Medical image processing device, medical image processing method, and medical image processing program

Abstract

To estimate the likelihood of a disease in a candidate region for the disease using a region related to a stricture in an imaged part.SOLUTION: A medical image processing device includes an acquisition unit, a first detection unit, a second detection unit, an estimation unit, and a display unit. The acquisition unit acquires a first medical image collected by predetermined imaging for an imaging part of a subject and a second medical image including a blood vessel on the imaging part collected by imaging different from the predetermined imaging. The first detection unit detects a disease candidate region indicating a candidate from a region of a disease in the imaging part on the basis of the first medical image. The second detection unit detects a stricture part on the stricture of the blood vessel on the basis of the second medical image. The estimation unit estimates the likelihood of the disease for the disease candidate region on the basis of the disease candidate region and the stricture part. The display unit displays the region of the disease on the likelihood and the second medical image by superimposing them on the first medical image.SELECTED DRAWING: Figure 4

Description

Technical Field

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

Background Art

[0002] Conventionally, as a method for automatically detecting the location of acute cerebral infarction, there is a method using non-contrast CT (Computed Tomography) images or DWI images (Diffusion Weighted Image). However, in non-contrast CT images, the change in signal value in the infarction region is small compared to the normal region. Therefore, it can be difficult to detect the location of acute cerebral infarction using non-contrast CT images. On the other hand, although the change in signal value in the infarction region is large in DWI images, they may be easily affected by image quality and artifacts.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to estimate the likelihood of a disease in a region that is a candidate for the disease using a region related to stenosis in the imaging site. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problems. The problems corresponding to the respective effects of each configuration shown in the embodiments described later can also be regarded as other problems.

Means for Solving the Problems

[0005] The medical image processing apparatus according to this embodiment includes an acquisition unit, a first detection unit, a second detection unit, an estimation unit, and a display unit. The acquisition unit acquires a first medical image collected by performing a predetermined imaging on an imaging region of a subject, and a second medical image collected by performing an imaging different from the predetermined imaging and including blood vessels related to the imaging region. The first detection unit detects a disease candidate region indicating a candidate for a disease region in the imaging region based on the first medical image. The second detection unit detects a stenosis site related to the stenosis of the blood vessels based on the second medical image. The estimation unit estimates the likelihood of the disease for the disease candidate region based on the disease candidate region and the stenosis site. The display unit displays the disease region related to the likelihood and the second medical image by superimposing them on the first medical image.

Brief Description of the Drawings

[0006]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Best Mode for Carrying Out the Invention

[0007] Hereinafter, embodiments of a medical image processing apparatus, a medical image processing method, and a medical image processing program will be described with reference to the drawings. In the following embodiments, parts denoted by the same reference numerals perform the same operations, and overlapping descriptions will be omitted as appropriate.

[0008] (Embodiment) FIG. 1 is a block diagram showing an example of the configuration of a medical image processing system 1 including a medical image processing apparatus 30 according to an embodiment. As shown in FIG. 1, the medical image processing system 1 according to the embodiment includes a medical image diagnostic apparatus 10, an image storage apparatus 20, and a medical image processing apparatus 30. As shown in FIG. 1, the medical image diagnostic apparatus 10, the image storage apparatus 20, and the medical image processing apparatus 30 are interconnected via a network.

[0009] The medical image diagnostic apparatus 10 is connected to, for example, a Magnetic Resonance Imaging (MRI) apparatus, a Computed Tomography (CT) apparatus, and / or an X-ray angiography apparatus (also referred to as X-ray angiography). The MRI apparatus, the X-ray CT apparatus, and the X-ray angiography apparatus are examples of image capturing apparatuses. The medical image diagnostic apparatus 10 collects a first medical image and a second medical image by imaging a subject. For example, the medical image diagnostic apparatus 10 collects the first medical image by performing a predetermined imaging on an imaging site of the subject. Further, the medical image diagnostic apparatus 10 collects the second medical image collected by an imaging different from the predetermined imaging. The second medical image includes blood vessels related to the imaging site. The second medical image may be in the same cross-section as the first medical image or may be in a cross-section different from the first medical image. Also, the imaging region related to the second medical image may be the same as the imaging region of the first medical image or may be different from the imaging region of the first medical image. Also, the first medical image and the second medical image are assumed to be axial cross-sections of the imaging site or coronal cross-sections of the imaging site. Also, the imaging site is, for example, the brain of the subject. The first medical image and the second medical image are, for example, images captured at different timings with respect to the subject.

[0010] The MRI apparatus collects a magnetic resonance image (MR image) from a subject. For example, the MRI apparatus generates an MR image by collecting and reconstructing MR data from the subject. The MRI apparatus transmits the generated MR image to the image storage device 20 or the medical image processing device 30. Since a known configuration can be applied as the configuration of the MRI apparatus, the description thereof is omitted. The MRI image is, for example, a Diffusion Weighted Imaging (DWI) image, a magnetic resonance angiography image (hereinafter referred to as an MRA (MR Angiography) image), or the like. The diffusion weighted image also includes an ADC (Apparent Diffusion Coefficient) map.

[0011] When the first medical image and the second medical image are collected by an MRI device, the DWI image corresponds to the first medical image, and the MRA image corresponds to the second medical image. When the first medical image and the second medical image are collected by an MRI device, a predetermined imaging is, for example, diffusion-weighted (DW) imaging (DW-EPI) using echo planar imaging (EPI). As the DW imaging, since known imaging methods of a T2-weighted image system are applicable, the description is omitted. The DW imaging is typically performed on an axial cross-section of the imaging region or a coronal cross-section of the imaging region. Also, a different imaging is MRA imaging. Note that the different imaging is MRA imaging for the same cross-section or a different cross-section with respect to the cross-section related to the DWI image. Since known imaging methods are applicable as the MRA imaging, the description is omitted. The MRA image is non-contrast and has an advantage of being often obtained by being imaged within the same examination as the DWI image.

[0012] An X-ray CT device acquires an X-ray CT image (CT image) of a subject by irradiating the subject with X-rays. For example, the X-ray CT device generates a CT image by collecting and reconstructing projection data related to the subject. The X-ray CT device transmits the generated CT image to the image storage device 20 or the medical image processing device 30. Since a known configuration is applicable as the configuration of the X-ray CT device, the description is omitted. The X-ray CT image is, for example, a non-contrast X-ray CT image (hereinafter referred to as a non-contrast CT image), a contrast X-ray CT image (hereinafter referred to as a contrast CT image (CTA image)), or the like.

[0013] When the first medical image and the second medical image are collected by an X-ray CT device, the non-contrast CT image corresponds to the first medical image, and the contrast CT image corresponds to the second medical image. When the first medical image and the second medical image are collected by an MRI device, a predetermined imaging corresponds to, for example, scanning the imaging region non-contrast, and a different imaging corresponds to a contrast scan. For example, the different imaging corresponds to a contrast scan for the same cross-section or a different cross-section with respect to the cross-section related to the non-contrast image.

[0014] An X-ray angiography device acquires a vascular image (angiogram) of a subject by irradiating the subject with X-rays. For example, the X-ray angiography device generates an angiogram by X-ray imaging under administration of a contrast agent to the subject. The X-ray angiography device transmits the generated angiogram to the image storage device 20 or the medical image processing device 30. Since a known configuration can be applied as the configuration of the X-ray angiography device, the description thereof is omitted. When the second medical image is collected by the X-ray angiography device, the angiogram corresponds to the second medical image. Different imaging corresponds to contrast imaging. For example, different imaging corresponds to contrast imaging including the same section or a different section as the section regarding the first medical image.

[0015] Note that the first medical image and the second medical image are not limited to the axial section or the coronal section of the imaging site, and may be performed on other sections such as a volume scan of the subject's brain or an oblique section. At this time, the first medical image and the second medical image are generated by cross-sectional conversion processing on the generated volume data.

[0016] The image storage device 20 stores the first medical image, the second medical image, etc. collected by the medical image diagnostic device 10. For example, the image storage device 20 is realized by a computer device such as a server device. Specifically, the image storage device 20 is realized by a PACS (Picture Archiving and Communication System) server or the like. The image storage device 20 may be referred to as a medical image management system. In the present embodiment, the image storage device 20 acquires the first medical image and the second medical image from the medical image diagnostic device 10 via a network, and stores the acquired first medical image and second medical image in a memory provided inside or outside the device.

[0017] The medical image processing apparatus 30 acquires the first medical image and the second medical image from the medical image diagnostic apparatus 10 or the image storage apparatus 20 via a network, and executes various processes using the acquired first medical image and second medical image. The medical image processing apparatus 30 may also be referred to as a medical image analysis apparatus or an analysis apparatus. For example, the medical image processing apparatus 30 is realized by a computer device such as a workstation. Further, the medical image processing apparatus 30 causes a display 32 to display the result of the process processed based on the first medical image and the second medical image.

[0018] As shown in FIG. 1, the medical image processing apparatus 30 includes an input interface 31, a display 32, a memory 33, and a processing circuit 34.

[0019] The input interface 31 is realized by a trackball, a switch, a button, a mouse, a keyboard, a touch pad that performs an input operation by touching an operation surface, a touch screen in which a display screen and a touch pad are integrated, a non-contact input circuit using an optical sensor, a voice input circuit, or the like for performing various instructions and various settings. The input interface 31 converts the input operation received from the operator into an electrical signal and outputs it to the processing circuit 34.

[0020] Note that the input interface 31 is not limited to those including physical operation components such as a mouse and a keyboard. For example, 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 30 and outputs this electrical signal to the processing circuit 34 is also included in the example of the input interface 31. The input interface 31 is an example of an input unit.

[0021] The display 32 displays various types of information under the control of the display control function 34e. For example, the display 32 displays a GUI (Graphical User Interface) for receiving an operator's instructions and various X-ray image data. For example, the display 32 is a liquid crystal display or a CRT (Cathode Ray Tube) display. The display 32 is an example of a display unit.

[0022] The memory 33 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, a hard disk, an optical disk, etc. For example, the memory 33 stores the first medical image and the second medical image acquired from the medical imaging device 10 or the image storage device 20. Also, for example, the memory 33 stores a program for each circuit included in the medical image processing device 30 to realize its function. The memory 33 is an example of a storage unit.

[0023] The processing circuit 34 controls the operation of the entire medical image processing device 30 by executing the acquisition function 34a, the first detection function 34b, the second detection function 34c, the estimation function 34d, and the display control function 34e.

[0024] The processing circuit 34 reads out and executes a program for realizing the acquisition function 34a from the memory 33, thereby acquiring the first medical image and the second medical image from the medical imaging device 10 or the image storage device 20. The acquisition function 34a stores the first medical image and the second medical image in the memory 33. The processing circuit 34 that realizes the acquisition function 34a corresponds to an acquisition unit.

[0025] The processing circuit 34 reads out and executes a program for realizing the first detection function 34b from the memory 33. Thereby, the first detection function 34b detects a disease candidate region based on the first medical image. The disease candidate region indicates a candidate for the region of the disease in the imaging site of the first medical image. The first detection function 34b executes image processing on the first medical image and identifies the disease candidate region in the first medical image.

[0026] For example, the first detection function 34b identifies, in the first medical image, a plurality of pixels having pixel values lower than a predetermined threshold as a disease candidate region. When the first medical image is an ADC map, the predetermined threshold corresponds to, for example, a value at which the apparent diffusion coefficient (ADC) is lower than that of a healthy part (hereinafter referred to as the ADC threshold). The ADC threshold is preset and stored in the memory 33. A small value of the apparent diffusion coefficient corresponds to a tissue affected by a vascular infarction. Therefore, when the imaging site is the brain, the disease candidate region corresponds to the region where a cerebral infarction has occurred.

[0027] Note that the identification of the disease candidate region is not limited to the segmentation process using the ADC threshold for the ADC map in the first medical image. For example, a learned model that outputs a disease candidate region with the first medical image as an input may be used for the identification of the first region.

[0028] FIG. 2 is a diagram showing an example of a disease candidate region DCR detected in the ADC map 3AM. The ADC map 3AM in FIG. 2 shows the case where the imaging site is the brain. As shown in FIG. 2, the first detection function 34b detects, for example, two disease candidate regions DCR by image processing on the ADC map 3AM corresponding to the first medical image.

[0029] When the first medical image is a non-contrast CT image, the predetermined threshold corresponds to a CT value corresponding to a vascular stenosis region. At this time, the predetermined threshold corresponds to, for example, a CT value for discriminating an early CT sign in the non-contrast CT image. The predetermined threshold for discriminating the early CT sign is preset and stored in the memory 33.

[0030] FIG. 3 is a diagram showing an example of a disease candidate region DCR detected in the non-contrast CT image 3NC. The non-contrast CT image 3NC in FIG. 3 shows the case where the imaging site is the brain. As shown in FIG. 3, the first detection function 34b detects, for example, two disease candidate regions DCR by image processing on the non-contrast CT image 3NC corresponding to the first medical image.

[0031] The processing circuit 34 stores, in the memory 33, the detected disease candidate regions in association with the first medical image by the first detection function 34b. The number of disease candidate regions detected by the first detection function 34b is not limited to one and may be plural. The processing circuit 34 that realizes the first detection function 34b corresponds to the first detection unit.

[0032] The processing circuit 34 reads and executes a program that realizes the second detection function 34c from the memory 33. Thereby, the second detection function 34c detects a stenosis site based on the second medical image. The stenosis site is a location related to the stenosis of a blood vessel regarding the imaging site and includes an infarction site (infarction location) of the blood vessel. For example, the stenosis site is a region where blood vessels are distributed downstream from the stenosis position. Specifically, the stenosis site corresponds to a region dominated by the downstream blood vessels (hereinafter referred to as the vascular dominance region).

[0033] The vascular dominance region is, for example, the middle cerebral artery (MCA) region, the anterior cerebral artery (ACA) region, the deep penetrating artery (anterior choroidal artery) region of the internal carotid artery (ICA), the posterior cerebral artery (PCA) region, the posterior inferior cerebellar artery (PICA) region, the anterior inferior cerebellar artery (AICA) region, the superior cerebellar artery (SCA) region, etc. The disease region is included in the stenosis site.

[0034] The processing circuit 34 detects the stenosis site in the second medical image by performing various image processes on the MRA image, the contrast CT image, or the angiogram image by the second detection function 34c. Since known processes such as known segmentation processes, threshold processes, and utilization of learned models are applicable to the image process, the description thereof is omitted.

[0035] Note that the processing circuit 34 may detect, by the second detection function 34c, the degree of stenosis of the blood vessel at the position of stenosis in the stenotic site, for example, the stenosis rate, based on the stenotic site in the second medical image. Since known methods such as the ratio of the inner diameter of the blood vessel at the stenosis position to the inner diameter of the blood vessel upstream of the stenotic site can be used for detecting the degree of stenosis of the blood vessel in the stenotic site, for example, calculating the stenosis rate, the description thereof is omitted.

[0036] The processing circuit 34 stores, by the second detection function 34c, the detected stenotic site in the memory 33 in association with the second medical image. Note that when the degree of stenosis of the blood vessel in the stenotic site is detected, the second detection function 34c stores the detected degree of stenosis in the memory 33 in association with the stenotic site. Note that the stenotic site detected by the second detection function 34c is not limited to one, and may be plural. The processing circuit 34 that realizes the second detection function 34c corresponds to the second detection unit. Also, the first detection function 34b and the second detection function 34c may be integrated as a detection function.

[0037] The processing circuit 34 reads out and executes a program that realizes the estimation function 34d from the memory 33. Thereby, the estimation function 34d estimates the probability of disease for the disease candidate region based on the disease candidate region and the stenotic site. The probability is higher when the stenotic site and the disease candidate region overlap than when they do not overlap. For example, when the stenotic site includes the disease candidate region, the estimation function 34d estimates the highest probability because the stenotic site and the disease candidate region match. Also, for example, when the stenotic site and the disease candidate region do not overlap at all, the estimation function 34d estimates the lowest probability.

[0038] Further, the processing circuit 34 may calculate the size (area) of the overlapping region where the stenosis site and the disease candidate region overlap by the estimation function 34d. At this time, the estimation function 34d reads a predetermined value set in advance from the memory 33. Next, the estimation function 34d compares the size of the overlapping region with the predetermined value. If the size of the overlapping region between the stenosis site and the disease candidate region is less than the predetermined value, the estimation function 34d estimates that the disease candidate region is a false positive as the probability of the disease.

[0039] Also, when the calculated size of the overlapping region is equal to or greater than the predetermined value, the estimation function 34d estimates that the disease candidate region is not a false positive (for example, a true positive) as the probability of the disease. The estimation function 34d that estimates whether it is a false positive (a binary value corresponding to the presence or absence of a positive) may be mounted on the processing circuit 34 as a determination function. At this time, the processing circuit 34 that realizes the determination function corresponds to a determination unit.

[0040] In addition, the processing circuit 34 may estimate the probability of the disease corresponding to the probability by the estimation function 34d based on the size of the overlapping region between the stenosis site and the disease candidate region and the degree of stenosis. For example, the estimation function 34d reads a correspondence table from the memory 33. The correspondence table is a look-up table (LUT) that represents the probability of the disease with respect to the size of the overlapping region and the degree of stenosis (for example, the stenosis rate). The LUT is preset and stored in the memory 33. The estimation function 34d estimates the probability of the disease by collating the size of the overlapping region and the degree of stenosis with the LUT.

[0041] Note that the estimation of the probability of the disease is not limited to using the LUT, and may be realized by, for example, a calculation formula or a learned model that outputs the probability of the disease with the size of the overlapping region and the degree of stenosis as inputs. For example, if the state of the blood vessel at the stenosis site is stenosis rather than occlusion, the estimation function 34d lowers the probability of the detected disease candidate region compared to the occlusion state. In other words, if the state of the blood vessel at the stenosis site is occlusion, the estimation function 34d raises the probability of the detected disease candidate region compared to the stenosis state.

[0042] Note that the estimation function 34d may estimate a disease region (hereinafter referred to as a disease region) regarding the probability of the estimated disease. That is, the estimation function 34d may estimate the probability of the disease in the disease candidate region and specify a disease region corresponding to the estimated probability of the disease. For example, in the estimation function 34d, for each of a plurality of disease candidate regions, a disease region regarding false positives or a disease region regarding non-false positives (true positives) is specified.

[0043] In addition, in the estimation function 34d, for each of a plurality of disease candidate regions, a disease region corresponding to the probability of the disease may be specified. In other words, the estimation function 34d may specify a disease region corresponding to the estimated probability of the disease based on a plurality of disease candidate regions and the estimated probability of the disease. Note that the estimation function 34d that estimates the disease region may be referred to as a specifying function. At this time, the processing circuit 34 that realizes the specifying function corresponds to the specifying unit.

[0044] The processing circuit 34 associates the estimated probability of the disease, false positives or non-false positives, and / or the probability of the disease with the disease candidate region DCR by the estimation function 34d and stores it in the memory 33. The processing circuit 34 that realizes the estimation function 34d corresponds to the estimation unit.

[0045] The processing circuit 34 reads out and executes a program corresponding to the display control function 34e from the memory 33. Thereby, the display control function 34e superimposes the disease region regarding the probability and the second medical image on the first medical image and displays them on the display 32. The disease region regarding the probability (disease region) is, for example, a disease candidate region with a high probability, a disease candidate region estimated as non-false positive, a disease candidate region with a high probability of the disease, and the like.

[0046] Specifically, when a plurality of disease candidate regions are detected by the first detection function 34b, the disease regions displayed on the display 32 are the disease candidate regions with the highest probability, the disease candidate regions estimated to be non-false positives (true positives), the disease candidate regions with the highest disease certainty, and the like. Note that the disease regions regarding probability may be the disease candidate regions estimated to be false positives.

[0047] More specifically, the processing circuit 34 performs positional association of the first medical image and the second medical image by alignment (registration) of the first medical image and the second medical image by the display control function 34e. The alignment of the first medical image and the second medical image is realized, for example, by image processing using respective anatomical landmark points in the first medical image and the second medical image.

[0048] Note that the alignment of the first medical image and the second medical image is not limited to the alignment using anatomical landmark points, and may be realized by other methods such as methods using various image recognition processes. Also, the alignment of the first medical image and the second medical image may be realized by an image processing function (not shown) or the like.

[0049] Next, the processing circuit 34 superimposes the second medical image aligned with the first medical image by the display control function 34e. For example, when the first medical image is a DWI image and the second medical image is an MRA image, the display control function 34e superimposes the MRA image on the DWI image and causes it to be displayed on the display 32. At this time, the display control function 34e further superimposes the disease region on the superimposed image obtained by superimposing the MRA image on the DWI image and causes it to be displayed on the display 32. Thereby, the display 32 displays the disease region regarding probability and the second medical image superimposed on the first medical image.

[0050] Note that the processing circuit 34 may cause the display control function 34e to further superimpose the probability corresponding to the disease region on the superimposed image and display it on the display 32. Further, when a plurality of disease candidate regions are detected and each of the plurality of disease candidate regions is estimated to be false positive or non-false positive, the display control function 34e causes the boundary line (frame line) of the disease region corresponding to the false positive and the boundary line of the disease region corresponding to the non-false positive to be displayed on the display 32 in different display modes. The boundary line of the disease region is a line indicating the boundary between the disease region and the tissue adjacent to the disease region. Different display modes are, for example, different hues or different line types, etc.

[0051] For example, the display control function 34e causes the boundary line of the disease region related to the false positive and the boundary line of the disease region related to the non-false positive to be further superimposed on the superimposed image in different hues or different line types and displayed on the display 32. Thereby, the display 32 displays the boundary line of the disease region corresponding to the false positive and the boundary line of the disease region corresponding to the non-false positive in different display modes.

[0052] Further, the processing circuit 34 causes the display control function 34e to display the disease region on the display 32 in a display mode according to the accuracy. For example, the display control function 34e further superimposes the boundary line of the disease region on the superimposed image in a hue or line type according to the magnitude of the accuracy and displays it. Thereby, the display 32 displays the disease region in a display mode according to the accuracy.

[0053] Note that the processing circuit 34 may cause the display control function 34e to store the display image in the memory 33 or the image storage device 20 in the display 32. The processing circuit 34 that realizes the display control function 34e corresponds to the display control unit.

[0054] Above, the overall configuration of the medical image processing system 1 according to the embodiment has been described. Hereinafter, the process of estimating and displaying the probability of the disease region using the first medical image and the second medical image (hereinafter referred to as the region estimation display process) will be described with reference to FIG. 4.

[0055] FIG. 4 is a flowchart showing an example of the procedure of the region estimation display process. Hereinafter, for the sake of specific description, the imaging site is the brain of the subject as described above, the first medical image is a diffusion-weighted image, and the second medical image is an MRA image. Also, the first medical image and the second medical image are assumed to have been generated in advance by MR imaging of the subject prior to the implementation of the region estimation display process.

[0056] (Region Estimation Display Process) (Step S401) The processing circuit 34 acquires the first medical image and the second medical image from the medical image diagnostic apparatus (MRI apparatus) 10 or the image storage apparatus 20 by the acquisition function 34a. The acquisition function 34a stores the first medical image and the second medical image in the memory 33.

[0057] (Step S402) The processing circuit 34 detects a disease candidate region in the imaging site of the first medical image based on the first medical image by the first detection function 34b. Hereinafter, for the sake of specific description, it is assumed that a plurality of regions are detected as the disease candidate regions. The first detection function 34b stores the detected plurality of disease candidate regions in the memory 33.

[0058] (Step S403) The processing circuit 34 detects a stenosis site in the imaging site of the second medical image, that is, a vascular territory located downstream of the stenosis position, based on the second medical image by the second detection function 34c. Note that the second detection function 34c may detect the degree of stenosis of the blood vessel at the position of stenosis in the stenosis site based on the stenosis site in the second medical image. The second detection function 34c stores the detected stenosis site and the degree of stenosis in the memory 33 in association with the second medical image.

[0059] (Step S404) The processing circuit 34 estimates the probability of a disease for the disease candidate region based on the disease candidate region and the stenosis site by means of the estimation function 34d. For example, the estimation function 34d estimates the probability of a disease (false positive, non-false positive (true positive), disease certainty, etc.) in the disease candidate region for each of the plurality of disease candidate regions. Thereby, the estimation function 34d associates the plurality of disease candidate regions with the probability of the disease and the first medical image, and stores them in the memory 33 as the disease region.

[0060] (Step S405) The processing circuit 34 causes the display control function 34e to superimpose the disease region (disease area) related to the probability and the second medical image on the first medical image and display them on the display 32. That is, the display 32 displays a superimposed image in which the disease region and the second medical image are superimposed on the first medical image. At this time, the display control function 34e may further superimpose the stenosis site on the superimposed image and display it on the display 32. At this time, the display control function 34e may further superimpose the stenosis position (including the occlusion position) on the superimposed image and display it on the display 32.

[0061] FIG. 5 is a diagram showing an example of the second medical image MI2, the disease region DR, and the stenosis site SP superimposed on the first medical image MI1. The first medical image MI1 in FIG. 5 corresponds to a DWI image. The second medical image MI2 in FIG. 5 corresponds to an MRA image. As shown in FIG. 5, the disease region DR in the first medical image MI1 includes the stenosis site SP.

[0062] Further, the processing circuit 34 may change the display mode of the disease region DR according to a binary value (for example, whether it is a false positive) corresponding to the probability by means of the display control function 34e, and display the superimposed image on the display 32. At this time, the display 32 displays the disease region DR in a display mode corresponding to the binary value corresponding to the probability in the superimposed image.

[0063] FIG. 6 is a diagram showing an example of a second medical image MI2 superimposed on a first medical image MI1, and three disease regions DR1, DR2, DR3 and a stenosis site SP in display modes according to the certainty binary values. The first medical image MI1 in FIG. 6 corresponds to a DWI image. The second medical image MI2 in FIG. 6 corresponds to an MRA image. The first disease region DR1 indicates a disease region corresponding to a non-false positive (true positive). Also, the second disease region DR2 and the third disease region DR3 indicate disease regions corresponding to false positives. As shown in FIG. 6, the line type of the frame line indicating the first disease region DR1 is displayed as a solid line. On the other hand, the line types of the frame lines indicating the second disease region DR2 and the third disease region DR3 are shown as dotted lines.

[0064] Further, the processing circuit 34 may change the display mode of the disease region DR according to the degree of certainty (for example, the probability of the disease) by the display control function 34e, and display the superimposed image on the display 32. At this time, the display 32 displays the disease region DR in a display mode according to the probability of the disease in the superimposed image.

[0065] FIG. 7 is a diagram showing an example of a second medical image MI2 superimposed on a first medical image MI1, and three disease regions DR1, DR2, DR3 and a stenosis site SP in display modes according to the degree of certainty. The first medical image MI1 in FIG. 7 corresponds to a DWI image. The second medical image MI2 in FIG. 7 corresponds to an MRA image. The first disease region DR1 indicates the disease region with the highest probability. Also, the second disease region DR2 indicates the disease region with the lowest probability. Also, the third disease region indicates a disease region with a medium probability, for example, a probability lower than that of the first disease region DR1 and higher than that of the second disease region DR2.

[0066] Also, as shown in FIG. 7, the line types of the frame lines indicating the first disease region DR1, the line types of the frame lines indicating the second disease region DR2, and the line types of the frame lines indicating the third disease region DR3 are all different. Also, although not shown in FIG. 7, the probability may be displayed in the vicinity of the three disease regions DR1, DR2, and DR3.

[0067] In addition, as an application example of this embodiment, when the imaging site is the brain of a subject, after the process of step S405, based on the result of the region estimation display process (for example, the superimposed image displayed on the display 32 in step S405), automatic determination of left and right infarcts (unilateral infarcts) or bilateral infarcts in the brain may be performed.

[0068] The medical image processing apparatus 30 according to the embodiment described above acquires a first medical image MI1 collected by a predetermined imaging of an imaging site of a subject and a second medical image MI2 collected by an imaging different from the predetermined imaging and including blood vessels related to the imaging site, detects a disease candidate region indicating a candidate for a disease region in the imaging site based on the first medical image MI1, detects a stenosis site related to stenosis of a blood vessel based on the second medical image MI2, estimates the probability of a disease for the disease candidate region based on the disease candidate region and the stenosis site, and superimposes and displays the disease region related to the probability and the second medical image on the first medical image.

[0069] In the medical image processing apparatus 30 according to the embodiment, the estimated probability is, for example, higher when the stenosis site and the disease candidate region overlap than when they do not overlap. In the medical image processing apparatus 30 according to the embodiment, the stenosis site is a region where blood vessels are distributed downstream from the stenosis position, and the disease region is included in the stenosis site. Also, in the medical image processing apparatus 30 according to the embodiment, the first medical image and the second medical image are, for example, images captured at different timings for the subject. Also, in the medical image processing apparatus 30 according to the embodiment, the first medical image MI1 is, for example, a diffusion-weighted image, and the second medical image MI2 is, for example, a magnetic resonance angiogram.

[0070] When the size of the overlapping region between the stenosis site and the disease candidate region is less than a predetermined value, the medical image processing apparatus 30 according to the embodiment estimates that the disease candidate region is a false positive as the probability, and when the size of the overlapping region is greater than or equal to the predetermined value, the medical image processing apparatus 30 estimates that the disease candidate region is not a false positive as the probability, and displays the boundary line (frame line) of the disease region corresponding to the false positive and the boundary line (frame line) of the disease region corresponding to the non-false positive in different display modes. Further, the medical image processing apparatus 30 according to the embodiment detects the degree of stenosis of the blood vessel at the position of the stenosis, and estimates the probability of the disease corresponding to the probability based on the size of the overlapping region between the stenosis site and the disease candidate region and the degree of stenosis, and displays the boundary line (frame line) of the disease region in a display mode corresponding to the probability.

[0071] From these, according to the medical image processing apparatus 30 according to the embodiment, in the second medical image obtained by imaging the same imaging site as the first medical image used for detecting the disease candidate region in the imaging site, the location where the blood vessel is stenosed (including occlusion) is specified, and considering the dominant region of the blood vessel, the disease region corresponding to the stenosis site can be narrowed down from the disease candidate region. For example, according to the medical image processing apparatus 30 according to the embodiment, based on the occlusion (stenosis) location of the blood vessel, the correctness (probability of the disease) of the extracted disease candidate region can be determined (estimated). Specifically, according to the medical image processing apparatus 30 according to the embodiment, based on the dominant region of the blood vessel (PCA, MCA, ACA, left and right), the probability of the disease in the extracted disease candidate region can be determined.

[0072] For example, according to the medical image processing apparatus 30 according to the embodiment, if there is no abnormality in the blood vessels (no stenosis site) in the extracted disease candidate region, the extracted disease candidate region can be treated as a false positive. Further, according to the medical image processing apparatus 30 according to the embodiment, if the state of the blood vessel is stenosis rather than occlusion, the probability of the disease in the extracted disease candidate region can be reduced compared to the case of occlusion. Further, according to the medical image processing apparatus 30 according to the embodiment, as the second medical image used to grasp the state of the blood vessels in the imaging region, a plurality of types (MRA image, CTA image, angiogram image, etc.) can be used. Further, according to the medical image processing apparatus 30 according to the embodiment, a non-contrast CT image may be used as the first medical image MI1 and an MRI image may be used as the second medical image MI2, or a DWI image may be used as the first medical image MI1 and a CTA image may be used as the second medical image MI2. As a combination of the first medical image MI1 and the second medical image MI2, medical images collected by different modalities can be used.

[0073] FIG. 8 is a diagram showing an example of a comparative example. In FIG. 8, two disease candidate regions DCR2 and DCR3 indicated by arrows are displayed in the same display mode (line type) as the other disease candidate region DCR1. In addition, in FIG. 8, the second medical image MI2 is not superimposed on the first medical image MI1 and is not used for estimating the probability of the disease for the disease candidate regions DCR1, DCR2, and DCR3. In FIG. 8, the user needs to judge the probability of the disease candidate region only from the first medical image MI1.

[0074] On the one hand, according to the medical image processing apparatus 30 according to the present embodiment, as shown in FIGS. 5 to 7, the second medical image MI2 superimposed on the first medical image MI1, the disease region DR, and the stenosis site SP can be displayed. In FIG. 5 compared to FIG. 8, the disease candidate regions DCR2 and DCR3 estimated to be false positives are not displayed, and the second medical image MI2 is displayed together with the stenosis site SP. Further, in FIG. 6 compared to FIG. 8, the disease candidate regions DCR2 and DCR3 estimated to be false positives and the disease candidate region DCR1 estimated to be non-false positive (true positive) are displayed in different line types, and the second medical image MI2 is displayed together with the stenosis site SP. Further, in FIG. 7 compared to FIG. 8, the three disease candidate regions DCR1, DCR2, and DCR3 are displayed in line types according to the probability indicating the likelihood of the disease, and the second medical image MI2 is displayed together with the stenosis site SP.

[0075] According to the medical image processing apparatus 30 according to the embodiment, as shown in FIG. 5, compared to FIG. 8 of the comparative example, since the stenosis site SP is superimposed on the first medical image MI1 together with the second medical image MI2 that is the basis for estimating the likelihood of the disease, the user can easily grasp the positional relationship between the disease region and the stenosis site. Further, according to the medical image processing apparatus 30 according to the embodiment, as shown in FIG. 6, compared to FIG. 8 of the comparative example, the user can easily grasp the likelihood of the disease in a plurality of disease regions. Further, according to the medical image processing apparatus 30 according to the embodiment, as shown in FIG. 7, compared to FIG. 8 of the comparative example, the user can easily grasp the degree of the likelihood of the disease in a plurality of disease regions.

[0076] From the above, according to the medical image processing apparatus 30 according to the embodiment, by estimating the likelihood of the disease in the region that is a candidate for the disease using the region related to the stenosis in the imaging site, the likelihood of the disease in the disease region can be presented to the user. Thereby, according to the medical image processing apparatus 30 according to the embodiment, since the qualitative judgment by the user can be reduced, the accuracy of the examination for the subject can be improved, and the throughput of the examination can be improved.

[0077] (First Modified Example) In this modified example, when a catheter is selected as a treatment policy for a disease, the type of catheter to be used in the treatment is estimated based on the degree of stenosis and the shape of the blood vessel, and the estimated catheter type is displayed. For example, when a catheter is selected for the treatment of a disease at the imaging site of a subject according to a user's instruction via the input interface 31, the processing circuit 34 estimates (identifies) the type of catheter to be used for the treatment of the imaging site based on the degree of stenosis and the shape of the blood vessel by the estimation function 34d. At this time, the estimation function 34d may also be referred to as an identification unit. The types of catheters are classified, for example, by the thickness of the catheter and the shape of the curve at the tip of the catheter.

[0078] Specifically, the estimation function 34d reads out a correspondence table of catheter types for the degree of stenosis (e.g., stenosis rate) and the shape of a blood vessel of a predetermined length including the position of stenosis (e.g., the degree of curvature of the blood vessel) from the memory 33. The predetermined length is preset, such as several centimeters or several millimeters. Next, the second detection function 34c detects the degree of stenosis and the shape of the blood vessel related to the stenosis based on the MRA (Magnetic Resonance Angiography). Since known image processing techniques can be applied to the detection of the shape of the blood vessel, the description thereof is omitted. The estimation function 34d identifies the type of catheter by comparing the detected degree of stenosis and the shape of the blood vessel with the correspondence table.

[0079] The display 32 displays the estimated catheter type. At this time, the display 32 may further display a superimposed image in which the MRA image is superimposed on the DWI image.

[0080] According to the medical image processing apparatus 30 according to the first modified example of the embodiment, when a catheter is selected as a treatment policy for a disease, the type of catheter suitable for the treatment can be notified to the user. Thereby, according to the medical image processing apparatus 30 according to the first modified example of the embodiment, the selection of a catheter suitable for the treatment by the user becomes simple, and the throughput related to the treatment of the subject can be improved.

[0081] (Second Modification Example) In this modification example, in order to align the second medical image (MRA image) with the fluoroscopic image at the imaging site of the subject and superimpose the second medical image on the fluoroscopic image, the second medical image is transmitted to an X-ray angiography apparatus (X-ray angio apparatus). Prior to performing X-ray fluoroscopy on the subject, the processing circuit 34 transmits the second medical image (MRA image) to the X-ray angiography apparatus. The processing circuit 34 that transmits the second medical image (MRA image) to the X-ray angiography apparatus corresponds to the transmission unit.

[0082] The X-ray angiography apparatus generates a fluoroscopic image by performing fluoroscopic imaging on the subject. Next, the X-ray angiography apparatus performs alignment between the MRA image and the fluoroscopic image. Since the alignment can be realized by a known method, the description thereof is omitted. The X-ray angiography apparatus superimposes the MRA image after alignment on the fluoroscopic image at a predetermined transparency and displays it on a display (not shown).

[0083] According to the medical image processing apparatus 30 according to the second modification example of the embodiment, in fluoroscopic imaging of a subject, the MRA image can be superimposed on the fluoroscopic image at a predetermined transparency and displayed on the display. Thereby, according to the medical image processing apparatus 30 according to the second modification example of the embodiment, in fluoroscopic imaging of a subject, for example, when using a catheter, the throughput regarding the treatment of the subject can be improved.

[0084] (Third Modification Example) In this modified example, an imaging of the imaging site after the treatment of the disease of the subject is performed to obtain a third medical image (MRA image) including blood vessels related to the imaging site, and the position of the stenosis site is indicated to display the third medical image (hereinafter referred to as the post-treatment MRA image). For example, the processing circuit 34 obtains, by the acquisition function 34a, a third medical image (MRA image) including blood vessels related to the imaging site by imaging the imaging site after the treatment of the disease of the subject from the medical image diagnostic apparatus (MRI apparatus) 10 or the image storage apparatus 20. At this time, the processing circuit 34 may cause the display control function 34e to superimpose the second medical image on the third medical image and display it on the display 32.

[0085] The display 32 displays the third medical image indicating the position of the stenosis site. Further, the display 32 displays the third medical image and the second medical image so as to be comparable. For example, the display 32 superimposes and displays the second medical image on the third medical image. At this time, the second medical image has a predetermined transparency. Note that the display 32 may display the third medical image and the second medical image in parallel. Further, the display 32 may display a difference image between the third medical image and the second medical image.

[0086] Accordingly, according to the medical image processing apparatus 30 according to the third modified example of the embodiment, the post-treatment MRA image can be displayed on the display 32 indicating the position of the stenosis site. Further, according to the medical image processing apparatus 30 according to the third modified example of the embodiment, the post-treatment MRA image and the pre-treatment MRA image can be displayed so as to be comparable. Therefore, according to the medical image processing apparatus 30 according to the third modified example of the embodiment, the user can easily grasp the effect of the treatment of the stenosis site in the post-treatment MRA image.

[0087] (Fourth Modified Example) This modification example is to obtain a fourth medical image by imaging the imaging site after the treatment of the disease, estimate the degree of reduction of the disease area based on the first medical image and the fourth medical image, and estimate and display the timing of the rehabilitation of the subject based on the degree of reduction of the disease area. For example, the processing circuit 34 obtains a fourth medical image by imaging the imaging site of the subject after the treatment of the disease through the acquisition function 34a. When the first medical image is an extended image, the fourth medical image corresponds to a diffusion-weighted image of the imaging site after the treatment.

[0088] The processing circuit 34 estimates the degree of reduction of the disease area of the imaging site based on the first medical image and the fourth medical image through the estimation function 34d. For example, the estimation function 34d calculates the ratio of the disease area in the first medical image to the disease area in the first medical image. If the ratio is 1 or less, the ratio corresponds to the reduction rate of the disease area. That is, the degree of reduction of the disease area corresponds to the reduction rate.

[0089] The processing circuit 34 estimates the timing of the rehabilitation of the subject based on the degree (reduction rate) of reduction through the estimation function 34d. For example, the estimation function 34d estimates the timing of the rehabilitation by comparing a preset threshold value with the reduction rate. That is, the estimation function 34d estimates the start timing of the rehabilitation based on the effect after the treatment.

[0090] The display 32 displays the estimated start timing of the rehabilitation. At this time, the display 32 may further display the first medical image and the fourth medical image. Also, the display 32 may display an image in which the fourth medical image is superimposed on the first medical image. Also, the display 32 may further display the degree of reduction of the disease area.

[0091] From these, according to the medical image processing apparatus 30 according to the fourth modification of the embodiment, it is possible to estimate and display the start timing of rehabilitation based on medical images (for example, diffusion-weighted images) before and after treatment. Therefore, according to the medical image processing apparatus 30 according to the fourth modification of the embodiment, the user can easily grasp the start timing of rehabilitation.

[0092] When the technical idea in the present embodiment is realized by a medical image processing method, the medical image processing method acquires a first medical image collected by a predetermined imaging of an imaging site of a subject and a second medical image collected by an imaging different from the predetermined imaging and including blood vessels related to the imaging site, detects a disease candidate region indicating a candidate for a disease region in the imaging site based on the first medical image, detects a stenosis site related to the stenosis of the blood vessels based on the second medical image, estimates the probability of the disease for the disease candidate region based on the disease candidate region and the stenosis site, and superimposes and displays the disease region related to the probability and the second medical image on the first medical image. The processing procedure in the medical image processing method conforms to the procedure of the region estimation display processing. Also, the effects of the medical image processing method are the same as those of the embodiment. From these, the description of the processing procedure and effects of the region estimation display processing in the medical image processing method is omitted.

[0093] When the technical idea in the embodiment is realized by a medical image processing program, the medical image processing program causes a computer to acquire a first medical image collected by a predetermined imaging of an imaging site of a subject and a second medical image collected by an imaging different from the predetermined imaging and including blood vessels related to the imaging site, detect a disease candidate region indicating a candidate for a disease region in the imaging site based on the first medical image, detect a stenosis site related to the stenosis of the blood vessels based on the second medical image, estimate the probability of the disease for the disease candidate region based on the disease candidate region and the stenosis site, and superimpose and display the disease region related to the probability and the second medical image on the first medical image.

[0094] For example, by installing an image processing program on a computer such as the medical image processing apparatus 30, the medical image diagnostic apparatus 10, and / or the image storage apparatus (PACS server) 20 shown in FIG. 1 and deploying them in the memory, the region estimation display process can also be realized. At this time, a program that can execute the process on the computer can also be stored in a storage medium such as a magnetic disk (such as a hard disk), an optical disk (such as a CD-ROM, DVD), or a semiconductor memory and distributed. Further, the distribution of the medical image processing program is not limited to the above media, and for example, it may be distributed using a telecommunication function such as downloading via the Internet. The processing procedure in the medical image processing program conforms to the region estimation display process. Further, the effects of the medical image processing program are the same as those in the embodiment. For these reasons, the description of the processing procedure and effects of the region estimation display process in the medical image processing program is omitted.

[0095] Note that the technical features in this embodiment can be realized by, for example, an MRI apparatus. At this time, the processing circuit mounted on the console in the MRI apparatus will have the acquisition function 34a, the first detection function 34b, the second detection function 34c, the estimation function 34d, and the display control function 34e shown in FIG. 1. At this time, the MRI apparatus realizes the region estimation display process. The processing procedure in the MRI apparatus that realizes the acquisition function 34a, the first detection function 34b, the second detection function 34c, the estimation function 34d, and the display control function 34e conforms to the region estimation display process of the embodiment. Further, the effects of the MRI apparatus are the same as those in the embodiment. For these reasons, the description of the processing procedure and effects of the region estimation display process in the MRI apparatus is omitted.

[0096] According to at least the embodiments described above, it is possible to estimate the probability of a disease in a region that is a candidate for a disease using a region related to stenosis at the imaging site.

[0097] Although several embodiments have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, changes, and combinations of embodiments can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, as well as in the invention described in the claims and the equivalent scope thereof.

Explanation of Reference Numerals

[0098] 1 Medical image processing system 10 Medical image diagnostic device 20 Image storage device 30 Medical image processing device 31 Input interface 32 Display 33 Memory 34 Processing circuit 34a Acquisition function 34b First detection function 34c Second detection function 34d Estimation function 34e Display control function

Claims

1. an acquisition unit that acquires a first medical image acquired by a predetermined imaging of an imaging region of a subject and a second medical image acquired by an imaging different from the predetermined imaging and including blood vessels related to the imaging region; a first detection unit that detects a disease candidate region indicating a candidate of a disease region in the imaging region based on the first medical image; a second detection unit that detects a stenosis site related to a stenosis of the blood vessel based on the second medical image; an estimation unit that estimates a likelihood of the disease for the disease candidate region based on the disease candidate region and the stenosis site; a display unit that displays the disease region related to the likelihood and the second medical image in a superimposed manner on the first medical image; A medical image processing device comprising:

2. The likelihood is higher when the stenosis site and the disease candidate region overlap than when the stenosis site and the disease candidate region do not overlap. The medical image processing device according to claim 1 .

3. When the size of the overlapping region between the stenosis site and the disease candidate region is less than a predetermined value, the estimation unit estimates that the disease candidate region is a false positive as the likelihood, When the size of the overlapping region is equal to or larger than a predetermined value, the estimation unit estimates that the disease candidate region is a non-false positive as the likelihood, the display unit displays a boundary line of the disease region corresponding to the false positive and a boundary line of the disease region corresponding to the non-false positive in different display modes. The medical image processing device according to claim 2 .

4. The stenosis site is a region where blood vessels are distributed downstream from the position of the stenosis, The diseased area is included in the stenosis site, The medical image processing device according to claim 1 .

5. The second detection unit detects a degree of stenosis of a blood vessel at a position of the stenosis, the estimation unit estimates a degree of certainty of the disease corresponding to the likelihood based on a size of an overlapping region between the stenosis site and the disease candidate region and a degree of the stenosis; The display unit displays a boundary line of the disease area in a display mode according to the accuracy. The medical image processing device according to claim 4 .

6. The first medical image and the second medical image are images captured at different times with respect to a subject. The medical image processing device according to claim 1 .

7. The first medical image is a diffusion weighted image, The second medical image is a magnetic resonance vascular image. The medical image processing apparatus according to claim 1 .

8. When a catheter is selected as the treatment for the disease, the estimation unit estimates a type of the catheter based on the degree of the stenosis and the shape of the blood vessel; The display unit displays the estimated type of the catheter. The medical image processing device according to claim 5 .

9. a transmitting unit configured to transmit the second medical image to an X-ray angiography apparatus in order to align the second medical image with a fluoroscopic image of the imaging site of the subject and superimpose the second medical image on the fluoroscopic image. The medical image processing device according to claim 1 .

10. the acquisition unit acquires a third medical image including the blood vessels related to the imaging site by imaging the imaging site after treatment of the disease; The display unit displays the third medical image, indicating the position of the stenosis site. The medical image processing device according to claim 5 .

11. The display unit displays the third medical image and the second medical image in a comparative manner. The medical image processing device according to claim 10.

12. the acquisition unit acquires a fourth medical image by imaging the imaging region after treatment of the disease; The estimation unit is Estimating a degree of reduction in the disease area based on the first medical image and the fourth medical image; Predicting the timing of rehabilitation for the subject based on the degree of the decrease; The display unit displays the timing of the rehabilitation. The medical image processing device according to claim 5 .

13. Obtaining a first medical image acquired by a predetermined imaging of an imaging region of a subject, and a second medical image acquired by an imaging method different from the predetermined imaging and including blood vessels related to the imaging region; detecting a disease candidate region indicating a candidate region of a disease in the imaging region based on the first medical image; Detecting a stenosis site related to a stenosis of the blood vessel based on the second medical image; estimating a likelihood of the disease for the disease candidate region based on the disease candidate region and the stenosis site; displaying the region of the disease related to the likelihood and the second medical image in a superimposed manner on the first medical image; A medical image processing method comprising:

14. On the computer, Obtaining a first medical image acquired by a predetermined imaging of an imaging region of a subject, and a second medical image acquired by an imaging method different from the predetermined imaging and including blood vessels related to the imaging region; detecting a disease candidate region indicating a candidate region of a disease in the imaging region based on the first medical image; Detecting a stenosis site related to a stenosis of the blood vessel based on the second medical image; estimating a likelihood of the disease for the disease candidate region based on the disease candidate region and the stenosis site; displaying the disease region related to the likelihood and the second medical image in a superimposed manner on the first medical image; A medical image processing program that makes this possible.

Images