An official website of the United States government
A major benefit of fluorescence microscopy is the now plentiful selection of fluorescent markers. These labels can be chosen to serve complementary functions, such as tracking labeled subcellular molecules near demarcated organelles. However, with the standard 3 or 4 emission channels, multiple label detection is restricted to segregated regions of the electromagnetic spectrum, as in RGB coloring. Hyperspectral imaging allows the user to discern many fluorescence labels by their unique spectral properties, provided there is significant differentiation of their emission spectra. The cost of this technique is often an increase in gain or exposure time to accommodate the signal reduction from separating the signal into many discrete excitation or emission channels. Recent advances in hyperspectral imaging have allowed the acquisition of more signal in a shorter time period by scanning the excitation spectra of fluorophores. Here, we explore the selection of optimal channels for both significant signal separation and sufficient signal detection using excitation-scanning hyperspectral imaging. Excitation spectra were obtained using a custom inverted microscope (TE-2000, Nikon Instruments) with a Xe arc lamp and thin film tunable filter array (VersaChrome, Semrock, Inc.) Tunable filters had bandwidths between 13 and 17 nm. Scans utilized excitation wavelengths between 340 nm and 550 nm. Hyperspectral image stacks were generated and analyzed using ENVI and custom MATLAB scripts. Among channel consideration criteria were: number of channels, spectral range of scan, spacing of center wavelengths, and acquisition time.
more »
« less
Using a genetic algorithm with histogram-based feature selection in hyperspectral image classification
Optical sensing has the potential to be an important tool in the automated monitoring of food quality. Specifically, hyperspectral imaging has enjoyed success in a variety of tasks ranging from plant species classification to ripeness evaluation in produce. Although effective, hyperspectral imaging is prohibitively expensive to deploy at scale in a retail setting. With this in mind, we develop a method to assist in designing a low-cost multispectral imager for produce monitoring by using a genetic algorithm (GA) that simultaneously selects a subset of informative wavelengths and identifies effective filter bandwidths for such an imager. Instead of selecting the single fittest member of the final population as our solution, we fit a univariate Gaussian mixture model to the histogram of the overall GA population, selecting the wavelengths associated with the peaks of the distributions as our solution. By evaluating the entire population, rather than a single solution, we are also able to specify filter bandwidths by calculating the standard deviations of the Gaussian distributions and computing the full-width at half-maximum values. In our experiments, we find that this novel histogram-based method for feature selection is effective when compared to both the standard GA and partial least squares discriminant analysis.
more »
« less
- Award ID(s):
- 1757351
- PAR ID:
- 10158969
- Date Published:
- Journal Name:
- Proceedings of the Genetic and Evolutionary Computation Conference
- Page Range / eLocation ID:
- 1364 to 1372
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The majority of microscopic and endoscopic technologies utilize white light illumination. For a number of applications, hyper-spectral imaging can be shown to have significant improvements over standard white-light imaging techniques. This is true for both microscopy and in vivo imaging. However, hyperspectral imaging methods have suffered from slow application times. Often, minutes are required to gather a full imaging stack. Here we will describe and evaluate a novel excitation-scanning hyperspectral imaging system and discuss some applications. We have developed and are optimizing a novel approach called excitation-scanning hyperspectral imaging that provides an order of magnitude increased signal strength. This excitation scanning technique has enabled us to produce a microscopy system capable of high speed hyperspectral imaging with the potential for live video acquisition. The excitation-scanning hyperspectral imaging technology we developed may impact a range of applications. The current design uses digital strobing to illuminate at 16 wavelengths with millisecond image acquisition time. Analog intensity control enables a fully customizable excitation profile. A significant advantage of excitation-scanning hyperspectral imaging is can identify multiple targets simultaneously in real time. Finally, we are exploring utilizing this technology for a variety of applications ranging from measuring cAMP distribution in three dimensions within a cell to electrophysiology.more » « less
-
Abstract We search for an optimal filter design for the estimation of stellar metallicity, based on synthetic photometry from Gaia XP spectra convolved with a series of filter-transmission curves defined by different central wavelengths and bandwidths. Unlike previous designs based solely on maximizing metallicity sensitivity, we find that the optimal solution provides a balance between the sensitivity and uncertainty of the spectra. With this optimal filter design, the best precision of metallicity estimates for relatively bright (G∼ 11.5) stars is excellent,σ[Fe/H]= 0.034 dex for FGK dwarf stars, superior to that obtained utilizing custom sensitivity-optimized filters (e.g., SkyMapperv). By selecting hundreds of high-probability member stars of the open cluster M67, our analysis reveals that the intrinsic photometric-metallicity scatter of these cluster members is only 0.036 dex, consistent with this level of precision. Our results clearly demonstrate that the internal precision of photometric-metallicity estimates can be extremely high, even providing the opportunity to perform chemical tagging for very large numbers of field stars in the Milky Way. This experiment shows that it is crucial to take into account uncertainty alongside the sensitivity when designing filters for measuring the stellar metallicity and other parameters.more » « less
-
Abstract Implantable image sensors have the potential to revolutionize neuroscience. Due to their small form factor requirements; however, conventional filters and optics cannot be implemented. These limitations obstruct high-resolution imaging of large neural densities. Recent advances in angle-sensitive image sensors and single-photon avalanche diodes have provided a path toward ultrathin lens-less fluorescence imaging, enabling plenoptic sensing by extending sensing capabilities to include photon arrival time and incident angle, thereby providing the opportunity for separability of fluorescence point sources within the context of light-field microscopy (LFM). However, the addition of spectral sensitivity to angle-sensitive LFM reduces imager resolution because each wavelength requires a separate pixel subset. Here, we present a 1024-pixel, 50 µm thick implantable shank-based neural imager with color-filter-grating-based angle-sensitive pixels. This angular-spectral sensitive front end combines a metal–insulator–metal (MIM) Fabry–Perot color filter and diffractive optics to produce the measurement of orthogonal light-field information from two distinct colors within a single photodetector. The result is the ability to add independent color sensing to LFM while doubling the effective pixel density. The implantable imager combines angular-spectral and temporal information to demix and localize multispectral fluorescent targets. In this initial prototype, this is demonstrated with 45 μm diameter fluorescently labeled beads in scattering medium. Fluorescent lifetime imaging is exploited to further aid source separation, in addition to detecting pH through lifetime changes in fluorescent dyes. While these initial fluorescent targets are considerably brighter than fluorescently labeled neurons, further improvements will allow the application of these techniques to in-vivo multifluorescent structural and functional neural imaging.more » « less
-
Hyperspectral imaging systems are becoming widely used due to their increasing accessibility and their ability to provide detailed spectral responses based on hundreds of spectral bands. However, the resulting hyperspectral images (HSIs) come at the cost of increased storage requirements, increased computational time to process, and highly redundant data. Thus, dimensionality reduction techniques are necessary to decrease the number of spectral bands while retaining the most useful information. Our contribution is two-fold: First, we propose a filter-based method called interband redundancy analysis (IBRA) based on a collinearity analysis between a band and its neighbors. This analysis helps to remove redundant bands and dramatically reduces the search space. Second, we apply a wrapper-based approach called greedy spectral selection (GSS) to the results of IBRA to select bands based on their information entropy values and train a compact convolutional neural network to evaluate the performance of the current selection. We also propose a feature extraction framework that consists of two main steps: first, it reduces the total number of bands using IBRA; then, it can use any feature extraction method to obtain the desired number of feature channels. We present classification results obtained from our methods and compare them to other dimensionality reduction methods on three hyperspectral image datasets. Additionally, we used the original hyperspectral data cube to simulate the process of using actual filters in a multispectral imager.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3321707.3321748
