Department of Biomedical Engineering, Washington University, St. Louis, MO 63130, USA; Department of Developmental Biology, Washington University School of Medicine, St. Louis, MO 63110, USA
Auto-generated profile, based on publicly available information
Kyaw Thu Minn
Department of Biomedical Engineering, Washington University, St. Louis, MO 63130, USA; Department of Developmental Biology, Washington University School of Medicine, St. Louis, MO 63110, USA
Human embryonic stem cells cultured in 2D micropatterns with BMP4 differentiate into a radial arrangement of germ layers and extraembryonic cells. Single-cell transcriptomes demonstrate generation of cell types transcriptionally similar to their in vivo counterparts in Carnegie stage 7 human gastrula. Time-course analyses indicate sequential differentiation, where the epiblast arises by 12 h between the prospective ectoderm in the center and the cells initiating differentiation toward extraembryonic fates at the edge. Extraembryonic and mesendoderm precursors arise from the epiblast by 24 h, while nascent mesoderm, endoderm, and primordial germ cell-like cells form by 44 h. Dynamic changes in transcripts encoding signaling components support a BMP, WNT, and Nodal hierarchy underlying germ-layer specification conserved across mammals, and FGF and HIPPO pathways being active throughout differentiation. This work also provides a resource for mining genes and pathways expressed in a stereotyped 2D gastruloid model, common with other species or unique to human gastrulation.
Accurately counting cells in microscopic images is important for medical diagnoses and biological studies, but manual cell counting is very tedious, time-consuming, and prone to subjective errors, and automatic counting can be less accurate than desired. To improve the accuracy of automatic cell counting, we propose here a novel method that employs deeply-supervised density regression. A fully convolutional neural network (FCNN) serves as the primary FCNN for density map regression. Innovatively, a set of auxiliary FCNNs are employed to provide additional supervision for learning the intermediate layers of the primary CNN to improve network performance. In addition, the primary CNN is designed as a concatenating framework to integrate multi-scale features through shortcut connections in the network, which improves the granularity of the features extracted from the intermediate CNN layers and further supports the final density map estimation. The experimental results on immunofluorescent images of human embryonic stem cells demonstrate the superior performance of the proposed method over other state-of-the-art methods.