Abstract: An Image Activated Cell Sorting (IACS) classification workflow includes: employing a neural network-based feature encoder (or extractor) to extract features of cell images; automatically clustering cells based on extracted cell features; identifying a cluster to pick which cluster(s) to sort based on the cell images; fine-tuning a classification network based on the cluster(s) selected; and once refined, the classification network is used to sort cells for real-time live sorting.

Abstract: An image-based classification workflow uses unsupervised clustering to help a user identify subpopulations of interest for sorting. Labeled cell images are used to fine-tune the supervised classification network for a specific experiment. The workflow allows the user to select the populations to sort in the same manner for a variety of applications. The supervised classification network is very fast, allowing it to make real-time sort decisions as the cell travels through a device. The workflow is more automated and has fewer user steps, which improves the ease of use. The workflow uses machine learning to avoid human error and bias from manual gating. The workflow does not require the user to be an expert in image processing, thus increasing the ease of use.

Abstract: A microparticle sorting apparatus includes a detection unit which detects microparticles flowing through a flow path; an imaging device which images a droplet containing the microparticles which is discharged from an orifice provided on an edge portion of the flow path; a charge unit which applies a charge to the droplets; and a control unit which determines a delay time as from a time that the microparticles are detected by the detection unit to the time at which the sum of intensity of an image region imaged by the imaging device reaches a maximum, making it possible for the charge unit to apply a charge to the microparticles once the delay time has lapsed after the microparticles are detected by the detection unit.

Abstract: A microparticle sorting apparatus includes a detection unit which detects microparticles flowing through a flow path; an imaging device which images a droplet containing the microparticles which is discharged from an orifice provided on an edge portion of the flow path; a charge unit which applies a charge to the droplets; and a control unit which determines a delay time as from a time that the microparticles are detected by the detection unit to the time at which the sum of intensity of an image region imaged by the imaging device reaches a maximum, making it possible for the charge unit to apply a charge to the microparticles once the delay time has lapsed after the microparticles are detected by the detection unit.

Abstract: Apparatus and methods for detecting, characterizing, and compensating motion-related error of moving micro-entities are described. Motion-related error may occur in streams of moving micro-entities, and may represent a deviation in and expected arrival time or an uncertainty in position of a micro-entity within the stream. Motion-related error of micro-entities is observed in a flow cytometer, e.g., as pulse jitter, and is found to have a functional dependence on a parameter of the system. The pulse jitter can be compensated, according to one embodiment, by adjusting data acquisition observation windows. For the flow cytometer, a reduction of pulse jitter can improve measurement accuracy, resolution of doublets, system throughput, and enable an increase in an interrogation region for probing the micro-entities.

Abstract: Apparatus and methods for detecting and characterizing motion-related error of moving micro-entities are described. Motion-related error may occur in streams of moving micro-entities, and may represent a deviation in and expected arrival time or an uncertainty in position of a micro-entity. Motion-related error of micro-entities is observed in a flow cytometer, e.g., as pulse jitter, and is found to have a functional dependence on a parameter related to a system clock. The motion-related error may be characterized by correlating measurements of micro-entities moving within a fluid stream.

Abstract: Apparatus and methods for detecting, characterizing, and compensating motion-related error of moving micro-entities are described. Motion-related error may occur in streams of moving micro-entities, and may represent a deviation in and expected arrival time or an uncertainty in position of a micro-entity within the stream. Motion-related error of micro-entities is observed in a flow cytometer, e.g., as pulse jitter, and is found to have a functional dependence on a parameter of the system. The pulse jitter can be compensated, according to one embodiment, by adjusting data acquisition observation windows. For the flow cytometer, a reduction of pulse jitter can improve measurement accuracy, resolution of doublets, system throughput, and enable an increase in an interrogation region for probing the micro-entities.

Abstract: A hybrid microfluidic biochip designed to perform multiplexed detection of singled- celled pathogens using a combination of SPR and epi-fluorescence imaging. The device comprises an array of gold spots, each functionalized with a capture biomolecule targeting a specific pathogen. This biosensor array is enclosed by a polydimethylsiloxane (PDMS) microfluidic flow chamber that delivers a magnetically concentrated sample to be tested. The sample is imaged by surface plasmon resonance on the bottom of the biochip, and epi- fluorescence on the top.