# US 10,872,410 B2 · Methods and apparatus for assessing immune system activity and therapeutic efficacy > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,410 B2 - Document ID: US10872410B2 - Status: Granted - Kind: B2 - Application number: 16/334,723 - Filed: 2017-09-21 - Published: 2019-08-29 - Granted: 2020-12-22 - Earliest claimed: 2016-09-29 - Assignees: Animantis, LLC - Applicants: Animantis, LLC - Inventors: Martin Russell Blanchard; Ryan Stanley Kerwin; Bryan James Walker - Web page: https://patentgrep.com/patent/US10872410B2 ## CPC - G06T 7/0012: {Biomedical image inspection} - G01N 33/5026: {on cell morphology} - G01N 33/5029: {on cell motility} - G06V 20/695: {Preprocessing, e.g. image segmentation} - G06V 20/698: {Matching; Classification} - G01N 2800/7028: Cancer - G01N 2800/7095: Inflammation - G06T 2207/20081: Training; Learning - G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Methods, compositions, and apparatuses are disclosed and described for assessing systemic immune response by monitoring changes of biophysical properties of mammalian immune cells or immune relevant bacterial cells in response to a gradient of chemoattractant in vitro. ## Claims ### Claim 1 A system for classifying a cell, the system comprising: a sample vessel including: a sample reservoir configured to receive a sample and said sample reservoir comprising one or more cell adhesion molecules and a chemoattractant for an assay; an elongate channel; and a processing chamber in fluid communication with the sample reservoir through the elongate channel; an imaging device configured to capture images of the processing chamber; a control server configured to adjust the imaging device based at last in part on the assay; and an image processing system configured to: receive the images, wherein each image shows the cell, wherein a plurality of images generates a video; generate a binary image for each image included in the images, individual binary image indicating a set of locations within the respective image where the cell may be located; and for each binary image: generate a probability that each location in the set of locations is the location of the cell; assign one location from the set of locations for each binary image, the assignment maximizing the probability for all of the binary images; generate a set of metrics for the cell, the set of metrics generated using changes in a characteristic for the cell between binary images for sequentially captured images included in the video; and classify the cell using the set of metrics and a classification model, the classification model receiving at least a portion of the set of metrics as an input and generating a classification as an output. ### Claim 2 A method of classifying a cell, the method comprising: combining the cell with a chemoattractant in a vessel having a first transparent portion; receiving a video including a plurality of images showing the cell through the first transparent portion; and for each image included in the plurality of images: identifying a set of locations within an image where the cell may be located using at least one of temporal variance in pixel values between images and pixel variance from a mean for the image, and generating a binary image for the image, the binary image indicating the set of locations; for each binary image: generating a probability that each location in the set of locations is the location of the cell; assigning one location from the set of locations for each binary image, the assignment maximizing the probability for all of the binary images; generating a set of metrics for the cell, the set of metrics generated using changes in location for the cell between binary images for sequentially captured images included in the video; obtaining a classification model, the classification model receiving at least a portion of the set of metrics as an input and generating a classification as an output; and classifying the cell using the set of metrics and the classification model. ### Claim 3 (depends on 2) The method of claim 2, further comprising: determining a hypothesis count based on at least one of a type for the cell and the chemoattractant; obtaining a motion model for the cell, the motion model receiving at least a location of the cell in a first image as an input and generating a predicted location for the cell in a subsequent image as an output; and for each binary image: generating a set of hypothetical locations for the cell using the motion model, wherein the size of the set of hypothetical locations corresponds to the hypothesis count, and assigning a score to each hypothetical location in the set of hypothetical locations based on a similarity calculated using a negative exponential Gaussian function of the Mean Squared Error (MSE) between the hypothetical location and a template image, wherein the probability that each location in the set of locations is the location of the cell is generated using the scores. ### Claim 4 (depends on 2) The method of claim 2, further comprising: generating a random seed value for generating the probability for each location in the set of locations for each binary image; storing the random seed value in a data storage device in association with an identifier for a source of the cell; receiving a second video including a plurality of images showing a second cell from the source; extracting a portion of an image included in the plurality of images, the portion indicating the identifier; retrieving the random seed value from the data storage device using the identifier; and classifying the second cell using the random seed value. ### Claim 5 (depends on 2) The method of claim 2, wherein the set of metrics includes a metric indicating a characteristic of the cell shown in the image included in the plurality of images sequentially captured. ### Claim 6 (depends on 2) The method of claim 2, wherein the set of metrics includes a metric indicating a change in a characteristic of the cell between images included in the plurality of images sequentially captured. ### Claim 7 (depends on 6) The method of claim 6, wherein the characteristic of the cell comprises cell area, cell velocity, direction of cell migration, cell speed, cell momentum, cell polarization, cell circularity, number of distinct protrusions from each cell, and all first order time-dependent derivatives thereof. ### Claim 8 (depends on 2) The method of claim 2, wherein the plurality of images comprises at least 180 images, and wherein each of the plurality of images further show between 1 and 299 other cells through the first transparent portion. ### Claim 9 (depends on 2) The method of claim 2, wherein the chemoattractant comprises N-Formylmethionyl-leucyl-phenylalanine (fMLF), fMet, IL-8, Leukotrene B4, CXCL1, CXCL2, CXCL8, CXCL9, CXCL10, CXCL12, CCL2, CCL3, CCL5, CCL11, CCL19, CCL21, CX3CL1, C5a, C5b, G-CSF, GM-CSF, IL-1, IL-3, IL-4 IL-5, IL-6, IL-7, IL-11 IL-17, IL-21, IL-1β, TNFα, stem cell factor (SCF), thrombin, erythropoietin (EPO), IFN-α, IFN-β, IFN-γ and any combination thereof. ### Claim 10 (depends on 2) The method of claim 2, further comprising: providing a device for measuring an inflammatory response in a subject, the device including: a sample reservoir having one or more cell adhesion molecules and a chemoattractant, and a processing chamber in fluid communication with the sample reservoir through an elongate channel; and applying a biological sample to the sample reservoir, the biological sample comprising one or more cells, and the one or more cells including the cell. ### Claim 11 A non-transitory computer-readable medium comprising instructions that, when executed by at least one processor of a computing device, cause the computing device to: receive a video including a plurality of images showing the cell through the first transparent portion; and for each image included in the plurality of images: identify a set of locations within an image where the cell may be located using at least one of temporal variance in pixel values between images and pixel variance from a mean for the image, and generate a binary image for the image, the binary image indicating the set of locations; and for each binary image: generate a probability that each location in the set of locations is the location of the cell; assign one location from the set of locations for each binary image, wherein the assignment maximizes the probability for all of the binary images; generate a set of metrics for the cell, the set of metrics generated using changes in location for the cell between binary images for sequentially captured images included in the video; obtain a classification model, the classification model receiving at least a portion of the set of metrics as an input and generating a classification as an output; and classify the cell using the set of metrics and the classification model. ### Claim 12 A method of classifying a cell, the method comprising: receiving a video including a plurality of images showing the cell; generating a binary image for each image included in the plurality of images, individual binary image indicating a set of locations within the respective image where the cell may be located; and for each binary image: generating a probability that each location in the set of locations is the location of the cell; assigning one location from the set of locations for each binary image, the assignment maximizing the probability for all of the binary images; generating a set of metrics for the cell, the set of metrics generated using changes in a characteristic for the cell between binary images for sequentially captured images included in the video; and classifying the cell using the set of metrics and a classification model, the classification model receiving at least a portion of the set of metrics as an input and generating a classification as an output. ### Claim 13 (depends on 1) The system of claim 1, wherein the one or more cell adhesion molecules is a lectin, a laminin, a selectin, a fibronectin, a collagen, a fibrinogen, or a gelatin. ### Claim 14 (depends on 1) The system of claim 1, wherein the chemoattractant is N-Formylmethionyl-leucyl-phenylalanine (fMLF), fMet, IL-8, Leukotrene B4, CXCL1, CXCL2, CXCL8, CXCL9, CXCL10, CXCL12, CCL2, CCL3, CCL5, CCL11, CCL19, CCL21, CX3CL1, C5a, C5b, G-CSF, GM-CSF, IL-1, IL-3, IL-4 IL-5, IL-6, IL-7, IL-11 IL-17, IL-21, IL-1β, TNFα, stem cell factor (SCF), thrombin, erythropoietin (EPO), IFN-α, IFN-β, or IFN-γ. ### Claim 15 (depends on 1) The system of claim 1, wherein the imaging device is a camera configured to capture magnified images of the processing chamber. ### Claim 16 (depends on 1) The system of claim 1, wherein the set of metrics includes a metric indicating a change in a characteristic of the cell between images included in the plurality of images sequentially captured. ### Claim 17 (depends on 11) The computer readable medium of claim 11, wherein a probability that each location in the set of locations is the location of the cell is generated using a score. ### Claim 18 (depends on 11) The computer readable medium of claim 11, wherein the set of metrics includes a metric indicating a change in a characteristic of the cell between images included in the plurality of images. ### Claim 19 (depends on 11) The computer readable medium of claim 11, wherein the cell is classified by assessing one or more physical variables of the cell. ### Claim 20 (depends on 19) The computer readable medium of claim 19, wherein the one or more physical variables include cell morphology, cell position, cell directionality, cell orientation, cell perimeter, cell luminance, cell area, cell velocity, cell speed, cell acceleration, cell direction, cell circularity, cellular branching events, cell branch length, cell image moments (or Hu moments), cell eccentricity, cell path trends, cell spreading, cell grouping, neutrophil extracellular trap (NET) formations, degranulation events, or overall prevalence. ### Claim 21 (depends on 12) The method of claim 12, wherein the set of metrics includes a metric indicating a change in a characteristic of the cell between images included in the plurality of images. ### Claim 22 (depends on 12) The method of claim 12, wherein the cell is classified by assessing one or more physical variables of the cell. ### Claim 23 (depends on 22) The method of claim 22, wherein the one or more physical variables include cell morphology, cell position, cell directionality, cell orientation, cell perimeter, cell luminance, cell area, cell velocity, cell speed, cell acceleration, cell direction, cell circularity, cellular branching events, cell branch length, cell image moments (or Hu moments), cell eccentricity, cell path trends, cell spreading, cell grouping, neutrophil extracellular trap (NET) formations, degranulation events, or overall prevalence. ### Claim 24 (depends on 12) The method of claim 12, wherein the plurality of images comprises at least 180 images.