# US 2013/0294675 A1 · Automatic segmentation and characterization of cellular motion

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2013/0294675 A1
- Document ID: US20130294675A1
- Status: Published application
- Kind: A1
- Application number: 13/463,100
- Filed: 2012-05-03
- Published: 2013-11-07
- Earliest claimed: 2012-05-03
- Assignees: General Electric Company
- Inventors: Xiaofeng Liu; Dirk Ryan Padfield
- Web page: https://patentgrep.com/patent/US20130294675A1

## CPC

- G06V 20/695: {Preprocessing, e.g. image segmentation}
- G06T 7/0016: {involving temporal comparison}
- G06T 7/136: involving thresholding
- G06T 7/194: involving foreground-background segmentation
- G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments
- G06T 7/254: involving subtraction of images
- G06V 20/69: Microscopic objects, e.g. biological cells or cellular parts
- G06T 2207/10016: Video; Image sequence
- G06T 2207/10056: Microscopic image
- G06T 2207/20021: Dividing image into blocks, subimages or windows
- G06T 2207/20036: Morphological image processing
- G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The present techniques provide for the evaluation of cellular motion and/or cellular properties based on an analysis of motion for cluster of cells. In an exemplary technique, images of cells are acquired and the image is segmented into clusters. Motion data for each respective cluster is derived from the segmented data. The properties of each cluster can be used to evaluate cellular properties and/or cellular motion properties.

## Claims

### Claim 1

A method for evaluating cellular motion and/or properties, comprising:
receiving image data corresponding to images of a plurality of cells;
segmenting the image data into a plurality of clusters;
extracting a motion signal from the image data of each respective cluster of the plurality of clusters; and
evaluating at least one of cellular motion properties or cellular properties based on the motion signal from each respective cluster.

### Claim 2 (depends on 1)

The method of claim 1, comprising measuring an effect of one or more treatments applied to the plurality of cells based on the evaluation of at least one of cellular motion or cellular properties.

### Claim 3 (depends on 1)

The method of claim 1, wherein segmenting the image data comprises:
subtracting stationary components;
extracting features of the image data; and
identifying the plurality of clusters based on the features.

### Claim 4 (depends on 3)

The method of claim 3, wherein the image data is divided into non-overlapping blocks.

### Claim 5 (depends on 4)

The method of claim 4, wherein each non-overlapping block is identified as a foreground block or a background block based on a proportion of pixels having foreground or background characteristics.

### Claim 6 (depends on 4)

The method of claim 4, wherein extracting the features of the image data comprises extracting the features of the foreground blocks.

### Claim 7 (depends on 4)

The method of claim 4, wherein each non-overlapping block comprises a single pixel or a plurality of pixels.

### Claim 8 (depends on 3)

The method of claim 3, wherein extracting the features of the image data comprises extracting texture-based or intensity-based features of the image data.

### Claim 9 (depends on 3)

The method of claim 3, wherein extracting the features of the image data comprises an auto-correlation function or extracting motion-based features.

### Claim 10 (depends on 3)

The method of claim 3, wherein extracting the features of the image data comprises extracting the spectral profile of the texture-based or intensity-based features, or an auto-correlation function of the image data.

### Claim 11 (depends on 1)

The method of claim 1, wherein the number of the plurality of clusters is not specified before the segmenting.

### Claim 12 (depends on 1)

The method of claim 1, wherein the images comprise frames of a video or a set of sequential periodic images.

### Claim 13 (depends on 1)

The method of claim 1, wherein the plurality of cells comprise at least one of progenitor cells or myocytes.

### Claim 14

A computer program provided on one or more tangible computer-readable media, the computer program comprising:
a memory storing executable instructions configured to:
receive image data corresponding to images acquired over time of a plurality of cells;
segment the image data into a plurality of clusters, wherein each individual cluster represents only a portion of the plurality of cells and wherein the image data is not separated into motion components before being segmented into the plurality of clusters;
extract a motion signal from each respective cluster of the plurality of clusters;
evaluate at least one of cellular motion properties or cellular properties based on the motion signal from each respective cluster; and
generate an output indicative of the cellular motion properties of the plurality of clusters.

### Claim 15 (depends on 14)

The computer program as recited in claim 14, wherein the instructions configured to segment the image data into a plurality of clusters comprise a learning algorithm configured to iteratively identify potential clusters.

### Claim 16 (depends on 15)

The computer program as recited in claim 15, wherein the learning algorithm is configured to assign each foreground pixel to one of the plurality of clusters.

### Claim 17 (depends on 14)

The computer program as recited in claim 14, wherein the instructions configured to extract a motion signal comprise instructions to perform principal component analysis on image intensity of each individual cluster.

### Claim 18

An image analysis system, comprising:
an imager configured to optically analyze a plurality of cells;
data acquisition circuitry configured to acquire images of the plurality of cells via the imager; and
data processing circuitry configured to:
segment image data from the images of the plurality of cells into a plurality of clusters, extract a motion signal from image data of each individual cluster, and evaluate at least one of cellular motion properties or cellular properties based on the motion signal of each individual cluster.

### Claim 19 (depends on 18)

The image analysis system of claim 18, wherein the circuitry configured to extract the motion signal does not use motion field data as an input to the cluster segmentation.

### Claim 20 (depends on 18)

The image analysis system of claim 18, wherein the image data of each individual cluster comprises non-stationary components of the image data.
