Employing Graph Representations for Cell-level Characterization of Melanoma MELC Samples

TL;DR

This paper presents a novel pipeline that uses graph representations of cell-level data from MELC imaging to classify melanoma samples with high accuracy, improving over existing methods.

Contribution

It introduces a new approach combining MELC imaging with graph neural networks for detailed melanoma classification at the cellular level.

Findings

Achieves 87% classification accuracy.

Outperforms existing methods by 10%.

Utilizes cellular-level tissue characterization.

Abstract

Histopathology imaging is crucial for the diagnosis and treatment of skin diseases. For this reason, computer-assisted approaches have gained popularity and shown promising results in tasks such as segmentation and classification of skin disorders. However, collecting essential data and sufficiently high-quality annotations is a challenge. This work describes a pipeline that uses suspected melanoma samples that have been characterized using Multi-Epitope-Ligand Cartography (MELC). This cellular-level tissue characterisation is then represented as a graph and used to train a graph neural network. This imaging technology, combined with the methodology proposed in this work, achieves a classification accuracy of 87%, outperforming existing approaches by 10%.