Image quality of whole-body diffusion MR images comparing deep-learning accelerated and conventional sequences.
Andrea PonsiglioneWill McGuireGiuseppe PetraliaMarie FennessyThomas BenkertAlfonso Maria PonsiglioneAnwar R PadhaniPublished in: European radiology (2024)
Deep learning reconstruction enables a more than 50% reduction in acquisition time for WB diffusion sequences. DRB images were preferred by radiologists in almost 80% of cases due to fewer artefacts, improved background signal suppression, higher signal-to-noise ratio, and increased lesion conspicuity in patients with higher body mass index. Cancer lesion diffusivity from DRB images was not different from conventional sequences.
Keyphrases
- deep learning
- artificial intelligence
- convolutional neural network
- image quality
- body mass index
- machine learning
- computed tomography
- papillary thyroid
- physical activity
- magnetic resonance
- air pollution
- squamous cell
- squamous cell carcinoma
- optical coherence tomography
- weight gain
- contrast enhanced
- lymph node metastasis