Science for Life Laboratory, Department of Biochemistry and Biophysics, Stockholm University, Tomtebodavägen 23, 171 65 Solna, Sweden.
Biomedical Imaging Group and EPFL Center for Imaging, École Polytechnique, Rte Cantonale, 1015 Lausanne, Switzerland.
J Cell Sci. 2024 Oct 15;137(20). doi: 10.1242/jcs.262095. Epub 2024 Oct 28.
Machine learning (ML) is transforming the field of image processing and analysis, from automation of laborious tasks to open-ended exploration of visual patterns. This has striking implications for image-driven life science research, particularly microscopy. In this Review, we focus on the opportunities and challenges associated with applying ML-based pipelines for microscopy datasets from a user point of view. We investigate the significance of different data characteristics - quantity, transferability and content - and how this determines which ML model(s) to use, as well as their output(s). Within the context of cell biological questions and applications, we further discuss ML utility range, namely data curation, exploration, prediction and explanation, and what they entail and translate to in the context of microscopy. Finally, we explore the challenges, common artefacts and risks associated with ML in microscopy. Building on insights from other fields, we propose how these pitfalls might be mitigated for in microscopy.
机器学习（ML）正在改变图像处理和分析领域，从繁琐任务的自动化到对视觉模式的无限探索。这对以图像为驱动的生命科学研究，特别是显微镜研究，具有显著的影响。在这篇综述中，我们从用户的角度出发，重点关注应用基于机器学习的流水线处理显微镜数据集所带来的机遇和挑战。我们研究了不同数据特征（数量、可转移性和内容）的重要性，以及这些特征如何决定使用哪种（或哪些）机器学习模型，以及它们的输出。在细胞生物学问题和应用的背景下，我们进一步讨论了机器学习的实用范围，即数据管理、探索、预测和解释，以及它们在显微镜背景下所包含的内容和转化。最后，我们探讨了机器学习在显微镜中面临的挑战、常见伪影和风险。我们借鉴了其他领域的见解，提出了如何在显微镜中减轻这些陷阱的影响。
