# US 12,008,760 B2 · Systems and methods for estimating the movement of a target using a universal deformation model for anatomic tissue

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

- Number: US 12,008,760 B2
- Document ID: US12008760B2
- Status: Granted
- Kind: B2
- Application number: 17/373,400
- Filed: 2021-07-12
- Published: 2022-01-27
- Granted: 2024-06-11
- Earliest claimed: 2020-07-24
- Assignees: Covidien LP
- Applicants: Covidien LP
- Inventors: Nicolas J. Merlet; Oren P. Weingarten; Ariel Birenbaum; Alexander Nepomniashchy; Evgeni Kopel; Guy Alexandroni
- Web page: https://patentgrep.com/patent/US12008760B2

## CPC

- G06T 7/0016: {involving temporal comparison}
- G06T 7/33: using feature-based methods
- G06T 3/20: Linear translation of whole images or parts thereof, e.g. panning
- G06T 3/4007: based on interpolation, e.g. bilinear interpolation (image demosaicing G06T3/4015; edge-driven or edge-based scaling G06T3/403)
- G06T 3/60: Rotation of whole images or parts thereof
- G06T 7/149: involving deformable models, e.g. active contour models
- G06T 7/344: {involving models}
- G06T 7/37: using transform domain methods
- G06T 17/20: Finite element generation, e.g. wire-frame surface description, {tesselation}
- G06T 2207/10028: Range image; Depth image; 3D point clouds
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/20081: Training; Learning
- G06T 2207/30061: Lung
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Systems and methods of estimating movement of anatomical structures of a new patient include learning one or more deformation models from preoperative and intraoperative imaging data of a set of other patients and estimating movement of anatomical structures of the new patient based on the one or more deformation models and preoperative imaging data of the new patient. Estimating movement of the anatomical structures may include applying deformation models to map data derived from preoperative imaging data of a new patient to obtain deformed map data for each deformation model, and determining the deformation model that best fits the intraoperative imaging data of the new patient. Applying a deformation model to map data may include applying a transformation to the deformation model and interpolating to obtain a deformed map data. Registration is computed between locations of a medical device sampled during navigation of the medical device through the new patient and the original and deformed map data. The map data which fits the 3D locations the best is applied to the targets of the new patient.

## Claims

### Claim 1

A method comprising:
receiving, for each patient of a set of patients, preoperative imaging data of a first imaging modality and intraoperative imaging data of a second imaging modality;
registering, for each patient of the set of patients, the preoperative imaging data of the first imaging modality to the intraoperative imaging data of the second imaging modality;
registering preoperative imaging data of each patient to preoperative imaging data of other patients;
registering different deformations of the set of patients into a common deformation space, yielding different possible deformations;
generating a set of deformation models representing the different possible deformations;
applying each deformation model of the deformation models to preoperative imaging data of a new patient to obtain deformed imaging data for each deformation model;
comparing, for each deformation model, the deformed imaging data to intraoperative data of the new patient; and
determining the deformation model that best fits the intraoperative imaging data of the new patient based on the comparing.

### Claim 2 (depends on 1)

The method of claim 1, wherein the intraoperative data of the new patient includes at least one of imaging data or navigation data.

### Claim 3 (depends on 1)

The method of claim 1, wherein registering the images of the preoperative imaging data to images of the intraoperative imaging data includes at least one of rotating and translating the images of the preoperative imaging data.

### Claim 4 (depends on 1)

The method of claim 1, wherein registering the images of the preoperative imaging data with each other includes at least one of scaling, rotating, and translating the images of the preoperative imaging data.

### Claim 5 (depends on 1)

The method of claim 1, wherein the first imaging modality is computed tomography (CT) and the second imaging modality is cone beam CT (CBCT).

### Claim 6 (depends on 1)

The method of claim 1, wherein registering the images of the preoperative imaging data to the images of the intraoperative imaging data includes:
applying an interpolation process to an airway skeleton of the images of the preoperative imaging data to obtain an equivalent airway skeleton in a coordinate system of the images of the intraoperative imaging data;
performing automatic registration between the equivalent airway skeleton and an airway distance map of the images of the preoperative imaging data to obtain a transformation; and
applying the transformation to coordinates of second 3D control points of the images of the intraoperative imaging data to obtain movement of the second 3D control points in the coordinate system of the images of the preoperative imaging data.

### Claim 7 (depends on 6)

The method of claim 6, wherein the interpolation process includes a thin plate spline (TPS) process.

### Claim 8 (depends on 6)

The method of claim 6, wherein registering the images of the preoperative imaging data with each other includes:
selecting a reference image of the preoperative imaging data;
performing registration between an airway skeleton of a current image of the preoperative imaging data and the airway distance map of the reference image of the preoperative imaging data to obtain a second transformation; and
applying the second transformation to the movement of the second 3D control points.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
creating a mesh grid for first 3D control points of the reference image of the preoperative imaging data; and
applying an interpolating process to the mesh grid relative to the movement of the first 3D control points of the current image of the preoperative imaging data to obtain a standardized mesh grid.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
determining a similarity measure between mesh grids of pairs of images of the preoperative imaging data, respectively; and
generating a first deformation model of images of the preoperative imaging data closest to a first center image of the preoperative imaging data based on the similarity measure.

### Claim 11 (depends on 10)

The method of claim 10, wherein the similarity measure between two mesh grids is an average Euclidean distance between first 3D control points of two images of the preoperative imaging data, respectively.

### Claim 12 (depends on 10)

The method of claim 10, wherein the similarity measure is between two mesh grids of the images of the intraoperative imaging data, between mesh grids of an image of the preoperative imaging data and an image of the intraoperative imaging data, or between a mesh grid of an image of the intraoperative imaging data and a model grid.

### Claim 13 (depends on 10)

The method of claim 10, further comprising:
generating a second deformation model of images of the preoperative imaging data closest to a second center image of the preoperative imaging data based on the similarity measure;
for each patient, computing a minimum of the similarity measure and each of the mesh grids of the first deformation model and the second deformation model to obtain scores; and
selecting the first deformation model or the second deformation model having a lowest score to perform a transformation.

### Claim 14 (depends on 9)

The method of claim 9, wherein the first and second 3D control points are crossing points of at least one of arteries, veins, and airways in the images of the preoperative imaging data and the images of the intraoperative imaging data, respectively.