Image processing device and image processing method in image processing device for identifying features in an image

• US 8,363,962 B2
• Filed: 06/23/2011
• Issued: 01/29/2013
• Est. Priority Date: 12/28/2005
• Status: Active Grant

• Current Assignee: Olympus Corporation
• Original Assignee: Olympus Medical Systems Corporation (Olympus Corporation)
• Inventors: Nishimura, Hirokazu, Nonami, Tetsuo
• Primary Examiner(s): Lu, Tom Y
• Assistant Examiner(s): CONWAY, THOMAS A
• Application Number:
  US13/166,938
• Publication Number:
  US 20110255757A1
• Time in Patent Office: 586 Days
• Field of Search: None
• US Class Current: 382/225
• CPC Class Codes: A61B 1/00016 using wireless means
• CPC Class Codes: A61B 1/00036 Means for power saving, e.g. sleeping mode
• CPC Class Codes: A61B 1/00055 for alerting the user
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• CPC Class Codes: A61B 5/073 Intestinal transmitters
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10068 Endoscopic image
• CPC Class Codes: G06T 2207/30028 Colon; Small intestine
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A plurality of images inputted in an image signal input portion are divided into a plurality of regions by an image dividing portion, and a feature value in each of the plurality of regions is calculated by a feature value calculation portion and divided into a plurality of subsets by a subset generation portion. On the other hand, a cluster classifying portion classifies a plurality of clusters generated in a feature space into any one of a plurality of classes on the basis of the feature value and occurrence frequency of the feature value. And a classification criterion calculation portion calculates a criterion of classification for classifying images included in one subset on the basis of a distribution state of the feature value in the feature space of each of the images included in the one subset.

Claims

1. An image processing device comprising:

an image signal input portion for inputting an image signal on the basis of a plurality of images obtained by medical equipment having an imaging function;

an image dividing portion for dividing the plurality of images into a plurality of regions, respectively, on the basis of the image signal inputted in the image signal input portion;

a feature value calculation portion for calculating one or more feature values in each of the plurality of regions divided by the image dividing portion;

a cluster classifying portion for generating a plurality of clusters in a feature space on the basis of each feature value and occurrence frequency of each feature value and for classifying the plurality of clusters into anyone of a plurality of classes, respectively, the plurality of classes including at least a class relating to a living mucosa and a class relating to a non-living mucosa;

a subset generation portion for generating a plurality of subsets on the basis of imaging timing of each of the plurality of images using the plurality of images;

a classification criterion calculation portion for calculating a criterion of classification when classifying the image included in at least one subset of the plurality of subsets into anyone of the plurality of classes on the basis of the distribution state of the feature value in the feature space of each image included in the at least one subset;

a classification portion for classifying each region in one image included in the at least one subset on the basis of the criterion of classification; and

a lesion detection portion for carrying out processing to detect a lesion spot for each of the regions when the one image has a region classified as the class relating to the living mucosa on the basis of the classification result of the one image.

3. The image processing device according to claim 1, wherein the lesion detection portion is provided at the medical equipment.

2. An image processing device comprising:

an image signal input portion for inputting an image signal on the basis of a plurality of images obtained by medical equipment having an imaging function;

an image dividing portion for dividing the plurality of images into a plurality of regions, respectively, on the basis of the image signal inputted in the image signal input portion;

a feature value calculation portion for calculating one or more feature values in each of the plurality of regions divided by the image dividing portion;

a cluster classifying portion for generating a plurality of clusters in a feature space on the basis of each feature value and occurrence frequency of each feature value and for classifying the plurality of clusters into anyone of a plurality of classes, respectively, the plurality of classes including at least a class relating to a living mucosa and class relating to a non-living mucosa;

a subset generation portion for generating a plurality of subsets on the basis of imaging timing of each of the plurality of images using the plurality of images;

a classification criterion calculation portion for calculating a criterion of classification when classifying the image included in at least one subset of the plurality of subsets into anyone of the plurality of classes on the basis of the distribution state of the feature value in the feature space of each image included in the at least one subset wherein the classification criterion calculation portion does not calculate the criterion of classification for the class where the feature value is not generated in the at least one subset in the plurality of classes;

a classification portion for classifying each region in one image included in the at least one subset on the basis of the criterion of classification; and

a lesion detection portion for carrying out processing to detect a lesion spot for each of the regions when the one image has a region classified as the class relating to the living mucosa on the basis of the classification result of the one image.

4. The image processing device according to claim 2, wherein the lesion detection portion is provided at the medical equipment.

5. An image processing method in an image processing device, comprising:

an image dividing step for dividing an image into a plurality of regions, respectively, on the basis of an image signal inputted on the basis of the image obtained by medical equipment having an imaging function;

a feature value calculating step for calculating one or more feature values in each of the plurality of regions divided by the image dividing step;

a cluster classifying step for generating a plurality of clusters in a feature space on the basis of each feature value and occurrence frequency of each feature value and for classifying the plurality of clusters into anyone of a plurality of classes, respectively, the plurality of classes including at least a class relating to a living mucosa and a class relating to a non-living mucosa;

a subset generating step for generating a plurality of subsets on the basis of an imaging timing of each of the plurality of images using the plurality of images;

a classification criterion calculating step for calculating a criterion of classification when classifying the image included in at least one subset of the plurality of subsets on the basis of a distribution state of the feature value in the feature space of each image included in the at least one subset;

a classification step for classifying each region in one image included in the at least one subset on the basis of the criterion of classification; and

a lesion detection step for carrying out processing to detect a lesion spot for each of the regions when the one image has a region classified as the class relating to the living mucosa on the basis of the classification result of the one image.

7. The image processing method according to claim 5, wherein the lesion detection step is carried out in the medical equipment.

6. An image processing method in an image processing device, comprising:

an image dividing step for dividing an image into a plurality of regions, respectively, on the basis of an image signal inputted on the basis of the image obtained by medical equipment having an imaging function;

a feature value calculating step for calculating one or more feature values in each of the plurality of regions divided by the image dividing step;

a cluster classifying step for generating a plurality of clusters in a feature space on the basis of each feature value and occurrence frequency of each feature value and for classifying the plurality of clusters into anyone of a plurality of classes, respectively, the plurality of classes including at least a class relating to a living mucosa and a class relating to a non-living mucosa;

a subset generating step for generating a plurality of subsets on the basis of an imaging timing of each of the plurality of images using the plurality of images;

a classification criterion calculating step for calculating a criterion of classification when classifying the image included in at least one subset of the plurality of subsets on the basis of a distribution state of the feature value in the feature space of each image included in the at least one subset generated by the subset generation step, wherein the classification criterion calculation step does not circulate the criterion of classification for the class where the feature value is not generated in the at least one subset in the plurality of classes;

a classification step for classifying each region in one image included in the at least one subset on the basis of the criterion of classification; and

a lesion detection step for carrying out processing to detect a lesion spot for each of the regions when the one image has a region classified as the class relating to the living mucosa on the basis of the classification result of the one image.

8. The image processing method according to claim 6, wherein the lesion detection step is carried out in the medical equipment.