VAE-MOTION: A deep generative model for cardiomyocyte contractility analysis for improving drug efficacy evaluation

Expert Systems with Applications, vol. 299, pp. 130302

Abstract

Deep learning has proven to be one of the most effective methods in analyzing biological images to extract parameters fundamental for studying physiological functions and pathological conditions. In particular, when coupled with time-lapse microscopy (TLM), deep learning proves particularly effective in studying behaviors involving temporal dynamics. However, TLM videos are often affected by experimental noise and setup limitations, which can lead to inaccurate and poorly reproducible results. Taking advantage of the variational and generative capabilities of Variational Autoencoders (VAEs), we propose VAE-MOTION, a deep learning-based model for the analysis of cardiac contractile dynamics. By incorporating a temporal encoder into its architecture, our model allows the restoration of video quality by removing noise or increasing resolution, while simultaneously extracting accurate contraction-related signals from the latent space. The generation of synthetic videos allowed extensive training of VAE-MOTION, which subsequently validated on real videos from two different cardiac tissue models: 2D monolayers and 3D microtissues. VAE-MOTION was compared to two gold-standard methods in extracting contraction parameters relevant to drug efficacy or toxicity studies, demonstrating its potential for analyzing temporal dynamics in a given phenomenon or process.

Authors 12

1. Giorgia Curci corresponding

   University of Rome Tor Vergata

   Affiliation as printed

   Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy

   Interdisciplinary Center for Advanced Studies on Lab-on-Chip and Organ-on-Chip Applications (ICLOC), Via del Politecnico 1, 00133 Rome, Italy

2. Paola Casti

   University of Rome Tor Vergata

   Affiliation as printed

   Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy

   Interdisciplinary Center for Advanced Studies on Lab-on-Chip and Organ-on-Chip Applications (ICLOC), Via del Politecnico 1, 00133 Rome, Italy

3. Luca Sala

   IRCCS Istituto Auxologico Italiano · University of Milano-Bicocca

   Affiliation as printed

   Department of Biotechnology and Biosciences, University of Milano – Bicocca, Milan, Italy

   Istituto Auxologico Italiano IRCCS, Center for Cardiac Arrhythmias of Genetic Origin and Laboratory of Cardiovascular Genetics, Milan, Italy

4. Marcella Brescia Aachen Department of Anatomy and Embryology

   Leiden University Medical Center

   Affiliation as printed

   Department of Anatomy & Embryology, Leiden University Medical Center, The Netherlands

5. Pasquale Cascarano

   University of Bologna

   Affiliation as printed

   Department of the Arts, University of Bologna, Bologna, Italy

6. Michele D’Orazio

   University of Rome Tor Vergata

   Affiliation as printed

   Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy

   Interdisciplinary Center for Advanced Studies on Lab-on-Chip and Organ-on-Chip Applications (ICLOC), Via del Politecnico 1, 00133 Rome, Italy

7. Joanna Filippi

   University of Rome Tor Vergata

   Affiliation as printed

   Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy

   Interdisciplinary Center for Advanced Studies on Lab-on-Chip and Organ-on-Chip Applications (ICLOC), Via del Politecnico 1, 00133 Rome, Italy

8. Gianni Antonelli

   University of Rome Tor Vergata

   Affiliation as printed

   Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy

   Interdisciplinary Center for Advanced Studies on Lab-on-Chip and Organ-on-Chip Applications (ICLOC), Via del Politecnico 1, 00133 Rome, Italy

9. Arianna Mencattini

   University of Rome Tor Vergata

   Affiliation as printed

   Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy

   Interdisciplinary Center for Advanced Studies on Lab-on-Chip and Organ-on-Chip Applications (ICLOC), Via del Politecnico 1, 00133 Rome, Italy

10. Massimo Mastrangeli

    Delft University of Technology

    Affiliation as printed

    Microelectronics Deparment, Delft University of Technology, Delft, The Netherlands

11. Berend J. van Meer Aachen Department of Anatomy and Embryology

    Leiden University Medical Center

    Affiliation as printed

    Department of Anatomy & Embryology, Leiden University Medical Center, The Netherlands

    Sync Biosystems, Leiden, The Netherlands

12. Eugenio Martinelli

    University of Rome Tor Vergata

    Affiliation as printed

    Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy

    Interdisciplinary Center for Advanced Studies on Lab-on-Chip and Organ-on-Chip Applications (ICLOC), Via del Politecnico 1, 00133 Rome, Italy