# US 10,482,314 B2 · Automatic calculation for ploidy classification

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

- Number: US 10,482,314 B2
- Document ID: US10482314B2
- Status: Granted
- Kind: B2
- Application number: 15/937,214
- Filed: 2018-03-27
- Published: 2018-10-11
- Granted: 2019-11-19
- Earliest claimed: 2017-03-28
- Assignees: Oslo Universitetssykehus, Institute for Cancer Genetics and Informatics
- Applicants: Oslo Universitetssykehus, Institute for Cancer Genetics and Informatics
- Inventors: Rolf Anders Syvertsen; Tarjei Sveinsgjerd Hveem; John Robert Maddison; Havard Emil Greger Danielsen
- Web page: https://patentgrep.com/patent/US10482314B2

## CPC

- G01N 15/1433: using image recognition
- G06V 10/50: by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V 20/698: {Matching; Classification}
- G01N 2015/1497: {Particle shape}
- 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

A method of image classification is used for classifying images of stained cell nuclei. For each nucleus, the total integrated optical density is calculated and a histogram calculated. The image is then classified by automatically identifying peaks, identifying the lowest peak as a 2C peak and classifying the image as at least one of diploid, tetraploid, aneuploid or polyploid based on the number of peaks and the count at an integrated optical densities above the 2C peak.

## Claims

### Claim 1

A method of image classification, comprising:
receiving an image section of a plurality of cell nuclei;
calculating a measure of the two-dimensional integrated optical density of a plurality of the nuclei;
creating a histogram by counting the number of nuclei within each of a plurality of bins, each bin relating to a respective range of the measure of the two-dimensional integrated optical density; and
classifying the image by:
identifying the peaks of the histogram, their count and their integrated optical density;
identifying the lowest peak as a 2C peak; and
classifying the image as at least one of diploid, tetraploid, aneuploid or polyploid based on the number of peaks and the count at an integrated optical densities above the 2C peak.

### Claim 2 (depends on 1)

The method according to claim 1, further comprising:
if there is a single peak, calculating the total count at an integrated optical density at 2.5 times the integrated optical density at the peak of the 2C peak as a 5C-exceeding value, and classifying the image as diploid if the 5C-exceeding value is not greater than 1% and as aneuploid if the 5C-exceeding value is greater than 1%.

### Claim 3 (depends on 1)

The method according to claim 1, further comprising:
if there are two peaks, classifying the image as diploid If the peak that is not the lowest peak has a count of at least 5% of the number of the lowest peak but less than 10% of the total count.

### Claim 4 (depends on 1)

The method according to claim 1
wherein classifying the image further comprises:
calculating the total count greater than 4.5× the integrated optical density corresponding to the 2c peak as a 9C-exceeding value;
classifying the image as tetraploid if there are two or three peaks, and the 9C-exceeding value is less than 1% of the total count.

### Claim 5 (depends on 4)

The method according to claim 4, further comprising:
if the image is not classified as tetraploid, classifying the image as polyploid if there are three or more peaks at integral multiples of the integrated optical density of the 2C peak; and
otherwise classifying the image as aneuploid.

### Claim 6 (depends on 1)

A non-transitory computer readable medium for image classification of an image section of a plurality of cell nuclei, wherein the computer program product is arranged, when run on a computer, to cause the computer to carry out the steps of a method according claim 1.

### Claim 7

An automatic classification system for an image section of a plurality of stained cell nuclei; comprising a computer and code for:
calculating a measure of the two-dimensional integrated optical density of a plurality of the nuclei;
creating a histogram by counting the number of nuclei within each of a plurality of bins, each bin relating to a respective range of the measure of the two-dimensional integrated optical density; and
classifying the image by:
identifying the peaks of the histogram, their count and their integrated optical density;
identifying the lowest peak as a 2C peak; and
classifying the image as at least one of diploid, tetraploid, aneuploid or polyploid based on the number of peaks and the count at an integrated optical densities above the 2C peak.