Related Experiment Video
Updated: May 24, 2025
06:16
Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies
Published on: July 28, 2023
2.4K
Artificial intelligence-enabled lipid droplets quantification: Comparative analysis of NIS-elements Segment.ai and
S Michurina1, Y Goltseva1, E Ratner2
1National Medical Research Centre for Cardiology Named After Academician E.I.Chazov, Moscow, Russia.
Methods (San Diego, Calif.)
|March 1, 2025
Summary
Quantifying lipid droplets (LDs) in adipocytes is crucial for understanding obesity. This study introduces Segment.ai and StarDist deep learning tools to accurately analyze LD number and morphology, accelerating research.
Area of Science:
- Cell Biology
- Bioinformatics
- Medical Imaging
Background:
- Lipid droplets (LDs) are vital organelles in adipocytes, reflecting cell function and metabolic state.
- Accurate quantification of LDs is essential for studying obesity and related metabolic disorders.
- Current LD analysis methods are challenging and require advanced computational approaches.
Purpose of the Study:
- To present a practical workflow for analyzing LD number and morphology using deep learning.
- To evaluate the performance of Segment.ai and StarDist for LD analysis in adipocytes.
- To demonstrate the utility of these tools in studying LD dynamics and metabolic regulation.
Main Methods:
- 3T3-L1 cells were differentiated into adipocytes and stained with BODIPY493/503.
- Confocal live cell imaging was performed, and data was annotated for training.
- Segment.ai (NIS-Elements) and StarDist (ZeroCostDL4Mic) deep learning models were applied for LD detection and analysis.
Main Results:
- Both Segment.ai and StarDist models accurately recognized and quantified LDs in microphotographs.
- The models demonstrated capability in detecting LD enlargement in adipocytes with inhibited lipolysis.
- Deep learning significantly accelerated the processing and analysis of imaging data.
Conclusions:
- Segment.ai and StarDist offer robust and efficient solutions for LD quantification and morphological analysis.
- These tools facilitate faster exploration of LD dynamics, aiding research into energy homeostasis.
- The developed approaches contribute to understanding the role of LDs in metabolic abnormalities and obesity.
