High-Precision Mixed Feature Fusion Network Using Hypergraph Computation for Cervical Abnormal Cell Detection

2025-08-22

AI Summary

Existing TCT-image-based methods for abnormal cervical cell detection struggle to model inter-cell spatial correlations and fail to jointly optimize and end-to-end integrate inter-cell relational features with intra-cell discriminative features. To address this, we propose a hypergraph-computation-driven cross-level feature fusion framework comprising a Multi-Level Fusion Subnetwork (MLF-SNet) and a Hypergraph-based Cross-Level Feature Fusion Module (CLFFS-HC). This is the first approach to simultaneously model inter-cell spatial dependencies and extract deep intra-cell discriminative representations within a unified, end-to-end trainable architecture. Evaluated on three public TCT datasets, our method significantly outperforms state-of-the-art baselines, achieving average improvements of 4.2% in precision and 5.8% in recall. It demonstrates enhanced robustness in identifying complex pathological morphologies, particularly under challenging imaging conditions and heterogeneous cellular appearances.

Technology Category

• Computer Vision: Other Foundations of Computer Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Automatic detection of abnormal cervical cells from Thinprep Cytologic Test (TCT) images is a critical component in the development of intelligent computer-aided diagnostic systems. However, existing algorithms typically fail to effectively model the correlations of visual features, while these spatial correlation features actually contain critical diagnostic information. Furthermore, no detection algorithm has the ability to integrate inter-correlation features of cells with intra-discriminative features of cells, lacking a fusion strategy for the end-to-end detection model. In this work, we propose a hypergraph-based cell detection network that effectively fuses different types of features, combining spatial correlation features and deep discriminative features. Specifically, we use a Multi-level Fusion Sub-network (MLF-SNet) to enhance feature extractioncapabilities. Then we introduce a Cross-level Feature Fusion Strategy with Hypergraph Computation module (CLFFS-HC), to integrate mixed features. Finally, we conducted experiments on three publicly available datasets, and the results demonstrate that our method significantly improves the performance of cervical abnormal cell detection.

Problem

• Detecting abnormal cervical cells in TCT images automatically
• Modeling spatial correlation features among cervical cells effectively
• Integrating inter-correlation and intra-discriminative features for detection

Innovation

• Hypergraph computation for feature fusion
• Multi-level fusion sub-network for extraction
• Cross-level feature fusion strategy integration