System and method of predicting future fractures

• US 8,600,124 B2
• Filed: 09/16/2005
• Issued: 12/03/2013
• Est. Priority Date: 09/16/2004
• Status: Active Grant

• Current Assignee: Imatx, Inc. (Conformis Incorporated)
• Original Assignee: Imatx, Inc. (Conformis Incorporated)
• Inventors: Arnaud, Claude Donald, Lang, Philipp, Liew, Siau-Way, Steines, Daniel, Vargas-Voracek, Rene
• Primary Examiner(s): Bitar, Nancy
• Application Number:
  US11/228,126
• Publication Number:
  US 20060062442A1
• Time in Patent Office: 3,000 Days
• Field of Search: 382/100, 382/128, 382/132, 382/156, 600/300, 600/407, 600/436, 600/408, 600/425, 378/54, 378/56
• US Class Current: 382/128
• CPC Class Codes: A61B 2576/02 specially adapted for a particular organ or body part
• CPC Class Codes: A61B 5/4509 Bone density determination
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 6/505 for diagnosis of bone
• CPC Class Codes: A61B 6/52 Devices using data or image processing specially adapted for radiation diagnosis
• CPC Class Codes: A61B 6/583 using calibration phantoms
• CPC Class Codes: A61B 8/52 Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves image processing per se G06T
• CPC Class Codes: G01R 33/54 Signal processing systems, e.g. using pulse sequences ; Generation or control of pulse sequences; Operator console
• 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: G06T 7/41 based on statistical description of texture
• CPC Class Codes: G06T 7/62 of area, perimeter, diameter or volume
• CPC Class Codes: G06T 7/66 of image moments or centre of gravity

Abstract

Methods of predicting fracture risk of a patient include: obtaining an image of a bone of the patient; determining one or more bone structure parameters; predicting a fracture line with the bone structure parameter; predicting a fracture load at which a fracture will happen; estimating body habitus of the patient; calculating a peak impact force on the bone when the patient falls; and predicting a fracture risk by calculating the ratio between the peak impact force and the fracture load. Inventive methods also includes determining the effect of a candidate agent on any subject'"'"'s risk of fracture.

Claims

1. A method for predicting fracture risk using an image of a part of a skeleton of a target in a computer system, the method comprising:

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

extracting image data from the image of the target;

performing a sliding window analysis to generate at least one bone structure parameter corresponding to at least a portion of the target;

generating a parameter map from the at least one bone structure parameter to predict a fracture line;

analyzing the at least one bone structure parameter along the predicted fracture line to predict a fracture load at which a fracture will occur;

estimating a body habitus of the target; and

calculating a peak impact force on the part of the skeleton of the target when the target falls.

2. The method of claim 1, further comprising:

comparing the at least one bone structure parameter to a reference parameter to identify a likely location of a fracture.

3. The method of claim 2, further comprising predicting the 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.

4. The method of claim 2, further comprising:

generating bone parameter data corresponding to a bone parameter map of at least a portion of the target.

5. The method of claim 4, wherein the data is stored based on clinical risk factors.

6. The method of claim 4, further comprising storing the bone parameter data in a database of bone parameter data.

7. The method of claim 1, wherein the at least one bone structure parameter is at least one parameter from the group of area ratio and trabecular perimeter.

8. The method of claim 7, wherein the at least one bone structure parameter further comprises a first bone parameter being area ratio and a second bone parameter being trabecular perimeter.

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

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

11. 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.

12. The method of claim 1, further comprising using watershed segmentation of parameter maps to identify the fracture line.

13. The method of claim 1, wherein the at least one bone structure parameter includes at least first and second bone structure parameters;

and further comprising calculating a fracture load from the first and second bone structure parameters.

14. The method according to claim 1, wherein the body habitus is related to a soft tissue thickness of the target.

15. The method according to claim 1, wherein the body habitus is related to a standing height of the target.

16. The method according to claim 1, wherein the body habitus is related to a body mass of the target.

17. The method of claim 1, further comprising predicting a fracture risk by calculating the ratio between the peak impact force and the fracture load.

18. The method of claim 1, wherein the bone structure parameter is a bone micro-structure parameter.

19. The method of claim 1, wherein the bone structure parameter is a bone macro-structure parameter.

20. The method of claim 1, wherein the at least one region of interest is located automatically.

21. The method of claim 1, wherein the image is selected from the group consisting of x-ray images, x-ray tomosynthesis, ultrasound, computed tomography, magnetic resonance imaging, optical coherence tomography, single photon emission tomography, and positron emission tomography.

22. The method of claim 1, wherein the image is a 2D image.

23. The method of claim 1, wherein the image is a 3D image.

24. The method of claim 1, wherein the image is a 4D image.

25. The method of claim 1, further comprising converting the image to an image of more dimensions.

26. The method of claim 1, further comprising obtaining an image of the target.

27. The method of claim 1, further comprising repeating the step for locating at least one region of interest.

28. The method of claim 1, further comprising repeating the step for extracting image data from the image.

29. The method of claim 1, further comprising:

transmitting the image to a second location;

converting the image to a pattern of normal or diseased using the bone structure parameter; and

analyzing the converted image.

30. The method of claim 29, further comprising transmitting the pattern to a third location for analyzing.

31. A system for analyzing musculoskeletal-related data of a target using a computer, comprising:

means for receiving an image of a part of a skeleton of the target;

means for deriving at least one bone structure parameter from the image;

means for performing a sliding window analysis;

means for calculating a possibility of a fracture of a target using a bone structure parameter of the target;

means for generating a parameter map from the target'"'"'s bone structure parameter for presenting a possible fracture line;

means for analyzing the target'"'"'s bone structure parameter along the possible fracture line to calculate a fracture load at which a fracture will occur;

means for estimating a body habitus of the target; and

means for calculating a peak impact force on the skeleton part when the target falls.

32. The system according to claim 31, further comprising:

means for obtaining a fracture load of a skeleton part of a reference; and

means for correlating a bone structure parameter of the reference to the fracture load of the reference.

33. The system according to claim 32, further comprising means for receiving the target'"'"'s bone structure parameter and the correlation of the reference'"'"'s bone structure parameter and the reference'"'"'s fracture load, and calculating the fracture load of the target.

34. The system according to claim 33 further comprising means for storing the correlation of the reference'"'"'s bone structure parameter and the reference'"'"'s fracture load.

35. The system according to claim 34, wherein the means for storing also receives clinical risk factors of the reference.

36. The system of claim 31, wherein the body habitus is related to a soft tissue thickness of the target.

37. The system of claim 31, wherein the body habitus is related to a standing height of the target.

38. The system of claim 31, wherein the body habitus is related to a body mass of the target.

39. The system of claim 31, further comprising means for calculating the ratio between the peak impact force and the fracture load of the target.

40. The system of claim 31, wherein the bone structure parameter is a bone microstructure parameter.

41. The system of claim 31, wherein the bone structure parameter is a bone macro-structure parameter.