Medical image display device, medical image display system, program, and medical image display method

Abstract

To intelligibly display which medical image must be preferentially checked first out of a plurality of medical images including lesion candidate regions.SOLUTION: An image display system 100 and a medical image display device 6 comprise: an acquisition unit for acquiring a series of medical images including a plurality of medical images; an extraction unit for performing image analysis on the plurality of medical images to extract a plurality of medical images including lesion candidate regions; a calculation unit that for at least two medical images of the plurality of extracted medical images including the lesion candidate regions, calculates lesion information on a lesion candidate region included in each medical image; and a control unit that on the basis of the lesion information in each medical image whose lesion information is calculated, controls display of information indicating lesion candidate region existence of the plurality of medical images including the lesion candidate regions.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to a medical image display device, a medical image display system, a program, and a medical image display method.

Background Art

[0002] Conventionally, a technique is known in which a series of medical images including a plurality of medical images is subjected to image analysis, and the positions of medical images including lesion candidate regions are displayed on a slider bar. For example, Patent Document 1 describes that a mark indicating the position of a cross-sectional image in which an abnormal shadow candidate is detected among a plurality of cross-sectional images constituting a CT image is displayed on a slider bar. Further, Patent Document 1 discloses that when displaying the above marks, the displayed and non-displayed marks are displayed so as to be distinguishable.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, when analyzing medical images by CAD (Computer Aided Diagnosis), AI (Artificial Intelligence), etc. to detect lesion candidate regions, the number of detected lesion candidate regions has increased due to the improvement of detection performance. Therefore, in the technique described in Patent Document 1, there is a problem that the number of marks indicating the positions of cross-sectional images including lesion candidate regions displayed on the slider bar increases too much, and it is not clear which cross-sectional image should be viewed preferentially.

[0005] The present invention has been made in view of the above problems, and an object thereof is to clearly display which medical image should be preferentially viewed among a plurality of medical images including lesion candidate regions.

Means for Solving the Problem

[0006] To solve the above problems, the medical image display device of the present invention includes: an acquisition unit that acquires a series of medical images including a plurality of medical images; an extraction unit that extracts a plurality of medical images including a lesion candidate region by performing image analysis on the plurality of medical images; a calculation unit that calculates lesion information of the lesion candidate regions included in each of at least two of the plurality of medical images including the extracted lesion candidate regions; a control unit that controls the display of information indicating the presence of the lesion candidate regions in the plurality of medical images including the lesion candidate regions based on the lesion information of each of the medical images for which the lesion information has been calculated.

[0007] The medical image display system of the present invention includes: an acquisition unit that acquires a series of medical images including a plurality of medical images; an extraction unit that extracts a plurality of medical images including a lesion candidate region by performing image analysis on the plurality of medical images; a calculation unit that calculates lesion information of the lesion candidate regions included in each of at least two of the plurality of medical images including the extracted lesion candidate regions; a control unit that controls the display of information indicating the presence of the lesion candidate regions in the plurality of medical images including the lesion candidate regions based on the lesion information of each of the medical images for which the lesion information has been calculated; and includes.

[0008] The program of the present invention causes a computer to: function as an acquisition unit that acquires a series of medical images including a plurality of medical images, an extraction unit that extracts a plurality of medical images including a lesion candidate region by performing image analysis on the plurality of medical images, a calculation unit that calculates lesion information of the lesion candidate regions included in each of at least two of the plurality of medical images including the extracted lesion candidate regions, and a control unit that controls the display of information indicating the presence of the lesion candidate regions in the plurality of medical images including the lesion candidate regions based on the lesion information of each of the medical images for which the lesion information has been calculated. A control unit that controls the display of information indicating the presence of lesion candidate regions in a plurality of medical images including the lesion candidate region based on the lesion information of each medical image for which the lesion information has been calculated. Function as.

[0009] The medical image display method of the present invention A step of acquiring a series of medical images including a plurality of medical images; A step of performing image analysis on the plurality of medical images to extract a plurality of medical images including lesion candidate regions; A step of calculating lesion information of the lesion candidate regions included in each medical image for at least two of the plurality of medical images including the extracted lesion candidate regions; A step of controlling the display of information indicating the presence of lesion candidate regions in a plurality of medical images including the lesion candidate region based on the lesion information of each medical image for which the lesion information has been calculated; Including.

Effect of the Invention

[0010] According to the present invention, it is possible to display in an easy-to-understand manner which medical image among a plurality of medical images including a lesion candidate region should be viewed preferentially.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Embodiments for Carrying Out the Invention

[0012] Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. Note that the present invention is not limited to the illustrated examples.

[0013] <First Embodiment> 〔Configuration of Image Display System〕 FIG. 1 is a diagram showing a system configuration example of an image display system 100 (medical image display system) according to the first embodiment. As shown in FIG. 1, the image display system 100 includes a modality 1, an analysis device 2, an image server 3, and a reading terminal 4. Each device constituting the image display system 100 is connected via a communication network N such as a LAN (Local Area Network), a WAN (Wide Area Network), or the Internet. Further, each device constituting the image display system 100 conforms to standards such as HL7 (Health Level Seven) and DICOM (Digital Image and Communications in Medicine). Communication between devices is carried out in accordance with HL7 and DICOM. Note that the number of modalities 1, analysis devices 2, reading terminals 4, etc. is not particularly limited.

[0014] Modality 1 captures the subject (the examination site of the patient) and generates a medical image of the captured subject. In the present embodiment, Modality 1 captures the subject and generates a series of medical images including a plurality of medical images. For example, Modality 1 is a CT (Computed Tomography) or an MRI (Magnetic Resonance Imaging), and generates a plurality of consecutive medical images (tomographic images) with different slice positions. Alternatively, Modality 1 is a radiation dynamic imaging device, a fluoroscopic device, or an ultrasonic diagnostic device, and generates a plurality of temporally consecutive medical images (frame images). In the present embodiment, the case where Modality 1 is a CT or an MRI will be described as an example.

[0015] Modality 1 attaches image attribute information related to the generated medical image to the medical image and transmits it to the analysis device 2 and the image server 3. Here, the image attribute information includes patient information, examination information, image identification information, etc. The patient information includes patient ID, patient name, date of birth, age, gender, height, weight, etc. The examination information includes examination ID, examination date and time, type of modality, examination site, requesting department, purpose of examination, etc. The image identification information includes instance number, UID (Unique ID). The instance number is a number indicating which image in a series of medical images a certain medical image is. The UID is information for uniquely identifying a medical image.

[0016] The analysis device 2 performs computer-processed image analysis on a series of medical images transmitted from Modality 1, extracts the medical images containing the lesion candidate regions, calculates the lesion information about the lesion candidate regions of the extracted medical images, and transmits (outputs) it to the image server 3.

[0017] The analysis device 2 has functions as an acquisition unit, an extraction unit, and a calculation unit of the present invention. The acquisition unit acquires, via a communication unit (not shown), a series of medical images including a plurality of medical images transmitted from modality 1. The extraction unit performs image analysis on a plurality of medical images among the series of medical images transmitted from modality 1, and extracts a plurality of medical images including lesion candidate regions. The calculation unit calculates lesion information of the lesion candidate regions included in at least two of the plurality of medical images extracted by the extraction unit for each medical image.

[0018] The analysis device 2 realizes functions as an extraction unit and a calculation unit by analysis (AI analysis) using, for example, CAD or a machine learning model. As a method of the machine learning model, for example, CNN (Convolutional Neural Network) or FCN (Fully Convolutional Networks) can be used, but it is not particularly limited. The functions of the extraction unit and the calculation unit are realized, for example, by cooperation between a processor such as a CPU and a program (machine learning model) stored in a storage unit (not shown).

[0019] Here, the lesion information calculated by the analysis device 2 is at least one of the risk degree of the lesion, the confidence degree of the lesion, the size of the lesion, the type of the lesion, the mode of change of the lesion between the past and the current time, and the anatomical structure information of the lesion. The risk degree of the lesion is, for example, a numerical value or a class representing the risk of the lesion in the lesion candidate region, such as the ease of canceration. The confidence degree of the lesion is a value indicating the probability that the lesion candidate region is a lesion. The size of the lesion is the size (for example, diameter or radius) of the lesion candidate region. The type of the lesion is the type of the lesion corresponding to the lesion candidate region. For example, when the medical image is a chest medical image, examples of the type of the lesion include nodules, tumors, pneumothorax, etc. The mode of change of the lesion between the past and the current time is information indicating the mode of change (such as size increase or decrease, new appearance, splitting, integration, disappearance, etc.) of the lesion (lesion candidate region) between the past (previous) examination and the current examination. The anatomical structure information of the lesion is information indicating the anatomical structure (site) where the lesion (lesion candidate region) exists.

[0020] When the lesion information is about a chest nodule, the lesion information may be at least one of the size of the lesion, the difference between the past and current lesions, the type of the lesion (Solid / P-Solid / GGN), and the location of the lesion. The size of the lesion may be the size of the lesion candidate region itself, or may be information indicating whether the size of the lesion is equal to or greater than a predetermined threshold. The difference between the past and current lesions is information indicating the difference (increase or decrease in size) between the lesions (lesion candidate regions) in the past (previous) examination and the current examination. The location of the lesion is information indicating the location where the lesion candidate region exists (for example, anatomical structure information).

[0021] When the lesion information is about a fracture, the lesion information may be at least one of the fracture site and the degree of fracture. The fracture site is a more detailed site than the above-mentioned anatomical structure. For example, when the second rib is fractured, the information of the above-mentioned anatomical structure is "rib", but the fracture site is "the second rib". The degree of fracture is information indicating the severity of the fracture.

[0022] When the lesion information is about the head, the lesion information may be at least one of the type of the lesion (high absorption / low absorption, cerebral aneurysm, leukoaraiosis) and the location of the lesion. The location of the lesion is information indicating the location where the lesion candidate region exists (for example, anatomical structure information).

[0023] In addition, the lesion information preferably includes the position information (coordinates) of the lesion candidate region in the medical image.

[0024] The analysis device 2 transmits the calculated lesion information to the image server 3 in association with the image attribute information of the medical image from which the lesion information is calculated.

[0025] The image server 3 is, for example, a server of a PACS (Picture Archiving and Communication System), and is an image management device that stores and manages medical images output from the modality 1. The image server 3 is an image server unit in a cloud type, on-premises type, or workstation type.

[0026] The image server 3 is provided with an image DB (Data Base) 30. The image DB 30 is a database for storing medical images transmitted from the modality 1 and lesion information transmitted from the analysis device 2. The image DB 30 has an image management table for storing information regarding the medical images stored in the image DB 30. In the image management table, for example, patient information, examination information, image identification information, and lesion information for each medical image are stored in association with each other.

[0027] The reading terminal 4 is, for example, a client of a PACS (PACS viewer). The reading terminal 4 reads out a medical image from the image server 3 and displays it for reading. The reading terminal 4 may be an application type viewer that operates by an application, or a browser type viewer that operates by a browser. In this embodiment, the case where the reading terminal 4 is an application type viewer will be described as an example.

[0028] FIG. 2 is a block diagram showing the functional configuration of the reading terminal 4. As shown in FIG. 2, the reading terminal 4 includes a control unit 41, a storage unit 42, a communication unit 43, an operation unit 44, a display unit 45, etc., and each unit is connected by a bus 46.

[0029] The control unit 41 is composed of a CPU (Central Processing Unit), a RAM (Random Access Memory), etc. The control unit 41 comprehensively controls the operations of each part of the radiography terminal 4. For example, the CPU of the control unit 41 reads out various processing programs stored in the storage unit 42, expands them in the RAM, and executes the processing on the radiography terminal 4 side shown in FIG. 3 according to the expanded programs. The control unit 41 functions as the control unit of the present invention.

[0030] The storage unit 42 is composed of an HDD (Hard Disk Drive), a semiconductor memory, etc. The storage unit 42 stores system programs, application programs for executing various processes, data such as parameters necessary for program execution, etc. For example, the storage unit 42 stores items of lesion information used for controlling the display mode of detection marks (M1 to M6) on the radiography screen 451 (see FIGS. 6 to 8). The items of lesion information used for controlling the display mode of the detection marks (M1 to M6) can be set by the user through the operation of the operation unit 44. Also, the storage unit 42 stores a correspondence table 421 (see FIG. 5). Details of the correspondence table 421 will be described later.

[0031] In addition, the storage unit 42 has an area for temporarily storing medical images acquired from the image server 3, the image attribute information thereof, and the lesion information.

[0032] The communication unit 43 is composed of a network interface, etc. The communication unit 43 transmits and receives data to and from external devices connected via the communication network N.

[0033] The operation unit 44 is composed of a keyboard with various keys, a pointing device such as a mouse, or a touch panel superimposed on the display unit 45. The operation unit 44 outputs an operation signal input by a key operation on the keyboard, a mouse operation, or a touch operation on the touch panel by the user to the control unit 41.

[0034] The display unit 45 is composed of a monitor such as an LCD (Liquid Crystal Display). The display unit 45 displays various screens according to the instructions of the display signal input from the control unit 41.

[0035] 〔Operation of the Image Display System 100〕 Next, the operation of the image display system 100 will be described. FIG. 3 is a sequence diagram showing the flow from shooting to image display in the image display system 100. Hereinafter, with reference to FIG. 3, the flow from shooting to image display in the image display system 100 will be described.

[0036] First, Modality 1 shoots a subject and acquires a series of medical images including a plurality of medical images (step S1). Next, Modality 1 attaches image attribute information to the acquired series of medical images and transmits them to the analysis device 2 and the image server 3 (step S2).

[0037] The analysis device 2 receives (acquires) the series of medical images transmitted from Modality 1 (step S3). Next, the analysis device 2 analyzes a plurality of medical images among the series of medical images transmitted from Modality 1 and extracts a plurality of medical images including lesion candidate regions (step S4). In addition, when the same lesion candidate region appears in a plurality of medical images, the analysis device 2 extracts, for example, the medical image in which the lesion candidate region appears the largest as the medical image including the lesion candidate region.

[0038] Next, the analysis device 2 calculates the lesion information of the lesion candidate regions included in at least two of the plurality of medical images including the lesion candidate regions (step S5).

[0039] Next, the analysis device 2 transmits the calculated lesion information to the image server 3 in association with the image attribute information of the medical image that is the source of the calculated lesion information (step S6).

[0040] When the image server 3 receives a series of medical images transmitted from Modality 1 (step S7), it stores the series of medical images in the image DB 30 (step S8). That is, the image server 3 stores the received series of medical images in the image DB 30 and writes the image attribute information of each medical image into the image management table.

[0041] Also, when the image server 3 receives the lesion information transmitted from the analysis device 2 (step S9), it stores the lesion information in the image DB 30 (step S10). That is, the image server 3 writes the lesion information into the record in the image management table where the image attribute information of the medical image corresponding to the received lesion information is written.

[0042] In the reading terminal 4, when inspection information or the like of a medical image to be displayed is specified by the operation unit 44, the control unit 41 transmits an image acquisition request for the specified inspection to the image server 3 via the communication unit 43 (step S11). The image server 3 reads out a series of medical images and lesion information of the specified inspection from the image DB 30 and transmits them to the reading terminal 4 (step S12).

[0043] In the reading terminal 4, when a series of medical images transmitted from the image server 3 are received (acquired) by the communication unit 43 (step S13), the control unit 41 causes the display unit 45 to display a reading screen 451 for displaying the received medical images (step S14). The user operates the reading screen 451 to perform reading.

[0044] Here, FIG. 4 is a diagram showing an example of a conventional reading screen 450. As shown in FIG. 4, the conventional reading screen 450 is provided with a medical image display area 450a and a slider bar 450b having a slider 450c. The medical image display area 450a is an area for displaying the medical image corresponding to the position of the slider 450c among the series of medical images to be displayed. The slider bar 450b is a bar-shaped UI (User Interface), i.e., an operating means, for specifying a medical image to be displayed among a series of medical images. The longitudinal direction of the slider bar 450b indicates a direction perpendicular to the plane (cross-section) of the subject in the series of medical images. One end (e.g., the upper end) of the slider bar 450b corresponds to the slice position of the first-taken medical image, and the other end (e.g., the lower end) corresponds to the slice position of the last-taken medical image. The position of the slider 450c indicates the slice position of the medical image currently displayed in the medical image display area 450a. When the slider 450c is moved on the slider bar 450b, the medical image displayed in the medical image display area 450a is changed to the medical image corresponding to the position of the slider 450c after the movement.

[0045] A detection mark M0 is displayed on the slider bar 450b of the reading screen 450. The detection mark M0 is information indicating the presence of a lesion candidate region in the medical image including the lesion candidate region. The detection mark M0 is displayed in association with the position of the medical image including the lesion candidate region on the slider bar 450b.

[0046] In the reading screen 450 shown in FIG. 4, the detection mark M0 is displayed in the same display mode at all positions of the medical images including the lesion candidate region. Therefore, when there are a large number of medical images including the lesion candidate region and a large number of detection marks M0 are displayed, the user will not know which medical image to view preferentially. In Patent Document 1, it is displayed so that it can be identified whether it has been displayed or not, but the user cannot recognize the medical image that should be preferentially read.

[0047] Therefore, based on the lesion information of each medical image for which the lesion information has been calculated, the control unit 41 controls the display of information indicating the presence of the lesion candidate region in each medical image including the lesion candidate region. As one embodiment, in the display of the reading screen 451, the control unit 41 controls the display of a detection mark as information indicating the presence of the lesion candidate region in the medical image including the lesion candidate region, based on the lesion information of each medical image for which the lesion information has been calculated. Note that the medical image display area 451a, the slider bar 451b, and the slider 451c on the reading screen 451 are the same as the above-described medical image display area 450a, the slider bar 450b, and the slider 450c, respectively, and thus the description thereof is incorporated by reference.

[0048] For example, based on the lesion information of each medical image for which the lesion information has been calculated, the control unit 41 makes the display mode of at least one detection mark among the detection marks as information indicating the presence of the lesion candidate region in the medical image including the lesion candidate region different from the display mode of the other detection marks. For example, the control unit 41 controls at least one of the size, color, and design of the detection mark based on the lesion information of each medical image, thereby making the display mode of at least one detection mark different from the display mode of the other detection marks.

[0049] For example, in step S14, the control unit 41 controls the display of the detection mark based on the lesion information of the medical image, using the item of the lesion information and the correspondence table 421 used for controlling the display mode of the detection mark, which are stored in the storage unit 42. FIG. 5 is a diagram showing an example of the correspondence table 421. As shown in FIG. 5, in the correspondence table 421, for each item of the lesion information, the range of the value of the item and the display mode of the detection mark to be displayed at the position of the medical image including the lesion candidate region corresponding to the range of the value are stored in association with each other. In the correspondence table 421, display modes in which at least one of the size, color, and design of the detection mark is different are stored according to the range of the value for each item. Note that the value is not limited to a numerical value and includes a character string and the like. For each of the medical images for which lesion information has been calculated, the control unit 41 acquires the items of lesion information stored in the storage unit 42 and used for controlling the display mode. Next, the control unit 41 refers to the correspondence table 421 and displays a detection mark of the display mode corresponding to the value range of the acquired item of lesion information at the position corresponding to that medical image on the slider bar 451b. Thereby, the control unit 41 can control so that at least one of the size, color, and design of the displayed detection marks is different among the medical images in which the value ranges of the predetermined items of lesion information are different. That is, the control unit 41 can make the display mode of at least one detection mark different from the display mode of other detection marks among the medical images in which the value ranges of the predetermined items of lesion information of the medical images are different.

[0050] FIG. 6 is a diagram showing an example of the interpretation screen 451. FIG. 6 shows a display example of the interpretation screen 451 when the item of lesion information used for controlling the display mode of the detection mark is "size", and in the correspondence table 421, a diamond shape (◇) of the first size is associated with "6 mm or more", and a diamond shape of the second size smaller than the first size is associated with "less than 6 mm".

[0051] As shown in FIG. 6, on the interpretation screen 451, detection marks M1 and M2 are displayed on the slider bar 451b. The detection marks M1 and M2 are information indicating the presence of the lesion candidate region in the medical image including the lesion candidate region. The detection mark M1 is displayed in association with the position on the slider bar 451b corresponding to the medical image including the lesion candidate region having a size of 6 mm or more. The detection mark M2 is displayed in association with the position on the slider bar 451b corresponding to the medical image including the lesion candidate region having a size of less than 6 mm. As described above, on the radiography screen 451 shown in FIG. 6, a detection mark M1 is displayed at the position of the medical image including a lesion candidate region of 6 mm or more, and a detection mark M2 of a size different from that of the detection mark M1 is displayed at the position of the medical image including a lesion candidate region of less than 6 mm. Therefore, the user can recognize which medical image includes a lesion candidate region with a size of 6 mm or more, and can easily recognize which medical image should be preferentially read.

[0052] FIG. 7 is a diagram showing another example of the radiography screen 451. FIG. 7 shows a display example of the radiography screen 451 when the item of lesion information used for controlling the display mode of the detection mark is "nodule type", and a diamond (◇) is associated with "Solid", a triangle (△) is associated with "Partial Solid", and a circle (○) is associated with "GGN" in the correspondence table 421.

[0053] As shown in FIG. 7, on the radiography screen 451, detection marks M3 to M5 are displayed on the slider bar 451b. The detection marks M3 to M5 are information indicating the presence of a lesion candidate region in the medical image including the lesion candidate region. The detection mark M3 is displayed in association with the position of the medical image including the lesion candidate region with the nodule type of "Solid" on the slider bar 451b. The detection mark M4 is displayed in association with the position of the medical image including the lesion candidate region with the nodule type of "Partial Solid" on the slider bar 451b. The detection mark M5 is displayed in association with the position of the medical image including the lesion candidate region with the nodule type of "GGN" on the slider bar 451b. As described above, on the radiography screen 451 shown in FIG. 7, the detection mark M3 is displayed at the position of the medical image including the lesion candidate region with the nodule type of "Solid", the detection mark M4 is displayed at the position of the medical image including the lesion candidate region with the nodule type of "Partial Solid", and the detection mark M5 is displayed at the position of the medical image including the lesion candidate region with the nodule type of "GGN", and they are displayed with different designs. Therefore, the user can recognize which type of nodule is included in which medical image, and can easily recognize which medical image should be preferentially read.

[0054] Further, the control unit 41 may control the display of the information indicating the presence of the lesion candidate region in a plurality of medical images including the lesion candidate region by making at least one of the information indicating the presence of the lesion candidate region non-displayed based on the lesion information of each medical image for which the lesion information has been calculated. For example, in the correspondence table 421, for each item of the lesion information, a detection mark with a predetermined shape, size, and color is associated with the range of values to be preferentially read, and "non-display" is associated with the range of other values and stored. In step S14, the control unit 41 acquires, for each medical image for which the lesion information has been calculated, the item of the lesion information used for controlling the display mode of the detection mark stored in the storage unit 42. Next, the control unit 41 refers to the correspondence table 421, and when the display mode corresponding to the range of the value of the acquired item of the lesion information is a predetermined detection mark, the control unit 41 displays the detection mark at the position corresponding to the medical image on the slider bar 451b. When the display mode corresponding to the range of the value of the acquired item of the lesion information is non-display, the detection mark is not displayed at the position corresponding to the medical image on the slider bar 451b. In this way, among the medical images including the lesion candidate region, the detection mark can be displayed at the position of the medical image on the slider bar 451b whose lesion information satisfies the predetermined condition, and the detection mark can be made non-displayed at the position of the medical image that does not satisfy the predetermined condition. Therefore, the user can easily recognize which medical image should be preferentially read.

[0055] In step S14, the control unit 41 may also control the display of a detection mark, which is information indicating the presence of a lesion candidate region in a medical image including the lesion candidate region, based on a comparison between the lesion information of each medical image for which the lesion information has been calculated. For example, when the lesion information of a plurality of medical images for which the lesion information has been calculated includes lesion information that the size of the lesion is 2 mm or more in diameter, the control unit 41 displays a detection mark M6 at a position corresponding to the medical image having the top four pieces of lesion information in terms of size among them. In addition, the control unit 41 makes the detection marks corresponding to medical images other than the above non-displayed.

[0056] FIG. 8 is a diagram showing another example of the reading screen 451. In FIG. 8, a detection mark M6 is displayed at a position corresponding to a medical image having the lesion information of the top four lesion candidate regions in terms of size among the lesion information of the lesion candidate regions having a size of 2 mm or more in diameter, and an example is shown in which the detection marks corresponding to other medical images are non-displayed at the corresponding positions. As described above, in the reading screen 451 shown in FIG. 8, the detection mark M6 is displayed only at a position corresponding to the medical image having the top four lesion candidate region reports in terms of size among the lesion candidate regions having a size of 2 mm or more in diameter. Therefore, the user can easily recognize which medical image should be preferentially read.

[0057] Note that when controlling the display of a detection mark, which is information indicating the presence of a lesion candidate region in a medical image including the lesion candidate region, based on a comparison between the lesion information of each medical image for which the lesion information has been calculated, the control unit 41 does not need to compare all the lesion candidate regions of the plurality of medical images. Also, it is not necessary to control the display of all the information indicating the presence of the lesion candidate region. For example, the control unit 41 may control the display of the information indicating the presence of the lesion candidate region in at least the first medical image based on the first lesion information of the first lesion candidate region included in the first medical image and the second lesion information of the second lesion candidate region included in the second medical image.

[0058] [Modification Example 1] In the above-described first embodiment, when the same lesion candidate region appeared across a plurality of medical images, the analysis device 2 extracted the medical image in which the lesion candidate region appeared the largest as the medical image including the lesion candidate region. Alternatively, when the same lesion candidate region appeared across a plurality of medical images, the analysis device 2 may extract all the medical images in which the lesion candidate region appears as the medical images including the lesion candidate region, and calculate the lesion information of the extracted medical images. Then, the control unit 41 of the reading terminal 4 may control the display of information indicating the presence of the lesion candidate region in the plurality of medical images including the lesion candidate region based on the lesion information of each medical image for which the lesion information has been calculated. For example, when two lesion candidate regions are detected across a plurality of medical images, the control unit 41 may display information M7 indicating the presence of one lesion candidate region on the left side of the slider bar 451b and information M8 indicating the presence of the other lesion candidate region on the right side, as shown in FIG. 9. At this time, the control unit 41 displays the information M7 and the information M8 with the length in the direction orthogonal (left or right) to the slider bar 451b as the size (radius or diameter) of the lesion candidate region detected from each medical image, and the vertical direction as the position of the medical image. Thereby, the user can recognize the ranges and sizes of the two lesion candidate regions included in the series of medical images.

[0059] [Modification Example 2] In the image display system 100 of the above-described first embodiment, the case where the analysis device 2 has functions as an acquisition unit, an extraction unit, and a calculation unit, and the reading terminal 4 has functions as a control unit and a display unit has been described as an example. However, the device having functions as an acquisition unit, an extraction unit, a calculation unit, a control unit, and a display unit is not limited to the above example.

[0060] For example, when the analysis device 2 is not provided in the image display system 100, the reading terminal 4 may be configured to have all the functions of the acquisition unit, extraction unit, calculation unit, control unit, and display unit as the medical image display device of the present invention. For example, in the storage unit 42 of the reading terminal 4, a program for causing the control unit 41 to execute the functions of the acquisition unit, extraction unit, calculation unit, and control unit of the present invention is stored. The control unit 41, in cooperation with the program stored in the storage unit 42, executes the functions of the acquisition unit, extraction unit, calculation unit, and control unit, and causes the display unit 45 to function as a display unit.

[0061] Also, when the analysis device 2 is not provided in the image display system 100, the image server 3 may be configured to have the functions of the acquisition unit, extraction unit, calculation unit, and control unit as the medical image display device of the present invention. For example, the image server 3 executes the functions of the acquisition unit, extraction unit, calculation unit, and control unit in cooperation with a processor such as a CPU and a program stored in the storage unit. Note that when the image server 3 controls the display of information indicating the presence of lesion candidate regions in a plurality of medical images as a control unit, the image server 3 may perform control to display the above information on the display unit provided in the own device. Alternatively, when the image server 3 controls the display of information indicating the presence of lesion candidate regions in a plurality of medical images as a control unit, the image server 3 may perform control to cause the display unit of the reading terminal 4 to display the above information.

[0062] Also, the analysis device 2 may be configured to have all the functions of the acquisition unit, extraction unit, calculation unit, control unit, and display unit as the medical image display device of the present invention. For example, the analysis device 2 includes a display unit, and when the analysis device 2 controls the display of information indicating the presence of lesion candidate regions in a plurality of medical images as a control unit, the analysis device 2 may perform control to display the above information on the display unit provided in the own device. Alternatively, when the analysis device 2 controls the display of information indicating the presence of lesion candidate regions in a plurality of medical images as a control unit, the analysis device 2 may perform control to cause the display unit of the reading terminal 4 to display the above information.

[0063] <Second Embodiment> Hereinafter, a second embodiment of the present invention will be described.

[0064] The image display system 100 shown in FIG. 1 is provided in a relatively large-scale medical facility. On the other hand, in small-scale medical facilities such as private practitioners and clinics, a medical image display device that integrates the functions of an analysis device, an image server, and a diagnostic reading terminal is often used. Hereinafter, an example in which the present invention is applied to such a medical image display device for small-scale medical facilities will be described.

[0065] FIG. 10 is a diagram showing an example of an image display system 200 in the second embodiment. As shown in FIG. 10, the image display system 200 includes a modality 1 and a medical image display device 6. The modality 1 and the medical image display device 6 are connected via a communication network N1 such as a LAN. Since the modality 1 is the same as that described in the first embodiment, the description thereof is incorporated herein by reference.

[0066] As shown in FIG. 10, the medical image display device 6 includes a control unit 61, a storage unit 62, a communication unit 63, an operation unit 64, and a display unit 65, and each unit is connected via a bus 66.

[0067] The control unit 61 is composed of a CPU, a RAM, etc. The control unit 61 comprehensively controls the operations of each unit of the medical image display device 6. Specifically, the CPU of the control unit 61 reads out various processing programs stored in the storage unit 62 and expands them in the RAM, and executes various processes according to the expanded programs.

[0068] The storage unit 62 is composed of an HDD, a semiconductor memory, etc. The storage unit 62 stores data such as system programs, application programs for executing various processes, and parameters necessary for program execution. The programs stored in the storage unit 62 include programs for causing a computer (control unit 61) to realize the functions as the acquisition unit, extraction unit, calculation unit, and control unit of the present invention. The acquisition unit acquires, via a communication unit (not shown), a series of medical images including a plurality of medical images transmitted from modality 1. The extraction unit performs image analysis on a plurality of medical images out of the series of medical images transmitted from modality 1, and extracts a plurality of medical images including lesion candidate regions. The calculation unit calculates lesion information of the lesion candidate regions included in each medical image for at least two medical images out of the plurality of medical images including the lesion candidate regions extracted by the extraction unit. The control unit controls the display of information indicating the existence of the lesion candidate regions in the plurality of medical images including the lesion candidate regions based on the lesion information of each medical image for which the lesion information has been calculated. Since the lesion information is the same as that described in the first embodiment, the description thereof is incorporated herein by reference.

[0069] The control unit 61 realizes the functions as the extraction unit and the calculation unit by cooperation with the programs stored in the storage unit 62, for example, by analysis (AI analysis) using CAD or a machine learning model. As the method of the machine learning model, for example, CNN or FCN can be used, but it is not particularly limited.

[0070] The storage unit 62 includes a correspondence table 621 and an image DB 622. Since the correspondence table 621 is the same as the correspondence table 421 described in the first embodiment, the description thereof is incorporated herein by reference. The image DB 622 is a database for storing the medical images transmitted from modality 1 and the lesion information calculated from the medical images. The image DB 622 has an image management table for storing information regarding the medical images stored in the image DB 622. In the image management table, for example, patient information, examination information, image identification information, and lesion information for each medical image are stored in association with each other.

[0071] The communication unit 63 is composed of a network interface or the like. The communication unit 63 transmits and receives data to and from an external device connected via the communication network N1.

[0072] The operation unit 64 is composed of a keyboard having various keys, a pointing device such as a mouse, or a touch panel superimposed on the display unit 65 or the like. The operation unit 64 outputs an operation signal input by a key operation on the keyboard, a mouse operation, or a touch operation on the touch panel by the user to the control unit 61.

[0073] The display unit 65 is composed of a monitor such as an LCD. The display unit 65 displays various screens according to an instruction of a display signal input from the control unit 61.

[0074] Next, the operation of the image display system 200 according to the second embodiment will be described. FIG. 11 is a sequence diagram showing the flow from imaging to image display in the image display system 200. Hereinafter, with reference to FIG. 11, the flow from imaging to image display in the image display system 200 will be described.

[0075] First, modality 1 captures a subject and acquires a series of medical images including a plurality of medical images (step T1). Next, modality 1 attaches image attribute information to the acquired series of medical images and transmits them to the medical image display device 6 (step T2).

[0076] The control unit 61 of the medical image display device 6 receives (acquires) the series of medical images transmitted from modality 1 by the communication unit 63 (step T3), and stores the acquired series of medical images in the image DB622 (step T4). That is, the control unit 61 stores the received series of medical images in the image DB622 and writes the image attribute information of each medical image in the image management table.

[0077] Next, the control unit 61 analyzes a plurality of medical images among a series of medical images transmitted from modality 1, and extracts a plurality of medical images including lesion candidate regions (step T5). Since the process of step T5 is the same as the process of step S4 in FIG. 3, the description thereof is incorporated herein by reference.

[0078] Next, the control unit 61 calculates lesion information of the lesion candidate regions included in each of at least two medical images among the plurality of medical images including the extracted lesion candidate regions (step T6).

[0079] Next, the control unit 61 causes the calculated lesion information to be stored in the image DB622 in association with the medical image that is the source of the calculation of the lesion information (step T7). The control unit 61 writes the lesion information to the record in the image management table of the image DB622 in which the image attribute information of the medical image corresponding to each lesion information is written.

[0080] Then, the control unit 61 causes the reading screen 651 for displaying the medical images received from modality 1 to be displayed on the display unit 65 (step T8).

[0081] As shown in FIGS. 6 to 8, the reading screen 651 that the control unit 61 causes to be displayed in step T8 displays a medical image display area 651a, a slider bar 651b, and a slider 651c. Since the medical image display area 651a, the slider bar 651b, and the slider 651c are the same as the medical image display area 451a, the slider bar 451b, and the slider 451c, respectively, the description thereof is incorporated herein by reference.

[0082] Detection marks (M1, M2 in FIG. 6, M3 to M5 in FIG. 7, M6 in FIG. 8, etc.) are displayed on the slider bar 651b of the reading screen 651. The detection marks are information indicating the presence of the lesion candidate regions in the medical images including the lesion candidate regions. The detection marks are displayed in association with the positions of the medical images including the lesion candidate regions on the slider bar 651b.

[0083] Based on the lesion information of each medical image for which the lesion information has been calculated, the control unit 61 makes the display mode of at least one detection mark, which is information indicating the presence of the lesion candidate region in the medical image including the lesion candidate region, different from the display mode of other detection marks. Since the method for controlling the display mode of the detection mark by the control unit 61 is the same as the method for controlling the display mode of the detection mark by the control unit 41 described in the first embodiment and its modified example, the description thereof is incorporated herein by reference.

[0084] The user operates the slider 651c of the slider bar 651b on the reading screen 651 to display a desired medical image in the medical image display area 651a for reading. On the slider bar 651b, detection marks, which are information indicating the presence of the lesion candidate region in the medical image including the lesion candidate region, are displayed in a display mode corresponding to the lesion information of the medical image. Therefore, the user can easily recognize which medical image should be preferentially read.

[0085] As described above, the image display system 100 and the medical image display device 6 include an acquisition unit that acquires a series of medical images including a plurality of medical images, an extraction unit that performs image analysis on the plurality of medical images to extract a plurality of medical images including lesion candidate regions, a calculation unit that calculates the lesion information of the lesion candidate regions included in each of at least two of the plurality of medical images including the extracted lesion candidate regions, and a control unit that controls the display of information indicating the presence of the lesion candidate regions in the plurality of medical images including the lesion candidate regions based on the lesion information of each medical image for which the lesion information has been calculated. Therefore, based on the lesion information, it is possible to clearly display which medical image among the plurality of medical images including the lesion candidate region should be preferentially viewed.

[0086] Note that the present invention is not limited to the above-described embodiment, and various modifications are possible without departing from the gist thereof.

[0087] For example, in the above embodiment, the case where there is one item of lesion information used for controlling the display mode of information (such as a detection mark) indicating the presence of a lesion candidate region in a medical image including the lesion candidate region was taken as an example for explanation. However, the display mode of the above information may also be controlled based on a plurality of items of lesion information. For example, the control unit 41(61) scores each of the plurality of items in the lesion information according to the value range, multiplies each item by a predetermined weight coefficient, and sums them up. Then, the control unit 41(61) displays the above information in a display mode corresponding to the summed value based on a table in which the correspondence between the range of the summed value and the display mode of the above information is stored. Thereby, information (such as a detection mark) indicating the presence of a lesion candidate region in a medical image including the lesion candidate region can be displayed in a display mode reflecting a plurality of items of lesion information.

[0088] Also, in the above embodiment, the case where a series of medical images in the present invention are a plurality of consecutive medical images (tomographic images) with different slice positions generated by CT or MRI was taken as an example for explanation, but it is not limited thereto. For example, a series of medical images may be a plurality of temporally consecutive medical images, for example, dynamic radiation images, fluoroscopic images, and ultrasonic images. In this case, the longitudinal direction of the slider bar 451b(651b) indicates the time axis. The position of the slider 451c(651c) indicates the time position of the medical image currently displayed in the medical image display area 451a(651a). In addition, in the above embodiment, the case where the longitudinal direction of the slider bar 451b(651b) is the vertical direction was shown as an example, but it may be the horizontal direction. Also, in the above embodiment, the slider bar 450b(651b) was assumed to be an operation means for designating a medical image to be displayed among a series of medical images, but it may also be an operation means for continuously displaying a series of medical images.

[0089] In the above-described embodiment, the display mode of the detection mark is switched according to the item of lesion information, but the present invention is not limited to this. For example, a switching button may be provided on the reading screen 451 (651), and the control unit 41 may switch the display mode of the detection mark according to the operation of the switching button.

[0090] In the above-described embodiment, the lesion candidate region is detected by image analysis. Alternatively, a region designated by a radiologist or the like (user) on the medical image may be detected as the lesion candidate region. In this case, the lesion information of the lesion candidate region may be calculated by computer processing or may be input by a radiologist or the like.

[0091] In the above description, an example in which a hard disk, a semiconductor non-volatile memory, or the like is used as the computer-readable medium of the program according to the present invention is disclosed, but the present invention is not limited to this example. As other computer-readable media, portable recording media such as CD-ROMs can be applied. In addition, a carrier wave is also applied as a medium for providing the data of the program according to the present invention via a communication line.

[0092] In addition, the detailed configuration and detailed operation of each device constituting the image display system can be appropriately changed within a range not departing from the gist of the invention.

Explanation of Reference Numerals

[0093] 1 Modality 2 Analysis Device 3 Image Server 30 Image DB 4 Reading Terminal 41 Control Unit 42 Storage Unit 421 Correspondence Table 43 Communication Unit 44 Operation Unit 45 Display Unit 46 Bus 6 Medical Image Display Device 61 Control Unit 62 Memory unit 621 Correspondence table 622 Image DB 63 Communication unit 64 Operation unit 65 Display unit 66 Bus

Claims

1. An acquisition unit that acquires a series of medical images including a plurality of medical images; An extraction unit that performs image analysis on the plurality of medical images and extracts a plurality of medical images including a lesion candidate region; A calculation unit that calculates lesion information of the lesion candidate region included in each of at least two medical images among the plurality of medical images including the extracted lesion candidate region; A control unit that controls display of information indicating the presence of the lesion candidate region in the plurality of medical images including the lesion candidate region based on the lesion information of each medical image for which the lesion information has been calculated; A medical image display device comprising the above.

2. An operation means for designating a medical image to be displayed among the series of medical images, and a display unit that displays a detection mark as the information indicating the presence; The medical image display device according to Claim 1, comprising the above.

3. The plurality of medical images including the lesion candidate region include at least a first medical image including a first lesion candidate region and a second medical image including a second lesion candidate region, The control unit controls display of information indicating the presence of the lesion candidate region in at least the first medical image based on at least the first lesion information of the first lesion candidate region and the second lesion information of the second lesion candidate region. The medical image display device according to Claim 1.

4. The control unit controls display of information indicating the presence of the lesion candidate region in each medical image including the lesion candidate region based on the lesion information of each medical image for which the lesion information has been calculated. The medical image display device according to Claim 1.

5. The control unit, based on the lesion information of each medical image for which the lesion information has been calculated, among the information indicating the presence of the lesion candidate region in the plurality of medical images including the lesion candidate region, makes the display mode of at least one of the information indicating the presence different from the display mode of the other information indicating the presence, thereby controlling the display of the information indicating the presence of the lesion candidate region in the plurality of medical images including the lesion candidate region. The medical image display device according to Claim 1.

6. The control unit, based on the lesion information of each medical image for which the lesion information has been calculated, among the information indicating the presence of the lesion candidate region in the plurality of medical images including the lesion candidate region, makes at least one piece of information non-displayed, thereby controlling the display of the information indicating the presence of the lesion candidate region in the plurality of medical images including the lesion candidate region. The medical image display device according to Claim 1.

7. The medical image display device according to claim 5, wherein the control unit controls at least one of the size, color, and design of a mark indicating the position of the lesion candidate region, thereby varying the display mode of information indicating the presence of the lesion candidate region.

8. The medical image display device according to claim 1, wherein the lesion information is at least one of a risk degree of a lesion calculated from the lesion candidate region, a confidence degree of the lesion, a size of the lesion, a type of the lesion, a mode of change of the lesion between the past and the present, and anatomical structure information of the lesion.

9. The medical image display device according to claim 1, wherein the lesion information is lesion information regarding a chest nodule and is at least one of information on the size of the lesion, the difference in the lesion between the past and the present, the type of the lesion, and the location of the lesion.

10. The medical image display device according to claim 1, wherein the lesion information is lesion information regarding a fracture and is at least one of information on the fracture site and the degree of the fracture.

11. The medical image display device according to claim 1, wherein the lesion information is lesion information regarding the head and is at least one of information on the type of the lesion and the location of the lesion.

12. The medical image display device according to claim 1, wherein the series of medical images are a plurality of consecutive tomographic images having different slice positions.

13. The medical image display device according to claim 1, wherein the series of medical images are a plurality of medically consecutive images in time.

14. An acquisition unit that acquires a series of medical images including a plurality of medical images; An extraction unit that performs image analysis on the plurality of medical images to extract a plurality of medical images including a lesion candidate region; A calculation unit that calculates lesion information of the lesion candidate region included in each of at least two of the plurality of medical images including the extracted lesion candidate region; A control unit that controls the display of information indicating the presence of the lesion candidate region in the plurality of medical images including the lesion candidate region based on the lesion information of each of the medical images for which the lesion information has been calculated; A medical image display system comprising the above.

15. A computer, An acquisition unit that acquires a series of medical images including a plurality of medical images, An extraction unit that performs image analysis on the plurality of medical images to extract a plurality of medical images including a lesion candidate region, A calculation unit that calculates lesion information of the lesion candidate region included in each of at least two of the plurality of medical images including the extracted lesion candidate region, A control unit that controls the display of information indicating the presence of lesion candidate regions in a plurality of medical images including the lesion candidate region, based on the lesion information of each medical image for which the lesion information has been calculated. A program for causing the above to function.

16. A step of acquiring a series of medical images including a plurality of medical images; A step of performing image analysis on the plurality of medical images to extract a plurality of medical images including lesion candidate regions; A step of calculating lesion information of lesion candidate regions included in each medical image for at least two medical images among the plurality of medical images including the extracted lesion candidate regions; A step of controlling the display of information indicating the presence of lesion candidate regions in a plurality of medical images including the lesion candidate region, based on the lesion information of each medical image for which the lesion information has been calculated; A medical image display method including the above.

Images