Towards Robust Retinal Vessel Segmentation via Reducing Open-Set Label Noises from SAM-Generated Masks
- 20 September 2025
- book chapter
- Published by Springer Nature
- p. 631-641
Abstract
No abstract availableKeywords
This publication has 19 references indexed in Scilit:
- Segment anything in medical imagesNature Communications, 2024
- FIVES: A Fundus Image Dataset for Artificial Intelligence based Vessel SegmentationScientific Data, 2022
- Characterizing Label Errors: Confident Learning for Noisy-Labeled Image Segmentation2020
- Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentation2019
- The Relationship of Retinal Vessel Geometric Characteristics to the Incidence and Progression of Diabetic RetinopathyOphthalmology, 2018
- Deep Co-Training for Semi-Supervised Image Recognition2018
- Decision support system for detection of hypertensive retinopathy using arteriovenous ratioArtificial Intelligence in Medicine, 2018
- Bright spot regions segmentation and classification for specular highlights detection in colonoscopy videosMachine Vision and Applications, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Locating blood vessels in retinal images by piecewise threshold probing of a matched filter responseIEEE Transactions on Medical Imaging, 2000