Deep active learning for suggestive segmentation of biomedical image stacks via optimisation of Dice scores and traced boundary length.
Alessia AtzeniLoïc PeterEleanor D. RobinsonEmily BlackburnJuri AlthonayanDaniel C. AlexanderJuan Eugenio IglesiasPublished in: Medical Image Anal. (2022)
Keyphrases
- image stacks
- active learning
- tubular structures
- electron microscopy
- deep learning
- image segmentation
- biomedical image analysis
- segmentation algorithm
- boundary extraction
- level set
- biomedical images
- boundary information
- region growing
- medical images
- x ray
- multiscale
- training set
- segmentation result
- segmentation method
- fully automated
- semi supervised
- data points
- fully automatic
- semi automatic
- energy function
- learning algorithm