A distance-based loss for smooth and continuous skin layer segmentation in optoacoustic images.
Stefan GerlJohannes C. PaetzoldHailong HeIvan EzhovSuprosanna ShitFlorian KoflerAmirhossein BayatGiles TettehVasilis NtziachristosBjoern H. MenzePublished in: CoRR (2020)
Keyphrases
- segmentation method
- segmentation algorithm
- test images
- image analysis
- image regions
- edge detection
- segmented images
- segmentation errors
- image retrieval
- skin lesion
- fully automatic
- segmentation accuracy
- image slices
- image features
- image data
- adaptive thresholding
- piece wise
- automatically segmented
- image segmentation
- grey level
- accurate segmentation
- region growing
- multiple objects
- level set
- image database
- input image
- object segmentation
- microscopic images
- bounding box
- pixel level
- tubular structures
- image registration
- ground truth
- region boundaries
- low depth of field
- pixel wise
- pigmented skin lesions
- skin surface
- cell nuclei
- microscopy images
- automated segmentation
- image segmentation algorithms
- piecewise smooth
- complex background
- lighting conditions
- object recognition
- segmented regions
- color features
- automatic segmentation
- medical images