Sam-Correction: Fully Adaptive Label Noise Reduction for Medical Image Segmentation
Abstract
The quality of the teacher label has a dramatic impact on the outcome of the machine learning process. Medical image segmentation often suffers from a noisy ground truth (GT) mask due to difficulties in consistent annotation. Although a recent study has proposed a promising method to curate the noisy GT mask, this requires additional well-curated GT masks that are not always accessible without the aid of multiple medical experts. As an alternative, we propose SAM-Correction, which utilizes a foundation model to correct the noisy GT mask in a fully adaptive manner instead of manually preparing well-curated masks. In our approach, we progressively mitigate label noise via the segment anything model (SAM), where prompts are given from another segmentation network that we train concurrently. Experiments with various types of label noise derived from actual human annotations demonstrate that SAM-C achieves precise noise reduction and high-performing segmentation models trained thereby. Our method paves the way for robust model training even when clean labels are entirely unavailable.
Versions
Related
- Fully automated diaphragm segmentation on routine 2D-cine and 3D thoracic MRI: multireader validation
- Anisotropic overlap reduction functions for arbitrary equal-arm TDI channels: A fully analytic framework and efficient evaluation
- Quantitative Fabrication-Error Reduction in Optomechanical Crystal using Proximity Error Correction
- Peripheral prototypical contrastive loss for supervised medical image segmentation
- Full-Stokes response to a stochastic gravitational-wave background in pulsar timing arrays: Fully analytic overlap reduction functions at finite distance and coherence of close pulsar pairs
BibTeX
@misc{shimaya2026samcorrection,
title = {{Sam-Correction: Fully Adaptive Label Noise Reduction for Medical Image Segmentation}},
author = {Takuro Shimaya and Masahiro Saiko},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32377},
eprint = {2610.32377},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32377},
}
RIS
TY - UNPB
TI - Sam-Correction: Fully Adaptive Label Noise Reduction for Medical Image Segmentation
AU - Takuro Shimaya
AU - Masahiro Saiko
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.32377
UR - https://arxiv.org/abs/2610.32377
AB - The quality of the teacher label has a dramatic impact on the outcome of the machine learning process. Medical image segmentation often suffers from a noisy ground truth (GT) mask due to difficulties in consistent annotation. Although a recent study has proposed a promising method to curate the noisy GT mask, this requires additional well-curated GT masks that are not always accessible without the aid of multiple medical experts. As an alternative, we propose SAM-Correction, which utilizes a foundation model to correct the noisy GT mask in a fully adaptive manner instead of manually preparing well-curated masks. In our approach, we progressively mitigate label noise via the segment anything model (SAM), where prompts are given from another segmentation network that we train concurrently. Experiments with various types of label noise derived from actual human annotations demonstrate that SAM-C achieves precise noise reduction and high-performing segmentation models trained thereby. Our method paves the way for robust model training even when clean labels are entirely unavailable.
ER -