Fig. 5.

Good quality predictions of patches from the test dataset. Column (A) shows NLM patches, column (B) visualizes contrast inverted NLM patches, column (C) shows histopathologically stained H&E patch, and columns (D) and (E) depict computationally stained H&E patch by the Pix2Pix model and the cycle CGAN model, respectively. The scale bar represents 50 $\mu$m. Here, the computationally stained H&E patches by the cycle CGAN model shows a good quality translation of NLM patches, whereas the translation by the Pix2Pix model produces blurry results within the crypt regions (marked by white arrows).