# US 2018/0021597 A1 · X-Ray Patient Position Monitoring

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

- Number: US 2018/0021597 A1
- Document ID: US20180021597A1
- Status: Published application
- Kind: A1
- Application number: 15/549,091
- Filed: 2015-02-09
- Published: 2018-01-25
- Earliest claimed: 2015-02-09
- Assignees: Brainlab AG
- Applicants: Brainlab AG
- Inventors: Kajetan BERLINGER; Jorg REHS
- Web page: https://patentgrep.com/patent/US20180021597A1

## CPC

- A61N 5/1049: {for verifying the position of the patient with respect to the radiation beam}
- A61N 5/1067: {in real time, i.e. during treatment}
- A61N 2005/1051: {using an active marker}
- A61N 2005/1058: {using ultrasound imaging}
- A61N 2005/1062: {using virtual X-ray images, e.g. digitally reconstructed radiographs [DRR]}
- A61N: ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY (measurement of bioelectric currents A61B; surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body A61B18/00; anaesthetic apparatus in general A61M; incandescent lamps H01K; infrared radiators for heating H05B)

## Abstract

A data processing method performed by a computer for monitoring the position of a patient, comprising the steps of: acquiring a 3D image dataset of the patient; acquiring an initial real image of the patient from a medical imaging system having a known and fixed location in space, thus defining a known viewing direction of the initial real image in space, the real image being taken at a first point in time; —performing 2D/3D registration by calculating a simulated image from the 3D image dataset which matches the initial real image best, the simulated image having a viewing direction onto the 3D image dataset; storing an initial similarity measure value for the pair of the initial real image and the calculated simulated image; —acquiring a subsequent real image from the medical imaging system taken at a second point in time later than the first point in time; calculating a subsequent similarity measure value for the pair of the subsequent real image and the calculated simulated image; and outputting an indication signal if the difference between the initial similarity measure value and the subsequent similarity measure value fulfills a predetermined criterion.

## Claims

### Claim at position 1

-15. (canceled)

### Claim 16

A computer implemented method for monitoring the position of a patient, comprising:
acquiring a 3D image dataset of the patient;
acquiring an initial real image of the patient from a medical imaging system having a known and fixed location in space, thus defining a known viewing direction of the initial real image in space, the real image being taken at a first point in time;
performing 2D/3D registration by calculating a simulated image from the 3D image dataset which substantially matches the initial real image, the simulated image having a viewing direction onto the 3D image dataset;
storing an initial similarity measure value for the pair of the initial real image and the calculated simulated image;
acquiring a subsequent real image from the medical imaging system taken at a second point in time later than the first point in time;
calculating a subsequent similarity measure value for the pair of the subsequent real image and the calculated simulated image; and
outputting an indication signal if the difference between the initial similarity measure value and the subsequent similarity measure value fulfills a predetermined criterion.

### Claim 17 (depends on 16)

The method of claim 16, wherein
acquiring a plurality of initial real images of the patient from a plurality of medical imaging systems having a known and fixed location in space, thus defining known viewing directions of the initial real images in space, the plurality of real images being taken at the first point in time;
wherein performing the 2D/3D registration involves calculating a plurality of simulated images from the 3D image dataset which substantially match the initial real images, wherein there is one simulated image for each of the initial real images and each simulated image has a viewing direction onto the 3D image dataset;
storing a plurality of initial similarity measure values which comprises one similarity measure value for each pair of an initial real image and a corresponding simulated image:
acquiring a plurality of subsequent real images from the plurality of medical imaging systems taken at the second point in time;
calculating a plurality of subsequent similarity measure values for each pair of a subsequent real image and the corresponding calculated simulated image; and
outputting the indication signal if a value which is calculated from the differences between the initial similarity measure values and the corresponding subsequent similarity measure values fulfills a predetermined criterion.

### Claim 18 (depends on 17)

The method of claim 17, wherein the relations between the viewing directions of the simulated images equal the relations between the viewing directions of the real images.

### Claim 19 (depends on 17)

The method of claim 17, wherein said value is calculated from all the differences or a subset of the differences.

### Claim 20 (depends on 16)

The method of claim 16, wherein the real image is an X-ray image and the simulated image is a DRR image.

### Claim 21 (depends on 16)

The method of claim 16, wherein the performing the 2D/3D registration involves positioning of the 3D image dataset in space, wherein a position of a virtual imaging system for calculating a simulated image equals the position of the corresponding medical imaging system in space.

### Claim 22 (depends on 21)

The method of claim 21, wherein the 2D/3D registration is an iterative process starting with an initial position of the 3D image dataset in space, wherein this initial position is a position in which an isocenter defined with respect to the 3D image dataset equals an isocenter of a medical treatment beam.

### Claim 23 (depends on 22)

The method of claim 22, wherein the difference between the initial position of the 3D image dataset and the adjusted position of the 3D image dataset is stored as an offset.

### Claim 24 (depends on 23)

The method of claim 23, wherein, if the position of the patient has been changed, acquiring a new initial real images; performing a new 2D/3D registration with an initial position of the 3D image dataset calculated from the offset and the change in the patient's position; and storing a new initial similarity measure value.

### Claim 25 (depends on 16)

The method of claim 16, further comprising stopping a treatment beam if the indication signal is output.

### Claim 26 (depends on 16)

The method of claim 16, further comprising performing a new 2D/3D registration if the indication signal is output.

### Claim 27 (depends on 16)

The method of claim 16, comprising the steps of:
calculating an additional initial similarity measure value for a pair of the initial real image and an additional simulated image having a viewing direction which differs from the viewing direction of the best matching simulated image by a known difference;
calculating an additional subsequent similarity measure value for a pair of the subsequent real image and the additional simulated image;
including the additional initial similarity measure value when calculating the initial similarity measure value; and
including the additional subsequent similarity measure value when calculating the subsequent similarity measure value.

### Claim 28 (depends on 16)

The method of claim 16, comprising the steps of:
calculating an additional initial similarity measure value for a pair of the initial real image and an additional simulated image having a viewing direction which differs from the viewing direction of the best matching simulated image by a known difference; and
calculating an additional subsequent similarity measure value for a pair of the subsequent real image and the additional simulated image;
wherein the indication signal is output if a value which is calculated from the difference between the initial similarity measure value and the corresponding subsequent similarity measure value and the difference between the additional initial similarity measure value and the corresponding additional subsequent similarity measure value fulfills a predetermined criterion.

### Claim 29

A non-transitory computer readable storage medium having a plurality of instructions for monitoring the position of a patient which, when executed by at least one processor, causes the at least one processor. to:
acquire a 3D image dataset of the patient;
acquire an initial real image of the patient from a medical imaging system having a known and fixed location in space defining a known viewing direction of the initial real image in space, the real image being taken at a first point in time;
perform a 2D/3D registration by determining a simulated image from the 3D image dataset which substantially matches the initial real image, the simulated image having a viewing direction onto the 3D image dataset;
store an initial similarity measure value for the pair of the initial real image and the calculated simulated image;
acquire a subsequent real image from the medical imaging system taken at a second point in time later than the first point in time;
determine a subsequent similarity measure value for the pair of the subsequent real image and the calculated simulated image; and
output an indication signal if the difference between the initial similarity measure value and the subsequent similarity measure value fulfills a predetermined criterion.

### Claim 30

A system including memory and one or more processors operable to execute instructions, stored in the memory, including instructions to perform the operation of:
acquiring a 3D image dataset of the patient;
acquiring an initial real image of the patient from a medical imaging system having a known and fixed location in space and a known viewing direction taken at a first point in time;
performing a 2D/3D registration by calculating a simulated image from the 3D image dataset, the simulated image having a viewing direction onto the 3D image dataset;
storing an initial similarity measure value for the pair of the initial real image and the calculated simulated image;
acquiring a subsequent real image from the medical imaging system taken at a second point in time;
calculating a subsequent similarity measure value for the pair of the subsequent real image and the calculated simulated image; and
outputting an indication signal if the difference between the initial similarity measure value and the subsequent similarity measure value fulfills a predetermined criterion.
