Generalizable Cervical Cancer Screening via Large-scale Pretraining and Test-Time Adaptation

2025-02-12

AI Summary

To address the poor generalizability of AI-based cervical cancer screening systems across multi-center, multi-device, and multi-staining conditions, this study proposes Smart-CCS, a universally deployable intelligent screening system. Methodologically, it introduces a two-stage paradigm: (1) large-scale self-supervised pretraining using Vision Transformer (ViT) architecture, and (2) test-time adaptation incorporating batch normalization optimization and cross-domain feature alignment; it further integrates cell-level and whole-slide interpretable predictions. Evaluated on CCS-127K—the largest publicly available whole-slide cervical cytology dataset to date (127K images from 48 clinical centers)—Smart-CCS achieves an internal test AUC of 0.965, an average external validation AUC of 0.950 across six independent centers, and prospective validation AUCs of 0.947–0.986 across three centers, with sensitivity >0.91. All predictions were histopathologically confirmed.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multi-Robot Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Cervical cancer is a leading malignancy in female reproductive system. While AI-assisted cytology offers a cost-effective and non-invasive screening solution, current systems struggle with generalizability in complex clinical scenarios. To address this issue, we introduced Smart-CCS, a generalizable Cervical Cancer Screening paradigm based on pretraining and adaptation to create robust and generalizable screening systems. To develop and validate Smart-CCS, we first curated a large-scale, multi-center dataset named CCS-127K, which comprises a total of 127,471 cervical cytology whole-slide images collected from 48 medical centers. By leveraging large-scale self-supervised pretraining, our CCS models are equipped with strong generalization capability, potentially generalizing across diverse scenarios. Then, we incorporated test-time adaptation to specifically optimize the trained CCS model for complex clinical settings, which adapts and refines predictions, improving real-world applicability. We conducted large-scale system evaluation among various cohorts. In retrospective cohorts, Smart-CCS achieved an overall area under the curve (AUC) value of 0.965 and sensitivity of 0.913 for cancer screening on 11 internal test datasets. In external testing, system performance maintained high at 0.950 AUC across 6 independent test datasets. In prospective cohorts, our Smart-CCS achieved AUCs of 0.947, 0.924, and 0.986 in three prospective centers, respectively. Moreover, the system demonstrated superior sensitivity in diagnosing cervical cancer, confirming the accuracy of our cancer screening results by using histology findings for validation. Interpretability analysis with cell and slide predictions further indicated that the system's decision-making aligns with clinical practice. Smart-CCS represents a significant advancement in cancer screening across diverse clinical contexts.

Problem

• Enhance cervical cancer screening generalizability
• Utilize large-scale pretraining for AI models
• Implement test-time adaptation for clinical settings

Innovation

• Large-scale self-supervised pretraining
• Test-time adaptation optimization
• Multi-center dataset curation