Multi-annotation agreement and prediction consistency networks: Improving semi-supervised segmentation of medical images with ambiguous boundaries
- 4 November 2025
- journal article
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 171, 103289
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (62571173)
- National Natural Science Foundation of China (62201323)
- Natural Science Foundation of Zhejiang Province (LD25F020005)
- Natural Science Foundation of Zhejiang Province (LQN25F030009)
- Natural Science Foundation of Zhejiang Province (LDT23F01015F01)
This publication has 26 references indexed in Scilit:
- Plug‐and‐play segment anything model improves nnUNet performanceMedical Physics, 2024
- Semi-supervised pathological image segmentation via cross distillation of multiple attentions and Seg-CAM consistencyPattern Recognition, 2024
- Segment anything in medical imagesNature Communications, 2024
- Multi-rater label fusion based on an information bottleneck for fundus image segmentationBiomedical Signal Processing and Control, 2022
- Interpolation consistency training for semi-supervised learningNeural Networks, 2022
- Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision2021
- Semi-Supervised Semantic Segmentation With Cross-Consistency Training2020
- REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographsMedical Image Analysis, 2020
- Agreement among ophthalmologists in marking the optic disc and optic cup in fundus imagesInternational Ophthalmology, 2016
- Fully convolutional networks for semantic segmentation2015