AI Imaging Reveals Hidden Differences Between Cells
From University of California Television (UCTV) · · 32 min

The player loads from YouTube only when you click. It uses YouTube's privacy-enhanced mode.
If the video does not play, the owner may have turned off embedding. Watch it on YouTube instead.
Description
A version of this video with audio description track is available here: https://www.youtube.com/watch?v=l1Ftb5M6tPw
AI-powered cell imaging may help researchers identify biological differences that are difficult or impossible to see by eye. Yu-Hwa Lo, Ph.D., and Louise Laurent, M.D., Ph.D., describe a system that combines high-speed imaging, cell sorting, microfluidics, and artificial intelligence. The technology creates label-free images of cells, uses AI to classify them, and can isolate selected cells for deeper molecular analysis. Laurent explains how the team is applying the system to human trophoblast stem cells, which give rise to specialized placental cells involved in nutrient transport, hormone production, blood vessel remodeling, and immune regulation. Lo describes how AI can distinguish cell populations and identify features that may not be apparent to human observers. The researchers ultimately hope to connect imaging features with gene expression, proteins, and metabolism, allowing cell characteristics and behavior to be predicted from images alone. Recorded on 05/27/2026. [9/2026] [Show ID: 41637]
0:00 Building a Long-Term Research Collaboration 1:55 Combining Cell Imaging With High-Speed Sorting 3:51 How Cells Are Imaged and Isolated 7:24 Using Label-Free Images to Identify Cells 11:09 How AI Learns to Classify Cell Types 17:28 Why Placental Trophoblast Cells Matter 21:32 Finding Hidden Cell Subtypes With AI 25:52 Predicting Cell Biology From Images
Donate to UCTV to support informative & inspiring programming: https://www.uctv.tv/donate
Please Note: Knowledge about health and medicine is constantly evolving. This information may become out of date.
More videos from: UC San Diego Women's Health Symposium (https://www.uctv.tv/ucsd-womens-health)
More from: Motherhood Channel (https://www.uctv.tv/motherhood)
Explore More Health & Medicine on UCTV (https://www.uctv.tv/health) UCTV features the latest in health and medicine from University of California medical schools. Find the information you need on cancer, transplantation, obesity, disease and much more.
UCTV is the broadcast and online media platform of the University of California, featuring programming from its ten campuses, three national labs and affiliated research institutions. UCTV explores a broad spectrum of subjects for a general audience, including science, health and medicine, public affairs, humanities, arts and music, business, education, and agriculture. Launched in January 2000, UCTV embraces the core missions of the University of California -- teaching, research, and public service – by providing quality, in-depth television far beyond the campus borders to inquisitive viewers around the world. (https://www.uctv.tv)
FAQ Q: How can AI identify different types of cells? A: The system collects multiple images of individual cells and converts those images into features that an AI model can analyze. The researchers show that AI can classify known cell types and detect differences that may not be visible to a person looking at the images. Q: What is label-free cell imaging? A: Label-free imaging examines cells without relying on fluorescent biomarkers to identify them. The system described here uses transmission, forward-scattering, and backscattering images to capture different physical properties of each cell and uses those images for classification. Q: How is this technology being used to study the placenta? A: The researchers are applying the system to human trophoblast stem cells and cells derived from them. Their goal is to identify subgroups within these cell populations, isolate them, and analyze their RNA to better understand biological differences among cells.
Back to University of California Television (UCTV) · Report a problem