Automated assessment of human engineered heart tissues using deep learning and template matching for segmentation and tracking
Bioengineering & Translational Medicine · 2023-05 · 8 (3)
DOI: 10.1002/btm2.10513 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering & Translational Medicine, online erschienen am 18.04.2023. Verfasst von José M Rivera-Arbeláez und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Stem Cell Technologies, TechMed Centre University of Twente Enschede the Netherlands. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The high rate of drug withdrawal from the market due to cardiovascular toxicity or lack of efficacy, the economic burden, and extremely long time before a compound reaches the market, have increased the relevance of human in vitro models like human (patient‐derived) pluripotent stem cell (hPSC)‐derived engineered heart tissues (EHTs) for the evaluation of the efficacy and toxicity of compounds at the early phase in the drug development pipeline. Consequently, the EHT contractile properties are highly relevant parameters for the analysis of cardiotoxicity, disease phenotype, and longitudinal measurements of cardiac function over time. In this study, we developed and validated the software HAARTA (Highly Accurate, Automatic and Robust Tracking Algorithm), which automatically analyzes contractile properties of EHTs by segmenting and tracking brightfield videos, using deep learning and template matching with sub‐pixel precision. We demonstrate the robustness, accuracy, and computational efficiency of the software by comparing it to the state‐of‐the‐art method (MUSCLEMOTION), and by testing it with a data set of EHTs from three different hPSC lines. HAARTA will facilitate standardized analysis of contractile properties of EHTs, which will be beneficial for in vitro drug screening and longitudinal measurements of cardiac function.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Applied Stem Cell Technologies, TechMed Centre University of Twente Enschede the Netherlands.
- BIOS Lab on a Chip Group, MESA+ Institute for Nanotechnology, TechMed Centre, Max Planck Institute for Complex Fluid Dynamics University of Twente Enschede the Netherlands.
- Data Management & Biometrics (DMB) Group University of Twente Enschede the Netherlands.
- River BioMedics Enschede the Netherlands.
- Microelectronics, TU Delft Delft the Netherlands.
- Department of Anatomy and Embryology Leiden University Medical Centre Leiden the Netherlands.
ORCID-Profile: José M Rivera-Arbeláez
Zitieren
APA
Rivera-Arbeláez, J. M., Keekstra, D., Cofiño-Fabres, C., Boonen, T., Dostanic, M., Ten Den, S. A., Vermeul, K., Mastrangeli, M., van den Berg, A., Segerink, L. I., Ribeiro, M. C., Strisciuglio, N., & Passier, R. (2023). Automated assessment of human engineered heart tissues using deep learning and template matching for segmentation and tracking. Bioengineering & Translational Medicine, 8(3). https://doi.org/10.1002/btm2.10513
Vancouver
Rivera-Arbeláez JM, Keekstra D, Cofiño-Fabres C, Boonen T, Dostanic M, Ten Den SA, et al. Automated assessment of human engineered heart tissues using deep learning and template matching for segmentation and tracking. Bioengineering & Translational Medicine. 2023;8(3). doi:10.1002/btm2.10513
BibTeX
@article{RiveraArbelez2023,
author = {Rivera-Arbeláez, José M and Keekstra, Danjel and Cofiño-Fabres, Carla and Boonen, Tom and Dostanic, Milica and Ten Den, Simone A and Vermeul, Kim and Mastrangeli, Massimo and van den Berg, Albert and Segerink, Loes I and Ribeiro, Marcelo C and Strisciuglio, Nicola and Passier, Robert},
title = {Automated assessment of human engineered heart tissues using deep learning and template matching for segmentation and tracking},
journal = {Bioengineering & Translational Medicine},
year = {2023},
volume = {8},
number = {3},
doi = {10.1002/btm2.10513}
}
EUVIMED