Related Experiment Video
Updated: Jul 13, 2025
06:51
Techniques to Induce and Quantify Cellular Senescence
Published on: May 1, 2017
33.4K
Form follows function: Nuclear morphology as a quantifiable predictor of cellular senescence.
Jakub Belhadj1,2, Surina Surina1,2,3, Markus Hengstschläger1
1Center for Pathobiochemistry & Genetics, Institute of Medical Genetics, Medical University of Vienna, Vienna, Austria.
Aging Cell
|October 17, 2023
Summary
Nuclear shape changes predict cellular senescence. Deep learning accurately classifies cells as proliferative or senescent using nuclear morphology, aiding disease research.
Area of Science:
- Cell Biology
- Biomarkers
- Computational Biology
Background:
- Enlarged or irregularly shaped nuclei are common in senescent cells.
- The role of nuclear morphology in causing or resulting from senescence was unclear.
- Its utility in distinguishing proliferative from senescent cells was unknown.
Purpose of the Study:
- To determine if nuclear morphology can predict cellular senescence.
- To assess the informative value of nuclear shape in distinguishing cell states.
- To explore the nucleus's role in driving senescence phenotypes.
Main Methods:
- Utilized deep learning algorithms for nuclear morphology analysis.
- Applied quantitative imaging to analyze cell nuclei.
- Validated the approach across diverse cell types and species, in vitro and in vivo.
Main Results:
- Deep learning accurately classifies cells as proliferative or senescent based on nuclear morphology.
- Nuclear morphology serves as a predictive biomarker for senescence.
- The approach is applicable across various biological contexts.
Conclusions:
- Nuclear morphology is an informative and predictive biomarker of cellular senescence.
- Deep learning-based nuclear analysis offers a robust method for cell classification.
- This approach can link senescence burden to clinical data for age-related disease research.
