METHOD AND SYSTEM FOR LESION SEGMENTATION

• US 20110158491A1
• Filed: 05/12/2009
• Published: 06/30/2011
• Est. Priority Date: 05/13/2008
• Status: Abandoned Application

• Current Assignee: AGFA Healthcare NV (Agfa-Gevaert N.V.), Toshiba Medical Visualization Systems Europe Ltd (Canon Inc.), Ibbt Vzw, Vrije Universiteit Brussel
• Original Assignee: AGFA Healthcare NV (Agfa-Gevaert N.V.), Toshiba Medical Visualization Systems Europe Ltd (Canon Inc.), Ibbt Vzw, Vrije Universiteit Brussel
• Inventors: Dewaele, Piet, Clerinx, Peter, Pole, Ian, Markova, Aneta, Demey, Johan, Deklerck, Rudi
• Application Number:
  US12/992,764
• Publication Number:
  US 20110158491A1
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/20036 Morphological image processing
• CPC Class Codes: G06T 2207/20096 Interactive definition of curve of interest
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 2207/30056 Liver; Hepatic
• CPC Class Codes: G06T 3/153 using elastic snapping
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/41 based on statistical description of texture

Abstract

A method and system for acquiring information on lesions in dynamic 3D medical images of a body region and/or organ, having the steps: applying a registration technique to align a plurality of volumetric image data of the body region and/or organ, yielding multi-phase registered volumetric image data of the body region and/or organ; applying a hierarchical segmentation on the multi-phase registered volumetric image data of the body region and/or organ, the segmentation yielding a plurality of clusters of n-dimensional voxel vectors of the multi-phase aligned volumetric image; determining from the plurality of clusters a cluster or set of clusters delineating the body and/or organ; identifying the connected region(s) of voxel vectors belonging to the body region and/or organ; refining/filling the connected region(s) corresponding to the body region and/or organ; reapplying the segmentation step to the refined/filled connected region(s) corresponding to the body region and/or organ, to obtain a more accurate segmentation; and acquiring information on the presence of lesions in cluster of set of clusters of said plurality of clusters.

Claims

1. Method for acquiring information on lesions in 3D medical images comprising a body part and/or organ, comprising the steps of

applying a registration technique to align a plurality of volumetric image data comprising the body part and/or organ, yielding multi-phase registered volumetric image data comprising the body part and/or organ,

applying a multi-dimensional segmentation on the multi-phase registered volumetric image data, said segmentation yielding a plurality of clusters of multi-dimensional voxel vectors of the multi-phase registered volumetric image data,

identifying the body part and/or organ as at least a part of a cluster or of a set of clusters of said plurality of clusters of multi-dimensional voxel vectors, and

acquiring information on lesions in the identified body part and/or organ.

2. Method as in claim 1, wherein the step of applying a segmentation further comprises a step of optimizing the segmentation into said plurality of clusters.

3. Method as in claim 1, wherein the step of applying a multi-dimensional segmentation is repeated for obtaining a refined segmentation.

4. Method as in claim 3, wherein morphological operations and/or active contours are applied on the result of the previous segmentation step before the segmentation is repeated.

5. Method as in claim 1, further comprising the step of selecting a region of interest for further analysis.

6. Method as in claim 5, wherein said selection is based on the acquired information on lesions in the body part and/or organ.

7. Method as in claim 5, further comprising the step of defining a viewport around said region of interest for visual assessment.

8. Method as in claim 7, further comprising the step of visualising said region of interest in said viewport at regular intervals or interactively.

9. Method as in claim 5, further comprising a step of selecting a predefined prototypical enhancement profile to compare said selected region with.

10. Method as in claim 5, wherein the further analysis comprises geometric analysis and/or radiometric analysis.

11. Method as in claim 10, wherein said geometric analysis comprises determining of said lesions the volume, diameter or perpendicular diameter.

12. Method as in claim 10, wherein said radiometric analysis comprises determining an intensity perfusion profile.

13. Method as in claim 5, wherein the selected region of interest comprises at least one spatially disconnected segment belonging to said organ or body part.

14. Method as in claim 5, further comprising the step of linking the selected region of interest to a corresponding region of interest in a previous study.

15. Method as in claim 1, wherein the step of applying a multi-dimensional segmentation is performed with a multi-dimensional watershed algorithm.

16. Method as in claim 1, wherein image data of at least two phases are combined.

17. Method as in claim 1, wherein the body part and/or organ is the liver.

18. A program, executable on a programmable device containing instructions, which when executed, perform the method as in claim 1.

19. System for acquiring information on lesions in 3D medical images of a body region and/or organ, comprising registration means arranged for multi-phase registration of volumetric image data comprising the body part and/or organ and a segmentation unit for performing a multi-dimensional segmentation of said registered volumetric image data.

20. System as in claim 19, further comprising visualisation means arranged for displaying the registered volumetric image data.