Device and method for determining a size of in-vivo objects

• US 9,412,054 B1
• Filed: 09/20/2011
• Issued: 08/09/2016
• Est. Priority Date: 09/20/2010
• Status: Active Grant

• Current Assignee: Given Imaging Limited (Medtronic Plc)
• Original Assignee: Given Imaging Limited (Medtronic Plc)
• Inventors: Krupnik, Hagai
• Primary Examiner(s): Bitar, Nancy
• Application Number:
  US13/237,117
• Time in Patent Office: 1,785 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: A61B 1/00009 of image signals during a use of endoscope
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• CPC Class Codes: G06V 10/754 involving a deformation of the sample pattern or of the reference pattern; Elastic matching
• CPC Class Codes: G06V 2201/032 of protuberances, polyps nodules, etc.

Abstract

A system and method for estimating a size of an object in an image is provided. A tissue model may be provided. Points in an image may be selected. A distance or estimated distance of the points from an imaging device may be determined based on the tissue model. A geometrical relation associating the point, distances and an object may be derived. A size parameter of the object may be calculated based on the geometrical relation. Other embodiments are described and claimed.

Claims

1. A method of estimating a distance of an object captured by an in-vivo imaging system, the method comprising:

obtaining, by said in-vivo imaging system, an image of said object;

selecting at least one pixel in said image, said at least one pixel associated with said object; and

calculating, based on a tissue model and data associated with said at least one pixel, a distance parameter related to a distance of said object from said in-vivo imaging system, the tissue model selected from the group consisting of;

a universal tissue model suitable for a plurality of patients;

a tissue model specific to a patient condition; and

a tissue model specific to a region of the GI tract, wherein said tissue model includes a representation of an interaction of tissue with light.

2. The method of claim 1, comprising:

selecting at least two pixels in said image, said at least two pixels associated with said object; and

calculating a size parameter related to said object by relating a sum related to said at least two pixels to an imaging parameter related to said in-vivo imaging system.

3. The method of claim 1, comprising:

selecting at least two pixels in said image, said at least two pixels associated with respective at least two locations in a space captured by said image;

determining, based on said tissue model and data associated with said at least two pixels, at least two distance parameters respectively related to a distance of said at least two locations from said in-vivo imaging system;

determining a geometrical relation of said at least two locations and said at least two distance parameters to said object; and

calculating, based at least in part on said geometrical relation, a size parameter of said object.

4. The method of claim 3, wherein said geometrical relation is determined based on a geometrical shape and wherein said geometrical shape is selected from the group consisting of:

a two dimensional geometric shape and a three dimensional geometric shape.

5. The method of claim 3, wherein said geometrical shape is selected from the group consisting of:

a triangle, a circle, a cone, a sphere and a cube.

6. The method of claim 3, comprising displaying said size parameter and said distance parameter on a display screen.

7. The method of claim 1, comprising calculating said distance parameter based on an illumination model.

8. The method of claim 1, wherein said tissue model provides a mapping of an intensity of light associated with said at least one pixel to at least one distance parameter, and wherein said mapping is a mapping of the intensity of light detected by only a red color channel to the at least one distance parameter.

9. The method of claim 1, comprising calibrating said tissue model to specific parameters of said in-vivo imaging system.

10. The method of claim 1, wherein said object is selected from the group consisting of:

a polyp, a lesion, a tumor, a cyst, a choristoma, a hamartoma, a tissue malformation and a nodule.

20. The method of claim 8, comprising modifying the mapping provided by the tissue model by an illumination model based on illumination used to capture the image.

23. The method of claim 1, wherein said tissue model provides a mapping of at least one of:

a color associated with said at least one pixel to at least one distance parameter, and an intensity of light associated with said at least one pixel to at least one distance parameter, and wherein each color is modeled separately.

11. A system for estimating a distance of an object imaged by an in-vivo imaging system, the system comprising:

a workstation comprising a memory and a processor, the memory to store an image captured by an in-vivo imaging system, and the processor to;

select at least one pixel in said image, said at least one pixel associated with said object; and

calculate, based on a tissue model stored in the memory and data associated with said at least one pixel, a distance parameter related to a distance of said object from said in-vivo imaging system, the tissue model selected from the group consisting of;

a universal tissue model suitable for a plurality of patients;

a tissue model specific to a patient condition; and

a tissue model specific to a region of the GI tract, wherein said tissue model includes a representation of an interaction of tissue with light.

12. The system of claim 11, wherein said processor is to:

select at least two pixels in said image, said at least two pixels associated with said object; and

calculate a size parameter related to said object by relating a sum related to said at least two pixels to an imaging parameter related to said in-vivo imaging system.

13. The system of claim 11, wherein said processor is to:

select at least two pixels in said image, said at least two pixels associated with respective at least two locations in a space captured by said image;

determine, based on said tissue model and data associated with said at least two pixels, at least two distance parameters respectively related to a distance of said at least two locations from said in-vivo imaging system;

determine a geometrical relation of said at least two locations and said at least two distance parameters to said object; and

calculate, based at least in part on said geometrical relation, a size parameter of said object.

14. The system of claim 13, wherein said processor is to determine said geometrical relation based on a geometrical shape and select said geometrical shape from the group consisting of:

a two dimensional geometric shape and a three dimensional geometric shape.

15. The system of claim 13, wherein said processor is to select said geometrical shape from the group consisting of:

a triangle, a circle, a cone, a sphere and a cube.

16. The system of claim 13, comprising a display screen, wherein said processor is to display said size parameter and said distance parameter on the display screen.

17. The system of claim 11, wherein said processor is to calculate said distance parameter based on an illumination model.

18. The system of claim 11, wherein said in-vivo imaging system is a swallowable capsule.

19. The system of claim 11, wherein said processor is to calibrate said tissue model to the specific parameters of said in-vivo imaging system.

21. A method of estimating a distance of an object captured by an in-vivo imaging system, the method comprising:

obtaining, by said in-vivo imaging system, an image of said object;

selecting at least one pixel in said image, said at least one pixel associated with said object; and

calculating, based on a tissue model and data associated with said at least one pixel, a distance parameter related to a distance of said object from said in-vivo imaging system, the tissue model selected from the group consisting of;

a universal tissue model suitable for a plurality of patients;

a tissue model specific to a patient condition; and

a tissue model specific to a region of the GI tract, wherein said tissue model includes a representation of an interaction of tissue with light, and wherein said tissue model provides a mapping of at least one of;

a color associated with said at least one pixel to at least one distance parameter, and an intensity of light associated with said at least one pixel to at least one distance parameter, and wherein the tissue model is adjustable based on an imaging environment.

22. The method of claim 21, wherein the imaging environment includes at least one of:

a condition of a patient, an imaging system used, the light used for imaging, and anatomical organ in a body.