Convulsive seizure behaviors are a hallmark feature of epilepsy, but automated detection of these events in freely moving animals is difficult. Here, we employed a high-resolution multi-camera array microscope with high-speed video acquisition and custom supervised machine learning (ML) for automated detection of larval zebrafish between 3- and 7-days post-fertilization (dpf). We assessed data from over 2700 zebrafish either exposed to a chemoconvulsant (pentylenetetrazole, PTZ) or genetic zebrafish lines representing Developmental Epileptic Encephalopathy (DEE) syndromes. Using eight-point skeletal body pose estimation for tracking individual larvae arrayed in a 96-well format, we report reliable, quantitative and age-dependent changes in maximum swim speed, as well as eye-, head- and tail- angle kinematics. Finally, we employed an ML-based algorithm to automatically identify normal and abnormal behaviors in an unbiased manner. Our results offer a robust framework for automated detection of zebrafish seizure-associated behaviors.

Normal development of the immune system is essential for overall health and disease resistance. Bony fish, such as the zebrafish (Danio rerio), possess all the major immune cell lineages as mammals and can be employed to model human host response to immune challenge. Zebrafish neutrophils, for example, are present in the transparent larvae as early as 48 hours post fertilization and have been examined in numerous infection and immunotoxicology reports. One significant advantage of the zebrafish model is the ability to affordably generate high numbers of individual larvae that can be arrayed in multi-well plates for high throughput genetic and chemical exposure screens. However, traditional workflows for imaging individual larvae have been limited to low-throughput studies using traditional microscopes and manual analyses. Using a newly developed, parallelized microscope, the Multi-Camera Array Microscope (MCAM™), we have optimized a rapid, high-resolution algorithmic method to count fluorescently labeled cells in zebrafish larvae in vivo. Using transgenic zebrafish larvae, in which neutrophils express EGFP, we captured 18 gigapixels of images across a full 96-well plate, in 75 seconds, and processed the resulting datastream, counting individual fluorescent neutrophils in all individual larvae in 5 minutes. This automation is facilitated by a machine learning segmentation algorithm that defines the most in-focus view of each larva in each well after which pixel intensity thresholding and blob detection are employed to locate and count fluorescent cells. We validated this method by comparing algorithmic neutrophil counts to manual counts in larvae subjected to changes in neutrophil numbers, demonstrating the utility of this approach for high-throughput genetic and chemical screens where a change in neutrophil number is an endpoint metric. Using the MCAM™ we have been able to, within minutes, acquire both enough data to create an automated algorithm and execute a biological experiment with statistical significance. Finally, we present this open-source software package which allows the user to train and evaluate a custom machine learning segmentation model and use it to localize zebrafish and analyze cell counts within the segmented region of interest. This software can be modified as needed for studies involving other zebrafish cell lineages using different transgenic reporter lines and can also be adapted for studies using other amenable model species.

Rapid, accurate insect identification is the first and most critical step of pest management and vital to agriculture for determining optimal management strategies. In many instances, classification is necessary within a short developmental window. Two examples, the tobacco budworm, Chloridea virescens, and bollworm, Helicoverpa zea, both have 99% accuracy using a convolutional neural architecture to classify the two species of caterpillars. A gigapixel scale parallelized microscope, referred to as the Multi-Camera Array Microscope (MCAM™), and automated image-processing pipeline allowed us to rapidly build a dataset of ~5500 images for training and testing the network. In the future, applications could be developed enabling farmers to photograph eggs on a leaf and receive an immediate species identification before the eggs hatch.

Understanding the behavioral and morphological dynamics of moving model organisms like the zebrafish larvae requires accurate, high-throughput 3D analysis. However, traditional single-view 2D video tracking fails to capture the full scope of natural 3D movements and postural dynamics. Here, we present a novel high-throughput 24-camera array microscope with a co-designed “mirrored well plate" that allows for snapshot imaging of up to 48 wells over a 118 mm × 82 mm field of view from two orthogonal directions (i.e., a top-view and side-view). Accurate 3D position estimation and tracking is achieved with an efficient machine learning algorithm that scales well to high-throughput measurements. The proposed approach automates parallelized 3D model organism behavioral analysis, providing 3D skeletal tracking, swim bladder morphological dynamics, and kinematics of up to 48 swimming zebrafish larvae at up to several hundred frames per second. The result is an efficient and scalable solution for high-throughput 3D behavioral studies with broad compatibility with standard workflows across laboratories and procedures working with pharmacology, toxicology, and neuroscience.

Normal development of the immune system is essential for overall health and disease resistance. Bony fish, such as the zebrafish ( Danio rerio ), possess all the major immune cell lineages as mammals and can be employed to model human host response to immune challenge. Zebrafish neutrophils, for example, are present in the transparent larvae as early as 48 hours post fertilization and have been examined in numerous infection and immunotoxicology reports. One significant advantage of the zebrafish model is the ability to affordably generate high numbers of individual larvae that can be arrayed in multi-well plates for high throughput genetic and chemical exposure screens. However, traditional workflows for imaging individual larvae have been limited to low-throughput studies using traditional microscopes and manual analyses. Using a newly developed, parallelized microscope, the Multi-Camera Array Microscope (MCAM™), we have optimized a rapid, high-resolution algorithmic method to count fluorescently labeled cells in zebrafish larvae in vivo . Using transgenic zebrafish larvae, in which neutrophils express EGFP, we captured 18 gigapixels of images across a full 96-well plate, in 75 seconds, and processed the resulting datastream, counting individual fluorescent neutrophils in all individual larvae in 5 minutes. This automation is facilitated by a machine learning segmentation algorithm that defines the most in-focus view of each larva in each well after which pixel intensity thresholding and blob detection are employed to locate and count fluorescent cells. We validated this method by comparing algorithmic neutrophil counts to manual counts in larvae subjected to changes in neutrophil numbers, demonstrating the utility of this approach for high-throughput genetic and chemical screens where a change in neutrophil number is an endpoint metric. Using the MCAM™ we have been able to, within minutes, acquire both enough data to create an automated algorithm and execute a biological experiment with statistical significance. Finally, we present this open-source software package which allows the user to train and evaluate a custom machine learning segmentation model and use it to localize zebrafish and analyze cell counts within the segmented region of interest. This software can be modified as needed for studies involving other zebrafish cell lineages using different transgenic reporter lines and can also be adapted for studies using other amenable model species.

Aggression is a nearly universal behavior used to secure food, territory, and mates across species, including the fruit fly Drosophila melanogaster . In fruit flies, both sexes display aggression through stereotypical motor patterns. This, along with their sophisticated genetic and molecular toolkit, makes Drosophila melanogaster an excellent model for studying aggression. While male- and female-specific aggressive motor programs have been qualitatively described, automated systems for quantifying these behaviors in freely moving flies remain limited in their ability to combine high-resolution analysis with high throughput. Here, we pair a high-resolution, high-throughput imaging system (the Kestrel) with DeepLabCut pose estimation to create a pipeline that tracks multiple freely moving fly pairs and quantifies social dynamics with high fidelity. We validated body-part tracking using published benchmarks. The platform reliably reproduced a known phenotype: heightened female aggression following thermogenetic activation of cholinergic pC1 neurons in female brain. It also detected increased unilateral wing extension, a courtship display inversely related to aggression, between two males upon activating a previously uncharacterized ∼40-neuron group in the male brain. Pose-based analysis revealed locomotive differences between experimental and control groups, and subtle, genotype-specific variations in head butts and UWEs. This workflow enables high-throughput screening and mechanistic dissection of social behaviors.