Detection of gastrointestinal sections and transition of an in-vivo device there between

• US 8,922,633 B1
• Filed: 09/26/2011
• Issued: 12/30/2014
• Est. Priority Date: 09/27/2010
• Status: Active Grant

• Current Assignee: Given Imaging Limited (Medtronic Plc)
• Original Assignee: Given Imaging Limited (Medtronic Plc)
• Inventors: Pfeffer, Yehuda
• Primary Examiner(s): Ustaris, Joseph
• Assistant Examiner(s): SECHSER, JILL D
• Application Number:
  US13/245,273
• Time in Patent Office: 1,191 Days
• US Class Current: 348/65
• CPC Class Codes: A61B 1/000094 extracting biological structures
• CPC Class Codes: A61B 1/000096 using artificial intelligence
• CPC Class Codes: A61B 1/00016 using wireless means
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• 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: G06V 10/761 Proximity, similarity or dissimilarity measures
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

An in-vivo device may capture images of the GI system and transfer frames to an external system for analysis. As frames are transferred from the in-vivo device to the external system each frame may be scored as belonging to a first GI section or to a second GI section, and the frame scores may be buffered in a score buffer. Based on shifting of a reference function across the buffered frame scores and calculating distances between the buffered frame scores and the shifted reference function, the time at which the in-vivo device transitions from the first section of the GI system to the second section of the GI section may be determined.

Claims

1. A method for detecting transition of an in-vivo device from one section of the gastrointestinal system to another, comprising:

receiving a stream of image frames, each of the image frames comprising an image captured by an in in-vivo device traversing the GI tract and related non-image data;

calculating frame scores, a frame score for each image frame;

calculating a sequence of distances between the frame scores and a reference function, ƒ

, by shifting the reference function across the frame scores and, after each shifting, calculating a distance between the frame scores and the reference function, wherein calculating a distance comprises calculating a difference between all frame scores and the shifted reference function; and

associating, based on the sequence of distances, a particular frame score with a time at which the in-vivo device transitioned from a first section of the gastrointestinal system to a second section of the gastrointestinal system.

2. The method as in claim 1, comprising, for each currently received image frame,

calculating the frame score based on features extracted from the image and from non-image data in the frame, and from image data and non-image data in past image frames;

buffering the frame score in a frame score buffer;

calculating the sequence of distances by shifting the reference function across frame scores that are buffered in the frame score buffer; and

determining whether the sequence of distances has a global minimum distance at the particular frame score, and if the sequence of distances has a global minimum distance at the particular frame score, associating the particular frame score with the time at which the in-vivo device transitioned from the first gastrointestinal section to the second gastrointestinal section, and if the sequence of distances resulting from the buffered frame scores does not have a global minimum distance at any currently buffered frame score,

(i) receiving a new image frame;

(ii) calculating and buffering a frame score for the new image frame;

(iii) recalculating a new sequence of distances for the buffered frame scores;

(iv) determining whether the new sequence of distances has a global minimum distance; and

if the new sequence of distances does not have a global minimum distance,

repeating steps (i) to (iv) until a global minimum distance is identified.

3. The method as in claim 2, wherein the determination that the sequence of distances has a global minimum distance at the particular frame score is made after shifting the reference function k frame scores away from the particular frame score.

4. The method as in claim 2, wherein shifting the reference function across the currently buffered frame scores starts after buffering at least N_min frame scores in the frame scores buffer, wherein N_min>

5.

5. The method as in claim 2, wherein the reference function ƒ

is defined as;

6. The method as in claim 5, wherein m0<

m1.

7. The method as in claim 5, wherein m0 and m1 are predetermined.

8. The method as in claim 5, wherein m0 and m1 are not predetermined.

9. The method as in claim 5, wherein the distance between the currently buffered frame scores and the reference function is calculated by using a function F(t₀, m0, m1) defined as:

10. The method as in claim 9, wherein P is selected from the group consisting of 1 and 2.

11. The method as in claim 1, further comprising performing a transition dependent action selected from the group consisting of:

changing a mode of operation of the in-vivo device, changing an image capturing rate of the in-vivo device, releasing a medication, refraining from performing certain activities, performing specified activities, displaying a message for a user regarding the time or frame identified as the transition time/frame, and instructing or prompting a user to swallow a medication.

12. The method as in claim 1, wherein the first gastrointestinal section is any one of:

(i) the stomach, (ii) the small bowel, and (iii) the colon.

13. The method as in claim 1, wherein the second gastrointestinal section is any one of:

(i) the stomach, (ii) the small bowel, and (iii) the colon.

14. The method as in claim 1, wherein the first gastrointestinal section and the second gastrointestinal section are adjacent sections.

15. The method as in claim 1, wherein the reference function is a step function ƒ

.

16. A method for detecting transition of an in-vivo device from one section of the gastrointestinal system to another, the method comprising:

for a stream of image frames, each of the frames comprising an image captured by an in in-vivo device traversing the gastrointestinal tract and related non-image data,

calculating a frame score for each image frame;

calculating a sequence of distances between the frame scores and a reference function, ƒ

, by shifting the reference function across the frame scores and, after each shifting, calculating a distance between the frame scores and the reference function, wherein calculating a distance comprises calculating a difference between all frame scores and the shifted reference function; and

associating a particular frame score with a time at which the in-vivo device transitioned from a first GI section to a second GI section based on the sequence of distances.

17. A system for detecting transition of an in-vivo device between sections of the gastrointestinal system, comprising:

a receiver to receive a stream of image frames from an in-vivo device traversing the gastrointestinal system, each of the image frames comprising an image of the gastrointestinal system captured by the in-vivo device and related non-image data;

a processor configured to,

calculate frame scores, a frame score for each image frame;

calculate a sequence of distances between the frame scores and a reference function by,

(i) shifting the reference function across the frame scores and, after each shifting,

(ii) calculating a distance between the frame scores and the reference function, wherein calculating a distance comprises calculating a difference between all frame scores and the shifted reference function; and

associate a particular frame score with a time at which the in-vivo device transitioned from a first section of the gastrointestinal system to a second section of the gastrointestinal system, based on the sequence of distances.

18. The system as in claim 17, wherein the processor is to extract features from images and related non-image data to facilitate calculation of a frame score.

19. The system as in claim 17, wherein the particular frame score associated with the time at which the in-vivo device transitioned from the first section of the gastrointestinal system to the second section of the gastrointestinal system is a frame score for which the sequence of distances has a global minimum distance.

20. The system as in claim 19, further comprising a frame score buffer to buffer frame scores, wherein the processor is to determine whether a sequence of distances resulting from buffered frame scores has a global minimum distance at the particular frame score, and if the sequence of distances has a global minimum distance at the particular frame score,

associate the particular frame score with the time at which the in-vivo device transitioned from the first gastrointestinal section to the second gastrointestinal section, and if the sequence of distances resulting from the buffered frame scores does not have a global minimum distance at any buffered frame score,

(i) receive a new image frame;

(ii) calculate and buffer a frame score for the new image frame;

(iii) recalculate a new sequence of distances for the buffered frame scores;

(iv) determine whether the new sequence of distances has a global minimum distance; and

if the new sequence of distances does not have a global minimum distance,

repeat operations (i) to (iv) until a global minimum distance is identified.