CARES 3.0: A two stage system combining feature-based recognition and edge-based segmentation for CIMT measurement on a multi-institutional ultrasound database of 300 images.
Filippo MolinariKristen M. MeiburgerU. Rajendra AcharyaGuang ZengPaulo Sergio RodriguesLuca SabaAndrew NicolaidesJasjit S. SuriPublished in: EMBC (2011)
Keyphrases
- segmentation method
- database
- medical ultrasound
- image features
- segmentation algorithm
- object recognition
- image analysis
- feature extraction and matching
- image data
- image regions
- edge detection
- ultrasound images
- test images
- accurate segmentation
- images depicting
- image matching
- texture and shape features
- input image
- segmentation errors
- segmentation accuracy
- segmented images
- fully automatic
- image database
- image retrieval
- adaptive thresholding
- image segments
- echocardiographic images
- image segmentation
- active contours
- pixel level
- automated segmentation
- image registration
- traffic signs
- cell nuclei
- multiple objects
- object segmentation
- ultrasound imaging
- level set
- feature extraction
- low contrast
- automatic segmentation
- speckle reduction
- shape prior
- fundamental problems in computer vision