3D Segmentation of Perivascular Spaces on T1-Weighted 3 Tesla MR Images With a Convolutional Autoencoder and a U-Shaped Neural Network.
Philippe BoutinaudAmi TsuchidaAlexandre LaurentFilipa AdoniasZahra HanifehlouVictor NozaisViolaine VerrecchiaLeonie LampeJunyi ZhangYi-Cheng ZhuChristophe TzourioBernard MazoyerMarc JoliotPublished in: Frontiers Neuroinformatics (2021)
Keyphrases
- mr images
- accurate segmentation
- medical images
- brain mr images
- magnetic resonance
- partial volume
- brain tumors
- mr brain
- magnetic resonance images
- segmentation result
- manual segmentation
- intensity inhomogeneity
- mr imaging
- cardiac magnetic resonance
- dice similarity coefficient
- bias field
- brain structures
- nonrigid registration
- image data
- tissue segmentation
- mr brain images
- intensity distribution
- mri data
- anatomical structures
- brain mri
- inhomogeneity correction
- brain tissue
- phantom images
- atlas construction
- contrast enhanced
- medical imaging
- inter patient
- restricted boltzmann machine
- lesion segmentation
- brain segmentation
- prostate cancer
- level set
- quantitative measurements
- automated segmentation
- prostate segmentation
- image analysis
- automatic segmentation
- quantitative evaluation
- gray matter
- model based segmentation
- medical image analysis
- fully automatic
- brain images
- image registration
- segmentation algorithm
- cerebrospinal fluid
- deformable models
- magnetic resonance imaging
- segmentation method