Fast structured illumination microscopy via deep learning

Ling, Chang; Zhang, Chonglei; Wang, Mingqun; Meng, Fanfei; Du, Luping; Yuan, Xiaocong

doi:10.1364/prj.396122

Cited by 59 publications

(27 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The amount of training data used, about 100 fields of view for training and test data together, is also small enough that specific training, capturing both a given instrument and a specific biological structure of interest, should often be feasible. While SR-REDSIM has similarities to other proposed end-to-end deep learning approaches for SIM [20][21][22], RED-fairSIM is a completely novel deep learning approach for SIM which is -as our data shows -superior to SR-REDSIM.…”

Section: Discussionmentioning

confidence: 70%

Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

Shah

Müller

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

Super-resolution structured illumination microscopy (SR-SIM) pro- vides an up to two-fold enhanced spatial resolution of fluorescently labeled samples. The reconstruction of high quality SR-SIM images critically depends on patterned illumination with high modulation contrast. Noisy raw image data, e.g. as a result of low excitation power or low exposure times, result in reconstruction artifacts. Here, we demonstrate deep-learning based SR-SIM image denoising that results in high quality reconstructed images. A residual encoding-decoding convolution neural network (RED-Net) was used to successfully denoise computationally reconstructed noisy SR-SIM images. We also demonstrate the entirely deep-learning based denoising and reconstruction of raw SIM images into high-resolution SR-SIM images. Both image reconstruction methods prove to be very robust against image reconstruction artifacts and generalize very well over various noise levels. The combination of computational reconstruction and subsequent denoising via RED-Net shows very robust performance during inference after training even if the microscope settings change.

show abstract

Section: Discussionmentioning

confidence: 70%

Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

Shah

Müller

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…5 (column 1) that the proposed methods SR-REDSIM and RED-fairSIM can be used to remove the reconstruction artifacts from the reference image after training, so even if high SNR data can be acquired easily, SR-REDSIM and RED-fairSIM still offer an improvement over the classical reconstruction approaches. A recent study [22] used cycle-consistent generative adversarial networks (CycleGAN) [36] to reconstruct SR-SIM images by using 3 to 9 clean raw SIM images. A CyleGAN contains two generators and two discriminators with multiple losses that are trained in a competitive process.…”

Section: Discussionmentioning

confidence: 99%

“…Christensen et al used a deep learning architecture for the reconstruction of synthetic SR-SIM images [21] with subsequent testing on real microscope images. Ling et al relied on a special type of convolutional neural network, a CycleGAN, for the same purpose [22]. Weigert et al used 2 deep learning algorithms to enhance isotropic resolution and signal-to-noise ratio of fluorescence microscopy images in general [23].…”

Section: Introductionmentioning

confidence: 99%

Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

et al. 2021

View full text Add to dashboard Cite

Super-resolution structured illumination microscopy (SR-SIM) provides an up to two-fold enhanced spatial resolution of fluorescently labeled samples. The reconstruction of high quality SR-SIM images critically depends on patterned illumination with high modulation contrast. Noisy raw image data, e.g. as a result of low excitation power or low exposure times, result in reconstruction artifacts. Here, we demonstrate deep-learning based SR-SIM image denoising that results in high quality reconstructed images. A residual encoding-decoding convolution neural network (RED-Net) was used to successfully denoise computationally reconstructed noisy SR-SIM images. We also demonstrate the entirely deep-learning based denoising and reconstruction of raw SIM images into high-resolution SR-SIM images. Both image reconstruction methods prove to be very robust against image reconstruction artifacts and generalize very well over various noise levels. The combination of computational reconstruction and subsequent denoising via RED-Net shows very robust performance during inference after training even if the microscope settings change.

show abstract

“…To illustrate how this works, one example of a deep neural network trained for SIM imaging is shown in Figure 8 [65]. Two datasets are needed for training the neural network, which are the SR image in one direction as train A (1d_SIM) and the SR image in three directions as train B (9_SIM).…”

Section: Deep Learningmentioning

confidence: 99%

Advances in High-Speed Structured Illumination Microscopy

et al. 2021

View full text Add to dashboard Cite

Super-resolution microscopy surpasses the diffraction limit to enable the observation of the fine details in sub-cellular structures and their dynamics in diverse biological processes within living cells. Structured illumination microscopy (SIM) uses a relatively low illumination light power compared with other super-resolution microscopies and has great potential to meet the demands of live-cell imaging. However, the imaging acquisition and reconstruction speeds limit its further applications. In this article, recent developments all targeted at improving the overall speed of SIM are reviewed. These comprise both hardware and software improvements, which include a reduction in the number of raw images, GPU acceleration, deep learning and the spatial domain reconstruction. We also discuss the application of these developments in live-cell imaging.

show abstract

Fast structured illumination microscopy via deep learning

Cited by 59 publications

References 30 publications

Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

Deep-learning based denoising and reconstruction of super-resolution structured illumination microscopy images

Advances in High-Speed Structured Illumination Microscopy

Contact Info

Product

Resources

About