# US 2024/0392380 A1 · Identifying candidate cells using image analysis with overlap thresholds

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

- Number: US 2024/0392380 A1
- Document ID: US20240392380A1
- Status: Published application
- Kind: A1
- Application number: 18/391,955
- Filed: 2023-12-21
- Published: 2024-11-28
- Earliest claimed: 2017-03-31
- Assignees: CellMax Ltd.
- Applicants: CellMax Ltd.
- Inventors: Huangpin B. Hsieh; XiaoMing Wang; Jr-Ming Lai; Rui Mei; Hung-Jen Shao; Jen-Chia Wu
- Web page: https://patentgrep.com/patent/US20240392380A1

## CPC

- C12Q 1/6886: for cancer (immunoassay for cancer G01N33/575)
- G01N 1/31: Apparatus therefor
- G01N 15/1433: using image recognition
- G01N 33/5094: {for blood cell populations (red blood cells G01N33/80)}
- G01N 33/5758: {involving compounds serving as markers for tumours, cancers or neoplasias, e.g. cellular determinants, receptors, heat shock/stress proteins, A-protein, oligosaccharides or metabolites}
- G01N 33/582: {with fluorescent label}
- C12Q 1/6883: for diseases caused by alterations of genetic material
- G01N 15/1468: {with spatial resolution of the texture or inner structure of the particle}
- G01N 2015/1472: {with colour}
- G01N 2333/4742: Keratin; Cytokeratin
- G01N 2333/70589: CD45
- G06T 7/0012: {Biomedical image inspection}
- G06T 2207/10056: Microscopic image
- G06T 2207/30096: Tumor; Lesion
- G06T 2207/30101: Blood vessel; Artery; Vein; Vascular
- C12Q: MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS (immunoassay G01N33/53); COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- 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)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method for identifying candidate target cells within a biological fluid specimen includes a digital image of the biological fluid specimen with the digital image having a plurality of color channels, identifying first connected regions of pixels of a minimum first intensity in a first channel, identifying second connected regions of pixels of a minimum second intensity in a second channel, and determining first connected regions and second connected regions that spatially overlap. For a pair of a first connected region and a second connected region that spatially overlap, whether the second connected region overlaps the first connected region by a threshold amount is determined, and if the second connected region overlaps the first connected region by the threshold amount then the portion of the image corresponding to the overlap is continued to be treated as a candidate for classification.

## Claims

### Claim 1

A computer program product for identifying candidate target cells within a biological fluid specimen, the computer program product tangibly embodied in a non-transitory computer readable medium, comprising instructions to cause a processor to
receive a digital image of the biological fluid specimen, the digital image having a plurality of color channels;
identify first connected regions of pixels of a minimum first intensity in a first channel of the plurality of color channels;
identify second connected regions of pixels of a minimum second intensity in a second channel of the plurality of color channels;
determine first connected regions and second connected regions that spatially overlap; and
for each of least one of one or more pairs of a first connected region and a second connected region that spatially overlap, determine whether the second connected region overlaps the first connected region by a threshold amount, and if the second connected region overlaps the first connected region by the threshold amount then continue to treat a portion of the image corresponding to the overlap of first connected region and the second connected region as a candidate for classification.

### Claim 2 (depends on 1)

The computer program product of claim 1, comprising instructions to cause a processor to:
if the second connected region does not overlap the first connected region by the threshold amount then treat the portion of the image corresponding to the overlap of first connected region and the second connected region as not a cell.

### Claim 3 (depends on 2)

The computer program product of claim 2, wherein the threshold amount is 50%.

### Claim 4 (depends on 1)

The computer program product of claim 1, wherein the first color is blue, and the second color is red or orange.

### Claim 5 (depends on 1)

The computer program product of claim 1, wherein the instructions to identify the first connected regions comprise instructions to identifying first connected regions that have a minimum first size, and wherein the instructions to identify the second connected regions comprise instructions to identify second connected regions that have a minimum second size.

### Claim 6 (depends on 5)

The computer program product of claim 5, wherein the instructions to identify the first connected regions comprise instructions to identify first connected regions that have a maximum first size, and wherein the instructions to identify the second connected regions comprise instructions to identify second connected regions that have a maximum second size.

### Claim 7 (depends on 1)

The computer program product of claim 1, comprising instructions to determine whether first connected regions and second connected regions that spatially overlap include pixels having a minimum third intensity in a third channel of the plurality of color channels, and if a candidate region does not have pixels having the minimum third intensity in the third channel then continue to treat the portions of the image corresponding to the candidate region as a candidates for classification.

### Claim 8 (depends on 7)

The computer program product of claim 7, comprising instructions to treat a candidate region having pixels having the minimum third intensity in the third channel as a leukocyte or white blood cell.

### Claim 9

A method for identifying candidate target cells within a biological fluid specimen, the method comprising:
receiving a digital image of the biological fluid specimen, the digital image having a plurality of color channels;
identifying first connected regions of pixels of a minimum first intensity in a first channel of the plurality of color channels;
identifying second connected regions of pixels of a minimum second intensity in a second channel of the plurality of color channels;
determining first connected regions and second connected regions that spatially overlap; and
for each of least one of one or more pairs of a first connected region and a second connected region that spatially overlap, determining whether the second connected region overlaps the first connected region by a threshold amount, and if the second connected region is determined to overlap the first connected region by the threshold amount then continuing to treat a portion of the image corresponding to the overlap of first connected region and the second connected region as a candidate for classification.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
if the second connected region is determined to not overlap the first connected region by the threshold amount then treating the portion of the image corresponding to the overlap of first connected region and the second connected region as not a cell.

### Claim 11 (depends on 10)

The method of claim 10, wherein the threshold amount is 50%.

### Claim 12 (depends on 9)

The method of claim 9, wherein the first color is blue, and the second color is red or orange.

### Claim 13 (depends on 9)

The method of claim 9, wherein identifying the first connected regions includes identifying first connected regions that have a minimum first size and identifying the second connected regions includes identifying second connected regions that have a minimum second size.

### Claim 14 (depends on 13)

The method of claim 13, wherein identifying the first connected regions comprises identifying first connected regions that have a maximum first size and identifying the second connected regions comprises identifying second connected regions that have a maximum second size.

### Claim 15 (depends on 9)

The method of claim 9, comprising determining whether first connected regions and second connected regions that spatially overlap include pixels having a minimum third intensity in a third channel of the plurality of color channels, and if a candidate region is determined to not have pixels having the minimum third intensity in the third channel then continuing to treat the portions of the image corresponding to the candidate region as a candidates for classification.

### Claim 16 (depends on 15)

The method of claim 15, comprising treating a candidate region having pixels having the minimum third intensity in the third channel as a leukocyte or white blood cell.
