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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Monroy, Luis Carlos Rivera, Rist, Leonhard, Eberhardt, Martin, Ostalecki, Christian, Baur, Andreas, Vera, Julio, Breininger, Katharina, Maier, Andreas
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912086830874624
author Monroy, Luis Carlos Rivera
Rist, Leonhard
Eberhardt, Martin
Ostalecki, Christian
Baur, Andreas
Vera, Julio
Breininger, Katharina
Maier, Andreas
author_facet Monroy, Luis Carlos Rivera
Rist, Leonhard
Eberhardt, Martin
Ostalecki, Christian
Baur, Andreas
Vera, Julio
Breininger, Katharina
Maier, Andreas
contents 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%.
format Preprint
id arxiv_https___arxiv_org_abs_2211_05884
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Employing Graph Representations for Cell-level Characterization of Melanoma MELC Samples
Monroy, Luis Carlos Rivera
Rist, Leonhard
Eberhardt, Martin
Ostalecki, Christian
Baur, Andreas
Vera, Julio
Breininger, Katharina
Maier, Andreas
Computer Vision and Pattern Recognition
Artificial Intelligence
Computational Engineering, Finance, and Science
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%.
title Employing Graph Representations for Cell-level Characterization of Melanoma MELC Samples
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2211.05884