A preliminary study of deep learning-based reconstruction specialized for denoising in high-frequency domain: usefulness in high-resolution three-dimensional magnetic resonance cisternography of the cerebellopontine angle.
Hiroyuki UetaniTakeshi NakauraMika KitajimaYuichi YamashitaTadashi HamasakiMachiko TateishiKosuke MoritaAkira SasaoSeitaro OdaOsamu IkedaYasuyuki YamashitaPublished in: Neuroradiology (2020)
DLR can improve the image quality of HR-MR cisternography by reducing image noise without sacrificing contrast or sharpness.
Keyphrases
- high frequency
- image quality
- magnetic resonance
- deep learning
- high resolution
- convolutional neural network
- contrast enhanced
- transcranial magnetic stimulation
- computed tomography
- artificial intelligence
- dual energy
- palliative care
- air pollution
- machine learning
- mass spectrometry
- magnetic resonance imaging
- tandem mass spectrometry