Automated human induced pluripotent stem cell colony segmentation for use in cell culture automation applications.
Kimerly A PowellLaura R BohrerNicholas E StoneBradley HittleKristin R AnfinsonViviane LuangphakdyGeorge MuschlerRobert F MullinsEdwin M StoneBudd A TuckerPublished in: SLAS technology (2023)
Human induced pluripotent stem cells (hiPSCs) have demonstrated great promise for a variety of applications that include cell therapy and regenerative medicine. Production of clinical grade hiPSCs requires reproducible manufacturing methods with stringent quality-controls such as those provided by image-controlled robotic processing systems. In this paper we present an automated image analysis method for identifying and picking hiPSC colonies for clonal expansion using the CellX TM robotic cell processing system. This method couples a light weight deep learning segmentation approach based on the U-Net architecture to automatically segment the hiPSC colonies in full field of view (FOV) high resolution phase contrast images with a standardized approach for suggesting pick locations. The utility of this method is demonstrated using images and data obtained from the CellX TM system where clinical grade hiPSCs were reprogrammed, clonally expanded, and differentiated into retinal organoids for use in treatment of patients with inherited retinal degenerative blindness.
Keyphrases
- deep learning
- induced pluripotent stem cells
- cell therapy
- convolutional neural network
- stem cells
- artificial intelligence
- high resolution
- optical coherence tomography
- endothelial cells
- machine learning
- big data
- diabetic retinopathy
- minimally invasive
- mesenchymal stem cells
- magnetic resonance
- single cell
- physical activity
- body mass index
- mass spectrometry
- high throughput
- magnetic resonance imaging
- oxidative stress
- diabetic rats
- intimate partner violence