Fig. 1. Style transfer algorithm of Gatys et al^[38]. (a) Style and content reconstruction; (b) Style transfer example

Fig. 2. Network structure of Johnson et al^[47]

Fig. 3. Example results of pix2 pix^[57]

Fig. 4. Paired training data and unpaired training data sets^[59]

Fig. 5. Structure of CycleGAN^[59]. (a) Two generators generate images cyclically; (b) Cyclic reconstruction process of X-domain images; (c) Cyclic reconstruction process of Y-domain images

Fig. 6. Application of CycleGAN in the field of color-transfer^[59]

Fig. 7. Experimental results of Pranita et al^[66] . (a) pix2 pix model for paired image translation; (b) Cycle CGAN model for unpaired image translation

Fig. 8. Experimental results of Teramoto et al^[68]. (a) Transformation results of adenocarcinoma; (b) Transformation results of squamous cell carcinomas

Fig. 9. Work done by Lo et al^[73]. (a) CycleGAN structure of Lo et al; (b) The faster R-CNN structure of Lo et al;(c) P–R curves using different H&E trained models to test images with different stains, where “O” and “×” denote the manual detection results of H&E and PAS images, respectively, performed by four doctors

Fig. 10. Work done by Xu et al^[75]. (a) Structure of cCGAN; (b) Example of the training datasets;(c) Experiment results with different parameters settings

Fig. 11. Work done by de Bel et al^[76]. (a) Architecture of the generator in the residual CycleGAN, closely resembling the standard U-net; (b) The generator learns the difference mapping or residual between a source and target domain; (c) Samples of colon tissue before and after transformation with the CycleGAN approaches

Fig. 12. UV-PAM and Deep-PAM validation using a 7 µm thick frozen section of a mouse brain^[80]

Fig. 13. Stain normalization network architecture proposed by Chen et al^[86]

Fig. 14. Examples of style normalized images of different normalization methods in the target domain^[86]

Fig. 15. Deep learning colorful PIE lens-less diffraction microscopy^[94]. (a) Flow charts of computational algorithms for colorful PIE microcopy with only one kind illumination; (b) Vision comparisons of colorful PIE microscopy images and conventional RGB brightfield images

Fig. 16. Virtual colorful lens-free on-chip microscopy^[95]. (a) Lens-free on-chip microscope; (b) Data process to achieve virtual colorful lens-free on-chip microscopy. The yellow scale bar is 200 μm; (c) Deep learning GAN network established to achieve virtual colorization; (d) Comparisons of lens-free on-chip microscopy image, bench-top commercial microscopy image and virtual colorization image

Fig. 17. Singlet microscopy colorization^[96]. (a) An overview to achieve the singlet microscopy colorization; (b) 200 group images under B/G/R illumination to evaluate the virtual colorized microscopy images’ average PNSRs and SSIMs

Table 1. Statistics on the usage of color transfer technology