Deep learning using a biophysical model for robust and accelerated reconstruction of quantitative, artifact-free and denoised R 2 * images.
Max ToropSatya V V N KothapalliYu SunJiaming LiuSayan KahaliDmitriy A YablonskiyUlugbek S KamilovPublished in: Magnetic resonance in medicine (2020)
RoAR is trained to recognize the macroscopic magnetic field inhomogeneities directly from the input magnitude-only mGRE data and eliminate their effect on R 2 ∗ measurements. RoAR training is based on the biophysical model and does not require ground-truth R 2 * maps. Since RoAR utilizes signal information not just from individual voxels but also accounts for spatial patterns of the signals in the images, it reduces the sensitivity of R 2 * maps to the noise in the data. These features plus high computational speed provide significant benefits for the potential usage of RoAR in clinical settings.
Keyphrases
- deep learning
- convolutional neural network
- electronic health record
- artificial intelligence
- big data
- optical coherence tomography
- machine learning
- high resolution
- computed tomography
- magnetic resonance imaging
- resistance training
- climate change
- body composition
- human health
- high intensity
- virtual reality
- mass spectrometry
- image quality