Hypergraph aggregation contrastive learning network for lung cancer prognostic prediction based on tumor microenvironment

Lung cancer remains a leading cause of cancer-related deaths globally, with non-small cell lung cancer (NSCLC) accounting for approximately 85% of cases. The tumor microenvironment (TME) plays a crucial role in lung cancer progression and treatment response. Multiplex immunofluorescence (MIF) technology provides a unique perspective for analyzing spatial relationships within the complex TME. However, existing methods for processing MIF pathological images often process each image in isolation, overlooking both intra-patient multi-image complementarity and inter-patient pathological similarities. To address these limitations, we introduce the Hypergraph Aggregation Contrastive Learning Network (HACLN), which constructs a hypergraph to jointly model intra-patient multi-image features and inter-patient pathological relationships. HACLN aggregates features from multiple MIF images per patient, decomposes them into specialized subgraphs, and integrates them to enhance feature discrimination. We validate HACLN using an immunofluorescence image dataset from the First Affiliated Hospital of Guangzhou Medical University, demonstrating its effectiveness in capturing microenvironmental features and modeling patient-to-patient similarities. Here, we show that HACLN achieves a C-index of 0.7023, outperforming existing methods, providing a new direction for future research in lung cancer prognostic prediction based on the tumor microenvironment. Code is available at: https://github.com/sujuKyukyu/HACLN_code