Automated microscopy can image specimens larger than the microscope’s field of view (FOV) by stitching overlapping image tiles. It also enables time-lapse studies of entire cell cultures in multiple imaging modalities. We created MIST (Microscopy Image Stitching Tool) for rapid and accurate stitching of large 2D time-lapse mosaics. MIST estimates the mechanical stage model parameters (actuator backlash, and stage repeatability ‘r’) from computed pairwise translations and then minimizes stitching errors by optimizing the translations within a (4r)² square area. MIST has a performance-oriented implementation utilizing multicore hybrid CPU/GPU computing resources, which can process terabytes of time-lapse multi-channel mosaics 15 to 100 times faster than existing tools. We created 15 reference datasets to quantify MIST’s stitching accuracy. The datasets consist of three preparations of stem cell colonies seeded at low density and imaged with varying overlap (10 to 50%). The location and size of 1150 colonies are measured to quantify stitching accuracy. MIST generated stitched images with an average centroid distance error that is less than 2% of a FOV. The sources of these errors include mechanical uncertainties, specimen photobleaching, segmentation, and stitching inaccuracies. MIST produced higher stitching accuracy than three open-source tools. MIST is available in ImageJ at isg.nist.gov.

Increases in the number of cell therapies in the preclinical and clinical phases have prompted the need for reliable and non-invasive assays to validate transplant function in clinical biomanufacturing. We developed a robust characterization methodology composed of quantitative bright-field absorbance microscopy (QBAM) and deep neural networks (DNNs) to non-invasively predict tissue function and cellular donor identity. The methodology was validated using clinical-grade induced pluripotent stem cell derived retinal pigment epithelial cells (iPSC-RPE). QBAM images of iPSC-RPE were used to train DNNs that predicted iPSC-RPE monolayer transepithelial resistance, predicted polarized vascular endothelial growth factor (VEGF) secretion, and matched iPSC-RPE monolayers to the stem cell donors. DNN predictions were supplemented with traditional machine learning algorithms that identified shape and texture features of single cells that were used to predict tissue function and iPSC donor identity. These results demonstrate non-invasive cell therapy characterization can be achieved with QBAM and machine learning.

Hyperspectral remote sensing produces large volumes of data, quite often requiring hundreds of megabytes to gigabytes of memory storage for a small geographical area for onetime data collection. Although the high spectral resolution of hyperspectral data is quite useful for capturing and discriminating subtle differences in geospatial characteristics of the target, it contains redundant information at the band level. The objective of this study was to identify those bands that contain the most information needed for characterizing a specific geospatial feature with minimal redundancy. Band selection is per- formed with both unsupervised and supervised approaches. Five methods (three unsupervised and two supervised) are pro- posed and compared to identify hyperspectral image bands to characterize soil electrical conductivity and canopy coverage in agricultural fields. The unsupervised approach includes information entropy measure and first and second derivatives along the spectral axis. The supervised approach selects hyperspectral bands based on supplemental ground truth data using principal component analysis (PCA) and artificial neural network (ANN) based models. Each hyperspectral image band was ranked using all five methods. Twenty best bands were selected by each method with the focus on soil and plant canopy charac- terization in precision agriculture. The results showed that each of these methods may be appropriate for different applica- tions. The entropy measure and PCA were quite useful for selecting bands with the most information content, while derivative methods could be used for identifying absorption features. ANN measure was the most useful in selecting bands specific to a target characteristic with minimum information redundancy. The results also indicated that a combination of wavebands with different bandwidths will allow use of fewer than 20 bands used in this study to represent the information contained in the top 20 bands, thus reducing image data dimensionality and volume considerably.

Pixel latency of event cameras is an important parameter to take into account in real-time applications. Currently, pixel latency is insufficiently described in event camera specifications as a “typical latency at a certain light level”. This work is motivated by the need to have a well-defined pixel latency measurement since the latency depends on the irradiance of the stimulus, the event camera configuration, and the number of active pixels. The problem lies in defining a hardware setup and a measurement procedure that could be reproduced by event camera vendors to specify pixel latency and then used by event camera consumers for selecting event cameras according to their real-time applications. The challenges of solving the problem involve selecting accessible hardware for all vendors, precisely specifying the hardware configuration and measurement procedure, and defining the pixel latency metrics that are directly related to real-time applications. We describe such a solution and report pixel latency measurements for three event cameras in order to illustrate the reproducibility aspects and the value added to the deployment of event cameras in practice. The interactive visualization of all latency measurements is available from https://usnistgov.github.io/pixel_latency_eventcameras/.