Medical image processing apparatus, and medical image processing method

Abstract

To present more appropriate information for diagnosis and treatment of thrombus.SOLUTION: An medical image processing apparatus of an embodiment includes an acquiring part, an estimation part, a determination part, and a display part. The acquiring part acquires a medical image on which at least a blood vessel of a patient is imaged and patient information related to the patient. The estimation part estimates a state of the thrombus imaged in the medical image based on the medical image and the patient information. The determination part determines a thrombus removal method for removing the thrombus based on the medical image, the patient information, and the estimation result, and outputs the determination result of the thrombus removal method. The display part generates a display image for presenting one or more of the medical image, the estimation result, and the determination result, and causes the display device to display the generated image.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The embodiments disclosed in this specification and the drawings relate to a medical image processing apparatus and a medical image processing method. [Background technology]

[0002] For example, in surgery for cerebral infarction, such as ischemic stroke caused by occlusion of a major cerebral artery, the cause of the stroke is removed by removing a blood clot that has formed inside the patient's blood vessels. In this case, the surgeon, such as a doctor, determines the location of the blood clot by referring to signs of the blood clot that appear in medical images, such as CT images taken by a computed tomography (CT) device or MR images taken by a magnetic resonance imaging (MRI) device. However, the patient's blood vessels and blood clots may not be clearly visible in the CT or MR images, making it difficult to determine the location of the blood clot.

[0003] In this regard, there has been a proposal for an information processing device that estimates an infarcted region and a location of occlusion in a major artery from a CT image, identifies a region governed by the occluded blood vessel based on the location of the occlusion in the major artery, and derives and presents the amount of overlap (volume) between the governed region and the infarcted region as a quantitative value. In the conventional technology, the CT image is divided into predetermined regions, such as regions governed by the left and right anterior cerebral arteries, regions governed by the middle cerebral artery, and regions governed by the posterior cerebral artery, and the CT image and the quantitative value are displayed by superimposing the derived quantitative value on each region.

[0004] Furthermore, recent advances in thrombus retrieval technology using thrombus removal devices, such as stent retrievers and aspiration catheters, have enabled detailed analysis of the morphological and histological composition of thrombi collected (removed) from patients. Consequently, it has become clear that thrombi are highly heterogeneous, consisting of components such as fibrin, platelets, red blood cells, white blood cells, von Willebrand factor (vWF), and neutrophil extracellular traps (NETs). Cerebral infarction can be broadly classified as cardiogenic cerebral embolism, atherothrombotic brain infarction (ATBI), lacunar infarction, stroke of other confirmed etiology, or stroke of undetermined etiology. It has become possible to estimate the composition of a thrombus captured in a medical image by identifying the composition of the thrombus collected from the patient and learning the relationship between the feature amount in the thrombus area captured in the medical image and the identified composition using machine learning, etc. If the composition of the thrombus can be estimated, it is thought that the hardness of the thrombus can be determined and an appropriate surgical procedure for removing the thrombus can be determined.

[0005] However, while it is possible to estimate the composition of a thrombus in a medical image, it is not yet possible to estimate the local composition of the thrombus. This makes it difficult to determine the surgical procedure for removing the thrombus, including the resistance of the thrombus to a thrombus removal device used to remove the thrombus and a thrombolytic agent used to dissolve the thrombus. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 2023-130231 Summary of the Invention [Problem to be solved by the invention]

[0007] The problem to be solved by the embodiments disclosed in this specification and the drawings is to present information more suitable for diagnosing and treating thrombus. However, the problem to be solved by the embodiments disclosed in this specification and the drawings is not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described below can also be positioned as other problems. [Means for solving the problem]

[0008] A medical image processing apparatus according to an embodiment includes an acquisition unit, an estimation unit, a determination unit, and a display unit. The acquisition unit acquires medical images showing at least a patient's blood vessels and patient information related to the patient. The estimation unit estimates the state of a thrombus shown in the medical image based on the medical image and the patient information, and outputs an estimation result related to the estimated thrombus. The determination unit determines a thrombus removal method for removing the thrombus based on the medical image, the patient information, and the estimation result, and outputs a determination result of the thrombus removal method. The display unit generates a display image for presenting one or more of the medical image, the estimation result, and the determination result, and displays the image on a display device. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram showing an example of the functional configuration of a medical image processing apparatus according to an embodiment. [Figure 2] 5A and 5B are diagrams showing examples of a thrombus removal method and a division method determined in advance in the medical image processing apparatus according to the embodiment. [Figure 3] 10A and 10B are diagrams showing an example (part 1) of image processing in which a region segmentation image processing function included in the medical image processing apparatus according to the embodiment segments a thrombus region image. [Figure 4] FIG. 10 is a diagram showing an example (part 2) of image processing in which a region segmentation image processing function included in the medical image processing apparatus according to the embodiment segments a thrombus region image. [Figure 5]FIG. 10 is a diagram showing an example (part 3) of image processing in which a region segmentation image processing function included in the medical image processing apparatus according to the embodiment segments a thrombus region image. [Figure 6] FIG. 10 is a diagram showing an example (part 4) of image processing in which a region segmentation image processing function included in the medical image processing apparatus according to the embodiment segments a thrombus region image. [Figure 7] FIG. 10 is a diagram showing an example (part 5) of image processing in which a region segmentation image processing function included in the medical image processing apparatus according to the embodiment segments a thrombus region image. [Figure 8] 10A and 10B are diagrams showing an example of differences in regions for which feature values are calculated by a region segmentation image processing function included in the medical image processing apparatus according to the embodiment. [Figure 9] 10A and 10B are diagrams showing an example of processing when calculating feature values of divided regions by the region division image processing function included in the medical image processing apparatus according to the embodiment; [Figure 10] FIG. 2 is a diagram showing an example (part 1) of a display image generated by a region display function included in the medical image processing apparatus according to the embodiment. [Figure 11] FIG. 10 is a diagram showing an example (part 2) of a display image generated by the region display function included in the medical image processing apparatus according to the embodiment. [Figure 12] FIG. 10 is a diagram showing an example (part 3) of a display image generated by the region display function included in the medical image processing apparatus according to the embodiment. [Figure 13] 10 is a flowchart showing an example of a processing flow in a medical image processing apparatus according to an embodiment. [Figure 14] FIG. 4 is a view showing an example of a display screen when the medical image processing apparatus according to the embodiment provides information. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, a medical image processing apparatus and a medical image processing method according to an embodiment will be described with reference to the drawings.

[0011] 1 is a diagram showing an example of the functional configuration of a medical image processing apparatus according to an embodiment. The medical image processing apparatus 100 displays information about thrombi on a display device (not shown) such as an LCD (Liquid Crystal Display) for presenting information, thereby presenting the information to a user of the medical image processing apparatus 100, such as a doctor who diagnoses cerebral infarction (thrombus) or an operator who performs surgery to remove the thrombus.

[0012] The medical image processing apparatus 100 is realized by a computer device such as a personal computer (PC) installed in, for example, a consultation room or operating room of a hospital. When the medical image processing apparatus 100 is realized by a personal computer, a display device (not shown) for presenting information to a user is connected to the medical image processing apparatus 100. An input interface (not shown) for a user to operate the medical image processing apparatus 100 or input information may be connected to the medical image processing apparatus 100. The display device and input interface may be connected to the medical image processing apparatus 100 by wireless communication. The medical image processing apparatus 100 may be realized by a server device on a network (not shown). In this case, it is sufficient that at least a display device (which may include an input interface) is installed in the consultation room or operating room, and the server device, which is the main device of the medical image processing apparatus 100, communicates with the display device (which may include an input interface) via a network (not shown). Furthermore, the medical image processing device 100 may have only some of the functions described below realized by a server device, in which case the server device, which is the main device of the medical image processing device 100, and the server device on which some of the functions are realized communicate with each other via a network not shown.

[0013] Networks not shown include, for example, the Internet, a wide area network (WAN), a local area network (LAN), a provider device, a wireless base station, etc. The input interface is realized by, for example, a mouse, a keyboard, a touch panel, a microphone, etc. If the input interface is a touch panel, the input interface may be formed integrally with a display device connected to the medical image processing apparatus 100. In this specification, the input interface is not limited to an interface having physical operation components such as the mouse and keyboard described above. For example, an example of an input interface also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the medical image processing apparatus 100 and outputs this electrical signal to the medical image processing apparatus 100.

[0014] [Functional configuration of medical image processing equipment] The medical image processing device 100 includes, for example, a processing circuitry 110. The processing circuitry 110 executes processes such as an acquisition function 120, an estimation function 130, a determination function 140, a segmentation function 150, and a display function 160. The acquisition function 120 executes processes such as a medical image acquisition function 122 and a patient information acquisition function 124. The estimation function 130 executes processes such as a thrombus region estimation function 132, a thrombus disease type estimation function 134, and a thrombus composition estimation function 136. The determination function 140 executes processes such as a region segmentation determination function 142. The segmentation function 150 executes processes such as a region segmentation image processing function 152. The display function 160 executes processes such as a region display function 162.

[0015] The processing circuit 110, for example, realizes the respective functions of an acquisition function 120 (including a medical image acquisition function 122 and a patient information acquisition function 124), an estimation function 130 (including a thrombus region estimation function 132, a thrombus disease type estimation function 134, and a thrombus composition estimation function 136), a judgment function 140 (including a region division judgment function 142), a division function 150 (including a region division image processing function 152), and a display function 160 (including a region display function 162) by having a hardware processor execute a program (software) stored in a memory (storage unit) not shown. The memory not shown is realized by, for example, a semiconductor memory element such as a ROM (Read Only Memory), a RAM (Random Access Memory), a flash memory, a hard disk drive (HDD), an optical disk, etc.

[0016] The term "hardware processor" refers to a circuit such as a central processing unit (CPU), a graphics processing unit (GPU), a large-scale integration (LSI), a system on chip (SOC), an application-specific integrated circuit (ASIC), or a programmable logic device (e.g., a simple programmable logic device (SPLD) or a complex programmable logic device (CPLD), or a field programmable gate array (FPGA)). Instead of storing a program in a memory (not shown), the program may be directly embedded in the hardware processor. In this case, the hardware processor realizes each function by reading and executing the program embedded in the circuit. The hardware processor is not limited to a single circuit, but may be configured as a single hardware processor by combining multiple independent circuits to realize each function. Multiple components may be integrated into a single hardware processor to realize each function. Multiple components may be integrated into a single dedicated LSI to realize each function. Here, the program (software) may be stored in advance in a storage device (storage device having a non-transitory storage medium) constituting a storage device such as a ROM, RAM, a semiconductor memory element such as a flash memory, or a hard disk drive (HDD), or may be stored in a removable storage medium (non-transitory storage medium) such as a DVD or CD-ROM, and installed in the storage device provided in the medical image processing apparatus 100 by loading the storage medium into a drive device provided in the medical image processing apparatus 100. The program (software) may be downloaded in advance from another computer device via a network (not shown) and installed in the storage device provided in the medical image processing apparatus 100.The program (software) installed in the storage device included in the medical image processing apparatus 100 may be transferred to a processing circuit included in the medical image processing apparatus 100 and executed therein.

[0017] The acquisition function 120 acquires medical images and patient information. The acquisition function 120 acquires medical images of the patient taken during the current diagnosis or surgery. The acquisition function 120 may acquire, for example, medical images of the patient recorded in a recording device such as a medical image management system (Picture Archiving and Communication Systems (PACS)) that manages medical image data, via a network (not shown). The acquisition function 120 acquires patient information (clinical information other than medical images) regarding the patient undergoing the current diagnosis or surgery. The acquisition function 120 may acquire patient information from, for example, a recording device that records data such as test results from previous examinations of the patient and medical records (electronic medical records) from when the patient was treated. The acquisition function 120 outputs the acquired medical images and patient information to the estimation function 130 and the display function 160, respectively.

[0018] The medical image acquisition function 122 acquires medical images. Medical images are primarily images of blood vessels in a patient's brain taken when diagnosing a stroke. Medical images include, for example, non-contrast-enhanced CT (NCCT) images (hereinafter simply referred to as "CT images") taken by a computed tomography (CT) device, CT angiography (CTA) images, and 4D-CT perfusion (CTP) images. Medical images also include, for example, MR images taken by a magnetic resonance imaging (MRI) device, MR angiography (MRA) images, and MR perfusion (MRP) images. Medical images include, for example, angiography images, ultrasound images captured by an ultrasound diagnostic device, and single-photon emission computed tomography (SPECT) images captured by a SPECT device. These medical images are merely examples, and the medical images acquired by the medical image acquisition function 122 may include other medical images as long as they depict the blood vessels (blood flow) in the patient's brain, which are necessary for diagnosing stroke. For example, the medical images may include DECT images captured by a DECT (Dual Energy CT) device and PCCT images captured by a PCCT (Photon-Counting CT) device. The medical image acquisition function 122 outputs the acquired medical images to each of the estimation function 130 and the display function 160. The medical image acquisition function 122 may be configured to store the acquired medical images in a storage unit (not shown) and output a notification indicating this to each of the estimation function 130 and the display function 160. In this case, for example, the estimation function 130 reads out medical images stored in a memory unit not shown, which is equivalent to a configuration in which the medical image acquisition function 122 outputs the acquired medical images to the estimation function 130.

[0019] The patient information acquisition function 124 acquires patient information. The patient information includes, for example, information typically collected when diagnosing a stroke, such as the patient's age, gender, NIHSS (National Institutes of Health Stroke Scale) score, blood pressure, medical history (diabetes, hypertension, dyslipidemia, smoking, stroke, myocardial infarction, atrial fibrillation, anticoagulation, etc.), time since onset, blood test results (brain natriuretic peptide (BNP), etc.), and genotype from a genetic test. These pieces of patient information are merely examples, and the patient information acquired by the patient information acquisition function 124 may also include other information about the patient. The patient information acquisition function 124 outputs the acquired patient information to each of the estimation function 130 and the display function 160. The patient information acquisition function 124 may be configured to store the acquired patient information in a storage unit (not shown) and output a notification indicating this to each of the estimation function 130 and the display function 160. In this case, for example, the estimation function 130 reads out the patient information stored in a storage unit (not shown), which is equivalent to a configuration in which the patient information acquisition function 124 outputs the acquired patient information to the estimation function 130.

[0020] The acquisition function 120 (including the medical image acquisition function 122 and the patient information acquisition function 124) is an example of an "acquisition unit."

[0021] The estimation function 130 estimates the state of a thrombus shown in a medical image based on the medical image and patient information output by the acquisition function 120, i.e., based on the medical image output by the medical image acquisition function 122 and the patient information output by the patient information acquisition function 124. The estimation function 130 estimates the area of the thrombus (hereinafter referred to as the "thrombus area"), the disease type (hereinafter referred to as the "thrombus disease type"), and the composition (hereinafter referred to as the "thrombus composition") from the image features (radiological features) of the thrombus shown in the medical image. Examples of image features include morphological features such as the size and shape of the thrombus, features based on the frequency distribution of pixel values in the thrombus area (histogram: minimum value, average value, percentile value, etc.), and features based on the spatial distribution of pixel values in the thrombus area (texture: gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLLM), etc.). The estimation function 130 outputs the estimated result regarding the estimated thrombus.

[0022] The thrombus region estimation function 132 estimates a thrombus region that is thought to be a thrombus in a medical image. The thrombus region estimation function 132 estimates a thrombus region using, for example, a machine learning function in AI (artificial intelligence) to use a machine learning model generated by a computing device (not shown) or the like. The machine learning model is a trained model that, when a medical image is input, uses, for example, a machine learning technique such as CNN (convolutional neural network) to output an image in which a hyperdense artery sign (HAS) region that indicates a thrombus symptom that can be confirmed on the medical image is identified (annotated) as a thrombus region. For example, the thrombus region estimation function 132 inputs an NCCT image (CT image) of a patient's brain before thrombus removal into the machine learning model to obtain an image in which the HAS region on the NCCT image is segmented (segmented) as a thrombus region. This image is associated with information indicating the position of the thrombus region on the NCCT image. The medical image from which the thrombus region estimation function 132 estimates a thrombus region is not limited to an NCCT image, and may be any medical image, including the various medical images described above, as long as it shows a thrombus sign that can be assumed to be a thrombus region. The thrombus region estimation function 132 outputs an image obtained by the machine learning model (an image of the segmented thrombus region) as an estimation result of the thrombus region to each of the determination function 140, the division function 150, and the display function 160. In the following description, the image of the estimation result of the thrombus region output by the thrombus region estimation function 132 is referred to as a "thrombus region image."

[0023] The thrombosis type estimation function 134 estimates the thrombosis type of a thrombus believed to be captured in a medical image based on the medical image and patient information. The thrombosis type estimation function 134 may use a thrombus region image in which a thrombus region is estimated by the thrombus region estimation function 132 when estimating the thrombosis type. The thrombosis type indicates the cause of a disease, such as cardiogenic cerebral embolism, atherothrombotic brain infarction (ATBI), lacunar infarction, or embolic stroke of undetermined source (ESUS). The thrombosis type estimation function 134 estimates the thrombosis type using, for example, a machine learning function in AI, using a machine learning model generated by a computing device (not shown) or the like. The machine learning model is a trained model that has been trained in advance using machine learning techniques such as a support vector machine (SVM) to output the thrombus type identified in a cerebral infarction patient after thrombus removal when image features of a medical image of the patient taken before thrombus removal and patient information are input. The thrombus type estimation function 134 obtains information on the thrombus type estimated before thrombus removal, for example, by inputting image features of the patient's medical image and patient information into the machine learning model. The thrombus type information is information indicating the probability of each thrombus type, such as "atheromatous = 0.8%" and "cardiogenic = 0.2%." The thrombus type information may be, for example, binary information indicating whether the thrombus type is atheromatous or cardiogenic, determined by determining the probability of each thrombus type using a predetermined threshold. These pieces of thrombus type information are merely examples, and the thrombus type information obtained by the thrombus type estimation function 134 when estimating the thrombus type may be any information on the thrombus type. The thrombosis type estimation function 134 outputs information on the thrombosis type obtained by the machine learning model as an estimation result of the thrombosis type to each of the judgment function 140, the division function 150, and the display function 160. In the following description, the information on the estimation result of the thrombosis type output by the thrombosis type estimation function 134 is referred to as "thrombosis type information."

[0024] The thrombus composition estimation function 136 estimates the thrombus composition of a thrombus that is thought to be captured in a medical image based on the medical image and patient information. For example, if a patient has multiple thrombi, such as when the patient has tandem occlusion in their cerebral infarction, the thrombus composition estimation function 136 may estimate the thrombus composition of each thrombus that has occurred in the patient. The thrombus composition represents, for example, the composition of fibrin, platelets, red blood cells, white blood cells, etc. The thrombus composition estimation function 136 estimates, for example, the number of red blood cells (RBC) as the thrombus composition. The thrombus composition estimation function 136 estimates the thrombus composition using, for example, a machine learning function in AI, using a machine learning model generated by a computing device (not shown) or the like. The machine learning model is a trained model that has been trained in advance using machine learning techniques such as CNN and support vector machines to output analysis results of a histopathological diagnosis of a cerebral infarction patient after thrombus removal when image features of medical images taken of the patient before thrombus removal and patient information are input. In the histopathological diagnosis, for example, sections of the thrombus removed and recovered from the cerebral infarction patient are stained (e.g., H&S staining) and analyzed using an optical microscope to analyze the proportions of each component that makes up the thrombus. The analysis results are expressed, for example, as "RBC = aa%, fibrin / platelets = bb%, white blood cells = cc%," with the total being 100%. The thrombus composition estimation function 136 obtains information estimating the thrombus composition before thrombus removal, for example, by inputting image features of the patient's medical images and patient information into the machine learning model. The thrombus composition estimation function 136 obtains information indicating the proportion of each component constituting the thrombus, such as "RBC = 0.8%, fibrin / platelets = 0.2%," as information on the thrombus composition. The ratio of RBC to fibrin / platelets in this thrombus can be used to determine, for example, the hardness of the thrombus. More specifically, the lower the RBC ratio (higher fibrin / platelets), the harder the thrombus will be, and the higher the RBC ratio (lower fibrin / platelets), the softer the thrombus will be.Such information on thrombus composition is merely an example, and the information on thrombus composition obtained by estimating thrombus composition by thrombus composition estimation function 136 may be any information as long as it is information on thrombus composition. The thrombus composition estimation function 136 outputs the information on thrombus composition obtained by the machine learning model as an estimation result of thrombus composition to each of the determination function 140, the division function 150, and the display function 160. In the following description, the information on the estimation result of thrombus composition output by thrombus composition estimation function 136 will be referred to as "thrombus composition information."

[0025] The estimation function 130 is an example of an "estimation unit." The thrombus region estimation function 132 is an example of a "thrombus region estimation unit." The thrombus disease type estimation function 134 is an example of a "thrombus disease type estimation unit." The thrombus composition estimation function 136 is an example of a "thrombus composition estimation unit."

[0026] The determination function 140 determines a method for removing the thrombus shown in the medical image (hereinafter referred to as a "thrombus removal method") based on the images and information of the respective estimation results output by the estimation function 130. More specifically, the determination function 140 determines the thrombus removal method based on the thrombus region image output by the thrombus region estimation function 132, the thrombus disease type information output by the thrombus disease type estimation function 134, and the thrombus composition information output by the thrombus composition estimation function 136.

[0027] The region division determination function 142 determines a division method for the thrombus region shown in the medical image, i.e., the thrombus region represented by the thrombus region image, based on a combination of the thrombus region image, thrombus disease type information, and thrombus composition information, and the determination result of the thrombus removal method by the determination function 140. More specifically, the region division determination function 142 determines which of the division methods described below the division function 150 will use to divide the thrombus region.

[0028] The thrombus removal method determined by the judgment function 140 and the division method determined by the region division judgment function 142 may be set, for example, by a user performing input operations on an input interface (not shown), or may be determined in advance for each combination of the estimated results of the thrombus region image, thrombus disease type information, and thrombus composition information.

[0029] [Example of a method for removing and dividing a thrombus] FIG. 2 illustrates an example of a thrombus removal method and a thrombus division method predefined in the medical image processing apparatus 100 according to the embodiment. FIG. 2 illustrates an example in which, for cases where the thrombus disease type indicated by the thrombus disease type information is "atheromatous" or "cardiogenic," the thrombus hardness is classified into three categories—"hard," "soft," and "medium"—according to the proportion of fibrin in the thrombus composition indicated by the thrombus composition information, and the thrombus size is classified into two categories—"large" and "small"—according to the volume and diameter of the thrombus region indicated by the thrombus region image. The number of categories for the thrombus hardness and thrombus size shown in FIG. 2 is merely an example, and more categories may be used. In other words, the thrombus hardness and thrombus size may be further classified. The thrombus hardness can be classified based on, for example, a threshold value set for the proportion of fibrin indicated by the thrombus composition information. The thrombus size can be classified based on, for example, a threshold value set for the size of the thrombus region indicated by the thrombus region image.

[0030] In the example shown in Figure 2, when the thrombus is "hard" and "large" regardless of the thrombus type, a procedure using an aspiration catheter as a thrombus removal device is selected as the thrombus removal method, and a division method corresponding to the aspiration catheter is selected. This is because, in the case of a hard thrombus, using a stent retriever as a thrombus removal device is generally considered more preferable because the stent retriever inserted into the thrombus may not sufficiently expand, making it unlikely that part of the thrombus will be removed. In the example shown in Figure 2, when the thrombus is "soft" and "large" regardless of the thrombus type, and when the thrombus is "atheromatous," the thrombus is "medium" in hardness, and the thrombus is "large," a procedure using a stent retriever as a thrombus removal device is selected as the thrombus removal method, and a division method corresponding to the stent retriever is selected. This is because, in the case of a soft thrombus of a certain size or larger, a stent retriever inserted into the thrombus is expected to expand sufficiently and remove the thrombus. In the example shown in Figure 2, regardless of the thrombus type and thrombus hardness, if the thrombus size is "small," the thrombus removal method is "medication" and the segmentation method is "no segmentation" of the thrombus region. This is because it is expected that small thrombus can be dissolved (removed) by administering a thrombolytic agent to dissolve the thrombus, such as intravenous alteplase (tPA) therapy. In this case, the user may confirm the overall condition of the thrombus from the thrombus region image, thrombus type information, and thrombus composition information, and then determine the thrombus removal procedure. In the example shown in Figure 2, if the thrombus type is "cardiogenic," the thrombus hardness is "medium," and the thrombus size is "large," the thrombus removal method is "composition analysis" and the segmentation method is "no segmentation." In other words, in this case, composition analysis is recommended as a method for removing the thrombus. This is because a thrombus in this state may have extremely hard or soft areas in certain regions, and it is thought that it is better to first calculate the composition distribution to determine the distribution of the thrombus composition before deciding on a surgical procedure.

[0031] In this way, the determination function 140 determines the thrombus removal method based on a combination of the thrombus region image, thrombus disease type information, and thrombus composition information, and the region division determination function 142 further adds the thrombus removal method to determine the division method by which the division function 150 divides the thrombus region. The determination function 140 outputs information representing the determined thrombus removal method (hereinafter simply referred to as the "thrombus removal method") to the division function 150 and the display function 160. The thrombus removal method includes information on the "thrombus disease type," "thrombus composition," and "thrombus region" shown in FIG. 2. In addition to the information shown in FIG. 2, this information includes values represented by the corresponding information output by the estimation function 130 (such as the probability of the thrombus disease type and the proportion of each component constituting the thrombus). The region division determination function 142 outputs information representing the determined division method (hereinafter simply referred to as the "division method") to the division function 150 and the display function 160.

[0032] In the above example, the determination function 140 determines (selects) one thrombus removal method, and the region division determination function 142 determines (selects) one division method for dividing the thrombus region by the division function 150. However, the thrombus removal method selected by the determination function 140 and the division method selected by the region division determination function 142 are not limited to one. For example, the determination function 140 may select multiple thrombus removal methods and present them to the user, allowing the user to compare the presented thrombus removal methods. For example, the region division determination function 142 may select multiple division methods and present them to the user, allowing the user to compare the presented division methods. For example, the determination function 140 and the region division determination function 142 may select the thrombus removal method and the division method input by the user through an input operation on an input interface (not shown), that is, the user may manually select the method.

[0033] The determination function 140 is an example of a "determination unit." The area division determination function 142 is an example of an "area division determination unit."

[0034] The division function 150 divides the thrombus region image (image of the segmented thrombus region) output by the estimation function 130 (more specifically, the thrombus region estimation function 132) according to the thrombus removal method output by the judgment function 140 and the division method output by the region division judgment function 142.

[0035] The region segmentation image processing function 152 performs image processing to segment the thrombus region image in accordance with the thrombus removal method or the segmentation method. The region segmentation image processing function 152 may be configured to select the results of segmenting the thrombus region image in accordance with the thrombus removal method or the segmentation method after segmentation using all the segmentation methods. In this case, the region segmentation image processing function 152 can perform image processing to segment the thrombus region image in parallel with the process of the region segmentation determination function 142 determining the segmentation method.

[0036] [An example of segmenting an image of a thrombus region] The following describes an example of image processing in which the region segmentation image processing function 152 segments a thrombus region image. Figures 3 to 7 are diagrams showing an example of image processing in which the region segmentation image processing function 152 included in the medical image processing apparatus 100 according to the embodiment segments a thrombus region image.

[0037] 3 and 4 schematically show an example of image processing when a segmentation method indicating "no segmentation" is output from the region segmentation determination function 142. FIGS. 3 and 4 show an example of an image (thrombus region image) of only a thrombus captured in a medical image estimated by the thrombus region estimation function 132. When a segmentation method indicating "no segmentation" is output from the region segmentation determination function 142, the region segmentation image processing function 152 performs image processing to represent the distribution (composition distribution) of the thrombus composition estimated by the thrombus composition estimation function 136 over the entire thrombus (entire thrombus region). At this time, the region segmentation image processing function 152 associates, as feature values, information representing the thrombus composition with each pixel constituting the thrombus region, for each pixel, or for each voxel of a predetermined size or a size specified by the user (e.g., a cubic voxel of 3 pixels x 3 pixels x 3 pixels).

[0038] FIG. 3(a) schematically illustrates an example in which information representing the thrombus composition is associated with each pixel. More specifically, FIG. 3(a-2) illustrates an example in which the distribution of feature values for the entire thrombus shown in FIG. 3(a-1) is represented by the brightness (or color) of each pixel. The feature value is, for example, a value representing the hardness of the thrombus based on the ratio of RBC and fibrin / platelets represented by the thrombus composition. In this case, the user can confirm the distribution of feature values for the entire thrombus by gradual changes in brightness (brightness) or color tone (so-called gradation). FIG. 3(b) schematically illustrates an example in which information representing the thrombus composition is associated with each voxel. More specifically, (b-2) of FIG. 3 shows an example in which the entire thrombus shown in (b-1) of FIG. 3 (a-1) is divided into six voxels horizontally, two voxels vertically, and two voxels depthwise, and the distribution of feature values for each voxel is represented by the voxel brightness (or color). In this case, the region segmentation image processing function 152 may represent the feature value corresponding to the pixel at the center of the same voxel as the feature value of the entire voxel by brightness or color, or may average the feature values corresponding to each pixel in the same voxel and represent the average value as the feature value of the entire voxel by brightness or color. In this case, the user can roughly check the distribution of feature values for the entire thrombus by the brightness and color of the distribution of feature values. When representing an outline of the distribution of feature values in a thrombus, the region division image processing function 152 may perform image processing such as that shown in (a-2) of Figure 3 or (b-2) of Figure 3, and then perform further image processing to represent the outline.

[0039] FIG. 4(a) schematically illustrates an example of an image processing example in which, after image processing for representing the distribution of the feature values of the thrombus shown in FIG. 3(a-2) has been performed, further image processing for representing an outline of the distribution of the feature values of the thrombus is performed. More specifically, FIG. 4(b) illustrates an example in which the entire thrombus shown in FIG. 4(a), which exhibits the same distribution of feature values as FIG. 3(a-2), is horizontally divided into three regions (which may be three voxels), and the distribution of feature values for each region is represented by the brightness or color of the region. In this case, the region division image processing function 152 may represent the feature value corresponding to the pixel at the center of the same region or the average feature value as the feature value of the entire region, as in the case of the voxels shown in FIG. 3(b-2). Alternatively, the region division image processing function 152 may distinguish each region by a threshold value set for the feature value and represent the entire region by the brightness or color indicating whether the feature value is above or below the threshold value.

[0040] As shown in FIG. 4(b), when the distribution of feature values in a thrombus is to be roughly represented, the region division image processing function 152 may first divide the entire thrombus into regions of a suitable size (divide it into three regions in FIG. 4(b)), and then perform image processing so that each region represents the distribution of feature values of the thrombus.

[0041] FIG. 5 shows a schematic example of image processing when the determination function 140 outputs a thrombus removal method indicating that the thrombus is "atheromatous." Similar to FIGS. 3 and 4, FIG. 5 also shows an example of an image of only a thrombus (thrombus region image) captured in a medical image, estimated by the thrombus region estimation function 132. When the determination function 140 outputs a thrombus removal method indicating "atheromatous," the region segmentation image processing function 152 divides the entire thrombus into two regions, an outer region (the blood vessel wall side) and an inner region (the center side), and performs image processing on each region to represent the distribution of the thrombus composition (composition distribution) estimated by the thrombus composition estimation function 136, thereby associating the information represented by the thrombus composition. This is because, in the case of atherothrombotic cerebral infarction, a thrombus may form near a stenotic portion of a blood vessel, and the composition of the thrombus may differ between the outer region (the region close to the stenosis) and the inner region (the center region).

[0042] FIG. 5(a) shows an example in which the entire thrombus is divided into an inner region Ca around the central axis C of the thrombus (blood vessel) and an outer region Wa around the inner region Ca, i.e., close to the vascular wall (stenosis), and the distribution of feature values for each region is represented by the brightness and color of the region. FIG. 5(b-1) and FIG. 5(b-2) show an example of the relationship between the inner region Ca and the outer region Wa when the blood vessel (thrombus) is viewed from the central axis C. FIG. 5(b-1) shows an example in which the inner region Ca is represented by a square, assuming that the cross section of the thrombus is square. FIG. 5(b-2) also shows an example in which the inner region Ca is represented by a circle, assuming that the cross section of the thrombus is square. The only difference between FIG. 5(b-1) and FIG. 5(b-2) is the shape of the inner region Ca. The brightness and color of the distribution of feature values shown for each region represent the feature values of the same region, as in the examples shown in FIG. 3 and FIG. 4. In these cases, the user can confirm the difference in feature values between the inside and outside of the thrombus based on the brightness and color tone of the distribution of feature values.

[0043] FIG. 6 schematically illustrates an example of image processing when a segmentation method indicating "stent retriever compatibility" is output from the region segmentation determination function 142. Like FIGS. 3 to 5, FIG. 6 also illustrates an example of an image of only a thrombus (thrombus region image) captured in a medical image, estimated by the thrombus region estimation function 132. When a segmentation method indicating "stent retriever compatibility" is output from the region segmentation determination function 142, the region segmentation image processing function 152 segments the entire thrombus into multiple regions representing the components of a stent retriever, which is a thrombus removal device, its shape, and the extent to which these components deform when removing the thrombus. This is because, when a thrombus is removed using a stent retriever, various components such as a guidewire and a microcatheter are inserted into the thrombus together with the stent retriever, and the thrombus is removed by expanding the stent retriever. Furthermore, the type and shape (diameter) of each component, as well as the amount of force required to perforate the thrombus, may vary depending on the shape and hardness (composition) of the thrombus. The region division image processing function 152 performs image processing on each region to represent the distribution (composition distribution) of the thrombus composition estimated by the thrombus composition estimation function 136, and associates the information represented by the thrombus composition.

[0044] FIG. 6(a) shows an example in which the entire thrombus is divided into five regions, for example, regions R1 to R5, from the central axis C of the thrombus (blood vessel) toward the periphery, and the distribution of feature values for each region R is represented by the brightness and color of the region. Region R1 represents the shape (diameter) of the guidewire. Region R2 represents the shape (diameter) of the stent retriever before expansion. Region R3 represents the shape (diameter) of the microcatheter housing the guidewire and stent retriever. Region R4 represents the shape (maximum diameter) of the stent retriever after expansion. Region R5 represents the remaining region, in other words, the region of the thrombus that cannot be removed by the stent retriever. When dividing the entire thrombus, the region division image processing function 152 calculates, for example, the position of the central axis C of the thrombus region. Then, the region segmentation image processing function 152 uses size information of each component (e.g., stent diameter, inner diameter, etc.) to create, for example, cylindrical regions in the normal direction from the calculated central axis C, and designates each region as region R. FIG. 6(b) shows an example of the relationship between regions R1 to R5 when the blood vessel (thrombus) is viewed from the central axis C side. The cylindrical region R may be created based on the upper or lower base of the thrombus, instead of the central axis C of the thrombus, and in accordance with the size of each component. The brightness and color of the distribution of feature values shown for each region represent the same feature value, as in the example shown in FIGS. 3 to 5. In this case, the user can confirm the difference in feature values of each region R in the thrombus in a state where the stent retriever has been penetrated, based on the brightness (brightness) and color of the distribution of feature values.

[0045] FIG. 7 is a schematic diagram illustrating an example of image processing performed when the region segmentation determination function 142 outputs a segmentation method indicating "suction catheter compatibility." Similarly to FIGS. 3 to 6, FIG. 7 also illustrates an example of an image (thrombus region image) of only a thrombus captured in a medical image, estimated by the thrombus region estimation function 132. When the region segmentation determination function 142 outputs a segmentation method indicating "suction catheter compatibility," the region segmentation image processing function 152 divides the entire thrombus (blood vessel) from the central axis C of the thrombus (blood vessel) toward the periphery into multiple regions according to the components, shape, and size of the suction catheter, which is a thrombus removal device, as in the example illustrated in FIG. 6. The region segmentation image processing function 152 then divides the thrombus into two regions: the proximal and distal sides of the thrombus. This is because, when a suction catheter is used to remove a thrombus, the distal side of the thrombus may be crushed during suction. Furthermore, when a suction catheter is used to remove a thrombus, a separator for crushing the thrombus may be used along with the suction catheter. When the separator crushes the thrombus, the distal side of the thrombus may be crushed and scattered further away. In other words, a thrombus that has been dispersed to a distant location due to fragmentation may become a factor in the formation of a new thrombus (i.e., a secondary thrombus). The region segmentation image processing function 152 may further divide the area between the proximal and distal sides of the thrombus into multiple regions depending on the distance the aspiration catheter is advanced when removing the thrombus. The region segmentation image processing function 152 performs image processing on each region to represent the distribution of the thrombus composition (composition distribution) estimated by the thrombus composition estimation function 136, and associates the image with information represented by the thrombus composition.

[0046] FIG. 7 shows an example in which the entire thrombus is divided into two regions, a proximal region P and a distal region D, and the distribution of feature values for each region R is represented by the brightness and color of the region. In FIG. 7, as in the example shown in FIG. 6, the regions divided from the central axis C toward the periphery are omitted. The brightness and color of the distribution of feature values shown for each region represent the feature values of the same region, as in the examples shown in FIGS. 3 to 6. In this case, the user can confirm the differences in the feature values of each region in the thrombus to be aspirated by the suction catheter by the brightness (brightness) and color tone of the distribution of feature values.

[0047] [Example of how to calculate feature values] 3 to 7, the feature value corresponding to the pixel at the center of each divided region or the average feature value is used to represent the feature values of the same region, but the method for calculating the feature value representing a region is not limited to the above-mentioned example. An example of a method for calculating a feature value representing a divided region by the region division image processing function 152 will be described below. FIG. 8 is a diagram showing an example of differences between regions for which the region division image processing function 152 included in the medical image processing apparatus 100 according to the embodiment calculates feature values. FIG. 9 is a diagram showing an example of processing when the region division image processing function 152 included in the medical image processing apparatus 100 according to the embodiment calculates feature values of divided regions.

[0048] When performing image processing to represent the distribution (composition distribution) of thrombus composition estimated by the thrombus composition estimation function 136, the region division image processing function 152 calculates, for each divided region, a feature value of the thrombus composition represented by the thrombus composition information output by the thrombus composition estimation function 136. At this time, the region division image processing function 152 may calculate the feature value of the divided region from only the feature values corresponding to pixels included in the difference region of the divided region, or may calculate the feature value of the divided region from the feature values corresponding to pixels including the overlapping range in the divided regions.

[0049] FIG. 8 schematically shows an example of differences in the ranges (regions) of feature values used when calculating feature values. (a) of FIG. 8 shows an example in which a thrombus (blood vessel) is divided into five regions, regions Fa to Fe, spreading out from the central axis of the thrombus (blood vessel) toward the periphery, similar to the example shown in FIG. 6. (b-1) of FIG. 8 shows an example in which the feature value of a divided region F is calculated from the feature value of the difference region of the divided region F. More specifically, the feature value of region Fa, which is the central part of the thrombus region, is calculated using all feature values included in the range of region Fa. The feature value of region Fb outside region Fa is calculated using feature values included in the range obtained by excluding region Fa from the entire range of region Fb. Similarly, the feature value of region Fc outside region Fb is calculated using feature values included in the range obtained by excluding region Fb from the entire range of region Fc. The feature values of regions Fd and Fe are calculated in a similar manner. (b-2) of FIG. 8 shows an example in which the feature value of divided region F is calculated, including overlapping ranges within region F. More specifically, the feature values of region Fa are calculated using all feature values included in the range of region Fa. The feature values of region Fb are calculated using all feature values included in the range of region Fb, that is, all feature values included in the range of region Fa. Similarly, the feature values of region Fc are calculated using all feature values included in the range of region Fc, that is, all feature values included in the ranges of regions Fa and Fb. The feature values of regions Fd and Fe are calculated in the same way.

[0050] The region division image processing function 152 then inputs the calculated feature values to, for example, a composition estimation model to calculate feature values representing each of the divided regions. The composition estimation model is a trained model that has been trained in advance by a computing device (not shown) or the like so that, when the calculated feature values are input, the model outputs the composition of the thrombus, such as the proportions of each component that constitutes the thrombus represented by the feature values (hereinafter referred to as "composition proportions").

[0051] FIG. 9 schematically illustrates an example of a process in which the feature values of each region F shown in FIG. 8 are input into the composition estimation model ML to calculate (obtain) the composition ratios represented by the input feature values. FIG. 9(a) schematically illustrates an example of a process in which the feature values of each region F shown in FIG. 8 are input into the composition estimation model ML to calculate the corresponding composition ratios. FIG. 9(b) schematically illustrates an example of a case in which each region F shown in FIG. 8 is divided into two regions, a proximal region P and a distal region D, similar to the example shown in FIG. 7. The example shown in FIG. 9(b) illustrates an example of a process in which the feature values of each region F belonging to the proximal region P are input into the composition estimation model ML to calculate the composition ratio corresponding to the proximal region P, and the feature values of each region F belonging to the distal region D are input into the composition estimation model ML to calculate the composition ratio corresponding to the distal region D.

[0052] In this way, the region division image processing function 152 calculates the composition ratio corresponding to the feature value of each divided region. Then, as described above, the region division image processing function 152 represents the calculated composition ratio as the feature value corresponding to each region. The region division image processing function 152 outputs information representing the feature value of each region into which the thrombus region image is divided (hereinafter referred to as "region division information") to the display function 160.

[0053] The division function 150 (including the region division image processing function 152) is an example of a "division unit."

[0054] 1 , the display function 160 presents to the user information output by each component included in the medical image processing apparatus 100. More specifically, the display function 160 presents to the user the medical image and patient information output by the acquisition function 120, information on the estimation result output by the estimation function 130, the thrombus removal method and segmentation method output by the determination function 140, and area segmentation information obtained by segmentation by the segmentation function 150.

[0055] The region display function 162 generates a display image including information to be presented to the user, and outputs and displays the generated display image on a display device (not shown), thereby presenting it to the user of the medical image processing device 100. More specifically, the region display function 162 generates a display image for displaying the medical image output by the medical image acquisition function 122, a display image for displaying the patient information output by the patient information acquisition function 124, a display image for displaying the thrombus region image output by the thrombus region estimation function 132, a display image for displaying the thrombus type information output by the thrombus type estimation function 134, a display image for displaying the thrombus composition information output by the thrombus composition estimation function 136, a display image for displaying the thrombus removal method output by the judgment function 140, a display image for displaying the division method output by the region division judgment function 142, and a display image for displaying the region division information output by the region division image processing function 152. The area display function 162 may generate a single display image by combining part or all of the generated display images (by synthesizing or superimposing the display images).

[0056] [Example of displayed image] The following describes an example of a display image generated by the region display function 162. Figures 10 to 12 are diagrams showing an example of a display image generated by the region display function 162 included in the medical image-processing apparatus 100 according to the embodiment.

[0057] FIG. 10 shows an example of a display image for the region-segmentation image processing function 152 to display region segmentation information corresponding to each region into which the thrombus region image estimated by the thrombus region estimation function 132 is divided. In other words, FIG. 10 shows an example of a display image for presenting to the user the distribution of thrombus composition (composition distribution) estimated by the thrombus composition estimation function 136. More specifically, FIG. 10 shows an example of a display image for presenting to the user the stiffness of each region by different colors (hatching in FIG. 10 ) when the thrombus (blood vessel) is divided into four regions extending from the central axis toward the periphery, similar to the example shown in FIG. 6 . As described above, the stiffness of a thrombus can be determined by the ratio of RBCs to fibrin / platelets. Therefore, in the example shown in FIG. 10 , the stiffness of each region is presented to the user by indicating the ratio of red blood cells (RBCs). More specifically, if the sum of the RBC and fibrin / platelet ratios is 100%, the RBC ratio in the central region is "RBC:>80%," meaning "fibrin / platelet<20%, indicating the softest region. Conversely, the RBC ratio in the outermost region is "RBC:<20%, meaning "fibrin / platelet>80%, indicating the hardest region.

[0058] When generating a display image such as that shown in FIG. 10 , the region display function 162, for example, assigns brightness and color tones to each region obtained by dividing the thrombus region image to represent region division information. At this time, the region display function 162 assigns color information representing each color (R), green (G), and blue (B) and transparency (α) information representing transparency (or translucency in some cases) to each pixel constituting the same region, using table information such as a lookup table (LUT) prepared in advance. The region display function 162 may also display a pattern in the same region. The region display function 162 may assign different transparencies to each region so that overlapping regions can be seen. At this time, the region display function 162 may, for example, assign higher transparency to outer regions when there are multiple overlapping regions. The region display function 162 may be configured to lower the transparency of a region that the user particularly wants to focus on, such as a region that is expected to have a high fibrin content and be hard, to make it stand out, that is, to improve the visibility of the region that the user particularly wants to focus on. For example, the region display function 162 may be configured to increase the transparency of other regions in order to present only the region that the user has specified by performing an input operation on an input interface (not shown).

[0059] FIG. 11 shows an example of a display image that the region segmentation image processing function 152 uses to display a thrombus region estimated by the thrombus region estimation function 132 on a CT angiography image (CTA image) or an MR angiography image (MRA image) output by the medical image acquisition function 122. Here, in cerebral infarction diagnosis, maximum intensity projection (MIP) images based on CTA images or MRA images are often used to visualize blood vessels without using an angiography image. This is because MIP images make it easier to understand the movement of blood vessels. FIG. 11 shows an example of a display image that shows a thrombus region on an MIP image. More specifically, FIG. 11(a) shows an example of an MIP image generated from a CTA image or an MRA image, and FIG. 11(b) shows an example of a display image in which a thrombus region image Ta reflecting the composition distribution of the thrombus is superimposed on the thrombus region in the MIP image. This allows the user to visually recognize the location of the thrombus relative to the blood vessel and its composition distribution, rather than simply having the thrombus region displayed on a CTA image or MRA image. This makes it easier for the user to imagine how to advance the thrombus removal device into the blood vessel during surgery to remove the thrombus. For example, if the MIP image is configured so that its angle can be changed (e.g., rotated), the region display function 162 may rotate the thrombus region image Ta superimposed on the MIP image according to the angle of the MIP image.

[0060] Fig. 12 shows an example of a display image for the region segmentation image processing function 152 to display the estimation result output by the estimation function 130 and the thrombus removal method and division method output by the judgment function 140. Fig. 12 shows an example of a display image showing the following information: "cardiogenic" as information on the thrombus disease type, "RBC>80%" as information on the thrombus composition, "shortest diameter xx mm" as information on the thrombus region, and "stent retriever, (type: xx) divided by shape" as information on the thrombus removal method and division method.

[0061] The display function 160 (including the area display function 162) is an example of a "display unit."

[0062] [Medical image processing equipment] Next, a description will be given of the overall operation of the medical image processing apparatus 100. Fig. 13 is a flowchart showing an example of the flow of processing in the medical image processing apparatus 100 according to the embodiment.

[0063] When the process of presenting information about a thrombus is started in the medical image processing device 100, first, the medical image acquisition function 122 included in the acquisition function 120 acquires a medical image (step S100). The medical image acquisition function 122 outputs the acquired medical image to each of the estimation function 130 and the display function 160. Furthermore, the patient information acquisition function 124 included in the acquisition function 120 acquires patient information (step S102). The patient information acquisition function 124 outputs the acquired patient information to each of the estimation function 130 and the display function 160.

[0064] The estimation function 130 estimates the thrombus region, thrombus type, and composition based on the medical image and patient information output by the acquisition function 120 (step S110). The estimation function 130 outputs an estimation result regarding the estimated thrombus. More specifically, a thrombus region estimation function 132 included in the estimation function 130 estimates a thrombus region that is thought to be a thrombus captured in the medical image, and outputs a thrombus region image as the estimation result to each of the determination function 140, the division function 150, and the display function 160. A thrombus type estimation function 134 included in the estimation function 130 estimates the thrombus type of the thrombus that is thought to be captured in the medical image, and outputs thrombus type information as the estimation result to each of the determination function 140, the division function 150, and the display function 160. The thrombus composition estimation function 136 included in the estimation function 130 estimates the thrombus composition of the thrombus that is thought to be captured in the medical image, and outputs thrombus composition information as the estimation result to each of the judgment function 140, the division function 150, and the display function 160.

[0065] The determination function 140 determines a thrombus removal method and a division method based on the respective estimation results output by the estimation function 130 (step S120). The determination function 140 outputs the determined thrombus removal method and division method to the division function 150 and the display function 160 as the determination results. More specifically, the determination function 140 determines a thrombus removal method for removing the thrombus shown in the medical image, and outputs the determined thrombus removal method to the division function 150 and the display function 160. The region division determination function 142 determines a division method for the thrombus region shown in the medical image, and outputs the determined division method to the division function 150 and the display function 160.

[0066] The division function 150 (including the region division image processing function 152) divides the thrombus region image output by the thrombus region estimation function 132 (step S130) in accordance with the thrombus removal method and division method output by the determination function 140. The division function 150 (including the region division image processing function 152) outputs region division information indicating the feature values of each region into which the thrombus region image is divided to the display function 160.

[0067] The display function 160 (including the region display function 162) generates a display image including information output by each component included in the medical image-processing device 100, and outputs the generated display image to a display device (not shown) for display (step S140). In this way, information about the thrombus processed by the medical image-processing device 100 is presented to the user.

[0068] Here, an example of information related to thrombi presented to the user by the medical image processing apparatus 100 will be described. Fig. 14 is a diagram showing an example of a display screen when the medical image processing apparatus 100 according to the embodiment provides information. Fig. 14 shows an example of a display screen IM in which the medical image processing apparatus 100 displays, on a display device (not shown), a single display image that combines multiple display images generated by the region display function 162.

[0069] On the display screen IM, an NCCT image I-1, a CTA image 1-2, an MIP image I-3, a display image I-4, and a display image I-5 are each synthesized and displayed on a display device (not shown). The NCCT image I-1 is an NCCT image acquired by the medical image acquisition function 122. The CTA image 1-2 is a CTA image acquired by the medical image acquisition function 122. A thrombus T is captured in the CTA image 1-2. The MIP image I-3 is a display image (see FIG. 11(b)) generated by the region segmentation image processing function 152. A thrombus region image Ta is superimposed on the MIP image I-3 by the region segmentation image processing function 152 at a position corresponding to the region of the thrombus T captured in the CTA image 1-2. The display image I-4 is a display image (see FIG. 10) generated by the region segmentation image processing function 152. Display image I-4 shows the hardness of each of the regions (four regions) into which the thrombus T is divided. Display image I-5 is a display image (see FIG. 12) generated by the region division image processing function 152. Display image I-5 shows the state of the thrombus T (thrombus disease type, thrombus composition, thrombus region), and information on the thrombus removal method and division method corresponding to the thrombus T.

[0070] The display screen IM shown in Figure 14 is merely an example, and the medical image or display image displayed on the display screen IM may be another medical image or display image instead of or in addition to the medical image or display image displayed on the display screen IM.

[0071] In this way, the medical image processing apparatus 100 presents the user with information about a thrombus that is thought to be captured in a medical image (information more suitable for diagnosing and treating the thrombus). This allows the user of the medical image processing apparatus 100 to confirm various information about the thrombus that has occurred in the patient, including the composition distribution (compositional composition of a local area) and thrombus removal. This allows the user to more appropriately diagnose the thrombus that has occurred in the patient. The user can then more appropriately make decisions about the treatment of the thrombus, such as the surgical procedure for removing the thrombus that has occurred in the patient (selection of a thrombus removal device and procedure). This is expected to improve the results (treatment outcomes) of the treatment of the thrombus that has occurred in the patient.

[0072] As described above, the medical image processing apparatus of the embodiment acquires medical images of a patient and patient information. Then, the medical image processing apparatus of the embodiment estimates the state of a thrombus captured in the medical image based on the acquired medical image and patient information. Furthermore, the medical image processing apparatus of the embodiment presents information such as the composition distribution of the thrombus and thrombus removal to the user based on the estimation result of the state of the thrombus. This allows the user to make appropriate decisions regarding diagnosis and treatment based on the respective pieces of information regarding the thrombus presented by the medical image processing apparatus of the embodiment. In other words, the medical image processing apparatus of the embodiment can provide support for the user's diagnosis and treatment of a thrombus.

[0073] In the above-described embodiment, the processing circuitry of the medical image processing apparatus is described as being implemented in a single computer device or a server device on a network (not shown). However, this is merely an example, and the processing circuitry of the medical image processing apparatus, or the functions realized by the processing circuitry of the medical image processing apparatus, may be implemented by a configuration combining multiple server devices or computer devices. In this case, the functional configuration, operation, and processing of the processing circuitry of the medical image processing apparatus should be equivalent to the functional configuration, operation, and processing of the processing circuitry of the medical image processing apparatus in the above-described embodiment. Therefore, detailed descriptions of the processing circuitry of the medical image processing apparatus in this case, or the functional configuration, operation, and processing that realizes its functions, will be omitted.

[0074] The above-described embodiment can be expressed as follows. processing circuitry; The processing circuitry acquiring a medical image showing at least a patient's blood vessels and patient information relating to the patient; estimating the state of the thrombus shown in the medical image based on the medical image and the patient information, and outputting an estimation result regarding the estimated thrombus; determining a thrombus removal method for removing the thrombus based on the medical image, the patient information, and the estimation result, and outputting the determination result of the thrombus removal method; generating a display image for presenting one or more of the medical image, the estimation result, and the judgment result, and displaying the generated image on a display device; Medical imaging equipment.

[0075] According to at least one of the embodiments described above, a medical image processing device and a medical image processing method capable of presenting more suitable information for diagnosing and treating thrombi can be realized by having an acquisition unit (120, 122, 124) that acquires at least a medical image showing a patient's blood vessels and patient information about the patient, an estimation unit (130) that estimates the state of a thrombus shown in the medical image based on the medical image and the patient information and outputs an estimation result about the estimated thrombus, a judgment unit (140) that judges a thrombus removal method for removing the thrombus based on the medical image, the patient information, and the estimation result and outputs a judgment result about the thrombus removal method, and a display unit (160, 162) that generates a display image for presenting one or more of the medical image, the estimation result, and the judgment result and displays it on a display device.

[0076] Although several embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0077] 100 Medical image processing device, 110 Processing circuit, 120 Acquisition function, 122 Medical image acquisition function, 124 Patient information acquisition function, 130 Estimation function, 132 Thrombus region estimation function, 134 Thrombus disease type estimation function, 136 Thrombus composition estimation function, 140 Judgment function, 142 Region division judgment function, 150 Division function, 152 Region division image processing function, 160 Display function, 162 Region display function

Claims

1. an acquisition unit that acquires a medical image showing at least a patient's blood vessels and patient information relating to the patient; an estimation unit that estimates the state of the thrombus shown in the medical image based on the medical image and the patient information, and outputs an estimation result regarding the estimated thrombus; a determination unit that determines a thrombus removal method for removing the thrombus based on the medical image, the patient information, and the estimation result, and outputs the determination result of the thrombus removal method; a display unit that generates a display image for presenting one or more of the medical image, the estimation result, and the judgment result, and displays the image on a display device; A medical image processing device comprising:

2. The estimation unit a thrombus region estimation unit that estimates a region of the thrombus in the medical image and outputs a thrombus region image of the estimated region of the thrombus as the estimation result; a thrombus disease type estimation unit that estimates the disease type of the thrombus and outputs thrombus disease type information indicating the estimated disease type of the thrombus as the estimation result; a thrombus composition estimation unit that estimates a composition of the thrombus and outputs thrombus composition information representing the estimated composition of the thrombus as the estimation result; Equipped with The medical image processing device according to claim 1 .

3. the thrombus region estimation unit, when receiving the medical image, outputs, as the estimation result, the image of the thrombus region segmented from the medical image using a trained model that has been trained to output an image in which a region showing a sign of thrombus that can be confirmed on the medical image is determined to be the thrombus region; the thrombus disease type estimation unit receives image features of a medical image before thrombus removal, and outputs the thrombus disease type information estimated from the medical image before thrombus removal as the estimation result using a trained model that has been trained to output a thrombus disease type determined after thrombus removal; the thrombus composition estimation unit receives image features of a medical image before thrombus removal, and outputs thrombus composition information estimated from the medical image before thrombus removal as the estimation result using a trained model that has been trained to output an analysis result after thrombus removal; The medical image processing device according to claim 2 .

4. the determining unit determines the thrombus removal method based on a combination of the thrombus region image, the thrombus disease type information, and the thrombus composition information.

4. The medical image processing device according to claim 2 or 3.

5. the determining unit determines a division method for dividing the thrombus region represented by the thrombus region image based on a combination of the thrombus region image, the thrombus disease type information, and the thrombus composition information, and the thrombus removal method, and outputs a determination result of the division method; Equipped with a division unit that performs image processing to divide the thrombus region image into a plurality of regions according to the judgment result and the judgment result of the division method, and outputs region division information that represents feature values including the composition of the thrombus in the divided regions; Further provided with The medical image processing device according to claim 4 .

6. the thrombus removal method includes information representing the hardness of the thrombus, the dividing unit performs the image processing to divide the thrombus into the regions according to the hardness of the thrombus. The medical image processing device according to claim 5 .

7. the thrombus removal method includes information representing a pathological type of the thrombus, the dividing unit performs the image processing for dividing the image into the regions according to the disease type of the thrombus. The medical image processing device according to claim 6 .

8. The thrombus removal method includes a procedure for removing the thrombus using a thrombus removal device, When the determination result is that the thrombus is to be removed by a procedure using the thrombus removal device, the dividing unit performs the image processing to divide the thrombus region image into the regions corresponding to the thrombus removal device used in the procedure to remove the thrombus. The medical image processing device according to claim 7 .

9. the dividing unit, when receiving the feature value, calculates a composition ratio corresponding to the feature value using a trained model that has been trained to output a composition composition including a ratio of a composition that constitutes the thrombus represented by the feature value, and outputs the calculated composition ratio as the region division information. The medical image processing device according to claim 8 .

10. the display unit generates the display image showing the area division information corresponding to each of the divided areas and displays the display image on the display device. The medical image processing device according to claim 9 .

11. The computer acquiring a medical image showing at least a patient's blood vessels and patient information relating to the patient; estimating the state of the thrombus shown in the medical image based on the medical image and the patient information, and outputting an estimation result regarding the estimated thrombus; determining a thrombus removal method for removing the thrombus based on the medical image, the patient information, and the estimation result, and outputting the determination result of the thrombus removal method; generating a display image for presenting one or more of the medical image, the estimation result, and the judgment result, and displaying the generated image on a display device; Medical image processing methods.

Images