Method and system for automatically generating a disease severity index

• US 7,929,737 B2
• Filed: 09/20/2006
• Issued: 04/19/2011
• Est. Priority Date: 09/29/2005
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Bembenek, Tamanna, Sirohey, Saad Ahmed, Avinash, Gopal B.
• Primary Examiner(s): Bhatnagar; Anand
• Assistant Examiner(s): WANG, CLAIRE X
• Application Number:
  US11/523,878
• Publication Number:
  US 20070081707A1
• Time in Patent Office: 1,672 Days
• Field of Search: 382/132, 382/128, 382/282, 382/209, 382/195, 600/407, 600/300
• US Class Current: 382/128
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/60 relating to pathologies
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Methods and systems for automatically generating a severity index for images of anatomical features of a patient are provided. In an exemplary embodiment, an image of an anatomical feature of a patient is compared with a normal, standardized image of the same anatomical feature. Based on this comparison, a deviation image for the anatomical feature is generated that represents the degree and manner the acquired image deviates from normal for that anatomical feature. The deviation image is automatically pattern matched against multiple images of known disease severity for the anatomical feature. Based on the automated pattern match, a known disease severity, such as in the form of a severity index, is provided as corresponding anatomical feature for the patient.

Claims

1. A method to create a normative categorical score of medical diagnostic images, the method comprising:

accessing an acquired image of an anatomical region of a patient, the acquired image depicting functional information regarding at least one tracer in the anatomical region at the time of the imaging;

generating, on a computer, a deviation image visually depicting the deviation of the acquired image from normative standardized anatomical image data based on one or more subject specific factors, wherein the deviation image represents the degree and manner in which the acquired image deviates from the corresponding normative standardized anatomical image data for the anatomical feature; and

comparing, on a computer, the generated deviation image with an existing database of disease severity images, each database image visually depicting a respective deviation from normality for the anatomical region and each corresponding to a respective severity index value.

2. The method of claim 1, comprising generating a combined severity score from a plurality of severity index values in reference to a rules-based process.

3. The method of claim 2, wherein generating the combined severity score comprises summing the plurality of severity indices in reference to a rules-based process.

4. The method of claim 1, wherein the one or more subject-specific factors comprise at least one of an age of the subject or a sex of the subject.

5. The method of claim 1, comprising acquiring the acquired image positron emission tomography, computed tomography, single photon emission computed tomography, ultrasound or optical imaging.

6. The method of claim 1, wherein generating the deviation image comprises comparing the acquired image of the anatomical region with normative standardized image data for the respective anatomical region and taking into account at least one tracer in the anatomical region at the time of the imaging.

7. The method of claim 1, wherein comparing comprises selecting one or more features within the deviation image for comparison to a set of disease severity deviation images categorized into a degree of severity for the anatomical region.

8. The method of claim 1, wherein comparing comprises classifying one or more features within the deviation image based on a comparison to a set of disease severity deviation images categorized into a degree of severity for the anatomical region.

20. The method of claim 1, wherein the deviation image comprises a Z-score image visually depicting the statistical degree of deviation of the acquired image of the anatomical region from a normal image of the anatomical region and wherein the existing database of disease severity images comprises a plurality of Z-score images each visually depicting the statistical degree of deviation of each respective database image from normality.

21. The method of claim 1, wherein the deviation image comprises a difference image visually depicting the mathematical difference between the acquired image of the anatomical region from a normal image of the anatomical region and wherein the existing database of disease severity images comprises a plurality of difference images each visually depicting the mathematical difference between each respective database image and a non-diseased image of the anatomical region.

9. One or more non-transitory computer readable media, comprising code executable to perform the acts of:

accessing an acquired image of an anatomical region of a patient, the acquired image depicting functional information regarding at least one tracer in the anatomical region at the time of the imaging

generating a deviation image visually depicting the deviation of the acquired image from normative standardized anatomical image data based on one or more subject specific factors, wherein the deviation image represents the degree and manner in which the acquired image deviates from the corresponding normative standardized anatomical image data for the anatomical feature; and

comparing the generated deviation image with an existing database of disease severity images, each database image visually depicting a respective deviation from normality for the anatomical region and each corresponding to a respective severity index value.

10. The one or more non-transitory computer readable media of claim 9, further comprising code executable to perform the acts of:

generating a combined severity score from a plurality of severity index values in reference to a rules-based process.

11. The one or more non-transitory computer readable media of claim 10, wherein the code executable to generate the combined severity score sums the plurality of severity indices in reference to a rules-based process.

12. The one or more non-transitory computer readable media of claim 9, wherein the one or more subject-specific factors comprise at least one of an age of the subject or a sex of the subject.

13. The one or more non-transitory computer readable media of claim 9, further comprising code executable to perform the acts of:

acquiring the acquired image of the anatomical region using one of magnetic resonance imaging, positron emission tomography, computed tomography, single photon emission computed tomography, ultrasound or optical imaging.

14. The one or more non-transitory computer readable media of claim 9, wherein the code executable to generate the deviation image compares the acquired image of the anatomical region with normative standardized image data for the respective anatomical region and takes into account at least one tracer in the anatomical region at the time of the imaging.

15. The one or more non-transitory computer readable media of claim 9, wherein the at least one specific anatomical region comprises at least a portion of a brain.

16. The one or more non-transitory computer readable media of claim 9, wherein the at least one tracer comprises a radioactive tracer.

17. The one or more non-transitory computer readable media of claim 9, wherein the code executable to compare selects one or more features within the deviation image for comparison to a set of disease severity deviation images categorized into a degree of severity for the anatomical region.

18. The one or more non-transitory computer readable media of claim 9, wherein the code executable to compare classifies one or more features within the deviation image based on a comparison to a set of disease severity deviation images categorized into a degree of severity for the anatomical region.

19. A method for automatically generating a severity score, comprising:

generating, on a computer, a severity index for each of a plurality of patient images by matching a respective deviation image generated for each patient image with a respective reference image of a set of reference deviation images, wherein each generated deviation image represents a degree and manner in which the respective patient image deviates from a corresponding anatomical image depicting a corresponding anatomical region in a non-diseased state; and

deriving, on a computer, a severity score based on the plurality of severity indexes.