Deep learning-based 3D cerebrovascular segmentation workflow on bright and black blood sequences magnetic resonance angiography.
Langtao ZhouHuiting WuGuanghua LuoHong ZhouPublished in: Insights into imaging (2024)
• The proposed deep learning-based workflow performs well in cerebrovascular segmentation tasks. • Among comparison models, SwinUNETR achieved the best DSC, ASD, PRE, and SPE values in lenticulostriate artery segmentation. • The proposed workflow can be used for different MR sequences, such as bright and black blood imaging.
Keyphrases
- deep learning
- magnetic resonance
- convolutional neural network
- artificial intelligence
- electronic health record
- machine learning
- contrast enhanced
- autism spectrum disorder
- optical coherence tomography
- high resolution
- computed tomography
- ms ms
- attention deficit hyperactivity disorder
- magnetic resonance imaging
- genetic diversity
- mass spectrometry
- liquid chromatography
- clinical evaluation