Image processing device and image processing method in image processing device

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.

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 features value 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 the feature value and occurrence frequency of the feature value and for classifying the plurality of clusters into any one of a plurality of classes, respectively;    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; and    a classification criterion calculation portion for calculating a criterion of classification when classifying the image included in the one subset into any one 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 one subset generated by the subset generation portion.    
     
     
         2 . The image processing device according to  claim 1 , 
 wherein the classification criterion calculation portion does not calculate the criterion of classification for the class where the feature value is not generated in one subset in the plurality of classes.    
     
     
         3 . The image processing device according to  claim 1 , 
 wherein the plurality of classes include at least a class relating to a living mucosa and a class relating to a non-living mucosa.    
     
     
         4 . The image processing device according to  claim 2 , 
 wherein the plurality of classes include at least a class relating to a living mucosa and a class relating to a non-living mucosa.    
     
     
         5 . The image processing device according to  claim 3 , further comprising: 
 a classification portion for classifying each region in one image included in the 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.    
     
     
         6 . The image processing device according to  claim 4 , further comprising: 
 a classification portion for classifying each region in one image included in the 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.    
     
     
         7 . An image processing device, comprising: 
 an image signal input portion for inputting an image signal on the basis of a plurality of images obtained in a time series 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;    an image region classifying portion for classifying each of regions into any one of the plurality of classes on the basis of the feature value;    a representative value calculation portion for calculating a representative value of the feature value of at least one class in each of the plurality of images; and    a variation detection portion for detecting variation in the representative value in a time series.    
     
     
         8 . The image processing device according to  claim 7 , 
 wherein a smoothing portion for applying smoothing in the time series direction to each of the representative value is provided; and    the variation detection portion detects either an image or time in which the variation of the representative value becomes the maximum on the basis of the representative value after being smoothed by the smoothing portion.    
     
     
         9 . The image processing device according to  claim 7 , 
 wherein the variation of the representative value is caused by a change in an observed portion in a living body.    
     
     
         10 . The image processing device according to  claim 8 , 
 wherein the variation of the representative value is caused by a change in an observed portion in a living body.    
     
     
         11 . The image processing device according to  claim 7 , 
 wherein the variation of the representative value is caused by presence of feces in a living body.    
     
     
         12 . The image processing device according to  claim 8 , 
 wherein the variation of the representative value is caused by presence of feces in a living body.    
     
     
         13 . The image processing device according to  claim 7 , 
 wherein the variation of the representative value is caused by presence of bile in a living body.    
     
     
         14 . The image processing device according to  claim 8 , 
 wherein the variation of the representative value is caused by presence of bile in a living body.    
     
     
         15 . The image processing device according to  claim 7 , 
 wherein the variation of the representative value is caused by presence of a lesion in a living body.    
     
     
         16 . The image processing device according to  claim 8 , 
 wherein the variation of the representative value is caused by presence of a lesion in a living body.    
     
     
         17 . The image processing device according to  claim 7 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         18 . The image processing device according to  claim 8 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         19 . The image processing device according to  claim 9 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         20 . The image processing device according to  claim 10 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         21 . The image processing device according to  claim 11 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         22 . The image processing device according to  claim 12 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         23 . The image processing device according to  claim 13 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         24 . The image processing device according to  claim 14 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         25 . The image processing device according to  claim 15 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         26 . The image processing device according to  claim 16 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         27 . An image processing device comprising: 
 an image signal input portion for inputting an image signal on the basis 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 the feature value and occurrence frequency of the feature value and for classifying the plurality of clusters into any one of a plurality of classes, respectively; and    an image region classifying portion for classifying the plurality of regions into any one of the plurality of classes on the basis of the classification result of the cluster classifying portion.    
     
     
         28 . An image processing device comprising: 
 an image signal input portion for inputting an image signal on the basis 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 the feature value and occurrence frequency of the feature value and for classifying the plurality of clusters into any one of a plurality of classes, respectively;    a feature value distribution information obtaining portion for obtaining feature value distribution information, which is information relating to a distribution state of the feature value in the feature space; and    an image region classifying portion for classifying the plurality of regions into any one of the plurality of classes on the basis of the feature value distribution information obtained by the feature value distribution information obtaining portion.    
     
     
         29 . The image processing device according to  claim 27 , 
 wherein the image is a plurality of images continuously obtained in a time series.    
     
     
         30 . The image processing device according to  claim 28 , 
 wherein the image is a plurality of images continuously obtained in a time series.    
     
     
         31 . An image processing device comprising: 
 an image signal input portion for inputting an image signal on the basis 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 a plurality of types of feature values in each of the plurality of regions divided by the image dividing portion;    a first cluster classifying portion for generating a plurality of clusters in one feature space on the basis of one type of feature value and the occurrence frequency of the one type of feature value in the plurality of types of feature values and for classifying the plurality of clusters into any one of a plurality of classes, respectively;    a second cluster classifying portion for generating a plurality of clusters in another feature space on the basis of another type of feature value and the occurrence frequency of the another type of feature value in the plurality of types of feature values and for classifying the plurality of clusters into any one of the plurality of classes, respectively; and    a cluster division portion for carrying out division processing for the plurality of clusters in the one feature space on the basis of a distribution state of the feature value in the one feature space and the another feature space.    
     
     
         32 . The image processing device according to  claim 5 , 
 wherein the lesion detection portion is provided at the medical equipment.    
     
     
         33 . The image processing device according to  claim 6 , 
 wherein the lesion detection portion is provided at the medical equipment.    
     
     
         34 . The image processing device according to  claim 7 , 
 wherein the variation detection portion carries out the processing to detect an image or time where the variation of the representative value detected in the time series becomes the maximum.    
     
     
         35 . The image processing device according to  claim 27 , further comprising 
 an imaged portion determining portion for determining that, if a specific region in the regions classified by the image region classifying portion holds a predetermined proportion or more in an image, the image is an image in which a specific organ is imaged.    
     
     
         36 . The image processing device according to  claim 28 , further comprising 
 an imaged portion determining portion for determining that, if a specific region in the regions classified by the image region classifying portion holds a predetermined proportion or more in an image, the image is an image in which a specific organ is imaged.    
     
     
         37 . 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 the feature value and occurrence frequency of the feature value and for classifying the plurality of clusters into any one of a plurality of classes, respectively;    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; and    a classification criterion calculating step for calculating a criterion of classification when classifying the image included in one subset on the basis of a distribution state of the feature value in the feature space of each image included in the one subset generated by the subset generation step.    
     
     
         38 . The image processing method according to  claim 37 , 
 wherein the classification criterion calculation step does not calculate the criterion of classification for the class where the feature value is not generated in one subset in the plurality of classes.    
     
     
         39 . The image processing method according to  claim 37 , 
 wherein the plurality of classes include at least a class relating to a living mucosa and a class relating to a non-living mucosa.    
     
     
         40 . The image processing method according to  claim 38 , 
 wherein the plurality of classes include at least a class relating to a living mucosa and a class relating to a non-living mucosa.    
     
     
         41 . The image processing method according to  claim 39 , further comprising: 
 a classification step for classifying each region in one image included in the 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.    
     
     
         42 . The image processing method according to  claim 40 , further comprising: 
 a classification step for classifying each region in one image included in the 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.    
     
     
         43 . 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 calculation step for calculating one or more feature values in each of the plurality of regions divided by the image dividing step;    an image region classifying step for classifying each of the plurality of regions to any one of the plurality of classes on the basis of the feature value;    a representative value calculation step for calculating a representative value of the feature value of at least one class in each of the plurality of images; and    a variation detection step for detecting variation in the representative value in a time series.    
     
     
         44 . The image processing method according to  claim 43 , 
 wherein a smoothing step for applying smoothing in the time series direction to each of the representative value is provided; and    the variation detection step detects either an image or time in which the variation of the representative value becomes the maximum on the basis of the representative value after being smoothed by the smoothing step.    
     
     
         45 . The image processing method according to  claim 43 , 
 wherein the variation of the representative value is caused by a change in an observed portion in a living body.    
     
     
         46 . The image processing method according to  claim 44 , 
 wherein the variation of the representative value is caused by a change in an observed portion in a living body.    
     
     
         47 . The image processing method according to  claim 43 , 
 wherein the variation of the representative value is caused by presence of feces in a living body.    
     
     
         48 . The image processing method according to  claim 44 , 
 wherein the variation of the representative value is caused by presence of feces in a living body.    
     
     
         49 . The image processing method according to  claim 43 , 
 wherein the variation of the representative value is caused by presence of bile in a living body.    
     
     
         50 . The image processing method according to  claim 44 , 
 wherein the variation of the representative value is caused by presence of bile in a living body.    
     
     
         51 . The image processing method according to  claim 43 , 
 wherein the variation of the representative value is caused by presence of a lesion in a living body.    
     
     
         52 . The image processing method according to  claim 44 , 
 wherein the variation of representative value is caused by presence of a lesion in a living body.    
     
     
         53 . The image processing method according to  claim 43 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         54 . The image processing method according to  claim 44 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         55 . The image processing method according to  claim 45 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         56 . The image processing method according to  claim 46 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         57 . The image processing method according to  claim 47 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         58 . The image processing method according to  claim 48 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         59 . The image processing method according to  claim 49 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         60 . The image processing method according to  claim 50 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         61 . The image processing method according to  claim 51 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         62 . The image processing method according to  claim 52 , 
 wherein the representative value is an average value of a feature value in each of the plurality of classes.    
     
     
         63 . 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 calculation 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 the feature value and occurrence frequency of the feature value and for classifying the plurality of clusters into any one of a plurality of classes, respectively; and    an image region classifying step for classifying the plurality of regions into any one of the plurality of classes on the basis of the classification result of the cluster classifying step.    
     
     
         64 . 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 calculation 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 the feature value and occurrence frequency of the feature value and for classifying the plurality of clusters into any one of a plurality of classes, respectively;    a feature-value distribution information obtaining step for obtaining feature value distribution information relating to a distribution state of the feature value in the feature space; and    an image region classifying step for classifying the plurality of regions into any one of the plurality of classes on the basis of the feature value distribution information obtained by the feature value distribution information obtaining step.    
     
     
         65 . The image processing method according to  claim 63 , 
 wherein the image is a plurality of images continuously obtained in a time series.    
     
     
         66 . The image processing method according to  claim 64 , 
 wherein the image is a plurality of images continuously obtained in a time series.    
     
     
         67 . 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 calculation step for calculating a plurality of types of feature values in each of the plurality of regions divided by the image dividing step;    a first cluster classifying step for generating a plurality of clusters in one feature space on the basis of one type of feature value and the occurrence frequency of the one type of feature value in the plurality of types of feature values and for classifying the plurality of clusters into any one of a plurality of classes, respectively;    a second cluster classifying step for generating a plurality of clusters in another feature space on the basis of another type of feature value and the occurrence frequency of the another type of feature value in the plurality of types of feature values and for classifying the plurality of clusters into any one of the plurality of classes, respectively; and    a cluster division step for carrying out division processing for the plurality of clusters in the one feature space on the basis of a distribution state of the feature value in the one feature space and the another feature space.    
     
     
         68 . The image processing method according to  claim 41 , 
 wherein the lesion detection step is carried out in the medical equipment.    
     
     
         69 . The image processing method according to  claim 42 , 
 wherein the lesion detection step is carried out in the medical equipment.    
     
     
         70 . The image processing method according to  claim 43 , 
 wherein the variation detection step carries out the processing to detect an image or time where the variation of the representative value detected in the time series becomes the maximum.    
     
     
         71 . The image processing method according to  claim 63 , further comprising 
 an imaged portion determining step for determining that, if a specific region in the regions classified by the image region classifying step holds a predetermined proportion or more in an image, the image is an image in which a specific organ is imaged.    
     
     
         72 . The image processing method according to  claim 64 , further comprising 
 an imaged portion determining step for determining that, if a specific region in the regions classified by the image region classifying step holds a predetermined proportion or more in an image, the image is an image in which a specific organ is imaged.    
     
     
         73 . An image processing method in an image processing device comprising: 
 dividing an image obtained by medical equipment into a plurality of regions;    calculating one or more feature values in each of the plurality of regions;    generating a plurality of clusters in a feature space on the basis of the feature value and occurrence frequency of the feature value and classifying the plurality of clusters into any one of a plurality of classes, respectively;    generating a plurality of subsets on the basis of an imaging timing of each of the plurality of images using the plurality of images; and    calculating a criterion of classification when classifying the image included in one subset on the basis of a distribution state of the feature value in the feature space of each image included in the generated one subset.    
     
     
         74 . An image processing method in an image processing device comprising: 
 dividing an image obtained by medical equipment into a plurality of regions;    calculating one or more feature values in each of the plurality of regions;    classifying each of the plurality of regions in any one of a plurality of classes on the basis of the feature value;    calculating a representative value of the feature value of at least one class in each of the plurality of images; and    detecting variation in the representative value in a time series.    
     
     
         75 . An image processing method in an image processing device comprising: 
 dividing an image obtained by medical equipment into a plurality of regions;    calculating one or more feature values in each of the plurality of regions;    generating a plurality of clusters in a feature space on the basis of the feature value and occurrence frequency of the feature value and classifying the plurality of clusters into any one of a plurality of classes, respectively; and    classifying the plurality of regions into any one of the plurality of classes on the basis of the classification result.    
     
     
         76 . An image processing method in an image processing device comprising: 
 dividing an image obtained by medical equipment into a plurality of regions;    calculating one or more feature values in each of the plurality of regions;    generating a plurality of clusters in a feature space on the basis of the feature value and occurrence frequency of the feature value and classifying the plurality of clusters into any one of a plurality of classes, respectively;    obtaining feature value distribution information relating to a distribution state of the feature value in the feature space; and    classifying the plurality of regions into any one of the plurality of classes on the basis of the obtained feature-value distribution information.    
     
     
         77 . An image processing method in an image processing device comprising: 
 dividing an image obtained by medical equipment into a plurality of regions;    calculating one or more feature values in each of the plurality of regions;    generating a plurality of clusters in one feature space on the basis of one type of feature value and the occurrence frequency of the one type of feature value in the plurality of types of feature values and classifying the plurality of clusters into any one of a plurality of classes, respectively;    generating a plurality of clusters in another feature space on the basis of another type of feature value and the occurrence frequency of the another type of feature value in the plurality of types of feature values and classifying the plurality of clusters into any one of the plurality of classes, respectively; and    carrying out division processing for the plurality of clusters generated in the one feature space on the basis of a distribution state of the feature value in the one feature space and the another feature space.