System and method for automatic navigation of a capsule based on image stream captured in-vivo

• US 10,102,334 B2
• Filed: 12/29/2011
• Issued: 10/16/2018
• Est. Priority Date: 12/30/2010
• Status: Active Grant

• Current Assignee: Given Imaging Limited (Medtronic Plc)
• Original Assignee: Given Imaging Limited (Medtronic Plc)
• Inventors: Rabinovitz, Elisha, Braun, Ori, Ben Zriham, Yaniv, Gerber, Jeremy Pinchas, Iddan, Gavriel J., Horn, Eli
• Primary Examiner(s): Vanni, G Steven
• Application Number:
  US13/976,891
• Publication Number:
  US 20130304446A1
• Time in Patent Office: 2,483 Days
• Field of Search: None
• CPC Class Codes: A61B 1/00097 Sensors
• CPC Class Codes: A61B 1/00158 using magnetic field
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10068 Endoscopic image
• CPC Class Codes: G06T 2207/30028 Colon; Small intestine
• CPC Class Codes: G06T 2207/30092 Stomach; Gastric
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G16B 5/00 ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks

Abstract

A system and method for automatically navigating an in vivo imaging capsule in a body lumen. The system comprises an imaging capsule including an imager, optional pressure sensor for producing data of forces acting on the imaging capsule in vivo, and a transmitter to transmit image, positioning and pressure data from the capsule to an external unit. A positioning system for providing current position data of the capsule in vivo may be included in the capsule and/or external to it. External magnets may generate a magnetic field to scan a body lumen by causing a predetermined motion pattern of the imaging capsule within a region proximate to its current position, and generate a driving force to propel the imaging capsule according to a calculated target direction vector. A processor may calculate a target direction vector for propelling the imaging capsule based, on unique patterns identifiable in one or more images.

Claims

1. A method for automatic generation of a model of an organ, the organ imaged by an in vivo capsule comprising an imager, the method comprising:

capturing, via the in vivo capsule, light-based images in-vivo;

generating, by a computer data processor, an initial organ model being a three-dimensional hollow geometric shell representing an inner surface of an organ within a body, the initial organ model based on a predetermined estimated structure of the imaged organ;

receiving, by the computer data processor, a user indication of an image captured while the in vivo capsule images a first point of interest to a user identified in the imaged organ;

determining a position and orientation of the in vivo capsule upon capturing the indicated image of the first point of interest;

based on the position and orientation of the in vivo capsule, updating, by the computer data processor, the initial model to a customized model, such that a location in the customized model corresponding to the position of the point of interest in vivo reflects the organ size and organ location within the body; and

based on the customized model and images captured by the in vivo capsule, constructing, by the computer data processor, a three-dimensional visualization of the organ including the images for display to the user.

2. The method of claim 1, wherein determining a position and orientation of the in vivo capsule comprises determining the position of the in vivo capsule relative to fiduciary elements positioned in a navigation system of the in vivo capsule.

3. The method of claim 1, comprising calculating the position of the in vivo capsule in relation to tissue walls of the imaged organ.

4. The method of claim 1, comprising estimating a projection of an image of the organ on the customized model.

5. The method of claim 1, comprising:

navigating the in vivo capsule to a second point of interest in the imaged organ, receiving an indication of an image captured while the in vivo capsule images the second point of interest,

determining a position and orientation of the in vivo capsule upon capturing the indicated image of the second point of interest;

updating the customized model, by setting a second location in the customized model, said second location corresponding to the position of the second point of interest in vivo.

6. The method of claim 5, comprising calculating, based on the customized organ model, a target position for navigating the in vivo capsule, the target position corresponding to the second point of interest.

7. The method of claim 1, comprising:

automatically navigating the in vivo capsule by selecting a predetermined motion pattern;

receiving an indication that the in vivo capsule touched the organ walls;

determining the location of the in vivo capsule when the indication that the in vivo capsule touched the organ walls is received; and

updating the initial model based on the determined location.

8. The method of claim 1, comprising changing a progress direction of the in vivo capsule upon receiving an indication that the in vivo capsule touched the organ walls.

9. The method of claim 1, comprising estimating a distance between the location of the in vivo capsule and the location of the organ'"'"'s wall based on the illumination level of an image or a portion of an image.

10. The method of claim 1, comprising calculating visual coverage of the organ imaged by the in vivo capsule, by calculating a percent of the organ that was imaged during the procedure, at a certain point of time.

11. The method of claim 10, comprising verifying, based on the visual coverage of the organ imaged by the in vivo capsule, that the organ under examination has been completely imaged during the imaging procedure.

12. The method of claim 1, comprising determining spatial coordinates of the first point of interest by estimating a distance of the first point of interest in the image from the in vivo capsule.

13. A system for automatic generation of a model of an organ, the system comprising:

coils to generate a magnetic field;

a processor to receive light-based images of an organ within a body captured from an in vivo capsule and input accepting a user indication of an image captured while the in vivo capsule images a first point of interest to a user identified in the imaged organ, the processor configured to;

generate an initial organ model being a three-dimensional hollow geometric shell representing an inner surface of an organ within a body, the initial organ model based on a predetermined estimated structure of the imaged organ;

receive the indication of an image captured while the in vivo capsule images a first point of interest identified in the imaged organ;

determine a position and orientation of the in vivo capsule upon capturing the indicated image of the first point of interest; and

based on the position and orientation of the in vivo capsule, update the initial model to a customized model, such that a location in the customized model corresponding to the position of the point of interest in vivo reflects the organ size and organ location within the body; and

based on the customized model and images captured by the in vivo capsule, construct a three-dimensional visualization of the organ including the images for display to the user.

14. The system of claim 13, comprising fiduciary elements positioned in a navigation system of the in vivo capsule, wherein the processor is to determine the position and orientation of the in vivo capsule relative to said fiduciary elements.

15. The system of claim 13, wherein the processor is configured to calculate the position of the in vivo capsule in relation to tissue walls of the imaged organ.

16. The system of claim 13, wherein the system further comprises:

a display to display the visualization to the user.

17. The system of claim 16, wherein the processor is configured to estimate a projection of an image of the organ on the customized model.

18. A method for automatic generation of a model of an in vivo organ, the organ imaged by an in vivo capsule comprising an imager, the method comprising:

capturing, via the in vivo capsule, light-based images in-vivo;

generating, by a computer data processor, an initial organ model being a three-dimensional hollow geometric shell representing an inner surface of an organ within an organ within a body;

receiving a user indication of an image captured while the in vivo capsule images a first point of interest to a user identified in the imaged organ;

determining a position of the in vivo capsule upon capturing the indicated image of the first point of interest;

and

based on the position and orientation of the in vivo capsule, updating, by the computer data processor, the initial model to a customized model such that a location in the customized model corresponding to the position of the point of interest in vivo reflects the organ size and organ location within the body; and

based on the customized model and images captured by the in vivo capsule, constructing, by the computer data processor, a three-dimensional visualization of the organ including the images for display to the user.