Efficiency and safety of automated label cleaning on multimodal retinal images
Abstract Label noise is a common and important issue that would affect the model’s performance in artificial intelligence. This study assessed the effectiveness and potential risks of automated label cleaning using an open-source framework, Cleanlab, in multi-category datasets of fundus photography...
Saved in:
Main Authors: | Tian Lin, Meng Wang, Aidi Lin, Xiaoting Mai, Huiyu Liang, Yih-Chung Tham, Haoyu Chen |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2025-01-01
|
Series: | npj Digital Medicine |
Online Access: | https://doi.org/10.1038/s41746-024-01424-x |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Multimodal heterogeneous graph fusion for automated obstructive sleep apnea-hypopnea syndrome diagnosis
by: Haoyu Wang, et al.
Published: (2024-11-01) -
Learning with noisy labels via clean aware sharpness aware minimization
by: Bin Huang, et al.
Published: (2025-01-01) -
A multimodal transformer system for noninvasive diabetic nephropathy diagnosis via retinal imaging
by: Zheyi Dong, et al.
Published: (2025-01-01) -
Utility of multimodal imaging in the clinical diagnosis of inherited retinal degenerations
by: Brian J. H. Lee, et al.
Published: (2024-12-01) -
Evaluation of a Novel Water-Based Automated Endoscope Cleaning Process Compared to Conventional Manual Cleaning for Reducing Duodenoscope Contaminatio
by: Koen van der Ploeg, et al.