Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth.
Vanya V. ValindriaIoannis LavdasWenjia BaiKonstantinos KamnitsasEric O. AboagyeAndrea G. RockallDaniel RueckertBen GlockerPublished in: IEEE Trans. Medical Imaging (2017)
Keyphrases
- ground truth
- classification accuracy
- image segmentation algorithms
- ground truth data
- segmented images
- quantitative evaluation
- level set
- image segmentation
- segmentation algorithm
- high quality
- word segmentation
- medical images
- feature selection
- test images
- segmentation method
- edge detection
- contour detection
- brain mri
- energy function
- image analysis
- object segmentation
- feature space
- multiscale
- neural network
- training set
- support vector