# US 2019/0172210 A1 · Automatic quality checks for radiotherapy contouring

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

- Number: US 2019/0172210 A1
- Document ID: US20190172210A1
- Status: Published application
- Kind: A1
- Application number: 16/252,848
- Filed: 2019-01-21
- Published: 2019-06-06
- Earliest claimed: 2015-09-22
- Assignees: Varian Medical Systems International AG
- Applicants: Varian Medical Systems International AG
- Inventors: Thomas ALBRECHT; Peter HESS; Nawal HOUHOU
- Web page: https://patentgrep.com/patent/US20190172210A1

## CPC

- G06T 7/143: involving probabilistic approaches, e.g. Markov random field [MRF] modelling
- G06F 16/54: Browsing; Visualisation therefor
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 7/001: {using an image reference approach}
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/12: Edge-based segmentation
- G06T 7/13: Edge detection
- G06T 7/50: Depth or shape recovery
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10116: X-ray image
- G06T 2207/20076: Probabilistic image processing
- G06T 2207/20212: Image combination
- G06T 2207/30008: Bone
- G06T 2207/30048: Heart; Cardiac
- G06T 2207/30096: Tumor; Lesion
- G06T 2207/30168: Image quality inspection
- G06T 2207/30242: Counting objects in image
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Systems, devices, methods, and computer processing products for automatically checking for errors in segmentation (contouring) using heuristic and/or statistical evaluation methods.

## Claims

### Claim at position 1

1-31. (canceled)

### Claim 32

A method for detecting a segmentation error in a segment representing a delineation of an anatomical structure of a subject on an image, comprising:
selecting an appropriate segment evaluation method from a plurality of segment evaluation methods available to be applied on the segment, the plurality of evaluation methods including a heuristic evaluation method and a statistical evaluation method; and
evaluating the segment using the selected evaluation method,
wherein the heuristic evaluation method includes evaluating whether one or more of a set of heuristic rules are violated, and the statistical evaluation method includes evaluating whether a shape of the segment is within a predetermined range of known shapes for the segment; and
providing a signal indicating that an error in the segmentation is present based on a result of the evaluating.

### Claim 33 (depends on 32)

The method of claim 32, wherein the determining whether one or more of the heuristic rules are violated includes using Boolean operators and pixel/voxel counting.

### Claim 34 (depends on 33)

The method of claim 33, wherein the determining whether one or more of the heuristic rules are violated using Boolean operators and pixel/voxel counting comprises:
generating binary images for the segment;
combining the binary images using at least one of a plurality of Boolean operators to obtain a resulting binary image; and
counting pixels/voxels in the resulting binary image,
wherein a heuristic rule is violated if the number of pixels/voxels is not within a predetermined range.

### Claim 35 (depends on 32)

The method of claim 32, wherein the determining whether one or more of the heuristic rules are violated includes using a 3D connectivity labeling process.

### Claim 36 (depends on 35)

The method of claim 35, wherein using the 3D connectivity labeling process includes identifying disconnections in the segment by:
determining how many segment components does the segment have; and
comparing the number of the segment components with a previously determined number representing the number of connected components delineating the anatomical structure,
wherein a heuristic rule is violated if the number of segment components is different from the previously determined number of connected components.

### Claim 37 (depends on 32)

The method of claim 32, wherein the evaluating whether the shape of the segment is within a predetermined range of known shapes for the segment includes:
generating a statistical shape model for the segment; and
determining whether the shape of the segment is within a predetermined range of known shapes for the segment,
wherein a segmentation error is present if the shape of the segment is not within the predetermined range.

### Claim 38 (depends on 37)

The method of claim 37, further comprising:
generating the shape model based on a probabilistic distribution of shape variations found in the range of known shapes for the segment; and
performing a statistical test to check if the shape of the segment is within the predetermined range.

### Claim 39 (depends on 38)

The method of claim 38, wherein the probabilistic distribution includes a multivariate normal distribution (μ, Σ), and the performing of the statistical check comprises evaluating how well the segment shape fits within the multivariate normal distribution using a probabilistic principal component analysis (PPCA),
wherein if the shape of the segment does not fit within the multivariate normal distribution within a predetermined value, it is determined that a segmentation error is present.

### Claim 40 (depends on 32)

The method of claim 32, wherein the evaluating is automatically performed after generating the segment on the image.

### Claim 41 (depends on 40)

The method of claim 40, wherein the generating of the segment on the image is by one of an automatic, manual, or a combination of automatic and manual segmentation.

### Claim 42 (depends on 41)

The method of claim 41, wherein the generating of the segment and the evaluating of the segment are performed by same device.

### Claim 43 (depends on 41)

The method of claim 41, wherein the generating of the segment and the evaluating of the segment are performed by different devices operably connected to each other.

### Claim 44 (depends on 32)

The method of claim 32, further comprising providing information regarding the nature and location of the detected segmentation error.

### Claim 45

A system for detecting a segmentation error in a segment representing a delineation of an anatomical structure of a subject on an image, the system being configured to:
select an appropriate segment evaluation method from a plurality of segment evaluation methods available to be applied on the segment, the plurality of evaluation methods including a heuristic evaluation method and a statistical evaluation method;
evaluate the segment using the selected evaluation method, the heuristic evaluation method including evaluating whether one or more of a set of heuristic rules are violated, and the statistical evaluation method including evaluating whether a shape of the segment is within a predetermined range of known shapes for the segment; and
provide a signal that an error in the segmentation is present based on a result of the evaluating.

### Claim 46 (depends on 45)

The system of claim 45, comprising a database including the set of heuristic rules.

### Claim 47 (depends on 45)

The system of claim 45, wherein the system is configured to determine whether one or more of the heuristic rules are violated using Boolean operators and pixel/voxel counting.

### Claim 48 (depends on 47)

The system of claim 47, wherein the system is further configured to:
generate binary images for the segment;
combine the binary images using at least one of a plurality of Boolean operators to obtain a resulting binary image;
count pixels/voxels in the resulting binary image; and
signal that a heuristic rule is violated when the number of pixels/voxels is not within a predetermined range.

### Claim 49 (depends on 45)

The system of claim 45, wherein the system is further configured to determine whether one or more of the heuristic rules are violated using a 3D connectivity labeling process.

### Claim 50 (depends on 49)

The system of claim 49, wherein the system is further configured to:
identify disconnections in the segment by determining how many segment components does the segment have; and
compare the number of the segment components with a previously determined number representing the number of connected components delineating the anatomical structure,
wherein a heuristic rule is violated if the number of segment components is different from the previously determined number of connected components.

### Claim 51 (depends on 45)

The system of claim 45, wherein the system is further configured to:
evaluate whether the shape of the segment is within a predetermined range of known shapes for the segment by generating a statistical shape model for the segment; and
determine whether the shape of the segment is within a predetermined range of known shapes for the segment,
wherein a segmentation error is present if the shape of the segment is not within the predetermined range.

### Claim 52 (depends on 51)

The system of claim 51, the system being further configured to generate the shape model based on a probabilistic distribution of shape variations found in the range of known shapes for the segment and perform a statistical test to check if the shape of the segment is within the predetermined range.

### Claim 53 (depends on 45)

The system of claim 45, wherein the system is configured to automatically perform the segment evaluation after the segment is generated on the image.

### Claim 54 (depends on 53)

The system of claim 53, further comprising a device for generating the segment on the image by one of an automatic, manual, or a combination of automatic and manual segmentation.