WO2020050272A1

WO2020050272A1 - Diagnosis support device, diagnosis support method and diagnosis support program

Info

Publication number: WO2020050272A1
Application number: PCT/JP2019/034623
Authority: WO
Inventors: 哲也上羽; 紀代美水口; 仁福田
Original assignee: 国立大学法人高知大学
Priority date: 2018-09-07
Filing date: 2019-09-03
Publication date: 2020-03-12
Also published as: JP7393798B2; JPWO2020050272A1

Abstract

This diagnosis support device (3), which supports a diagnosis of a vascular disease, includes: an image acquisition unit (341) which acquires an image including a cross section of a blood vessel; a line segment setting unit (342) which sets one or more line segments crossing the cross section; and a luminance distribution calculation unit (343) which calculates a luminance distribution on the line segment.

Description

Diagnosis support device, diagnosis support method, and diagnosis support program

The present invention relates to a technique for supporting diagnosis of a vascular disease, and particularly to a technique for supporting diagnosis of arterial dissection.

Arterial dissection is defined as blood flow in a blood vessel that has entered the blood vessel wall and has developed between the walls. The vascular wall of the artery is composed of the inner elastic plate, the media and the adventitia from the inside, and the artery consists of an elastic artery whose media is rich in elastic fibers and a muscular muscle whose media is almost free of elastic fibers. Arteries are classified. In a muscular artery, the media (media smooth muscle) is soft, so if the internal elastic plate is torn by any cause, blood flows into the media smooth muscle layer to form a false lumen, thereby causing arterial dissection.

Muscular arteries include, for example, cerebral arteries, brachial arteries, femoral arteries, popliteal arteries, and the like, and arterial dissection is particularly common in cerebral arteries. According to the nationwide survey data described in Non-Patent Document 1, it is shown that cerebral artery dissections, which are common in Japanese, are vertebral arteries and basilar arteries.

臨床 In clinical diagnosis of cerebral artery dissection, image diagnosis is particularly important, in addition to the presence of antecedent headache, changes in the shape of blood vessels over time. Specifically, the presence of intimal flap (hereinafter referred to as “flap”) specific to arterial dissection or false intracavitary hematoma is demonstrated by angiography, MRA (CE-MRA) original image, CTA original image, and the like. Diagnosis of cerebral artery dissection is made (Non-Patent Document 2). In particular, the presence of flaps is a reliable indicator of cerebral artery dissection.

In addition, in a study conducted by the present inventors on 10 patients in whom temporal changes in the shape of blood vessels and pseudointracavitary hematoma were confirmed, flaps of vertebral basilar artery dissection and structures such as pseudointraluminal hematoma were depicted. Showed that a 3T fat-suppressed T1-weighted image using local excitation (HR @ vfl-TSE method) was more useful than the MRA original image and the CTA original image.

However, at present, the image diagnosis of arterial dissection is performed only by MRI, and cerebral angiography and histological proof have not been made. In addition, the ability to detect flaps and false intracavitary hematomas depends on the qualitative evaluation of doctors and technicians who interpret cerebral blood vessel images, and thus there is room for bias. In addition, even when the resolution of the HR @ vfl-TSE method was used, there were cases in which the depiction of structures in the dissociation space was insufficient, and the situation was not high in diagnostic accuracy by interpretation.

The present invention has been made to solve the above-described problem, and has as its object to provide a diagnosis support apparatus that improves the accuracy of diagnosing a vascular disease.

As a result of intensive studies to solve the above problems, the present inventors have found that a disease can be predicted based on the luminance distribution in a line segment set in a cross-sectional image of a blood vessel.

That is, the present invention includes the inventions described in the following items.
Item 1.
A diagnosis support device that supports diagnosis of a vascular disease,
An image acquisition unit that acquires an image including a cross section of the blood vessel,
A line segment setting unit that sets one or more line segments that cross the cross section;
A luminance distribution calculation unit that calculates a luminance distribution in the line segment;
, A diagnosis support device.
Item 2.
A curve creation unit that creates a brightness distribution curve indicating the brightness distribution,
A display unit that displays the luminance distribution curve;
The diagnosis support device according to item 1, further comprising:
Item 3.
Item 3. The diagnosis support device according to item 1 or 2, further comprising a prediction unit that predicts the presence or absence of the disease based on the luminance distribution.
Item 4.
Item 4. The diagnosis support device according to item 3, wherein the prediction unit predicts the presence or absence of the disease based on a luminance change pattern of the line segment.
Item 5.
The diagnosis support device according to

item

3 or 4, wherein the prediction unit predicts the presence or absence of the disease based on a difference between a maximum value and a minimum value of luminance in the line segment.
Item 6.
Item 4. The diagnosis support device according to item 3, wherein the prediction unit performs prediction using artificial intelligence.
Item 7.
Item 7. The diagnosis support device according to any one of Items 1 to 6, wherein the blood vessel is a cerebral artery.
Item 8.
Item 8. The diagnosis support device according to item 7, wherein the disease is arterial dissection.
Item 9.
Item 9. The diagnosis support device according to any one of Items 1 to 8, wherein the line segment setting unit sets four or more line segments that cross each other at at least one place.
Item 10.
Item 10. The diagnosis support device according to item 9, wherein the line segment passes through a central region of the cross section.
Item 11.
Item 11. The diagnosis support device according to any one of Items 1 to 10, wherein the image is a 3T fat suppression T1 weighted image using local excitation.
Item 12.
The diagnosis support apparatus according to any one of Items 1 to 10, wherein the image is a CTA original image.
Item 13.
The diagnosis support apparatus according to any one of Items 1 to 10, wherein the image is an MRA original image.
Item 14.
A diagnosis support method for supporting diagnosis of a vascular disease,
An image acquisition step of acquiring an image including a cross section of the blood vessel,
A line segment setting step of setting one or more line segments crossing the cross section;
A luminance distribution calculating step of calculating a luminance distribution in the line segment of the cross section;
, A diagnostic support method.
Item 15.
A diagnosis support program that operates a computer as a diagnosis support device that supports diagnosis of a vascular disease,
An image acquisition unit that acquires an image including a cross section of the blood vessel,
A line segment setting unit that sets one or more line segments that cross the cross section, and
A luminance distribution calculation unit that calculates a luminance distribution in the line segment of the cross section,
A diagnostic support program that operates a computer as a computer.

According to the present invention, the accuracy of diagnosing a vascular disease can be improved.

It is a block diagram showing the composition of the diagnosis support system concerning one embodiment of the present invention. (A) is a cross-sectional view showing an example of a patent type arterial dissection, and (b) to (d) are an HR @ vfl-TSE image, an MRA original image, and a CTA original image, respectively, corresponding to the cross section. . (A) is a cross-sectional view showing an example of a pseudo-intraluminal hematoma formation type artery dissection, and (b) to (d) respectively show an HR @ vfl-TSE image, an MRA original image, and a CTA original corresponding to the cross section. It is an image. (A) shows a state in which four line segments are set in the HR @ vfl-TSE image shown in FIG. 2 (b), and (b) to (e) show each of the four line segments. It is a graph which shows a brightness distribution curve. (A) shows a state in which four line segments are set in the HR @ vfl-TSE image shown in FIG. 3 (b), and (b) to (e) respectively show each of the four line segments. It is a graph which shows a brightness distribution curve. (A) shows a state in which four line segments are set in a cross-sectional image of a normal artery in which an artifact has appeared, and (b) to (e) show respective luminance distribution curves in each of the four line segments. FIG. (A) shows a state where four line segments are set in the MRA original image shown in FIG. 2 (c) or the CTA original image shown in FIG. 2 (d), and (b) to (e) respectively. 4 is a graph showing each luminance distribution curve in each of the four line segments. 3A shows a state in which four line segments are set in the MRA original image shown in FIG. 3C, and FIGS. 3B to 3E show respective luminance distributions in the four line segments. It is a graph which shows a curve. 3A shows a state in which four line segments are set in the CTA original image shown in FIG. 3D, and FIGS. 3B to 3E show respective luminance distributions in each of the four line segments. It is a graph which shows a curve. 5 is a flowchart illustrating a procedure of a diagnosis support method according to an embodiment of the present invention. It is a block diagram showing the composition of the diagnosis support system concerning the modification of one embodiment of the present invention. It is a box-and-whisker diagram which shows the distribution of the brightness | luminance difference in each brightness | luminance distribution curve of patent type arterial dissection, pseudointrahematoma formation type artery dissection, and atherosclerosis.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. Note that the present invention is not limited to the embodiments described below.

(overall structure)
FIG. 1 is a block diagram illustrating a configuration of a diagnosis support system 1 according to an embodiment of the present invention. The diagnosis support system 1 includes an imaging device 2 and a diagnosis support device 3.

The imaging device 2 is a device that captures a medical image. As the imaging device 2, an MRI device or a CT device can be used, but a 3 Tesla MRI device is preferable. The 3 Tesla MRI apparatus uses a local excitation technique and a high resolution 3D vfl-TSE 3T fat suppression T1-weighted image (hereinafter, “HR”) using a variable flip angle Turbo Spin Echo method (hereinafter, “vfl-TSE method”). vfl-TSE image ").

In the present embodiment, the imaging apparatus 2 captures an HR @ vfl-TSE image (3T fat suppression T1-weighted image using local excitation) including a cross section of the subject's cerebral artery. The imaging device 2 is communicably connected to the diagnosis support device 3, and an image captured by the imaging device 2 is input to the diagnosis support device 3.

(Diagnosis support device)
The diagnosis support device 3 can be configured by, for example, a general-purpose personal computer, and has a hardware configuration including a CPU (not shown), a main storage device (not shown), an auxiliary storage device 31, an input unit 32, and a display unit. 33 are provided. In the diagnosis support device 3, the CPU reads out various programs stored in the auxiliary storage device 31 to the main storage device and executes the programs, thereby executing various calculation processes.

The auxiliary storage device 31 can be composed of, for example, a hard disk drive (HDD) or a solid state drive (SSD). The auxiliary storage device 31 stores a diagnosis support program P in addition to the medical image captured by the imaging device 2. The diagnosis support program P may be recorded on a non-transitory computer-readable recording medium such as a CD-ROM, and by causing the diagnosis support device 3 to read the recording medium, the diagnosis support program P is read. 3 may be installed. Alternatively, the code of the diagnosis support program P may be downloaded to the diagnosis support device 3 via a communication network such as the Internet. The auxiliary storage device 31 may be built in the diagnosis support device 3 or may be provided as an external storage device separate from the diagnosis support device 3.

The input unit 32 can be configured with, for example, a keyboard, a mouse, a touch panel, and the like. The display unit 33 can be configured by, for example, a liquid crystal display.

The diagnosis support device 3 has a function of supporting diagnosis of a vascular disease, and in this embodiment, particularly has a function of supporting diagnosis of arterial dissection of a cerebral artery. In order to realize the function, the diagnosis support device 3 includes a control unit 34. The control unit 34 is a functional block realized by the CPU reading the diagnostic support program P stored in the auxiliary storage device 31 into the main storage device and executing the program.

The control unit 34 includes an image acquisition unit 341 that acquires an image including a cross section of a blood vessel, a line segment setting unit 342 that sets one or more line segments that cross the cross section, and a luminance that calculates a luminance distribution in the line segment. A distribution calculation unit 343 and a curve creation unit 344 that creates a brightness distribution curve indicating the brightness distribution are provided. Hereinafter, the functions of these units will be described more specifically.

(Image acquisition)
The image acquisition unit 341 acquires an image including a cross section of the cerebral artery of the subject from the imaging device 2. In the present embodiment, the cross section means a plane substantially perpendicular to the short axis (Axial) of the blood vessel.

The following describes how the cross section of the artery is displayed according to the medical image and the type of arterial dissection. As described above, in the present embodiment, the HR @ vfl-TSE image (3T fat suppression T1-weighted image using local excitation), the MRA original image, and the CTA original image are assumed as medical images. Arterial dissection is classified into a patency type and a pseudo-intraluminal hematoma formation type depending on whether or not a thrombus has occurred in the false lumen.

FIG. 2 (a) shows an example of a cross-sectional structure of an artery of patent type arterial ablation. In a patent type arterial detachment, a flap dissociated from the blood vessel wall exists in the lumen, blood flow exists in both the true lumen and the false lumen, and the artery is subjected to HRＨvfl-TSE image, MRA source. The images and the CTA original images are displayed as shown in FIGS. 2B to 2D, respectively. That is, in the HR @ vfl-TSE image, the luminance of the blood flow part is low, whereas in the MRA original image and the CTA original image, the luminance of the blood flow part is high. Further, in any of the HR @ vfl-TSE image, the MRA original image, and the CTA original image, the blood vessel wall and the flap have a luminance between black and white.

FIG. 3 (a) shows an example of a cross-sectional structure of an artery of a pseudo-intraluminal hematoma formation type arterial detachment. In false lumen hematoma formation type arterial detachment, there is a flap dissociated from the vessel wall in the lumen, blood flow exists in the true lumen, hematoma exists in the false lumen, and the artery is The HR @ vfl-TSE image, the MRA original image, and the CTA original image are displayed as shown in FIGS. 3B to 3D, respectively. That is, in the HR @ vfl-TSE image and the MRA original image, the luminance of the hematoma portion is high, whereas in the CTA original image, the luminance of the hematoma portion is low.

(Line setting)
In the present embodiment, the line segment setting unit 342 illustrated in FIG. 1 sets four line segments that cross the cross section of the cerebral artery and intersect with each other in the central region of the cross section. For example, when the image acquired by the image acquiring unit 341 is an HR vfl-TSE image, and a cross section of a patent type arterial dissection artery shown in FIG. 342 sets four line segments L1 to L4 as shown in FIG.

The 分 line segments L1 to L4 are all straight lines and intersect with each other in the center region of the cross section. The angle between the line L1 and the line L2, the angle between the line L2 and the line L3, the angle between the line L3 and the line L4, and the angle between the line L4 and the line L1 are all 45 °. It is. Note that these angles do not necessarily have to be the same.

線 Moreover, the line segments L1 to L4 do not necessarily have to be straight lines and do not need to protrude from the cross section. The line segments L1 to L4 do not necessarily have to intersect at one point, but preferably pass through the central region. If the cross section is not circular, the center region may be specified by, for example, obtaining the center of gravity of the cross section.

(Calculation of luminance distribution and creation of luminance distribution curve)
The luminance distribution calculation unit 343 illustrated in FIG. 1 calculates a luminance distribution in the line segment set by the line segment setting unit 342. For example, as shown in FIG. 4A, when the line segments L1 to L4 are set in the arterial cross-sectional image of the patent type arterial dissection, the luminance distribution calculation unit 343 determines from one end to the other end of the cross section in the line segment L1. , And the same calculation is performed for the other line segments L2 to L4.

The curve creation unit 344 creates a brightness distribution curve (profile curve) indicating the brightness distribution calculated by the brightness distribution calculation unit 343. The luminance distribution curve created by the curve creating unit 344 is displayed on the display unit 33.

(Prediction when HR vfl-TSE image is used)
FIGS. 4B to 4E are graphs showing respective luminance distribution curves on the line segments L1 to L4 set in the HR vfl-TSE image shown in FIG. 4A. In each graph, the vertical axis corresponds to luminance, and the horizontal axis corresponds to coordinates along each of the line segments L1 to L4. In the HR vfl-TSE image, the portion where the blood flow exists has low luminance, and the flap has medium luminance. Therefore, in the line segment crossing the flap, the luminance changes from middle (blood vessel wall) to low (blood flow) → middle (flap) → low (blood flow) → middle (blood vessel wall).

Here, since the diagrams shown in FIG. 4A and the like are schematic cross-sectional views, the change in luminance at the boundary portion is steep, but the change in luminance at the boundary portion is gradual in an actual image. . Therefore, the actual luminance distribution curve is not an angular curve as shown in FIGS. 4B to 4E, but a rounded curve. Therefore, as shown in FIGS. 4C and 4D, the luminance distribution curve in which the luminance changes from middle → low → medium → low → medium has an ω shape as a whole.

Further, as shown in FIG. 5A, when the line segments L1 to L4 are set in the HR @ vfl-TSE image of the arterial cross section of the pseudo-intraluminal hematoma formation type arterial dissection, each luminance in the line segments L1 to L4 is set. The distribution curves are shown in FIGS. 5B to 5E, respectively. In the HR @ vfl-TSE image, the portion where the hematoma exists has a higher luminance than the flap. Therefore, in the line segment crossing the flap, the luminance is medium (blood vessel wall) → low (hematoma) → medium (flap) → high (blood flow) → medium (blood vessel wall) or medium (blood vessel wall) → high. (Blood flow) → medium (flap) → low (hematoma) → medium (blood vessel wall).

Here, as described above, since the actual luminance distribution curve is rounded and the width of the flap is small, the luminance of a portion from the blood flow (or hematoma) through the flap to the hematoma (or blood flow) is obtained. The distribution curve has a ∫ (integral symbol) shape. For example, the luminance distribution curves shown in FIGS. 5C and 5D include a portion having a ∫ shape that is inverted left and right.

Thus, in the HR vfl-TSE image, when a flap exists in the artery of the patent type arterial dissection, at least one of the luminance distribution curves of the line segments L1 to L4 has an ω shape. Further, when a flap exists in an artery dissociated in a pseudoluminal hematoma formation type artery, at least one of the luminance distribution curves of the line segments L1 to L4 includes a portion exhibiting a ∫ shape. Therefore, the user (a doctor, a technician, or the like) determines whether or not the flap exists and whether or not the artery dissection exists based on whether or not the luminance distribution curve has an ω shape and whether or not it includes a portion having a ∫ shape. The type can be predicted.

Note that, even in a normal artery where no flap has occurred, in the HR @ vfl-TSE image, as shown in FIG. 6A, a high-luminance portion called an artifact may appear in the center of the blood flow region. . When the line segments L1 to L4 pass through the artifact, as shown in FIGS. 6B to 6E, each of the luminance distribution curves of the line segments L1 to L4 has an ω shape.

Here, when less than four line segments are set in the cross section where the flap exists, the probability that all the line segments cross the flap increases as the number of line segments decreases. Therefore, when the set number of line segments is less than four, it is difficult to determine whether the luminance distribution curve is due to a flap or an artifact even if the luminance distribution curve has an ω shape.

On the other hand, when four or more line segments are set, only a part of the four line segments L1 to L4 is removed from the false lumen in the section where the flap exists, as shown in FIG. , The brightness distribution curves of all the line segments L1 to L4 do not necessarily have an ω shape. Therefore, by setting four or more line segments, even if an artifact occurs in a normal artery image, it is possible to prevent erroneous prediction that a flap exists in the artery. This makes it possible to further improve the prediction accuracy of arterial dissection as compared to the case where the set number of line segments is less than four.

(Prediction when using MRA original image or CTA original image)
FIG. 7A shows a state in which the line segments L1 to L4 are set in the MRA original image or the CTA original image of the arterial cross section of the patent type arterial dissection, and FIGS. 8 is a graph showing respective luminance distribution curves on line segments L1 to L4 shown in FIG. In both the MRA original image and the CTA original image, the luminance of the blood flow portion is higher than that of the flap. Therefore, in the line segment from the false lumen to the true lumen via the flap, the luminance changes from middle (blood vessel wall) to high (blood flow) → middle (flap) → high (blood flow) → middle (blood vessel wall). Therefore, as shown in FIGS. 7 (c) and 7 (d), the luminance distribution curve in which the luminance changes from medium → high → medium → high → medium has a vertically inverted ω shape (inverted ω shape) as a whole. Present.

FIG. 8A shows a state in which the line segments L1 to L4 are set in the MRA original image of the arterial cross section of the pseudo-intraluminal hematoma formation type arterial dissection, and FIGS. 8B to 8E respectively. FIG. 9 is a graph showing each luminance distribution curve in the line segments L1 to L4 shown in FIG. In the MRA original image, the brightness of the hematoma portion is higher than that of the flap similarly to the blood flow portion. Therefore, in the line segment from the false lumen to the true lumen via the flap, the luminance changes from middle (blood vessel wall) to high (hematoma) → middle (flap) → high (blood flow) → middle (blood vessel wall). Therefore, as shown in FIGS. 8C and 8D, the luminance distribution curve in which the luminance changes from middle to high to middle to high to middle has an inverted ω shape as a whole.

Thus, in the MRA original image, when a flap is present in the artery, at least one of the luminance distribution curves is inverted ω-shaped regardless of whether the artery is a patent type or a pseudo-intraluminal hematoma formation type. Present. Therefore, when an MRA original image is used, the presence of a flap can be predicted, but the type of arterial dissection cannot be determined.

FIG. 9A shows a state in which the line segments L1 to L4 are set in the CTA original image of the arterial cross section of the pseudo-intraluminal hematoma formation type arterial dissection, and FIG. 9B to FIG. 10 is a graph showing luminance distribution curves on line segments L1 to L4 shown in FIG. 9 (a). In the CTA original image, the brightness of the hematoma portion is lower than that of the flap. Therefore, in the line segment from the false lumen to the true lumen via the flap, the luminance changes from middle (blood vessel wall) to low (hematoma) → middle (flap) → high (blood flow) → middle (blood vessel wall). As described above, since the actual luminance distribution curve is a rounded curve, a portion where the luminance distribution curve changes from middle to high to middle has a △ (delta) shape. Therefore, as shown in FIGS. 9C and 9D, the luminance distribution curve in which the luminance changes from medium → low → medium → high → medium includes a portion exhibiting a △ shape.

Thus, in the CTA original image, in the case of patent type arterial dissection, as shown in FIGS. 7C and 7D, at least one of the luminance distribution curves has an inverted ω shape, and pseudointracavitary hematoma formation In the case of type arterial dissection, as shown in FIGS. 9C and 9D, at least one of the luminance distribution curves includes a portion having a △ shape. Therefore, the user can predict the presence or absence of a flap and the type of arterial dissection based on whether or not the luminance distribution curve has an inverted ω shape and whether or not the portion has a △ shape. it can.

(Diagnosis support method)
FIG. 10 is a flowchart illustrating a procedure of the diagnosis support method according to the present embodiment. The diagnosis support method according to the present embodiment is performed by the diagnosis support system 1.

In step S1, the imaging device 2 captures an image including a cross section of the cerebral artery of the subject.

In step S2 (image acquisition step), the image acquisition unit 341 acquires an image including a cross section of the cerebral artery from the imaging device 2.

In step S3 (line segment setting step), the line segment setting unit 342 sets one or more line segments that cross the cross section included in the image. In the present embodiment, as shown in FIG. 4A and the like, four line segments L1 to L4 are set.

In step S4 (luminance distribution calculation step), the luminance distribution calculation unit 343 calculates the luminance distribution in the line segments L1 to L4.

In step S5, the curve creating unit 344 creates a brightness distribution curve indicating the calculated brightness distribution.

In step S6, the display unit 33 displays the created luminance distribution curve.

(Summary)
As described above, in the present embodiment, for the image including the cross section of the artery acquired by the image acquisition unit 341, the line segment setting unit 342 sets one or more line segments that cross the cross section, and the luminance distribution calculation unit A calculation unit 343 calculates a luminance distribution in the line segment, a curve generation unit 344 generates a luminance distribution curve indicating the luminance distribution, and a display unit 33 displays the luminance distribution curve. This allows the user to predict the presence or absence of cerebral artery dissection based on the shape of the luminance distribution curve.

If the image is an HR vfl-TSE image, the user can determine whether or not a flap exists based on whether the luminance distribution curve has an ω shape and whether or not the portion has a ∫ shape, The type of cerebral artery dissection can be predicted. When the image is the CTA original image, the user can determine whether or not the flap exists and whether or not the brain has a flap based on whether or not the luminance distribution curve has an inverted ω shape and whether or not the portion has a △ shape. The type of arterial dissection can be predicted. If the image is the MRA original image, the user cannot predict the type of cerebral artery dissection, but based on whether or not the luminance distribution curve has an inverted ω shape, the presence or absence of a flap, that is, the cerebral artery It can be predicted whether or not dissociation has occurred.

Therefore, the use of the diagnosis support apparatus 3 makes it possible to improve the diagnosis accuracy of cerebral artery dissection as compared with the diagnosis based on the interpretation of an image that is likely to differ depending on the skills of doctors and technicians.

(Modification)
Hereinafter, a modified example of the present embodiment will be described. In the present modification, members having the same functions as those already described are denoted by the same reference numerals, and description thereof will be omitted.

FIG. 11 is a block diagram showing a configuration of a diagnosis support system 1 'according to a modification of the present embodiment. The diagnosis support system 1 'includes an imaging device 2 and a diagnosis support device 3'. That is, the diagnosis support system 1 'has a configuration in which the diagnosis support device 3 is replaced with the diagnosis support device 3' in the diagnosis support system 1 shown in FIG.

The diagnosis support device 3 'includes a CPU (not shown), a main storage device (not shown), an auxiliary storage device 31, an input unit 32, a display unit 33, and a control unit 34'. . That is, the diagnosis support device 3 'has a configuration in which the control unit 34 is replaced with a control unit 34' in the diagnosis support device 3 shown in FIG.

The control unit 34 ’includes an image acquisition unit 341, a line segment setting unit 342, a luminance distribution calculation unit 343, and a prediction unit 345. That is, the control unit 34 ′ has a configuration in which the curve creation unit 344 is replaced by the prediction unit 345 in the control unit 34 shown in FIG.

The prediction unit 345 predicts the presence or absence of a disease, in particular, the presence or absence of cerebral artery dissection based on the luminance distribution calculated by the luminance distribution calculation unit 343. That is, in the above embodiment, the user predicts the presence or absence of cerebral artery dissection based on the shape of the luminance distribution curve displayed on the display unit 33. However, in the present modification, the prediction unit 345 Using the same criteria, the presence or absence of cerebral artery dissection is predicted.

For example, the medical image is an HR @ vfl-TSE image, and the luminance of at least one of the set line segments changes from medium to low to medium to low to medium (that is, when a luminance distribution curve is created). , A curve exhibiting an ω shape as a whole), the prediction unit 345 predicts a patent type arterial dissection. Similarly, the medical image is an HR @ vfl-TSE image, and in at least one of the set line segments, the luminance partially changes from low to medium to high or from high to medium to low (ie, In the case where the brightness distribution curve is created, a curve including a portion having a ∫ shape is obtained). In this case, the prediction unit 345 predicts that it is a pseudo-intracavity hematoma formation type arterial dissection.

In addition, the medical image is the MRA original image, and the brightness of at least one of the set line segments changes from medium to high to medium to high to medium. In this case, the prediction unit 345 predicts that it is arterial dissection. When the medical image is the MRA original image, the prediction unit 345 does not predict whether the type of arterial dissection is a patent type or a pseudointracavitary hematoma formation type.

Also, the medical image is a CTA original image, and the luminance of at least one of the set line segments changes from medium to high to medium to high to medium (that is, when a luminance distribution curve is created, In this case, the prediction unit 345 predicts a patent type arterial dissection. Similarly, the medical image is a CTA original image, and at least one of the set line segments has a luminance that partially changes from medium to high to medium (that is, when a luminance distribution curve is created, In the case where the curve includes a portion having a shape), the prediction unit 345 predicts that the intraluminal hematoma formation type arterial dissection is to be performed.

予測 Thus, the prediction unit 345 can predict the presence or absence of arterial dissection based on the luminance change pattern in the line segment. The prediction result by the prediction unit 345 is displayed on the display unit 33. Thereby, the diagnosis support apparatus 3 'can support the diagnosis of cerebral artery dissection by the user.

As a further modification, it is preferable that the prediction unit 345 performs prediction using artificial intelligence (AI). In this case, the luminance distribution of each line set on the cross section of the artery is calculated using the image acquisition unit 341, the line segment setting unit 342, and the luminance distribution calculating unit 343 for the medical images of many subjects. Teacher data is created by associating the distribution data with the definitive diagnosis result of each subject. Based on the teacher data, machine learning is performed using, for example, a neural network or the like, and the prediction unit 345 is realized by a learned algorithm. The artificial intelligence is not limited to the neural network, and any known artificial intelligence technology can be used.

Generally, the prediction accuracy improves as the number of line segments set in the cross section of the artery increases. However, in the prediction performed by the user described in the above embodiment, the luminance distribution curve increases, which makes prediction more difficult. On the other hand, in the prediction by the prediction unit 345 (particularly, prediction using artificial intelligence), highly accurate prediction is possible by setting many line segments.

疾患 Atherosclerosis is a disease in which a cross-sectional image of a blood vessel is similar to arterial dissection. In blood vessels that have developed atherosclerosis, plaques (atheromas) in which cholesterol and the like are accumulated are formed. Therefore, in FIG. 5A, the cross-sectional image of the blood vessel approximates that obtained by replacing the hematoma in the false cavity with cholesterol or the like. Therefore, in the HR @ vfl-TSE image, in at least one of the set line segments, the luminance partially changes from low to medium to high or from high to medium to low, and when a luminance distribution curve is created, Similar to the intraluminal hematoma formation type arterial dissection, a curve including a ∫-shaped portion is obtained.

Here, the brightness distribution curve of atherosclerosis is a difference between the maximum value and the minimum value of the brightness (hereinafter, referred to as a signal difference) as compared to the brightness distribution curve of a pseudointracavitary hematoma-forming artery dissection. Tend to be small (see FIG. 12). Therefore, the prediction unit 345 further determines that at least one of the line segments set in the blood vessel portion of the HR @ vfl-TSE image has changed in luminance from low to medium to high or from high to medium to low. Based on the luminance difference in the luminance distribution curve, it is possible to predict whether it is pseudo-intraluminal hematoma formation type arterial dissection or atherosclerosis.

Further, as shown in FIG. 12, the luminance difference of the luminance distribution curve is
There is a tendency for pseudointrahematoma-forming arterial dissection>atherosclerosis> patent type arterial dissection. Therefore, the prediction unit 345 can predict the presence or absence of the above three diseases based only on the luminance difference of the luminance distribution curve. However, in order to increase the prediction accuracy, it is preferable that the prediction unit 345 predicts the presence or absence of a disease based on both the luminance change pattern and the luminance difference in the line segment.

[Appendix]
The present invention is not limited to the above-described embodiment, and various changes can be made within the scope shown in the claims, and a form obtained by appropriately combining the technical means disclosed in the embodiment is also a technology of the present invention. Included in the target range.

Hereinafter, examples of the present invention will be described, but the present invention is not limited thereto.
In the present example, HR vfl-TSE images were obtained for 26 patients with patent type arterial dissection, 28 patients with pseudointracavitary hematoma-forming type arterial dissection, and 15 patients with atherosclerosis. Then, four line segments were set in the blood vessel portion in each image, and the luminance distribution in the line segments was calculated. Further, for each luminance distribution, a difference (luminance difference) between the maximum value and the minimum value of the luminance was calculated.

FIG. 12 is a box-and-whisker plot showing the distribution of luminance differences in the luminance distribution curves of patent-type arterial dissection (ω), pseudo-intraluminal hematoma-forming arterial dissection (∫), and atherosclerosis (p∫). . As shown in the figure, the brightness difference in each brightness distribution curve of the patent type arterial dissection, pseudointracavitary hematoma formation type arterial dissection and atherosclerosis, the interquartile ranges do not overlap each other,
There is a tendency for pseudointrahematoma-forming arterial dissection>atherosclerosis> patent type arterial dissection. Therefore, it was found that the luminance difference between the luminance distribution curves could be an index for predicting the presence or absence of the above three diseases.

In the above embodiment, the diseases to be predicted are cerebral artery dissection and atherosclerosis, but are not particularly limited as long as they are vascular diseases.

DESCRIPTION OF SYMBOLS 1 Diagnosis support system 1 'Diagnosis support system 2 Imaging device 3 Diagnosis support device 3' Diagnosis support device 31 Auxiliary storage device 32 Input unit 33 Display unit 34 Control unit 34 'Control unit 341 Image acquisition unit 342 Line segment setting unit 343 Luminance distribution Calculation unit 344 Curve creation unit 345 Prediction units L1 to L4 Line segment P Diagnosis support program

Claims

A diagnosis support device that supports diagnosis of a vascular disease,
An image acquisition unit that acquires an image including a cross section of the blood vessel,
A line segment setting unit that sets one or more line segments that cross the cross section;
A luminance distribution calculation unit that calculates a luminance distribution in the line segment;
, A diagnosis support device.
A curve creation unit that creates a brightness distribution curve indicating the brightness distribution,
A display unit that displays the luminance distribution curve;
The diagnosis support device according to claim 1, further comprising:
The diagnosis support apparatus according to claim 1 or 2, further comprising a prediction unit that predicts the presence or absence of the disease based on the luminance distribution.
The diagnosis support device according to claim 3, wherein the prediction unit predicts the presence or absence of the disease based on a luminance change pattern of the line segment.
5. The diagnosis support apparatus according to claim 3, wherein the prediction unit predicts the presence or absence of the disease based on a difference between a maximum value and a minimum value of luminance in the line segment.
The diagnosis support apparatus according to claim 3, wherein the prediction unit performs prediction using artificial intelligence.
7. The diagnosis support device according to claim 1, wherein the blood vessel is a cerebral artery.
The diagnosis support apparatus according to claim 7, wherein the disease is arterial dissection.
The diagnosis support device according to any one of claims 1 to 8, wherein the line segment setting unit sets four or more line segments that intersect each other at at least one location.
The diagnosis support apparatus according to claim 9, wherein the line segment passes through a central region of the cross section.
The diagnosis support apparatus according to any one of claims 1 to 10, wherein the image is a 3T fat suppression T1-weighted image using local excitation.
The diagnosis support apparatus according to any one of claims 1 to 10, wherein the image is a CTA original image.
The diagnostic support apparatus according to any one of claims 1 to 10, wherein the image is an MRA original image.
A diagnosis support method for supporting diagnosis of a vascular disease,
An image acquisition step of acquiring an image including a cross section of the blood vessel,
A line segment setting step of setting one or more line segments crossing the cross section;
A luminance distribution calculating step of calculating a luminance distribution in the line segment of the cross section;
, A diagnostic support method.
A diagnosis support program that operates a computer as a diagnosis support device that supports diagnosis of a vascular disease,
An image acquisition unit that acquires an image including a cross section of the blood vessel,
A line segment setting unit that sets one or more line segments that cross the cross section, and
A luminance distribution calculation unit that calculates a luminance distribution in the line segment of the cross section,
A diagnostic support program that operates a computer as a computer.