Two-Stage Cross-Domain Cervical Abnormality Screening with Cytopathological Image Synthesis and Knowledge Distillation
For medical imaging researchers, this addresses the practical problem of domain shift in cervical abnormality screening, though the improvements are incremental over existing domain adaptation methods.
This paper tackles cross-domain cervical cell detection by proposing a two-stage framework that uses a Schrödinger bridge for image synthesis and knowledge distillation for feature alignment, achieving improved cross-domain detection performance.
Cross-domain diagnosis remains a major challenge in cervical cell pathology due to pronounced domain shifts across institutions and the subtle visual differences among disease stages, which jointly impair model generalization. To address these issues, this paper proposes a two-stage framework for cross-domain cervical cell detection. In the first stage, we propose the Spatially-Continuous Unpaired Neural Schrödinger Bridge (SC-UNSB), which constructs a synthetic intermediate domain to mitigate cross-domain distribution shifts by modeling image translation as an entropy-regularized optimal transport process. In the second stage, we propose a dual-level feature alignment strategy within a knowledge distillation, which progressively aligns shallow structural features and deep semantic representations to facilitate the transfer of domain-invariant knowledge from the source to the target model. Experimental results demonstrate that the proposed method effectively mitigates domain shift and category ambiguity, improving the cross-domain detection performance.