Artificial intelligence-based full aortic CT angiography imaging with ultra-low-dose contrast medium: a preliminary study.
Zhen ZhouYifeng GaoWeiwei ZhangKairui BoNan ZhangHui WangRui WangZhiqiang DuDavid FirminGuang YangHeye ZhangLei XuPublished in: European radiology (2022)
• The required dose of contrast medium (CM) for full ACTA imaging can be reduced to one-third of the CM dose of the low-dose contrast medium (LDCM) protocol using the Au-CycleGAN algorithm. • Except for the image noise, the AI-based ultra-low-dose contrast medium (ULDCM) images had better quantitative image quality parameters than the ULDCM and LDCM images. • No significant diagnostic differences were noted between the AI-based ULDCM and LDCM images regarding all the analyzed aortic disease diagnoses.
Keyphrases
- artificial intelligence
- deep learning
- low dose
- high resolution
- magnetic resonance
- convolutional neural network
- big data
- machine learning
- high dose
- image quality
- contrast enhanced
- aortic valve
- randomized controlled trial
- magnetic resonance imaging
- air pollution
- mass spectrometry
- pulmonary artery
- pulmonary hypertension
- pulmonary arterial hypertension
- dual energy
- reduced graphene oxide