Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection

TL;DR

This paper introduces a novel cross-domain knowledge transfer method using prototype-based filtering and alignment techniques to improve automatic cervical dysplasia diagnosis from visual images, especially in low-resource settings.

Contribution

It proposes a new prototype-based knowledge filtering and alignment approach for effective cross-domain transfer learning in cervical dysplasia detection.

Findings

Outperforms state-of-the-art methods with 4.7% higher top-1 accuracy

Achieves 7.0% better precision and 1.4% higher recall

Improves F1 score by 4.6% and ROC-AUC by 0.05

Abstract

Early detection of dysplasia of the cervix is critical for cervical cancer treatment. However, automatic cervical dysplasia diagnosis via visual inspection, which is more appropriate in low-resource settings, remains a challenging problem. Though promising results have been obtained by recent deep learning models, their performance is significantly hindered by the limited scale of the available cervix datasets. Distinct from previous methods that learn from a single dataset, we propose to leverage cross-domain cervical images that were collected in different but related clinical studies to improve the model's performance on the targeted cervix dataset. To robustly learn the transferable information across datasets, we propose a novel prototype-based knowledge filtering method to estimate the transferability of cross-domain samples. We further optimize the shared feature space by aligning the cross-domain image representations simultaneously on domain level with early alignment and class level with supervised contrastive learning, which endows model training and knowledge transfer with stronger robustness. The empirical results on three real-world benchmark cervical image datasets show that our proposed method outperforms the state-of-the-art cervical dysplasia visual inspection by an absolute improvement of 4.7% in top-1 accuracy, 7.0% in precision, 1.4% in recall, 4.6% in F1 score, and 0.05 in ROC-AUC.