A Deformable-Based Source-Free Unsupervised Domain Adaptation Method for Cervical Cell Detection

Abstract

As the application of AI in cervical cancer cell detection expands, the demand for large-scale labeled pathological slide data has increased, resulting in a time-consuming and costly process. Furthermore, significant domain shifts caused by variations in sample collection, processing, and staining conditions across different medical institutions limit the generalization capability of detection models. To address these challenges, existing unsupervised domain adaptation (UDA) methods attempt to generalize source domain models to target domains with unannotated data, reducing reliance on annotated datasets. However, these approaches still face challenges, such as the unavailability of source data, label noise leading to model degradation, and insufficient convolutional feature extraction. To overcome these limitations, this paper proposes a Deformable-based Source-Free Unsupervised Domain Adaptation (DSFUDA) method for cervical cell detection, which utilizes only on the source domain model and unlabeled target domain data. The proposed approach introduces a novel source-free UDA framework for cervical cell detection, incorporating a denoising module based on a diffusion model (FD-Module) to suppress erroneous and domain-specific features, preventing model degradation. Additionally, a deformable context-aware module (DCA-Module) is developed to adaptively adjust convolutional receptive fields, enhancing feature extraction and improving the accuracy of abnormal cell detection. The effectiveness of the proposed method is validated on two public datasets, CDTBS and Sipakmed.