Skip to main content
. Author manuscript; available in PMC: 2019 Nov 2.
Published in final edited form as: IEEE Trans Med Imaging. 2019 Mar 18;38(11):2545–2555. doi: 10.1109/TMI.2019.2905917

TABLE IX:

The classification results using different distributions on latent variables

Patch Dimension Validation Classification Heldout Classification
Gaussian prior with k-means clustering 84.2±1% 83.8±1%
Gaussian mixture prior with nearest neighbor clustering 77.5±1.1% 67.5±1.3%
Gaussian mixture prior with likelihood clustering 75 ±1.2% 70±1.3%