Search

Deep learning is a significant step forward for developing autonomous tasks. One of its branches, computer vision, allows image recognition with high accuracy thanks to the use of convolutional neural networks (CNNs). Our goal was to train a CNN with transmitted light microscopy images to distinguish pluripotent stem cells from early differentiating cells. We induced differentiation of mouse embryonic stem cells to epiblast-like cells and took images at several time points from the initial stimulus. We found that the networks can be trained to recognize undifferentiated cells from differentiating cells with an accuracy higher than 99%. Successful prediction started just 20 min after the onset of differentiation. Furthermore, CNNs displayed great performance in several similar pluripotent stem cell (PSC) settings, including mesoderm differentiation in human induced PSCs. Accurate cellular morphology recognition in a simple microscopic set up may have a significant impact on how cell assays are performed in the near future., (Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved.)

Joint injury and osteoarthritis affect millions of people worldwide, but attempts to generate articular cartilage using adult stem/progenitor cells have been unsuccessful. We hypothesized that recapitulation of the human developmental chondrogenic program using pluripotent stem cells (PSCs) may represent a superior approach for cartilage restoration. Using laser-capture microdissection followed by microarray analysis, we first defined a surface phenotype (CD166(low/neg)CD146(low/neg)CD73(+)CD44(low)BMPR1B(+)) distinguishing the earliest cartilage committed cells (prechondrocytes) at 5-6 weeks of development. Functional studies confirmed these cells are chondrocyte progenitors. From 12 weeks, only the superficial layers of articular cartilage were enriched in cells with this progenitor phenotype. Isolation of cells with a similar immunophenotype from differentiating human PSCs revealed a population of CD166(low/neg)BMPR1B(+) putative cartilage-committed progenitors. Taken as a whole, these data define a developmental approach for the generation of highly purified functional human chondrocytes from PSCs that could enable substantial progress in cartilage tissue engineering.