Deep learning‐based identification of sinoatrial node‐like pacemaker cells from <scp>SHOX2</scp>/<scp>HCN4</scp> double‐positive cells differentiated from human <scp>iPS</scp> cells

Background Cardiomyocytes derived from human iPS cells (hiPSCs) include showing SAN- and non-SAN-type spontaneous APs. Objectives To examine whether the deep learning technology could identify hiPSC-derived SAN-like SAN-type-APs by their shape. Methods We acquired phase-contrast images for SHOX2/HCN4 double-positive non-SAN-like made a VGG16-based CNN model to classify an input image as or cell, compared discriminability. Results All parameter values such accuracy, recall, specificity, precision obtained trained were higher than those of classification. Conclusions Deep with considerable accuracy.