System and method for automatic processing of images from an autonomous endoscopic capsule

• US 9,854,958 B1
• Filed: 03/23/2014
• Issued: 01/02/2018
• Est. Priority Date: 03/23/2013
• Status: Active Grant

• Current Assignee: Psimos Inc.
• Original Assignee: Garini Technologies Corporation Pte. Ltd.
• Inventors: Kukushkin, Alexander, Tolstaya, Anastasia, Starikovsky, Andrey, Gubaidulina, Landysh, Fedorov, Eugene, Ivanova, Ekaterina, Zhukov, Igor, Mikhailov, Dmitry, Khabibullin, Timur
• Primary Examiner(s): Leubecker, John P
• Application Number:
  US14/222,637
• Time in Patent Office: 1,381 Days
• CPC Class Codes: A61B 1/0005 combining images e.g. side-by-side, superimposed or tiled
• 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 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30032 Colon polyp
• CPC Class Codes: G06T 2207/30092 Stomach; Gastric
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/0014 using an image reference approach
• CPC Class Codes: G06T 7/0016 involving temporal comparison
• CPC Class Codes: G06T 7/90 Determination of colour characteristics

Abstract

A method and system for processing of images from an autonomous endoscopic capsule includes acquiring a video stream from the endoscopic capsule; detecting repeat frames; removing repeat frames from the video stream; adjusting a speed of play back of the video stream based on a value of possibility of skipping significant frames; detecting anomalies; marking frames with anomalies for further review by a physician; and displaying multiple images on a physician'"'"'s desktop simultaneously in a chronological order in a form of a matrix.

Claims

1. A system for processing images from an autonomous endoscopic capsule, comprising:

a processor;

a memory coupled to the processor;

an analysis module stored in the memory and executed on the processor, the analysis module configured to;

detect repeat frames in an incoming video stream;

remove repeat frames that are similar to each other based on a degree of similarity from the video stream, wherein the degree of similarity is determined using Pearson'"'"'s test

2. The system of claim 1, wherein the analysis module is configured to adjust the speed of the play back to show frames with a high degree of similarity faster and frames with a low degree of similarity slower.

3. The system of claim 1, wherein the detecting of the anomalies comprises detecting any of:

color anomalies;

texture anomalies; and

shape anomalies.

4. The system of claim 1, wherein the analysis module is configured to remove frames based on a pre-set degree of similarity.

5. The system of claim 1, wherein the analysis module is configured to detect anomalies by extracting a signal x corresponding to a set of x pixels in a frame and comparing a value of the signal x for frames without anomalies against the current frame.

6. The system of claim 5, wherein the signal x is a histogram for different color channels of the frame used for detection of color anomalies.

7. The system of claim 6, wherein the color channels are saturation channels.

8. The system of claim 6, wherein the color channels are hue channels.

9. The system of claim 5, wherein the signal x is a value of a curvature in different regions of the video frame used for detection of shape anomalies.

10. The system of claim 9, wherein a two-dimensional Gaussian coefficient is used for measuring the curvature in the different regions of the video frame.

11. The system of claim 5, wherein the signal x is a set of values representing an average brightness of the frame with the Gabor filter used for detection of the texture anomalies.

12. The system of claim 1, wherein the analysis module is configured to apply Gaussian smoothing to enhance image structures and reduce noise.

13. The system of claim 1, wherein the analysis module is configured to convert the frames into HSV format.

14. The system of claim 1, wherein the analysis module is configured to detect anomalies by any of:

quintiles of the histograms of RGB channels;

an average curvature of a surface of an intestine;

a Gaussian curvature of a surface of an intestine; and

a Gabor filter spectrogram.

15. A method for processing images from an autonomous endoscopic capsule, the method comprising:

acquiring a video stream from the endoscopic capsule;

detecting repeat frames that are similar to each other based on a degree of similarity, wherein the degree of similarity is determined using Pearson'"'"'s test