| Summary: | Summary: Image analysis in the field of digital pathology has recently gained increased popularity. The use of high-quality whole-slide scanners enables the fast acquisition of large amounts of image data, showing extensive context and microscopic detail at the same time. Simultaneously, novel machine-learning algorithms have boosted the performance of image analysis approaches. In this paper, we focus on a particularly powerful class of architectures, the so-called generative adversarial networks (GANs) applied to histological image data. Besides improving performance, GANs also enable previously intractable application scenarios in this field. However, GANs could exhibit a potential for introducing bias. Hereby, we summarize the recent state-of-the-art developments in a generalizing notation, present the main applications of GANs, and give an outlook of some chosen promising approaches and their possible future applications. In addition, we identify currently unavailable methods with potential for future applications. The Bigger Picture: The use of high-quality whole-slide scanners enables the fast acquisition of large amounts of image data, showing extensive context and microscopic detail at the same time. While manual examination of these images of considerable size is highly time consuming and error prone, state-of-the-art machine-learning approaches enable efficient, automated processing of whole-slide images. In this paper, we focus on a particularly powerful class of deep-learning architectures, the so-called generative adversarial networks. Over the past years, the high number of publications on this topic indicates a very high potential of generative adversarial networks in the field of digital pathology. In this survey, the most important publications are collected and categorized according to the techniques used and the aspired application scenario. We identify the main ideas and provide an outlook into the future.
|
|---|