Digital Staining with Knowledge Distillation: A Unified Framework for Unpaired and Paired-But-Misaligned Data
Journal:
arXiv
Published Date:
Apr 14, 2025
Abstract
Staining is essential in cell imaging and medical diagnostics but poses
significant challenges, including high cost, time consumption, labor intensity,
and irreversible tissue alterations. Recent advances in deep learning have
enabled digital staining through supervised model training. However, collecting
large-scale, perfectly aligned pairs of stained and unstained images remains
difficult. In this work, we propose a novel unsupervised deep learning
framework for digital cell staining that reduces the need for extensive paired
data using knowledge distillation. We explore two training schemes: (1)
unpaired and (2) paired-but-misaligned settings. For the unpaired case, we
introduce a two-stage pipeline, comprising light enhancement followed by
colorization, as a teacher model. Subsequently, we obtain a student staining
generator through knowledge distillation with hybrid non-reference losses. To
leverage the pixel-wise information between adjacent sections, we further
extend to the paired-but-misaligned setting, adding the Learning to Align
module to utilize pixel-level information. Experiment results on our dataset
demonstrate that our proposed unsupervised deep staining method can generate
stained images with more accurate positions and shapes of the cell targets in
both settings. Compared with competing methods, our method achieves improved
results both qualitatively and quantitatively (e.g., NIQE and PSNR).We applied
our digital staining method to the White Blood Cell (WBC) dataset,
investigating its potential for medical applications.
