Related Experiment Video
Updated: Aug 16, 2026
11:38
A Live-cell Image-Based Machine Learning Strategy to Monitor Pluripotent Stem Cell Differentiation
Published on: October 4, 2024
From pixels to patterns: the AI revolution in stem cell-derived models
Luca Deininger1,2,3, Paolo Caldarelli4, Magdalena Zernicka-Goetz5
1Group for Automated Image and Data Analysis, Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology, Eggenstein‑Leopoldshafen, Germany. ldeininger@ethz.ch.
Nature Methods
|August 14, 2026
Summary
Artificial intelligence (AI) is revolutionizing stem cell research by enabling automated analysis of complex biological systems like organoids. This technology accelerates discovery and enhances our understanding of self-organization in developmental biology.
Area of Science:
- Stem cell biology
- Developmental biology
- Bioinformatics
Background:
- Artificial intelligence (AI) is increasingly vital in analyzing complex biological systems.
- Stem cell research and developmental biology generate vast, dynamic datasets.
- Organoids and stem cell-derived embryo models present unique analytical challenges.
Purpose of the Study:
- To review the integration of AI in image-based analysis of stem cell systems.
- To highlight AI's role in automating classification, segmentation, and phenotyping.
- To discuss applications, challenges, and future opportunities of AI in this field.
Main Methods:
- Deep learning and convolutional neural networks for image analysis.
- Foundation models for enhanced scale and precision in phenotyping.
- AI-driven analysis for real-time fate prediction and morphological signature identification.
Main Results:
- AI enables automated, high-precision phenotyping of stem cell systems.
- Applications include drug screening and mechanistic discovery.
- AI identifies hidden morphological signatures linked to differentiation and disease states.
Conclusions:
- AI acts as a discovery engine, not just an analytical tool.
- It enhances reproducibility and accelerates scientific insight.
- AI facilitates a deeper mechanistic understanding of self-organization in stem cell models.
Related Concept Videos
01:21EPS and iPS Cells in Disease Research
Embryonic and induced pluripotent stem cells are excellent models for disease research because of their ability to self-renew and differentiate into most cell types. Somatic cells from a patient are isolated and reprogrammed into induced pluripotent stem cells or iPSCs. These iPSCs are later differentiated into the desired cell type, which mirrors the diseased cell of the patient. In this way, disease models have been created for investigating diseases such as Down syndrome, type I diabetes,...
01:13Induced Pluripotent Stem Cells
Stem cells are undifferentiated cells that divide and produce different types of cells. Ordinarily, cells that have differentiated into a specific cell type are post-mitotic—that is, they no longer divide. However, scientists have found a way to reprogram these mature cells so that they “de-differentiate” and return to an unspecialized, proliferative state. These cells are also pluripotent like embryonic stem cells—able to produce all cell types—and are therefore called induced pluripotent stem...
01:06Induced Pluripotent Stem Cells
Stem cells are undifferentiated cells that divide and produce different cell types. Ordinarily, cells that have differentiated into a specific cell type are terminally differentiated; however, scientists have found a way to reprogram these mature cells so that they dedifferentiate and return to an unspecialized, proliferative state. These cells are pluripotent like embryonic stem cells—able to produce all cell types—and are called induced pluripotent stem cells (iPSCs).
Somatic cells are...
Somatic cells are...
01:22iPS Cell Differentiation
The ability of induced pluripotent stem cells or iPSCs to differentiate into most body cell types has stimulated repair and regenerative medicine research over the past few decades. iPSC-derived blood cells, hepatocytes, beta islet cells, cardiomyocytes, neurons, and other cell types can repair injuries or regenerate damaged tissue in diseases such as diabetes and neurodegenerative disorders.
01:28Forced Transdifferentiation
Transdifferentiation, also known as lineage reprogramming, was first discovered by Selman and Kafatos in 1974 in silkmoths. They observed that the moths’ cuticle-producing cells transformed into salt-producing cells. Many such cases of natural transdifferentiation occur in organisms. In humans, pancreatic alpha cells can become beta cells. In newts, the loss of the eye’s lens causes the pigmented epithelial cells to transdifferentiate into the lens cells.
Artificial transdifferentiation occurs...
Artificial transdifferentiation occurs...
01:29Somatic to iPS Cell Reprogramming
Reprogramming alters the gene expression in somatic cells, transforming them into induced pluripotent stem (iPS) cells over several generations. Scientists can reprogram cells by introducing genes for four transcription factors—Oct4, Sox2, Klf4, and c-Myc (OSKM) by viral or non-viral methods. These factors are also known as Yamanaka factors after Shinya Yamanaka, who first generated iPS cells using mouse skin cells. Yamanaka was awarded the Nobel Prize in Physiology or Medicine in 2012 for this...