Granted Patent B2

US 12,733,978 · App. 17/413,414 · Granted Sep 15, 2026

Inventors: Jean Chaoui (Locmaria Plouzané, FR); Charlotte Le Saint (Brest, FR); Maximilien Mayya (Brest, FR); Manuel Jean-Marie Urvoy (Brest, FR)

Assignee: Howmedica Osteonics Corp.

A61B34/10A61B5/1121A61B5/4519A61B5/4528A61B5/4872A61B6/032A61B34/20A61B34/25A61B90/36A61F2/46G06F3/011G06N3/045G06T7/0012G06T7/30G16H20/40G16H30/20A61B6/505A61B2034/102A61B2034/105A61B2034/108A61B2034/2068A61B2034/252A61B2090/365A61F2002/4018A61F2002/4633G06T2200/24G06T2207/10081G06T2207/20084G06T2207/30008

Abstract

Claims (95)

1 . A system for modeling a soft-tissue structure of a patient, the system comprising:

a memory configured to store patient-specific computed tomography (CT) image data generated from the patient; and

processing circuitry configured to:

receive the patient-specific CT image data from the memory;

determine, based on intensities of the patient-specific CT image data, a patient-specific shape representative of the soft-tissue structure, wherein, to determine the patient-specific shape, the processing circuitry is configured to:

receive an initial shape;

determine a plurality of surface points on the initial shape;

register the initial shape to the patient-specific CT image data;

identify one or more contours in the patient-specific CT image data representative of at least a partial boundary of the soft-tissue structure, wherein to identify the one or more contours, the processing circuitry is configured to:

generate a Hessian feature image from the patient-specific CT image data, wherein the Hessian feature image indicates regions of the patient-specific CT image data comprising higher intensity gradients between two or more voxels of the patient-specific CT image data,

identify, based on the Hessian feature image, one or more separation zones between the soft-tissue structure and an adjacent soft-tissue structure; and

determine at least a portion of the one or more contours as passing through the one or more separation zones;

iteratively move the plurality of surface points towards respective locations of the one or more contours to change the initial shape to a patient-specific shape; and

output the patient-specific shape for display overlaid on the patient-specific CT image data.

2 . The system of claim 1 , wherein the processing circuitry is configured to iteratively move the plurality of surface points towards respective locations of the one or more contours by, for each iteration of moving the plurality of surface points:

for each respective surface point of the plurality of surface points:

extending, from the respective surface point, a vector from the respective surface point and normal to a surface comprising the respective surface point;

determining, for the vector from the respective surface point, a respective point in the patient-specific CT image data exceeding a threshold intensity value;

determining a plurality of potential locations within an envelope of the respective point and exceeding the threshold intensity value in the patient-specific CT image data, wherein the plurality of potential locations at least partially define a surface of the one or more contours;

determining normal vectors from the plurality of potential locations that are normal to the surface;

determining a plurality of angles, each angle of the plurality of angles being between one of the normal vectors from the potential locations and the vector from the respective surface point;

selecting one potential location of the plurality of potential locations having a smallest angle of the plurality of angles; and

moving the respective surface point at least partially towards the selected one potential location, wherein moving the respective surface point modifies the initial shape towards the patient-specific shape.

3 . The system of claim 2 , wherein the processing circuitry is configured to move the respective surface point at least half of a distance between the respective surface point and the selected one potential location.

4 . The system of claim 2 , wherein the processing circuitry is configured to iteratively move the plurality of surface points towards the respective locations of the one or more contours by:

moving, in a first iteration from the initial shape, each surface point of the plurality of surface points a first respective distance within a first tolerance of a first modification distance to generate a second shape, the first tolerance selected to maintain smoothness of the second shape; and

moving, in a second iteration following the first iteration, each surface point of the plurality of surface points a second respective distance within a second tolerance of a second modification distance to generate a third shape from the second shape, wherein the second tolerance is larger than the first tolerance.

5 . The system of claim 1 , wherein the processing circuitry is configured to register the initial shape by registering a plurality of locations on the initial shape to corresponding insertion locations on one or more bones identified in the patient-specific CT image data.

6 . The system of claim 1 , wherein the initial shape comprises an anatomical shape representative of the soft-tissue structure of a plurality of subjects different than the patient.

7 . The system of claim 6 , wherein the anatomical shape comprises a statistical mean shape generated from the soft-tissue structure imaged for the plurality of subjects.

8 . The system of claim 1 , wherein the processing circuitry is configured to:

determine a fat volume ratio for the patient-specific shape;

determine an atrophy ratio for the patient-specific shape;

determine, based on the fat volume ratio and the atrophy ratio of the patient-specific shape of the soft-tissue structure of the patient, a range of motion of a humerus of the patient; and

determine, based on the range of motion of the humerus, a type of shoulder treatment for the patient, wherein the type of shoulder treatment is selected from one of an anatomical shoulder replacement surgery or a reverse shoulder replacement surgery.

9 . The system of claim 8 , wherein the processing circuitry is configured to determine the range of motion of the humerus by determining, based on fat volume ratios and atrophy ratios for each muscle of a rotator cuff of the patient, the range of motion of the humerus of the patient.

10 . The system of claim 1 , wherein the processing circuitry is configured to:

apply a mask to the patient-specific shape;

apply a threshold to voxels of the patient-specific CT image data that are under the mask;

determine a fat volume based on the voxels of the patient-specific CT image data that are under the threshold;

determine a fatty infiltration value based on the fat volume and a volume of the patient-specific shape; and

output a fatty infiltration value for the soft-tissue structure.

11 . The system of claim 1 , wherein the processing circuitry is configured to:

determine bone to muscle dimensions for the soft-tissue structure;

obtain a statistical mean shape (SMS) for the soft-tissue structure;

deform the SMS by satisfying a threshold of an algorithm to fit a deformed version of the SMS to the bone to muscle dimensions of the soft-tissue structure;

determine an atrophy ratio for the soft-tissue structure by dividing a volume of the SMS by a volume of the soft-tissue structure; and

output the atrophy ratio for the soft-tissue structure.

12 . A method for modeling a soft-tissue structure of a patient, the method comprising:

storing, by a memory, patient-specific computed tomography (CT) image data generated from the patient;

receiving, by processing circuitry, the patient-specific CT image data from the memory;

determining, by the processing circuitry and based on intensities of the patient-specific CT image data, a patient-specific shape representative of the soft-tissue structure; wherein determining the patient-specific shape comprises:

receiving an initial shape;

determining a plurality of surface points on the initial shape;

registering the initial shape to the patient-specific CT image data;

identifying one or more contours in the patient-specific CT image data representative of at least a partial boundary of the soft-tissue structure, wherein identifying the one or more contours comprises:

generating a Hessian feature image from the patient-specific CT image data, wherein the Hessian feature image indicates regions of the patient-specific CT image data comprising higher intensity gradients between two or more voxels of the patient-specific CT image data,

identifying, based on the Hessian feature image, one or more separation zones between the soft-tissue structure and an adjacent soft-tissue structure; and

determining at least a portion of the one or more contours as passing through the one or more separation zones;

iteratively moving the plurality of surface points towards respective locations of the one or more contours to change the initial shape to a patient-specific shape; and

outputting, by the processing circuitry, the patient-specific shape for display overlaid on the patient-specific CT image data.

13 . The method of claim 12 , wherein iteratively moving the plurality of surface points towards respective locations of the one or more contours comprises, for each iteration of moving the plurality of surface points:

for each respective surface point of the plurality of surface points:

extending, from the respective surface point, a vector from the respective surface point and normal to a surface comprising the respective surface point;

determining, for the vector from the respective surface point, a respective point in the patient-specific CT image data exceeding a threshold intensity value;

determining a plurality of potential locations within an envelope of the respective point and exceeding the threshold intensity value in the patient-specific CT image data, wherein the plurality of potential locations at least partially define a surface of the one or more contours;

determining normal vectors from the plurality of potential locations that are normal to the surface;

determining a plurality of angles, each angle of the plurality of angles being between one of the normal vectors from the potential locations and the vector from the respective surface point;

selecting one potential location of the plurality of potential locations comprising having a smallest angle of the plurality of angles; and

moving the respective surface point at least partially towards the selected one potential location, wherein moving the respective surface point modifies the initial shape towards the patient-specific shape.

14 . The method of claim 13 , further comprising moving the respective surface point at least half of a distance between the respective surface point and the selected one potential location.

15 . The method of claim 13 , wherein iteratively moving the plurality of surface points towards the respective locations of the one or more contours comprises:

moving, in a first iteration from the initial shape, each surface point of the plurality of surface points a first respective distance within a first tolerance of a first modification distance to generate a second shape, the first tolerance selected to maintain smoothness of the second shape; and

moving, in a second iteration following the first iteration, each surface point of the plurality of surface points a second respective distance within a second tolerance of a second modification distance to generate a third shape from the second shape, wherein the second tolerance is larger than the first tolerance.

16 . The method of claim 12 , wherein registering the initial shape comprises registering a plurality of locations on the initial shape to corresponding insertion locations on one or more bones identified in the patient-specific CT image data.

17 . The method of claim 12 , wherein the initial shape comprises an anatomical shape representative of the soft-tissue structure of a plurality of subjects different than the patient.

18 . The method of claim 17 , wherein the anatomical shape comprises a statistical mean shape generated from the soft-tissue structure imaged for the plurality of subjects.

19 . The method of claim 12 , further comprising:

determining a fat volume ratio for the patient-specific shape;

determining an atrophy ratio for the patient-specific shape;

determining, based on the fat volume ratio and the atrophy ratio of the patient-specific shape of the soft-tissue structure of the patient, a range of motion of a humerus of the patient; and

determining, based on the range of motion of the humerus, a type of shoulder treatment for the patient, wherein the type of shoulder treatment is selected from one of an anatomical shoulder replacement surgery or a reverse shoulder replacement surgery.

20 . The method of claim 19 , wherein determining the range of motion of the humerus comprises determining, based on fat volume ratios and atrophy ratios for each muscle of a rotator cuff of the patient, the range of motion of the humerus of the patient.

21 . The method of claim 12 , further comprising:

applying a mask to the patient-specific shape;

applying a threshold to voxels of the patient-specific CT image that are under the mask;

determining a fat volume based on the voxels of the patient-specific CT image that are under the threshold;

determining a fatty infiltration value based on the fat volume and a volume of the patient-specific shape; and

outputting a fat volume ratio for the soft-tissue structure.

22 . The method of claim 12 , further comprising:

determining bone to muscle dimensions for the soft-tissue structure;

obtaining a statistical mean shape (SMS) for the soft-tissue structure;

deforming the SMS by satisfying a threshold of an algorithm to fit a deformed version of the SMS to the bone to muscle dimensions of the soft-tissue structure;

determining an atrophy ratio for the soft-tissue structure by dividing a volume of the SMS by a volume of the soft-tissue structure; and

outputting the atrophy ratio for the soft-tissue structure.

Assignments (3)

Continuity (7)

References Cited (361)