Cargando…

Calibrating agent-based models to tumor images using representation learning

Agent-based models (ABMs) have enabled great advances in the study of tumor development and therapeutic response, allowing researchers to explore the spatiotemporal evolution of the tumor and its microenvironment. However, these models face serious drawbacks in the realm of parameterization – ABM pa...

Descripción completa

Detalles Bibliográficos
Autores principales: Cess, Colin G., Finley, Stacey D.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10156003/
https://www.ncbi.nlm.nih.gov/pubmed/37083821
http://dx.doi.org/10.1371/journal.pcbi.1011070
_version_ 1785036448858112000
author Cess, Colin G.
Finley, Stacey D.
author_facet Cess, Colin G.
Finley, Stacey D.
author_sort Cess, Colin G.
collection PubMed
description Agent-based models (ABMs) have enabled great advances in the study of tumor development and therapeutic response, allowing researchers to explore the spatiotemporal evolution of the tumor and its microenvironment. However, these models face serious drawbacks in the realm of parameterization – ABM parameters are typically set individually based on various data and literature sources, rather than through a rigorous parameter estimation approach. While ABMs can be fit to simple time-course data (such as tumor volume), that type of data loses the spatial information that is a defining feature of ABMs. While tumor images provide spatial information, it is exceedingly difficult to compare tumor images to ABM simulations beyond a qualitative visual comparison. Without a quantitative method of comparing the similarity of tumor images to ABM simulations, a rigorous parameter fitting is not possible. Here, we present a novel approach that applies neural networks to represent both tumor images and ABM simulations as low dimensional points, with the distance between points acting as a quantitative measure of difference between the two. This enables a quantitative comparison of tumor images and ABM simulations, where the distance between simulated and experimental images can be minimized using standard parameter-fitting algorithms. Here, we describe this method and present two examples to demonstrate the application of the approach to estimate parameters for two distinct ABMs. Overall, we provide a novel method to robustly estimate ABM parameters.
format Online
Article
Text
id pubmed-10156003
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-101560032023-05-04 Calibrating agent-based models to tumor images using representation learning Cess, Colin G. Finley, Stacey D. PLoS Comput Biol Research Article Agent-based models (ABMs) have enabled great advances in the study of tumor development and therapeutic response, allowing researchers to explore the spatiotemporal evolution of the tumor and its microenvironment. However, these models face serious drawbacks in the realm of parameterization – ABM parameters are typically set individually based on various data and literature sources, rather than through a rigorous parameter estimation approach. While ABMs can be fit to simple time-course data (such as tumor volume), that type of data loses the spatial information that is a defining feature of ABMs. While tumor images provide spatial information, it is exceedingly difficult to compare tumor images to ABM simulations beyond a qualitative visual comparison. Without a quantitative method of comparing the similarity of tumor images to ABM simulations, a rigorous parameter fitting is not possible. Here, we present a novel approach that applies neural networks to represent both tumor images and ABM simulations as low dimensional points, with the distance between points acting as a quantitative measure of difference between the two. This enables a quantitative comparison of tumor images and ABM simulations, where the distance between simulated and experimental images can be minimized using standard parameter-fitting algorithms. Here, we describe this method and present two examples to demonstrate the application of the approach to estimate parameters for two distinct ABMs. Overall, we provide a novel method to robustly estimate ABM parameters. Public Library of Science 2023-04-21 /pmc/articles/PMC10156003/ /pubmed/37083821 http://dx.doi.org/10.1371/journal.pcbi.1011070 Text en © 2023 Cess, Finley https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Cess, Colin G.
Finley, Stacey D.
Calibrating agent-based models to tumor images using representation learning
title Calibrating agent-based models to tumor images using representation learning
title_full Calibrating agent-based models to tumor images using representation learning
title_fullStr Calibrating agent-based models to tumor images using representation learning
title_full_unstemmed Calibrating agent-based models to tumor images using representation learning
title_short Calibrating agent-based models to tumor images using representation learning
title_sort calibrating agent-based models to tumor images using representation learning
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10156003/
https://www.ncbi.nlm.nih.gov/pubmed/37083821
http://dx.doi.org/10.1371/journal.pcbi.1011070
work_keys_str_mv AT cesscoling calibratingagentbasedmodelstotumorimagesusingrepresentationlearning
AT finleystaceyd calibratingagentbasedmodelstotumorimagesusingrepresentationlearning