Figure 1.

A schematic showing how the proposed TzanckNet works. TzanckNet accepts a Tzanck smear image as an input and outputs which cell types among six cell types are present and absent in the image. As an example, a Tzanck smear image from a patient with herpetic infection goes into the TzanckNet and the network predicts that there are acantholytic and multinucleated giant cells in the image, the remaining four cell types does not exist in the image. On the right-hand side of the figure, an example image from each cell type is presented.