Enhancement of evaluating flatfoot on a weight-bearing lateral radiograph of the foot with U-Net based semantic segmentation on the long axis of tarsal and metatarsal bones in an active learning manner.
Seung Min RyuKeewon ShinSoo Wung ShinSeungjun LeeNamkug KimPublished in: Comput. Biol. Medicine (2022)
Keyphrases
- semantic segmentation
- active learning
- x ray images
- long axis
- x ray
- left ventricle
- conditional random fields
- weakly supervised
- magnetic resonance imaging
- medical images
- scene classification
- superpixels
- object categories
- image processing
- semi supervised
- machine learning
- training examples
- object classes
- left ventricular
- training set
- multiscale
- three dimensional
- learning algorithm
- image sequences
- object recognition
- image set
- fully automatic
- graph cuts
- ground truth
- probabilistic model
- optical flow
- image analysis