ARGUS: Accelerated, Robust, General, and Unsupervised Cell Tracking Solutions

Jul 16, 2026

Upload by Aurelia

ARGUS is a modular framework for accelerated, robust, general, and unsupervised cell tracking in time-lapse microscopy, targeting the core difficulty of quantitative cell-dynamics analysis under noise, morphological variability, overlapping cells, and complex events like divisions and fusions. The method combines adaptive cell detection, dense Farneback optical-flow prediction, frame-to-frame linear assignment, and sequence-level tracklet refinement to reconnect trajectories across short temporal gaps. On Cell Tracking Challenge datasets, it achieves detection accuracy of 0.905–0.971 and tracking accuracy of 0.897–0.964 within about one minute, and requires no training data or GPU infrastructure.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

Abstract

Introduction

Challenges in 2D Cell Tracking

Benchmarking on Cell Tracking Challenge

Categories of Tracking Methods

Local vs Global Approaches

Dynamic Programming

Integer Linear Programming

Minimum-Cost Flow

Optical-Flow-Based Methods

Proposed ARGUS Framework

Two-Stage Association Strategy

Component Overview

arXiv :2607 .08297v 1 [ cs .CV] 9 Jul 2026 ARGUS: Accelerated, Robust, General, and Unsupervised Cell Tracking Solutions Noah Jaitner 1 Kandice Tanner2 Ingolf Sack 1 Hossein S. Aghamiry 1,* 1 Department of Radiology, Charité – Universitätsmedizin Berlin, 10117 Berlin, Germany 2 Laboratory of Cell Biology, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA * Corresponding author: [hossein.aghamiry@charite.de](hossein.aghamiry@charite.de) Abstract Background and Objective: Quantitative analysis of cell dynamics is central to modern biological research, providing critical insights into immune cell interactions, disease progression, and drug mechanisms. Automated cell tracking in time-lapse microscopy remains challenging due to noise, morphological variations, overlapping cells, and dynamic events such as divisions and fusions. Methods: We present ARGUS, a framework for Accelerated, Robust, General, and Unsupervised cell tracking Solutions. ARGUS combines adaptive cell detection, dense Farneback optical-flow prediction, frame-to-frame linear assignment, and a sequence-level tracklet-refinement step that reconnects trajectory fragments across short temporal gaps. Results: On publicly available Cell Tracking Challenge datasets, ARGUS achieved detection accuracy of 0.905–0.971 and tracking accuracy of 0.897–0.964, with runtimes within 1 minute (5–6 seconds for 3 frames) . Conclusions: ARGUS is a modular, interpretable framework that can be adapted to different imaging modalities and biological applications without training data or GPU infrastructure. The implementation is publicly available at [https://github.com/Gitinc/argus](https://github.com/Gitinc/argus). Keywords: Cell tracking; Optical flow; Monogenic signal; Assignment problem; Tracklet association; Time-lapse microscopy 1 Introduction Live-cell imaging combined with quantitative cell tracking has become essential for studying cellular processes. By tracking cells over time, researchers can directly observe migration, proliferation, differentiation, and apoptosis [1] . They can also characterize how cells interact and respond to therapeutic compounds [1–4] . From a clinical perspective, these measurements are important for CAR-T cell therapy [2], high-throughput drug screening [3], and detection of circulating tumor cells [5, 6] . Development of automated, large-scale spatiotemporal imaging methods allows millions of cells to be imaged per day at subcellular resolution [7] . However, the resulting terabyte-scale datasets require efficient computational methods that can extract reliable quantitative information [1, 8] . 2D live-cell microscopy tracking remains computationally challenging. The Cell Tracking Challenge (CTC), an ongoing community benchmark, has assessed algorithmic progress over the past decade [7, 9 , 10] . No method has yet achieved perfect accuracy across all datasets. Reported scores range from 52% to 99%, depending on dataset complexity [7] . These challenges arise from image noise, defocused cells, morphological variability, overlapping cells, cell division, fusion, and data volumes that often exceed 500 GB. Existing tracking methods can be broadly grouped into local and global approaches. Local methods, such as nearest-neighbor linking, are computationally fast but prone to errors during occlusion and division. In such cases, accuracy can decrease by 20-30%[7] . Global methods consider the full image sequence and usually achieve higher accuracy through three main optimization strategies: • Dynamic Programming: The Viterbi algorithm and related methods [11] maximize a scoring function over event probabilities across the full sequence. These approaches can produce globally optimal tracks, but their complexity often scales quadratically with the number of detections. Notably, the KTH-SE algorithm [12] showed that a classical Viterbi formulation, without machine learning,

FAQs

What problem does ARGUS address in time-lapse microscopy?

ARGUS targets automated cell tracking that is difficult due to noise, changing cell shapes, overlapping cells, and dynamic events such as divisions and fusions.

How does ARGUS generate and refine cell trajectories?

ARGUS first predicts dense motion with Farneback optical flow and then uses frame-to-frame linear assignment to form initial trajectory fragments. It then performs sequence-level tracklet refinement to reconnect compatible fragments across short temporal gaps.

What performance does ARGUS achieve on public benchmarks, and what resources does it require?

On Cell Tracking Challenge datasets, ARGUS reports detection accuracy of 0.905–0.971 and tracking accuracy of 0.897–0.964 with runtimes within about one minute, and it can run without training data or GPU infrastructure.

Jul 16, 2026

Upload by Aurelia