Image processing device, image processing method, and computer-readable recording medium

Patent metadata

Field	Value
Publication number	US-2018014902-A1
Application number	US-201715705657-A
Country	US
Kind code	A1
Filing date	Sep 15, 2017
Priority date	Mar 20, 2015
Publication date	Jan 18, 2018
Grant date	—

Abstract

An image processing device includes: an abnormality candidate region detection unit configured to detect, from an intraluminal image obtained by imaging a living body lumen, an abnormality candidate region in which a tissue characteristic of the living body or an in-vivo state satisfies a predetermined condition; a feature data calculation unit configured to calculate, from each of a plurality of regions inside the intraluminal image, a plurality of pieces of feature data including different kinds; an integrated feature data calculation unit configured to calculate integrated feature data by integrating the plurality of pieces of feature data based on information of the abnormality candidate region; and a detection unit configured to detect an abnormality from the intraluminal image by using the integrated feature data.

First claim

What is claimed is:

1 . An image processing device comprising:
an abnormality candidate region detection unit configured to detect, from an intraluminal image obtained by imaging a living body lumen, an abnormality candidate region in which a tissue characteristic of the living body or an in-vivo state satisfies a predetermined condition; a feature data calculation unit configured to calculate, from each of a plurality of regions inside the intraluminal image, a plurality of pieces of feature data including different kinds; an integrated feature data calculation unit configured to calculate integrated feature data by integrating the plurality of pieces of feature data based on information of the abnormality candidate region; and a detection unit configured to detect an abnormality from the intraluminal image by using the integrated feature data.

2 . The image processing device according to claim 1 , wherein
the integrated feature data calculation unit includes:
an abnormality candidate region information acquiring unit configured to acquire the information of the abnormality candidate region; and
a parameter control unit configured to control a calculation parameter for the integrated feature data based on the information of the abnormality candidate region, and
the integrated feature data calculation unit calculates the integrated feature data based on the calculation parameter.

3 . The image processing device according to claim 2 , wherein the abnormality candidate region information acquiring unit estimates an abnormality kind in the abnormality candidate region.

4 . The image processing device according to claim 3 , wherein the parameter control unit includes a feature data selector configured to select feature data to be used when the integrated feature data calculation unit calculates integrated feature data based on an estimation result of the abnormality candidate region information acquiring unit.

5 . The image processing device according to claim 4 , wherein abnormality kinds includes abnormalities of a color, a shape, and texture in the intraluminal image, and the feature data selector preferentially selects, in accordance with an estimation result of the abnormality candidate region information acquiring unit, feature data corresponding to the abnormality kinds over feature data corresponding to other abnormality kinds.

6 . The image processing device according to claim 3 , wherein
the abnormality candidate region information acquiring unit estimates an abnormality kind in the abnormality candidate region by a plurality of methods different from each other, and the parameter control unit includes a feature data selection unit configured to select feature data to be used when the integrated feature data calculation unit calculates integrated feature data by combining at least part of estimation results of the abnormality kind by the plurality of methods.

7 . The image processing device according to claim 3 , wherein the parameter control unit includes at least any one of: an integrated feature data dimension number determination unit configured to determine number of dimensions for the integrated feature data; and a feature data transform dimension number determination unit configured to determine transform number of dimensions for the feature data.

8 . The image processing device according to claim 7 , wherein
the abnormality candidate region information acquiring unit estimates, as an abnormality kind, which one of a color, a shape and texture an abnormality exists in, at least any one of the integrated feature data dimension number determination unit and the feature data transform dimension number determination unit determines number of dimensions, and the number of dimensions when an abnormality exists in the color is set smaller than the number of dimensions when an abnormality exists in the shape and/or the texture.

9 . The image processing device according to claim 3 , wherein
the abnormality candidate region information acquiring unit estimates an abnormality kind in the abnormality candidate region based on a plurality of methods different from each other, and the parameter control unit includes at least any one of: an integrated feature data dimension number determination unit configured to determine number of dimensions for the integrated feature data by combining at least part of estimation results of the abnormality kind by the plurality of methods; and a feature data transform dimension number determination unit configured to determine transform number of dimensions for the feature data.

10 . The image processing device according to claim 2 , wherein the abnormality candidate region information acquiring unit calculates clarity at a boundary of the abnormality candidate region.

11 . The image processing device according to claim 10 , wherein the parameter control unit includes a feature data selector configured to select feature data to be used when the integrated feature data calculation unit calculates integrated feature data.

12 . The image processing device according to claim 11 , wherein the feature data selector preferentially selects at least any one of color feature data and shape feature data when the boundary is clear, and the feature data selector preferentially selects texture feature data when the boundary is unclear.

13 . The image processing device according to claim 10 , wherein the parameter control unit includes at least any one of: an integrated feature data dimension number determination unit configured to determine number of dimensions for the integrated feature data; and a feature data transform dimension number determination unit configured to determine transform number of dimensions for the feature data.

14 . The image processing device according to claim 13 , wherein
when at least any one of the integrated feature data dimension number determination unit and the feature data transform dimension number determination unit determines number of dimensions, the number of dimensions when the boundary is clear is set smaller than the number of dimensions when the boundary is unclear.

15 . The image processing device according to claim 2 , wherein the abnormality candidate region information acquiring unit calculates information on a peripheral region of the abnormality candidate region.

16 . The image processing device according to claim 15 , wherein the parameter control unit includes a feature data selector configured to select feature data to be used when the integrated feature data calculation unit calculates integrated feature data based on information on a peripheral region of the abnormality candidate region.

17 . The image processing device according to claim 16 , wherein the abnormality candidate region information acquiring unit categorizes organs in the intraluminal image into kinds.

18 . The image processing device according to claim 17 , wherein when the kind of the organ is the stomach or small intestine, the feature data selector preferentially selects at least any one of color feature data and texture feature data, and when the organ kind is a large intestine, the feature data selector preferentially selects shape feature data.

19 . The image processing device according to claim 16 , wherein the abnormality candidate region information acquiring unit determines whether the abnormality candidate region exists in a bubble inner region.

20 . The image processing device according to claim 19 , wherein when the a

Assignees

• Olympus Corp

Inventors

• Kitamura Makoto
• Kamiyama Toshiya
• Kimura Mitsutaka

Classifications

• G06T2207/10068

  Endoscopic image · CPC title

• A61B1/041

  Capsule endoscopes for imaging · CPC title

• A61B1/045

  Control thereof · CPC title

• G06T2207/30096

  Tumor; Lesion · CPC title

• A61B1/000094 Primary

  extracting biological structures · CPC title