Lesmes-Leon Duway Nicolas, Dengel Andreas, Ahmed Sheraz
University of Kaiserslautern-Landau (RPTU), Kaiserslautern, Germany.
DFKI: German Research Center for Artificial Intelligence GmbH, Kaiserslautern, Germany.
PLoS One. 2025 Jun 24;20(6):e0291217. doi: 10.1371/journal.pone.0291217. eCollection 2025.
Cell microscopy is the main tool that allows researchers to study microorganisms and plays a key role in observing and understanding the morphology, interactions, and development of microorganisms. However, there exist limitations in both the techniques and the samples that impair the amount of available data to study. Generative adversarial networks (GANs) are a deep learning alternative to alleviate the data availability limitation by generating nonexistent samples that resemble the probability distribution of the real data. The aim of this systematic review is to find trends, common practices, and popular datasets and analyze the impact of GANs in image augmentation of cell microscopy images. We used ScienceDirect, IEEE Xplore, PubMed, bioRxiv, and arXiv to select English research articles that employed GANs to generate any kind of cell microscopy images independently of the main objective of the study. We conducted the data collection using 15 selected features from each study, which allowed us to analyze the results from different perspectives using tables and histograms. 46 studies met the legibility criteria, where 23 had image augmentation as the main task. Moreover, we retrieved 29 publicly available datasets. The results showed a lack of consensus with performance metrics, baselines, and datasets. Additionally, we evidenced the relevance of popular architectures such as StyleGAN and losses, including Vanilla and Wasserstein adversarial losses. This systematic review presents the most popular configurations to perform image augmentation. It also highlights the importance of design good practices and gold standards to guarantee comparability and reproducibility. This review implemented the ROBIS tool to assess the risk of bias, and it was not registered in PROSPERO.
细胞显微镜检查是使研究人员能够研究微生物的主要工具,在观察和理解微生物的形态、相互作用及发育方面发挥着关键作用。然而,技术和样本方面都存在局限性,这影响了可用于研究的数据量。生成对抗网络(GAN)是一种深度学习方法,通过生成类似于真实数据概率分布的不存在的样本,来缓解数据可用性的限制。本系统综述的目的是找出趋势、常见做法和流行数据集,并分析GAN对细胞显微镜图像增强的影响。我们使用科学Direct、IEEE Xplore、PubMed、bioRxiv和arXiv来选择独立于研究主要目标、使用GAN生成任何类型细胞显微镜图像的英文研究文章。我们使用每项研究的15个选定特征进行数据收集,这使我们能够使用表格和直方图从不同角度分析结果。46项研究符合可读性标准,其中23项以图像增强为主要任务。此外,我们检索到29个公开可用的数据集。结果表明,在性能指标、基线和数据集方面缺乏共识。此外,我们证明了StyleGAN等流行架构以及损失函数(包括香草和瓦瑟斯坦对抗损失)的相关性。本系统综述展示了执行图像增强最流行的配置。它还强调了设计良好实践和黄金标准以保证可比性和可重复性的重要性。本综述使用ROBIS工具评估偏倚风险,且未在PROSPERO中注册。