Generation of PAS-stained images of glomerular tissue units using a generative adversarial network with spectral normalization colorization method

Jincheng Peng, Guoyue Chen, Kazuki Saruta, Yuki Terata

Article ID: 4085
Vol 7, Issue 1, 2024

VIEWS - 164 (Abstract) 94 (PDF)


In recent years, the pathological diagnosis of glomerular diseases typically involves the study of glomerular his-to pathology by specialized pathologists, who analyze tissue sections stained with Periodic Acid-Schiff (PAS) to assess tissue and cellular abnormalities. In recent years, the rapid development of generative adversarial networks composed of generators and discriminators has led to further developments in image colorization tasks. In this paper, we present a generative adversarial network by Spectral Normalization colorization designed for color restoration of grayscale images depicting glomerular cell tissue elements. The network consists of two structures: the generator and the discriminator. The generator incorporates a U-shaped decoder and encoder network to extract feature information from input images, extract features from Lab color space images, and predict color distribution. The discriminator network is responsible for optimizing the generated colorized images by comparing them with real stained images. On the Human Biomolecular Atlas Program (HubMAP)—Hacking the Kidney FTU segmentation challenge dataset, we achieved a peak signal-to-noise ratio of 29.802 dB, along with high structural similarity results as other colorization methods. This colorization method offers an approach to add color to grayscale images of glomerular cell tissue units. It facilitates the observation of physiological information in pathological images by doctors and patients, enabling better pathological-assisted diagnosis of certain kidney diseases.


spectral normalization; generative adversarial networks; PAS staining; medical image colorization

Full Text:



1. Schell C, Wanner N, Huber TB. Glomerular development – Shaping the multi-cellular filtration unit. Seminars in Cell & Developmental Biology. 2014; 36: 39-49. doi: 10.1016/j.semcdb.2014.07.016

2. Yang S, Wang J, Chen Y, et al. Concurrent Kidney Glomerular and Interstitial Lesions Associated with Kimura’s Disease. Nephron. 2019; 143(2): 92-99. doi: 10.1159/000501638

3. Iizuka S, Simo-Serra E, Ishikawa H. Let there be color! ACM Transactions on Graphics. 2016; 35(4): 1-11. doi: 10.1145/2897824.2925974

4. Zhang R, Isola P, Efros AA. Colorful image colorization. In: Leibe B, Matas J, Sebe N, Welling M (editors). Computer Vision—ECCV 2016, Proceedings of 14th European Conference; 11–14 October 2016; Amsterdam, The Netherlands. Springer; 2016. pp. 649–666. doi: 10.1007/978-3-319-46487-9_40

5. Larsson G, Maire M, Shakhnarovich G. Learning representations for automatic colorization. In: Leibe B, Matas J, Sebe N, Welling M (editors). Computer Vision—ECCV 2016, Proceedings of 14th European Conference; 11–14 October 2016; Amsterdam, The Netherlands. Springer; 2016. pp. 577–593. doi: 10.1007/978-3-319-46493-0_35

6. Nazeri K, Ng E, Ebrahimi M. Image colorization using generative adversarial networks. In: Perales FJ, Kittler J (editors). Articulated Motion and Deformable Objectives, Proceedings of 10th International Conference, AMDO 2018; 12–13 July 2018; Palma de Mallorca, Spain. Springer, Cham; 2018. pp. 85–94. doi: 10.1007/978-3-319-94544-6_9

7. Cao Y, Zhou Z, Zhang W, Yu Y. Unsupervised diverse colorization via generative adversarial networks. In: Ceci M, Hollmén J, Todorovski L, et al. (editors). Machine Learning and Knowledge Discovery in Databases, Proceedings of European Conference, ECML PKDD 2017; 18–22 September 2017; Skopje, Macedonia. Springer, Cham; 2017. pp. 151–166. doi: 10.1007/978-3-319-71249-9_10

8. Miyato T, Kataoka T, Koyama M, et al. Spectral normalization for generative adversarial networks. ArXiv. 2018.

9. Lagodzinski P, Smolka B. Colorization of medical images. Asia-Pacific Signal and Information Processing Association; 2009.

10. Khan TH, Mohammed SK, Imtiaz MS, et al. Efficient Color Reproduction Algorithm for Endoscopic Images Based on Dynamic Color Map. Journal of Medical and Biological Engineering. 2016; 36(2): 226-235. doi: 10.1007/s40846-016-0120-5

11. Liang Y, Lee D, Li Y, et al. Unpaired medical image colorization using generative adversarial network. Multimedia Tools and Applications. 2021; 81(19): 26669-26683. doi: 10.1007/s11042-020-10468-6

12. Chen S, Xiao N, Shi X, et al. ColorMedGAN: A Semantic Colorization Framework for Medical Images. Applied Sciences. 2023; 13(5): 3168. doi: 10.3390/app13053168

13. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A (editors). Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Proceedings of 18th International Conference; 5–9 October 2015; Munich, Germany. Springer, Cham; 2017. pp. 234–241. doi: 10.1007/978-3-319-24574-4_28

14. Kiani L, Saeed M, Nezamabadi-pour H. Image colorization using generative adversarial networks and transfer learning. In: Proceedings of 2020 International Conference on Machine Vision and Image Processing (MVIP); 18–20 February 2020; Iran. pp. 1–6. doi: 10.1109/MVIP49855.2020.9116882

15. Coyle EJ, Lin JH. Stack filters and the mean absolute error criterion. IEEE Transactions on Acoustics, Speech, and Signal Processing. 1988; 36(8): 1244-1254. doi: 10.1109/29.1653

16. Wang Z, Bovik AC, Sheikh HR, et al. Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing. 2004; 13(4): 600-612. doi: 10.1109/tip.2003.819861

17. HuBMAP Hacking the Kidney. Available online: (accessed on 22 December 2023).



  • There are currently no refbacks.

License URL:

Creative Commons License

This site is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.