Paper 13329-26
Paper 13329-26
Non-invasive and unbiased AI-based 3D-holotomography analysis for pluripotency prediction of human induced pluripotent stem cells
26 January 2025 • 11:40 AM - 12:00 PM PST | Moscone South, Room 311 (Level 3)
Abstract
Using a label-free and high-resolution imaging system, holotomography (HT), we observed early differentiation of human pluripotent stem cells (hPSCs) and generated a morphology-based pluripotency level prediction model by integrating artificial intelligence (AI). We applied non-invasive pluripotency prediction model for quality control of reprogrammed patient-derived induced pluripotent stem cells (iPSCs) selection, which can be further used in stem cell-based research and therapeutics. Moreover, we identified previously undetectable morphological properties depending on variable pluripotency and newly suggested standardized colonial and intracellular structure of hPSCs.
Presenter
Hoewon Park
KAIST (Korea, Republic of)
Hoewon Park received his B.S. in Biological Science from the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea, in 2018, where he is currently undergoing an integrated Master-PhD course. His major research interest is in stem cell biology and tissue regeneration. An important point of his ongoing research is deciphering the general properties of stable hPSC as starting materials for further stem cell-based research and therapeutics, such as transplantation therapy and tissue-specific organoids studies. For this purpose, he has been using a non-invasive and 3-dimensional high-resolution imaging system, holotomography (HT), to observe the microstructure of hPSCs without any cellular perturbation. With his optical approaches to hPSCs, he is now focusing on applying morphological results to generate a standardized hPSC structure as a basis for stem cell quality control and classify variable human induced pluripotent stem cells (hiPSCs) for clinical usages.