End-to-end plaque counting and virus titration from laboratory plate images with deep learning

2026-05-15

AI Summary

This study addresses the inefficiency and subjectivity inherent in manual plaque counting in traditional plaque assays by proposing an end-to-end deep learning framework for fully automated viral titer (PFU/mL) quantification. The method uniquely integrates the Segment Anything Model (SAM) and its successor SAM2 to perform well localization and plaque segmentation, respectively, enabling robust performance across diverse virus types and plate formats. The system is complemented by an interactive web-based review platform and has been rigorously validated on multi-virus datasets, demonstrating strong agreement with manual annotations (Pearson correlation coefficients ranging from 0.88 to 0.92). This approach substantially reduces manual labor while maintaining high accuracy, and the implementation code will be publicly released.

Abstract

Plaque assays remain the gold standard readout of virus infectivity; however, plaque counting from plate images is labor-intensive and prone to inter-operator variability. We present an end-to-end, computer-aided workflow for cytopathic effect-based virus titration directly from laboratory plaque assay images. The proposed approach combines two models derived from the Segment Anything Model (SAM): a SAM2-based well-segmentation module that localizes assay wells across heterogeneous imaging conditions, and a SAM-based plaque-segmentation model that detects and enumerates plaques within each well. The method was evaluated on a mixed dataset comprising private plaque assay images of Mayaro virus and Coxsackievirus B3, together with public Vaccinia virus images from the VACVPlaque dataset. The pipeline outputs per-well plaque counts, automatically computes plaque-forming units per milliliter (PFU/mL), and is integrated into a web-based platform that allows users to review results and organize experiments. On held-out plates (17 from MAYV/CVB3 and 22 from VACV), the workflow generalized across two plate formats (6-well and 12-well) and showed strong agreement with manual annotations (Pearson correlation coefficients of 0.92 for MAYV/CVB3 and 0.88 for VACV). Automated plaque counts were further compared with annotations from four independent experts, demonstrating high concordance. The proposed system will be open sourced and publicly released upon acceptance of this manuscript to enable reproducible, scalable, and audit-ready plaque assay analysis while substantially reducing manual annotation effort.

Problem

• plaque counting
• virus titration
• inter-operator variability
• labor-intensive
• plaque assay

Innovation

• deep learning
• plaque assay
• Segment Anything Model
• virus titration
• automated counting