Infrared and Laser Engineering, Volume. 51, Issue 2, 20210891(2022)
Deep learning-based color transfer biomedical imaging technology
Fig. 1. Style transfer algorithm of Gatys et al[38]. (a) Style and content reconstruction; (b) Style transfer example
Fig. 5. Structure of CycleGAN[59]. (a) Two generators generate images cyclically; (b) Cyclic reconstruction process of
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
|
Get Citation
Copy Citation Text
Yinxu Bian, Tao Xing, Weijie Deng, Qin Xian, Honglei Qiao, Qian Yu, Jilong Peng, Xiaofei Yang, Yannan Jiang, Jiaxiong Wang, Shenmin Yang, Renbin Shen, Hua Shen, Cuifang Kuang. Deep learning-based color transfer biomedical imaging technology[J]. Infrared and Laser Engineering, 2022, 51(2): 20210891
Category: Special issue-Computational optical imaging technology
Received: Nov. 24, 2021
Accepted: --
Published Online: Mar. 21, 2022
The Author Email: Bian Yinxu (byx@zju.edu.cn)