Claims
- 1. A computer-implemented method for characterizing a shape in medical images, comprising:
a) obtaining a candidate shape; b) computing a visible surface adjacent to said candidate shape, wherein said visible surface comprises one or more portions of said medical image that are visible by said candidate shape; and c) computing one or more parameters of said visible surface.
- 2. The method as set forth in claim 1, further comprising, depending on values of said one or more parameters, determining whether said candidate shape corresponds to a shape of interest.
- 3. The method as set forth in claim 2, wherein said shape of interest comprises pre-malignant or malignant tissue.
- 4. The method as set forth in claim 2, wherein said candidate of interest is a nodule, a polyp or a lesion.
- 5. The method as set forth in claim 1, wherein said one or more parameters represent axes of an ellipsoid that fit said visible surface.
- 6. The method as set forth in claim 1, wherein step (c) comprises the step of performing a principle components analysis of said visible surface.
- 7. The method as set forth in claim 1, further comprising the step of computing one or more features of said candidate shape.
- 8. The method as set forth in claim 1, further comprising the step of classifying said candidate shape.
- 9. The method as set forth in claim 1, wherein said candidate shape is obtained manually by a user.
- 10. The method as set forth in claim 1, wherein said candidate shape is obtained by a computer-implemented location and detection method.
- 11. A computer-implemented method for characterizing a lung nodule in medical images, comprising:
a) obtaining a candidate lung nodule; b) computing a visible surface adjacent to said candidate lung nodule, wherein said visible surface comprises one or more portions of said medical image that are visible by said candidate lung nodule; c) computing one or more parameters of said visible surface; and d) depending on values of said one or more parameters, determining whether said candidate lung nodule is a true lung nodule.
- 12. The method as set forth in claim 11, wherein said one or more parameters represent axes of an ellipsoid that fit said visible surface.
- 13. The method as set forth in claim 11, wherein step (c) comprises the step of performing a principle components analysis of said visible surface.
- 14. The method as set forth in claim 11, further comprising the step of computing one or more features of said candidate lung nodule.
- 15. The method as set forth in claim 11, further comprising the step of classifying said candidate lung nodule.
- 16. The method as set forth in claim 11, wherein said candidate lung nodule is obtained manually by a user.
- 17. The method as set forth in claim 11, wherein said candidate lung nodule is obtained by a computer-implemented location and detection method.
- 18. A computer-implemented method for characterizing a colonic polyp in medical images, comprising:
a) obtaining a candidate colonic polyp; b) computing a visible surface adjacent to said candidate colonic polyp, wherein said visible surface comprises one or more portions of said medical image that are visible by said candidate colonic polyp; c) computing one or more parameters of said visible surface; and d) depending on values of said one or more parameters, determining whether said candidate colonic polyp is a true colonic polyp.
- 19. The method as set forth in claim 18, wherein said one or more parameters represent axes of an ellipsoid that fit said visible surface.
- 20. The method as set forth in claim 18, wherein step (c) comprises the step of performing a principle components analysis of said visible surface.
- 21. The method as set forth in claim 18, further comprising the step of computing one or more features of said candidate colonic polyp.
- 22. The method as set forth in claim 18, further comprising the step of classifying said candidate colonic polyp.
- 23. The method as set forth in claim 18, wherein said candidate colonic polyp is obtained manually by a user.
- 24. The method as set forth in claim 18, wherein said candidate colonic polyp is obtained by a computer-implemented location and detection method.
CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] The present application is cross-referenced to and claims priority from U.S. Provisional Application No. 60/288,674 filed May 4, 2001 and No. 60/288,621 filed May 4, 2001, which are both hereby incorporated by reference. This application is also cross-referenced to co-pending U.S. Patent Application entitled “Method for Detecting Shapes in Medical Images” filed with the USPTO on May 3, 2002, which is hereby incorporated by reference.
Provisional Applications (2)
|
Number |
Date |
Country |
|
60288674 |
May 2001 |
US |
|
60288621 |
May 2001 |
US |