Nested U-Net for Segmentation of Red Lesions in Retinal Fundus Images and Sub-image Classification for Removal of False Positives.
Swagata KunduVikrant Anilrao KaraleGoutam Kumar GhoraiGautam SarkarSambuddha GhoshAshis Kumar DharaPublished in: J. Digit. Imaging (2022)
Keyphrases
- false positives
- image classification
- optic disc
- false negative
- retinal fundus images
- false positive rate
- number of false positives
- detection rate
- image analysis
- segmentation method
- image segmentation
- level set
- segmentation algorithm
- segmentation accuracy
- true positive
- blood vessels
- retinal images
- multiscale
- low false positive rate
- shape prior
- feature extraction
- false alarms
- region growing
- medical images
- energy function
- breast mri
- skin lesion
- computational cost