Knowledge based computer aided diagnosis

• US 7,203,354 B2
• Filed: 12/06/2000
• Issued: 04/10/2007
• Est. Priority Date: 12/07/1999
• Status: Expired due to Fees

• Current Assignee: Commonwealth Scientific & Industrial Research Organisation (Commonwealth Of Australia As Represented By Department Of Industry, Innovation, Climate Change, Science, Research And Tertiary Education)
• Original Assignee: Commonwealth Scientific & Industrial Research Organisation (Commonwealth Of Australia As Represented By Department Of Industry, Innovation, Climate Change, Science, Research And Tertiary Education)
• Inventors: Brown, Stephen Frank, Li, Rongxin, Wilson, Laurence Sydney
• Primary Examiner(s): Wu; Jingge
• Assistant Examiner(s): Tabatabai; Abolfazl
• Application Number:
  US10/149,163
• Publication Number:
  US 20030076987A1
• Time in Patent Office: 2,316 Days
• Field of Search: 382128-134, 382/164, 382/171, 382/173, 382/177, 382/179, 382/172, 600/36, 600/381, 600/410, 600/480, 600/482, 600/485, 600/490, 600/500, 600/505, 600/499, 604/22, 604/27, 604/28, 604/159, 606/159, 378/4, 378/15, 378/901
• US Class Current: 382/131
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/20044 Skeletonization; Medial axis transform
• CPC Class Codes: G06T 2207/20124 Active shape model [ASM]
• CPC Class Codes: G06T 2207/30101 Blood vessel; Artery; Vein; Vascular
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models
• CPC Class Codes: G06T 7/155 involving morphological operators
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes

Abstract

A method of extracting computer graphical objects including at least one vessel structure from a data volume of a portion of an anatomy, the method comprising the steps of: utilizing knowledge based image processing to locate centerlines and utilizing an active surface technique to extract the outer surface of said vessel structure; and storing co-ordinate information of said outer surface for subsequent display.

Claims

1. A method of extracting computer graphical objects including at least one vessel structure from a data volume of a portion of an anatomy, the method comprising the steps of:

utilising a three-dimensional medical image segmentation process to segment a three-dimensional medical image to determine an approximate axial location of said vessel structure;

utilising an active surface technique to extract a computer model of the outer surface of said vessel structure based on said approximate axial position as a seed for the active surface technique;

and digitally storing three-dimensional co-ordinate information of the computer model of said outer surface for subsequent display.

2. A method as claimed in claim 1 wherein said image segmentation process further includes the step of processing said data volume to produce an intermediate data structure and utilising an inferencing system on said intermediate data structure to determine the most suitable candidate for said at least one vessel structure.

3. A method as claimed in claim 1 wherein the inferencing process system is arranged in manner such that the most suitable candidate is identified based on model object frames, the model object frames each including a set of data entries specifying information about a model object.

4. A method as claimed in claim 1 wherein the information includes unary properties of the model object and/or relationship properties of the model object.

5. A method as claimed in claim 4, wherein the relationship properties include one or more of the group of membership property of a semantic network, and relative location data with respect to other model objects.

6. A method as claimed in claim 1, wherein the inferencing system is arranged in a manner such that is bases its determination on the law of fuzzy logic.

7. A method as claimed in claim 1, wherein the step of determining the outer surface of said vessel includes utilising manually designated points through which the resultant surface must go in the active surface technique.

8. A method as claimed in claim 1 wherein the active surface technique is based on data provided by a user from an initial analysis of the date volume.

9. A method as claimed in claim 8 wherein the data provided includes one or more of the group of at least two points located inside said at least one vessel structure, and at least two manually traced perpendicular vessel outlines.

10. A method as claimed in claim 1, wherein said at least one vessel structure includes a thrombus.

11. A method as claimed in claim 1, wherein said at least one vessel structure comprises one of a blood vessel, an airway, and other passageways of a human'"'"'s anatomy.

12. A method as claimed in claim 11 wherein said at least one vessel structure comprises one of the aorta, the superior mesenteric artery, a renal artery or an iliac artery.

13. A method as claimed in claim 1, wherein said data volume comprises a series of two-dimensional computer tomography scanned images of a human'"'"'s anatomy.

14. A method as claimed in claim 1, wherein said segmentation process utilises a series of sampled images at different sampling resolutions for identification of different vessel structures.

15. A method as claimed in claim 1, wherein said segmentation process includes applying a 3-dimensional line enhancement filter to said data volume.

16. A method as claimed in claim 1, wherein said segmentation process includes skeltonisation of a line enhanced filtering of an initial data volume.

17. A method as claimed in claim 1, wherein said active surface technique includes an adaptive thresholding processes.

18. An apparatus for extracting computer graphical objects including at least one vessel structure from a data volume of a portion of an anatomy, the apparatus comprising:

three-dimensional medical image segmentation processing means for applying a three-dimensional medical image segmentation process to determine an approximate axial location of said vessel structure;

active surface processing means for applying an active surface technique to extract a computer model of the outer surface of said vessel structure based on said approximate axial position as a seed for the active surface technique;

and a database for digitally storing co-ordinate information of the computer model of said outer surface for subsequent display.