System and method for labeling and identifying lymph nodes in medical images

1. A method for assigning a lymph node in a medical image with an anatomical name, the method comprising:

identifying landmarks in a medical image;

receiving a location of a lymph node in the medical image;

automatically computing features in spatial relation to the location of the lymph node, wherein the features are computed using the landmarks; and

automatically assigning an anatomical name to the location of the lymph node by using a classifier that compares the computed features with classification rules,

wherein the method is performed using a processor.

2. The method of claim 1 , wherein the landmarks include centerlines of airways and a centerline of an aorta.

3. The method of claim 1 , wherein the computed features include positional vectors of the lymph node relative to locations on the landmarks.

4. The method of claim 1 , wherein the computed features include distance values of the lymph node relative to locations on the landmarks.

5. The method of claim 1 , wherein the classifier is a trained Support Vector Machine (SVM) that includes a model having a set of anatomical names associated with locations in the medical image defining the classification rules.

6. The method of claim 1 , further comprising:

acquiring the medical image by using a computed tomographic (CT), magnetic resonance (MR), or ultrasound imaging technique.

7. The method of claim 1 , wherein when assigning the anatomical name to the location of the lymph node biopsy-related information associated with the anatomical name is provided.

8. A system for assigning a lymph node in a medical image with an anatomical name, the system comprising:

a memory device for storing a program;

a processor in communication with the memory device, the processor operative with the program to:

identify landmarks in a medical image;

receive a location of a lymph node in the medical image;

automatically compute features in spatial relation to the location of the lymph node, wherein the features are computed using the landmarks; and

automatically assign an anatomical name to the location of the lymph node by using a classifier that compares the computed features with classification rules.

9. The system of claim 8 , wherein the landmarks include centerlines of airways and a centerline of an aorta.

10. The system of claim 8 , wherein the computed features include positional vectors of the lymph node relative to locations on the landmarks.

11. The system of claim 8 , wherein the computed features include distance values of the lymph node relative to locations on the landmarks.

12. The system of claim 8 , wherein the classifier is a trained Support Vector Machine (SVM) that includes a model having a set of anatomical names associated with locations in the medical image defining the classification rules.

13. The system of claim 8 , wherein the processor is further operative with the program to:

acquire the medical image by using a computed tomographic (CT), magnetic resonance (MR), or ultrasound imaging technique.

14. The system of claim 8 , wherein when assigning the anatomical name to the location of the lymph node, the processor is further operative with the program to:

provide biopsy-related information associated with the anatomical name.

15. A method for finding a region in a first medical image that contains a lymph node, the method comprising:

identifying landmarks in a first medical image;

receiving locations of lymph nodes within an area of the first medical image;

automatically computing features in spatial relation to the locations, wherein the features are computed using the landmarks;

automatically assigning the locations of the lymph nodes with anatomical names by using a classifier that compares the computed features with classification rules; and

providing a region associated with a given anatomical name,

wherein the method is performed using a processor.

16. The method of claim 15 , wherein when a location and an anatomical name is obtained from the first medical image or a second medical image, the method further comprises:

identifying landmarks in the second medical image

performing a registration between the landmarks of the first and second medical images; and

providing the location associated with the given anatomical name in the other of the first and second medical images.

17. The method of claim 15 , wherein the area is a portion of the first medical image determined by defining a region of interest in the first medical image.

18. A method for assigning a lymph node in a medical image with a label, the method comprising:

identifying landmarks in the medical image;

receiving a location of a lymph node in the medical image;

automatically computing features in spatial relation to the location of the lymph node, wherein the features are computed using the landmarks; and

automatically assigning a label to the location of the lymph node by using a classifier that compares the computed features with classification rules,

wherein the method is performed using a processor.

19. The method of claim 18 , wherein the computed features comprise intensity values of the location of the lymph node or a model of lymph node within the medical image.

20. A method for assigning a lymph node in a medical image with an anatomical name, the method comprising:

identifying landmarks in a medical image;

receiving a location of a lymph node in the medical image;

automatically computing features in spatial relation to the location of the lymph node, wherein the features are computed using the landmarks; and

automatically assigning an anatomical name to the location of the lymph node by using the computed features,

wherein the method is performed using a processor.