Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement
This is an incremental review that synthesizes existing approaches for researchers in biological imaging facing data scarcity issues.
The paper reviews unsupervised deep learning methods for biological image reconstruction and enhancement, addressing the challenge of obtaining paired reference data by focusing on self-supervised learning and generative models, and discusses their applications across various imaging techniques.
Recently, deep learning approaches have become the main research frontier for biological image reconstruction and enhancement problems thanks to their high performance, along with their ultra-fast inference times. However, due to the difficulty of obtaining matched reference data for supervised learning, there has been increasing interest in unsupervised learning approaches that do not need paired reference data. In particular, self-supervised learning and generative models have been successfully used for various biological imaging applications. In this paper, we overview these approaches from a coherent perspective in the context of classical inverse problems, and discuss their applications to biological imaging, including electron, fluorescence and deconvolution microscopy, optical diffraction tomography and functional neuroimaging.