StainGAN: Learning a Structural Preserving Translation for White Blood Cell Images

• Published in: Journal of biophotonics Vol. 16; no. 11; p. e202300196
• Main Authors: Huang, Maoye, Wang, Tao, Cai, Yuanzheng, Fan, Haoyi, Li, Zuoyong
• Format: Journal Article
• Language: English
• Published: Germany Wiley Subscription Services, Inc 01.11.2023
• Subjects: Algorithms; Annotations; Image segmentation; Leukocytes; Machine learning; Medical imaging; Translation; generative adversarial networks; stain-style translation; white blood cells; deep neural networks
• ISSN: 1864-063X; 1864-0648
• DOI: 10.1002/jbio.202300196

Analysis of white blood cells in blood smear images plays a vital role in computer-aided diagnosis for the analysis and treatment of many diseases. However, different techniques for blood smear preparation result in images with large appearance variations, which limits the performance of large-scale machine learning algorithms. In this paper, we propose StainGAN, an image translation framework to transform the conventional Wright-stained white blood cell images into their rapidly-stained counterpart. Moreover, we design a cluster-based learning strategy that does not require manual annotations and a multi-scale discriminator that incorporates a richer hierarchy of the spatial context to generate sharper images with better semantic consistency. Experimental results on multiple real-world datasets prove the effectiveness of our proposed framework. Moreover, we show that the transformed images from StainGAN can be used to boost the downstream segmentation performance under the label-limiting scenario. This article is protected by copyright. All rights reserved.