# US 12,700,100 B2 · Methods for automatic target identification, tracking, and safety evaluation for radiotherapy

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

- Number: US 12,700,100 B2
- Document ID: US12700100B2
- Status: Granted
- Kind: B2
- Application number: 18/456,396
- Filed: 2023-08-25
- Published: 2024-03-28
- Granted: 2026-08-04
- Earliest claimed: 2021-02-26
- Assignees: RefleXion Medical, Inc.
- Applicants: RefleXion Medical, Inc.
- Inventors: Yevgen Voronenko; Maksat Haytmyradov; Peter Demetri Olcott; Lingxiong Shao; Manoj V. Narayanan
- Web page: https://patentgrep.com/patent/US12700100B2

## CPC

- G06T 7/11: Region-based segmentation
- A61N 5/103: {Treatment planning systems}
- A61N 5/1031: {using a specific method of dose optimization}
- A61N 5/1039: {using functional images, e.g. PET or MRI}
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/12: Edge-based segmentation
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 7/73: using feature-based methods
- A61N 2005/1052: {using positron emission tomography [PET] single photon emission computer tomography [SPECT] imaging}
- G06T 2207/10016: Video; Image sequence
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/10104: Positron emission tomography [PET]
- G06T 2207/10108: Single photon emission computed tomography [SPECT]
- G06T 2207/10116: X-ray image
- G06T 2207/20076: Probabilistic image processing
- G06T 2207/30096: Tumor; Lesion
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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

Disclosed herein are methods and systems for identifying the location of a target region using a tumor identification (ID) profile. A tumor ID profile includes identification parameters that characterize the target region. The tumor ID profile may be used to facilitate the identification of multiple target regions and to evaluate whether it is safe to deliver radiation to the target regions at their updated locations. Also disclosed herein are methods for analyzing a dose distribution to a target region by generating a bounded dose volume histogram (bDVH) based on gamma criteria comprising a distance-to-agreement (DTA) criterion and a dose difference (DD) criterion. In one variation, a gamma-derived bDVH is used in a method for selecting gamma criteria values for evaluating a radiotherapy treatment plan.

## Claims

### Claim 1

A method for locating a target region, the method comprising:
acquiring imaging data of a patient region that includes a tumor;
generating a map of pixel tumor likelihood values by calculating a tumor-likelihood value and background-likelihood value for each pixel of the imaging data; and
determining a location of the tumor by shifting a tumor contour within the imaging data to a centroid location of the map of pixel tumor likelihood values within a BTZ contour, wherein the BTZ contour encompasses the tumor contour.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining the location of the tumor further comprises:
iteratively updating the map of pixel tumor likelihood values to generate a final map of pixel tumor likelihood values such that an average pixel value within the shifted tumor contour is within a previously-defined threshold of an average pixel value within a pre-shifted tumor contour;
calculating a centroid location of the final map of pixel tumor likelihood values; and
determining the location of the tumor by shifting the tumor contour to the calculated centroid location.

### Claim 3 (depends on 2)

The method of claim 2, wherein generating a map of pixel tumor likelihood values comprises calculating a tumor-likelihood value and background-likelihood value for each pixel in the acquired imaging data.

### Claim 4 (depends on 3)

The method of claim 3, wherein calculating a tumor-likelihood value comprises calculating an average pixel value over the pixels within the tumor contour and a standard deviation value of the pixel values within the tumor contour.

### Claim 5 (depends on 4)

The method of claim 4, wherein calculating a background-likelihood value comprises calculating an average pixel value over the pixels outside the tumor contour and within the BTZ contour and a standard deviation value of the pixel values outside the tumor contour and within the BTZ contour.

### Claim 6 (depends on 5)

The method of claim 5, wherein iteratively updating the map of pixel tumor likelihood values comprises:
updating the map of pixel tumor probability values by assigning pixels within the shifted tumor contour a high tumor-probability value and assigning pixels outside the shifted tumor contour a low tumor-probability value;
updating tumor-likelihood values and background-likelihood values for each pixel in the acquired imaging data; and
adjusting the map of pixel tumor likelihood values using the updated map of pixel tumor probability values, updated tumor-likelihood values, and background-likelihood values.

### Claim 7 (depends on 2)

The method of claim 2, further comprising generating a graphical representation that comprises the tumor contour that has been shifted to the centroid location of the final map of pixel tumor likelihood values, the acquired updated imaging data and displaying the graphical representation to a display device.

### Claim 8 (depends on 1)

The method of claim 1, further comprising generating an initial map of pixel tumor probability values based on an initial image of the tumor, wherein the pixel tumor probability values are binary values and pixel likelihood values are any values greater than or equal to zero and less than or equal to one.

### Claim 9 (depends on 1)

The method of claim 1, wherein the acquired imaging data of the tumor comprises one or more of PET imaging data, CT imaging data, MR imaging data, and X-ray imaging data.

### Claim 10 (depends on 1)

The method of claim 1, further comprising generating an initial map of pixel tumor probability values based on an initial image of the tumor by assigning pixels within the tumor contour a high tumor-probability value and assigning pixels outside the tumor contour a low tumor-probability value.

### Claim 11 (depends on 10)

The method of claim 10, wherein the high tumor-probability value is one and the low tumor-probability value is zero.

### Claim 12 (depends on 1)

The method of claim 1, wherein acquiring imaging data comprises acquiring PET imaging data.

### Claim 13 (depends on 1)

The method of claim 1, wherein acquiring imaging data comprises acquiring CT imaging data.

### Claim 14 (depends on 1)

The method of claim 1, wherein acquiring imaging data comprises acquiring MR imaging data.

### Claim 15 (depends on 1)

The method of claim 1, wherein acquiring imaging data comprises acquiring SPECT imaging data.

### Claim 16 (depends on 1)

The method of claim 1, further comprising generating a graphical representation that comprises the tumor contour that has been shifted to the location of the tumor and displaying the graphical representation to a display device.

### Claim 17 (depends on 16)

The method of claim 16, wherein the graphical representation further comprises the BTZ contour, and wherein the shifted tumor contour and BTZ contour are superimposed on the acquired imaging data.

### Claim 18 (depends on 1)

The method of claim 1, further comprising generating a notification if a proximity of the shifted tumor contour to the BTZ contour is within a pre-determined margin.

### Claim 19

A method for evaluating a PET signal for radiotherapy, the method comprising:
acquiring PET imaging data of a patient region that includes a biology targeting zone (BTZ) region and a target region within the BTZ region;
determining a location of the target region within the BTZ region based on the PET imaging data;
calculating a target region standard uptake value (SUV) for pixels of the PET imaging data within the target region;
calculating a BTZ region SUV for pixels of the PET imaging data outside the target region and within the BTZ region;
calculating a normalized PET signal metric value of the target region using the target region SUV and the BTZ region SUV; and
evaluating the PET imaging data by comparing the normalized PET signal metric value with a planning PET signal metric value.

### Claim 20 (depends on 19)

The method of claim 19, wherein comparing the normalized PET signal metric value with a planning PET signal metric value comprises calculating a predicted radiation dose for the target region based on the net PET signal metric value and comparing the predicted radiation dose with a prescribed radiation dose.

### Claim 21 (depends on 19)

The method of claim 19, wherein determining the location of the target region comprises:
generating a map of pixel tumor likelihood values by calculating a tumor- likelihood value and background-likelihood value for each pixel of the PET imaging data;
shifting a contour of the target region to a centroid location of the map of pixel tumor likelihood values;
iteratively updating the map of pixel tumor likelihood values to generate a final map of pixel tumor likelihood values such that an average pixel value within the shifted target region contour is within a previously-defined threshold of an average pixel value within a pre-shifted tumor contour;
calculating a centroid location of the final map of pixel tumor likelihood values; and
determining the target region location by shifting the target region contour to the calculated centroid location.

### Claim 22

A method of tracking a target region, the method comprising:
acquiring PET imaging data of a target region;
identifying, using the acquired PET imaging data and a tumor identification (ID) profile, a location of the target region;
determining whether the location of the target region is within a target region contour; and
generating a notification if the location of the target region is outside a target region contour.

### Claim 23 (depends on 22)

The method of claim 22, wherein the target region contour is a biology-tracking zone (BTZ) contour.

### Claim 24 (depends on 22)

The method of claim 22, wherein the target region contour is a planning target volume (PTV) contour.

### Claim 25 (depends on 22)

The method of claim 22, further comprising generating an interlock to stop radiation delivery if the location of the target region is outside the target region contour.

### Claim 26 (depends on 22)

The method of claim 22, wherein determining whether the location of the target region is within a target region contour comprises determining whether any portion of the target region is outside the target region contour, and the method further comprises generating an interlock to stop radiation delivery if any portion of the target region is outside the target region contour.

### Claim 27 (depends on 22)

The method of claim 22, wherein the notification is a graphical user interface that comprises the location of the target region and the target region contour, and the method further comprises outputting the graphical user interface to a display device.

### Claim 28 (depends on 22)

The method of claim 22, wherein the notification is an audible alert, and the method further comprises outputting the audible alert to a speaker device.

### Claim 29

A method of tracking a target region, the method comprising:
acquiring PET imaging data of a target region;
identifying, using the acquired PET imaging data, a location of the target region, and wherein identifying the location of the target region comprises generating a map of pixel tumor likelihood values by calculating a tumor-likelihood value and background-likelihood value for each pixel of the PET imaging data and identifying the location of the target region by shifting a tumor contour within the PET imaging data to a centroid location of the map of pixel tumor likelihood values;
determining whether the location of the target region is within a target region contour; and
generating a notification if the location of the target region is outside a target region contour.