Method and system for multiple passes diagnostic alignment for in vivo images

• US 7,319,781 B2
• Filed: 10/06/2003
• Issued: 01/15/2008
• Est. Priority Date: 10/06/2003
• Status: Active Grant

• Current Assignee: CareStream Health Incorporated
• Original Assignee: CareStream Health Incorporated
• Inventors: Chen, Shoupu, Ray, Lawrence A., Cahill, Nathan D., Goodgame, Marvin M.
• Primary Examiner(s): Ahmed; Samir
• Assistant Examiner(s): Patel; Jayesh A
• Application Number:
  US10/679,712
• Publication Number:
  US 20050074151A1
• Time in Patent Office: 1,562 Days
• Field of Search: 382128-132, 382/294, 382/305, 348/65, 348/45, 348/72, 356/241.1, 600/109, 600/112, 600/111, 600/424, 600/310, 396/427
• US Class Current: 382/128
• CPC Class Codes: A61B 1/000094 extracting biological structures
• CPC Class Codes: A61B 1/00016 using wireless means
• CPC Class Codes: A61B 1/00045 Display arrangement
• CPC Class Codes: A61B 1/00055 for alerting the user
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• CPC Class Codes: A61B 1/042 characterised by a proximal camera, e.g. a CCD camera
• CPC Class Codes: A61B 1/273 for the upper alimentary canal, e.g. oesophagoscopes, gastroscopes
• CPC Class Codes: A61B 5/073 Intestinal transmitters
• CPC Class Codes: A61B 5/14539 for measuring pH
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/30 Determination of transform parameters for the alignment of images, i.e. image registration
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

A digital image processing method for multiple passes diagnostic alignment of in vivo images, comprising the steps of: acquiring images using an in vivo video camera system; forming an in vivo video camera system examination bundlette; transmitting the examination bundlette to proximal in vitro computing device(s); processing the transmitted examination bundlette; automatically identifying abnormalities in the transmitted examination bundlette; and setting off alarm signals to a local site provided that suspected abnormalities have been identified for each pass forming a registration bundle; selecting identification elements of an image from the registration bundle of one pass; and retrieving corresponding images from another pass.

Claims

1. A digital image processing method for aligning in vivo images from multiple passes of a gastrointestinal tract to aid in diagnosing gastrointestinal disease, comprising the steps of:

a) conducting multiple passes of in vivo imaging within the gastrointestinal tract;

b) forming a registration bundle of metadata for each of the multiple passes;

c) identifying features of an in vivo image using digital image processing that enable diagnosis of the gastrointestinal disease;

d) automatically selecting possible image features of an in vivo image from the registration bundle, associated with one pass, using algorithmic classification;

e) retrieving a global index and an anatomical index and computing local travel distance based on said global index and said anatomical index; and

f) retrieving corresponding images in a neighborhood of said computed local travel distance from another pass based on prior selection of the possible image features.

2. The digital image processing method claimed in claim 1, wherein forming a registration bundle of metadata, includes the steps of:

b1) retrieving an anatomical identity label associated with the gastrointestinal tract;

b2) retrieving a global index label corresponding to each in vivo imaging pass;

b3) retrieving a local index label with respect to a specific anatomical section within the gastrointestinal tract;

b4) calculating global travel distance within the gastrointestinal tract;

b5) forming at least one registration bundlette from information in steps b1-b4; and

b6) forming a registration bundle from the at least one registration bundlette, wherein the at least one registration bundlette includes at least a combination of the anatomical identity label, the global index label, the local index label, and the global travel distance.

3. The digital image processing method claimed in claim 1, wherein selection of the possible indexed features includes the step of selecting an in vivo image using a global index.

4. The digital image processing method claimed in claim 1, wherein selection of the possible indexed features includes the step of selecting an in vivo image by browsing a plurality of images.

5. The digital image processing method claimed in claim 1, wherein selection of the possible indexed features includes the step of selecting an in vivo image using an anatomical identity and a local index.

6. A digital image processing method for aligning in vivo images from multiple passes of a gastrointestinal tract to aid in diagnosing gastrointestinal disease, comprising the steps of:

a) conducting multiple passes of in vivo imaging within the gastrointestinal tract;

b) forming a registration bundle of metadata for each of the multiple passes;

c) identifying features of an in vivo image using digital image processing that enable diagnosis of the gastrointestinal disease;

d) automatically selecting possible image features of an in vivo image from the registration bundle, associated with one pass, using algorithmic classification;

e) retrieving corresponding images from another pass based on prior selection of the possible image features;

wherein selection of the possible indexed features includes the step of selecting an in vivo image using a global index;

wherein retrieving corresponding images from another pass based on prior selection of the in vivo image using the global index further includes the steps of;

d1) retrieving anatomical identity based on a global index;

d2) computing a local travel distance using a global travel distance and the anatomical identity;

d3) locating images corresponding to the anatomical identity; and

d4) locating a set of images in a neighborhood of computed local travel distance.

7. A digital image processing method for aligning in vivo images from multiple passes of a gastrointestinal tract to aid in diagnosing gastrointestinal disease, comprising the steps of:

a) conducting multiple nasses of in vivo imaging within the gastrointestinal tract;

b) forming a registration bundle of metadata for each of the multiple passes;

c) identifying features of an in vivo image using digital image processin that enable diagnosis of the gastrointestinal disease;

d) automatically selecting possible image features of an in vivo image from the registration bundle, associated with one pass, using algorithmic classification;

e) retrieving corresponding images from another pass based on prior selection of the possible image features;

wherein selection of the possible indexed features includes the step of selecting an in vivo image by browsing a plurality of images;

wherein retrieving corresponding images from another pass based on prior selection of the possible indexed features further includes the steps of;

d1) retrieving a global index;

d2) retrieving anatomical identity based on the global index;

d3) computing a local travel distance using a global travel distance and the anatomical identity;

d4) locating images corresponding to the anatomical identity; and

d5) locating a set of images in a neighborhood of computed local travel distance.

8. A digital image processing method for aligning in vivo images from multiple passes of a gastrointestinal tract to aid in diagnosing gastrointestinal disease, comprising the steps of:

a) conducting multiple passes of in vivo imaging within the gastrointestinal tract;

b) forming a registration bundle of metadata for each of the multiple passes;

c) identifying features of an in vivo image using digital image processing that enable diagnosis of the gastrointestinal disease;

d) automatically selecting possible image features of an in vivo image from the registration bundle, associated with one pass, using algorithmic classification; and

e) retrieving corresponding images from another pass based on prior selection of the possible image features,

wherein selection of the possible indexed features includes the step of selecting an in vivo image using an anatomical identity and a local index;

wherein retrieving corresponding image) from another pass based on prior selection of the possible indexed features further includes the steps of;

d1) computing a local travel distance using a global travel distance and the anatomical identity;

d2) locating images corresponding to the anatomical identity; and

d3) locating a set of images in a neighborhood of computed local travel distance.

9. An in vivo imaging alignment and processing system, comprising:

a) an image alignment processor for selecting and retrieving possible indexed features of a plurality of in vivo images from multiple image capturing passes, wherein the possible indexed features enable one to correctly align the plurality of in vivo images from multiple image capturing passes according to images captured at substantially similar positions in a gastrointestinal tract based on a computed local travel distance based on a global index and an anatomical index, and images in a neighborhood of said computed local travel distance;

b) a template source for detecting in vivo images that indicate a diseased gastrointestinal tract and sending the in vivo images to the image alignment processor;

c) a display for displaying a plurality of aligned in vivo images;

d) a means for transmitting the plurality of in vivo images;

e) a means for storing metadata associated with the plurality of in vivo images;

f) a means for communicating selected in vivo images across a network;

g) a means for outputting the plurality of aligned in vivo images; and

h) a user interactive means for inputting and/or controlling the metadata and/or the plurality of in vivo images.