Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement

Abstract

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.

To appear in IEEE Signal Processing Magazine

References in corpus (6)

• NICE: Non-linear Independent Components Estimation
• Score-Based Generative Modeling through Stochastic Differential Equations
• Unsupervised MRI Reconstruction with Generative Adversarial Networks
• Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images
• Three dimensional blind image deconvolution for fluorescence microscopy using generative adversarial networks
• Feature Disentanglement in generating three-dimensional structure from two-dimensional slice with sliceGAN

Cited by in corpus (5)

• Zero-DeepSub: Zero-Shot Deep Subspace Reconstruction for Rapid Multiparametric Quantitative MRI Using 3D-QALAS
• SSL-QALAS: Self-Supervised Learning for Rapid Multiparameter Estimation in Quantitative MRI Using 3D-QALAS
• Unsupervised Knowledge-Transfer for Learned Image Reconstruction
• Enhancing quality and speed in database-free neural network reconstructions of undersampled MRI with SCAMPI
• PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstruction