Transformer-based out-of-distribution detection for clinically safe segmentation.
Mark S. GrahamPetru-Daniel TudosiuPaul WrightWalter Hugo Lopez PinayaU. Jean-MarieYee H. MahJames T. TeoHans Rolf JägerDavid WerringParashkev NachevSébastien OurselinM. Jorge CardosoPublished in: CoRR (2022)
Keyphrases
- level set
- segmentation algorithm
- segmentation method
- detection method
- image segmentation
- medical images
- detection algorithm
- multiscale
- false alarms
- fully automatic
- cell segmentation
- reliable detection
- low signal to noise ratio
- complex background
- object segmentation
- automatically segmented
- boundary detection
- edge detection
- energy function
- rib cage
- mixture of gaussian distributions
- image analysis
- probability distribution
- segmentation accuracy
- bounding box
- automatic detection
- false positives
- anomaly detection
- fault diagnosis
- medical imaging
- neural network
- object detection
- intensity variations
- fully unsupervised
- fuzzy logic
- detection rate
- curvilinear structures
- landmark detection
- high voltage
- video segmentation
- image sequences
- computed tomography angiography
- video data