Inductive bias influences the spatial scale of biological features learned from images
Bioinformatics Advances · 07.01.2026 · 6 (1)
DOI: 10.1093/bioadv/vbag238 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics Advances, online erschienen am 17.08.2026. Verfasst von Jacob I Evarts und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biology, University of Washington, Seattle, WA 98195, United States. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NICHD NIH HHS, National Science Foundation Graduate Research, National Institutes of Health.
Abstract (Originalsprache)
Motivation The inductive bias of a deep learning model influences the features it extracts from biological images, making model selection a critical scientific decision. We systematically compare representations learned from scratch without pre-training by convolutional neural networks (CNNs), vision transformers, and Fourier neural operators (FNOs)—an emerging architecture largely unexplored in biological imaging—to determine how their distinct learning mechanisms shape feature learning from spatiotemporal data. Results Using a self-supervised representation learning framework on microscopy images of 2D gastruloids, as well as a distinct synthetic tumor image dataset, we show that while CNNs and FNOs achieve comparable accuracy on biological tasks, they learn features at different scales. Visual interpretation methods reveal that CNNs prioritize local, fine-grained details, whereas FNOs capture global, low-frequency structures, in line with overall population morphology. These findings demonstrate that deep learning model architecture is a choice that shapes the biological scale of extracted features, highlighting the need to align a model’s inductive bias with the scientific question. Availability and implementation All source code for the representation learning model, the tumor simulation dataset, and the gastruloid microscopy imaging dataset are available at the corresponding DOIs: https://doi.org/10.5281/zenodo.19672838, https://doi.org/10.5281/zenodo.19361370, https://doi.org/10.5281/zenodo.19373112, respectively.
Autor:innen und Institutionen
- Department of Biology, University of Washington, Seattle, WA 98195, United States.
- Department of Chemical Engineering, University of Washington, Seattle, WA 98195, United States.
- Department of Bioengineering, University of Washington, Seattle, WA 98195, United States.
ORCID-Profile: Neda Bagheri
Förderung
- NICHD NIH HHS
- National Science Foundation Graduate Research
- National Institutes of Health
- Washington Research Foundation
Zitieren
APA
Evarts, J. I., Cain, J. Y., Chiu, P. H., Jan, I., Allbritton, N. L., & Bagheri, N. (2026). Inductive bias influences the spatial scale of biological features learned from images. Bioinformatics Advances, 6(1). https://doi.org/10.1093/bioadv/vbag238
Vancouver
Evarts JI, Cain JY, Chiu PH, Jan I, Allbritton NL, Bagheri N. Inductive bias influences the spatial scale of biological features learned from images. Bioinformatics Advances. 2026;6(1). doi:10.1093/bioadv/vbag238
BibTeX
@article{Evarts2026,
author = {Evarts, Jacob I and Cain, Jason Y and Chiu, Po-Hao and Jan, Ian and Allbritton, Nancy L and Bagheri, Neda},
title = {Inductive bias influences the spatial scale of biological features learned from images},
journal = {Bioinformatics Advances},
year = {2026},
volume = {6},
number = {1},
doi = {10.1093/bioadv/vbag238}
}
EUVIMED