An open imaging and AI resource enabling unbiased quantification of extrachromosomal DNA at scale
- 1University of North Carolina at Chapel Hill
Abstract
Quantitative imaging of extrachromosomal DNA (ecDNA) is increasingly important for studying cancer heterogeneity and adaptation, yet automated analysis has been limited by the absence of accessible imaging data, gold standard annotations and adaptable computational tools. Here we establish an open resource for computational ecDNA imaging, integrating 2,986 native-resolution metaphase FISH image sets with manual annotations, standardized benchmarks and open-source quantification frameworks. We use this resource to systematically compare existing and newly developed approaches spanning rule-based computer vision, deep-learning-based segmentation and probabilistic localization. This comparison reveals count-dependent underestimation that distorts ecDNA copy-number distributions and motivates ecCount, a probabilistic localization method developed here to preserve individual ecDNA signals and quantitative burden. ecCount achieves an object-level F1 score of 0.939 on held-out images with minimal count bias. Together, the images, annotations, retrainable models, evaluation tools and guided workflows provide community infrastructure for applying, adapting and improving automated ecDNA quantification across experimental systems.
Related
- GaussF: An Unbiased Gaussian Framework for High-Precision Transcript Quantification with a Programmable Self-Benchmark Model
- MRSIPrep: A Standardized Post-Quantification Framework for Preprocessing Whole-Brain Magnetic Resonance Spectroscopic Imaging
- Visualization and quantification of phage-induced bacterial lysis by phosphotungstic acid-based SEM imaging
- Impacts of retrospective lipid suppression on metabolite quantification in preclinical proton MR spectroscopic imaging
- An imaging framework for nuclei-based three-dimensional cell quantification in intact tissue using phase-contrast X-ray CT
BibTeX
@misc{behnamie2026open,
title = {{An open imaging and AI resource enabling unbiased quantification of extrachromosomal DNA at scale}},
author = {P. Behnamie and R. Summers and J. Chen and A. Mehta and A. Igbinigie and Q. Liu and M. Murray and D. Guilbaud and M. Niethammer and E. C. Brunk},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.18.752721},
url = {https://www.biorxiv.org/content/10.64898/2026.09.18.752721v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - An open imaging and AI resource enabling unbiased quantification of extrachromosomal DNA at scale
AU - P. Behnamie
AU - R. Summers
AU - J. Chen
AU - A. Mehta
AU - A. Igbinigie
AU - Q. Liu
AU - M. Murray
AU - D. Guilbaud
AU - M. Niethammer
AU - E. C. Brunk
PY - 2026
DA - 2026/09/18
PB - bioRxiv
DO - 10.64898/2026.09.18.752721
UR - https://www.biorxiv.org/content/10.64898/2026.09.18.752721v1
AB - Quantitative imaging of extrachromosomal DNA (ecDNA) is increasingly important for studying cancer heterogeneity and adaptation, yet automated analysis has been limited by the absence of accessible imaging data, gold standard annotations and adaptable computational tools. Here we establish an open resource for computational ecDNA imaging, integrating 2,986 native-resolution metaphase FISH image sets with manual annotations, standardized benchmarks and open-source quantification frameworks. We use this resource to systematically compare existing and newly developed approaches spanning rule-based computer vision, deep-learning-based segmentation and probabilistic localization. This comparison reveals count-dependent underestimation that distorts ecDNA copy-number distributions and motivates ecCount, a probabilistic localization method developed here to preserve individual ecDNA signals and quantitative burden. ecCount achieves an object-level F1 score of 0.939 on held-out images with minimal count bias. Together, the images, annotations, retrainable models, evaluation tools and guided workflows provide community infrastructure for applying, adapting and improving automated ecDNA quantification across experimental systems.
ER -