The invention belongs to the field of biological recognition, and discloses a
cell detection method, device and apparatus for a glomerular
pathological section image, and the method comprises the steps: obtaining a to-be-detected glomerular
pathological section image; inputting the to-be-detected glomerular
pathological section image into a preset neural
network model for identification and detection, with the preset neural
network model being obtained by training a neural network through a predetermined number of glomerular pathological section images for identifying and labeling mesangial cells, endothelial cells and podocytes; respectively outputting probability graphs of mesangial cells, endothelial cells and podocytes in the glomerular pathological section image to be detected from three output channels of a preset neural
network model; and calculating the number of the mesangial cells, the endothelial cells and the podocytes in the glomerular pathological section image to be detected according to the probability graphs of the mesangial cells, the endothelial cells and the podocytes. The causes and conditions of the patient are determined according to the number of mesangial cells, endothelial cells and
podocyte, and a treatment scheme is made accurately.