Method and device for analyzing location of brain disease lesion

Abstract

The present invention relates to a method and a device for analyzing the location of a brain disease lesion. The method according to one embodiment of the present invention is performed by an electronic device, and comprises the steps of: match-processing a plurality of first medical images so that a brain shape matches the plurality of first medical images obtained by capturing brain portions of vascular occlusion stroke patients; setting a common region including common voxels, which are voxels of a lesion location overlapped in at least N (N is a natural number of 2 or higher) images from among the plurality of first medical images; performing clustering on data of the common region so as to divide the common region into a plurality of regions, thereby deriving a clustered image, which is an image in which each divided region is displayed; and reflecting the pathological cause of a small subcortical infarction so as to divide each region of the stroke portion, thereby analyzing whether the cerebral infarction is caused by an occlusion of a small blood vessel or an occlusion of a large blood vessel entrance.

Description

Method and device for analyzing the location of brain disease lesions

[0001] The present invention relates to a technique for analyzing the location of a lesion in a brain disease, and more particularly, to a technique for analyzing the detailed location of a lesion in a stroke.

[0002] In the event of a brain disease such as a stroke, the golden hour for treatment is crucial. To achieve this, a rapid and accurate analysis of the patient's condition must be performed based on medical imaging of the patient's brain. These medical images depict the internal structures of the brain, including structural details, internal tissues, and fluid flow.

[0003] A technology for analyzing brain diseases based on such medical images is disclosed in KR 10-2012-50379 A (hereinafter referred to as "prior art"). This prior art relates to a technology for determining whether a subject is suffering from a brain disease.

[0004] Meanwhile, for cerebral infarctions, such as small subcortical infarctions, treatment methods vary depending on the location of the occlusion (i.e., the location of the lesion) causing the stroke. For example, treatment methods may vary depending on whether the stroke is caused by occlusion of a small blood vessel located in a specific brain region or by occlusion of the entrance to a large blood vessel, which is the superior vessel from which the small blood vessel branches.

[0005] However, conventional technologies have limitations in that they are technologies that simply determine whether a brain disease has occurred or whether it is a blockage of a small blood vessel or a large blood vessel entrance.

[0006] However, the above-described content merely provides background information on the present invention and does not correspond to previously disclosed technology.

[0007] (Prior Art) KR 10-2012-50379 A

[0008] In order to solve the problems of the prior art as described above, the purpose of the present invention is to provide a technology for analyzing the detailed lesion location for stroke.

[0009] In particular, the present invention aims to provide a technique for analyzing detailed lesion locations for small subcortical cerebral infarctions such as small subcortical cerebral infarctions or large vessel branch occlusive cerebral infarctions.

[0010] However, the problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

[0011] According to an embodiment of the present invention for solving the above-described problem, a method is performed in an electronic device, comprising: a step of performing alignment processing on a plurality of first medical images taken of brain regions of patients with vascular occlusive stroke so that brain shapes are aligned with respect to the plurality of first medical images; a step of setting a common region including common voxels, which are voxels of overlapping lesion locations, in at least N images (wherein N is a natural number greater than or equal to 2) of the plurality of first medical images; and a step of performing clustering on data of the common region to divide the common region into a plurality of regions, thereby deriving a clustered image, which is an image in which each of the divided regions is displayed.

[0012] The method according to one embodiment of the present invention further includes a step of reducing the dimension of data in the common region between the setting step and the deriving step, and the deriving step may include a step of performing the clustering on data in the common region whose data dimension has been reduced.

[0013] A method according to one embodiment of the present invention may further include a step of displaying a template for the clustered image and a second medical image capturing a brain region of a patient with vascular occlusion stroke who is a target of treatment.

[0014] The step of displaying the above may include a step of displaying the clustered regions of the template and the stroke region of the second medical image so as to overlap.

[0015] The above first medical image may be a medical image of patients who have suffered a vascular occlusive stroke due to either a first blockage corresponding to a small vessel blockage or a second blockage corresponding to a large vessel entrance blockage.

[0016] A method according to one embodiment of the present invention may further include a step of determining that a patient in the second medical image has suffered a vascular occlusive stroke due to a first blockage or a second blockage, based on the similarity between each clustered region of the clustered image and a stroke site in the second medical image.

[0017] The above-described judging step may include a step of judging that the patient of the second medical image has suffered a vascular occlusive stroke due to a first blockage when the similarity is greater than a certain level, and a step of judging that the patient of the second medical image has suffered a vascular occlusive stroke due to a second blockage when the similarity is less than a certain level.

[0018] The first medical image may include a first-first medical image for patients who have suffered a vascular occlusive stroke due to either a first blockage corresponding to a small vessel blockage or a second blockage corresponding to a large vessel entrance blockage, and a first-second medical image for patients who have suffered a vascular occlusive stroke due to either the other of the first and second blockages.

[0019] The plurality of first medical images used in the setting step are the 1-1 medical images, and the method according to one embodiment of the present invention may further include, after the deriving step, a step of comparing the clustered image with the 1-2 medical image to determine whether the clustered image is suitable.

[0020] The above-described judging step may include a step of judging whether the clustered image is suitable based on whether the difference between the stroke area of ​​the first-second medical image and each clustered area of ​​the clustered image is greater than a certain level.

[0021] The setting step may include a step of setting a first common region, which is the common region for a plurality of 1-1 medical images, and a second common region, which is the common region for a plurality of 1-2 medical images, and the deriving step may include a step of deriving a first clustered image, which is the clustered image for data of the first common region, and a second clustered image, which is the clustered image for data of the second common region.

[0022] A device according to one embodiment of the present invention includes a memory storing a plurality of first medical images of brain regions of patients with vascular occlusion stroke; and a control unit controlling the derivation of a clustered image to assist in the analysis of a second medical image of a brain region of a patient with vascular occlusion stroke who is a subject of treatment, using the plurality of first medical images.

[0023] The control unit may control to process the plurality of first medical images for matching so that the brain shapes of each first medical image are matched, control to set a common region including common voxels that are voxels of overlapping lesion locations in at least N images (wherein N is a natural number greater than or equal to 2) of the plurality of first medical images, and control to perform clustering on data of the common region to divide the common region into a plurality of regions, thereby deriving the clustered image in which each divided region is displayed.

[0024] The above control unit can control to reduce the dimension of data in the common area, and perform the clustering on data in the common area whose data dimension has been reduced.

[0025] The above control unit can control to display, on a display, a template for a clustered image and a second medical image taken of a brain region of a patient with vascular occlusion stroke who is the subject of treatment.

[0026] The first medical image is a medical image of patients who have suffered a vascular occlusive stroke due to either a first blockage corresponding to a small vessel blockage or a second blockage corresponding to a large vessel entrance blockage, and the control unit can control the determination that the patient of the second medical image has suffered a vascular occlusive stroke due to the first blockage or the second blockage based on the similarity between each clustered region of the clustered image and the stroke site of the second medical image.

[0027] The control unit can determine that the patient of the second medical image has suffered a vascular occlusive stroke due to the first blockage when the similarity is greater than a certain level, and can control the control to determine that the patient of the second medical image has suffered a vascular occlusive stroke due to the second blockage when the similarity is less than a certain level.

[0028] The first medical image may include a first-first medical image for patients who have suffered a vascular occlusive stroke due to either a first blockage corresponding to a small vessel blockage or a second blockage corresponding to a large vessel blockage, and a first-second medical image for patients who have suffered a vascular occlusive stroke due to either the other of the first and second blockages.

[0029] The above control unit can control the setting of the common area using a plurality of 1-1 medical images, and compare the clustered image with the 1-2 medical image to determine whether the clustered image is suitable.

[0030] The above control unit can be controlled to determine whether the clustered image is suitable based on whether the difference between the stroke area of ​​the first-second medical image and each clustered area of ​​the clustered image is greater than a certain level.

[0031] The control unit controls to set a first common area, which is the common area for a plurality of 1-1 medical images, and a second common area, which is the common area for a plurality of 1-2 medical images, to derive a first clustered image, which is the clustered image for data of the first common area, and to derive a second clustered image, which is the clustered image for data of the second common area, and to display the first and second clustered images and the second medical image, which is an image of a brain region of a patient with vascular occlusion stroke who is a target of treatment, on a display, respectively.

[0032] According to another embodiment of the present invention, a device is provided for assisting analysis of a second medical image of a brain region of a patient with vascular occlusion stroke who is a subject of treatment, using a clustered image derived from a plurality of first medical images of the brain region of the patient with vascular occlusion stroke, the device including: a memory storing the clustered image and the second medical image; and a control unit controlling the display of a template for the clustered image and the second medical image, respectively, on a display.

[0033] The clustered image may be an image prepared through a process of matching a plurality of first medical images so that the brain shapes of each first medical image are matched, a process of setting a common region including common voxels that are voxels of overlapping lesion locations in at least N images (wherein N is a natural number greater than or equal to 2) of the plurality of first medical images, and a process of performing clustering on data of the common region to divide the common region into a plurality of regions and thereby deriving the clustered image in which each of the divided regions is displayed.

[0034] The present invention, configured as described above, can analyze detailed lesion locations for stroke, and has the advantage of being able to analyze detailed lesion locations for small subcortical cerebral infarctions such as small subcortical cerebral infarctions or large vascular occlusion strokes in particular.

[0035] In addition, the present invention has the advantage of providing a visual guideline for clinicians to differentiate the cause of small subcortical cerebral infarction by providing a brain lesion template related to small subcortical cerebral infarction.

[0036] In addition, the present invention has the advantage of improving the accuracy of analysis for small subcortical cerebral infarction by dividing each region of the cerebral infarction area by reflecting the pathological cause of small subcortical cerebral infarction caused by blockage of blood vessels in the subcortical brain region.

[0037] The effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention belongs from the description below.

[0038] Figure 1 shows a block diagram of a system (10) according to one embodiment of the present invention.

[0039] Figure 2 shows examples of lesion locations when small subcortical cerebral infarctions occur.

[0040] Figure 3 shows a block diagram of an analysis device (200) according to one embodiment of the present invention.

[0041] Figure 4 shows a block diagram of a control unit (250) in an analysis device (200) according to one embodiment of the present invention.

[0042] Figure 5 shows a flowchart of an analysis method according to one embodiment of the present invention.

[0043] Figure 6 shows an example for S520 to S540.

[0044] Figure 7 shows an example of a 1-1 clustered image when the number of clusters (k) is set to 12.

[0045] The above-described objects, means, and resulting effects of the present invention will become more apparent through the following detailed description, taken in conjunction with the accompanying drawings. Accordingly, those skilled in the art will be able to readily implement the technical concepts of the present invention. Furthermore, in describing the present invention, if a detailed description of known technology related to the present invention is deemed to unnecessarily obscure the gist of the invention, such detailed description will be omitted.

[0046] The terminology used herein is for the purpose of describing embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms, unless specifically stated otherwise. In this specification, terms such as "include," "provide," "provide," or "have" do not exclude the presence or addition of one or more other components other than the mentioned components.

[0047] In this specification, terms such as "or", "at least one", etc. may refer to one of the words listed together, or to a combination of two or more. For example, "A or B", "at least one of A and B" may include only one of A or B, or may include both A and B.

[0048] In this specification, descriptions using the phrase "for example" or the like should not be construed as limiting the embodiments of the invention in terms of the effects of variations such as tolerances, measurement errors, limitations of measurement accuracy, and other commonly known factors, including the information presented, such as cited characteristics, variables, or values, may not be exact matches.

[0049] In this specification, when a component is described as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. Conversely, when a component is described as being "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0050] In this specification, when a component is described as being "on" or "in contact with" another component, it should be understood that it may be directly on or connected to the other component, but there may be another component in between. Conversely, when a component is described as being "directly on" or "in direct contact with" another component, it should be understood that there is no other component in between. Other expressions that describe the relationship between components, such as "between" and "directly between", can be interpreted similarly.

[0051] In this specification, terms such as "first" and "second" may be used to describe various components, but the components should not be limited by these terms. Furthermore, these terms should not be construed to limit the order of each component, but rather may be used to distinguish one component from another. For example, a "first component" may be referred to as a "second component," and similarly, a "second component" may also be referred to as a "first component."

[0052] Unless otherwise defined, all terms used herein may be used in their common sense by those of ordinary skill in the art to which the present invention pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0053]

[0054] Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the attached drawings.

[0055] Figure 1 shows a block diagram of a system (10) according to one embodiment of the present invention.

[0056] A system (10) according to one embodiment of the present invention (hereinafter referred to as “the system”) is a system for analyzing the detailed lesion location of a stroke, such as a small subcortical cerebral infarction (small vessel occlusion stroke; lacunar cerebral infarction in the traditional sense) or a large vessel occlusion stroke (branch atheromatous stroke). Of course, the system may also be a system for assisting (i.e., providing assistance to) a user (e.g., a medical professional) in the analysis.

[0057] Stroke, in this case, is a disease in which a blood vessel supplying blood to the brain becomes blocked or bursts, damaging brain cells supplied by that blood vessel. Furthermore, cerebral infarction, caused by occlusion of a blood vessel, occurs when a cerebral blood vessel is blocked, preventing blood flow and resulting in the death of a portion of brain tissue.

[0058] Cerebral infarction can be generally divided into four categories based on clinical symptoms and lesion size on brain MRI. In particular, small subcortical infarction refers to a stroke that occurs in a small vessel among the brain's blood vessels. It corresponds to a cerebral infarction that occurs in the presence of a typical lacunar syndrome, without cerebral cortical symptoms, and with a lesion diameter of 20 mm or less (e.g., 1 mm to 20 mm). For example, small subcortical infarction may include lacunar infarction. Most lacunar infarctions occur in the periventricular white matter (PVWM) and basal ganglia (BG), with some occurring in the cerebellum or brainstem. Lesions that appear similar to small vessel occlusion infarction on brain imaging may be large vessel ostial occlusion infarctions. Differential diagnosis is important but difficult due to differences in treatment strategies and prognosis. In addition, cerebral infarction can be classified into large artery atherosclerotic stroke, stroke due to cardioembolism, and stroke of unknown cause, which is a cerebral infarction that occurs when a large cerebral blood vessel is stenotic or occluded by more than 50% due to atherosclerosis, and there is cerebral cortex or cerebellar dysfunction and the lesion is larger than 20 mm in diameter.

[0059] Figure 2 shows examples of lesion locations when lacunar cerebral infarction occurs. That is, Figure 2(a) shows an example of occlusion of a small vessel (V1), and Figure 2(b) shows an example of occlusion of the entrance to a large vessel (V2).

[0060] In particular, in the case of small subcortical cerebral infarctions such as small subcortical cerebral infarctions or large vessel entrance occlusion strokes, the treatment method and prognosis vary depending on the location of the occlusion (i.e., the location of the lesion) that causes the cerebral infarction. For example, referring to Fig. 2, the treatment method is applied differently depending on whether the cause of the small subcortical cerebral infarction is occlusion of a small blood vessel (V1), which is a blood vessel with a small diameter among microvessels, or occlusion of the entrance of a large blood vessel (V2), which is an upper blood vessel from which the small blood vessel (V1) differentiates.

[0061] However, even if brain images are provided for the brain regions of patients with small subcortical cerebral infarctions, the brain images do not provide detailed images of small vessel (V1) occlusion or large vessel entrance (V2) occlusion as shown in Figure 2, and only provide images of the stroke region for the damaged brain tissue region according to the occlusion.

[0062] Accordingly, the present system (10) and the analysis method described below are intended to provide a technology for analyzing the detailed lesion location and cause of a stroke (particularly, a small subcortical cerebral infarction) in a corresponding medical image. For example, referring to FIG. 2, the present system (10) and the analysis method described below are intended to provide a technology for analyzing whether a small subcortical cerebral infarction is due to occlusion of a small blood vessel (V1) or occlusion of the entrance to a large blood vessel (V2).

[0063] This system (10) may include a medical imaging device (100) and an analysis device (200), as shown in FIG. 1.

[0064] A medical imaging device (100) is a device that captures medical images of a brain region of a patient with a brain disease who has suffered a stroke. In other words, the medical image is an image captured by the medical imaging device (100) of a brain region of a patient with a small subcortical cerebral infarction, and may be a two-dimensional or three-dimensional image obtained using radiation, electromagnetic waves, etc. to understand the inside of the corresponding brain region.

[0065] For example, the medical image may be a computed tomography (CT) image, a magnetic resonance image (MRI), etc. In particular, since the image is of a small subcortical cerebral infarction such as a lacunar infarction, the medical image may be an MRI, and diffusion weighted MRI (DWI) may be preferable, but is not limited thereto.

[0066] DWI is a technique that measures the irregular movement of water molecules within tissue, i.e., the diffusion velocity. It is generally an image processing method that can detect cerebral infarction or lesions caused by cerebral vascular occlusion at an early stage. By detecting these signal changes, various ischemic brain tissue damages, such as the site and volume of brain tissue damage, can be visualized. The diffusion velocity is determined by the b-value, which represents the strength of the gradient magnetic field.

[0067] In particular, the medical imaging device (100) can be connected to the analysis device (200) and transmit the captured medical image to the analysis device (200). Of course, the medical image may be separately stored in another server, device, or storage medium and then transmitted to the analysis device (200). For example, the medical image may be transmitted to the analysis device (200) from the medical imaging device (100), another server or device, etc. through an internal network or an external network such as the Internet, or may be stored in a storage medium such as a flash memory or an optical disk and then stored in the analysis device (200) by connecting the storage medium to the analysis device (200).

[0068] Figure 3 shows a block diagram of an analysis device (200) according to one embodiment of the present invention.

[0069] The analysis device (200) is a device that processes a medical image captured by a medical imaging device (100). That is, the analysis device (200) may be a device that analyzes the detailed lesion location and cause of a small subcortical cerebral infarction in a medical image, or assists (i.e., provides assistance to) a user (e.g., a medical professional) in the analysis. This analysis device (200) is an electronic device capable of computing installed in a medical field, etc., and may include an input unit (210), a communication unit (220), a display (230), a memory (140), and a control unit (250), as illustrated in FIG. 3.

[0070] For example, the electronic device may be a general-purpose computing system such as a desktop personal computer, a laptop personal computer, a tablet personal computer, a netbook computer, a workstation, a personal digital assistant (PDA), a smartphone, a smartpad, or a mobile phone, or a dedicated embedded system implemented based on Embedded Linux, but is not limited thereto.

[0071] The input unit (210) generates input data in response to various user inputs and may include various input means.

[0072] For example, the input unit (210) may include, but is not limited to, a keyboard, a keypad, a dome switch, a touch panel, a touch key, a touch pad, a mouse, a menu button, etc.

[0073] The communication unit (220) is a component that performs communication with other devices, servers, medical imaging devices (100), etc. (hereinafter referred to as "other devices, etc."). For example, the communication unit (220) can receive various data or medical images, etc. required for performing the analysis method described below, from other devices, etc. In addition, the communication unit (200) can transmit data, such as the results of performing the analysis method of the analysis device (200) described below, to other devices, etc.

[0074] For example, the communication unit (220) may perform wireless communication such as 5G (5th generation communication), LTE-A (long term evolution-advanced), LTE (long term evolution), Bluetooth, BLE (Bluetooth low energy), NFC (near field communication), WiFi communication, or wired communication such as cable communication, but is not limited thereto.

[0075] The display (230) displays various image data on a screen and may be configured as a non-luminous panel or a luminous panel. That is, the display (230) can display image data according to the performance of the analysis method described below.

[0076] For example, the display (230) may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a micro electro mechanical systems (MEMS) display, or an electronic paper display. In addition, the display (230) may be implemented as a touch screen or the like by being coupled with an input unit (220, 220).

[0077] The memory (240) stores various types of information necessary for the operation of the analysis device (200). The information stored in the memory (240) may include, but is not limited to, image information, information transmitted and received with other devices via the communication unit (220), information for the control operation of the control unit (250), and program information related to the analysis method described below.

[0078] For example, the memory (240) may include, but is not limited to, a volatile memory device such as DRAM or SRAM, a non-volatile memory such as PRAM, MRAM, ReRAM, or NAND flash memory, a hard disk drive (HDD), or a solid state drive (SSD). In addition, the memory (240) may include, but is not limited to, a cache, a buffer, a main memory, an auxiliary memory, or a separately provided storage system depending on its use / location.

[0079] The control unit (250) can perform various control operations of the analysis device (200). That is, the control unit (250) can perform control over the medical imaging device (100) or control the execution of the analysis method described below. For example, the control unit (250) can control the display (230) to display a medical image, and can control the execution process and results of the analysis method described below to be displayed through the display (230).

[0080] In addition, the control unit (250) can control the operation of the remaining components of the analysis device (200), such as the input unit (210), the communication unit (220), the display (230), the memory (240), etc. Of course, the control unit (205) can also perform control on the medical imaging device (100). For example, the control unit (250) may include, but is not limited to, a hardware processor or a software process executed on the processor. For example, the processor may include, but is not limited to, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc.

[0081] Figure 4 shows a block diagram of a control unit (250) in an analysis device (200) according to one embodiment of the present invention.

[0082] The control unit (250) may include a matching unit (251), a boundary setting unit (252), a dimension reduction unit (253), a clustering unit (254), a comparison unit (255), and an analysis unit (256), as illustrated in FIG. 4, to control the execution of the analysis method described later. For example, the matching unit (251), the boundary setting unit (252), the dimension reduction unit (253), the clustering unit (254), the comparison unit (255), and the analysis unit (256) may be hardware components of the control unit (250), or may be software processes executed in the control unit (250), but are not limited thereto.

[0083] Hereinafter, an analysis method according to one embodiment of the present invention will be described in more detail.

[0084] Figure 5 shows a flowchart of an analysis method according to one embodiment of the present invention.

[0085] An analysis method according to one embodiment of the present invention (hereinafter referred to as “the analysis method”) is a method performed under the control of a control unit (250) of an analysis device (200), and may include S510 to S560, as illustrated in FIG. 5. That is, the processor of the control unit (250) may process the execution of S510 to S560 using information stored in the memory (240). However, at least one of S510 to S560 may be omitted, if necessary. For example, S530 or S550 may be omitted.

[0086] However, when performing S510 to S560, medical images previously stored in the memory (240) may be used. At this time, the medical images may be received by the analysis device (200) through an internal network or an external network such as the Internet from another device through the communication unit (220) and stored in the memory (240), or may be stored in a storage medium such as a flash memory or an optical disk and then stored in the memory (240) by connecting the storage medium to the analysis device (200).

[0087] These medical images can be divided into a first medical image (i.e., a training medical image) used in S510 to S550, and a second medical image (i.e., a target medical image) that is applied using the results of S510 to S550. It is preferable that these first and second medical images are medical images of different patients.

[0088] In this case, the first medical image is a medical image of a brain region of a patient who has previously suffered a small subcortical infarction (subcortical cerebral infarction) and is currently being treated. The second medical image is a medical image of a brain region of a patient who has suffered or is currently being treated and is predicted to suffer a small subcortical infarction (subcortical cerebral infarction).

[0089] This analysis method relates to a technique for analyzing the detailed lesion location and cause of small subcortical cerebral infarction in the second medical image by performing S510 to S550 based on a number of first medical images of patients who were previously treated, and then applying the second medical image of the patient who is currently being treated to the results of S510 to S550.

[0090] These S510 to S550, as described below, may be performed in the analysis device (200). At this time, the control unit (250) may also control the results of S510 to S550 to be transmitted to another device, which is an electronic device capable of computing, via the communication unit (220). In this case, the analysis device (200) may function as a server that provides the results of S510 to S550 to the other device.

[0091] In addition, the analysis device (200) may perform only S560. In this case, S510 to S550 may be performed on another device or server capable of computing, as described below. In this case, the results of S510 to S550 performed on the other device or server may be received by the analysis device (200) from the other device or server through the communication unit (220) via an internal network or an external network such as the Internet and stored in the memory (240), or may be stored in a storage medium such as a flash memory or an optical disk and then stored in the memory (240) by connecting the storage medium to the analysis device (200).

[0092] Additionally, the analysis device (200) stores the results of S510 to S550, receives a second medical image from another computing-capable device, performs S560 on the received second medical image, and transmits the results of S560 to the other device. In this case, the analysis device (200) may function as a server that provides the results of S560 to the other device.

[0093] Meanwhile, the first and second medical images used in S510 to S560 may be images that also include information about the stroke site. That is, the first and second medical images include image data taken of a brain site of a stroke patient, as well as data about the location of the site of the stroke (i.e., the location of the lesion) within the brain site.

[0094] Hereinafter, occlusion of the small vessel (V1) is referred to as “first occlusion,” and occlusion of the entrance to the large vessel (V2) is referred to as “second occlusion.”

[0095] In addition, the first medical image can be classified into a 1-1 medical image and a 1-2 medical image. In this case, the 1-1 medical image is a first medical image of a patient who has suffered a small subcortical cerebral infarction due to occlusion of either the first or second blockage. On the other hand, the 1-2 medical image is a first medical image of a patient who has suffered a small subcortical cerebral infarction due to occlusion of the other of the first and second blockages. Of course, the 2nd medical image is a second medical image of a current patient who has suffered or is predicted to suffer a small subcortical cerebral infarction due to the first or second blockage.

[0096] Below, the details of S510 to S550 will be explained.

[0097] <Example 1>

[0098] First, in S510, the alignment unit (251) aligns multiple first medical images. Each first medical image was acquired from a different patient and thus contains images of different brain morphologies. Accordingly, by performing alignment processing on each first medical image, the brain morphologies of each first medical image can be aligned and made similar.

[0099] For example, multiple first medical images can be aligned and processed based on a standard medical image. At this time, the standard medical image is a medical image captured of a corresponding brain region, and is an image that includes a standard brain shape for each medical image, which inevitably has a different brain shape for each person. Accordingly, the alignment unit (251) aligns the different brain shapes of different patients included in each first medical image to the standard brain shape included in the standard medical image. As a result, the brain shape of each aligned first medical image can be similar to the brain shape of the standard medical image. Of course, as a result of the alignment process, data on the location of the stroke site included in each first medical image is also corrected.

[0100] For this registration process, various conventional image registration algorithms that process heterogeneous images can be used. For example, linear or nonlinear rigid body registration algorithms can be used for registration processing of multiple primary medical images, but are not limited thereto.

[0101] For example, there may be 1000 first-order medical images, of which 600 may be first-order medical images and the remaining 400 may be first-order medical images.

[0102] Fig. 6 shows an example for S520 to S540. That is, Fig. 6(a) shows an example for the execution process of S520, Fig. 6(b) shows an example for the execution process of S530, Fig. 6(c) shows an example for the execution process of S540, and Fig. 6(d) shows an example for the execution result of S540.

[0103] Next, in S520, the boundary setting unit (252) sets a common area where a small subcortical cerebral infarction has occurred among a plurality of aligned 1-1 medical images, and sets a boundary (i.e., a brain lesion boundary) for the common area.

[0104] That is, the boundary setting unit (252) extracts voxels (hereinafter referred to as "common voxels") of overlapping lesion locations from at least N images (wherein N is a natural number of 2 or 3 or more) among a plurality of aligned 1-1 medical images, sets a common area including these common voxels, and sets a boundary for the common area, thereby setting a spatially connected brain lesion boundary. At this time, a voxel means a regular grid unit in the space of a 3D image, and may mean a pixel in a 2D plane image.

[0105] In particular, it may be desirable for the common voxel to be a voxel of a lesion location that overlaps in at least two different Type 1-1 medical images. However, for greater accuracy in lesion location, it may be more desirable for the common voxel to be a voxel of a lesion location that overlaps in at least three different Type 1-1 medical images.

[0106] For example, as illustrated in FIG. 6(a), the boundary setting unit (252) can mark voxels in a common region corresponding to common voxels overlapping three 1-1 medical images as 1 in a three-dimensional region corresponding to the brain region of a standard medical image, and mark voxels in regions corresponding to the remaining voxels other than the common voxels as 0. That is, the boundary setting unit (252) can set the boundary of the region marked as 1 in the three-dimensional region as the boundary of a brain lesion.

[0107] Next, in S530, the dimension reduction unit (253) reduces the dimension of the data of the common voxels (i.e., data of the common area) according to the setting of the brain lesion boundary to remove unnecessary information.

[0108] For example, as illustrated in FIG. 6(b), the dimensionality reduction unit (253) can reduce the dimensionality of the data of the common voxels (i.e., data of the common region) by performing logistic non-negative matrix factorization (logistic NMF). Data having a dimension of the number of voxels x the number of patients is converted into data having a dimensionality of the number of voxels x the number of reduced dimensions through dimensionality reduction in the patient dimension. This process compresses information about the patients, thereby preventing data overfitting during data clustering in S540. However, S530 may be omitted.

[0109] Next, at step S540, the clustering unit (254) performs clustering on the data of common voxels to divide the common region into multiple regions. Each of the divided regions contains information on the co-occurrence of similar lesions within the brain lesion boundary. Of course, if step S530 is performed, the data of the common voxels to be clustered may be dimensionally reduced data.

[0110] For example, as illustrated in Fig. 6(c), the clustering unit (254) can segment multiple regions by performing hierarchical clustering in the spatial dimension on data of common voxels in multiple 1-1 medical images. At this time, the number of clusters (k) can be applied in various ways as needed. That is, k is a natural number greater than or equal to 2.

[0111] Figure 7 shows an example of a 1-1 clustered image when the number of clusters (k) is set to 12.

[0112] As a result of performing S540, data of common voxels in a plurality of 1-1 medical images are clustered, and an image (hereinafter referred to as a "1-1 clustered image") showing a plurality of clustered (i.e. segmented) regions in a standard medical image can be derived. At this time, as illustrated in FIG. 6(d) and FIG. 7, each segmented region can be displayed in a different color in the 1-1 clustered image.

[0113] Next, in S550, the comparison unit (255) tests the suitability of the 1-1 clustered image by comparing the stroke area of ​​the 1-2 medical image with each clustered region of the 1-1 clustered image. At this time, it is preferable that the 1-2 medical image be an image that has been aligned with a standard medical image according to the process described above in S510.

[0114] That is, the comparison unit (255) can compare the 1-2 medical images one by one with the 1-1 clustered image. At this time, since the 1-1 clustered image is an image in which data of common voxels in multiple 1-1 medical images are clustered, the detailed lesion location and cause of the stroke are different from those of the 1-2 medical image. Accordingly, during the comparison, there is bound to be a significant difference between the stroke site of the 1-2 medical image and each clustered area of ​​the 1-1 clustered image.

[0115] For example, the 1-1 medical image may be the 1-1 medical image for a small subcortical cerebral infarction caused by the first blockage (i.e., blockage of a small blood vessel). In this case, the stroke area of ​​the 1-2 medical image caused by the second blockage (i.e., blockage of the entrance of a large blood vessel) usually occupies a wider area than each clustered area of ​​the 1-1 clustered image. At this time, if the area of ​​the stroke area of ​​the 1-2 medical image that deviates from each clustered area of ​​the 1-1 clustered image (i.e., the difference area between the stroke area of ​​the 1-2 medical image and each clustered area of ​​the 1-1 clustered image) is greater than or equal to a certain level, the comparison unit (255) may determine that the 1-1 clustered image is suitable. On the other hand, if the difference area is less than a certain level, the comparison unit (255) may determine that the 1-1 clustered image is not suitable.

[0116] Meanwhile, the 1-1 medical image may be the 1st medical image for a small subcortical cerebral infarction caused by a second blockage (i.e., blockage of a large blood vessel entrance). In this case, the stroke area of ​​the 1-2 medical image caused by the first blockage (i.e., blockage of a small blood vessel) usually occupies a narrower area than each clustered area of ​​the 1-1 clustered image. At this time, if the area among the clustered areas of the 1-1 clustered image that deviates from the stroke area of ​​the 1-2 medical image (i.e., the difference area between the clustered areas of the 1-1 clustered image and the stroke area of ​​the 1-2 medical image) is greater than or equal to a certain level, the comparison unit (255) may determine that the 1-1 clustered image is suitable. On the other hand, if the difference area is less than a certain level, the comparison unit (255) may determine that the 1-1 clustered image is not suitable.

[0117] Next, at S560, the analysis unit (256) provides a template of the first-first clustered image including each clustered region (also referred to as a “brain lesion template”). At this time, the template of the first-first clustered image may be a template for the first-first clustered image determined to be suitable at S550.

[0118] That is, the analysis unit (256) can display the templates of the second medical image and the 1-1 clustered image on the display (230), respectively. At this time, the template of the 1-1 clustered image can be displayed so as to overlap with the second medical image. That is, the clustered regions of the template of the 1-1 clustered image and the stroke area of ​​the second medical image can be displayed so as to overlap. Through this, a user (e.g., a medical professional, etc.) can easily analyze the detailed lesion location and cause of a small subcortical cerebral infarction in the second medical image.

[0119] For example, if the stroke area of ​​the second medical image is similar to each clustered area of ​​the first-1 clustered image, the user can analyze that the detailed lesion location and cause of the stroke of the second medical image are the same as the detailed lesion location and cause of the stroke of the first-1 clustered image (i.e., analyze that the detailed lesion location and cause of the stroke of the first-1 medical image are the same).

[0120] Of course, the analysis unit (256) can directly analyze the detailed lesion location and cause of small subcortical cerebral infarction in the second medical image by comparing the template of the 1-1 clustered image with the stroke area in the second medical image.

[0121] That is, the analysis unit (256) can compare the similarity between each clustered region of the 1-1 clustered image and the stroke region of the 2nd medical image. At this time, since the 1-1 clustered image is an image in which data of common voxels in a plurality of 1-1 medical images are clustered, if the stroke region of the 2nd medical image is similar to each clustered region of the 1-1 clustered image as a result of the comparison (i.e., if the similarity is above a certain level), the analysis unit (256) can analyze that the detailed lesion location and cause of the stroke of the 2nd medical image are the same as the detailed lesion location and cause of the stroke of the 1-1 clustered image (i.e., analyze that they are the same as the detailed lesion location and cause of the stroke of the 1-1 medical image).

[0122] On the other hand, if the stroke area of ​​the second medical image is dissimilar to each clustered area of ​​the first-first clustered image (i.e., the similarity is below a certain level), the analysis unit (256) can analyze that the detailed lesion location and cause of the stroke of the second medical image are different from the detailed lesion location and cause of the stroke of the first-first clustered image (i.e., analyze that the detailed lesion location and cause of the stroke of the first-second medical image are the same).

[0123] For example, the first-1 medical image may be a first medical image of a small subcortical cerebral infarction caused by a first blockage (i.e., blockage of a small blood vessel). In this case, if the difference between the stroke area of ​​the second medical image and each clustered region of the first-1 clustered image is greater than or equal to a certain level (i.e., if the similarity is less than or equal to a certain level), the analysis unit (256) may analyze that the second medical image is a medical image of a patient who suffered a small subcortical cerebral infarction caused by a second blockage that is a different type from the first blockage. On the other hand, if the difference is less than a certain level (i.e., if the similarity is greater than or equal to a certain level), the analysis unit (256) may analyze that the second medical image is a medical image of a patient who suffered a small subcortical cerebral infarction caused by the first blockage.

[0124] Meanwhile, the 1-1 medical image may be a first medical image of a small subcortical cerebral infarction caused by a second blockage (i.e., blockage of a large blood vessel entrance). In this case, if the difference between the stroke area of ​​the 2nd medical image and each clustered area of ​​the 1-1 clustered image is greater than a certain level, the analysis unit (256) may analyze that the 2nd medical image is a medical image of a patient who suffered a small subcortical cerebral infarction caused by a first blockage that is a different type from the 2nd blockage. On the other hand, if the difference is less than a certain level, the analysis unit (256) may analyze that the 2nd medical image is a medical image of a patient who suffered a small subcortical cerebral infarction caused by the 2nd blockage.

[0125] <Example 2>

[0126] In the second embodiment, some details may be changed from the first embodiment described above. Below, only these changed parts will be described.

[0127] First, the S510 performs the same.

[0128] Next, in S520, the boundary setting unit (252) sets a first common region where a small subcortical cerebral infarction has occurred among the plurality of matched 1-1 medical images, and sets a brain lesion boundary (i.e., a first brain lesion boundary) for the first common region. In addition, the boundary setting unit (252) sets a second common region where a small subcortical cerebral infarction has occurred among the plurality of matched 1-2 medical images, and sets a brain lesion boundary (i.e., a second brain lesion boundary) for the second common region.

[0129] That is, the boundary setting unit (252) extracts first common voxels of overlapping lesion locations from at least N images (where N is a natural number greater than or equal to 2 or 3) among a plurality of aligned 1-1 medical images, sets a first common area including these first common voxels, and sets a boundary for the first common area, thereby setting a spatially connected first brain lesion boundary.

[0130] In addition, the boundary setting unit (252) extracts second common voxels of overlapping lesion locations from at least N images (where N is a natural number greater than or equal to 2 or 3) among a plurality of aligned first-second medical images, sets a second common region including these second common voxels, and sets a boundary for the second common region, thereby setting a spatially connected second brain lesion boundary.

[0131] Next, in S530, the dimension reduction unit (253) reduces the dimension of the data of the first common voxel (i.e., data of the first common region) according to the setting of the first brain lesion boundary, and reduces the dimension of the data of the second common voxel (i.e., data of the second common region) according to the setting of the second brain lesion boundary.

[0132] Next, in S540, the clustering unit (254) performs clustering on the data of the first common voxel to divide the first common region according to the first brain lesion boundary into multiple regions. In addition, the clustering unit (254) performs clustering on the data of the second common voxel according to the setting of the second brain lesion boundary to divide the second common region according to the second brain lesion boundary into multiple regions.

[0133] As a result of performing S540, the aforementioned 1-1 clustered image and the 1-2 clustered image can be derived, respectively. At this time, the 1-2 clustered image is an image that displays multiple clustered (i.e., segmented) regions from a standard medical image as data of common voxels in multiple 1-2 medical images are clustered. At this time, each segmented region can be displayed in a different color in the 1-1 and 1-2 clustered images, respectively.

[0134] Next, in S550, the comparison unit (255) tests the suitability of the 1-1 clustered image by comparing the stroke area of ​​the 1-2 medical image with each clustered region of the 1-1 clustered image. At this time, the comparison of the 1-2 medical image with the 1-1 clustered image is as described above in S540.

[0135] In addition, the comparison unit (255) tests the suitability of the 1-2 clustered image by comparing the stroke area of ​​the 1-1 medical image with each clustered area of ​​the 1-2 clustered image.

[0136] That is, the comparison unit (255) can compare the 1-1 medical image to the 1-2 clustered image one by one. At this time, since the 1-2 clustered image is an image in which data of common voxels in multiple 1-2 medical images are clustered, the detailed lesion location and cause of the stroke are different from those of the 1-1 medical image. Accordingly, during the comparison, there is bound to be a significant difference between the stroke site of the 1-1 medical image and each clustered area of ​​the 1-2 clustered image.

[0137] For example, the 1-2 medical image may be the 1-2 medical image for a small subcortical cerebral infarction caused by the 1st blockage (i.e., blockage of a small blood vessel). In this case, the stroke area of ​​the 1-1 medical image caused by the 2nd blockage (i.e., blockage of a large blood vessel entrance) usually occupies a wider area than each clustered area of ​​the 1-2 clustered image. At this time, if the area of ​​the stroke area of ​​the 1-1 medical image that deviates from each clustered area of ​​the 1-2 clustered image (i.e., the difference area between the stroke area of ​​the 1-1 medical image and each clustered area of ​​the 1-2 clustered image) is greater than or equal to a certain level, the comparison unit (255) may determine that the 1-2 clustered image is suitable. On the other hand, if the difference area is less than a certain level, the comparison unit (255) may determine that the 1-2 clustered image is not suitable.

[0138] Meanwhile, the 1-2 medical image may be the 1st medical image for a small subcortical cerebral infarction caused by a 2nd blockage (i.e., blockage of a large blood vessel entrance). In this case, the stroke area of ​​the 1-1 medical image caused by the 1st blockage (i.e., blockage of a small blood vessel) usually occupies a narrower area than each clustered area of ​​the 1-2 clustered image. At this time, if the area among the clustered areas of the 1-2 clustered image that deviates from the stroke area of ​​the 1-1 medical image (i.e., the difference area between the clustered areas of the 1-2 clustered image and the stroke area of ​​the 1-1 medical image) is greater than or equal to a certain level, the comparison unit (255) may determine that the 1-2 clustered image is suitable. On the other hand, if the difference area is less than a certain level, the comparison unit (255) may determine that the 1-2 clustered image is not suitable.

[0139] Next, in S560, the analysis unit (256) provides templates (also referred to as “brain lesion templates”) of the first-1 and first-2 clustered images including each clustered region. At this time, the templates of the first-1 and first-2 clustered images may be templates for the first-1 and first-2 clustered images determined to be suitable in S550.

[0140] That is, the analysis unit (256) can display the second medical image and the templates of the first-1 and first-2 clustered images on the display (230), respectively. At this time, the template of the first-1 clustered image can be displayed so as to overlap the second medical image, and the template of the first-2 clustered image can be displayed so as to overlap the second medical image. That is, each clustered area of ​​the template of the first-1 clustered image and the stroke area of ​​the second medical image can be displayed so as to overlap, and each clustered area of ​​the template of the first-2 clustered image and the stroke area of ​​the second medical image can be displayed so as to overlap. Through this, a user (e.g., a medical professional, etc.) can easily analyze the detailed lesion location and cause of a small subcortical cerebral infarction of the second medical image.

[0141] For example, if the stroke site in the second medical image is more similar to each clustered region in the first-first clustered image, the user can analyze that the detailed lesion location and cause of the stroke in the second medical image are the same as the detailed lesion location and cause of the stroke in the first-first clustered image (i.e., analyzed as the same as the detailed lesion location and cause of the stroke in the first-first medical image). On the other hand, if the stroke site in the second medical image is more similar to each clustered region in the first-second clustered image, the user can analyze that the detailed lesion location and cause of the stroke in the second medical image are the same as the detailed lesion location and cause of the stroke in the first-second clustered image (i.e., analyzed as the same as the detailed lesion location and cause of the stroke in the first-second medical image).

[0142] Of course, the analysis unit (256) can directly analyze the detailed lesion location and cause of small subcortical cerebral infarction in the second medical image by comparing the similarity between the template of the 1-1 clustered image and the stroke area of ​​the second medical image (hereinafter referred to as the “first comparison”) and comparing the similarity between the template of the 1-2 clustered image and the stroke area of ​​the second medical image (hereinafter referred to as the “second comparison”).

[0143] At this time, if the stroke area of ​​the second medical image is more similar to each clustered area of ​​the 1-1 clustered image as a result of the first and second comparison, the analysis unit (256) can analyze that the detailed lesion location and cause of the stroke of the second medical image are the same as the detailed lesion location and cause of the stroke of the 1-1 clustered image (i.e., analyze that they are the same as the detailed lesion location and cause of the stroke of the 1-1 medical image).

[0144] On the other hand, if the stroke area of ​​the second medical image is more similar to each clustered area of ​​the first-second clustered image, the analysis unit (256) can analyze that the detailed lesion location and cause of the stroke of the second medical image are the same as the detailed lesion location and cause of the stroke of the first-second clustered image (i.e., analyze that they are the same as the detailed lesion location and cause of the stroke of the first-second medical image).

[0145] For example, the 1-1 medical image may be a first medical image for a small subcortical cerebral infarction caused by a first blockage (i.e., blockage of a small blood vessel), and the 1-2 medical image may be a first medical image for a small subcortical cerebral infarction caused by a second blockage (i.e., blockage of a large blood vessel entrance). In this case, if the similarity value (hereinafter referred to as “first similarity”) between the stroke area of ​​the 2nd medical image and each clustered region of the 1-1 clustered image is greater than the similarity value (hereinafter referred to as “second similarity”) between the stroke area of ​​the 2nd medical image and each clustered region of the 1-2 clustered image, the analysis unit (256) may analyze that the 2nd medical image is a medical image of a patient who has suffered a small subcortical cerebral infarction caused by the 1st blockage. On the other hand, if the second similarity is greater than the first similarity, the analysis unit (256) can analyze that the second medical image is a medical image of a patient who suffered a small subcortical cerebral infarction due to the second blockage.

[0146] Meanwhile, the 1-1 medical image may be a first medical image for a small subcortical cerebral infarction caused by a second blockage (i.e., blockage of a large blood vessel entrance), and the 1-2 medical image may be a first medical image for a small subcortical cerebral infarction caused by a first blockage (i.e., blockage of a small blood vessel). In this case, if the first similarity is greater than the second similarity, the analysis unit (256) may analyze that the second medical image is a medical image of a patient who suffered a small subcortical cerebral infarction caused by the second blockage. On the other hand, if the second similarity is greater than the first similarity, the analysis unit (256) may analyze that the second medical image is a medical image of a patient who suffered a small subcortical cerebral infarction caused by the first blockage.

[0147] The present invention, configured as described above, has the advantage of being able to analyze detailed lesion locations for stroke, and particularly, for small subcortical cerebral infarctions such as lacunar infarctions. In addition, the present invention has the advantage of being able to provide a visual guideline for diagnosing small subcortical cerebral infarctions to clinicians by providing a brain lesion template related to small subcortical cerebral infarctions. In addition, the present invention has the advantage of being able to improve the accuracy of analysis for small subcortical cerebral infarctions by segmenting each region of the stroke site by reflecting the pathological cause of small subcortical cerebral infarctions caused by blockage of blood vessels in the subcortical region of the brain.

[0148] While the detailed description of the present invention has described specific embodiments, it should be understood that various modifications are possible without departing from the scope of the present invention. Therefore, the scope of the present invention is not limited to the described embodiments, but should be determined by the claims and their equivalents.

[0149]

[0150] This invention was researched with the support of a national research and development project, and the specific details of the national research and development project are as follows.

[0151] [Project ID] 1345364864

[0152] [Assignment Number] 2021R1A6A1A03038865

[0153] [Ministry Name] Ministry of Education

[0154] [Name of Project Management (Specialist) Institution] National Research Foundation of Korea

[0155] [Research Project Name] Establishment of a Research Base for Science and Engineering

[0156] [Research Project Name] Medical Science Research Institute

[0157] [Project Implementing Organization Name] Dongguk University Industry-Academic Cooperation Foundation

[0158] Research Period: June 1, 2021 - May 31, 2030

[0159]

[0160] [Project ID] 2410000881

[0161] [Project Number] RS-2024-00431821

[0162] Ministry of Trade, Industry and Energy

[0163] [Name of Project Management (Specialist) Institution] Korea Institute of Industrial Technology Planning and Evaluation

[0164] [Research Project Name] National Standard Technology Development and Distribution (R&D)

[0165] [Research Project Name] Development and Distribution of National Reference Standard Data

[0166] [Project Implementing Organization Name] Dongguk University Ilsan Hospital

[0167] Research Period: April 1, 2024 - December 31, 2026

[0168]

[0169] [Project ID] 1711195356

[0170] [Assignment Number] 2022M3H9A2096198

[0171] [Ministry Name] Ministry of Education

[0172] [Name of Project Management (Specialist) Institution] National Research Foundation of Korea

[0173] [Research Project Name] Establishment of a Bio Research Data Utilization Base

[0174] [Research Project Name] Biodata Quality Leadership Center (Bioimaging)

[0175] [Project Implementing Organization Name] Dongguk University Industry-Academic Cooperation Foundation

[0176] Research Period: July 1, 2022 - December 31, 2026

[0177] The present invention relates to a method and device for analyzing the location of a brain disease lesion, and can provide a technology for analyzing the detailed location of a stroke lesion, and thus has industrial applicability.

Claims

1. A method performed in an electronic device, A step of aligning a plurality of first medical images so that the brain shape of the plurality of first medical images taken of brain regions of patients with vascular occlusion stroke is aligned; A step of setting a common region including common voxels that are voxels of overlapping lesion locations in at least N images (wherein N is a natural number greater than or equal to 2) among the plurality of first medical images; and A step of performing clustering on data of the common area to divide the common area into multiple areas, thereby deriving a clustered image, which is an image in which each divided area is displayed; How to include.

2. In paragraph 1, Between the above setting step and the above deriving step, a step of reducing the dimension of the data of the common area is further included, A method wherein the deriving step includes a step of performing the clustering on data in a common area with reduced data dimension.

3. In paragraph 1, A method further comprising the step of displaying a template for the above clustered image and a second medical image capturing a brain region of a patient with vascular occlusion stroke who is the subject of treatment.

4. In paragraph 3, A method in which the step of displaying includes a step of displaying each clustered region of the template and the stroke region of the second medical image so as to overlap.

5. In paragraph 1, The above first medical image is a method of medical imaging of patients who have suffered a vascular occlusive stroke due to either a first blockage corresponding to a small vessel blockage or a second blockage corresponding to a large vessel entrance blockage.

6. In paragraph 5, A method further comprising a step of determining that the patient of the second medical image has suffered a vascular occlusive stroke due to a first blockage or a second blockage based on the similarity between each clustered region of the clustered image and the stroke site of the second medical image.

7. In paragraph 6, A method in which the step of determining comprises a step of determining that the patient of the second medical image has suffered a vascular occlusive stroke due to a first blockage when the similarity is greater than a certain level, and a step of determining that the patient of the second medical image has suffered a vascular occlusive stroke due to a second blockage when the similarity is less than a certain level.

8. In paragraph 1, A method comprising: a first medical image, wherein the first medical image comprises a first medical image for patients who have suffered a vascular occlusive stroke due to either a first blockage corresponding to a small vessel blockage or a second blockage corresponding to a large vessel entrance blockage; and a first medical image for patients who have suffered a vascular occlusive stroke due to either the other of the first and second blockages.

9. In paragraph 8, The plurality of first medical images used in the above setting step are the first-1 medical images, A method further comprising, after the deriving step, a step of comparing the clustered image with the first and second medical images to determine whether the clustered image is suitable.

10. In paragraph 9, A method in which the above-mentioned judging step includes a step of judging whether the clustered image is suitable based on whether the difference between the stroke area of ​​the first-second medical image and each clustered area of ​​the clustered image is greater than a certain level.

11. In paragraph 8, The above setting step includes a step of setting a first common area, which is the common area for a plurality of first-1 medical images, and a step of setting a second common area, which is the common area for a plurality of first-2 medical images. A method wherein the deriving step includes deriving a first clustering image, which is the clustering image for data of the first common area, and deriving a second clustering image, which is the clustering image for data of the second common area.

12. A memory storing a number of first medical images of brain regions of patients with vascular occlusion stroke; and A control unit for controlling the derivation of a clustered image to assist in the analysis of a second medical image taken of a brain region of a patient with vascular occlusion stroke who is the subject of treatment, using the plurality of first medical images; The above control unit, A device that controls a plurality of first medical images to be processed for matching so that the brain shapes of each first medical image are matched, controls to set a common region including common voxels that are voxels of overlapping lesion locations in at least N images (wherein N is a natural number greater than or equal to 2) of the plurality of first medical images, and controls to perform clustering on data of the common region to divide the common region into a plurality of regions, thereby deriving the clustered image in which each divided region is displayed.

13. In paragraph 12, The above control unit is a device that controls to reduce the dimension of data in the common area, and performs the clustering on data in the common area whose data dimension has been reduced.

14. In paragraph 13, The above control unit is a device that controls the display to display a template for a clustered image and a second medical image taken of a brain region of a patient with vascular occlusion stroke who is the subject of treatment.

15. In paragraph 13, The above first medical image is a medical image of patients who suffered a vascular occlusive stroke due to either the first blockage corresponding to small vessel blockage or the second blockage corresponding to large vessel entrance blockage. The above control unit is a device that controls to determine that the patient of the second medical image has suffered a vascular occlusion stroke due to a first blockage or a second blockage based on the similarity between each clustered area of ​​the clustered image and the stroke area of ​​the second medical image.

16. In paragraph 15, The control unit determines that the patient of the second medical image has suffered a vascular occlusive stroke due to a first blockage when the similarity is greater than a certain level, and determines that the patient of the second medical image has suffered a vascular occlusive stroke due to a second blockage when the similarity is less than a certain level.

17. In paragraph 12, The first medical image includes a first-1 medical image for patients who suffered a vascular occlusive stroke due to either a first blockage corresponding to a small vessel blockage or a second blockage corresponding to a large vessel entrance blockage, and a first-2 medical image for patients who suffered a vascular occlusive stroke due to either the other of the first and second blockages, respectively. The above control unit is a device that controls the settings for the common area using a plurality of 1-1 medical images, and compares the clustered image with the 1-2 medical image to determine whether the clustered image is suitable.

18. In paragraph 17, The above control unit is a device that controls to determine whether the clustered image is suitable based on whether the difference between the stroke area of ​​the first-second medical image and each clustered area of ​​the clustered image is greater than a certain level.

19. In paragraph 17, The above control unit controls to set a first common area, which is the common area for a plurality of 1-1 medical images, and a second common area, which is the common area for a plurality of 1-2 medical images, and controls to derive a first clustered image, which is the clustered image for data of the first common area, and to derive a second clustered image, which is the clustered image for data of the second common area, and controls to display the first and second clustered images and the second medical image, which is an image of a brain region of a patient with vascular occlusion stroke who is a target of treatment, on a display, respectively.

20. A device for assisting the analysis of a second medical image of a brain region of a patient with vascular occlusion stroke who is the subject of treatment, using a clustered image derived from a plurality of first medical images of brain regions of patients with vascular occlusion stroke, A memory storing the clustered image and the second medical image; and A control unit for controlling the display of the template for the clustered image and the second medical image, respectively; The above clustered image is, A device for producing an image, comprising: a process of aligning a plurality of first medical images so that the brain shapes of each first medical image are aligned; a process of setting a common region including common voxels, which are voxels of overlapping lesion locations in at least N images (wherein N is a natural number greater than or equal to 2) of the plurality of first medical images; and a process of performing clustering on data of the common region to divide the common region into a plurality of regions, thereby deriving the clustered image in which each of the divided regions is displayed.

Images