Automatic deep learning-driven label-free image-guided patch clamp system

Abstract Patch clamp recording of neurons is a labor-intensive and time-consuming procedure. Here, we demonstrate tool that fully automatically performs electrophysiological recordings in label-free tissue slices. The automation covers the detection cells images, calibration micropipette movement, approach to cell with pipette, formation whole-cell configuration, recording. based on deep learning. model trained new image database unlabeled brain pipette tip approaching phase use analysis techniques for precise movements. High-quality measurements are performed hundreds human rodent neurons. We also further molecular anatomical can be recorded cells. software has diary module logs patch events. Our multiply number daily help research.