System and Method For Labeling and Identifying Lymph Nodes In Medical Images

• US 20070237373A1
• Filed: 01/19/2007
• Published: 10/11/2007
• Est. Priority Date: 01/25/2006
• Status: Active Grant

• Current Assignee: Siemens Healthineers AG (Siemens AG)
• Original Assignee: Siemens Corporate Research Incorporated (Siemens AG)
• Inventors: Zhang, Li, Gundel, Lutz, Kiraly, Atilla, Novak, Carol
• Granted Patent: US 7,804,990 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• 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 2207/10132 Ultrasound image
• CPC Class Codes: G06T 2207/30101 Blood vessel; Artery; Vein; Vascular
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 2201/03 Recognition of patterns in medical or anatomical images

Abstract

A method for assigning a lymph node in a medical image with an anatomical name, the method including: identifying landmarks in a medical image; computing features relative to the landmarks given a location of a lymph node in the medical image; and assigning an anatomical name to the location of the lymph node by using a classifier that compares the computed features with classification rules.

Claims

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;

computing features relative to the landmarks given a location of a lymph node in the medical image; and

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

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;

compute features relative to the landmarks given a location of a lymph node in the medical image; and

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;

computing features relative to the landmarks for locations within an area of the first medical image and assigning the locations 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.

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 determining a label of a lymph node in a medical image, the method comprising:

identifying landmarks in a medical image; and

visualizing the landmarks along with a given object location for manual interpretation of a label of a lymph node in the medical image.

19. A method for assigning a structure in a medical image with a label, the method comprising:

identifying landmarks in the medical image;

computing features relative to the landmarks of the medical image given a location of a structure in the medical image; and

assigning a label to the location of the structure by using a classifier that compares the computed features with classification rules.

20. The method of claim 19, wherein the computed features are spatial and relative to the landmarks, intensity values of the anatomical locations or models of structures within the medical image.

21. The method of claim 19, wherein the structure is a lymph node.

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

identifying landmarks in a medical image;

computing features relative to the landmarks given a location of a lymph node in the medical image; and

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