Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Deep-MSIM: Fast Image Reconstruction with Deep Learning in Multifocal Structured Illumination Microscopy.

ABSTRACT: Fast and precise reconstruction algorithm is desired for for multifocal structured illumination microscopy (MSIM) to obtain the super-resolution image. This work proposes a deep convolutional neural network (CNN) to learn a direct mapping from raw MSIM images to super-resolution image, which takes advantage of the computational advances of deep learning to accelerate the reconstruction. The method is validated on diverse biological structures and in vivo imaging of zebrafish at a depth of 100 µm. The results show that high-quality, super-resolution images can be reconstructed in one-third of the runtime consumed by conventional MSIM method, without compromising spatial resolution. Last but not least, a fourfold reduction in the number of raw images required for reconstruction is achieved by using the same network architecture, yet with different training data.

SUBMITTER: Liao J

PROVIDER: S-EPMC10520669 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Deep-MSIM: Fast Image Reconstruction with Deep Learning in Multifocal Structured Illumination Microscopy.

Liao Jianhui J Zhang Chenshuang C Xu Xiangcong X Zhou Liangliang L Yu Bin B Lin Danying D Li Jia J Qu Junle J

Advanced science (Weinheim, Baden-Wurttemberg, Germany) 20230709 27

Fast and precise reconstruction algorithm is desired for for multifocal structured illumination microscopy (MSIM) to obtain the super-resolution image. This work proposes a deep convolutional neural network (CNN) to learn a direct mapping from raw MSIM images to super-resolution image, which takes advantage of the computational advances of deep learning to accelerate the reconstruction. The method is validated on diverse biological structures and in vivo imaging of zebrafish at a depth of 100 µm ...[more]

PMID: 37424045

Similar Datasets

Multifocal structured illumination optoacoustic microscopy.

Project description:Optoacoustic (OA) imaging has the capacity to effectively bridge the gap between macroscopic and microscopic realms in biological imaging. High-resolution OA microscopy has so far been performed via point-by-point scanning with a focused laser beam, thus greatly restricting the achievable imaging speed and/or field of view. Herein we introduce multifocal structured illumination OA microscopy (MSIOAM) that attains real-time 3D imaging speeds. For this purpose, the excitation laser beam is shaped to a grid of focused spots at the tissue surface by means of a beamsplitting diffraction grating and a condenser and is then scanned with an acousto-optic deflector operating at kHz rates. In both phantom and in vivo mouse experiments, a 10 mm wide volumetric field of view was imaged with 15 Hz frame rate at 28 μm spatial resolution. The proposed method is expected to greatly aid in biological investigations of dynamic functional, kinetic, and metabolic processes across multiple scales.

| S-EPMC7459102 | biostudies-literature

Nonsmooth Convex Optimization for Structured Illumination Microscopy Image Reconstruction.

Project description:In this paper, we propose a new approach for structured illumination microscopy image reconstruction. We first introduce the principles of this imaging modality and describe the forward model. We then propose the minimization of nonsmooth convex objective functions for the recovery of the unknown image. In this context, we investigate two data-fitting terms for Poisson-Gaussian noise and introduce a new patch-based regularization method. This approach is tested against other regularization approaches on a realistic benchmark. Finally, we perform some test experiments on images acquired on two different microscopes.

| S-EPMC6075701 | biostudies-literature

Deep learning for blind structured illumination microscopy.

Project description:Blind-structured illumination microscopy (blind-SIM) enhances the optical resolution without the requirement of nonlinear effects or pre-defined illumination patterns. It is thus advantageous in experimental conditions where toxicity or biological fluctuations are an issue. In this work, we introduce a custom convolutional neural network architecture for blind-SIM: BS-CNN. We show that BS-CNN outperforms other blind-SIM deconvolution algorithms providing a resolution improvement of 2.17 together with a very high Fidelity (artifacts reduction). Furthermore, BS-CNN proves to be robust in cross-database variability: it is trained on synthetically augmented open-source data and evaluated on experiments. This approach paves the way to the employment of CNN-based deconvolution in all scenarios in which a statistical model for the illumination is available while the specific realizations are unknown or noisy.

| S-EPMC9124205 | biostudies-literature

Fast reconstruction and optical-sectioning three-dimensional structured illumination microscopy.

Project description:Three-dimensional structured illumination microscopy (3DSIM) is a popular method for observing subcellular/cellular structures or animal/plant tissues with gentle phototoxicity and 3D super-resolution. However, its time-consuming reconstruction process poses challenges for high-throughput imaging and real-time observation. Moreover, traditional 3DSIM typically requires more than six z layers for successful reconstruction and is susceptible to defocused backgrounds. This poses a great gap between single-layer 2DSIM and 6-layer 3DSIM, and limits the observation of thicker samples. To address these limitations, we developed FO-3DSIM, a novel method that integrates spatial-domain reconstruction with optical-sectioning SIM. FO-3DSIM enhances reconstruction speed by up to 855.7 times with superior performance with limited z layers and under high defocused backgrounds. It retains the high-fidelity, low-photon reconstruction capabilities of our previously proposed Open-3DSIM. Utilizing fast reconstruction and optical sectioning, we achieved large field-of-view (FOV) 3D super-resolution imaging of mouse kidney actin, covering a region of 0.453 mm × 0.453 mm × 2.75 μm within 23 min of acquisition and 13 min of reconstruction. Near real-time performance was demonstrated in live actin imaging with FO-3DSIM. Our approach reduces photodamage through limited z layer reconstruction, allowing the observation of ER tubes with just three layers. We anticipate that FO-3DSIM will pave the way for near real-time, large FOV 6D imaging, encompassing xyz super-resolution, multi-color, long-term, and polarization imaging with less photodamage, removed defocused backgrounds, and reduced reconstruction time.

| S-EPMC11846033 | biostudies-literature

Rapid, artifact-reduced, image reconstruction for super-resolution structured illumination microscopy.

Project description:Super-resolution structured illumination microscopy (SR-SIM) is finding increasing application in biomedical research due to its superior ability to visualize subcellular dynamics in living cells. However, during image reconstruction artifacts can be introduced and when coupled with time-consuming postprocessing procedures, limits this technique from becoming a routine imaging tool for biologists. To address these issues, an accelerated, artifact-reduced reconstruction algorithm termed joint space frequency reconstruction-based artifact reduction algorithm (JSFR-AR-SIM) was developed by integrating a high-speed reconstruction framework with a high-fidelity optimization approach designed to suppress the sidelobe artifact. Consequently, JSFR-AR-SIM produces high-quality, super-resolution images with minimal artifacts, and the reconstruction speed is increased. We anticipate this algorithm to facilitate SR-SIM becoming a routine tool in biomedical laboratories.

| S-EPMC10173768 | biostudies-literature

Rapid Image Reconstruction of Structured Illumination Microscopy Directly in the Spatial Domain.

Project description:Super-resolution structured illumination microscopy (SIM) routinely performs image reconstruction in the frequency domain using an approach termed frequency-domain reconstruction (FDR). Due to multiple Fourier transforms between the spatial and frequency domains, SIM suffers from low reconstruction speed, constraining its applications in real-time, dynamic imaging. To overcome this limitation, we developed a new method for SIM image reconstruction, termed spatial domain reconstruction (SDR). SDR is intrinsically simpler than FDR, does not require Fourier transforms and the theory predicts it to be a rapid image reconstruction method. Results show that SDR reconstructs a super-resolution image 7-fold faster than FDR, producing images that are equal to either FDR or the widely-used FairSIM. We provide a proof-of-principle using mobile fluorescent beads to demonstrate the utility of SDR in imaging moving objects. Consequently, replacement of the FDR approach with SDR significantly enhances SIM as the desired method for live-cell, instant super-resolution imaging. This means that SDR-SIM is a "What You See Is What You Get" approach to super-resolution imaging.

| S-EPMC8054977 | biostudies-literature

Artifact-free whole-slide imaging with structured illumination microscopy and Bayesian image reconstruction.

Project description:Structured illumination microscopy (SIM) is a method that can be used to image biological samples and can achieve both optical sectioning and super-resolution effects. Optimization of the imaging set-up and data-processing methods results in high-quality images without artifacts due to mosaicking or due to the use of SIM methods. Reconstruction methods based on Bayesian estimation can be used to produce images with a resolution beyond that dictated by the optical system. Five complete datasets are presented including large panoramic SIM images of human tissues in pathophysiological conditions. Cancers of the prostate, skin, ovary, and breast, as well as tuberculosis of the lung, were imaged using SIM. The samples are available commercially and are standard histological preparations stained with hematoxylin-eosin. The use of fluorescence microscopy is increasing in histopathology. There is a need for methods that reduce artifacts caused by the use of image-stitching methods or optical sectioning methods such as SIM. Stitched SIM images produce results that may be useful for intraoperative histology. Releasing high-quality, full-slide images and related data will aid researchers in furthering the field of fluorescent histopathology.

| S-EPMC7155289 | biostudies-literature

Open-source image reconstruction of super-resolution structured illumination microscopy data in ImageJ.

Project description:Super-resolved structured illumination microscopy (SR-SIM) is an important tool for fluorescence microscopy. SR-SIM microscopes perform multiple image acquisitions with varying illumination patterns, and reconstruct them to a super-resolved image. In its most frequent, linear implementation, SR-SIM doubles the spatial resolution. The reconstruction is performed numerically on the acquired wide-field image data, and thus relies on a software implementation of specific SR-SIM image reconstruction algorithms. We present fairSIM, an easy-to-use plugin that provides SR-SIM reconstructions for a wide range of SR-SIM platforms directly within ImageJ. For research groups developing their own implementations of super-resolution structured illumination microscopy, fairSIM takes away the hurdle of generating yet another implementation of the reconstruction algorithm. For users of commercial microscopes, it offers an additional, in-depth analysis option for their data independent of specific operating systems. As a modular, open-source solution, fairSIM can easily be adapted, automated and extended as the field of SR-SIM progresses.

| S-EPMC4802170 | biostudies-literature

Structured illumination microscopy with noise-controlled image reconstructions.

Project description:Super-resolution structured illumination microscopy (SIM) has become a widely used method for biological imaging. Standard reconstruction algorithms, however, are prone to generate noise-specific artifacts that limit their applicability for lower signal-to-noise data. Here we present a physically realistic noise model that explains the structured noise artifact, which we then use to motivate new complementary reconstruction approaches. True-Wiener-filtered SIM optimizes contrast given the available signal-to-noise ratio, and flat-noise SIM fully overcomes the structured noise artifact while maintaining resolving power. Both methods eliminate ad hoc user-adjustable reconstruction parameters in favor of physical parameters, enhancing objectivity. The new reconstructions point to a trade-off between contrast and a natural noise appearance. This trade-off can be partly overcome by further notch filtering but at the expense of a decrease in signal-to-noise ratio. The benefits of the proposed approaches are demonstrated on focal adhesion and tubulin samples in two and three dimensions, and on nanofabricated fluorescent test patterns.

| S-EPMC7611169 | biostudies-literature

Resolution doubling in live, multicellular organisms via multifocal structured illumination microscopy.

Project description:We demonstrate three-dimensional (3D) super-resolution in live multicellular organisms using structured illumination microscopy (SIM). Sparse multifocal illumination patterns generated by a digital micromirror device (DMD) allowed us to physically reject out-of-focus light, enabling 3D subdiffractive imaging in samples eightfold thicker than had been previously imaged with SIM. We imaged samples at one 2D image per second, at resolutions as low as 145 nm laterally and 400 nm axially. In addition to dual-labeled, whole fixed cells, we imaged GFP-labeled microtubules in live transgenic zebrafish embryos at depths >45 μm. We captured dynamic changes in the zebrafish lateral line primordium and observed interactions between myosin IIA and F-actin in cells encapsulated in collagen gels, obtaining two-color 4D super-resolution data sets spanning tens of time points and minutes without apparent phototoxicity. Our method uses commercially available parts and open-source software and is simpler than existing SIM implementations, allowing easy integration with wide-field microscopes.

| S-EPMC3462167 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data