Calibrating agent-based models to tumor images using representation learning
PLOS Computational Biology · 21.04.2023 · 19 (4) · e1011070
DOI: 10.1371/journal.pcbi.1011070 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 21.04.2023. Verfasst von Colin G Cess und 1 weiteren Autor:innen. Beteiligte Einrichtung: Alfred E. Mann Department of Biomedical Engineering, University of Southern California, Los Angeles, California, United States of America. Hauptthemen laut MEDLINE: Algorithms, Neoplasms. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: USC Center for Computational Modeling of Cancer, USC Ming Hsieh Institute.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Alfred E. Mann Department of Biomedical Engineering, University of Southern California, Los Angeles, California, United States of America.
- Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, California, United States of America.
- Mork Family Department of Chemical Engineering and Materials Science, University of Southern California, Los Angeles, California, United States of America.
ORCID-Profile: Stacey D Finley
Förderung
- USC Center for Computational Modeling of Cancer
- USC Ming Hsieh Institute
Zitieren
APA
Cess, C. G., & Finley, S. D. (2023). Calibrating agent-based models to tumor images using representation learning. PLOS Computational Biology, 19(4), e1011070. https://doi.org/10.1371/journal.pcbi.1011070
Vancouver
Cess CG, Finley SD. Calibrating agent-based models to tumor images using representation learning. PLOS Computational Biology. 2023;19(4):e1011070. doi:10.1371/journal.pcbi.1011070
BibTeX
@article{Cess2023,
author = {Cess, Colin G and Finley, Stacey D},
title = {Calibrating agent-based models to tumor images using representation learning},
journal = {PLOS Computational Biology},
year = {2023},
volume = {19},
number = {4},
pages = {e1011070},
doi = {10.1371/journal.pcbi.1011070}
}
EUVIMED