System and method for predicting future fractures

• US 9,460,506 B2
• Filed: 02/12/2015
• Issued: 10/04/2016
• Est. Priority Date: 09/16/2002
• Status: Expired due to Term

• Current Assignee: Imatx, Inc. (Conformis Incorporated)
• Original Assignee: Imatx, Inc. (Conformis Incorporated)
• Inventors: Arnaud, Claude D., Liew, Siau-Way, Steines, Daniel, Vargas-Voracek, Rene, Lang, Philipp
• Primary Examiner(s): Bitar, Nancy
• Application Number:
  US14/620,824
• Publication Number:
  US 20150178918A1
• Time in Patent Office: 600 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 2207/30008 Bone
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 2201/033 of skeletal patterns

Abstract

A method of predicting bone or articular disease in a subject includes determining one or more micro-structural parameters, one or more macroanatomical parameters or biomechanical parameters of a joint in the subject and combining at least two of the parameters to predict the risk of bone or articular disease.

Claims

1. A method for analyzing, in a computer system, bone condition in a target, comprising:

extracting electronic image data from an image of a bone of the target;

defining a first region of interest (ROI) from the image data;

defining a second region of interest (ROI) from the image data, wherein the first and second regions of interest (ROIs) overlap;

analyzing information in the first and second ROIs to derive first and second values for at least one bone structure parameter from the image data of the target;

creating a parameter map for the at least one bone structure parameter using the first and second values, and

predicting a fracture line of the bone with the parameter map.

2. The method of claim 1, wherein the parameter map is further derived using statistical comparisons of the derived bone structure parameter to a reference population.

3. The method of claim 1, further comprising identifying local abnormalities of bone structure from the parameter map.

4. The method of claim 1, further comprising:

tracing low values or high values on the parameter map; and

determining a potential fracture line from the low values or high values.

5. The method of claim 4, further comprising using watershed segmentation of the parameter maps to identify the potential fracture line.

6. The method of claim 1, further comprising analyzing the at least one bone structure parameter along the predicted fracture line to predict a fracture load at which a fracture will occur.

7. The method of claim 6, further comprising:

deriving a second bone parameter from the image of the target;

combining the bone structure parameter and the second bone parameter; and

calculating the fracture load using multivariate regression.

8. The method of claim 7, wherein the second parameter is a parameter related to bone mineral density, bone biomechanical characteristics, or bone structure.

9. The method of claim 1, further comprising:

receiving an image of a bone of a reference;

locating at least one region of interest on the image of the reference;

extracting image data from the image of the reference;

deriving at least one bone structure parameter from the image data of the reference;

measuring a fracture load of the bone of the reference; and

correlating the reference'"'"'s bone structure parameter to the reference'"'"'s fracture load.

10. The method of claim 9, further comprising predicting a fracture load of the target with the target'"'"'s bone structure parameter and the correlation of the reference'"'"'s bone structure parameter and the reference'"'"'s fracture load.

11. The method of claim 9, further comprising:

creating a fracture load reference database with data about at least one bone structure parameter and fracture load of a bone of at least two references; and

predicting a fracture load of the target with the target'"'"'s bone structure parameter and data from the fracture load reference database.

12. The method of claim 11, wherein the data is stored based on clinical risk factors of the references.

13. The method of claim 11, further comprising creating a fracture risk model correlated with the fracture load of the target by statistically analyzing at least one bone structure parameter of the at least two references.

14. The method of claim 13, wherein the fracture risk model is a multivariate linear model derived from multivariate linear regression of the at least one bone structure parameter and clinical risk factors of the at least two references.

15. The method of claim 14, further comprising deriving a second parameter from the image data of the target and the reference.

16. The method of claim 15, wherein the second parameter is a parameter related to bone mineral density, bone biomechanical characteristics, or bone structure.