- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
A machine learning approach for online automated optimization of super-resolution optical microscopy
摘要： Traditional approaches for finding well-performing parameterizations of complex imaging systems, such as super-resolution microscopes rely on an extensive exploration phase over the illumination and acquisition settings, prior to the imaging task. This strategy suffers from several issues: it requires a large amount of parameter configurations to be evaluated, it leads to discrepancies between well-performing parameters in the exploration phase and imaging task, and it results in a waste of time and resources given that optimization and final imaging tasks are conducted separately. Here we show that a fully automated, machine learning-based system can conduct imaging parameter optimization toward a trade-off between several objectives, simultaneously to the imaging task. Its potential is highlighted on various imaging tasks, such as live-cell and multicolor imaging and multimodal optimization. This online optimization routine can be integrated to various imaging systems to increase accessibility, optimize performance and improve overall imaging quality.
关键词： machine learning,multicolor imaging,online automated optimization,live-cell imaging,super-resolution optical microscopy,multimodal optimization
更新于2025-09-04 15:30:14
-
Super-resolution microscopy and empirically validated autocorrelation image analysis discriminates microstructures of dairy derived gels
摘要： The food industry must capitalise on advancing technologies in order to optimise the potential from emerging ingredient technologies. These can aid in product optimisation and provide quantitative empirical data to which there is a fundamental physical understanding. Super-resolution microscopy provides a tool to characterise the microstructure of complex colloidal materials under near native conditions. Coherent Anti-Stokes Raman Scattering (CARS) microscopy was used to show the presence of fluorescent dye required for imaging does not affect gel microstructure and super-resolution Stimulated Emission Depletion (STED) microscopy is used to image four dairy derived gels. Image analysis has been developed based on 2D spatial autocorrelation, and a model that extracts parameters corresponding to a typical length of the protein domains and the inter pore distance. The model has been empirically validated through the use of generated images to show the fitting parameters relate to precise physical features. The fractal dimension is extracted from Fourier space analysis. The combination of STED microscopy and image analysis is sensitive enough to significantly differentiate samples based on whether gels were made from fresh or reconstituted milk, and whether gelation was induced through acidification or rennet addition. Rheometry shows that the samples exhibit different macroscopic behaviours, and these differences become increasingly significant with time. Samples can be differentiated earlier in the gelation process with imaging as compared to rheometry. This highlights the potential of STED imaging and image analysis to characterise the size of protein domains, pore spacing and the fractal dimensions of microstructures to aid product optimisation.
关键词： Stimulated Emission Depletion (STED) microscopy,Super-resolution microscopy,Fractal dimension,Coherent Anti-stokes Raman Scattering (CARS) microscopy,2D spatial autocorrelation analysis
更新于2025-09-04 15:30:14
-
Example-based image super-resolution via blur kernel estimation and variational reconstruction
摘要： Single image super-resolution aims at generating clear high-resolution image from one low-resolution image. Due to the limited low-resolution information, it is a challenging task to restore clear, artifacts-free image, meanwhile preserving finer structures and textures. This paper proposes an effective example-based image super-resolution method while making clear image and no compromise on quality. Firstly, the image prior is imposed on the anchor neighborhood regression model to optimize mapping coefficient for interim latent image construction. In order to remove its blur, kernel estimation iteration optimization algorithm is proposed based on the salient edges which are extracted through texture-structure discriminate minimum energy function and fractional order mask enhancement. Finally, an accurate reconstruction constraint combined with a simple gradient regularization is applied to reconstruct the super-resolution image. The proposed method is able to produce clear high-frequency texture details and maintain clean edges even under large scaling factors. Experimental results show that the proposed method performs well in visual effects and similarities. Furthermore, we test our algorithm in multi-texture images for robust evaluation. It is demonstrated that our algorithm is robust under complicated textures condition.
关键词： image reconstruction,super-resolution,fractional-order,blur kernel estimation
更新于2025-09-04 15:30:14
-
Towards a nanophotonic nose: a compressive sensing-enhanced, optoelectronic mid-infrared spectrometer
摘要： Infrared (IR) spectroscopy has been a central tool for chemical analysis for decades, useful in a wide range of fields for the detection and quantification of molecules based on their unique vibrational resonances. Conventional IR spectroscopy relies on bulky, dispersive optics, however, making portability and miniaturization a substantial challenge. Here we demonstrate a micron-scale IR spectrometer where spectrally selective detection is performed optoelectronically, based on the wavelength-dependent mid-IR photocurrent responses of an array of Al grating-based detectors fabricated on a doped Si substrate. Compressive sensing techniques extend our resolution, enabling spectral features to be identified with a remarkably small number of detectors. This work demonstrates a CMOS-compatible, readily scalable approach for the fabrication of compact, room-temperature IR spectrometers capable of use in fieldable applications.
关键词： miniature,aluminum,infrared,super-resolution,compressive sensing,Spectroscopy
更新于2025-09-04 15:30:14
-
Deep learning in imaging
摘要： Machine learning approaches that include deep learning are moving beyond image classification to change the way images are made. Computers are powerful tools for carrying out tasks such as image classification or identification as well as or better than human experts. Conventional machine learning approaches are widely used for segmentation and phenotyping in fluorescence microscopy. These tools are now being largely outperformed by their deep-learning-based counterparts, some of which are available as user-friendly tools. But a perhaps more astonishing wave of developments has recently come about through the use of deep learning not for image analysis but for image transformation. In these cases, deep convolutional networks are trained to transform one type of image into another. For example, two studies have shown the power of deep learning for the creation of fluorescence micrographs of cells directly from bright-field or phase images, to facilitate multiplexed and longitudinal imaging. Researchers have also used deep learning to go from low signal-to-noise images to high-quality images, which opens the door to extended imaging of even very light-sensitive living organisms. Deep learning can similarly overcome obstacles associated with super-resolution microscopy. Two approaches, ANNA-PALM and DeepSTORM, were developed to improve the speed of localization microscopy, which is one of the major hurdles of the technique. Deep learning can also enable cross-modality imaging, where applications such as a shift from confocal images to stimulated-emission-depletion-microscopy-resolution images could democratize super-resolution imaging. As with any method, the caveats associated with deep learning in such applications, such as the potential for artifacts, must be carefully considered and analyzed. Nevertheless, we think we have seen only the tip of the iceberg, and that deep learning stands to improve all aspects of imaging, from acquisition to analysis.
关键词： image transformation,machine learning,fluorescence microscopy,deep learning,super-resolution microscopy,imaging
更新于2025-09-04 15:30:14
-
Multi-resolution Image Fusion in Remote Sensing () || Image Fusion: Application to Super-resolution of Natural Images
摘要： Increasing the spatial resolution of a given test image is of interest to the image processing community since the enhanced resolution of the image has better details when compared to the corresponding low resolution image. Super-resolution (SR) is an algorithmic approach in which a high spatial resolution image is obtained by using single/multiple low resolution observations or by using a database of LR–HR pairs. The linear image formation model discussed for image fusion in Chapter 4 is extended here to obtain an SR image for a given LR test observation. In the image fusion problem, the available Pan image was used in obtaining a high resolution fused image. Similar to the fusion problem, SR is also concerned with the enhancement of spatial resolution. However, we do not have a high resolution image such as a Pan image as an additional observation. Hence, we make use of a database of LR–HR pairs in order to obtain the SR for the given LR observation. Here, we use contourlet based learning to obtain the initial SR estimate which is then used in obtaining the degradation as well as the MRF parameter. Similar to the fusion problem discussed in Chapter 4, an MAP–MRF framework is used to obtain the final SR image.
关键词： image processing,degradation estimation,MAP–MRF framework,Super-resolution,contourlet transform
更新于2025-09-04 15:30:14
-
DNA-Based Super-Resolution Microscopy: DNA-PAINT
摘要： Super-resolution microscopies, such as single molecule localization microscopy (SMLM), allow the visualization of biomolecules at the nanoscale. The requirement to observe molecules multiple times during an acquisition has pushed the field to explore methods that allow the binding of a fluorophore to a target. This binding is then used to build an image via points accumulation for imaging nanoscale topography (PAINT), which relies on the stochastic binding of a fluorescent ligand instead of the stochastic photo-activation of a permanently bound fluorophore. Recently, systems that use DNA to achieve repeated, transient binding for PAINT imaging have become the cutting edge in SMLM. Here, we review the history of PAINT imaging, with a particular focus on the development of DNA-PAINT. We outline the different variations of DNA-PAINT and their applications for imaging of both DNA origamis and cellular proteins via SMLM. Finally, we reflect on the current challenges for DNA-PAINT imaging going forward.
关键词： DNA PAINT,SMLM,DNA origami,DNA,fluorescence microscopy,super-resolution microscopy
更新于2025-09-04 15:30:14