Faster R-Cnn For Ipsc-Derived Mesenchymal Stromal Cells Senescent Detection From Bright-Field Microscopy

iPSC-derived mesenchymal stromal cells (iMSCs) play an important role in cell therapy and regenerative medicine, but the differentiation and proliferation ability of senescent iMSCs decline greatly, which will also bring heterogeneity and potential side effects. The whole senescent degree of iMSCs can only be obtained by vital stain. However, this process is labor-intensive, time-consuming and costly. To solve this problem, we apply a deep learning-based method for automated iMSCs senescent recognition, which can quickly and accurately get the senescent status of single-cell without staining. The adopted Faster R-CNN uses ResNet as the backbone network with an FPN module. We also obtain the senescent degree of each generation of cells, and predict the ratio of young cells to senescent cells of the next generation of cells. Then we judge whether the next generation of cells can be used in the experiments. The experiments on the collected dataset show that our method has achieved a detection accuracy of 0.768 in the mixed test set of each generation of cells and the independent test set of each generation of cells.