# US 2026/0076745 A1 · Device and method for obtaining an augmented patient-specific bone/cartilage model of a target anatomical structure of a patient

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

- Number: US 2026/0076745 A1
- Document ID: US20260076745A1
- Status: Published application
- Kind: A1
- Application number: 19/337,380
- Filed: 2025-09-23
- Published: 2026-03-19
- Earliest claimed: 2024-01-19
- Assignees: Ganymed Robotics
- Applicants: Ganymed Robotics
- Inventors: Marion DECROUEZ; Anna GOUNOT; Valérie BURDIN; Guillaume DARDENNE; Baptiste DEHAINE
- Web page: https://patentgrep.com/patent/US20260076745A1

## CPC

- A61B 34/10: Computer-aided planning, simulation or modelling of surgical operations
- G06T 7/344: {involving models}
- A61B 2034/105: {Modelling of the patient, e.g. for ligaments or bones}
- A61B 2034/107: {Visualisation of planned trajectories or target regions}
- A61B 2034/108: {Computer aided selection or customisation of medical implants or cutting guides}
- A61B 2090/365: {augmented reality, i.e. correlating a live optical image with another image}
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/30008: Bone
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The present invention relates to a device and method for obtaining an augmented patient-specific bone/cartilage model of a target anatomical structure of a patient.

## Claims

### Claim 1

A device for obtaining an augmented patient-specific bone/cartilage model of a target anatomical structure of a patient, said target anatomical structure including at least one portion of a target bone and at least one portion of a target cartilage, said device comprising:
at least one input configured to receive:
a dataset comprising 3D images acquired on a plurality of subjects, each 3D image acquired on a subject comprising a subject anatomical structure corresponding to the target anatomical structure, wherein each of said 3D images comprise bone tissues of the subject anatomical structure and at least part of each of said 3D images comprise cartilage tissues of the subject anatomical structure, and
a previously generated patient-specific 3D model of at least one portion of said target bone of the patient;
at least one processor configured to:
for at least two 3D images of the dataset, segment the bone tissues of the subject anatomical structure,
determine a bone Statistical Shape Model based on said segmented bone tissues,
for at least two 3D images of the dataset comprising cartilage tissues of the subject anatomical structure, segment the subject anatomical structure and perform a rigid registration of said bone Statistical Shape Model with the segmented bone tissues of the subject anatomical structure and optimize at least one parameter of said bone Statistical Shape Model to correspond with said bone tissues so as to obtain a global dataset comprising the optimized bone Statistical Shape Model associated with the cartilage tissues from the segmented subject anatomical structure,
determine a global Statistical Shape Model of the subject anatomical structure based on said global dataset, said global Statistical Shape Model including a bone portion and a cartilage portion,
perform a rigid registration of the bone portion from said global Statistical Shape Model with said patient-specific 3D model and optimize at least one parameter of said global Statistical Shape Model to correspond with said patient-specific 3D model, and
generate said augmented patient-specific bone/cartilage model of the target anatomical structure based on the optimized global Statistical Shape Model registered with said patient-specific 3D model.

### Claim 2 (depends on 1)

The device according to claim 1, wherein said dataset comprises:
a first ensemble comprising 3D images acquired from a plurality of subjects, said 3D images comprising bone tissues from the subject anatomical structure, and
a second ensemble comprising 3D images acquired from a plurality of subjects, said 3D images comprising bone tissues and cartilage tissues from the subject anatomical structure.

### Claim 3 (depends on 1)

The device according to claim 1, wherein the at least one input is further configured to receive at least one 3D image acquired from at least one 3D image sensor during surgery, wherein said at least one 3D image represents at least one exposed portion of the target anatomical structure, and wherein the at least one processor is further configured to register and optimize at least one parameter of the augmented patient-specific bone/cartilage model associated to the cartilage with the at least one exposed portion of the target anatomical structure of the 3D image.

### Claim 4 (depends on 3)

The device according to claim 3, wherein registering and optimizing the at least one parameter of the augmented patient-specific bone/cartilage model is achieved by minimizing a cost function that takes into account the at least one parameter of the augmented patient-specific bone/cartilage model and localization parameters.

### Claim 5 (depends on 1)

The device according to claim 1, wherein determining said global Statistical Shape Model comprises:
defining a plurality of vectors being normal to at least one portion of a surface of said optimized bone Statistical Shape Model of the global dataset;
for each of the segmented cartilage of the global dataset, obtaining a first and a second intersection between each of said plurality of vectors and said segmented cartilage; and
determining said global Statistical Shape Model using said first and second intersections, obtained from the plurality of segmented cartilages of the global dataset, and the optimized bone Statistical Shape Model of the global dataset.

### Claim 6 (depends on 1)

The device according to claim 1, wherein the at least one input is further configured to receive at least one thickness measurement performed on a predetermined position on the cartilage, and wherein the processor is further configured to constrain the optimization of the at least one parameter of the global Statistical Shape Model associated to the cartilage based on the at least one measurement so as to generate an updated augmented patient-specific bone/cartilage model.

### Claim 7 (depends on 1)

The device according to claim 1, wherein the at least one input is further configured to receive at least one metadata, and wherein the processor is further configured to constrain the optimization of the at least one parameter of the global Statistical Shape Model based on the at least one metadata so as to generate an updated augmented patient-specific bone/cartilage model.

### Claim 8 (depends on 1)

The device according to claim 1, wherein said at least one processor is further configured to use said augmented patient-specific bone/cartilage model to guide an orthopedic surgery guidance system.

### Claim 9

A computer implemented method for obtaining an augmented patient-specific bone/cartilage model of a target anatomical structure of a patient, said target anatomical structure including at least one portion of a target bone and at least one portion of a target cartilage, said method comprising:
receiving:
a dataset comprising 3D images acquired on a plurality of subjects, each 3D image acquired on a subject comprising a subject anatomical structure corresponding to the target anatomical structure, wherein said 3D images comprise bone tissues of the subject anatomical structure and at least part of said 3D images comprise cartilage tissues of the subject anatomical structure, and
a previously generated patient-specific 3D model of at least one portion of said target bone of the patient;
for at least two 3D image of the dataset, segmenting the bone tissues of the subject anatomical structure,
determining a bone Statistical Shape Model based on said segmented bone tissues,
for at least two 3D image of the dataset comprising cartilage tissues of the subject anatomical structure, segmenting the subject anatomical structure and performing a rigid registration of said bone Statistical Shape Model with the segmented bone tissues of the subject anatomical structure and optimizing at least one parameter of said bone Statistical Shape Model to correspond with said bone tissues so as to obtain a global dataset comprising the optimized bone Statistical Shape Model associated with the cartilage tissues from the segmented subject anatomical structure, and
determining a global Statistical Shape Model of the at least one portion of target bone and target cartilage of the target anatomical structure based on said global dataset, said global Statistical Shape Model including a bone portion and a cartilage portion,
performing a rigid registration of the bone portion from said global Statistical Shape Model with said patient-specific 3D model and optimizing at least one parameter of said global Statistical Shape Model to correspond with said patient-specific 3D model, and
generating said augmented patient-specific bone/cartilage model of the target anatomical structure based on the optimized global Statistical Shape Model registered with said patient-specific 3D model.

### Claim 10 (depends on 9)

The computer implemented method according to claim 9, wherein said dataset comprises:
a first ensemble comprising 3D images acquired from a plurality of subjects, said 3D images comprising bone tissues from the subject anatomical structure, and
a second ensemble comprising 3D images acquired from a plurality of subjects, said 3D images comprising bone tissues and cartilage tissues from the subject anatomical structure.

### Claim 11 (depends on 9)

The computer implemented method according to claim 9, further comprising:
receiving at least one 3D image acquired from at least one 3D image sensor during surgery, wherein said at least one 3D image represents at least one exposed portion of the target anatomical structure,
registering and optimizing at least one parameter of the augmented patient-specific bone/cartilage model associated to the cartilage with the at least one exposed portion of the target anatomical structure of the 3D image.

### Claim 12 (depends on 11)

The computer implemented method according to claim 11, wherein registering and optimizing the at least one parameter of the augmented patient-specific bone/cartilage model is achieved by minimizing a cost function that takes into account the at least one parameter of the augmented patient-specific bone/cartilage model and localization parameters.

### Claim 13 (depends on 9)

The computer implemented method according to claim 9, wherein determining said global Statistical Shape Model comprises:
defining a plurality of vectors being normal to at least one portion of a surface of said optimized bone Statistical Shape Model of the global dataset;
for each of the segmented cartilage of the global dataset, obtaining a first and a second intersection between each of said plurality of vectors and said segmented cartilage; and
determining said global Statistical Shape Model using said first and second intersections, obtained from the plurality of segmented cartilages of the global dataset, and the optimized bone Statistical Shape Model of the global dataset.

### Claim 14 (depends on 9)

The computer implemented method according to claim 9, further comprising:
receiving at least one thickness measurement performed on a predetermined position on the cartilage,
constraining the optimization of the at least one parameter of the global Statistical Shape Model associated to the cartilage based on the at least one measurement so as to generate an updated augmented patient-specific bone/cartilage model.

### Claim 15 (depends on 9)

The computer implemented method according to claim 9, further comprising:
receiving at least one metadata,
constraining the optimization of the at least one parameter of the global Statistical Shape Model based on the at least one metadata so as to generate an updated augmented patient-specific bone/cartilage model.

### Claim 16 (depends on 9)

The computer implemented method according to claim 9, further comprising using said augmented patient-specific bone/cartilage model to guide an orthopedic surgery guidance system.

### Claim 17 (depends on 9)

A non-transitory program storage device, readable by a computer, tangibly embodying a program of instructions executable by the computer to perform the method according to claim 9.

### Claim 18 (depends on 9)

A non-transitory computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to claim 9.
