UniLVSeg: Unified Left Ventricular Segmentation with Sparsely Annotated Echocardiogram Videos through Self-Supervised Temporal Masking and Weakly Supervised Training.
Fadillah MaaniAsim UkayeNada SaadiNuman SaeedMohammad YaqubPublished in: CoRR (2023)
Keyphrases
- cardiac mr images
- left ventricular
- supervised training
- cardiac mri
- fully automatic
- short axis
- mri data
- left ventricle
- spatio temporal
- video frames
- motion analysis
- medical images
- displacement field
- motion tracking
- training algorithm
- image segmentation
- recognition process
- neural nets
- semi automatic
- segmentation algorithm
- level set
- unsupervised learning
- supervised learning
- video sequences
- active learning
- training phase
- conditional random fields
- object recognition
- feature selection
- b spline
- small number