Method of Selecting and Visualizing Findings Within Medical Images

• US 20100021031A1
• Filed: 10/06/2009
• Published: 01/28/2010
• Est. Priority Date: 04/08/2005
• Status: Active Grant

• Current Assignee: 361 Degrees Systems, Inc.
• Original Assignee: 361º Systems Incorporated
• Inventors: Carruthers, William Benjamin III, Brockway, John Philip
• Granted Patent: US 8,611,632 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: G06T 15/08 Volume rendering
• CPC Class Codes: G06T 19/00 Manipulating 3D models or images for computer graphics
• CPC Class Codes: G06T 2207/10096 Dynamic contrast-enhanced magnetic resonance imaging [DCE-MRI]
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/20092 Interactive image processing based on input by user
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 2207/20132 Image cropping
• CPC Class Codes: G06T 2207/30068 Mammography; Breast
• CPC Class Codes: G06T 2210/41 Medical
• CPC Class Codes: G06T 2219/028 Multiple view windows (top-side-front-sagittal-orthogonal)
• CPC Class Codes: G06T 7/0014 using an image reference approach
• CPC Class Codes: G06T 7/44 using image operators, e.g. filters, edge density metrics or local histograms
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]

Abstract

A method of processing regions of interest (ROI) obtained using computed-aided detection (CAD) along with reference image data to assist in evaluation of disease within an anatomical volume. After obtaining ROIs and reference image data, additional information related to each ROI is automatically computed. Subsets of ROIs are selected for use in visualization. ROIs are then presented to an observer in interactive, linked views, each view presenting optimally certain aspects of the ROIs and mapping ROI inclusion within the subsets to visual parameters.

Claims

1. A computer-implemented method for processing regions of interest (ROI) derived at least partially from image data corresponding to an anatomical volume, comprising:

accessing ROIs;

accessing reference image data corresponding to said anatomical volume;

generating additional information related to the ROIs;

selecting one or more subsets of ROIs; and

presenting said ROIs with the additional information and said reference images to an observer, the ROIs in the subsets being visually distinct.

2. The method of claim 1, further comprising the step of selecting a set of points, each point corresponding to a location within said anatomical volume.

3. The method of claim 1, further comprising the step of presenting said ROIs in a spatial view using volume rendering.

4. The method of claim 3, further comprising the step of presenting each of said ROIs in said spatial view using a lighting model and determining lighting parameters of the ROI based on information related to the ROI and the inclusion of the ROI within said subsets of ROIs.

5. The method of claim 3, further comprising the step of simultaneously presenting a plurality of volumes in said spatial view, each volume comprising a subset of the anatomical volume.

6. The method of claim 3, further comprising the step of navigating said spatial view using said subset of ROIs.

7. The method of claim 2, further comprising the step of modifying said set of points according to the focal points of ROIs within one or more of said subset of ROIs, each focal point being a representative location of part of an anatomical process.

8. The method of claim 2, further comprising the step of presenting said selected points in a composition view.

9. The method of claim 8, further comprising the step of presenting a plurality of signal-time curves in said composition view, each signal-time curve corresponding to a plurality of signal intensities over time at a location within a neighborhood of each of said selected points.

10. The method of claim 1, further comprising the step of presenting said ROIs in an enumerated view.

11. The method of claim 10, further comprising the step of presenting a plurality of ROI icons, each icon corresponding to a ROI.

12. The method of claim 11, wherein each ROI icon comprises a projection of image data corresponding to the ROI.

13. The method of claim 11, further comprising the step of ordering said ROI icons based on information related to each corresponding ROI.

14. The method of claim 11, further comprising the step of determining the size or color of each ROI icon based on information related to each corresponding ROI.

15. The method of claim 1, wherein said observer is a clinician screening for lesions within the anatomical volume.

16. The method of claim 1, further comprising the step of merging ROIs according to compositional and morphological similarity and proximity.

17. The method of claim 1, further comprising the step of computing a plurality of focal points related to each ROI, each focal point representing a substantially separate part of the same anatomical process.

18. The method of claim 17, wherein each of said focal points is a location substantially within the interior of a lesion with characteristics similar to those exhibited by a particular type of tissue or abnormality.

19. The method of claim 1, further comprising the step of selecting one or more subsets of ROIs by applying one or more filters to said ROIs.

20. The method of claim 19, wherein said filters comprise a plurality of ROI thresholds using confidence levels or category levels.