JP2017213097A - Image processing device, image processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing device, an image processing method, and a program that enable reliability of a detection result on a lesion candidate region to be grasped.SOLUTION: An image processing device 5 includes an acquisition part 51 for acquiring image data of a body cavity of a subject, a blur calculation part 541 for calculating a blur evaluation value on the blur of a lesion image corresponding to lesion image data based on one of the image data and the lesion image data in which a lesion candidate region is extracted based on the image data, and a display control part 56 for superposing the blur evaluation value of the lesion image on the lesion image and outputting the blur evaluation value superposed on the lesion image to the outside.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an image processing apparatus, an image processing method, and a program for performing image processing on image data.

  2. Description of the Related Art Conventionally, in an image processing apparatus, a technique for automatically detecting a lesion candidate area such as a lesion by performing pattern matching on an endoscopic image input from an endoscope using a specific pattern is known. (See Patent Document 1). In this technique, an alert image is superimposed on a lesion candidate area of an endoscopic image detected by pattern matching, and the lesion candidate area is notified to the user.

JP 2011-255006 A

  By the way, the contrast of an endoscopic image is significantly reduced due to blurring caused by the pulsation of an organ at the time of imaging. In this case, in Patent Document 1 described above, the matching accuracy by pattern matching decreases, and the detection accuracy of the lesion candidate area also decreases. For this reason, the technique which can grasp | ascertain the reliability with respect to the detection result of a lesion candidate area | region was desired.

  The present invention has been made in view of the above, and an object of the present invention is to provide an image processing apparatus, an image processing method, and a program capable of grasping the reliability of the detection result of a lesion candidate region.

  In order to solve the above-described problems and achieve the object, an image processing apparatus according to the present invention corresponds to the acquisition unit that acquires image data obtained by imaging the body cavity of a subject, the image data, and the image data. A calculation unit that calculates a blur evaluation value for evaluating a blur condition of a lesion image corresponding to the lesion image data based on either one of the lesion image data in which information on a lesion candidate region is superimposed on the image; and the lesion image And an output unit that superimposes the blur evaluation value and outputs the output to the outside.

  The image processing apparatus according to the present invention further includes a first image processing unit that performs predetermined image processing on the image data in the above invention, and the acquisition unit performs the predetermined image processing. Two lesion image data that are generated by an external lesion detection device based on the image data and acquired in time are acquired from the lesion detection device, and the calculation unit is configured to acquire the time sequence acquired by the acquisition unit. The blur evaluation value is calculated based on the lesion image corresponding to each of the two lesion image data.

  In the image processing apparatus according to the present invention, in the above invention, a first image processing unit that performs predetermined image processing on the image data, and the first image processing unit performs the predetermined image processing. A lesion detection unit that generates the lesion image data by performing pattern matching on the image corresponding to the image data using a lesion pattern, and the calculation unit performs the predetermined image processing. The blur evaluation value is calculated based on each of the two pieces of the image data that are temporally changed.

  In the image processing apparatus according to the present invention as set forth in the invention described above, the lesion detection unit changes a lesion pattern used in the pattern matching based on the blur evaluation value.

  The image processing apparatus according to the present invention further includes a determination unit that determines whether or not the blur evaluation value calculated by the calculation unit is equal to or greater than a predetermined threshold in the above invention, and the output unit includes the output unit The blur evaluation value is superimposed on the lesion image when the determination unit determines that the blur evaluation value is equal to or greater than the predetermined threshold.

  Further, in the image processing apparatus according to the present invention, in the above invention, the output unit superimposes and outputs information related to the blur evaluation value in an area of the image corresponding to the lesion candidate area in the lesion image. Features.

  The image processing apparatus according to the present invention is characterized in that, in the above invention, the image processing apparatus further includes a combining unit that combines the image corresponding to the image data and the lesion image to generate combined image data.

  The image processing method according to the present invention includes an acquisition step of acquiring image data obtained by imaging the body cavity of a subject, and a lesion in which information about a lesion candidate region is superimposed on the image data and an image corresponding to the image data. Based on either one of the image data, a calculation step for calculating a blur evaluation value for evaluating the blur condition of the lesion image corresponding to the lesion image data; and the blur evaluation value is superimposed on the lesion image And an output step for outputting.

  In the program according to the present invention, an acquisition step of acquiring image data obtained by imaging the body cavity of the subject is superimposed on the image processing apparatus, and information regarding the lesion candidate region is superimposed on the image data and an image corresponding to the image data. And calculating a blur evaluation value for evaluating a blur condition of the lesion image corresponding to the lesion image data based on either one of the lesion image data, and superimposing the blur evaluation value on the lesion image. And an output step of outputting to the outside.

  According to the present invention, there is an effect that the reliability of lesion detection can be improved.

FIG. 1 is a block diagram showing a functional configuration of an endoscope system according to Embodiment 1 of the present invention. FIG. 2 is a flowchart showing an outline of processing executed by the image processing apparatus according to Embodiment 1 of the present invention. FIG. 3 is a diagram illustrating an example of an endoscopic image generated by the endoscope according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a lesion image generated by the lesion detection apparatus according to Embodiment 1 of the present invention. FIG. 5 is a diagram illustrating an example of a composite image generated by the combining unit of the image processing apparatus according to Embodiment 1 of the present invention. FIG. 6 is a diagram showing an example of an image displayed by the display device according to Embodiment 1 of the present invention. FIG. 7 is a block diagram showing a functional configuration of the endoscope system according to Embodiment 2 of the present invention. FIG. 8 is a diagram showing an example of an image displayed by the display device according to Embodiment 2 of the present invention. FIG. 9 is a block diagram showing a functional configuration of the endoscope system according to Embodiment 3 of the present invention. FIG. 10 is a diagram showing an example of an image displayed by the display device according to Embodiment 3 of the present invention. FIG. 11 is a diagram showing another example of an image displayed by the display device according to Embodiment 3 of the present invention.

  Hereinafter, modes for carrying out the present invention (hereinafter referred to as “embodiments”) will be described. In the embodiment, an endoscope system including an image processing apparatus according to the present invention will be described as an example. Note that the present invention is not limited to the embodiments. Further, in the description of the drawings, the same portions will be described with the same reference numerals.

(Embodiment 1)
[Configuration of endoscope system]
FIG. 1 is a block diagram showing a functional configuration of an endoscope system according to Embodiment 1 of the present invention. An endoscope system 1 shown in FIG. 1 includes an endoscope 2 (endoscope scope), a lesion detection device 3, a display device 4, and an image processing device 5 (processor).

  The endoscope 2 generates image data obtained by imaging the inside of the subject by being inserted into the subject. The endoscope 2 is provided with an imaging device at a distal end portion to be inserted into a subject. The imaging device captures an irradiation area irradiated from the distal end portion, thereby generating image data and outputting the image data to the image processing device 5. To do. In addition, the kind of endoscope 2 is not specifically limited, In this Embodiment 1, a flexible endoscope or a rigid endoscope may be sufficient.

  The lesion detection device 3 generates lesion image data on which information related to a lesion candidate region is superimposed based on the image data generated by the endoscope 2. Specifically, the lesion detection device 3 acquires image data generated by the endoscope 2 via the image processing device 5, and based on pattern matching processing using a lesion pattern for an image corresponding to the acquired image data. A lesion candidate area is detected, and lesion image data is generated by superimposing information including a frame, a symbol, a character, and a figure on the area corresponding to the detected lesion candidate area so as to be identifiable. Here, the lesion candidate region is an abnormal surface layer region that is different from a healthy surface layer on the surface of the subject, for example, a region with an abnormal color (reddish brown), a region with an abnormal blood vessel structure, a bleeding region, an ulcer region, Either a polyp region or a cancer region. The lesion detection device 3 is realized by using a personal computer or the like having a discriminator learned in advance using a plurality of medical images.

  The display device 4 displays an image that has been subjected to image processing by the image processing device 5 and various types of information related to the endoscope system 1. The display device 4 is realized using a display monitor having liquid crystal, organic EL (Electro Luminescence), or the like.

  The image processing apparatus 5 includes an acquisition unit 51, an image processing unit 52, a frame memory 53, a blur evaluation unit 54, a synthesis unit 55, and a display control unit 56.

  The acquisition unit 51 acquires image data obtained by imaging the body cavity of the subject generated by the endoscope 2, and outputs the acquired image data to the image processing unit 52. In addition, the acquisition unit 51 acquires lesion image data from the lesion detection device 3 and outputs the acquired lesion image data to the frame memory 53.

  The image processing unit 52 performs predetermined image processing on the image data input from the acquisition unit 51 and outputs the image data to the lesion detection device 3 and the synthesis unit 55. Here, the predetermined image processing includes, for example, A / D conversion processing, optical black subtraction processing, white balance adjustment processing, image data synchronization processing, and color matrix calculation when the endoscope 2 is a frame sequential type. Image processing including processing, γ correction processing, color reproduction processing, edge enhancement processing, and the like.

  The frame memory 53 temporarily records a plurality of lesion image data sequentially input from the acquisition unit 51, and outputs the plurality of lesion image data to the blur evaluation unit 54 and the synthesis unit 55 in time series. Specifically, the frame memory 53 temporarily records a predetermined number of frames (for example, 10 frames). The frame memory 53 is realized using, for example, an SDRAM (Synchronous Dynamic Random Access Memory).

  The blur evaluation unit 54 calculates a blur evaluation value for evaluating the blur condition of the lesion image based on the lesion image corresponding to the lesion image data that is temporally changed and input from the frame memory 53, and calculates the calculated blur evaluation. The value is output to the display control unit 56. The blur evaluation unit 54 includes a blur calculation unit 541 and a blur determination unit 542.

  The blur calculation unit 541 calculates a blur evaluation value for evaluating the blur condition of a lesion image based on two lesion images corresponding to two lesion image data that are temporally changed and input from the frame memory 53. Here, the blur evaluation value calculated by the blur calculation unit 541 is a similarity between two lesion images, a movement amount of a feature point included in the two lesion images, a motion vector of each pixel in the two lesion images, and two lesions. The integrated value of the high-frequency component in the image, the edge of the high-frequency component in the two lesion images, and the motion vector of the pixel of interest in the two lesion images. In addition to the above, the blur calculation unit 541 may calculate the blur evaluation value in the lesion image using another known technique. In the first embodiment, the blur calculation unit 541 functions as a calculation unit.

  The blur determination unit 542 determines whether or not the blur evaluation value calculated by the blur calculation unit 541 is greater than or equal to a predetermined threshold. Here, the threshold value is set to be equal to or greater than the predetermined threshold value, but the threshold value may be changed as appropriate depending on the blur evaluation value calculation method. That is, the shake determination unit 542 may determine whether or not the shake evaluation value calculated by the shake calculation unit 541 is equal to or less than a predetermined threshold according to a method for calculating the shake evaluation value. In the first embodiment, the blur determination unit 542 functions as a determination unit.

  The combining unit 55 combines an image corresponding to the image data input from the image processing unit 52 (hereinafter referred to as “endoscopic image”) and a lesion image corresponding to the lesion image data input from the frame memory 53. Composite image data is generated and output to the display control unit 56. Specifically, the composition unit 55 displays an image corresponding to the image data subjected to the image processing by the image processing unit 52 in the display area where the display device 4 displays an image, and a lesion image input from the frame memory 53. Composite image data obtained by combining a lesion image corresponding to the data is generated. Here, the display area of the lesion image is smaller than the display area of the endoscopic image.

  The display control unit 56 superimposes the shake evaluation value calculated by the shake evaluation unit 54 on the composite image corresponding to the composite image data input from the synthesis unit 55 and outputs the superimposed image to the display device 4. Specifically, the display control unit 56 superimposes the blur evaluation value on the composite image as the reliability (reliability) of the lesion image and outputs it to the display device 4 for display. In addition, when the blur determination unit 542 determines that the blur evaluation value calculated by the blur calculation unit 541 is equal to or greater than a predetermined threshold, the display control unit 56 superimposes the blur evaluation value on the composite image to the display device 4. On the other hand, when the blur determination unit 542 determines that the blur evaluation value calculated by the blur calculation unit 541 is not equal to or greater than a predetermined threshold, only the composite image is displayed without superimposing the blur evaluation value on the composite image. Output to the display device 4 to display. In the first embodiment, the display control unit 56 functions as an output unit.

[Processing of image processing apparatus]
Next, processing executed by the image processing apparatus 5 will be described. FIG. 2 is a flowchart showing an outline of processing executed by the image processing apparatus 5.

  As illustrated in FIG. 2, first, the acquisition unit 51 acquires image data from the endoscope 2 and lesion image data from the lesion detection device 3 (step S101). Specifically, the acquisition unit 51 acquires the endoscopic image P1 illustrated in FIG. 3 and acquires the lesion image P2 from which the lesion candidate area A1 is extracted based on the endoscopic image P1 illustrated in FIG. . In this case, the acquisition unit 51 outputs the endoscopic image P1 acquired from the endoscope 2 to the image processing unit 52, and outputs the lesion image P2 acquired from the lesion detection device 3 to the frame memory 53.

  Subsequently, the blur calculation unit 541 calculates a blur evaluation value related to blur of the lesion image based on the two lesion images that are recorded in the frame memory 53 and that are temporally changed (step S102).

  Thereafter, the blur determination unit 542 determines whether or not the blur evaluation value calculated by the blur calculation unit 541 is greater than or equal to a threshold value (step S103). When the blur determination unit 542 determines that the blur evaluation value calculated by the blur calculation unit 541 is greater than or equal to the threshold (step S103: Yes), the image processing apparatus 5 proceeds to step S104 described later. On the other hand, when it is determined by the blur determination unit 542 that the blur evaluation value calculated by the blur calculation unit 541 is not equal to or greater than the threshold (step S103: No), the image processing apparatus 5 proceeds to step S107 described later.

  In step S <b> 104, the synthesis unit 55 synthesizes the endoscopic image input from the image processing unit 52 and the lesion image input from the frame memory 53 to generate composite image data. Specifically, as illustrated in FIG. 5, the combining unit 55 combines the endoscope image P1 and the lesion image P2 to generate a combined image W1.

  Subsequently, the display control unit 56 causes the display device 4 to display the blur evaluation value calculated by the blur calculation unit 541 on the composite image corresponding to the composite image data (step S105). Specifically, as illustrated in FIG. 6, the display control unit 56 causes the display device 4 to display the information A <b> 2 indicating reliability as a blur evaluation value on the composite image W <b> 1. Thereby, the user can intuitively grasp the reliability of the current lesion image P2. Note that the display control unit 56 displayed the blur evaluation value as a number (70%) as the information A2, but instead of the number, for example, the frame of the lesion candidate region A1 is highlighted according to the blur evaluation value. Or may be highlighted. Of course, the display control unit 56 may superimpose symbols and characters on the composite image W1 as the information A2 and cause the display device 4 to display the information A2.

  Thereafter, when the observation of the subject is ended (step S106: Yes), the image processing apparatus 5 ends the present process. On the other hand, when the observation of the subject is not finished (step S106: No), the image processing apparatus 5 returns to step S101 described above.

  In step S <b> 107, the synthesis unit 55 synthesizes the endoscopic image input from the image processing unit 52 and the lesion image input from the frame memory 53 to generate composite image data. In this case, the display control unit 56 causes the display device 4 to display the information on the reliability as the blur evaluation value on the combining unit 55 without superimposing the information. After step S107, the image processing apparatus 5 proceeds to step S106. Thereby, the user can intuitively grasp that the current lesion image P2 is not reliable. Further, the display control unit 56 may hide the lesion image P2 when the blur determination unit 542 determines that the blur evaluation value calculated by the blur calculation unit 541 is not greater than or equal to the threshold value.

  According to the first embodiment of the present invention described above, since the display control unit 56 superimposes the blur evaluation value on the lesion image and outputs it to the display device 4 for display, the reliability of the lesion candidate area in the current lesion image is displayed. Can intuitively grasp the sex.

  Further, according to the first embodiment of the present invention, the display control unit 56 superimposes the blur evaluation value on the synthesized image generated by the synthesizing unit 55 and outputs it to the display device 4 for display. The subject can be observed while comparing the lesion image with the lesion image.

  Further, according to the first embodiment of the present invention, when the shake determination unit 542 determines that the shake evaluation value calculated by the shake calculation unit 541 is greater than or equal to the threshold, the display control unit 56 Since the calculated blur evaluation value is superimposed on the lesion image and output to the display device 4 for display, the reliability of the lesion candidate area in the lesion image can be intuitively grasped.

  In the embodiment of the present invention, the blur evaluation value is displayed as the reliability for one lesion candidate area. However, when the lesion detection apparatus 3 detects a plurality of lesion candidate areas, for example, the blur evaluation unit 54 The blur evaluation value of each of the plurality of lesion candidate areas detected by the lesion detection apparatus 3 is calculated, and the display control unit 56 superimposes information on the blur evaluation value of each lesion candidate area and outputs it to the display apparatus 4 for display. You may let them.

(Embodiment 2)
Next, a second embodiment of the present invention will be described. In the first embodiment described above, the lesion detection device 3 generates the lesion image data in which the lesion candidate area is detected based on the image data subjected to the image processing by the image processing unit 52. In 2, the lesion detection device 3 generates lesion image data in which a lesion candidate area is detected based on the image data of the RAW data. Hereinafter, the configuration of the endoscope system according to the second embodiment will be described. In addition, the same code | symbol is attached | subjected to the structure same as the endoscope system 1 which concerns on Embodiment 1 mentioned above, and description is abbreviate | omitted.

[Configuration of endoscope system]
FIG. 7 is a block diagram showing a functional configuration of the endoscope system according to Embodiment 2 of the present invention. An endoscope system 1a illustrated in FIG. 7 includes an image processing device 5a instead of the image processing device 5 of the endoscope system 1 according to the first embodiment described above.

  The image processing device 5a includes a first image processing unit 52a and a second image processing unit 52b instead of the image processing unit 52 of the image processing device 5 according to Embodiment 1 described above.

  The first image processing unit 52 a performs basic image processing on the image data of the RAW data input from the acquisition unit 51 and outputs the image data to the lesion detection device 3. Here, the basic image processing is image processing that does not affect picture making, such as at least A / D conversion processing and optical black subtraction processing.

  The second image processing unit 52 b performs image processing necessary for picture creation on the lesion image data input from the frame memory 53 and outputs the image processing to the display control unit 56. Here, as image processing necessary for picture creation, white balance adjustment processing, when the endoscope 2 is a frame sequential type, image data synchronization processing, color matrix calculation processing, γ correction processing, color reproduction processing, and Image processing including edge enhancement processing and the like.

  In the endoscope system 1a configured as described above, the lesion detection device 3 generates lesion image data in which a lesion candidate region is detected based on the image data of the RAW data from the image processing device 5a. Then, the blur evaluation unit 54 calculates a blur evaluation value related to the blur of the lesion image corresponding to the two lesion image data moving back and forth in time. Thereafter, the display control unit 56 causes the display device 4 to display the blur evaluation value superimposed on the lesion image corresponding to the lesion image data as information on reliability. Specifically, as shown in FIG. 8, the display control unit 56 causes the display device 4 to display an image W2 in which the blur evaluation value is superimposed as the reliability information A2 on the lesion image P10 in real time. Accordingly, the user can intuitively grasp the reliability of the lesion image P10 while visually recognizing only the image W2.

  According to the second embodiment of the present invention described above, since the display control unit 56 superimposes the blur evaluation value on the lesion image and outputs it to the display device 4 for display, the reliability of the lesion candidate area in the current lesion image is displayed. Can intuitively grasp the sex.

  Further, according to the second embodiment of the present invention, the lesion detection device 3 generates lesion image data in which a lesion candidate region is detected based on the image data of the RAW data from the image processing device 5a, and the blur evaluation unit 54 Since the blur evaluation value regarding the blur of the lesion image corresponding to the two lesion image data before and after the time is calculated, the lesion candidate area is detected in the image data before the color and gradation are changed. It is possible to detect a lesion with high accuracy.

(Embodiment 3)
Next, a third embodiment of the present invention will be described. In the third embodiment, the image processing apparatus extracts a lesion candidate area. Below, the same code | symbol is attached | subjected to the structure same as the endoscope system 1a which concerns on this Embodiment 2, and description is abbreviate | omitted.

[Configuration of endoscope system]
FIG. 9 is a block diagram showing a functional configuration of the endoscope system according to Embodiment 3 of the present invention. An endoscope system 1b illustrated in FIG. 9 includes an image processing device 5b instead of the image processing device 5a according to the endoscope system 1a according to the second embodiment described above.

  The image processing device 5b further includes a lesion candidate region detection unit 57 in addition to the configuration of the image processing device 5a according to the second embodiment described above.

  The lesion candidate area detection unit 57 generates lesion image data obtained by extracting the lesion candidate area based on the image data of the RAW data input from the frame memory 53. Specifically, the lesion candidate area detection unit 57 extracts a lesion candidate area based on a pattern matching based on a lesion pattern or a high frequency component from an image corresponding to the image data of the RAW data acquired from the frame memory 53, and the lesion image. Generate data. Further, the lesion candidate area detection unit 57 generates lesion image data weighted on the lesion candidate area based on the blur evaluation value calculated by the blur evaluation unit 54, and outputs the lesion image data to the second image processing unit 52b.

  The endoscope system 1b configured as described above is based on the image data of the raw data input from the frame memory 53 by the lesion candidate area detection unit 57 and the blur evaluation value calculated by the blur evaluation unit 54. Generate data. Specifically, as shown in FIG. 10, the lesion candidate area detection unit 57 is based on the image data of the RAW data input from the frame memory 53 and the blur evaluation value calculated by the blur evaluation unit 54. A lesion image P20 corresponding to the lesion image data in which the region A1 is emphasized is generated. Then, the display control unit 56 causes the display device 4 to display the image W3 including the lesion image P10 in real time. Accordingly, the user can intuitively grasp the reliability of the lesion image P20 while visually recognizing only the lesion image WP20.

  According to the third embodiment of the present invention described above, since the display control unit 56 superimposes the blur evaluation value on the lesion image and outputs it to the display device 4 for display, the reliability of the lesion candidate area in the current lesion image is displayed. Can intuitively grasp the sex.

  Further, according to the third embodiment of the present invention, the lesion candidate area detection unit 57 sequentially generates lesion image data based on the image data sequentially input from the endoscope 2, so that the lesion candidate to be reflected in real time. Inspection can be performed while checking the area.

  In the third embodiment of the present invention, the lesion candidate region detection unit 57 generates the lesion image P20 in which the lesion candidate region is emphasized with a rectangular frame. In this way, the lesion candidate area A1 may be highlighted.

(Other embodiments)
In the embodiment of the present invention, the image data and the lesion image data are transmitted to the image processing apparatus via the transmission cable. However, for example, the image data and the lesion image data are not necessarily wired and may be wireless. In this case, image data, lesion image data, and the like may be transmitted to the image processing device in accordance with a predetermined wireless communication standard (for example, Wi-Fi (registered trademark) or Bluetooth (registered trademark)). Wireless communication may be performed according to a communication standard.

  In the embodiment of the present invention, the processor and the light source are integrally formed. However, the present invention is not limited to this. For example, the processor and the light source may be configured as separate devices.

  In the embodiment of the present invention, a frame sequential endoscope has been described as an example, but a simultaneous endoscope can also be applied.

  In the embodiment of the present invention, the endoscope is inserted into the subject. However, the present invention can also be applied to, for example, a capsule endoscope or an imaging device that images the subject.

  In the description of the flowchart in the present specification, the context of each process is clearly indicated using expressions such as “first”, “subsequent”, and “follow”, but this is necessary to implement the present invention. The order of processing is not uniquely determined by their expression. That is, the order of processing in the flowcharts described in this specification can be changed within a consistent range.

  As described above, the present invention can include various embodiments not described herein, and various design changes can be made within the scope of the technical idea specified by the claims. It is.

1, 1a, 1b Endoscope system 2 Endoscope 3 Lesion detection device 4 Display device 5, 5a, 5b Image processing device 51 Acquisition unit 52 Image processing unit 52a First image processing unit 52b Second image processing unit 53 Frame memory 54 blur evaluation unit 55 synthesis unit 56 display control unit 57 lesion candidate region detection unit 541 blur calculation unit 542 blur determination unit A1 lesion candidate region A2 information P1 endoscopic image P2 lesion image R1, W2, W3 lesion candidate region W1 synthesized image

Claims (9)

An acquisition unit for acquiring image data obtained by imaging the body cavity of the subject;
A blur evaluation value for evaluating the degree of blurring of a lesion image corresponding to the lesion image data based on one of the image data and lesion image data in which information about a lesion candidate region is superimposed on the image corresponding to the image data A calculation unit for calculating
An output unit for superimposing the blur evaluation value on the lesion image and outputting it to the outside;
An image processing apparatus comprising: A first image processing unit that performs predetermined image processing on the image data;
The acquisition unit acquires, from the lesion detection device, two lesion image data that are temporally generated and generated by an external lesion detection device based on the image data subjected to the predetermined image processing,
The said calculation part calculates the said blur evaluation value based on the said lesion image corresponding to each of the two said lesion image data which the said acquisition part acquired before and behind in time. Image processing apparatus. A first image processing unit that performs predetermined image processing on the image data;
A lesion detection unit that generates the lesion image data by performing pattern matching using a lesion pattern on an image corresponding to the image data on which the first image processing unit has performed the predetermined image processing;
Further comprising
The image processing apparatus according to claim 1, wherein the calculation unit calculates the blur evaluation value based on each of the two pieces of image data that are temporally changed and subjected to the predetermined image processing. .   The image processing apparatus according to claim 3, wherein the lesion detection unit changes a lesion pattern used in the pattern matching based on the blur evaluation value. A determination unit that determines whether the blur evaluation value calculated by the calculation unit is equal to or greater than a predetermined threshold;
The output unit superimposes the blur evaluation value on the lesion image when the determination unit determines that the blur evaluation value is greater than or equal to the predetermined threshold. The image processing apparatus according to claim 1.   The said output part superimposes and outputs the information regarding the said blur evaluation value to the area | region of the said image corresponding to the said lesion candidate area | region in the said lesion image, The output of Claim 1 characterized by the above-mentioned. Image processing apparatus.   The image processing apparatus according to claim 1, further comprising a combining unit that combines the image corresponding to the image data and the lesion image to generate combined image data. An acquisition step of acquiring image data obtained by imaging the body cavity of the subject;
A blur evaluation value for evaluating the degree of blurring of a lesion image corresponding to the lesion image data based on one of the image data and lesion image data in which information about a lesion candidate region is superimposed on the image corresponding to the image data A calculating step for calculating
An output step of superimposing the blur evaluation value on the lesion image and outputting it to the outside;
An image processing method comprising: In the image processing device,
An acquisition step of acquiring image data obtained by imaging the body cavity of the subject;
Based on either the image data or the lesion image data in which the information related to the lesion candidate area is superimposed on the image corresponding to the image data, a blur evaluation value for evaluating the blur condition of the lesion image corresponding to the lesion image data is obtained. A calculating step for calculating;
An output step of superimposing the blur evaluation value on the lesion image and outputting it to the outside;
A program characterized by having executed.

Images