2017-2024
Harvard University
2023-2024
Amager Hospital
2023
Medical University of South Carolina
2023
Technical University of Denmark
2013-2021
Despite advances in data augmentation and transfer learning, convolutional neural networks (CNNs) difficultly generalise to unseen domains. When segmenting brain scans, CNNs are highly sensitive changes resolution contrast: even within the same MRI modality, performance can decrease across datasets. Here we introduce SynthSeg, first segmentation CNN robust against contrast resolution. SynthSeg is trained with synthetic sampled from a generative model conditioned on segmentations. Crucially,...
Quantitative analysis of magnetic resonance imaging (MRI) scans the brain requires accurate automated segmentation anatomical structures. A desirable feature for such methods is to be robust against changes in acquisition platform and protocol. In this paper we validate performance a algorithm designed meet these requirements, building upon generative parametric models previously used tissue classification. The method tested on four different datasets acquired with scanners, field strengths...
Transcranial brain stimulation (TBS) has been established as a method for modulating and mapping the function of human brain, potential treatment tool in several disorders. Typically, is applied using one-size-fits-all approach with predetermined locations electrodes, electric (TES), or coil, magnetic (TMS), which disregards anatomical variability between individuals. However, induced field distribution head largely depends on features implying need individually tailored protocols focal...
Here we present a method for the simultaneous segmentation of white matter lesions and normal-appearing neuroanatomical structures from multi-contrast brain MRI scans multiple sclerosis patients. The integrates novel model into previously validated generative whole-brain segmentation. By using separate models shape anatomical their appearance in MRI, algorithm can adapt to data acquired with different scanners imaging protocols without retraining. We validate four disparate datasets, showing...
Abstract Magnetic resonance imaging (MRI) is the standard tool to image human brain in vivo . In this domain, digital atlases are essential for subject-specific segmentation of anatomical regions interest (ROIs) and spatial comparison neuroanatomy from different subjects a common coordinate frame. High-resolution, derived histology (e.g., Allen atlas [7], BigBrain [13], Julich [15]), currently state art provide exquisite 3D cytoarchitectural maps, but lack probabilistic labels throughout...
Numerical simulation of the electric fields induced by Non-Invasive Brain Stimulation (NIBS), using realistic anatomical head models has gained interest in recent years for understanding NIBS effects individual subjects. Although automated tools generating and performing field simulations have become available, individualized modelling is still not standard practice studies. This likely partly explained lack robustness usability previously available software tools, developing link between...
Comparing electric field simulations from individualized head models against in-vivo intra-cranial recordings is considered the gold standard for direct validation of computational modeling transcranial brain stimulation and mapping techniques such as electro- magnetoencephalography. The measurements also help to improve simulation accuracy by pinning down factors having largest influence on simulations. Here we compare four different automated pipelines intracranial voltage in an existing...
In this paper we present a method for simultaneously segmenting brain tumors and an extensive set of organs-at-risk radiation therapy planning glioblastomas. The combines contrast-adaptive generative model whole-brain segmentation with new spatial regularization tumor shape using convolutional restricted Boltzmann machines. We demonstrate experimentally that the is able to adapt image acquisitions differ substantially from any available training data, ensuring its applicability across...
Abstract Objective. Transcranial ultrasound stimulation (TUS) presents challenges in wave transmission through the skull, affecting study outcomes due to aberration and attenuation. While planning strategies incorporating 3D computed tomography (CT) scans help mitigate these issues, they expose participants radiation, which can raise ethical concerns. A solution involves generating skull masks from participants’ anatomical magnetic resonance imaging (MRI). This aims compare field predictions...
Head and brain anatomy have been related to e-field strength induced by transcranial electrical stimulation (tES). Individualization based on anatomic factors require high-quality structural magnetic resonance images, which are not always available. circumference (HC) can serve as an alternative means, but its linkage electric field has yet established.We simulated fields tES individual T1w- T2w-images of 47 healthy adults, for four conventional ("standard") corresponding focal ("4x1")...
Accurate labeling of specific layers in the human cerebral cortex is crucial for advancing our understanding neurodevelopmental and neurodegenerative disorders. Building on recent advancements ultra-high-resolution ex vivo MRI, we present a novel semi-supervised segmentation model capable identifying supragranular infragranular MRI with unprecedented precision. On dataset consisting 17 whole-hemisphere scans at 120 $\mu $m, propose Multi-resolution U-Nets framework that integrates global...
<ns4:p>During the past decade, it became clear that electric field elicited by non-invasive brain stimulation (NIBS) techniques such as transcranial direct current (tDCS) and magnetic (TMS) are substantially influenced variations in individual head anatomy. In addition to structural healthy, several psychiatric disorders characterized anatomical alterations likely further constrain intracerebral effects of NIBS. Here, we present high-resolution realistic models derived from resonance imaging...
Transcranial focused Ultrasound Stimulation (TUS) at low intensities is emerging as a novel non-invasive brain stimulation method with higher spatial resolution than established transcranial methods and the ability to selectively stimulate also deep areas. Accurate control of focus position strength TUS acoustic waves important enable beneficial use high ensure safety. As human skull causes strong attenuation distortion waves, simulations transmitted are needed accurately determine dose...