JP2023168534A - Information processor, information processing method, and program - Google Patents

Abstract

To provide an information processor capable of selecting a medical image to be compared from a plurality of medical images according to a condition related to an imaging date and time.SOLUTION: An information processor 10 which has a selection part 55 selecting a second image to be compared with a first image from a plurality of candidate images includes: an imaging date and time acquisition part 53 acquiring imaging dates and times when the plurality of candidate images were captured; and a condition setting part 54 setting a condition related to the imaging dates and times. The selection part 55 selects at least one candidate image as a second image from the plurality of candidate images on the basis of the condition related to the imaging dates and times set by the condition setting part 54 and the imaging dates and times of the plurality of candidate images.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing apparatus, an information processing method, and a program for processing medical images captured using various modalities.

In the medical field, doctors perform diagnoses using medical images captured using various modalities. In particular, in order to observe the condition of a subject over time, doctors compare a plurality of medical images taken at different times using the same modality to observe changes in the subject over time. As a method for supporting the observation of changes over time in a subject, Patent Document 1 discloses a medical image depicting the difference between a medical image to be diagnosed (diagnosis target image) and a medical image to be compared (comparison image). A technique is disclosed for generating images (images) and displaying changes in a subject over time.

Japanese Patent Application Publication No. 2013-126575

However, when observing changes over time in a subject using a plurality of medical images, it is necessary to select an appropriate comparison image from among the plurality of medical images taken at different times.

SUMMARY OF THE INVENTION Therefore, an object of the present invention is to provide an information processing apparatus that can select a medical image to be compared from a plurality of medical images based on conditions related to imaging date and time.

In order to achieve the object of the present invention, an information processing apparatus having a selection means for selecting a second image to be compared with a first image from a plurality of candidate images is provided. The selection means includes an acquisition device that acquires the imaging date and time, and a condition setting device that sets conditions regarding the imaging date and time, and the selection device selects the imaging date and time of the plurality of candidate images based on the conditions regarding the imaging date and time set by the condition setting device. , select at least one candidate image from the plurality of candidate images as the second image.

According to the present invention, a medical image to be compared can be selected from a plurality of medical images based on conditions regarding the imaging date and time.

1 is a diagram showing the configuration of an information processing apparatus according to a first embodiment of the present invention. FIG. 3 is a diagram showing conditions related to imaging date and time by a condition setting unit of the present invention. 1 is a flowchart showing the operation of Example 1 of the present invention. FIG. 2 is a diagram showing the configuration of an information processing device according to a second embodiment of the present invention. 7 is a flowchart showing the operation of Example 2 of the present invention. FIG. 3 is a diagram showing an example of the relationship between the imaging range of a diagnostic target image and the imaging range of a candidate image according to the present invention. FIG. 3 is a diagram showing an example of the relationship between the imaging range of a diagnostic target image and the imaging range of a candidate image according to the present invention. FIG. 3 is a diagram showing an example of the relationship between the imaging range of a diagnostic target image and the imaging range of a candidate image according to the present invention. FIG. 3 is a diagram showing an example of the relationship between the imaging range of a diagnostic target image and the imaging range of a candidate image according to the present invention.

Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.

An information processing apparatus 10 according to a first embodiment will be explained using FIGS. 1 to 3. The information processing device 10 according to the embodiment of the present invention provides the following functions to users such as doctors and radiology technicians in medical institutions. That is, the information processing device 10 performs a comparison process between a diagnosis target image and a comparison image regarding a patient (subject) on whom a user is attempting to perform medical treatment, and provides the user with the results of the comparison process.

In this embodiment, a case will be described in which there are a plurality of medical images (candidate images) obtained by capturing the same subject at a time point different from the time point at which the diagnosis target image was captured. The information processing device 10 selects a medical image suitable for comparison with the diagnosis target image from among the plurality of candidate images as a comparison image, and performs a comparison process between the diagnosis target image and the comparison image. Here, the comparison process means, for example, displaying the respective medical images so that the user can compare them, or performing difference processing between the diagnosis target image and the candidate image and displaying the difference image.

The information processing device 10 compares a medical image captured at the current time or the latest medical image (diagnosis target image) with a medical image captured in the past (comparison image) than the diagnosis target image. Depicting the development and progression of lesions.

The information processing device 10 acquires the imaging dates and times when a plurality of candidate images were captured, and sets conditions regarding the imaging dates and times. Then, a comparison image is selected from the plurality of candidate images based on the set conditions and the imaging date and time of the plurality of candidate images. Then, the information processing device 10 generates a difference image depicting the difference between the diagnosis target image and the comparison image, and displays the change over time of the subject on the display unit 36. Note that in the following description, the imaging date and time includes not only information representing both the imaging date and imaging time, but also information representing only the imaging date. It is also assumed that information representing only the imaging time is included. For example, the information may include information recording only the elapsed time from a predetermined starting point (for example, 0:00:00 on January 1, 1970). Furthermore, the image capture date generally refers to the date of image capture, but may be information representing only the month and year of image capture.

FIG. 1 is a diagram showing the overall configuration of a medical information processing system and the configuration of an information processing device 10 of the present invention. The medical information processing system includes an information processing device 10 and a medical image database 23. The information processing device 10 and the medical image database 23 are communicably connected to each other via a communication means. In this embodiment, the communication means is composed of a LAN (Local Area Network) 21, but it may also be a WAN (Wide Area Network). Further, the connection method of the communication means may be a wired connection or a wireless connection.

The medical image database 23 holds a plurality of medical images and their accompanying information regarding a plurality of subjects. A medical image is an image captured by a modality such as a CT device or an MRI device, and can include various images such as two-dimensional, three-dimensional, monochrome, and color images. The incidental information of a medical image includes information such as a subject ID (patient ID), imaging date and time, imaging site, imaging conditions such as reconstruction conditions and tube voltage values and tube current values. In addition to this, the purpose of the test, the name of the organ to be tested, the name of the disease to be tested, etc. can also be used as additional information.

Each medical image and its accompanying information are given a unique identifier (examination ID) to enable identification from other information, and the information processing device 10 reads out the information based on the exam ID. be exposed. If the medical image is a three-dimensional volume image composed of multiple two-dimensional cross-sectional images (tomographic images), each two-dimensional cross-sectional image (tomographic image) and a three-dimensional volume image that is a collection of cross-sectional images A test ID is attached to the test ID. In addition to reading information, the medical image database 23 cooperates with the information processing device 10 to provide functions such as displaying a list of medical images, displaying thumbnails, searching, and writing information. Note that in this embodiment, a medical image refers to medical image data.

The information processing device 10 acquires information held by the medical image database 23 via the LAN 21. The information processing device 10 includes a communication IF 31 , a ROM 32 , a RAM 33 , a storage section 34 , an operation section 35 , a display section 36 , and a control section 50 .

The communication IF (Interface) 31 is realized by, for example, a LAN card, and performs communication between an external device (medical image database 23) and the information processing device 10 via the LAN 21. The ROM (Read Only Memory) 32 is implemented with a nonvolatile memory or the like, and stores various programs and the like. A RAM (Random Access Memory) 33 is realized by a volatile memory or the like, and temporarily stores various information. The storage unit 34 is realized by, for example, an HDD (Hard Disk Drive), and stores various information. The operation unit 35 is realized by, for example, a keyboard, a mouse, etc., and the user can input various information via the operation unit 35. The display unit 36 is, for example, a display. The operation unit 35 and the display unit 36 have a function as a graphical user interface (GUI) under control from the control unit 50.

The control unit 50 is realized by, for example, a CPU (Central Processing Unit), and centrally controls the processing in the information processing device 10. The control unit 50 includes a diagnosis target image acquisition unit 51, a candidate image acquisition unit 52, an imaging date and time acquisition unit 53, a condition setting unit 54, a selection unit 55, an image processing unit 56, and a display control unit 57.

The diagnosis target image acquisition unit 51 acquires a medical image of the subject as a diagnosis target image from the medical image database 23 via the communication IF 31 and the LAN 21 in accordance with a user's operation input through the operation unit 35 . Then, the diagnostic target image acquisition unit 51 outputs the acquired diagnostic target image together with the accompanying information to the image processing unit 56.

The candidate image acquisition unit 52 transmits medical images captured in the past of the same subject to the communication IF 31 and the LAN 21 as medical images (candidate images) that are candidates for comparison images with respect to the diagnosis target image acquired by the diagnosis target image acquisition unit 51. A plurality of images are acquired from the medical image database 23 via. Then, the candidate image acquisition section 52 outputs the supplementary information of the plurality of acquired candidate images to the imaging date and time acquisition section 53, and outputs the plurality of candidate images to the selection section 55.

The imaging date and time acquisition unit 53 acquires the imaging dates and times of a plurality of candidate images. Since the additional information added to the plurality of candidate images includes the imaging date and time, the imaging date and time acquisition unit 53 reads the additional information added to the plurality of candidate images. It is possible to obtain the imaging date and time of the image.

The condition setting unit 54 sets conditions regarding the imaging date and time in order to select a medical image to be compared (comparison image) from a plurality of candidate images. Specifically, the condition setting unit 54 sets the imaging date and time based on the imaging date and time of the image to be diagnosed.

FIG. 2 is an example showing conditions regarding the imaging date and time set by the condition setting unit 54. Although the imaging date and time includes the date and time when the subject was imaged, here, for the purpose of simplifying the explanation, the date will be used in the explanation. For example, the condition setting unit 54 can set the latest imaging date and time (the closest past imaging date and time to the imaging date and time of the diagnosis target image) as the condition regarding the imaging date and time. According to this, it is possible to perform a comparison with the most recent examination, which is the basis of comparative image interpretation. Under this condition, the selection unit 55 selects the candidate image corresponding to the latest imaging date and time as the comparison image. In the example of FIG. 2, the imaging date and time of the diagnosis target image is April 15, 2019. Among the plurality of candidate images 1 to 5, candidate image 5 has an imaging date and time of October 20, 2018, and is the candidate image with the latest imaging date and time, so candidate image 5 is selected by selection unit 55. The selection unit 55 outputs the selected candidate image 5 to the image processing unit 56 as a comparison image. Furthermore, the oldest imaging date and time (the farthest imaging date and time from the imaging date and time of the image to be diagnosed) can be set as a condition regarding the imaging date and time. According to this, the image in which the most change has occurred from the diagnosis target image can be selected as the comparison image. Under this condition, the selection unit 55 selects the candidate image corresponding to the earliest imaging date and time as the comparison image.

Furthermore, the condition setting unit 54 can set an imaging date and time within a predetermined period as a condition regarding the imaging date and time, based on the imaging date and time of the image to be diagnosed. For example, a lower limit of the period can be set as the predetermined period. For example, it can be set as a condition that the examination is performed after a predetermined period (for example, one year) or more from the date and time when the image to be diagnosed is taken. According to this, when it is known that a certain amount of time is required for the occurrence of a lesion of interest, a candidate image of an examination performed in an appropriate period can be selected as a comparison image. Furthermore, it is possible to set as an additional condition regarding the imaging date and time that the imaging date and time is the latest within a predetermined period. According to this, it is possible to select as a comparison image the candidate image of the examination that is closest to the diagnosis target image and that does not have any extra changes while satisfying the period conditions.

Conversely, an upper limit of the period can be set as the predetermined period. For example, as shown in FIG. 2A, the condition setting unit 54 can set the period to, for example, within two years based on the imaging date and time of 2019/4/15 of the diagnosis target image. According to this, it is possible to reduce the increase in noise caused by even changes that occurred in the past appearing in the difference image due to the period being too far away from the comparison image. Alternatively, a period having an upper limit and a lower limit, such as one year or more and less than two years, can be set as the predetermined period. When a predetermined period is set as a condition, the selection unit 55 selects a candidate image corresponding to an imaging date and time within the predetermined period as a comparison image. In the example of FIG. 2A, the imaging date and time of candidate image 4 among the plurality of candidate images is September 5, 2018, and the imaging date and time of candidate image 5 is October 20, 2018, so the selection unit 55 Candidate image 4 and candidate image 5 are selected by. The selection unit 55 outputs the selected candidate image 4 and candidate image 5 to the image processing unit 56 as comparison images. Furthermore, it is possible to set as an additional condition regarding the imaging date and time that the imaging date and time is the earliest within a predetermined period. According to this, it is possible to select the test that produces the largest change while satisfying the period conditions. In this case, in the example of FIG. 2(a), candidate image 4 is selected as the comparison image.

Note that the condition setting unit 54 may be configured to be able to set a plurality of conditions with different priorities as conditions regarding the imaging date and time. For example, if there is no candidate image that satisfies the conditions of the first priority, a candidate image that satisfies the conditions of the second priority may be selected, so that multiple stages of conditions can be set. For example, the first priority condition may be that the imaging date and time is between one year and less than two years, and the second priority condition may be between two years and less than three years. Furthermore, an arbitrary number of three or more conditions may be prioritized and set, such as setting three or more years but less than four years as a third priority condition. According to this, even if a comparison image with ideal conditions does not exist, a comparison image that satisfies the next best conditions can be selected, which has the effect of reducing cases where images cannot be compared.

Furthermore, the condition setting unit 54 can also set, as a condition regarding the imaging date and time, an imaging date and time that does not include a predetermined treatment such as surgery between the imaging date and time of the image to be diagnosed. In the case of this condition, the selection unit 55 selects, as a comparison image, a candidate image corresponding to an imaging date and time that does not include a predetermined treatment such as surgery between the imaging date and time of the diagnosis target image.

If a treatment such as surgery is performed between the imaging date and time of the candidate image and the imaging date and time of the diagnostic target image, the pixel values around the treatment site in the candidate image and the diagnostic target image differ greatly, making the candidate image unsuitable for comparison. FIG. 2B shows that the surgery was performed on the imaging date and time of candidate image 4 and the imaging date and time of candidate image 5. Among the plurality of candidate images, candidate image 5 is selected by the selection unit 55 because the imaging date and time of candidate image 5 is a candidate image whose imaging date and time does not involve any treatment such as surgery between the imaging dates and times of the diagnosis target images. The selection unit 55 outputs the selected candidate image 5 to the image processing unit 56 as a comparison image. Note that the conditions for the imaging date and time may be that the imaging date and time is as old as possible and does not include a predetermined treatment such as surgery. According to this, an image in which the most change has occurred from the diagnosis target image can be selected as a comparison image within a range where major changes such as surgery do not occur.

Furthermore, the condition setting unit 54 can also set the latest imaging date and time as the condition regarding the imaging date and time before starting a predetermined treatment. In the case of this condition, the selection unit 55 selects a candidate image with the latest imaging date and time before the designated predetermined treatment date and time as a comparison image. According to this, when it is desired to observe changes due to treatment effects, an appropriate comparison image can be selected.

Further, the condition setting unit 54 can also set, as a condition regarding the imaging date and time, an imaging date and time in which the model of the modality has not been changed between the imaging date and time of the diagnosis target image.

In the case of this condition, the selection unit 55 selects, as a comparison image, a candidate image corresponding to an imaging date and time in which the modality model has not been changed between the imaging date and time of the diagnosis target image.

This is because if the model of modality is changed between the imaging date and time of the candidate image and the imaging date and time of the diagnosis target image, the image quality of the candidate image and the diagnosis target image will be significantly different, and the candidate image will not be suitable as a comparison target. FIG. 2C shows that the modality model has been changed between the imaging date and time of candidate image 3 and the imaging date and time of candidate image 4. Among the plural candidate images, the imaging date and time of candidate image 4 and the imaging date and time of candidate image 5 are candidate images with imaging dates and times that do not involve changing the model of modality between the imaging dates and times of the diagnostic target images, so the selection unit 55 selects candidate images as candidates. Image 4 or candidate image 5 is selected. The selection unit 55 outputs the selected candidate image 4 or candidate image 5 to the image processing unit 56 as a comparison image. Note that the conditions for the imaging date and time may be that the modality has not been changed and the imaging date and time is as old as possible. According to this, it is possible to select, as a comparison image, an image in which the greatest change has occurred from the diagnosis target image within a range where no major change occurs due to a change in modality model. In addition, although we have described a modality model change as an example here, any event that affects image quality, such as a change in the imaging protocol or a version upgrade of the reconstruction algorithm, can also be recorded using the date and time of any event. may be used as a condition.

Note that the conditions regarding the imaging date and time may be a combination of the above conditions.

Here, since a plurality of images are generally captured in an examination on the same imaging date and time, it may not be possible to identify one comparative image from the candidate images based only on the imaging date and time conditions. Furthermore, even if there are multiple examinations that satisfy the imaging date and time conditions, one comparative image cannot be identified from the candidate images based only on the imaging date and time conditions. In such a case, the selection unit 55 may be configured to further narrow down the comparison images by setting conditions other than the imaging date and time. In this case, the condition setting unit 54 can select a comparison image based on conditions other than the imaging date and time (imaging range, imaging region, imaging conditions, etc.) from among the candidate images that satisfy the imaging date and time condition. As long as it is an imaging part, the lung field, abdomen, head, etc. can be set. For example, the condition setting unit 54 can set conditions for selecting candidate images of the same imaged region as the imaged region of the diagnosis target image. For example, if the image to be diagnosed is an image of the abdomen, the condition setting unit 54 sets the condition that the imaging region is the abdomen, and the selection unit 55 selects the candidate image of the abdomen as the comparison image. Similarly, if the diagnosis target image is an image of the head, the condition setting unit 54 sets the condition that the imaged region is the head, and the selection unit 55 selects the candidate image of the head as the comparison image. do. Similarly, the selection condition may be that the purpose of the test, the name of the disease to be tested, etc. match the diagnosis target image.

In addition, as far as imaging conditions are concerned, reconstruction conditions, slice thickness, contrast conditions (presence or absence of contrast agent), etc. can be set as comparison image selection conditions. For example, the condition setting unit 54 can set, as a condition for selecting a comparison image, that the image has imaging conditions suitable for differential processing. For example, conditions can be set such as the slice thickness being 5 mm or less, the reconstruction function meeting the mediastinal condition, non-contrast imaging, and the range of tube voltage and tube current. Further, the condition setting unit 54 can set, as a condition for selecting a comparison image, that the image is captured under the same imaging conditions as the imaging condition of the diagnosis target image. For example, if the slice thickness of the diagnosis target image is 2.5 mm, the condition setting unit 54 sets the slice thickness to be 2.5 mm as a condition for selecting the comparison image from the candidate images. At this time, the selection unit 55 selects a candidate image with a slice thickness of 2.5 mm as a comparison image from among the plurality of candidate images. Similarly, conditions for selecting comparison images can be set such that the reconstruction function, tube voltage, and tube current match the diagnosis target image, or that the difference is within a predetermined range. . Additionally, conditions may be set that are a combination of multiple items. In this case, for example, a comprehensive evaluation value can be calculated based on the degree of matching of each item by the product or sum of these, and the candidate image giving the best evaluation value can be selected as the comparison image. Alternatively, all candidate images whose evaluation values exceed a predetermined threshold can be selected as comparison images. Note that in the above example, a comparison image is selected from candidate images that meet the shooting date and time conditions based on conditions other than the shooting date and time, but the order in which the conditions are applied is limited to this. isn't it. For example, candidate images may be narrowed down based on conditions other than the shooting date and time, and then comparison images may be selected based on the shooting date and time. In particular, when the imaging date/time condition is "oldest" or "newest", it is desirable to first narrow down the search based on conditions other than the imaging date/time. For example, it is possible to set conditions such as selecting the candidate image with the oldest image capture date and time, or selecting the candidate image with the newest image capture date and time from candidate images that satisfy conditions other than the capture date and time. According to this, from among candidate images that meet conditions other than the imaging date and time, images can be selected according to the purpose (for example, to see changes that have occurred in the patient so far, or to see changes since the previous examination for the same purpose). Comparisons can be made.

Then, the image processing unit 56 performs comparison processing (difference processing) between the diagnosis target image and the comparison image (selected candidate image), and outputs the comparison result of the comparison processing to the display control unit 57. Specifically, the image processing unit 56 generates a difference image depicting the difference between the diagnosis target image and the comparison image. The display processing section 57 causes the display section 36 to display the comparison result (difference image).

Note that at least a part of each unit included in the control unit 50 may be realized as an independent device. Alternatively, each may be realized as software that realizes the function. In this case, the software that implements the function may operate on a server via a network such as a cloud. In this embodiment, it is assumed that each part is realized by software in a local environment.

Furthermore, the configuration of the information processing device 10 shown in FIG. 1 is merely an example. For example, the storage unit 34 of the information processing device 10 may have the function of the medical image database 23, and the storage unit 34 may hold a plurality of medical images and their accompanying information regarding a plurality of subjects.

Next, the operation of the information processing apparatus 10 in this embodiment will be described in detail using FIG. 3. In addition, although the case where a CT image is used as a medical image is demonstrated below as an example, implementation of this invention is not limited to this. Further, the diagnosis target image and the candidate image do not necessarily have to be images of the same subject and the same modality.

(Step S1010) <Acquisition of diagnosis target image>
In this step, the diagnosis target image acquisition unit 51 executes a process of acquiring a diagnosis target image (first image) to be processed from the medical image database 23. This process is executed by receiving an operation from the user using the GUI provided by the operation unit 35 and the display unit 36. Through this process, the diagnosis target image acquisition unit 51 reads the diagnosis target image from the medical image database 23, and the information processing device 10 stores it using the ROM 32, RAM 33, storage unit 34, etc. In this embodiment, a case will be described in which a three-dimensional CT image composed of a plurality of tomographic images is acquired as a diagnosis target image. However, the implementation of the present invention is not limited to this, and may be a two-dimensional CT image, a simple X-ray image, an MRI image, a camera image of a lesion of a subject, or the like. Note that incidental information such as a subject ID (patient ID), imaging date and time, imaging site, imaging parameters, etc. is attached to the diagnosis target image.

(Step S1020) <Obtain multiple candidate images>
In this step, the candidate image acquisition unit 52 executes a process of acquiring a plurality of medical images (candidate images) that are candidates for comparison with the diagnosis target image acquired in step S1010 from the medical image database 23. As an example of this process, the candidate image acquisition unit 52 acquires a medical image of the same subject as the diagnosis target image as a candidate image from among a plurality of medical images recorded in the medical image database 23. Specifically, the candidate image acquisition unit 52 uses a search function provided in the medical image database 23 to search for medical images that have the same subject ID as the subject ID that is the supplementary information of the diagnosis target image. get.

The method for acquiring candidate images is not limited to the above method. For example, the candidate image acquisition unit 52 may refer to the imaging date and time of the diagnosis target image and acquire only older (past) medical images. In this example, by the above-described method, medical images of the same subject that were taken at a time in the past than the time when the image to be diagnosed was taken, and in the same modality as the image to be diagnosed (in the specific example of this example, CT It is assumed that candidate images are acquired only from medical images captured by a device (device).

(Step S1030) <Obtain the imaging date and time of multiple candidate images>
In this step, the imaging date and time acquisition unit 53 acquires the imaging dates and times of the plurality of candidate images acquired by the candidate image acquisition unit 52. The imaging date and time recorded together with the candidate images is recorded as supplementary information in the header area of each candidate image. The imaging date and time acquisition unit 53 acquires the imaging dates and times of the plurality of candidate images by reading the supplementary information of the plurality of candidate images. Here, the imaging date and time acquisition unit 53 may acquire the implementation date (examination date) of the examination on which the candidate image was acquired, and use it as the imaging date and time of each candidate image acquired in the examination. Furthermore, information correlated with the imaging date and time, such as the date when the candidate image was reconstructed or the date when the image was first interpreted, may be substituted as the imaging date and time.

(Step S1035) <Set conditions regarding imaging date and time>
In this step, the condition setting unit 54 sets conditions regarding the imaging date and time for selecting a comparison image from a plurality of candidate images. For example, the conditions are set by having the user select a condition from among the variations of conditions related to the imaging date and time listed above via a GUI (not shown). Alternatively, the configuration may be such that conditions written in advance in a configuration file are read. Note that it is desirable that the condition setting unit 54 also set other conditions other than the imaging date and time in this step.

(Step S1040) <Select comparison image>
In this step, the selection unit 55 selects a comparison image from among the plurality of candidate images based on the condition regarding the imaging date and time set by the condition setting unit 54 and the imaging date and time of the plurality of candidate images.

Note that in the process performed by the selection unit 55, the comparison images do not necessarily need to be narrowed down to one, and a plurality of comparison images may be selected. In this case, the configuration may be such that the user can select a comparison image to be output to the image processing section 56 from among the plurality of comparison images selected by the selection section 55 via a GUI (not shown). Alternatively, a configuration may be adopted in which all of the selected comparison images are output to the image processing section 56.

(Step S1050) <Comparison process>
In this step, the image processing unit 56 performs comparison processing between the diagnosis target image and the comparison image. Specifically, the image processing unit 56 performs image difference processing between the diagnosis target image and the comparison image, and calculates a difference image as a comparison result. Here, if the selection unit 55 selects a plurality of comparison images, the image processing unit 56 generates a difference image between the diagnosis target image and the comparison image for each comparison image. That is, the image processing unit 56 generates a difference image between the first image and the second image by comparing the first image that is the diagnosis target image and the second image that is the comparison image. Difference processing between the diagnosis target image and comparison image corrects image differences that are unnecessary for image diagnosis, such as differences in the position and shape of the subject depicted in the diagnosis target image and comparison image, and differences in image quality between images. It is desirable to carry out the process after Correction of differences between images may be performed using any known method, and detailed description thereof will be omitted here.

Note that the process for calculating the comparison result is not limited to the above-mentioned difference process. For example, the image processing unit 56 may generate a superimposed image for the diagnosis target image and the comparison image. In this case, a superimposed image can be generated as a color image by assigning different color channels to the diagnosis target image and the comparison image, and mixing them. Alternatively, a modified image may be generated by modifying the comparison image so that the shape of the diagnosis target image and the subject match.

(Step S1060) <Display of comparison results>
In this step, the display control unit 57 executes a process of displaying the comparison result obtained by the process of step S1050 on the display unit 36. As a specific example, the display control unit 57 performs volume rendering on each of the diagnosis target image, comparison image, and difference image, and displays each of the images created by volume rendering (hereinafter referred to as volume rendering images) on the display unit 36. Display side by side.

The method of displaying the comparison results is not limited to the above method, and the display control unit 57 may display a tomographic image at an arbitrary position in each image on the display unit 36, and the displayed tomographic image may be changed by a user's operation. The display control unit 57 can perform processing such as identifying a corresponding position in each of the diagnosis target image and the comparison image, and displaying a tomographic image at the position (displaying a corresponding cross section). That is, when the user changes the tomographic image of the diagnosis target image to be displayed, the display control unit 57 displays on the display unit 36 the tomographic image at the position of the comparison image corresponding to the position of the relevant tomographic image. Further, when the diagnosis target image and the comparison image are aligned in step S1050, the display control unit 57 links the tomographic images to be displayed in the diagnosis target image and the difference image based on the result of the alignment. It is desirable to perform processing such as switching by

As described above, according to the present invention, the information processing apparatus 10 includes the selection unit 55 that selects a comparison image (second image) to be compared with the diagnosis target image (first image) from a plurality of candidate images. The selection unit 55 includes an imaging date and time acquisition unit 53 that acquires the imaging date and time when a plurality of candidate images were captured, and a condition setting unit 54 that sets conditions regarding the imaging date and time. At least one candidate image is selected as a comparison image (second image) from the plurality of candidate images based on the conditions regarding the imaging date and time and the imaging dates and times of the plurality of candidate images. Therefore, the selection unit 55 can select a candidate image (comparison image) to be compared from a plurality of candidate images based on the conditions related to the imaging date and time, and the display unit 36 can quickly display the comparison result using the comparison images.

As described above, according to the present embodiment, it is possible to select comparison images that can be suitably compared with the diagnosis target image and provide the user with the results of comparison processing of those images, without requiring the user to perform any troublesome operations.

Note that in the above embodiment, the result of the comparison process between the selected comparison image and the diagnosis target image is displayed, but the display of the result is not necessarily necessary. For example, the configuration may be such that only the process of storing the results of the comparison process and information identifying the comparison image in the medical image database 23 in association with the diagnosis target image is possible. In this case, when observing the diagnosis target image using another image viewer, the linked comparison processing result and the comparison image can be read and displayed. Furthermore, it is not always necessary to perform comparison processing. For example, the configuration may be such that only the process of storing information identifying the selected comparison image in the medical image database 23 in association with the diagnosis target image is possible. In this case, when observing the diagnosis target image using another image viewer, you can load the linked comparison image and display it in a form that allows comparison, or display a superimposed image between the diagnosis target image and the comparison image. You can also generate difference images.

Next, the information processing device 10 of Example 2 will be explained using FIGS. 4 to 9. The difference from the first embodiment is that a combination of a plurality of candidate images is evaluated and the combination is selected. FIG. 4 is a diagram showing the overall configuration of the medical information processing system and the configuration of the information processing device 10 of the present invention. Here, the configuration different from that in FIG. 1 will be mainly explained.

The candidate image acquisition unit 52 acquires a plurality of medical images (candidate images) that are candidates for comparison images with respect to the diagnosis target image acquired by the diagnosis target image acquisition unit 51 from the medical image database 23 via the communication IF 31 and the LAN 21. Then, the candidate image acquisition section 52 outputs the plurality of acquired candidate images to the combination generation section 60 and the selection section 55.

The combination generation unit 60 generates at least one combination of the candidate images acquired by the candidate image acquisition unit 52. Here, the combination of candidate images is a combination of one or more candidate images. Further, it is assumed that the combination of candidate images generated by the combination generation unit 60 includes at least one combination of a plurality of (that is, two or more) candidate images. The combination generation unit 60 then outputs the generated combination of candidate images to the evaluation unit 61.

The evaluation unit 61 calculates, for each combination of candidate images generated by the combination generation unit 60, an evaluation value regarding the appropriateness of comparison with the diagnosis target image. The evaluation unit 61 then outputs each calculated evaluation value to the selection unit 55.

The selection unit 55 selects a combination of candidate images to be compared with the diagnosis target image from among the combinations of candidate images based on each evaluation value. The selected candidate image combination is composed of one or more candidate images. Hereinafter, the combination of selected candidate images will be referred to as a set of comparison images, and the candidate images forming the set of comparison images will be referred to as comparison images. The selection unit 55 then outputs the set of comparison images to the image processing unit 56.

The image processing unit 56 performs a comparison process between the diagnosis target image and the set of comparison images, and outputs the comparison result of the comparison process to the display control unit 57. The display control section 57 causes the display section 36 to display the comparison result of the image processing section 56.

Next, using FIG. 5, the entire processing procedure by the information processing apparatus 10 in this embodiment will be explained in detail. Steps S1010, S1020, S1050, and S1060 are generally the same steps as in FIG. 3.

Here, the candidate image is expressed as I_r,i (1≦i≦N). N represents the number of candidate images acquired in step S1020. In this embodiment, the following explanation will be given using the case where N=3 as a specific example.

Note that when the number N of candidate images acquired in this step is 1, the processes of steps S2000 to S2020, which will be described later, are omitted, and the acquired candidate images are regarded as a set of comparison images, which will be described in detail later. Processing after step S1050 may be executed.

(Step S2000) <Generate combination of candidate images>
In this step, the combination generation unit 60 generates a plurality of combinations of one or more candidate images, including at least one combination of two or more candidate images, from the N candidate images acquired in step S1020. That is, the combination generation unit 60 corresponds to a setting unit that sets a plurality of combinations including two or more candidate images among the plurality of candidate images. In this embodiment, an example is shown in which the combination of candidate images is generated by a combination of two different candidate images. In a specific example where N=3, the following three combinations <I_r, 1, I_r, 2>, <I_r, 1, I_r, 3>, and <I_r, 2, I_r, 3> are generated. In this embodiment, a combination of candidate images is expressed as P_j (1≦j≦M). Here, M is the total number of combinations. In this embodiment, the following explanation will be given using the case where M=3 as an example.

(Step S2010) <Calculation of evaluation value>
In this step, the evaluation unit 61 executes a process of calculating an evaluation value regarding comparison with the diagnosis target image for each of the combinations of candidate images generated in step S2000. In this embodiment, a case will be described as a specific example in which an evaluation value is calculated based on an overlapping range (common imaging range) between the imaging range of a combination of candidate images to be evaluated and the imaging range of an image to be diagnosed.

Here, the processing of this step will be explained in detail using FIGS. 6 to 9. 6 to 9 are diagrams showing the relationship between the imaging range of the diagnosis target image and the imaging range of the candidate image. In FIG. 6, 400 is the subject in this example. 410 indicates the range in the body axis direction of the subject 400 in the imaging range of the diagnosis target image acquired in step S1010. Here, a case is shown in which the imaging range of the diagnosis target image includes the range from the chest to the abdomen of the subject 400. Further, in FIG. 6, 420, 430, and 440 respectively indicate the imaging range (in the body axis direction) of the candidate images I_r,1, I_r,2, and I_r,3 acquired in step S1020. Here, a case is shown in which I_r,1 is a candidate image of the subject's head, I_r,2 is the abdomen, and I_r,3 is the chest.

In FIG. 7, 450 indicates the overlapping range between the imaging range (range of the sum of 420 and 430) of the candidate image combination P_1 (combination of candidate images I_r, 1 and I_r, 2) and the imaging range 410 of the diagnosis target image. It shows. In other words, 450 represents the range in which comparison processing between images and the diagnosis target image can be performed using the candidate image combination P_1. FIG. 7 shows that the imaging ranges of the diagnosis target image and the candidate image I_r, 1 do not overlap, and that the imaging ranges of the diagnosis target image and the candidate image I_r, 2 partially overlap. Therefore, the overlapping imaging range of the diagnosis target image and candidate image I_r,2 becomes the overlap range of the combination P_1 of the diagnosis target image and candidate image.

In FIG. 8, 460 indicates the imaging range of the diagnosis target image (the range of the sum of 420 and 440) of the candidate image combination P_2 (combination of candidate images I_r, 1, I_r, 3) using the same expression as in FIG. An overlapping range with range 410 is shown. FIG. 8 shows that the imaging ranges of the diagnosis target image and the candidate image I_r, 1 do not overlap, and that the imaging ranges of the diagnosis target image and the candidate image I_r, 3 partially overlap. Therefore, the overlapping imaging range of the diagnosis target image and candidate image I_r,3 becomes the overlap range of the combination P_2 of the diagnosis target image and candidate image.

In FIG. 9, 470 indicates the imaging range of the diagnosis target image using the same expression as in FIG. An overlapping range with range 410 is shown. FIG. 9 shows that the imaging range 410 of the diagnosis target image and the imaging ranges 430 and 440 of the candidate images I_r, 2 and I_r, 3 partially overlap. In this step, the evaluation unit 61 calculates the size of each range (overlapping range) 450 in FIG. 7, 460 in FIG. 8, and 470 in FIG. 9, and combines the candidate images based on the size of the overlapping range. An evaluation value E_j (1≦j≦M) is calculated for each of . The evaluation value E_j may be the length of the overlapping range of the subject 400 in the body axis direction as shown in FIGS. 7, 8, and 9, or may be the volume of the overlapping range. Alternatively, the ratio of the overlapping range to the entire imaging range of the diagnosis target image may be used. That is, the evaluation unit 61 includes an overlapping range calculating means that calculates an overlapping range with the first image for each of the plurality of combinations, and an evaluation value for each of the multiple combinations based on the overlapping range. This corresponds to an example of an evaluation value calculation means. In particular, the evaluation unit 61 calculates, as the overlapping range, an overlapping range between the sum of the imaging ranges of two or more candidate images included in the combination and the imaging range of the first image. This corresponds to an example of a calculation means.

The above description assumes that the relative positional relationship between the imaging ranges of the diagnosis target image and the candidate image is clear. If the relative positional relationship between the imaging ranges of each image is not clear, the information processing device 10 can calculate the relative positional relationship by performing positioning between the images in this step. This positioning process may be performed using any known method, and detailed explanation will be omitted here.

Further, the calculation of the relative positional relationship between the imaging ranges of each image is not limited to the method based on alignment between images, but may be calculated based on supplementary information of each image. For example, if the diagnosis target image and the candidate image are accompanied by information on "imaged region," the positional relationship between the images can be calculated based on that information. For example, the additional information regarding the imaged region of the diagnosis target image is "chest, abdomen," the additional information regarding the imaged region of candidate image I_r,1 is "head," and the additional information regarding the imaged region of candidate image I_r,2. Assume that the candidate image I_r, 3 is "abdomen" and the additional information regarding the imaged region of candidate image I_r,3 is "chest". In this case, the imaging range of candidate image combination P_1 (combination of I_r, 1 and I_r, 2) is "head and abdomen," and the overlapping range with the diagnosis target image is estimated to be "abdomen." . Furthermore, it is estimated that the imaging range of candidate image combination P_2 (combination of I_r,1 and I_r,3) is "head and chest," and the overlapping range with the diagnosis target image is "chest." Furthermore, the imaging range of candidate image combination P_3 (combination of I_r,2 and I_r,3) is "chest and abdomen," and the overlapping range with the diagnosis target image is estimated to be "chest and abdomen." . In this case, the evaluation unit 61 can set the number of parts included in the overlapping range (1 if the overlapping range is "chest" or "abdomen", 2 if the overlapping range is "chest and abdomen") as an evaluation value. . Alternatively, a predetermined coefficient may be set in advance for each part of the human body such as the "chest" or "abdomen", and the evaluation value may be calculated by multiplying each of the above overlapped ranges by the coefficient. As a more specific example, regarding "chest", "abdomen", etc., the size of the relevant part in a standard human body is set as a coefficient. According to this, it is possible to calculate the size of the overlapping range using a simpler method and use it as an evaluation value.

Using the method described above, the evaluation unit 61 calculates an evaluation value E_j (1≦j≦M) for each of the candidate image combinations P_j generated in step S2010.

(Step S2020) <Select a set of comparison images>
In this step, the selection unit 55 executes a process of selecting a combination of candidate images suitable for comparison with the diagnosis target image from among the M combinations of candidate images, based on each evaluation value calculated in step S2010. do. Specifically, the selection unit 55 selects the combination with the highest evaluation value among the evaluation values E_j (1≦j≦M) for the combinations of M candidate images. The combination of selected candidate images becomes a set of comparison images, and the candidate images forming the set of comparison images become comparison images. That is, the selection unit 55 corresponds to an example of a selection unit that selects a plurality of second images to be compared with the first image from among a plurality of candidate images. In particular, the selection unit 55 corresponds to an example of a selection means characterized by selecting one of a plurality of combinations as a plurality of second images based on the evaluation value.

(Step S1050) <Comparison process>
In this step, the image processing unit 56 executes a comparison process between the diagnosis target image and the set of comparison images, and calculates a comparison result. Specifically, for example, the image processing unit 56 performs image difference processing between the diagnosis target image and the set of comparison images, and calculates a difference image as a comparison result. That is, the image processing unit 56 corresponds to an example of a generation unit that generates a difference image between the first image and the second image by comparing the first image and the second image. In this embodiment, the set of comparison images is composed of a plurality of comparison images. An example of a processing method in this step is a method in which the image processing unit 56 performs difference processing between each of a plurality of comparison images included in the set of comparison images and the diagnosis target image. In this case, difference images between each of the plurality of comparison images and the diagnosis target image are calculated, and a set of these difference images can be used as the processing result of this step. Difference processing between the diagnosis target image and each of the multiple comparison images is performed to detect differences in the position and shape of the subject depicted in the diagnosis target image and each of the multiple comparison images, and differences in image quality between the images. It is desirable to perform this after correcting image differences that are unnecessary for diagnosis. Further, the comparison process can target only the overlapping range between the imaging range of each of the plurality of comparison images and the imaging range of the diagnosis target image. Since the overlapping range can be easily obtained from the processing results of steps S2000 and S2010, detailed explanation will be omitted. Note that a plurality of comparison images constituting a set of comparison images may be combined into one comparison image by a stitching process, and then a comparison process between the combined comparison image and the diagnosis target image may be performed. At this time, for areas where a plurality of comparison images overlap, one of the comparison images including the overlapping area can be selected and combined. Also, select a comparison image with a similar imaging date and time to the diagnosis target image, select a comparison image with similar imaging conditions to the diagnosis target image, or select a comparison image with better image quality than others. You can do it like this. Furthermore, in addition to selecting and combining any comparison images, an embodiment of the present invention may also include a method of smoothly weighted averaging and combining overlapping images.

Note that the process for calculating the comparison result is not limited to the above-mentioned difference process. For example, the image processing unit 56 may generate a superimposed image for each of the diagnosis target image and the plurality of comparison images. In this case, a superimposed image can be generated as a color image by assigning different color channels to the diagnosis target image and the comparison image, and mixing them.

(Step S1060) <Display of comparison results>
In this step, the display control unit 57 executes a process of displaying the comparison result obtained by the process of step S1050 on the display unit 36. As a specific example, the display control unit 57 performs volume rendering on each of the diagnosis target image, the set of comparison images, and the set of difference images that are the comparison results, and images created by volume rendering (hereinafter referred to as volume rendered images) ) may be displayed side by side on the display section 36. At this time, regarding the set of comparison images and the set of difference images, the display control unit 57 performs volume rendering on each of the plurality of comparison images and difference images constituting the set of comparison images and the set of difference images. Volume rendering images may be displayed side by side. In addition to this, the display control unit 57 may, for example, combine a plurality of images constituting each set into one three-dimensional image by stitching processing based on the result of step S1050, etc., and then execute volume rendering. Good too.

The method of displaying the comparison results is not limited to the above method, and the display control unit 57 may display a tomographic image at an arbitrary position in each image on the display unit 36, and the displayed tomographic image may be changed by a user's operation. In this case, based on the positional relationship between the diagnosis target image and the comparison image set, the display control unit 57 identifies the corresponding position in each of the diagnosis target image and comparison image set, and displays the tomographic image at the corresponding position. It is desirable to perform processing such as (displaying the corresponding cross section). That is, when the user changes the tomographic image of the diagnosis target image to be displayed, the display control unit 57 displays on the display unit 36 the tomographic image at the position of the set of comparison images corresponding to the position of the relevant tomographic image. In addition, when the diagnosis target image and the set of comparison images are aligned in step S1050, the display control unit 57 displays tomographic images to be displayed between the diagnosis target image and the difference image based on the result of the alignment. It is desirable to perform processing such as switching in conjunction with each other.

The information processing device 10 also includes a combination generation unit 60 that sets a plurality of combinations of a plurality of candidate images, and calculates an overlapping range between the candidate images included in the plurality of combinations and the diagnosis target image (first image). It has an overlap range calculation means (evaluation unit 61) and a selection unit 55 that selects at least one combination from a plurality of combinations based on the overlap range, and the selection unit 55 further includes a combination included in the selected combination. The candidate image that is displayed is selected as the comparison image (second image).

As described above, according to the present embodiment, it is possible to select a plurality of comparison images that can be suitably compared with the diagnosis target image and provide the user with the results of comparison processing of those images, without requiring the user to perform any troublesome operations. be.

(Modification 2-1: Combination of candidate images <Evaluation based on number/number of candidate images>)
In the process of step S2000 of the present embodiment, an example has been described in which the candidate images are combined and two candidate images are combined, but the present embodiment is not limited to this. For example, three or more candidate images may be combined. In this case, in the process of step S2010, the evaluation unit 61 calculates an evaluation value by comparing the imaging range of the combination of three or more candidate images with the imaging range of the diagnosis target image. Further, the number of candidate images included in each combination of candidate images may be a predetermined constant number, or may be different numbers from each other. Further, in this case, the combination of candidate images is not necessarily limited to the case where a plurality of candidate images are combined, and one candidate image may be treated as one of the combinations of candidate images. For example, when the total number N of candidate images is 3, the combination generation unit 60 generates 3 types of combinations containing only one candidate image, 3 types of combinations containing 2 candidate images, and 1 combination containing 3 candidate images as combinations of candidate images. Generate each type. Then, the subsequent processing may be executed with the total number of combinations M=7. In this case, the larger the number of candidate images to be combined, the wider the overlapping range tends to be. Therefore, the evaluation value calculated in step S2010 is preferably calculated based on the number of candidate images included in the combination of candidate images to be evaluated, in addition to the information on the overlapping range. For example, if there is a combination of two candidate images that have approximately the same evaluation value based on the overlapping range (the difference between the evaluation values is less than or equal to a predetermined threshold), the evaluation unit 61 selects a candidate image that is composed of a smaller number of candidate images. Possible methods include increasing the evaluation value of a combination of images. For example, among the combinations of candidate images in which the entire range of the diagnosis target images overlaps, the selection unit 55 selects a combination of candidate images consisting of a smaller number of candidate images as a set of comparison images. It may be. Alternatively, a configuration in which a value obtained by multiplying the evaluation value based on the overlapping range by a predetermined correction coefficient according to the number of candidate images to be combined (the value becomes smaller as the number of images to be combined increases) is used as the evaluation value after correction. It may be. According to this, the comparison process in step S1050 can be executed on a smaller number of comparison images, so that the process in step S1050 can be made more efficient and the comparison results with higher quality can be obtained. be.

(Modification 2-2: Evaluation value calculation method <Image quality/imaging conditions>)
The process of step S2010 in this embodiment will be explained using an example in which an evaluation value is calculated based on the overlapping range between the imaging range of the diagnosis target image and the imaging range of the combination of candidate images (hereinafter referred to as overlapping range evaluation). However, implementation of the present invention is not limited to this.

For example, apart from the evaluation of the overlapping range, the evaluation unit 61 performs an evaluation based on the image quality of each candidate image included in the combination of candidate images (hereinafter referred to as image quality evaluation), and integrates the evaluation based on the overlapping range evaluation and the image quality evaluation. The evaluation value may also be calculated. That is, the evaluation unit 61 corresponds to an example of an image quality evaluation unit that evaluates the image quality of each candidate image included in a plurality of combinations. Specifically, the evaluation unit 61 estimates the noise level of each candidate image included in each candidate image combination, and lowers the evaluation value for the combination that includes a candidate image with a high noise level. For example, a configuration may be adopted in which a value obtained by multiplying the evaluation value obtained by overlapping range evaluation by a predetermined correction coefficient according to the noise level of the candidate image (the value becomes smaller as the noise level is higher) is used as the evaluation value after correction. . At this time, the evaluation unit 61 calculates the size of the overlapping range between each candidate image and the diagnosis target image, and calculates the evaluation value by giving more importance to the noise level of the candidate image with a large overlapping range. This is desirable. Furthermore, the evaluation unit 61 may calculate the evaluation value by giving importance to the noise level of the candidate image with the highest noise level among the candidate images that at least partially overlap with the imaging range of the diagnosis target image. In addition to this, for example, when a plurality of candidate images included in the same combination of candidate images have different image qualities, the evaluation unit 61 may lower the evaluation value of the combination. For example, a configuration may be adopted in which a value obtained by multiplying the evaluation value based on the overlapping range by a correction coefficient predetermined according to the image quality of the candidate image (the lower the image quality evaluation value, the smaller the value) is used as the corrected evaluation value. .

In addition, the evaluation unit 61 is not limited to the above method, and may evaluate candidate images based on, for example, reconstruction conditions that are supplementary information of the candidate images, and imaging conditions such as the tube voltage and tube current of the X-ray radiation device. It's okay. Furthermore, the evaluation unit 61 may evaluate the candidate image based on the resolution of the candidate image (the pixel size of the two-dimensional slice, the slice interval, etc.). For example, the evaluation unit 61 may correct the evaluation value of the combination so that the evaluation value of the candidate image with a narrow slice interval becomes higher. Furthermore, when the plurality of candidate images included in the same combination of candidate images have different imaging conditions, the evaluation unit 61 may lower the evaluation value of the combination.

Further, in the above description, an example of a method of evaluation based on the image quality of the candidate image has been described, but evaluation may be performed based on the image quality of the diagnosis target image in other ways. For example, the evaluation unit 61 evaluates the image quality of the diagnosis target image using a method similar to the method described above, and gives an evaluation value based on the evaluation of both the image quality of the candidate image and the image quality of the diagnosis target image. can be calculated. More specifically, the evaluation value may be lowered for a combination of candidate images that includes candidate images whose image quality is lower than that of the diagnosis target image. In addition to this, the evaluation value may be increased for combinations of candidate images that include candidate images whose image quality is close to that of the diagnosis target image.

In addition, the evaluation unit 61 acquires incidental information such as the examination purpose of each candidate image included in the combination of candidate images, the name of the organ to be examined, the name of the disease to be examined, etc. as examination information from the medical image database, and obtains the examination information. Candidate images may be evaluated based on. For example, the evaluation value may be corrected so that the evaluation value of a combination of candidate images including candidate images having test information close to the test information of the diagnosis target image as supplementary information becomes high. That is, the evaluation unit 61 corresponds to an example of an examination information acquisition unit that acquires examination information of each candidate image included in a plurality of combinations. Alternatively, a configuration may be adopted in which a value obtained by multiplying the evaluation value by a correction coefficient determined according to the degree of matching of the supplementary information between the diagnosis target image and the candidate image (a value that decreases as the degree of matching decreases) is used as the corrected evaluation value. .

(Modification 2-3: Selection method)
In step S2020 in this embodiment, an example has been described in which the selection unit 55 selects one combination of candidate images with the highest evaluation value calculated in step S2010, but the present invention is not limited to this. For example, in step S2020, the selection unit 55 may select a plurality of combinations of candidate images having evaluation values higher than a predetermined value as a set of comparison images. In this case, the image processing unit 56 may perform similar comparison processing on each of the plurality of comparison image sets, and calculate the same number of comparison results as the number of comparison image sets. According to the above method, there is an advantage that the user can arbitrarily select and observe a desired comparison result from among the comparison results for a plurality of sets of comparison images that meet a predetermined condition.

(Modification 2-4: Comparison method)
In the process of step S1050 in this embodiment, the case where the image processing unit 56 generates a difference image or a superimposed image as a comparison process between a diagnosis target image and a set of comparison images has been described as an example. It is not limited to this. For example, the image processing unit 56 processes each of the comparison images constituting the set of comparison images so that the anatomical structure depicted in each comparison image substantially matches the anatomical structure depicted in the diagnosis target image. A deformed alignment process may be performed, and an image obtained by deforming each comparison image based on the result of the deformed position alignment process may be used as the result of the comparison process. According to this, there is an effect that the user can easily grasp the position in each comparison image forming the set of comparison images corresponding to the part of the user's attention in the diagnosis target image.

The implementation of the present invention is not limited to this, and the display control unit 57 may display the diagnosis target image and the set of comparison images side by side on the display unit 36 in step S1060. This has the advantage that a set of comparison images selected from a plurality of candidate images of the same subject as images suitable for comparison with the diagnosis target image can be displayed in a form that can be easily compared with the diagnosis target image.

Further, the information processing device 10 may be configured to perform only a process of storing information identifying the selected set of comparison images in the medical image database 23 in association with the diagnosis target image. In this case, when viewing a diagnosis target image using another image viewer, it is possible to load a set of linked comparison images and display them in a comparable format, or to It is possible to generate superimposed images and difference images.

(Modification 2-5: Save in association)
In this embodiment, a case has been described in which the display control unit 57 displays a comparison processing result between a diagnosis target image and a set of comparison images as the processing in step S1060, but the implementation of the present invention is not limited to this. . For example, the comparison result calculated in step S1050 by the image processing unit 56 may be stored in the medical image database 23, and the control unit 37 may obtain it through a user's operation or the like. Then, a mechanism may be provided in which the display control unit 57 displays the comparison results obtained from the medical image database 23 through processing similar to step S1060. In this case, it is preferable that the control unit 37 saves the comparison processing result in association with the diagnosis target image acquired in step S1010 or the comparison image included in the set of comparison images selected in step S2020.

The information processing apparatus 10 according to the present embodiment performs a comparison process between a diagnosis target image and a comparison image regarding a subject for which a user intends to perform medical treatment, and provides the result of the comparison process to the user. As a specific example, a case will be described in which there are multiple images (hereinafter referred to as candidate images) of the same subject captured on a different date and time from the imaging date and time of the diagnosis target image. The information processing device 10 according to the present embodiment selects an image suitable for comparison with the diagnosis target image from among the plurality of candidate images as a comparison image based on information regarding the imaging date and time of the diagnosis target image and the imaging date and time of the candidate image. select.

The overall configuration of the medical information processing system according to this embodiment is the same as that shown in FIG. 4 used in the explanation of the second embodiment. However, only the details of the processing performed by the evaluation unit 61 differ from the second embodiment. Further, the processing procedure executed by the information processing apparatus 10 according to the present embodiment is the same as that in FIG. 5 used in the description of the second embodiment. In steps S1010 to S2000 in FIG. 5, the information processing device 10 executes the same processing as in the second embodiment. A detailed explanation will be omitted here.

(Step S2010)
In this step, the evaluation unit 61 executes a process of calculating an evaluation value regarding comparison with the diagnosis target image for each of the combinations of candidate images generated in step S2000.

In this embodiment, the evaluation unit 61 calculates the following evaluation values in addition to the evaluation values (evaluation values based on the overlapping range) calculated using the same method as in step S2010 of the second embodiment. That is, the evaluation unit 61 also calculates the imaging date and time (imaging date) of each candidate image included in the combination of candidate images to be evaluated, and the evaluation value based on the imaging date and time of the diagnosis target image (evaluation value based on the imaging date and time). do. Then, the evaluation unit 61 calculates an evaluation value by integrating (for example, adding or multiplying) the above two evaluation values.

As a specific example of calculating the evaluation value based on the imaging date and time, the evaluation value is calculated based on the difference between the imaging date and time of the image to be diagnosed and the imaging date and time (imaging date) of each candidate image included in the combination of candidate images. There are possible ways. More specifically, the period (elapsed period) between the imaging date and time of the image to be diagnosed and the representative value of the imaging date and time of the candidate image included in the candidate image combination (representative imaging date and time of the candidate image combination) is long. In this case, a high value can be calculated as the evaluation value. Here, the representative value is the average imaging date and time of candidate images included in the combination of candidate images, the oldest or newest imaging date and time, and the like. According to this, in step S2020, which will be described later, a combination of candidate images with a long elapsed time is preferentially selected based on the imaging date and time of the image to be diagnosed. Note that conditions based on the imaging date and time of the diagnostic target image and the representative imaging date and time of the combination of candidate images include, in addition to the above, conditions based on the imaging date and time of the diagnostic target image and the imaging date and time of the candidate image described in Example 1. Various conditions based on the above can be used. Here, if the condition is that there is no prescribed treatment such as surgery between images to be diagnosed, the oldest candidate image included in the combination of candidate images is used as the representative imaging date and time of the combination of candidate images. It is desirable to set the imaging date and time.

Note that the method of calculating the evaluation value by the evaluation unit 61 is not limited to the method exemplified above. For example, the evaluation unit 61 sets a low evaluation value when the variation in the imaging date and time (imaging date) of the candidate images included in the combination of candidate images is large (for example, the interval between the oldest imaging date and time and the latest imaging date and time). may be calculated. In this case, the evaluation value does not depend on the imaging date and time of the image to be diagnosed. Furthermore, the evaluation unit 61 determines that when the ratio between the imaging date and time of the diagnosis target image and the imaging date and time of the oldest candidate image is large, and the ratio between the imaging date and time of the diagnosis target image and the imaging date and time of the newest candidate image, A low value may be calculated as the evaluation value. According to this, combinations made up of candidate images with small differences in imaging date and time are preferentially selected. According to this, a combination of candidate images that minimizes the difference between candidate images is preferentially selected.

Note that the conditions regarding the imaging date and time may be a combination of the above conditions.

Note that the condition under which the evaluation unit 61 calculates the evaluation value regarding the imaging date and time may be a pre-fixed condition, or as in the first embodiment, a condition setting unit (not shown) may be provided to allow the user to calculate the evaluation value. It may be possible to set the settings according to the purpose.

In steps S2020 to S1060, the information processing device 10 performs the same processing as in the second embodiment. A detailed explanation will be omitted here.

As described above, in this embodiment, the information processing apparatus 10 includes the selection unit 55 that selects the comparison image (second image) to be compared with the diagnosis target image (first image) from a plurality of candidate images. an imaging date and time acquisition unit 53 that acquires the imaging date and time when a plurality of candidate images were captured; a combination generation unit 60 that sets a plurality of combinations of the plurality of candidate images; and a condition setting unit 54 that sets conditions regarding the imaging date and time. The selection unit 55 further includes a selection unit 55 that selects at least one combination from the plurality of combinations based on the conditions regarding the imaging date and time set by the condition setting unit 54 and the imaging date and time of the candidate image. A candidate image included in the selected combination is selected as a comparison image (second image). Furthermore, the evaluation unit 61 obtains the evaluation values of the imaging date and time of the plurality of candidate images with respect to the conditions regarding the imaging date and time, and the selection unit 55 selects at least one candidate image from the plurality of candidate images based on the evaluation values. You may.

According to the procedure described above, the processing of the information processing apparatus 10 in this embodiment is executed. This embodiment has the advantage of being able to select a plurality of comparison images that can be more suitably compared based on the imaging date and time of the diagnosis target image and the candidate image, and providing the user with the results of comparison processing of those images.

(Modification 3-1)
Although the present embodiment has been described as an example in which the imaging date and time of the diagnosis target image and the imaging date and time of the candidate image are used in the evaluation value calculation process executed as step S2010, the implementation of the present invention is not limited to this. For example, when generating a combination of candidate images in step 2000, a condition is set on the length of the period between the imaging date and time of the diagnosis target image and the imaging date and time of the candidate image, and a combination of candidate images that satisfies the condition is generated. You may also do so. Alternatively, a condition may be set for variations in imaging date and time among candidate images, and a combination of candidate images satisfying the condition may be generated. In addition, conditions are set regarding whether surgery or treatment has been performed on the subject during the period between the imaging date and time of the diagnosis target image and the imaging date and time of the candidate image, and a combination of candidate images that satisfy the conditions is generated. You may also do so. For example, when generating a combination of candidate images, the imaging dates and times of a plurality of comparison images constituting the combination can be set within a predetermined range (for example, within one year). According to this, it becomes possible to omit the process of generating a combination of candidate images that do not satisfy a predetermined condition and the process of calculating an evaluation value, and it is expected that the process will become more efficient.

(Modification 3-2)
The evaluation unit 61 can calculate an evaluation value based on the contrast conditions of the diagnosis target image and the candidate image. Specifically, a high evaluation value can be calculated for a combination of candidate images made up of candidate images with the same contrast condition as the contrast condition of the diagnosis target image. In addition to this, for example, evaluation values can be calculated based on variations in contrast conditions of a plurality of candidate images included in a combination of candidate images. For example, when dealing with the presence or absence of contrast enhancement as a contrast condition, a combination of candidate images consisting only of images with contrast enhancement (or images of the same time phase of contrast enhancement) or a combination of candidate images consisting only of images without contrast enhancement can be made to have a higher evaluation value. Furthermore, the evaluation value can be calculated based on both the evaluation based on the difference between the contrast conditions of the diagnosis target image and the contrast conditions of the candidate images, and the dispersion of the contrast conditions of the plurality of candidate images constituting the combination of candidate images. . For example, a higher evaluation value can be calculated for a combination of candidate images made up of only images with the same contrast conditions as the diagnosis target image. In addition, when the diagnosis target image and candidate image are MRI images, the evaluation value is calculated based on the type of image sequence (for example, T1 or T2) using the same method as explained as an example of contrast conditions. You can do it like this. According to these methods, a high evaluation value is calculated for a combination of candidate images made up of candidate images whose image characteristics match those of the image to be diagnosed, and as a result, it is possible to provide the user with suitable comparison processing results. be.

(Modification 3-3)
In step S2010, the evaluation unit 61 may calculate the evaluation value not based on the overlapping range of imaging between the candidate image and the diagnosis target image, but based on the imaging date and time of each image. Here, the evaluation value can be calculated based on the imaging date and time of each image using the method described above. According to this, the evaluation value based on the overlap range is not important, such as when it is known that the overlap range with the diagnosis target image is almost the same between each of the combinations of the plurality of candidate images generated in step S2000. This has the effect of allowing more efficient processing in some cases.

<Other Examples>
It is also possible to combine at least two of the plurality of modifications described above.

Further, the disclosed technology can be implemented as, for example, a system, an apparatus, a method, a program, a recording medium (storage medium), or the like. Specifically, it may be applied to a system consisting of multiple devices (for example, a host computer, an interface device, an imaging device, a web application, etc.), or it may be applied to a device consisting of a single device. good.

Moreover, it goes without saying that the object of the present invention is achieved by the following steps. That is, a recording medium (or storage medium) recording a software program code (computer program) that implements the functions of the embodiments described above is supplied to the system or device. Such a storage medium is, of course, 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 read from the recording medium itself realizes the functions of the embodiments described above, and the recording medium on which the program code is recorded constitutes the present invention.

10 Information processing device 21 LAN
23 Medical image database 31 Communication IF
32 ROM
33 RAM
34 Storage unit 35 Operation unit 36 Display unit 50 Control unit 51 Diagnosis target image acquisition unit 52 Comparison candidate image acquisition unit 53 Photographing date and time acquisition unit 54 Condition setting unit 55 Selection unit 56 Image processing unit 57 Display control unit

Claims (18)

An information processing apparatus comprising a selection means for selecting a second image to be compared with the first image from a plurality of candidate images,
acquisition means for acquiring the imaging date and time when the plurality of candidate images were taken;
and a condition setting means for setting conditions regarding the imaging date and time,
The selection means selects at least one candidate image from the plurality of candidate images as the second image based on a condition regarding the imaging date and time set by the condition setting means and the imaging date and time of the plurality of candidate images. An information processing device characterized by: The condition setting means sets as a condition regarding the imaging date and time that the imaging date and time is the closest to the first image, and the selection means selects from the plurality of candidate images the imaging date and time that is closest to the first image. The information processing apparatus according to claim 1, wherein a candidate image that satisfies the condition of being closest is selected as the second image. The condition setting means sets the latest imaging date and time as a condition regarding the imaging date and time, and the selection means selects a candidate image that satisfies the condition that the imaging date and time is the latest from among the plurality of candidate images. The information processing apparatus according to claim 1, wherein the information processing apparatus selects the image as the second image. The condition setting means sets, as a condition for the imaging date and time, that the imaging date and time is within a predetermined period based on the imaging date and time of the first image, and the selection means selects one of the plurality of candidate images. 2. The information processing apparatus according to claim 1, wherein a candidate image that satisfies the condition that the image was taken within the predetermined period is selected as the second image. The condition setting means sets, as a condition for the imaging date and time, that the imaging date and time does not involve a predetermined treatment between the imaging date and time of the first image, and the selection means selects one of the plurality of candidate images. , selecting as the second image a candidate image that satisfies the condition that the imaging date and time do not include the predetermined treatment between the imaging date and time of the first image. information processing equipment. The condition setting means sets, as a condition for the imaging date and time, that the imaging date and time does not involve a change in modality between the imaging date and time of the first image, and the selection means selects the plurality of candidate images. According to claim 1, a candidate image that satisfies the condition that the imaging date and time does not involve a change in modality between the imaging date and time of the first image is selected as the second image. The information processing device described. The information processing apparatus according to claim 1, wherein the selection means selects at least one candidate image from the plurality of candidate images based on supplementary information other than the imaging date and time. 8. The information processing apparatus according to claim 7, wherein the additional information other than the imaging date and time includes at least one of an imaging range, an imaging site, an imaging condition, a reconstruction condition, a slice thickness, and a contrast condition. The selection means further includes evaluation means for obtaining evaluation values of the imaging date and time of the plurality of candidate images for the conditions regarding the imaging date and time, and the selection means selects at least one candidate image from the plurality of candidate images based on the evaluation values. 2. The information processing apparatus according to claim 1, wherein the information processing apparatus selects. The information processing apparatus according to any one of claims 1 to 9, further comprising generation means for generating a difference image from the first image and the second image. An information processing device comprising selection means for selecting a second image to be compared with the first image from among a plurality of candidate images,
acquisition means for acquiring the imaging date and time when the plurality of candidate images were taken;
Setting means for setting a plurality of combinations of the plurality of candidate images;
a condition setting means for setting conditions regarding the imaging date and time;
combination selection means for selecting at least one combination from the plurality of combinations based on the conditions regarding the imaging date and time set by the condition setting means and the imaging date and time of the candidate image;
The information processing apparatus is characterized in that the selection means selects the candidate image included in the combination selected by the combination selection means as the second image. An information processing device comprising selection means for selecting a second image to be compared with the first image from among a plurality of candidate images,
Setting means for setting a plurality of combinations of the plurality of candidate images;
Overlapping range calculating means for calculating an overlapping range between the candidate images included in the plurality of combinations and the first image;
combination selection means for selecting at least one combination from the plurality of combinations based on the overlapping range;
The information processing apparatus is characterized in that the selection means selects the candidate image included in the combination selected by the combination selection means as the second image. An information processing method for selecting a second image to be compared with a first image from a plurality of candidate images, the method comprising:
acquiring the imaging date and time when the plurality of candidate images were taken;
a step of setting conditions regarding imaging date and time;
An information processing method comprising the step of selecting at least one candidate image from the plurality of candidate images as the second image based on the set condition and the imaging date and time of the plurality of candidate images. An information processing method for selecting a second image to be compared with a first image from a plurality of candidate images, the method comprising:
acquiring the imaging date and time when the plurality of candidate images were taken;
setting a plurality of combinations of the plurality of candidate images;
a step of setting conditions regarding imaging date and time;
selecting at least one combination from the plurality of combinations based on the conditions regarding the imaging date and time and the imaging date and time of the candidate image;
An information processing method comprising the step of selecting the candidate image included in the selected combination as the second image. An information processing method for selecting a second image to be compared with a first image from a plurality of candidate images, the method comprising:
setting a plurality of combinations of the plurality of candidate images;
calculating an overlapping range between the candidate images included in the plurality of combinations and the first image;
selecting at least one combination from the plurality of combinations based on the overlapping range;
An information processing method comprising the step of selecting the candidate image included in the selected combination as the second image. A program for causing a computer to execute the information processing method according to any one of claims 13 to 15. An information processing device comprising selection means for selecting a second image to be compared with the first image from among a plurality of candidate images,
and acquisition means for acquiring the imaging date and time when each of the candidate images was captured,
The information processing device is characterized in that the selection means selects the second image from the candidate images based on the context between the date of treatment or surgery for the subject and the imaging date and time of each of the candidate images. . An information processing device comprising selection means for selecting a second image to be compared with the first image from among a plurality of candidate images,
acquisition means for acquiring the imaging date and time when each of the candidate images was captured;
a setting means for setting a plurality of combinations of the candidate images;
combination selection means for selecting one of the combinations of candidate images based on an interval between imaging dates and times between candidate images included in the combination of candidate images;
The information processing apparatus is characterized in that the selection means selects a candidate image included in the combination of candidate images selected by the combination selection means as the second image.

Images