Structured crowdsourcing enables convolutional segmentation of histology images.
Mohamed AmgadHabiba ElfandyHagar HusseinLamees A. AtteyaMai A. T. ElsebaieLamia S. Abo ElnasrRokia Adel SakrHazem S. E. SalemAhmed F. IsmailAnas M. SaadJoumana AhmedMaha A. T. ElsebaieMustafijur RahmanInas A. RuhbanNada M. ElgazarYahya AlaghaMohamed H. OsmanAhmed M. AlhusseinyMariam M. KhalafAbo-Alela F. YounesAli AbdulkarimDuaa M. YounesAhmed M. GadallahAhmad M. ElkashashSalma Y. FalaBasma M. ZakiJonathan D. BeezleyDeepak Roy ChittajalluDavid MantheyDavid A. GutmanLee A. D. CooperPublished in: Bioinform. (2019)
Keyphrases
- segmentation algorithm
- image analysis
- segmentation method
- image data
- image database
- image regions
- test images
- edge detection
- segmented images
- input image
- ground truth
- image features
- accurate segmentation
- grey level
- unsupervised segmentation
- segmentation errors
- fully automatic
- gray level images
- image pixels
- piece wise
- adaptive thresholding
- automatically segmented
- image slices
- image segmentation
- brain mr images
- three dimensional
- microscopic images
- pixel level
- pixel wise
- image retrieval
- complex background
- segmentation accuracy
- multiple objects
- tubular structures
- image classification
- image segments
- microscope images
- low depth of field
- object recognition
- medical images
- mr images
- region growing
- image segmentation algorithm
- object segmentation
- gray value
- bounding box
- graph cuts
- level set
- brain tumors
- foreground and background
- outdoor scenes
- fundamental problem in computer vision
- pigmented skin lesions
- cardiac magnetic resonance