Deep learning in label-free cell classification and machine vision extraction of particles
US-2018286038-A1 · Oct 4, 2018 · US
US12078587B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12078587-B2 |
| Application number | US-202217953976-A |
| Country | US |
| Kind code | B2 |
| Filing date | Sep 27, 2022 |
| Priority date | Mar 17, 2016 |
| Publication date | Sep 3, 2024 |
| Grant date | Sep 3, 2024 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
In one aspect, a method of sorting cells in a flow cytometry system is disclosed, which includes illuminating a cell with radiation having at least two optical frequencies shifted from one another by a radiofrequency to elicit fluorescent radiation from the cell, detecting the fluorescent radiation to generate temporal fluorescence data, and processing the temporal fluorescence data to arrive at a sorting decision regarding the cell without generating an image (i.e., a pixel-by-pixel image) of the cell based on the fluorescence data. In some cases, the sorting decision can be made with a latency less than about 100 microseconds. In some embodiments, the above method of sorting cells can have a sub-cellular resolution. In some embodiments, a single radiofrequency shift is employed to separate the optical frequencies while in other such embodiments a plurality of different radiofrequency shifts are employed.
Opening claim text (preview).
What is claimed is: 1. A method comprising: receiving a temporal data signal generated from light detected from a sample comprising particles irradiated with an illumination system comprising a laser and an acousto-optic device; and generating a sort decision for sorting one or more particles of the sample based on the temporal data signal. 2. The method according to claim 1 , wherein light detected from the irradiated sample is fluorescence. 3. The method according to claim 1 , wherein light detected from the irradiated sample is scattered light. 4. The method according to claim 1 , wherein the sort decision is generated without forming an image of the sample. 5. The method according to claim 1 , wherein the sort decision is generated based on the temporal signal with a latency equal to or less than about 100 microseconds. 6. The method according to claim 1 , wherein the method further comprises determining a characteristic of the one or more particles in the sample based on the temporal data signal. 7. The method according to claim 6 , wherein the particles are cells in a biological sample. 8. The method according to claim 7 , wherein the characteristic is associated with an internal organelle. 9. The method according to claim 8 , wherein the characteristic of the cells in the biological sample comprises any of a dimensional size of the cell, a ratio of sizes of the cell in along two different dimensions, co-localization of fluorescence radiation emitted by two or more markers associated with the cell, a ratio of sizes of the cell's cytoplasm and nucleus, a degree of punctateness of fluorescent radiation emitted from the cell, a measure of the spatial distribution of the fluorescent radiation, a measure of location or orientation of the cell, a measure of the eccentricity of the cell, a measure of the cell's similarity to a reference cell, a combination of one or more spatial Fourier components of the cell, a measure of the degree to which the cell lies in a focal point of the illuminating radiation. 10. The method according to claim 9 , wherein the cells in the biological sample are stained with two or more fluorescent markers. 11. The method according to claim 10 , wherein the method comprises generating temporal fluorescence waveforms for each of the fluorescent markers. 12. The method according to claim 11 , wherein the method comprises: measuring co-localization of fluorescence signals corresponding to the fluorescent markers; and generating the sort decision based on the measure of co-localization. 13. The method according to claim 11 , wherein the method comprises: obtaining an estimate of a size of cells in the biological sample; and generating the sort decision based on the estimated cell size. 14. The method according to claim 11 , wherein the method comprises estimating the cell size based on a temporal duration of a pulse of fluorescence from the cell. 15. The method according to claim 6 , wherein a spatial characteristic of the particle in the sample is determined based on the temporal data signal. 16. The method according to claim 15 , wherein the spatial characteristic is determined based on a temporal data waveform generated from the detected light from the sample. 17. The method according to claim 15 , wherein the sort decision is generated based on the determined spatial characteristic. 18. A system for sorting particles, the system comprising: an illumination system for illuminating particles in a flow stream comprising a laser and an acousto-optic device; a detection system for detecting light emanating from particles in the flow stream in response to said illumination to generate temporal data; an analysis module in communication with said detection system for receiving said temporal data and processing said data to arrive at a sorting decision regarding said particle, and an actuator capable of diverting the particles from their flow path to separate containers based upon the sorting decision. 19. The system according to claim 18 , wherein the analysis module arrives at the sorting decision without forming an image of the particle based on said fluorescence data. 20. The system according to claim 18 , wherein light detected from the irradiated sample is fluorescence. 21. The system according to claim 18 , wherein light detected from the irradiated sample is scattered light. 22. The system according to claim 18 , wherein the sort decision module comprises instructions for generating the sort decision without forming an image of the sample. 23. The system according to claim 18 , wherein the analysis module generates the sort decision based on the temporal signal with a latency equal to or less than about 100 microseconds. 24. The system according to claim 18 , wherein the detection system is configured to generate a temporal data waveform from the detected light from the sample. 25. The system according to claim 24 , wherein the analysis module is configured to determine a spatial characteristic of the particle based on the temporal data waveform.
with indicators, stains, dyes, tags, labels, marks · CPC title
Measuring fluorescence of fluorescent products of reactions or of fluorochrome labelled reactive substances, e.g. measuring quenching effects, using measuring "optrodes" (in vivo A61B5/00; immunoassay G01N33/53) · CPC title
Atomic fluorescence; Laser induced fluorescence · CPC title
specially adapted for sorting particles, e.g. by their size or optical properties · CPC title
the analysis being performed on a sample stream · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.