JP5846925B2 - Medical image display device - Google Patents

Description

  The present invention relates to a medical image display device suitable for a medical institution or the like.

  In a medical institution or the like, a medical image captured by a medical image capturing apparatus is registered and stored in a server that manages medical images. In addition to diagnostic interpretation of registered medical images, doctors, etc., provide various types of findings and biopsy information that are given as examination information for the same patient or examiner (hereinafter collectively referred to as the subject). A comprehensive diagnosis is also made.

  In recent years, a system that supports future examination and treatment planning of a subject has been put into practical use by providing similar medical images and case information based on the region of interest and various information of the medical image of the subject. Yes. In particular, there is a demand for a system capable of efficiently displaying similar case information on a screen from a large amount of stored and stored medical images and examination information.

  Patent Document 1 discloses a data search system that displays similar cases extracted based on the similarity in order of increasing similarity.

JP 2010-79568 A

  However, in Patent Document 1, although case information is rearranged according to the degree of similarity, rearrangement of similar case information based on the degree of recovery or the like is not considered.

  The object of the present invention has been made in view of the above-mentioned problems, and in similar case retrieval based on medical images, case information according to the user's purpose is efficiently displayed to diagnose for treatment planning. To provide a medical image display device and a medical image display method for providing support information.

  In order to achieve the above-described object, the first invention is a medical image display device that is connected to a medical image database that stores medical images and case information associated with the medical images via a network, and displays the medical images. The medical image, the medical image to be acquired out of the case information, the case information and the input means for inputting the region of interest of the acquired medical image, and the medical image and the case information from the medical image database. Obtaining, extracting the region of interest of the medical image, searching the medical image database using the feature amount of the region of interest as a search condition, and arranging them based on the similarity defined by the degree of similarity of the feature amount A similarity case list is created, and the degree of recovery defined by the degree of recovery by treatment of the diagnosis subject is used as a reference for the similarity case list. And control means for creating an ordered degree of recovery cases listed, a medical image display apparatus characterized by comprising a display means for displaying the similarity case list and the degree of recovery cases list.

  According to the present invention, a case list with similarity based on the similarity of medical images and a case list with recovery based on the degree of recovery registered by the user for each case are arranged on the screen at the same time. Can be displayed. As a result, it is possible to compare and refer to case lists lined up with two different reference items, and to support more efficient diagnosis and examination / treatment plan planning from a wider viewpoint.

  The display means further displays a vector diagram having the similarity as a first vector axis and the recovery degree as a second vector axis, and the control means displays an arbitrary point on the vector diagram as a reference point. And the degree of coincidence case list arranged based on the degree of coincidence defined by the distance from the reference point to each case information on the vector diagram with respect to the similarity case list or the recovery case list It is desirable to create.

  As a result, it is possible to display a case list rearranged by the proximity of the reference point arbitrarily selected by the user, using a vector diagram centered on two different sort reference items. This makes it possible to provide a list of cases intended by the user numerically without depending on the subjectivity of the user, and to assist in making a more rational diagnosis and examination / treatment plan.

  In addition, the control unit performs filtering processing on the similarity case list, the recovery case list, or the coincidence case list according to a progress degree defined by a progress degree of a medical condition of a diagnosis target person It is desirable to create a progress case list.

  This makes it possible to efficiently refer to examination / treatment methods for cases progressing to the same extent.

  According to the present invention, a diagnostician can easily obtain a list of similar cases according to the purpose from a vast amount of medical images and case information, and can diagnose more accurately and efficiently, and can be more accurate and comprehensive. Can make a proper examination and treatment plan.

The block diagram which shows an example of a structure of the medical image display apparatus 1 Flowchart diagram in the first embodiment Flowchart diagram in the second embodiment Display example of region of interest extraction screen and similar case search function screen of medical image display device 1 Example of similar case list display screen (when similarity “area” is selected) in the first embodiment Example of a standard diagram of the degree of recovery in the first embodiment Example of similar case list and vector diagram display screen in the second embodiment Flowchart diagram in the third embodiment Window display example of progress filter list in the third embodiment Flowchart diagram in the fourth embodiment Window display example of filter types and items in the fourth embodiment

DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, preferred embodiments of a medical image display device and the like according to the invention will be described with reference to the drawings.
First, the hardware configuration of the medical image display apparatus 1 according to the embodiment of the present invention will be described with reference to FIG.

  As shown in FIG. 1, the medical image display apparatus 1 includes a CPU 2, a main memory 3, a storage device 4, a display memory 5, an input controller 7, and a network adapter 10 connected to each other via a system bus 11 so that signals can be transmitted and received. The computer system includes a device 15 (control means), a display device 6 (display means), and an input device 16 (input means) such as a mouse 8 and a keyboard 9. The medical image display apparatus 1 is connected to a medical image photographing apparatus 13 and a medical image database 14 via a network 12 so as to be able to transmit and receive signals. The numbers of the display device 6, the medical image photographing device 13, and the medical image database 14 are arbitrary, and are not limited to one as shown in FIG. Moreover, the control apparatus 15, the display apparatus 6, and the input device 16 may be integrated like a notebook PC or a tablet terminal.

  The CPU 2 of the medical image display device 1 is a device that controls each unit, and loads a program stored in the storage device 4 (hard disk or the like) and data necessary for program execution into the main memory 3 and executes the program. The storage device 4 acquires and stores images captured by the medical image capturing device 13 and images stored in the medical image database 14 via the network 12.

  The display device 6 displays an image using image information stored in the display memory 5. The mouse 8 and the keyboard 9 are operation devices used when the operator operates the medical image display apparatus 1. The network adapter 10 is a device for connecting the medical image display device 1 to the network 12.

  The medical imaging apparatus 13 is an apparatus that acquires medical image information of a subject such as an MRI apparatus, an X-ray CT apparatus, an ultrasonic apparatus, a scintillation camera apparatus, a PET apparatus, and a SPECT apparatus. The medical image database 14 is a database system or the like that stores medical images acquired by the medical image photographing device 13 and examination information.

  When the CPU 2 executes a medical image display method to be described later, the similar case list is rearranged, and the similar case list after the rearrangement is displayed on the display device 6. In FIG. 1, the medical image display device 1, the medical image photographing device 13, and the medical image database 14 are separate housings, but they may be configured as the same housing or one computer system.

The processing flow in the first embodiment will be described with reference to the flowchart of FIG.
In step S200, the user (diagnostic doctor) first selects a part of the medical image to be diagnosed. Here, the part refers to a part of the subject imaged by the medical image photographing apparatus 13 such as a brain, heart, lung, or the like.

  Next, in step S201, the user extracts a region of interest in the medical image to be diagnosed. For the extraction of the region of interest, a function capable of freely drawing a line by operating the mouse, such as a freehand function, is used.

  Here, FIG. 4 will be described. FIG. 4 is a display example of a region of interest extraction screen and a similar case search function screen displayed on the display device 6 of FIG. On the left side of the screen, a medical image to be diagnosed is acquired from the medical image database 14 and displayed. The screen example of FIG. 4 is a lung CT image. The medical image of FIG. 4 is used when the user performs an interpretation diagnosis, and is selected by the user from a list of past images recorded and stored in the medical image database 14 together with case information as a medical image of the subject to be diagnosed. Is displayed.

  In step S201 in FIG. 2, the user operates the free hand function using the mouse 8 on the left medical image in FIG. When the region of interest 401 is extracted, the CPU 2 calculates the area value of the region of interest 401 and the average value of the gradation within the region, and displays the value on the viewer 402 at the bottom of the screen. The area value and the average gradation value are calculated by a known image processing method.

  Further, the area value of the region of interest 401 calculated by the CPU 2 and the average value of the in-region gradation are recorded and stored in the medical image database 14 in association with the case information.

  Subsequently, in step S202, the user selects whether the past case list stored in the medical image database 14 is rearranged in order of decreasing area value of the region of interest 401 or in order of decreasing gradation value.

  This will be specifically described with reference to FIG. On the right side of the similar case search function screen of FIG. 4, there are an area value check box 403a and a gradation value check box 403b, which are alternative selection formulas. When one of the check boxes is checked, the other check box is blinded and cannot be checked. In step 202, the user checks either the area value check box 403a or the gradation value check box 403b, and selects which value is to be sorted in order of closeness.

  Further, the similar case search function screen of FIG. 4 has a check box 404a for displaying only the upper cases of the number of cases to be displayed as a search result and a check box 404b for displaying all the cases. Check one of them. When the user selects the upper display check box 404a, the number of cases to be displayed or the number of cases is numerically input. When 404b is selected, all cases are displayed (step S203).

  The user selects the area value or gradation value check box (403a or 403b) and the upper case or all cases check box (404a or 404b), inputs the area value or gradation value, and presses the search button 405 The search is performed (step S204).

  When the search button 405 is pressed, the CPU 2 selects cases with the same type of medical image capturing apparatus 13 and cases with the same examination site from the past case list. Further, the past case list is rearranged based on the rearrangement condition selected in step S202, and the case list A is created (step S205a).

Simultaneously with step S205a, the CPU 2 selects cases with the same type of medical imaging device 13 and the same examination site from the past case list, and arranges them based on the degree of recovery (described later) possessed by each case data. The replaced case list B is created.
The degree of recovery is that the user inputs in advance the degree of recovery of the subject with a 10-step evaluation for each diagnosis. The inputted recovery value is recorded and stored in the medical image database 14 in association with each case.

  Here, the degree of recovery input by the user will be described with reference to FIG. FIG. 6 is an example of a standard diagram of the degree of recovery of the subject. The horizontal axis is a scale in 10 steps from 0 (zero) to 10, the start of treatment is 0 (zero), complete cure is 10, and the diagnosis of the subject is improved as the value increases. When the user inputs the diagnosis information of the subject, the user inputs the degree of recovery based on the standard of FIG. Note that although the degree of recovery is 10 stages, the number of stages is not particularly limited and may be changed. Further, the user may instruct the setting change of the number of steps through the input device.

  In the case of the degree of recovery shown in FIG. 6, for example, in the case of a laceration, the horizontal axis indicates 0 when treatment is started after a laceration. Then, the doctor performs a suturing treatment on the laceration, and the state where the laceration is closed is set to 5, and the state where the laceration is fused and completely cured is set to 10. In some cases, the wound may easily suppurate depending on the constitution of the subject, and if the suppuration occurs even after the suturing is completed, the degree of recovery may be 3 or 4. Whether the subject is purulent or not may be contributed to the rearrangement of the case list as well as the degree of recovery. Further, since there is a difference in the degree of whether or not the subject is purulent, it may be divided into a plurality of stages in the same manner as the degree of recovery.

  Another example of the degree of recovery shown in FIG. 6 is, for example, for hepatitis, the horizontal axis indicates 0 when the treatment is started due to hepatitis. Then, the doctor prescribes the drug, the state where the area of hepatitis is half of the initial value at the time of illness is set to 5, and the state where the area of hepatitis disappears and is completely cured is set to 10. In addition, if the subject is an allergic constitution, the medicine prescribed for the subject may not be able to use an effective medicine prescribed for the subject not having the allergic constitution. Therefore, whether the subject is allergic or not may be contributed to the rearrangement of the case list in the same manner as the degree of recovery. In addition, since there is a difference in degree depending on whether or not the subject is allergic, it may be divided into a plurality of stages in the same manner as the degree of recovery.

  In step S206, the CPU 2 uses the case list A and the case list B as a trigger, and displays the case list A 501a and the case list B 501b side by side on the same screen as shown in FIG. 5 (described later).

Here, an example of the similar case list display screen in FIG. 5 (when the similarity “area” is selected) will be described.
FIG. 5 is an example of a similar case list display screen when the user selects an area value in step S202 of FIG. In step S206, the CPU 2 displays the case list A501a (similarity case list) in which the case list is rearranged in the descending order of the similarity of the area values on the left side of the display device 6, and the case list on the right side of the screen The case list B501b (recovery degree case list) rearranged from is displayed. The similarity case list is generally a case list in which the medical image database 14 is searched using the feature quantity of the region of interest as a search condition, and arranged based on the similarity defined by the degree of similarity of the feature quantity. Further, the recovery degree case list is generally a case list arranged on the basis of the recovery degree defined by the degree of recovery by the treatment of the diagnosis subject with respect to the similarity case list.

  Similarly, when the user selects a gradation value in step S202, the CPU 2 displays a case list A501a in which the case list is rearranged in descending order of similarity of the gradation values on the left side of the screen. Furthermore, there are a vector diagram button 502 and a filter button 503 (described later) at the lower right of the screen.

  In this way, by using the similarity and the recovery degree as the sorting criteria when displaying the similar case search result, the user simultaneously compares the case with the high similarity and the case with the high recovery degree in the first diagnosis. This makes it possible to efficiently make diagnosis, examination and treatment plans from various fields. For example, it is possible to use a method such as a case where the degree of similarity is low but a case where the degree of recovery is high is used for future treatment planning.

Next, a second embodiment according to the present invention will be described with reference to FIGS.
In the first embodiment, in the rearrangement of the case list of the similar case search result, the rearrangement is performed in each case list by one reference item of the similarity or the recovery degree. On the other hand, in the second embodiment, a method of using two reference items for one rearrangement will be described.

  After searching the case list of similarity, use a vector diagram that takes any two reference items on the vertical and horizontal axes, and the absolute value of the distance between the point that the user clicked on the vector diagram and the point of the past case calculate. For calculating the absolute value of the distance, the following well-known formula is used.

d = √ {(x1-x2) ² + (y1-y2) ² } (Formula 1)
((Expression 1) is an expression for obtaining the distance d between point 1 (x1, y1) and point 2 (x2, y2))

  The distance calculated by Equation 1 becomes a new sorting reference item created by the user's weighting. By rearranging similar cases using this new reference item, the similar case list can be displayed in the order intended by the user.

Here, the flow of processing in the second embodiment will be described with reference to FIGS.
First, each step of FIG. 3 will be described in detail.
When the vector diagram button 502 is pressed from step S206 in which the similar case list is displayed in FIG. 5 (step S301), the CPU 2 uses the step S301 as a trigger, and the CPU 2 uses the vector and the vertical axis and horizontal axis to indicate the similarity and the recovery degree (step S301). A vector diagram 701 in FIG. 7 is created and displayed on the display device 6 (step S302).

  Here, an example of the vector diagram of FIG. 7 will be described. FIG. 7 is a screen displayed when the user presses the vector diagram button 502 from the similar case list display screen of FIG. A case list 706 (matching case list) arranged in ascending order of absolute values of points and distances specified by the user on the left side of the screen, that is, in descending order of matching degree, is displayed on the right side of the screen, and the degree of similarity and recovery degree are plotted on the vertical axis. A vector diagram 701 with the horizontal axis is displayed. The coincidence case list is generally a case list arranged based on the coincidence defined by the distance from the reference point on the vector diagram to each case information with respect to the similarity case list or the recovery case list. is there. In FIG. 7, the similarity on the vertical axis is an area value. On the similar case list display screen in FIG. 5, when the case list A 501a of similarity is a gradation value, the user presses the vector diagram button 502 in step S301. In this case, the vertical axis in FIG.

In step S303, the user clicks an arbitrary point as a user click point (reference point) 702 on the vector diagram 701 in step S302.
Next, the CPU 2 uses the expression 1 to calculate the points of each case from the reference point 702 selected by the user in step S303, specifically, the point 703 of the case 1, the point 704 of the case 2, and the point 705 of the case 3 The distance is calculated (step S304).

  Based on the distance to the point of each case calculated in step S304, the CPU 2 displays a case list C706 in which the cases are rearranged in ascending order of distance, that is, from the case having the highest degree of coincidence with the point designated by the user. Create (step S305). Subsequently, in step S306, the case list C706 created in step S305 is displayed on the screen of the display device 6.

  In this way, the selection of similar cases using the two reference items of the similarity and the recovery degree is largely dependent on the user's sense in the first embodiment. In the second embodiment, since a list of cases having a high degree of coincidence with the case intended by the user can be posted with a numerical value of the distance from the two reference items, the user can perform more rational diagnosis, examination / treatment. You can make a plan.

  In the above description, the area value and the gradation value are used as examples of items for calculating similarity, but other items for calculating similarity may be used.

  Next, in the case lists A, B, and C created in the first embodiment and the second embodiment, a third reference item called progress is added to perform filtering, and the progress case list is displayed. A third embodiment to be created will be described. The progress case list is generally a case where filtering processing is applied to the similarity case list, the recovery case list, or the coincidence case list according to the progress degree defined by the progress degree of the medical condition of the diagnosis target person It is a list.

  First, the degree of progression indicates an index of how much the condition of the subject has progressed at the time of diagnosis. For example, at the time of diagnosis, a user selects a four-stage index for a case of a subject to be diagnosed. This will be specifically described with reference to FIG. FIG. 9 is a window display example of the progress filter list. The progress is divided into four stages, the progress I 901a is “follow-up”, the progress II 902b is “hospital required”, the progress III 903c is “surgery required”, and the progress IV 904d is “end stage”. The user selects stages I to IV in advance of the degree of progression of the medical condition of the subject at the time of diagnosis, and records and stores them as case information in the medical image database 14.

  In the third embodiment, when the case list is displayed (step S206 and step S306) in the first embodiment and the second embodiment, the current diagnosis target is selected from the four stages of progress. Filtering is performed by selecting the degree of progression of a disease state of a subject, and only cases having the same degree of progression as the degree of progression selected from the case list are displayed.

Although the degree of progress is four, the number of stages is not particularly limited and may be changed. Further, the setting change of the number of steps may be instructed by the user via the input device.
The processing flow of the third embodiment will be described in detail with reference to the flowchart of FIG.

  In step S801, the user presses the filter button 503 at the lower right of the screen in FIG. 5 that displays the case list A and the case list B side by side on the same screen of the display device 6 in step S206 in the first embodiment, or In step S306 in the second embodiment, the filter button 707 at the lower left of the screen in FIG. 7 that displays the case list C on the display device 6 is pressed.

Using step S801 as a trigger, the CPU 2 displays the progress filter list window of FIG. 9 on the display device 6 (step S802).
Next, from the progress filter list window of FIG. 9, the progress as an index of the filter is selected from the progress I 901a to the progress IV 901d of FIG. 9 and input to the check box (step S802).

  When the user inputs a check in the progress check box, the OK button 902 and the apply button 903 in FIG. 9 change from inactive to active using that as a trigger, so the user presses the OK button 902 or the apply button 903. (Step S803).

  Using step S803 as a trigger, the CPU 2 selects only cases having the same progress as the progress selected by the user in step S802 from the case list A, B, or C, and creates a case list D (step S804).

  Further, the CPU 2 displays the case list D created in step S804 on the display device 6 (step S805).

  In the third embodiment, the similar case list displayed in the first embodiment and the second embodiment can be further narrowed down by applying a progress degree filter to the more accurate similar case search. It is possible to connect to the diagnosis by, and the examination / treatment plan of the case closer to the diagnosis target.

  Next, a description will be given of a fourth embodiment in which a narrowing search using a similar case filter in the third embodiment is performed using a plurality of filter items having a degree of freedom.

The processing flow of the fourth embodiment will be described in detail with reference to the flowchart of FIG.
When the user presses the filter button 503 or 707 in step S801 in FIG. 8, the CPU 2 displays a list of set filter items on the screen using step S801 as a trigger (step S1000).

Here, the filter items are items in which the user freely sets and registers filter types and detailed items in advance in order to narrow down the case search.
Here, the flow of the processing in FIG. 10 will be described with reference to FIG. 11 in which the types and items of the filters are displayed in the window.

  FIG. 11 is a list of filter items displayed in step S1000. In the third embodiment, only the degree of progress filter is used, but in the fourth embodiment, a plurality of set filters are displayed as a list at the same time.

  In step S1000, the CPU 2 displays the filter type and all items as shown in FIG. In the case of FIG. 11, the filter set by the user is the fifth type, and includes basic data 1101, treatment period 1102, treatment content 1103, an abnormal part 1104 other than the diagnosis target, and a recurrence frequency 1105 at the diagnosis target part. A check box is displayed for each filter type. When the user inputs a check in the check box of the filter type, the check box of the detailed filter item in the type is changed from inactive to active, and the user can input. A plurality of filter items and detailed items can all be selected.

Note that the contents of the filter items and the contents and number of items are arbitrary, and the setting is instructed by the user via the input device.
Here, an example of filter items and detailed items shown in FIG. 11 will be described in order.

  In the basic data 1101, for example, items of age, sex, and lifestyle are set as detailed items. Under age items 1101a, 10's 1101b and 20's 1101c, gender items 1101d and 1101e, and lifestyle items include sake 1101f and tobacco 1101g.

  In the treatment period 1102, for example, detailed items 1102a for 3 months, 1102b for 6 months, 1102c for 1 year, and 1102d for 2 years are set.

  In the treatment content 1103, medication 1103a, radiation treatment 1103b, palliative care 1103c, and the like are set.

  In an abnormal region 1104 other than the diagnosis target, a brain 1104a, a lung 1104b, a stomach 1104c, and the like are set.

  For the frequency of recurrence 1105 at the site to be diagnosed, 1105a, second time 1105b, third time 1105c, etc. are set for the first time.

  The user selects a filter item necessary for obtaining the intended case list (step S1001), and further selects a detailed filter item in the item and inputs it to the check box (step S1002).

  When the user inputs a check in the check box of the filter item, the OK button 1110 and the apply button 1111 in FIG. 11 change from inactive to active, and the user presses the OK button 1110 or the apply button 1111. Step S1003).

  Using step S1003 as a trigger, the CPU 2 selects only cases having the same conditions as the filter item selected by the user in step S1002 from the case list A, B, or C, and creates a case list E (step S1004). Further, the CPU 2 displays the case list E created in step S1004 on the display device 6 (step S1005).

  As a result, the case list A arranged in the order of similarity includes not only the similarity of the area value and the gradation value, but also the similarity of the degree of progress determined comprehensively from other items, and is more accurate. A list of cases similar to. Case list B, arranged in order of recovery degree, can use the progress filter to refer to examination / treatment methods for cases that are progressing to the same extent, and to plan more effective examination / treatment methods I can do it. Furthermore, the case list C arranged on the basis of both the degree of similarity and the degree of recovery can support efficient referencing of more similar past cases having a higher degree of recovery by adding a progress degree filter.

  In addition, by applying filter processing based on the basic data of the subject and the treatment period and content in the filter items set by the user, what kind of treatment can be expected to recover early, or the effect can be improved It is possible to make a treatment plan more accurately and considering the time axis. In addition, when the subject is a cancer patient or the like, a more comprehensive and overall diagnosis can be performed by adding filter items such as abnormal sites other than the diagnostic target and the frequency of recurrence at the diagnostic target site.

  The preferred embodiments of the medical image display apparatus and the like according to the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to such examples. It will be apparent to those skilled in the art that various changes or modifications can be conceived within the scope of the technical idea disclosed in the present application, and these naturally belong to the technical scope of the present invention. Understood.

1: Medical image display device 8: Display device (display means)
14: Medical image database 15: Control device (control means)
16: Input device (input means)
501a: Case list A (similarity case list)
501b: Case list B (recovery degree case list)
701: Vector diagram 706: Case list (coincidence case list)

Claims (3)

A medical image display device connected via a network to a medical image database for storing medical images and case information associated with the medical images, and displaying the medical images,
Input means for inputting the medical image, the medical image to be acquired among the case information, the case information, and the region of interest of the acquired medical image;
The medical image and the case information are acquired from the medical image database, the region of interest of the medical image is extracted, the medical image database is searched using the feature amount of the region of interest as a search condition, and the similarity of the feature amount A similarity case list is created that is arranged based on the similarity defined by the degree of similarity, and the similarity case list is arranged based on the degree of recovery defined by the degree of recovery by the treatment of the diagnosis subject. A control means for creating a recovery case list,
Display means for displaying the similarity case list and the recovery case list;
A medical image display device comprising: The display means further displays a vector diagram having the similarity as a first vector axis and the recovery as a second vector axis,
The control means accepts an arbitrary point on the vector diagram as a reference point, and the distance from the reference point on the vector diagram to each case information with respect to the similarity case list or the recovery case list The medical image display apparatus according to claim 1, wherein a coincidence case list arranged based on the coincidence defined by is created. The control means is a degree of progress obtained by filtering the similarity case list, the recovery case list, or the coincidence case list according to the degree of progress defined by the degree of progress of the medical condition of the diagnosis subject the medical image display device according to 請 Motomeko 2 you, characterized in that to create a case list.

Images