RapidHRV: an open-source toolbox for extracting heart rate and heart rate variability.

Heart rate and heart rate variability have enabled insight into a myriad of psychophysiological phenomena. There is now an influx of research attempting using these metrics within both laboratory settings (typically derived through electrocardiography or pulse oximetry) and ecologically-rich contexts (via wearable photoplethysmography, i.e., smartwatches). However, these signals can be prone to artifacts and a low signal to noise ratio, which traditionally are detected and removed through visual inspection. Here, we developed an open-source Python package, RapidHRV, dedicated to the preprocessing, analysis, and visualization of heart rate and heart rate variability. Each of these modules can be executed with one line of code and includes automated cleaning. In simulated data, RapidHRV demonstrated excellent recovery of heart rate across most levels of noise (>=10 dB) and moderate-to-excellent recovery of heart rate variability even at relatively low signal to noise ratios (>=20 dB) and sampling rates (>=20 Hz). Validation in real datasets shows good-to-excellent recovery of heart rate and heart rate variability in electrocardiography and finger photoplethysmography recordings. Validation in wrist photoplethysmography demonstrated RapidHRV estimations were sensitive to heart rate and its variability under low motion conditions, but estimates were less stable under higher movement settings.

The in vitro micronucleus assay using imaging flow cytometry and deep learning.

The in vitro micronucleus (MN) assay is a well-established assay for quantification of DNA damage, and is required by regulatory bodies worldwide to screen chemicals for genetic toxicity. The MN assay is performed in two variations: scoring MN in cytokinesis-blocked binucleated cells or directly in unblocked mononucleated cells. Several methods have been developed to score the MN assay, including manual and automated microscopy, and conventional flow cytometry, each with advantages and limitations. Previously, we applied imaging flow cytometry (IFC) using the ImageStream® to develop a rapid and automated MN assay based on high throughput image capture and feature-based image analysis in the IDEAS® software. However, the analysis strategy required rigorous optimization across chemicals and cell lines. To overcome the complexity and rigidity of feature-based image analysis, in this study we used the Amnis® AI software to develop a deep-learning method based on convolutional neural networks to score IFC data in both the cytokinesis-blocked and unblocked versions of the MN assay. We show that the use of the Amnis AI software to score imagery acquired using the ImageStream® compares well to manual microscopy and outperforms IDEAS® feature-based analysis, facilitating full automation of the MN assay.

Advanced Characterization of Silicone Oil Droplets in Protein Therapeutics Using Artificial Intelligence Analysis of Imaging Flow Cytometry Data.

Monitoring protein particles is increasingly emphasized in the development of biopharmaceuticals due to potential immunogenicity. Accurate quantitation of protein particles is complicated by silicone oil droplets, a common pharmaceutical component in pre-filled syringes. Though silicone oil is typically regarded as harmless, numerous reports have indicated protein adsorption may render these particles with immunostimulatory properties. Imaging flow cytometry (IFC) is an emerging pharmaceutical method capable of capturing high-resolution brightfield and fluorescence imagery from samples in suspension. In this study, we created a data analysis strategy using artificial intelligence (AI) software to classify brightfield images collected with IFC as protein or silicone oil. The AI software performs image classification using deep learning with a convolutional neural network architecture, for identification of subtle morphological phenotypes. The AI model yielded robust classification of particles >2 µm across various sources of protein and silicone oil particles and over the instrument life cycle. Next, the AI model was combined with IFC fluorescence images to differentiate potentially immunogenic protein-adsorbed silicone and innocuous native silicone. The methods reported herein provide added analytical capability for characterization of particulate matter in therapeutic formulations, and may be applied for optimization of protein formulations and evaluation of product consistency.

Application of optical coherence tomography to automated contact lens metrology.

Optical coherence tomography (OCT) is a nondestructive imaging modality with the potential to make quantitative spatial measurements. OCT's noncontact nature, sensitivity to small refractive index mismatches, and micron-scale resolution make it attractive for contact lens metrology, specifically, measuring prism. Prism is defined as the maximum difference in thickness of the contact lens, measured over a full 360 deg of rotation, at a fixed distance from the contact lens edge. We develop and test a novel algorithm that automatically analyzes OCT images and calculates prism. Images are obtained using a Thorlabs OCT930SR OCT system. The OCT probe is fastened to an automated rotation stage that rotates 360 deg in small increments (typically 10 deg) to acquire OCT images of the edge of the contact lens around the entire circumference. The images are 1.6 mm in optical depth (512 pixels) and 2 mm wide (1000 pixels). Several sets of images are successfully analyzed. The prism measured for a toric lens is 42 microm, which is in line with design parameters. Thickness measurements are repeatable with a standard deviation of 0.5 microm and maximum range of 1.8 microm over ten image sets. This work demonstrates the possibility of using OCT to perform nondestructive contact lens metrology.

Enhanced inflow and outflow rates despite lower IOP in bestrophin-2-deficient mice.

PURPOSE: Bestrophin-2 (Best2), a putative Cl(-) channel is expressed in the nonpigmented epithelium (NPE). Disruption of Best2 in mice results in a diminished intraocular pressure (IOP). Aqueous humor dynamics were compared in Best2(+/+) and Best2(-/-) mice, to better understand the contribution of Best2 to IOP. METHODS: Measurements of IOP, episcleral venous pressure (EVP), conventional outflow facility (C(t)), aqueous humor production (F(a)), and anterior chamber volume (V(a)) were made using anterior chamber cannulation. Conventional (F(c)) and uveoscleral outflow (F(u)), and rate of aqueous humor turnover, were calculated from measured data. The anterior chamber was examined in live mice by optical coherence tomography (OCT) and postmortem by light microscopy. RESULTS: IOP in Best2(-/-) mice was lower compared with Best2(+/+) littermates. EVP was unchanged. Since Best2 is expressed in NPE cells, the hypothesis was that Best2 is involved in generating aqueous flow. However, F(a) in Best2(-/-) mice was increased by approximately 73% compared with Best2(+/+) mice. This was accompanied by increases in F(c) and F(u). Aqueous humor turnover was enhanced more than twofold in Best2(-/-) mice. No evidence of developmental structural changes was noted. CONCLUSIONS: Best2 appears to antagonize the formation of aqueous humor and cause an inhibition of both F(c) and F(u), despite being expressed only in NPE cells. These data support the hypothesis that the inflow and outflow pathways communicate via soluble agents present in the aqueous humor and implicate Best2 as a critical mediator of that communication.