1.2k citations
- Eindhoven University of TechnologyNL56 papers
- Delft University of TechnologyNL21 papers
- Leiden UniversityNL20 papers
- Signify (Netherlands)NL18 papers
- Institute for Atomic and Molecular PhysicsNL14 papers
- NXP (Netherlands)NL13 papers
- Philips (Finland)FI9 papers
- Utrecht UniversityNL8 papers
- Max Planck Institute for Solid State ResearchDE7 papers
- Philips (Germany)DE6 papers
- Radboud University NijmegenNL6 papers
- RWTH Aachen UniversityDE5 papers
5 papers · 2 filters
Physics-informed neural networks for myocardial perfusion MRI quantification
Rudolf L. M. van Herten, Amedeo Chiribiri, Marcel Breeuwer +2
Tracer-kinetic models allow for the quantification of kinetic parameters such as blood flow from dynamic contrast-enhanced magnetic resonance (MR) images. Fitting the observed data…
XCAT-GAN for Synthesizing 3D Consistent Labeled Cardiac MR Images on Anatomically Variable XCAT Phantoms
Sina Amirrajab, Samaneh Abbasi-Sureshjani, Yasmina Al Khalil +4
Generative adversarial networks (GANs) have provided promising data enrichment solutions by synthesizing high-fidelity images. However, generating large sets of labeled images with…
Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet
Hongxu Yang, Caifeng Shan, Alexander F. Kolen +1
Catheter segmentation in 3D ultrasound is important for computer-assisted cardiac intervention. However, a large amount of labeled images are required to train a successful deep co…
3D medical image segmentation with labeled and unlabeled data using autoencoders at the example of liver segmentation in CT images
Cheryl Sital, Tom Brosch, Dominique Tio +2
Automatic segmentation of anatomical structures with convolutional neural networks (CNNs) constitutes a large portion of research in medical image analysis. The majority of CNN-bas…
4D Semantic Cardiac Magnetic Resonance Image Synthesis on XCAT Anatomical Model
Samaneh Abbasi-Sureshjani, Sina Amirrajab, Cristian Lorenz +3
We propose a hybrid controllable image generation method to synthesize anatomically meaningful 3D+t labeled Cardiac Magnetic Resonance (CMR) images. Our hybrid method takes the mec…