Automatic 3D Bi-Ventricular Segmentation of Cardiac Images by a Shape-Refined Multi- Task Deep Learning Approach.
Jinming DuanGhalib BelloJo SchlemperWenjia BaiTimothy J. W. DawesCarlo BiffiAntonio de MarvaoGeorgia DoumouDeclan P. O'ReganDaniel RueckertPublished in: IEEE Trans. Medical Imaging (2019)
Keyphrases
- deep learning
- multi task
- shape prior
- learning tasks
- unsupervised learning
- level set
- multi class
- shape model
- segmentation algorithm
- machine learning
- image segmentation
- segmentation method
- learning problems
- graph cuts
- energy function
- transfer learning
- medical images
- multiscale
- mental models
- weakly supervised
- active contours
- supervised learning
- object segmentation
- data sets