Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.05250 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910012247375872 |
|---|---|
| author | Tan, Jieyun Liu, Shuo Zhang, Guibin Li, Ziqi Geng, Jian Zhang, Lei Cao, Lei |
| author_facet | Tan, Jieyun Liu, Shuo Zhang, Guibin Li, Ziqi Geng, Jian Zhang, Lei Cao, Lei |
| contents | Automated detection of electron dense deposits (EDD) in glomerular disease is hindered by the scarcity of high-quality labeled data. While crowdsourcing reduces annotation cost, it introduces label noise. We propose an active label cleaning method to efficiently denoise crowdsourced datasets. Our approach uses active learning to select the most valuable noisy samples for expert re-annotation, building high-accuracy cleaning models. A Label Selection Module leverages discrepancies between crowdsourced labels and model predictions for both sample selection and instance-level noise grading. Experiments show our method achieves 67.18% AP\textsubscript{50} on a private dataset, an 18.83% improvement over training on noisy labels. This performance reaches 95.79% of that with full expert annotation while reducing annotation cost by 73.30%. The method provides a practical, cost-effective solution for developing reliable medical AI with limited expert resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05250 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images Tan, Jieyun Liu, Shuo Zhang, Guibin Li, Ziqi Geng, Jian Zhang, Lei Cao, Lei Computer Vision and Pattern Recognition Automated detection of electron dense deposits (EDD) in glomerular disease is hindered by the scarcity of high-quality labeled data. While crowdsourcing reduces annotation cost, it introduces label noise. We propose an active label cleaning method to efficiently denoise crowdsourced datasets. Our approach uses active learning to select the most valuable noisy samples for expert re-annotation, building high-accuracy cleaning models. A Label Selection Module leverages discrepancies between crowdsourced labels and model predictions for both sample selection and instance-level noise grading. Experiments show our method achieves 67.18% AP\textsubscript{50} on a private dataset, an 18.83% improvement over training on noisy labels. This performance reaches 95.79% of that with full expert annotation while reducing annotation cost by 73.30%. The method provides a practical, cost-effective solution for developing reliable medical AI with limited expert resources. |
| title | Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.05250 |