Comparative Analysis of Radiomic Features and Gene Expression Profiles in Histopathology Data Using Graph Neural Networks

TL;DR

This paper demonstrates that combining radiomic features with gene expression data using graph neural networks improves melanoma classification accuracy and efficiency, highlighting the potential for cost-effective diagnostic methods in computational dermatology.

Contribution

It introduces a novel approach integrating radiomic features and gene expression profiles via graph neural networks for melanoma classification, emphasizing the benefits of dimensionality reduction and operational cost savings.

Findings

Radiomic features enhance classification accuracy.

Combining radiomics with gene expression improves performance.

Dimensionality reduction with UMAP is effective.

Abstract

This study leverages graph neural networks to integrate MELC data with Radiomic-extracted features for melanoma classification, focusing on cell-wise analysis. It assesses the effectiveness of gene expression profiles and Radiomic features, revealing that Radiomic features, particularly when combined with UMAP for dimensionality reduction, significantly enhance classification performance. Notably, using Radiomics contributes to increased diagnostic accuracy and computational efficiency, as it allows for the extraction of critical data from fewer stains, thereby reducing operational costs. This methodology marks an advancement in computational dermatology for melanoma cell classification, setting the stage for future research and potential developments.