Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SINETRA: a Versatile Framework for Evaluating Single Neuron Tracking in Behaving Animals

Raphael Reme, Alasdair Newson, Elsa Angelini, Jean-Christophe Olivo-Marin, Thibault Lagache

TL;DR

This work developed SINETRA, a versatile simulator that generates synthetic tracking data for particles on a deformable background, closely mimicking live animal recordings, and evaluated four state-of-the-art tracking algorithms highlighting the current limitations of these methods in challenging scenarios.

Abstract

Accurately tracking neuronal activity in behaving animals presents significant challenges due to complex motions and background noise. The lack of annotated datasets limits the evaluation and improvement of such tracking algorithms. To address this, we developed SINETRA, a versatile simulator that generates synthetic tracking data for particles on a deformable background, closely mimicking live animal recordings. This simulator produces annotated 2D and 3D videos that reflect the intricate movements seen in behaving animals like Hydra Vulgaris. We evaluated four state-of-the-art tracking algorithms highlighting the current limitations of these methods in challenging scenarios and paving the way for improved cell tracking techniques in dynamic biological systems.

SINETRA: a Versatile Framework for Evaluating Single Neuron Tracking in Behaving Animals

TL;DR

This work developed SINETRA, a versatile simulator that generates synthetic tracking data for particles on a deformable background, closely mimicking live animal recordings, and evaluated four state-of-the-art tracking algorithms highlighting the current limitations of these methods in challenging scenarios.

Abstract

Accurately tracking neuronal activity in behaving animals presents significant challenges due to complex motions and background noise. The lack of annotated datasets limits the evaluation and improvement of such tracking algorithms. To address this, we developed SINETRA, a versatile simulator that generates synthetic tracking data for particles on a deformable background, closely mimicking live animal recordings. This simulator produces annotated 2D and 3D videos that reflect the intricate movements seen in behaving animals like Hydra Vulgaris. We evaluated four state-of-the-art tracking algorithms highlighting the current limitations of these methods in challenging scenarios and paving the way for improved cell tracking techniques in dynamic biological systems.

Paper Structure

This paper contains 18 sections, 9 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Method
  3. Modeling fluorescent particles and background
  4. Particles
  5. Background & Noise
  6. Intensity variations
  7. Shape evolution
  8. Motion modeling
  9. Optical flow motion
  10. Springs motion
  11. Damped harmonic oscillators
  12. Results and Discussions
  13. Evaluation
  14. Evaluated algorithms
  15. Results
  16. ...and 3 more sections

Figures (3)

  • Figure 1: Synthetic image simulator (Hydra flow) (a) A synthetic image using the default imaging parameters $\alpha=0.2$ and $\Delta=50$. (b) Synthetic tracks on 50 frames centered around a contraction (frames 90 to 140, with a contraction at $t = 100$). (c) 100x100 pixels from fluorescence videos of Hydra Vulgaris' neurons hanson2024automaticdupre2017non. (d) 100x100 pixels from synthetic videos using different imaging parameters. Left: $\Delta=15$, $\alpha=0.5$. Right: $\Delta=200$, $\alpha=0.2$.
  • Figure 2: Synthetic image simulator (Springs 2D/3D). (a): Visual appearance of the initial 2D frame with springs between control points (in blue). (b): Motion induced by random forces and springs constraints over time. The motion of each particle (bright spots) is determined by interpolating control points. (c): 3D projection of springs (in blue) and noisy particles (in white).
  • Figure 3: Temporal projection of tracks (Hydra flow scenario) on 50 frames centered around a contraction (frames $90$ to $140$, contraction at $t=100$).