AI-assisted quantification of the clonogenic assay
- 1Department of Radiation Oncology, Mayo Clinic, Jacksonville, United States
Abstract
The clonogenic assay is the foundational standard for evaluating cellular radiosensitivity, yet its manual quantification is limited by labor-intensive processing, high inter-observer variability, and a reductive binary scoring system. Here, we present and validate a deep learning-based segmentation pipeline for the automated, high-throughput quantification of mammalian cell survival across diverse radiation qualities (photons, protons, and carbon ions). By benchmarking against expert consensus using Bland-Altman analysis, we demonstrate that this AI framework consistently operates within natural human error margins. Crucially, transitioning to automated whole-well image-based analysis enables the extraction of continuous multidimensional data, including colony area, density, and cellularity. This phenotypic profiling successfully identified and quantified high-cellularity colonies formed by radioresistant BxPC-3 cells under particle irradiation. Coupled with rapid image acquisition platforms, this methodology significantly reduces processing bottlenecks while standardizing the derivation of relative biological effectiveness (RBE). By advancing beyond binary survival metrics to continuous morphological profiling, this framework provides a vital new analytical dimension for investigating structural mechanisms of radioresistance.
Related
- Quantification by Real-Time PCR Assay of Staphylococcus aureus Load: a Useful Tool for Rapidly Identifying Persistent Nasal Carriers
- A multiplex serological assay for quantification of arbovirus antibody kinetics and neutralizing antibodies
- Quantifying Assay Confidence in Barrier Organ-on-Chip Systems: A Monte Carlo Assay-Readiness Framework for Detecting Modest Permeability Shifts
- Multiplex hyperspectral IHC: A 12-plex assay for high-dimensional analysis of the tumor microenvironment
- Benchmarking Large Language Models for Assay-Aware Drug-Target Binding Affinity Prediction
BibTeX
@misc{radstake2026aiassisted,
title = {{AI-assisted quantification of the clonogenic assay}},
author = {W. E. Radstake and A. Kneringer and J. M. Denbeigh and K. Rangan and M. Bhalloo and C. J. Beltran},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.01.755964},
url = {https://www.biorxiv.org/content/10.64898/2026.10.01.755964v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - AI-assisted quantification of the clonogenic assay
AU - W. E. Radstake
AU - A. Kneringer
AU - J. M. Denbeigh
AU - K. Rangan
AU - M. Bhalloo
AU - C. J. Beltran
PY - 2026
DA - 2026/10/01
PB - bioRxiv
DO - 10.64898/2026.10.01.755964
UR - https://www.biorxiv.org/content/10.64898/2026.10.01.755964v1
AB - The clonogenic assay is the foundational standard for evaluating cellular radiosensitivity, yet its manual quantification is limited by labor-intensive processing, high inter-observer variability, and a reductive binary scoring system. Here, we present and validate a deep learning-based segmentation pipeline for the automated, high-throughput quantification of mammalian cell survival across diverse radiation qualities (photons, protons, and carbon ions). By benchmarking against expert consensus using Bland-Altman analysis, we demonstrate that this AI framework consistently operates within natural human error margins. Crucially, transitioning to automated whole-well image-based analysis enables the extraction of continuous multidimensional data, including colony area, density, and cellularity. This phenotypic profiling successfully identified and quantified high-cellularity colonies formed by radioresistant BxPC-3 cells under particle irradiation. Coupled with rapid image acquisition platforms, this methodology significantly reduces processing bottlenecks while standardizing the derivation of relative biological effectiveness (RBE). By advancing beyond binary survival metrics to continuous morphological profiling, this framework provides a vital new analytical dimension for investigating structural mechanisms of radioresistance.
ER -