Employing Graph Representations for Cell-level Characterization of Melanoma MELC Samples
This work addresses the challenge of limited data and annotations in computer-assisted diagnosis of skin diseases like melanoma, offering a domain-specific improvement.
The paper tackled the problem of classifying melanoma samples from histopathology imaging by representing cellular-level tissue characterizations as graphs and training a graph neural network, achieving a classification accuracy of 87% and outperforming existing approaches by 10%.
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%.