JP2022023564A - Information processing device, information processing method, and program - Google Patents

Abstract

To provide a technology to accurately associate pixels among images taken of a moving object.SOLUTION: An information processing device includes an image acquisition part for acquiring a first image and a second image by imaging a moving object at different timings, and an image processing part for executing positioning processing for the first image and the second image. The image processing part converts pixel values of the first image and/or the second image so that a difference between statistics of pixel values in the region of the object in the first image and statistics of pixel values in the region of the object in the second image becomes small, and on the basis of the converted pixel values, acquires the correspondence of the pixel values in the region of the object between the first image and the second image.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing apparatus, an information processing method, and a program.

In the medical field, a patient is imaged by a medical imaging device such as an X-ray CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, and a PET (Positron Emission Tomography) device. By observing the captured medical images in detail, information on the anatomical structures and functions of various types of organs in the patient's body is obtained, and the information is used for diagnosis and treatment.

Among the various types of organs that make up the human body, there are organs that move relative to the surrounding tissues. For example, the lungs move by breathing movements, and the heart moves to circulate blood in the body. Then, even if the organ is the same, the relative movement (direction of movement or movement) with respect to the surrounding tissue depends on the position in the organ or on the surface (hereinafter referred to as the position in the organ) depending on the structure, the presence or absence of a lesion, and the like. It is known that the amount) is different. Here, a user who wants to visualize the difference in the direction of movement and the amount of movement (hereinafter referred to as movement information) depending on the position of the target organ in the organ from the medical image (that is, visualize the distribution of the direction and amount of movement). There is a request from (doctors, etc.). This is to recognize the position in an organ with abnormal movement and to help detect diseases and lesions. For example, there is a desire to identify the position of adhesion with the pleura on the surface of the lung from a medical image by visualizing the movement information due to the respiratory movement of the lung at each position on the surface of the lung.

In Patent Document 1, the time-series three-dimensional images (volume data) of the lungs are aligned with each other, and the amount of slippage of the surface position due to respiratory movement, which is closely related to the adhesion of the pleura on the surface of the lungs. The technique for calculating the above is disclosed.

Japanese Unexamined Patent Publication No. 2016-67832

In medical images of moving organs taken at different timings, the density value (pixel value) of the organ may fluctuate for each image. The amount of air and blood contained in the tissue changes depending on the condition of the organ, and the contrast conditions (for example, the presence or absence of contrast medium and the difference in blood concentration of contrast medium) change over time. Is. Such fluctuations (differences) in density values are problematic because they can cause failure in alignment between images (that is, correspondence between pixels) and deterioration in accuracy. In particular, in the case of an algorithm that associates pixels between images based on the similarity of pixel density values, the problem becomes remarkable.

The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a technique for accurately associating pixels between images obtained by photographing a moving object.

In the present disclosure, an image acquisition unit that acquires a first image and a second image by photographing a moving object at different timings, and an alignment process between the first image and the second image. The image processing unit has an image processing unit for performing the above, and the image processing unit has a statistic of the pixel value of the region of the object in the first image and a pixel value of the region of the object in the second image. The pixel values of the first image and / or the second image are converted so that the difference from the statistics becomes small, and the first image and the second image are based on the converted pixel values. It includes an information processing apparatus characterized by acquiring the correspondence of pixels in the region of the object between images.

In the present disclosure, a step of acquiring a first image and a second image by photographing a moving object at different timings, and an alignment process of the first image and the second image are performed. And, in the alignment process, the statistic of the pixel value of the area of the object in the first image and the statistic of the pixel value of the area of the object in the second image. The pixel values of the first image and / or the second image are converted so that the difference is small, and based on the converted pixel values, between the first image and the second image. Includes an information processing method characterized by acquiring the correspondence of pixels in the region of the object.

The present disclosure includes a program for causing a computer to execute each step of the above information processing method.

According to the present invention, pixels can be associated with each other with high accuracy between images of moving objects.

It is a figure which shows the equipment structure of the information processing system which concerns on 1st Embodiment. It is a flow chart which shows the whole processing procedure in 1st Embodiment. It is a figure explaining 3DCT data of a subject. It is a flow chart which shows the whole processing procedure in 2nd Embodiment. It is a flow chart which shows the processing procedure of step S2040 of FIG. It is a flow chart which shows the whole processing procedure in 3rd Embodiment.

Hereinafter, preferred embodiments of the information processing apparatus disclosed in the present specification will be described in detail with reference to the accompanying drawings. However, the components described in this embodiment are merely examples, and the technical scope of the information processing apparatus disclosed in the present specification is determined by the scope of claims, and the following individual embodiments are made. It is not limited by the form. Further, the disclosure of the present specification is not limited to the following embodiments, and various modifications can be made based on the purpose of the disclosure of the present specification, and these may be excluded from the scope of the disclosure of the present specification. do not have. That is, all the configurations in which the examples described later and the modifications thereof are combined are included in the embodiments disclosed in the present specification.

In the present specification, the word "image" is used as a concept including both "two-dimensional image" and "three-dimensional image (also referred to as volume data)". Further, time-series data (a set of a plurality of two-dimensional images or a set of a plurality of three-dimensional images) composed of a plurality of images having different shooting times may be referred to as an "image". Further, the word "pixel" is used as a concept including both a minimum element constituting a two-dimensional image and a minimum element (also referred to as a voxel) constituting a three-dimensional image.

[First Embodiment]
The information processing system according to the first embodiment of the present invention provides a user such as a doctor or a technician in a medical institution with a function of supporting grasping and diagnosing the adhesion state of the pleura of a subject to be examined. Specifically, it provides a function of generating an observation image in which the slipping state of the pleura, which is a kind of feature amount related to the movement of the lung of the subject, can be easily visually recognized as the movement information of the lung. More specifically, the movement of the pleural portion (lung contour portion) of the lung of the subject is measured from the time-series 3DCT data (4DCT data, 4-dimensional CT image) of the lung of the subject exercising by breathing. Then, the slip state of the portion is visualized as a slip amount map. Note that "slip" is the relative movement between a moving object (lung, etc.) and its surrounding area, and the "slip amount map" is between the object area and the surrounding area (boundary). It is information showing the distribution of the amount of slip.

By the way, in time-series data obtained by photographing a moving object such as a lung at different timings, the density value (luminance value, pixel value) of the object may fluctuate between images. For example, in the case of the lungs, the concentration value in the lung field differs depending on the respiratory condition (mainly the ventilation volume) of the subject. Since the difference in the density value may lead to the failure of the alignment process between the images and the deterioration of the accuracy, in the present embodiment, the alignment process is performed after correcting the difference in the density value of the object between the images. Specifically, the pixel values of one or both images are converted (corrected) so that the difference in the statistic of the pixel values of the object region between the two images is small, and the converted pixel values are obtained. Based on this, the process of acquiring the correspondence between the pixels in the object region between the two images is performed. As a result, pixels can be associated with each other with high accuracy between images of moving objects.

FIG. 1 is a diagram showing an overall configuration of an information processing system according to an embodiment of the present invention. The information processing system includes an information processing device 10, an inspection image database 30, and an inspection image capturing device 40, and these devices are communicably connected to each other via a communication means. In the present embodiment, the communication means is configured by LAN (Local Area Network) 50, but may be WAN (Wide Area Network). Further, the connection method of the communication means may be a wired connection or a wireless connection.

The examination image database 30 holds a plurality of examination images related to a plurality of patients and their incidental information. The inspection image is, for example, a medical image taken by an image diagnostic device such as CT or MRI, and may be a two-dimensional image, a three-dimensional image, or a four-dimensional image which is a moving image of a three-dimensional image. In addition, each image can be an image of various modes such as monochrome and color. The examination image database 30 in the present embodiment holds 4DCT data obtained by photographing the lungs of a subject. The inspection image database 30 holds the patient name (patient ID), the inspection date information (date when the inspection image was taken), the shooting modality name of the inspection image, and the like as incidental information of the inspection image. Further, each inspection image and its incidental information are assigned a unique number (inspection image ID) so as to be able to be distinguished from the others, and the information processing device 10 can read out the information based on the unique number (inspection image ID).

The information processing apparatus 10 acquires the information held by the inspection image database 30 via the LAN 50. The inspection image acquisition unit 100 acquires an inspection image of a subject taken by the inspection image photographing apparatus 40 and held by the inspection image database 30. The region extraction unit 110 analyzes the inspection image acquired by the inspection image acquisition unit 100 and extracts the lung region of the subject. The mean density value calculation unit 120 is based on the inspection image acquired by the inspection image acquisition unit 100 and the lung region of the subject extracted by the region extraction unit 110, and the density value (pixel value) of the inspection image in the lung region of the subject. ) Is calculated as a statistic. The density value correction unit 130 corrects the density value of the inspection image acquired by the inspection image acquisition unit 100 based on the average value of the density values of the lung region of the subject calculated by the average density value calculation unit 120. calculate. The displacement field calculation unit 140 calculates the displacement field due to the respiration of the subject based on the inspection image acquired by the inspection image acquisition unit 100 and the correction image calculated by the density value correction unit 130. The map generation unit 150 generates a map of the amount of slippage of the lung contour due to the respiration of the subject based on the lung region of the subject calculated by the region extraction unit 110 and the displacement field of the subject calculated by the displacement field calculation unit 140. do. The display control unit 160 controls the display device 60 to display the slip amount map calculated by the map generation unit 150. In the present embodiment, the inspection image acquisition unit 100 constitutes an image acquisition unit that acquires an image of an object. Further, the area extraction unit 110, the average density value calculation unit 120, the density value correction unit 130, the displacement field calculation unit 140, and the map generation unit 150 constitute an image processing unit that performs image alignment processing and the like.

The information processing device 10 can be configured by a computer including a processor (CPU, GPU, etc.), a memory (RAM, ROM, etc.), a storage (HDD, SSD, etc.), a communication IF, an input / output IF, and the like. In that case, the functions of each part shown in FIG. 1 are realized by the processor reading and executing the program stored in the storage. The configuration of the information processing system shown in FIG. 1 is merely an example. For example, the information processing apparatus 10 may have a storage unit (not shown) and may have the function of the inspection image database 30. Further, the information processing apparatus 10 may be configured by a general-purpose computer (personal computer, server computer, etc.) or a dedicated computer. Further, the information processing system of FIG. 1 may be realized by implementing a function required for a computer (also referred to as a console) provided in an imaging system such as a CT device or an MRI device.

Next, with reference to FIG. 2, the entire processing procedure by the information processing apparatus 10 in the present embodiment will be described in detail. Further, in the following, as an example, a case where time-series 3DCT data (4DCT data, 4-dimensional CT image) is used as an inspection image will be described as an example, but the implementation of the present invention is not limited to this. It may be a plurality of images obtained by shooting moving objects at different timings. For example, a plurality of three-dimensional images (volume data) in which the lungs of a subject are photographed in different respiratory phases do not have to be time-series images (moving images) captured in one examination. Further, the image may be an MRI image or an ultrasonic image instead of the CT image.

(Step S1000): Acquisition of 4DCT data In step S1000, the inspection image acquisition unit 100 acquires 4DCT data obtained by photographing the lungs of the subject from the inspection image database 30. The 4DCT data in the present embodiment is time-series three-dimensional volume data, and is data obtained by photographing the dynamics of the subject due to respiration. More specifically, 4DCT data composed of a plurality of 3DCT data having two or more phase phases including the inspiratory position (for example, the maximum inspiratory position) and the expiratory position (for example, the maximum expiratory position) of the subject is acquired. In this embodiment, as a specific example, a case of acquiring 3DCT data of 3 time phase will be described as an example. Here, the 3DCT data of each time phase is expressed as I_t (1 ≦ t ≦ 3). Further, in the description of the present embodiment, each 3DCT data is described as a function that takes I_t (x, y, z) and a position in the image as arguments and returns the pixel value at the position. Further, in the present embodiment, the case where the 3DCT data of the inspiratory position is I_1, the 3DCT data of the expiratory position is I_3, and the 3DCT data of the intermediate time phase is I_2 will be described as an example.

3A to 3C are diagrams conceptually showing 3DCT data of the three-time phase acquired by the inspection image acquisition unit 100 in the present embodiment. The image 200 of FIG. 3A is an image of the coronal cross section of the 3DCT data I_1, and the contour 204 of the lung field 202, which is the target site, is drawn. Image 210 in FIG. 3B is an image of the coronal cross section of 3DCT data I_2, and image 220 in FIG. 3C is an image of the coronal cross section of 3DCT data I_3. In the lung fields 202, 212, and 222 of each image, the density value of the image differs depending on the difference in the respiratory state of the subject at the time when each image is taken. In FIGS. 3A to 3C, it is assumed that the closer to white, the higher the density value. That is, the concentration value of the lung field 222 of the expiratory position 3DCT data I_3 is higher than that of the lung field 202 of the inspiratory position 3DCT data I_1. Further, the lung field 212 of the 3DCT data I_2, which is the respiratory state during that period, is a value between the concentration values of the lung field 202 and the lung field 222.

In the present embodiment, the case of using the 3D CT data of the 3rd phase including the 2nd phase of the inspiratory position and the expiratory position as described above will be described as an example, but the embodiment of the present invention is not limited to this. If the movement of the lung field due to the respiration of the subject is captured, 3DCT data of the time phase of other respiration states may be used. Here, the image may be taken at a cycle sufficiently earlier than the respiratory cycle, and an image of a desired respiratory phase may be extracted as a processing target image from the obtained plurality of images. Further, the operation by the user may be accepted and the image to be processed may be selected accordingly. Alternatively, imaging may be performed at the timing of the desired respiratory phase in synchronization with the patient's respiration. Further, when acquiring a time-series image taken by another modality such as an MRI or an ultrasonic image, it can be an embodiment of the present invention.

(Step S1010): Extraction of lung field region In step S1010, the region extraction unit 110 executes a process of extracting the lung field region for each of the plurality of 3DCT data acquired in step S1000. The process of extracting the region of the lung field from the 3DCT data can be realized by using a known image processing method. For example, a method of applying arbitrary threshold processing to the pixel value may be used, or a known segmentation method such as a graph cut method may be used. Further, a segmentation (semantic segmentation) method using a neural network such as Deep Learning may be used. Further, the lung region may be manually extracted by the user using drawing software (not shown), or the lung region extracted by a known image processing method may be manually modified by the user. In the present embodiment, the lung field region is extracted from the 3DCT data of all the time phases acquired in step S1000 by using a method of applying arbitrary threshold processing to the pixel values. Specifically, after binarizing all the pixels in the 3DCT data depending on whether the pixel value is within the predetermined threshold range, post-processing such as isolated point removal and smoothing is performed to extract the lung field region. do. Then, the extraction result of the lung field region of each time phase is calculated as a mask image M_t (1 ≦ t ≦ 3). The mask image M_t is information representing the lung field region with respect to each of I_t (1 ≦ t ≦ 3) of the 3DCT data, and the pixel value is 1 when the corresponding position of the 3DCT data is the lung field, and other than that. In this case, the pixel value is 0. In the description of the present embodiment, the mask image M_t has M_t (x, y, z) and the pixel position in the image as arguments, and the pixel value at the position, that is, whether or not the position is the region of the lung field. It is also expressed as a function that returns the value of. In the present embodiment, M_t is retained as volume data that is discretized to the same extent as 3DCT data I_t.

In the above description, the case where the mask image is calculated as the extraction result of the lung field region of the 3DCT data has been described as an example, but the implementation of the present invention is not limited to this. For example, a set of pixels in the lung field may be calculated, or the coordinate values of the contour positions surrounding them may be calculated.

(Step S1020): Average concentration value calculation In step S1020, the average concentration value calculation unit 120 calculates the average concentration value in the region in the lung field extracted in step S1010 for each of the plurality of 3DCT data acquired in step S1000. To execute. Specifically, the operation shown in the equation (1) is executed for each of the plurality of 3DCT data. In the formula (1), Ω represents the entire image (all pixels) of the 3DCT data. C_ave_t is an average concentration value of 3DCT data I_t.

In the above processing, the case where the average concentration value is calculated as the statistic of the pixels in the lung field of the 3DCT data of each time phase has been described as an example, but the statistic is not limited to the average density value and the pixel group in the lung field. Any representative value obtained or calculated from the pixel value of the above may be used. For example, the mode, median, maximum value, minimum value, etc. of the pixels in the lung field of the 3DCT data of each time phase may be calculated. Further, not only when these values are calculated only from the region in the lung field, the average concentration value of the entire 3DCT data of each time phase may be calculated. Conversely, the statistic of some pixels may be calculated instead of the statistic of all pixels in the lung field.

(Step S1030): Concentration value correction In step S1030, the concentration value correction unit 130 concentrates each of the plurality of 3DCT data acquired in step S1000 based on the average concentration value in the lung field in each 3DCT data acquired in step S1020. Executes the process of correcting (converting) the value. More specifically, each time phase so that the average concentration value in the lung field of all 3DCT data is the same as the average concentration value in the lung field of the 3DCT data of the reference time phase (for example, the inspiratory position). The correction process shown in the equation (2) is performed on the density value of the entire 3DCT data of. In the formula (2), C_ave_1 is the average concentration value of the reference time phase (for example, the inspiratory position), C_ave_t is the average concentration value of the 3DCT data I_t before correction, and I'_t is the 3DCT data after correction. ..

By the processing of the formula (2), the pixel between the lung field region (first object region) in I_t (first image) and the lung field region (second object region) in I_1 (second image). The pixel values of I_t are converted so that the difference in the value statistics is small. This converted image I'_t is used for alignment of pixels in the lung field region between images (acquisition of pixel correspondence).

The 3DCT data of the time phase (intake position) as a reference can be set to I'_1 = I_1 without processing the equation (2). Further, in the above description, the case of correcting the density value of the entire 3DCT data of each time phase has been described as an example, but the implementation of the present invention is not limited to this. For example, only the pixels in the lung field of the 3DCT data of each time phase may be corrected by the same method as described above. Further, the reference time phase does not have to be the intake position.

In the above description, a reference time phase is provided so that the average concentration value in the lung field of the 3DCT data of each time phase is the same as the average concentration value in the lung field of the 3DCT data of the reference time phase. Although the case of performing correction has been described as an example, the implementation of the present invention is not limited to this. For example, without setting a reference time phase, the 3DCT data of all time phases are corrected so that the average concentration value in the lung field of the 3DCT data of each time phase is aligned with the predetermined reference concentration value Cref set in advance. Is also good. In that case, the reference concentration value Cref may be substituted for C_ave_1 in the equation (2).

(Step S1040): Alignment between images in the lung field In step S1040, the displacement field calculation unit 140 determines the 3DCT of the inspiratory position based on the plurality of 3DCT data I'_t (1 ≦ t ≦ 3) after the concentration value correction. Alignment processing in the lung field between data I_1 and 3DCT data I_3 of the expiratory position is performed. In the present embodiment, the alignment between I'_1 and I'_2 and the alignment between I'_2 and I'_3 are performed respectively, and the results are integrated to form I'_1 and I'_3. Get the alignment result between. In this way, instead of directly calculating the alignment between the image of the inspiratory position and the image of the expiratory position, the indirect calculation using the image of the intermediate state (time phase) is the accuracy of the alignment. It is advantageous for improvement. That is, since the amount of movement (difference in position) of the lungs is large between the inspiratory position and the expiratory position, it is difficult to grasp the correspondence relationship between the pixels, and the possibility that the search for the corresponding pixel fails increases. In that respect, by sandwiching the images in the intermediate state between the images, the alignment process is performed between the images having a relatively small movement amount (difference in position), so that the alignment can be facilitated and the accuracy can be improved. Although the alignment becomes easier as the number of images in the intermediate state is increased, the processing time is conversely increased. Therefore, it is advisable to determine the number of images in the intermediate state in consideration of the balance between accuracy and processing time. ..

As a result of the alignment process, the displacement field calculation unit 140 acquires the displacement field D_inner (x, y, z). Any known method may be used as a method for integrating a plurality of displacement fields. D_inner (x, y, z) is an arbitrary three-dimensional position (x, y, z) in the lung field in the 3DCT data I_1 of the inspiratory position, and a three-dimensional position (x') in the corresponding 3DCT data I_3 of the expiratory position. , Y', z') is a function to calculate the amount of displacement for conversion. That is, the displacement field D_inner (x, y, z) represents the correspondence between the pixels in the object region (lung field region) between the two images.

It should be noted that the above-mentioned alignment between I'_1 and I'_2 and the alignment between I'_2 and I'_3 can be performed by using any known image-to-image alignment method. good. There are various alignment methods between two images, such as a method of associating pixels based on the similarity of pixel values (density values), and a method of associating areas based on edges and textures. There is a method. In the present embodiment, a method of associating pixels based on the similarity of pixel values (density values) is adopted. This is because high-speed processing is possible. For example, when aligning the first image and the second image, the lung field region of the first image is deformed, and the pixels between the second image and the first image after the deformation are deformed. The process of evaluating the similarity of the values (concentration values) may be repeated to find the optimum solution having the highest similarity. In this method, the deformation of the three-dimensional region can be expressed by using, for example, FFD (Free Form Deformation), and the similarity of the pixel values (density values) may be evaluated by SSD (Sum of Square Difference) or the like.

When performing this alignment, it is desirable to apply image processing to each image to emphasize the image features in the lung field to be visualized, and to perform alignment using the result. For example, the window conversion may be performed so as to emphasize the difference in the concentration values of air and parenchyma contained in the lung field, that is, the image features in the lung field. The window conversion is a process of extracting only a part of the range of the original image and converting it into a predetermined density resolution. By changing the center (window level) and width (window width) of the range to be extracted (called a window), a desired image feature in the original image can be emphasized. It is used in a scene where an image for display (for example, an 8-bit image) is generated from a wide range of images (for example, a 10 to 16-bit image) such as a medical image.

For example, in the case of general CT data in which air is -1000 and water is 0, the image features in the lung field can be emphasized by setting the density value at the center of the window to -700 and the window width to 1000. .. In the present embodiment, by performing such window conversion, an image in which the image features in the lung field are emphasized is generated, and the alignment process is performed on the image. This makes it possible to improve the accuracy of alignment in the lung field.

The window conversion setting may be set by the information processing apparatus 10 in advance, or may be set by an operation by the user. Further, the setting may be made based on the 3DCT data acquired in step S1000 and the incidental information held by the inspection image database 30.

In the above description, a case where the density value of each 3DCT data is corrected in step S1030 and the window conversion is performed in step S1040 has been described as an example, but a process in which these processes are integrated is executed in step S1040. You may do so. That is, the process of step S1030 can be omitted, and the window center of the window conversion executed in step S1040 can be changed and set for each of the 3DCT data. Specifically, based on C_ave_t (1 ≦ t ≦ 3), the window center can be set so that the concentration values in the lung field of each 3DCT data are the same.

(Step S1050): Alignment between images outside the lung field In step S1050, the displacement field calculation unit 140 is based on the plurality of 3DCT data I_t (1 ≦ t ≦ 3) acquired in step S1000, and the 3DCT data I_1 of the inspiratory position. And the 3DCT data I_3 of the expiratory position, the alignment process outside the lung field is performed. The outside of the lung is the area around the lung field (object area). In the present embodiment, the alignment between I_1 and I_2 and the alignment between I_1 and I_3 are performed respectively, and the results are integrated to obtain the alignment result between I_1 and I_3. Since the specific processing method is the same as the method described in step S1040, detailed description thereof will be omitted here. Since the change in the concentration value due to respiration is small for the pixels outside the lung field, it is preferable to use the 3DCT data before converting the pixel value.

Through the above processing, the displacement field calculation unit 140 acquires the displacement field D_outer (x, y, z). D_outer (x, y, z) is an arbitrary three-dimensional position (x, y, z) outside the lung field of the subject in 3DCT data I_1 of the inspiratory position, and a three-dimensional position in 3DCT data I_3 of the corresponding expiratory position. It is a function to calculate the displacement amount to be converted into (x', y', z'). That is, the displacement field D_outer (x, y, z) represents the correspondence between the pixels in the peripheral region between the two images.

The above-mentioned alignment between I_1 and I_2 and the alignment between I_1 and I_3 may be performed by any known image-to-image alignment method. The same method as exemplified in the alignment process of the lung field region may be used. When performing this alignment, it is desirable to perform image processing that emphasizes the image features of the lung field depicted in each image, and to perform alignment using the result. For example, the window conversion may be performed so that the difference in the density value of the tissue around the lung field, that is, the image feature outside the lung field is emphasized. By setting the density value at the center of the window to 0 and the window width to 400 or the like, the image features of the soft tissue outside the lung field can be emphasized. In addition to this, by setting the density value at the center of the window to 200, the window width to 2000, and the like, the image features of the bone outside the lung field can be emphasized. In the present embodiment, an image in which the image features outside the lung field are emphasized is generated by performing the window conversion exemplified above, and the alignment process is performed on the image.

The window conversion setting may be set by the information processing apparatus 10 in advance, or may be set by an operation by the user. Further, the setting may be made based on the 3DCT data acquired in step S1000 and the incidental information held by the inspection image database 30.

In the above description, an example is used in which an image emphasizing the image features outside the lung field is generated based on the 3DCT data I_t (1 ≦ t ≦ 3) and the displacement field D_outer (x, y, z) is calculated. However, the implementation of the present invention is not limited to this. For example, as in step S1040, based on the 3DCT data I'_t (1 ≦ t ≦ 3) after the concentration value conversion, an image emphasizing the image features of the lung field is generated, and the displacement field D_outer (x, y, z) is generated. ) May be calculated.

(Step S1060): Calculation of slip amount map In step S1060, the map generation unit 150 executes a process of generating a map of the slip amount due to breathing on the lung surface (lung contour) of the subject. In this process, the lung field mask image M_1 of the inspiratory position calculated in step S1010, the displacement field D_inner (x, y, z) calculated in step S1040, and the displacement field D_outer (x, y, z) calculated in step S1050 are performed. ) Is executed. More specifically, it can be carried out by the method described in Patent Document 1. That is, D_out in the contour portion of the lung field mask image M_1
The difference between the two displacement fields of er (x, y, z) and D_inner (x, y, z) is calculated, and it is generated as a slip amount map S (x, y, z) which is a three-dimensional map. .. In the present embodiment, the slip amount map S (x, y, z) is a function that returns the slip amount at the position of the intake position 3DCT data in the image coordinate system as an argument. More specifically, it is retained as volume data that is discretized to the same extent as 3DCT data. The map generation unit 150 stores the generated slip amount map S (x, y, z) in a storage unit (not shown) or an inspection image database 30 in association with the inspection image of the subject, if necessary. Perform the processing.

(Step S1070): Display of the slip amount map In step S1070, the display control unit 160 controls the display device 60 to display the slip amount map S (x, y, z) calculated in step S1060. Specifically, an image (observation image) for observing the slip amount map is generated, and control is performed so that the image is displayed on the display device 60. The observation image can be generated, for example, as a surface-rendered image in which the slip amount map is gradation-converted by a gray scale, a color map, or the like on the three-dimensional lung field contour shape of the subject. The above method is only an example of the present invention, and can be an embodiment of the present invention regardless of how the slip amount map is displayed or the display itself is not performed.

By the method described above, the processing of the information processing apparatus 10 in the present embodiment is executed. According to this, since the alignment between 3DCT data having different respiratory states can be performed with high accuracy, it is possible to provide the user with an effective slip amount map for grasping the adhesion state of the pleura of the subject and supporting the diagnosis.

(Deformation Example 1-1): Deformation Example in which the density value correction due to the volume change is further added In the description of step S1040 of the first embodiment, the alignment in the lung field is executed using the image I'_t after the pixel value conversion. Although a specific example of the above has been described, the implementation of the present invention is not limited to this. For example, after executing the process of S1040 described in the first embodiment, it is possible to execute a process of further modifying the displacement field D_inner (x, y, z) which is the process result. For example, the local volume change in the lung field is calculated based on the displacement field D_inner (x, y, z) calculated by the above processing, and the pixel value of each position in the lung field is further corrected based on the calculation. Specifically, the concentration value of the portion where the volume expands locally can be lowered, and conversely, the concentration value of the portion where the volume contracts locally can be increased. Then, the displacement field D_inner (x, y, z) may be corrected by further performing the alignment process based on the corrected image. Further, based on the displacement field corrected by this process, the same process as described above may be repeated to correct the displacement field. According to this, in addition to the alignment in the lung field described in the first embodiment, it is possible to estimate the local volume change in the lung field region of the subject and correct the concentration value based on the estimation. It has the effect of enabling more accurate alignment.

(Variation Example 1-2): Variation of Pixel Value Correction Method In the first embodiment of the present invention, the average concentration value of each lung field of a plurality of 3DCT data is calculated in step S1020, and the difference is calculated in step S1030. The case where the correction for shifting the density value of each image is performed so as to absorb the image has been described as an example. However, the implementation of the present invention is not limited to this. For example, in step S1020, for each 3DCT data, the variance C_div_t of the concentration value can be calculated in addition to the average concentration value C_ave_t of the lung field. In this case, in step S1030, the concentration values are corrected by linear conversion (shift and scaling) so that the average concentration values and the variances of the concentration values in the lung field of all 3DCT data are the same as those in the inspiratory position. You may try to do it. A linear conversion for matching the mean value and the dispersion value with the desired values can be performed by a known method. According to the above method, not only the average concentration value but also the variance of the concentration value can be matched with the 3DCT data of the intake position for the 3DCT data of each time phase, so that the 3DCT data of each time phase is closer to the 3DCT data of the intake position. It can be corrected to an image. This has the effect of more accurately performing alignment within the lung field.

Further, the method of correcting the density value is not limited to the above method. For example, for each 3DCT data, the concentration value representing the air region (-1000 in the case of general CT data) is set while matching the average concentration value in the lung field with the average concentration value in the lung field of the 3DCT data at the inspiratory position. The density value may be linearly converted so as not to change.

The implementation of the present invention is not limited to the case where the density value is corrected by a uniform linear transformation for the region to be corrected as described above. For example, the mixing ratio of the air / tissue parenchyma of the pixel may be estimated based on the concentration value of each pixel in the lung field, and the magnitude of the correction of the concentration value may be changed according to the air content ratio. This has the effect of making corrections that reflect changes in local ventilation volume associated with respiration in the lungs of the actual subject.

In addition to the above method, the concentration value may be corrected based on the difference in the volume of the lung field region of each 3DCT data calculated in step S1010. For example, the larger the difference between the volume of the lung field in the 3DCT data of the inspiratory position and the volume of the lung field of the 3DCT data to be corrected, the larger the correction amount of the concentration value can be made. According to this method, more accurate concentration value correction reflects the phenomenon that the content ratio of parenchymal tissue in the lung field increases as the volume decreases due to the exhaustion of air from the lung field of the subject by respiration. Has the effect of being able to do. Further, the method for correcting the density value is not limited to the above method. For example, the lung field may be further divided into a plurality of partial regions, and different corrections may be made for each of the divided partial regions. For example, even if each of the plurality of lung lobes constituting the lung is divided into partial regions, the average concentration value is calculated for each lobe, and the concentration value of the integrated lung field is corrected based on the average value. good. Alternatively, each of the left and right lungs may be divided into partial regions to perform the same correction as described above. According to this, there is an effect that highly accurate correction can be performed in consideration of the difference in the ventilation volume for each lung lobe and each left and right lungs.

(Variation Example 1-3): In the case of 2 phase phase or in the case of 4 phase phase or more In the first embodiment of the present invention, the case of acquiring 3 DCT data of 3 phase phase in step S1000 has been described as an example. The implementation of the present invention is not limited to this. For example, in step S1000, only the 3DCT data of the two time phases of the inspiratory position and the expiratory position may be acquired. In this case, in the process of step S1030, the concentration values of the 3DCT data of the inspiratory position and the expiratory position are corrected. Then, in step S1040, the displacement field in the lung field between the inspiratory position and the expiratory position is calculated by aligning the images. Further, in step S1050, the displacement field outside the lung field is calculated by the alignment between the 2 time phase 3DCT data acquired in step 1000. By the method described above, the process when the 2nd phase 3DCT data is input is carried out.

Further, the implementation of the present invention is not limited to the above method, and 3DCT data of 4 o'clock phase or higher may be acquired in step S1000. Even in this case, the slip amount map of the subject can be calculated by the same processing as in the first embodiment.

[Second Embodiment]
A second embodiment of the present invention will be described. In the first embodiment, a case where an image in which the density value is corrected is generated and the alignment process in the lung field is executed using the image has been described as an example. However, the implementation of the present invention is not limited to this. In the second embodiment, a case where the density value is corrected in pixel units in the alignment process in the lung field is described as an example, instead of generating the image in which the density value is corrected.

The overall configuration of the information processing system according to the second embodiment of the present invention is the same as that shown in FIG. 1 as an explanation of the overall configuration of the information processing system of the first embodiment. A detailed description will be omitted here.

The entire processing procedure by the information processing apparatus 10 in the present embodiment will be described in detail with reference to FIG.

From (Step S2000) to (Step S2020)
Steps S2000 to S2020 perform the same processing as steps S1000 to S1020 of the first embodiment. A detailed description will be omitted here.

(Step S2040)
In step S2040, the displacement field calculation unit 140 is a lung between the inspiratory 3DCT data I_1 and the expiratory 3DCT data I_3 based on the plurality of 3DCT data I_t (1 ≦ t ≦ 3) acquired in step S2000. Executes Nouchi's alignment process. In the present embodiment, the alignment between I_1 and I_1 and the alignment between I_1 and I_3 are performed respectively, and the results are integrated to obtain the alignment result between I_1 and I_3. As a result of the above processing, the displacement field calculation unit 140 acquires the displacement field D_inner (x, y, z). Any known method may be used as a method for integrating a plurality of displacement fields. Here, D_inner (x, y, z) sets an arbitrary three-dimensional position (x, y, z) in the lung field of the subject in the 3DCT data I_1 of the inspiratory position in the corresponding 3DCT data I_3 of the expiratory position. It is a coordinate conversion function that converts to a three-dimensional position (x', y', z').

In this embodiment, a case where the above-mentioned alignment process between I_1 and I_1 and the alignment process between I_1 and I_3 are performed by using the FFD (Free Form Deformation) method will be described as an example. However, the implementation of the present invention is not limited to this, for example, LDDMM (lage deformation diffusion metric matrix).
Other deformation alignment methods such as the mapping) method may be used.

This process will be described in detail along with the process flow of FIG. In the following description, an example of calculating the displacement field D_inner12 (x, y, z) as the alignment result between I_1 and I_1 will be described. The alignment process between I_2 and I_3 executed in step S2040 can also be executed in the same manner as the process described in detail below.

(Step S20400): Initialization In step S20400, the displacement field calculation unit 140 executes a process of initializing the displacement field D_inner12 (x, y, z). Specifically, the control quantities of all control points of the FFD are initialized to zero vectors. In this embodiment, a case where the number of control points of the FFD is N and a three-dimensional control amount parameter is set for each control point will be described as an example. That is, a case where the displacement field is expressed by 3N control quantity parameters as a whole will be described as an example. In this embodiment, the control amount parameter is expressed as V. Here, V is 3N-dimensional vector format data that stores the control amount of FFD. Further, in this step, the displacement field calculation unit 140 executes a process of calculating the image similarity between I_1 and I_2. Any known method may be used for calculating the image similarity, but in the present embodiment, the image similarity E_org is calculated by the SSD (Sum of Square Difference) represented by the formula (3) as an example.

In the formula (3), the portion of "+ C_ave_1-C_ave_2" is a concentration value correction term for aligning the concentration values between the 3DCT data I_1 and I_2. As described above, in the alignment process of the present embodiment, the density value correction for each pixel is performed at the same time in the calculation for calculating the similarity between the images. W is a function of image window conversion. In the present embodiment, in order to emphasize the image features in the lung field and calculate the image similarity, the difference in the concentration values of air and parenchymal tissue contained in the lung field, that is, the window transformation in which the image features in the lung field are emphasized. I do. As an example, conversion is performed when the density value at the center of the window is -700 and the window width is 1000.

Hereinafter, the processes from step S20401 to step S20405 are repeatedly executed.

(Step S20401): Initialization of control point index i In step S20401, the displacement field calculation unit 140 initializes the index value i of the control point to be processed from step S20403 to step S20404 to 1.

(Step S20403): Calculation of similarity after change in control amount In step S20403, the displacement field calculation unit 140 calculates a displacement field when the control amount of the control point of the index i is slightly changed. Then, the image similarity between I_1 and I_2 is calculated based on the calculated displacement field.

Specifically, first, the controlled variable parameter V'_i after the fluctuation is generated by slightly varying the element value of the i-th dimension of the controlled variable parameter V. Here, a variation that increases the parameter value by δ is given.

Next, the displacement field calculation unit 140 calculates the displacement field D_inner12_i (x, y, z) based on the controlled variable parameter V'_i that gives the variation. Since this process is the same as the known method using the FFD method, detailed description thereof will be omitted.

Further, the displacement field calculation unit 140 calculates the degree of similarity with I_1 when the 3DCT data I_2 is deformed based on the displacement field D_inner12_i (x, y, z) calculated by the above method. Specifically, the image similarity E_i is calculated by the process of the equation (4).

Note that dx_i represents the amount of displacement of D_inner12_i (x, y, z) in the x-axis direction. Similarly, dy_i represents the amount of displacement in the y-axis direction, and dz_i represents the amount of displacement in the z-axis direction. The effect of the density value correction term and the window conversion is the same as that described in the equation (3).

By the above processing, the image similarity E_i when the i-th control amount parameter is changed is calculated.

(Step S20404): Index Increment In step S20404, the displacement field calculation unit 140 executes a process of incrementing the index value i of the control amount parameter.

(Step S20405): Judgment (i> 3N)
In step S20405, the displacement field calculation unit 140 determines whether or not the index value i of the control quantity parameter exceeds the total number of control quantity parameters 3N. If it exceeds, the process proceeds to step S20406, and if not, the process returns to step S20403.

By the processing from step S2403 to step S20405 described above, the image similarity E_i (1 ≦ i ≦ 3N) when the element values of all the dimensions of the control amount parameter V are changed can be obtained.

(Step S20406): Displacement field update In step S20406, the displacement field calculation unit 140 performs a process of updating the displacement field D_inner12 (x, y, z) based on the image similarity E_org and E_i (1 ≦ i ≦ 3N). Execute. Specifically, a process of updating the controlled variable parameter V based on the image similarity E_org and E_i (1 ≦ i ≦ 3N) and updating the displacement field D_inner12 (x, y, z) is executed.

The update of the control amount parameter V based on the image similarity E_org and E_i (1 ≦ i ≦ 3N) can be performed by, for example, the steepest descent method. That is, the fluctuation amount E_i-E_org of the image similarity with respect to the fluctuation of the value of each of the 3N elements constituting the control quantity parameter V is obtained, and the value of each element of the control quantity parameter V is corrected in proportion to the magnitude thereof. .. Then, D_inner12 (x, y, z) is updated based on the corrected controlled variable parameter V.

(Step S20407): Displacement field update similarity calculation In step S20407, the displacement field calculation unit 140 between I_1 and I_1 based on the displacement field D_inner12 (x, y, z) modified in step S20406. The image similarity is calculated and the process of updating E_org is executed. The calculation method of the image similarity is the same as the calculation method shown in the equation (3), and detailed description thereof will be omitted.

(Step S20408): Convergence determination In step S20408, the displacement field calculation unit 140 determines whether or not to end the process of step S2040 based on the similarity calculated in step S20407. Specifically, if the image similarity E_org is larger than a predetermined threshold value, the process of step S2040 is terminated, and if not, the process is returned to step S20401.

The process of step S2040 is executed by the process of steps S20408 to S20408 described above.

Next, the information processing apparatus 10 executes the same processing as in steps S1050 to S1070 of the first embodiment as the processing from step S2050 to step S2070. Detailed explanation will be omitted.

By the above processing, the processing according to the second embodiment of the present invention is executed. According to this method, it is not necessary to generate the image I'_t after the density value correction and hold it in a memory (not shown) as compared with the first embodiment, so that there is an effect that the alignment process can be performed more efficiently. be.

(Modification 2-1)
In the description of the present embodiment, as an example of the method of calculating the image similarity E_org in step S20400, as shown in the equation (3), the pixel value of I_1 and the pixel value of I_2 after the density value correction are converted into the same window. The case of converting with the function W has been described as an example. However, the implementation of the present invention is not limited to this. For example, as shown in the equation (5), the pixel value of I_1 and the pixel value of I_2 may be converted by using different window conversion functions. For example, the window center of the window conversion function W_1 for I_1 may be set to C_ave_1, and the window center of the window conversion function W_1 for I_1 may be set to C_ave_1, respectively. Further, the window width of W_1 may be set based on the dispersion of the concentration value inside the lung field of I_1, and the window width of W_1 may be set based on the dispersion of the concentration value inside the lung field of I_1.

Further, in step S20403, the case where the calculation shown in the equation (4) is performed as an example of the calculation method of the image similarity E_i has been described as an example, but the equation using the window conversion functions W_1 and W_2 (as in the equation (5)) E_i may be calculated by the calculation of 6).

According to the method described above, since the window conversion is performed for each of I_1 and I_2 according to the difference in the distribution of the concentration values inside the lung field, more accurate alignment can be performed as the process of step S2040. effective.

[Third Embodiment]
A third embodiment of the present invention will be described. This embodiment is different from the first embodiment in which the lung slip amount map of the subject is generated as the lung movement information, and the lung movement amount map of the subject is generated as the lung movement information.

The overall configuration of the information processing system according to the present embodiment is the same as that shown in FIG. 1 as an explanation of the overall configuration of the information processing system of the first embodiment. A detailed description will be omitted here.

The entire processing procedure by the information processing apparatus 10 in the present embodiment will be described in detail with reference to FIG.

From (Step S3000) to (Step S3040)
In steps S3000 to S3040, the information processing apparatus 10 executes the same processing as in steps S1000 to S1040 executed by the information processing apparatus of the first embodiment. A detailed description will be omitted here.

(Step S3060)
In step S3060, the map generation unit 150 executes a process of generating a map of the amount of movement due to breathing on the lung surface (lung contour) of the subject. This process is executed based on the lung field mask image M_1 of the inspiratory position calculated in step S3010 and the displacement field D_inner (x, y, z) calculated in step S3040. More specifically, the displacement amount of the displacement field D_inner (x, y, z) in the contour portion of the lung field mask image M_1 is calculated, and the displacement amount map S (x, y, z) which is a three-dimensional map is calculated. ). In the present embodiment, the motion amount map S (x, y, z) is a function that returns the motion amount at the position of the intake position 3DCT data in the image coordinate system as an argument. More specifically, it is retained as volume data that is discretized to the same extent as 3DCT data. This movement amount map S (x, y, z) represents the distribution of lung movement amount between two time phases (states). The map generation unit 150 stores the generated motion amount map S (x, y, z) in a storage unit (not shown) or an inspection image database 30 in association with the inspection image of the subject, if necessary. Perform the processing.

(Step S3070)
In step S3070, the display control unit 160 controls the display device 60 to display the motion amount map S (x, y, z) calculated in step S3060. The specific control method can be performed in the same manner as the display control of the slip amount map described in step S1070 of the first embodiment. Detailed explanation will be omitted.

The processing of the information processing apparatus 10 of the present embodiment is executed by the method described above. According to this, since the alignment between 3DCT data having different respiratory states can be performed with high accuracy, it is possible to provide the user with a movement amount map effective for grasping the adhesion state of the pleura of the subject and supporting the diagnosis.

(Modification 3-1)
In the description of the present embodiment, the case where the motion amount map is generated in step S3060 has been described as an example, but the embodiment of the present invention is not limited to this. For example, the ventilation volume map of the lung may be calculated as the process of step S3060. In this case, the magnitude of the change in volume at each position in the lung field may be visualized based on the displacement field D_inner (x, y, z) in the lung field calculated in step S3040. For example, in this implementation of calculating the displacement field D_inner (x, y, z) representing the displacement from the inspiratory position to the expiratory position, the displacement amount in the lung field is large for a subject having normal lung function. It becomes a displacement that contracts. On the other hand, when the local volume contraction is small, it is suspected that the ventilation function of the lungs at the site is impaired. As an example of the practice of the present invention, an image that visualizes the state of local volume change may be generated from the displacement field in the lung field so that the existence of such a portion can be visually recognized by the user.

In addition, the processes from step S3000 to step S3040 can be performed for any purpose of aligning the three-dimensional images of the lungs imaged in different respiratory phases. According to this, accurate alignment can be performed by reducing the alignment error caused by the change in the concentration value in the lung field due to the difference in the respiratory phase.

[Other embodiments]
The above-described embodiment is merely an example of the present invention, and the configuration and scope of the present invention are not limited to the above-mentioned embodiment. The processes of a plurality of embodiments may be combined, or the processes of a plurality of modifications may be combined.

In the above-described embodiment, a processing example in which the present invention is applied to the alignment of the image of the lung field has been described, but the application target of the present invention is not limited to the image of the lung field, and there is movement and the density value of the image. If the object is variable, the alignment process of the present invention can be preferably applied. For example, the present invention can be applied to the alignment of images of hearts having different contrast conditions. Specifically, regarding the alignment between the image of the heart taken with contrast medium (with contrast medium introduced) and the image of the same site taken without contrast medium (without contrast medium introduced). , The present invention may be applied. Further, the present invention is applied with respect to the alignment between the image of the heart in which the blood concentration of the contrast medium is higher than the predetermined value and the image of the heart in which the blood concentration of the contrast medium is lower than the predetermined value. You may. Further, the present invention may be applied to images of organs other than lungs and heart.

Further, the disclosed technology can take an embodiment as a system, an apparatus, a method, a program, a recording medium (storage medium), or the like. Specifically, it may be applied to a system composed of a plurality of devices (for example, a host computer, an interface device, an image pickup device, a web application, etc.), or may be applied to a device consisting of one device. good.

Needless to say, the object of the present invention is achieved by doing the following. That is, a recording medium (or storage medium) in which a program code (computer program) of software that realizes the functions of the above-described embodiment is recorded is supplied to the system or device. Needless to say, the storage medium is a computer-readable storage medium. Then, the computer (or CPU or MPU) of the system or device reads and executes the program code stored in the recording medium. In this case, the program code itself read from the recording medium realizes the function of the above-described embodiment, and the recording medium on which the program code is recorded constitutes the present invention.

10: Information processing device 100: Inspection image acquisition unit 110: Area extraction unit 120: Average concentration value calculation unit 130: Concentration value correction unit 140: Displacement field calculation unit 150: Map generation unit

Claims (15)

An image acquisition unit that acquires a first image and a second image by photographing moving objects at different timings, and an image acquisition unit.
It has an image processing unit that performs alignment processing between the first image and the second image.
The image processing unit
The first image and the first image so that the difference between the statistic of the pixel value of the region of the object in the first image and the statistic of the pixel value of the region of the object in the second image is small. / Or convert the pixel value of the second image,
An information processing apparatus for acquiring a correspondence between a first image and a pixel in a region of the object between the first image and the second image based on the converted pixel value. The image processing unit further
With respect to the peripheral region which is the peripheral region of the object, the correspondence relationship of the pixels in the peripheral region between the first image and the second image is acquired.
It is characterized in that the distribution of the amount of slip between the region of the object and the peripheral region is acquired based on the correspondence of the pixels in the region of the object and the correspondence of the pixels in the peripheral region. The information processing apparatus according to claim 1. The image processing unit uses the first image and the second image before converting the pixel value to obtain pixels in the peripheral region between the first image and the second image. The information processing apparatus according to claim 2, wherein a correspondence relationship is acquired. The image processing unit further
The said between the state of the first image and the state of the second image, based on the correspondence of the pixels in the region of the object between the first image and the second image. The information processing apparatus according to any one of claims 1 to 3, wherein the distribution of the amount of movement of the object is acquired. In the image processing unit, the difference between the statistic of the pixel value of the area of the object in the first image and the statistic of the pixel value of the area of the object in the second image becomes small, and One of claims 1 to 4, characterized in that the pixel values of the first image and / or the second image are converted so that the image features within the region of the object are emphasized. The information processing device described in the section. The image processing unit
The first image and the first image so that the difference between the statistic of the pixel value of the region of the object in the first image and the statistic of the pixel value of the region of the object in the second image is small. / Or the pixel value of the second image is converted, and further
The information processing apparatus according to claim 5, wherein window conversion using a predetermined window is performed on the converted first image and / or the second image. The image processing unit
Using the first window set based on the statistic of the pixel value of the area of the object in the first image, the window conversion for the first image is performed and the window is converted.
5. The fifth aspect of the present invention, wherein the window conversion for the second image is performed using the second window set based on the statistic of the pixel value of the region of the object in the second image. Information processing equipment. The image acquisition unit acquires an image in an intermediate state taken between the first image and the second image.
The image processing unit
The image of the intermediate state, the first image, so that the difference in the statistic of the pixel value of the region of the object between the image of the intermediate state, the first image, and the second image is small. And the pixel values of at least two of the second images are converted.
Based on the converted pixel values, the first correspondence relationship, which is the correspondence relationship of the pixels in the region of the object between the first image and the image in the intermediate state, and the image in the intermediate state. The second correspondence, which is the correspondence between the pixels in the region of the object between the second images, is acquired.
By integrating the first correspondence and the second correspondence, it is possible to generate a correspondence of pixels in the region of the object between the first image and the second image. The information processing apparatus according to any one of claims 1 to 7. The image processing unit
After acquiring the correspondence of the pixels in the region of the object between the first image and the second image,
Based on the correspondence, the volume change of the object between the first image and the second image is calculated.
Based on the volume change of the object, the converted pixel value of the first image and / or the second image is corrected.
Of claims 1 to 8, wherein the correspondence between the first image and the second image of the pixels in the region of the object is modified based on the corrected pixel value. The information processing apparatus according to any one of the following items. One of claims 1 to 9, wherein the image processing unit associates pixels between the first image and the second image based on the similarity of pixel values. The information processing device described in. The object according to any one of claims 1 to 10, wherein the object is a lung, and the first image and the second image are images taken in different respiratory phases. Information processing device. The information processing apparatus according to any one of claims 1 to 10, wherein the first image and the second image are images taken under different contrast conditions. The information processing apparatus according to any one of claims 1 to 12, wherein the first image and the second image are CT data. A step of acquiring a first image and a second image by shooting a moving object at different timings, and
It has a step of performing an alignment process between the first image and the second image.
In the alignment process,
The first image and the first image so that the difference between the statistic of the pixel value of the region of the object in the first image and the statistic of the pixel value of the region of the object in the second image is small. / Or convert the pixel value of the second image,
An information processing method comprising acquiring a correspondence relationship between a first image and a pixel in a region of the object between the first image and the second image based on the converted pixel value. A program for causing a computer to execute each step of the information processing method according to claim 14.

Images