A resolution adaptive deep hierarchical (RADHicaL) learning scheme applied to nuclear segmentation of digital pathology images.
Andrew JanowczykScott DoyleHannah GilmoreAnant MadabhushiPublished in: Comput. methods Biomech. Biomed. Eng. Imaging Vis. (2018)
Keyphrases
- learning scheme
- segmentation algorithm
- test images
- image analysis
- segmentation method
- fully automatic
- input image
- image regions
- adaptive thresholding
- segmented images
- low level image segmentation
- edge detection
- accurate segmentation
- piece wise
- segmentation errors
- segmentation accuracy
- image resolution
- image data
- image database
- image features
- image pyramid
- microscopic images
- tubular structures
- microscopy images
- image slices
- ground truth
- low depth of field
- three dimensional
- image retrieval
- grey level
- digital imaging
- region growing
- cell nuclei
- object recognition
- image segmentation algorithms
- medical images
- learning algorithm
- high resolution
- pixel wise
- pixel level
- multiscale
- image segmentation
- image segments
- coarse to fine
- automatically segmented
- object segmentation
- segmented regions
- watershed transform
- energy function
- image quality
- level set
- decision trees