	US 12,461,105 B2
	System, method, and article for detecting abnormal cells using multi-dimensional analysis
Michael R. Loken, Mercer Island, WA (US); and Andrew P. Voigt, Seattle, WA (US)
Assigned to Hermatologics, Inc., Seattle, WA (US)
Filed by Hematologics, Inc., Seattle, WA (US)
Filed on Mar. 20, 2023, as Appl. No. 18/186,747.
Application 18/186,747 is a continuation of application No. 16/334,657, granted, now 11,639,936, previously published as PCT/US2017/052311, filed on Sep. 19, 2017.
Claims priority of provisional application 62/396,621, filed on Sep. 19, 2016.
Prior Publication US 2024/0044904 A1, Feb. 8, 2024
Int. Cl. G01N 33/48 (2006.01); G01N 33/574 (2006.01); G06F 17/18 (2006.01); G16B 20/00 (2019.01); G16B 40/00 (2019.01); G16B 40/20 (2019.01); G16B 40/30 (2019.01)

CPC G01N 33/57492 (2013.01) [G06F 17/18 (2013.01); G16B 20/00 (2019.02); G16B 40/00 (2019.02); G16B 40/20 (2019.02); G16B 40/30 (2019.02); G01N 2333/70589 (2013.01); G01N 2333/70596 (2013.01)]

21 Claims

1. A method of characterizing a test set of biological cells in an n-dimensional space, comprising:

exposing each cell in a normal set of biological cells to a plurality of four or more reagents using a first protocol;

measuring a corresponding plurality of fluorescence intensities of each cell in the normal set of biological cells using a second protocol;

mapping each cell in the normal set of biological cells to a corresponding point in an n-dimensional space based at least in part on the measured plurality of fluorescence intensities of the cell in the normal set of biological cells, wherein the corresponding points form a normal set of points;

defining a plurality of reference populations in the normal set of points, the plurality of reference populations including a lymphocyte reference population and a monocyte reference population;

defining a set of reference clusters in the n-dimensional space by defining a centroid line and radii based at least in part on the defined reference populations, wherein each cluster in the set of reference clusters corresponds to a maturation level within a cell lineage;

exposing each cell in a test set of biological cells to the plurality of reagents using the first protocol;

measuring a corresponding plurality of fluorescence intensities of each cell in the test set of biological cells using the second protocol;

mapping each cell in the test cell of biological cells to a corresponding point in an n-dimensional space based at least in part on the measured plurality of fluorescence intensities of the cell in the test set of biological cells, wherein the corresponding points form a test set of points; and

comparing the test set of points to the set of reference clusters, wherein the defining the set of reference clusters and the comparing the test set of points to the set of reference clusters includes defining one or more multidimensional boundaries in the n-dimensional space, and the method comprises:

determining a standard reference mean for each reference population, the determining the standard reference mean for a reference population including:

training support vector machines to generate the one or more multidimensional boundaries in the n-dimensional space identifying reference populations of interest;

for each normal patient in a set of normal patients, applying a multidimensional boundary of the one or more multidimensional boundaries to identify the reference population of interest for the normal patient, and determining a mean intensity of one or more parameters of the reference population by adding intensities of the population of interest for a given parameter and dividing by a total number of cells of the population of interest; and

computing a standard reference mean for the reference population by determining a mean of all the mean reference intensities for each parameter of the reference population, wherein the standard reference mean is a vector; and

normalizing the test set of points, the normalizing the test set of points including:

identifying a lymphocyte reference population of the test set of points;

determining a mean intensity of one or more parameters of the lymphocyte reference population for the test set of points by adding intensities of the points for a given parameter in the lymphocyte reference population and dividing by a total number of cells of the lymphocyte reference population for the test set of points;

generating a normalization vector for the lymphocyte reference population of the test set of points by determining a difference between the mean parameter intensities for the lymphocyte reference population for the test set of points and the standard reference mean vector;

determining whether the normalization vector for the lymphocyte reference population for the test set of points satisfies a quality control criteria;

in response to determining the normalization vector for the lymphocyte reference population for the test set of points satisfies the quality control criteria:

normalizing intensities of the points of each reference population of the test set of points based on the normalization vector generated for the lymphocyte reference population of the test set of points;

using the normalized test set of points in the comparing; and

diagnosing cancer based on the comparing of the normalized test set of points to the set of reference clusters; and

in response to determining the normalization vector for the lymphocyte reference population for the test set of points does not satisfy the quality control criteria, flagging the test set of points as not satisfying the quality control criteria.