A deep learning-based stripe self-correction method for stitched microscopic images
Problem
Stitched fluorescence microscope images contain stripes and artifacts from optics or specimens that degrade image quality and ruin downstream quantitative analysis.
Why it matters
Artifact-free microscopy images are essential for accurate biological measurements and diagnostics.
What the AI did
SSCOR, a deep learning method using proximity sampling and adversarial reciprocal self-training, corrects stripe patches using clean patches sampled from the same image, without manual annotation or parameter estimation.
Results
not stated in source (state-of-the-art performance claimed, no numeric metrics in abstract)
Impact
Claims state-of-the-art stripe and artifact correction across imaging conditions and modalities.
Record
| Venue | Nature Communications |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Shu Wang, Xixiang Liu, Yueying Li, Xinquan Sun, Qi Li, Yinhua She, Yixuan Xu, Xingxin Huang et al. |
| Citations | 36 (OpenAlex, at import time) |
| References | 57 |
| Model or method | SSCOR (deep learning, adversarial self-training) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41467-023-41165-1 |
| Open access | gold |
| Keywords | deep learning, fluorescence microscopy, image stitching, artifact removal, self-training |
Importance rating
real but narrower advance
Artifact correction improves microscopy image quality for biomedical analysis, but abstract states no scale and no numeric results; narrower technical advance.