Graph Neural Networks in Multi-Stained Pathological Imaging: Extended Comparative Analysis of Radiomic Features

Abstract Purpose: This study investigates Radiomics features for Graph Neural Networks (GNNs) in MELC pathology sample classification focusing on often misdiagnosed skin diseases. Methods: GNNs processing multiple pathological slides together as cell-level graphs are compared to XGBoost and Random Forest. The analysis assesses the use of MELC vs. Radiomics features, their dimensionality reduction with UMAP or tSNE and the graph connectivity based on spatial and feature closeness. Results: Integrating Radiomics features in a spatially connected graph markedly outperforms standard models when classifying pathologically similar diseases. Additionally, the UMAP dimensionality reduction techniques improves GNN classification performance. Conclusion: Radiomics, processed with GNNs, shows promise for multi-disease classification, enhancing diagnosis accuracy. Considering the potential, future research should extend these methods to a broader range of diseases.