# US 2021/0065358 A1 · System for detecting contrast in medical scans

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

- Number: US 2021/0065358 A1
- Document ID: US20210065358A1
- Status: Published application
- Kind: A1
- Application number: 16/552,249
- Filed: 2019-08-27
- Published: 2021-03-04
- Earliest claimed: 2019-08-27
- Assignees: Aidoc Medical Ltd
- Applicants: AIDOC Medical LTD
- Inventors: Eugene WALACH; Elad WALACH; Idan BASSUKEVITCH; Yonatan ROSMARIN; Michael BRAGINSKI
- Web page: https://patentgrep.com/patent/US20210065358A1

## CPC

- G06V 10/507: {Summing image-intensity values; Histogram projection analysis}
- G06T 7/0012: {Biomedical image inspection}
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/30016: Brain
- G06V 2201/031: of internal organs
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

An apparatus for analysing a head CT scan is provided, wherein the head CT scan includes a plurality of cross-sections. The apparatus includes a processor configured to: select a first cross-section from among the plurality of cross-sections in the head CT scan; and analyse the first cross-section to determine whether the whole head CT scan was taken with contrast, the analysing including: determining whether the first cross-section shows contrast, based on a presence of bright patches in the first cross-section, determining whether an amount of sulci in the first cross-section is below a threshold amount, in response to determining that the first cross-section shows contrast, determine that the whole head CT scan was taken with contrast, and in response to the determining that the first cross-section does not show contrast and that the amount of sulci is below the threshold amount determining that the whole head CT scan was taken without contrast.

## Claims

### Claim 1

An apparatus for analysing a head CT scan, wherein the head CT scan comprises a plurality of cross-sections, the apparatus comprising a processor configured to:
select a first cross-section from among the plurality of cross-sections in the head CT scan; and
analyse the first cross-section to determine whether the whole head CT scan was taken with contrast, the analysing comprising:
determining whether the first cross-section shows contrast, based on a presence of bright patches in the first cross-section,
determining whether an amount of sulci in the first cross-section is below a threshold amount,
in response to determining that the first cross-section shows contrast, determine that the whole head CT scan was taken with contrast, and
in response to the determining that the first cross-section does not show contrast and that the amount of sulci is below the threshold amount determining that the whole head CT scan was taken without contrast.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the processor is further configured to, in response to determining that the first cross-section does not show contrast and that the amount of sulci in the first cross-section is not below the threshold amount, select a second cross-section from among the plurality of cross-sections and analyse the second cross-section to determine whether the whole head CT scan was taken with contrast.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the processor is further configured to:
identify a brain area in the first cross-section, the brain area showing brain tissue; and
calculate an average brain pixel value of pixels from among a plurality of pixels in the cross section which are in the brain area.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein the processor is configured to identify the brain area in the first cross-section by:
identifying a maximal connected component in the cross-section, comprising a plurality of connected pixels with pixel values above a threshold pixel value,
identifying the brain area as a largest hole in the maximal connected component.

### Claim 5 (depends on 4)

The apparatus of claim 4, wherein the threshold pixel value is 1000 Hounsfield units.

### Claim 6 (depends on 3)

The apparatus of claim 3, wherein the processor is configured to determine whether the amount of sulci in the first cross-section is below the threshold amount by:
generating a binary image of pixels in the brain area which have a pixel value below the average brain pixel value;
obtaining an Euler number of the binary image;
determining whether the Euler number of the binary image is below a threshold Euler number; and
determining that the amount of sulci in the first cross-section is below the threshold amount in response to determining that the Euler number of the binary image is below the threshold Euler number.

### Claim 7 (depends on 6)

The apparatus of claim 6, wherein the threshold Euler number is zero.

### Claim 8 (depends on 3)

The apparatus of claim 3, wherein the processor is configured to determine whether the amount of sulci in the first cross-section is below the threshold amount by:
generating a binary image of pixels in the brain area which have a pixel value below a threshold amount below the average brain pixel value;
identifying groups of pixels in the binary image representing pixels in the first cross-section with pixel values a threshold amount below the average brain pixel value;
determining whether a percentage of pixels in the binary image identified as being in a group is below a threshold percentage; and
determining that the amount of sulci in the first cross-section is below the threshold amount in response to determining that the percentage of pixels identified as being in a group is below the threshold percentage.

### Claim 9 (depends on 8)

The apparatus of claim 8, wherein the threshold percentage is 20%.

### Claim 10 (depends on 8)

The apparatus of claim 8, wherein the threshold amount below the average brain pixel value is 20 Hounsfield units.

### Claim 11 (depends on 3)

The apparatus of claim 3, wherein the processor is configured to determine whether the first cross-section shows contrast by:
identifying groups of pixels in the brain area, the groups of pixels having average pixel values a threshold amount above the average brain pixel value;
determining that the cross-section shows contrast in response to determining that the number of identified groups is above a threshold number of groups.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the threshold amount above the average brain pixel value is 40 Hounsfield units.

### Claim 13 (depends on 11)

The apparatus of claim 11, wherein the threshold number of groups is 20.

### Claim 14 (depends on 1)

The apparatus of claim 1, wherein the processor is configured to:
assign a plurality of priority levels to cross-sections in the CT scan based on a set of predetermined rules, and
select the first cross-section as the cross-section in the CT scan with the highest priority level.

### Claim 15 (depends on 14)

The apparatus of claim 14, wherein the priority levels decrease from cross-sections at a top of the CT scan to cross-sections at a bottom of the CT scan.

### Claim 16 (depends on 1)

A system comprising:
the apparatus of any of claim 1, further comprising:
a first image analysis unit to analyse a CT scan taken with contrast and output a result indicating whether the CT scan shows a predetermined feature; and
a second image analysis unit to analyse a CT scan taken without contrast and output a result indicating whether the CT scan shows a predetermined feature,
wherein the processor of the apparatus is further configured to:
in response to determining that the whole head CT scan was taken with contrast, control the first image analysis unit to analyse the head CT scan, and
in response to determining that the whole head CT scan was taken without contrast, control the second image analysis unit to analyse the head CT scan.

### Claim 17 (depends on 16)

The system of claim 16, wherein at least one of the first image analysis unit and the second image analysis unit is an artificial intelligence, AI, classifier.

### Claim 18 (depends on 16)

The system of claim 16, wherein the predetermined feature is a brain bleed.

### Claim 19

A computer-implemented method for analysing a head CT scan, wherein the head CT scan comprises a plurality of cross-sections, the method comprising:
selecting a first cross-section from among the plurality of cross-sections in the head CT scan; and
analysing the first cross-section to determine whether the whole head CT scan was taken with contrast, the analysing comprising:
determining whether the first cross-section shows contrast, based on a presence of bright patches in the first cross-section,
determining whether an amount of sulci in the first cross-section is below a threshold amount,
in response to determining that the first cross-section shows contrast, determine that the whole head CT scan was taken with contrast, and
in response to the determining that the first cross-section does not show contrast and that the amount of sulci is below the threshold amount determining that the whole head CT scan was taken without contrast.
