JP5599683B2 - Medical image processing apparatus and medical image processing method - Google Patents

Description

  The present invention relates to a medical image processing apparatus that extracts an organ region from a medical image.

Conventionally, an image processing method for extracting only a desired organ region from a medical image acquired by a medical imaging apparatus such as an X-ray CT apparatus, an MRI apparatus, or an ultrasonic diagnostic apparatus is known.
For example, in Patent Document 1, a feature amount of an image is calculated based on the density of each pixel, and the portion is recognized by comparing the calculated feature amount with a feature amount of each portion stored in advance. (See paragraph [0031] of Patent Document 1). Further, in Patent Document 1, anatomical charts used for comparison with medical images, and attribute information in which attributes representing the contents of each anatomical chart are recorded together are held (see paragraph [0026] of Patent Document 1). It describes that an anatomical chart in which a part recognized by matching and a part recorded in attribute information match is searched (see paragraph [0044] of Patent Document 1).

JP 2008-73397 A

However, there are individual differences in the size and shape of the organ, and recording a template such as a feature value or an anatomical chart that matches all subjects requires a huge recording capacity.
Further, even for the same organ, the pixel value indicating the organ region generally differs for each imaging. For example, when a liver is extracted from an abdominal tomographic image acquired by an X-ray CT apparatus, the CT value indicating the liver region varies depending on the adjustment status of the apparatus and imaging conditions. When using a template such as a feature quantity or an anatomical chart calculated statistically to absorb these differences, the matching rate is reduced, so that accurate organ region extraction cannot be performed.

  The present invention has been made in view of the above-described problems, and an object of the present invention is to reduce the amount of data to be stored for extracting an organ region and accurately extract the organ region. It is to provide a medical image processing apparatus and the like.

In order to achieve the above-described object, a first invention is a medical image processing apparatus for extracting an organ region from a medical image, wherein each organ is a region associated with the organ in the region of the medical image. Storage means for storing a division condition for dividing into a first divided area and a second divided area excluding the first divided area, and the medical image divided based on the dividing condition Determining means for determining a threshold for extracting an organ region so that the number of pixels included in the first divided region is maximum and the number of pixels included in the second divided region is minimum And an extraction unit that performs threshold processing according to the threshold determined by the determination unit and extracts an organ region of the medical image.
A second invention is a medical image processing apparatus that extracts an organ region from a medical image, and for each organ, a first divided region that is a region associated with the organ in the region of the medical image; Storage means for storing a division condition to be divided into a second division area that is an area excluding the first division area, and the first medical image divided based on the division condition, Determining means for determining a threshold for extracting an organ region so that a value obtained by dividing the number of pixels included in the divided region by the number of pixels included in the second divided region is maximized; and The medical image processing apparatus includes: an extraction unit that performs threshold processing according to the determined threshold and extracts an organ region of the medical image.

A third invention is a medical image processing method for extracting an organ region from a medical image, and for each organ, a first divided region that is a region associated with the organ in the region of the medical image; The number of pixels included in the first divided area is the maximum for the medical image divided based on the division condition to be divided into the second divided area that is an area excluding the first divided area , And determining a threshold for extracting an organ region so that the number of pixels included in the second divided region is minimized, and performing threshold processing according to the threshold determined by the determining step, And a extracting step of extracting an organ region of the medical image.

  According to the present invention, it is possible to provide a medical image processing apparatus or the like that can reduce the amount of data stored for extracting an organ region and can accurately extract the organ region.

The figure which shows schematic structure of the image processing system 1 The figure which shows an example of the division | segmentation of the medical image 2 The figure which shows an example of the division | segmentation of the medical image 2 The figure which shows an example of the division | segmentation of the medical image 2 The figure which shows an example of the division | segmentation condition table 51 Figure showing an example of an organ selection screen Flow chart showing an example of organ region extraction processing Figure showing an example of an organ selection screen Flow chart showing an example of organ region extraction processing

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
First, the configuration of a medical image processing system 1 to which the medical image processing apparatus 3 of the present invention is applied will be described with reference to FIG.
As shown in FIG. 1, a medical image processing system 1 is installed in a hospital or the like, and a medical image processing device 3, a medical image photographing device 5, an image database 7, and the like are connected via a network 9.

The medical image processing apparatus 3 is a computer that performs image processing of medical images.
The medical image processing apparatus 3 includes a CPU (Central Processing Unit) 11, a main memory 12, a storage device 13, a communication interface (communication I / F) 14, a display memory 15, a controller 16, a display device 17, a mouse 18, a keyboard 19, and the like. Each part is connected via a bus 20.

  The CPU 11 calls a program stored in the main memory 12 or the storage device 13 to a work memory area on the RAM of the main memory 12 and executes the program, drives and controls each unit connected via the bus 20, and performs medical image processing. Various processes performed by the device 3 are realized. Moreover, CPU11 performs an organ area | region extraction process in embodiment of this invention.

  The main memory 12 includes a ROM (Read Only Memory), a RAM (Access Memory), and the like. The ROM permanently holds a computer boot program, a program such as BIOS, data, and the like. The RAM temporarily stores programs, data, and the like loaded from the ROM, the storage device 13, and the like, and includes a work area that the CPU 11 uses to perform various processes.

  The storage device 13 is a device that reads / writes data to / from an HDD (hard disk drive) or other recording medium, and stores a program executed by the CPU 11, data necessary for executing the program, an OS (operating system), and the like. . As for the program, a control program corresponding to the OS and an application program for executing processing to be described later are stored. Each of these program codes is read by the CPU 11 as necessary, transferred to the RAM of the main memory 12, and executed as various means.

  The communication I / F 14 includes a communication control device, a communication port, and the like, and mediates communication between the medical image processing device 3 and the network 9. The communication I / F 14 controls communication with the image database 7, another computer, the medical image photographing device 5, and the like via the network 9.

The display memory 15 is a buffer that temporarily accumulates display data input from the CPU 11. The accumulated display data is output to the display device 17 at a predetermined timing.
The display device 17 includes a display device such as a liquid crystal panel and a CRT monitor, and a logic circuit for executing display processing in cooperation with the display device, and is connected to the CPU 11 via the display memory 15. The display device 17 displays the display data stored in the display memory 15 on the display device under the control of the CPU 11.

The controller 16 is an interface for connecting the mouse 18 to the bus 20 and transmits / receives data to / from the mouse 18.
The mouse 18 and the keyboard 19 are input devices, and receive data from the user and input data.
The user interactively operates the medical image processing apparatus 3 using the display device 17, the mouse 18, the keyboard 19, and the like.

  The network 9 includes various communication networks such as a LAN (Local Area Network), a WAN (Wide Area Network), an intranet, and the Internet, and mediates communication connection between the medical image processing device 3, the medical image photographing device 5, the image database 7, and the like. To do.

The image database 7 accumulates and stores medical images taken by the medical image photographing device 5, and is provided in, for example, a server such as a hospital or a medical center.
In the image processing system 1 shown in FIG. 1, the image database 7 is configured to be connected to the medical image processing apparatus 3 via the network 9, but the image database 7 is provided in the storage device 13 of the medical image processing apparatus 3. May be.
The medical image photographing apparatus 5 is an X-ray CT apparatus, an MRI apparatus, an ultrasonic diagnostic apparatus, or the like, and photographs an image used for medical diagnosis.

Next, data stored in the storage device 13 in the embodiment of the present invention will be described with reference to FIGS.
In the embodiment of the present invention, the medical image processing apparatus 3 extracts a pixel group indicating a desired organ, that is, a desired organ region from the medical image by threshold processing. In the embodiment of the present invention, the threshold for extracting an organ region is determined for each medical image, not a value stored in advance. In order to determine a threshold value for each medical image, the medical image processing apparatus 3 stores only rough information about where each organ exists in the storage device 13. More precisely, in a region of a medical image, a region associated with each organ (hereinafter referred to as “first divided region”) and a region excluding the first divided region (hereinafter referred to as “second segment”). The division condition for dividing into “divided areas” is stored in the storage device 13.
Then, the medical image processing device 3 determines a threshold for extracting the organ region so that the number of pixels included in the first divided region is the maximum and the number of pixels included in the second divided region is the minimum. To do.
The organ region extracted by the embodiment of the present invention includes not only organ regions such as liver, kidney and spleen but also tissue regions such as bone, fat and muscle.

2 to 4 show an example of the medical image 2 that is divided based on the division condition. The medical image 2 exemplified in the embodiment of the present invention is a tomographic image of the abdomen taken and reconstructed by an X-ray CT apparatus. However, the technical idea of the present invention is not applied only to the medical image 2, and if the pixel values have a certain distribution, the apparatus, imaging conditions, imaging locations, image processing conditions (tomographic image) If so, it can be applied regardless of the direction and position of the tomographic plane, for example.
The division conditions are (1) a division method for defining a division reference point, a division line, a division coordinate system, a division reference figure, etc. for dividing the medical image 2, and (2) a plurality of division areas divided by the division method. Specific conditions for specifying the first divided region are included.

FIG. 2 shows an example of the division condition when extracting the liver.
The division condition in FIG. 2A is a division method “division by two straight lines 22a and 23a orthogonal to each other, with the division reference point passing through the division reference point and the division line passing through the division reference point” and the specific condition “division” Defined by region B ". That is, the first divided area is the divided area B, and the second divided areas are the divided areas A, C, and D.
The coordinates of the center of gravity 21a of the abdominal region serving as the division reference point are calculated by the medical image processing device 3 for each medical image 2 using a known technique (edge extraction processing). For example, the medical image processing apparatus 3 extracts the boundary between the abdomen and the air by the edge extraction process, sets the pixel group indicating the inside of the abdomen as the abdomen region, and calculates the coordinates of the center of gravity 21a. The process of extracting the boundary between the abdomen and the air can be accurately performed by a known technique without storing feature amounts or the like in advance.

As can be seen from FIG. 2 (a), since there are many pixels indicating the liver in the divided region B and few pixels indicating the liver in the divided regions A, C, and D, the divided region B (the first divided region) The threshold value is determined so that the number of pixels included in the region) is maximum and the number of pixels included in the divided regions A, C, and D (second divided regions) is minimum, and threshold processing is performed using the determined threshold value. By performing the above, it is possible to extract the liver region.
Since the center of gravity 21a of the abdominal region is divided, the division condition can be uniformly defined and stored in the storage unit 13 regardless of individual differences in organ size and shape caused by sex, age, and the like. it can.

The threshold value determination process described above can be formulated as follows.
Consider two cases where the threshold is an upper limit and a lower limit. T (T1, T2) (T1 <T2): threshold, pi (i = 1,..., N): pixel values of pixels included in the first divided region, qj (j = 1,..., n): pixel value of pixels included in second divided region, s1 = {total number of pixels satisfying T1 ≦ pi ≦ T2}, s2 = {total number of pixels satisfying T1 ≦ qj ≦ T2} “Determining the threshold value so that the number of pixels included in one divided region is the maximum and the number of pixels included in the second divided region is the minimum” means “s1 / s2 (included in the first divided region) “T1 and T2 that maximize the value obtained by dividing the number of pixels by the number of pixels included in the second divided region)” can be formulated.

Note that a part of the medical image 2 may be extracted before performing the threshold determination process. For example, the boundary between the abdomen and air is extracted by a known technique, only the pixel group indicating the inside of the abdomen is extracted, and the pixel (pixels indicating air) outside the abdomen is excluded from the threshold determination process. It is also good.
In a special case such as when the first area is substantially equal to the entire area of the medical image 2, the threshold value may be determined so that the number of pixels included in the first divided area is maximized. The threshold value may be determined so that the number of pixels included in the second divided region is minimized. That is, T1 and T2 that maximize s1 may be obtained, or T1 and T2 that minimize s2 may be obtained.

The division condition in FIG. 2B is a division method “division by two straight lines 22b and 23b orthogonal to each other, with a division reference point passing through the division center point 21b and a division line passing through the division reference point”, a specific condition “division” Defined by region F ". That is, the first divided area is the divided area F, and the second divided areas are the divided areas E, G, and H.
The coordinates of the center of gravity 21b of the spinal region that is the division reference point are calculated by the medical image processing device 3 for each medical image 2 by a known technique. For example, the medical image processing apparatus 3 stores a general CT value range of bone in the storage device 13 and extracts a pixel group indicating bone. Next, the medical image processing apparatus 3 calculates an area for each region (hereinafter referred to as “connected region”) in which pixels indicating bone are connected, and a connected region (abdominal tomography) having an area corresponding to the spine. In the case of an image, the connected area having the largest area is defined as the spinal area. Then, the medical image processing apparatus 3 calculates the coordinates of the centroid 21b of the spinal region. Since the CT value of the bone has a large difference compared to other organs and tissues, the CT value range may be defined including errors caused by the adjustment status of the apparatus and imaging conditions. Further, for example, the medical image processing apparatus 3 may extract the spine region by threshold processing according to the embodiment of the present invention and calculate the coordinates of the centroid 21b of the spine region, as in the example of FIG. 3 to be described later. .
In FIG. 2 (b), since the centroid 21b of the spinal region is divided as a reference, the division conditions are uniformly defined and stored regardless of individual differences in organ size and shape caused by gender, age, and the like. It can be stored in the unit 13.

  Comparing FIG. 2A and FIG. 2B, it can be seen that there are more pixels indicating the liver in the divided region F than in the divided region B. However, depending on the slice position of the tomographic image (position in the body axis direction of the subject), the divided area B may have more pixels indicating the liver than the divided area F. Therefore, in the case of a tomographic image, the medical image processing device 3 may store the division condition in the storage device 13 for each slice position.

FIG. 3 shows angle division using the polar coordinate system as a divided coordinate system.
In FIG. 3A, the division reference point is the center of gravity 31 of the abdominal region. Consider a division by a polar coordinate system in which the division reference point is the origin, the position of the straight line 32 is the declination θ = 0 degrees, and the straight line 33 is the moving radius.
In the graph of FIG. 3B, the horizontal axis is “deflection angle θ”, and the vertical axis is “the number of pixels indicating a predetermined organ in the radial pixel group”. A solid line 34 indicates the number of pixels indicating the liver. A dotted line 35 indicates the number of pixels indicating the spine.
Since the solid line 34 has a peak when the angle θ is between 150 degrees and 190 degrees, in the case of the division method “division reference point is the center of gravity 31 of the abdominal region and angle division by the polar coordinate system with the division reference point as the origin” By defining the specific condition “deflection angle θ = 150 degrees to 190 degrees”, it becomes a division condition when the liver is extracted.
In addition, since the dotted line 35 has a peak when the angle θ is between 250 degrees and 190 degrees, in the case of the division method “the division reference point is the center of gravity 31 of the abdominal region and the angle division by polar coordinates with the division reference point as the origin” By defining the specific condition “deflection angle θ = 250 degrees to 290 degrees”, it becomes a division condition when extracting the spine.
In FIG. 3, since the center of gravity 31 of the abdominal region is divided, the division condition is uniformly defined regardless of individual differences in organ size and shape caused by gender, age, etc. Can be remembered.
Even in the case of angle division by polar coordinates as shown in FIG. 3, it goes without saying that the division reference point may be the center of gravity of the spinal region.

FIG. 4 shows an example of the division condition when extracting the spleen.
In FIG. 4, the division reference point is the center of gravity 41 of the abdominal region. Consider a division by a polar coordinate system in which the division reference point is the origin, the position of the straight line 42 is the declination θ = 0 °, and the straight lines 43 and 44 are the moving radius.
The division condition in FIG. 4 is a division method “division reference point is the center of gravity 41 of the abdominal region, angular division by polar coordinates with the division reference point as the origin, and division by two concentric circles 45 and 46 having the division reference point concentric”, Specific condition “declination θ = −30 degrees to 5 degrees and radius 0.8 × R0 to 1.0 × R0 (R0 is a radius of a circle approximating the inside of the abdomen (hereinafter referred to as“ divided reference circle ”)) ”.
The division reference circle is calculated by the medical image processing apparatus 3 for each medical image 2 using a known technique. For example, as in the case of FIG. 2A, the medical image processing apparatus 3 extracts the boundary between the abdomen and the air by the edge extraction process, and sets a pixel group indicating the inside of the abdomen as an abdominal region. Then, the radius R0 of the division reference circle is calculated from the area of the abdominal region using the circle formula.

  As can be seen from FIG. 4, the region (first divided region) specified by the above-described specific condition has many pixels indicating the spleen, and the other region (second divided region) has the spleen. Since the number of pixels shown is small, the threshold value is determined so that the number of pixels included in the first divided region is the maximum and the number of pixels included in the second divided region is the minimum, and threshold processing is performed using the determined threshold value By performing the above, the spleen region can be extracted.

In the example shown in FIG. 4, the inside of the abdomen is approximated by a circle and the division reference circle is defined. However, the division reference figure may be defined by approximation by other figures such as a polygon such as an ellipse or a rectangle. . The calculation process of the division reference graphic such as an ellipse or a polygon is the same as that for a circle.
Therefore, when the division condition of the example shown in FIG. 4 is more generalized, the division condition is the distance from the center of gravity of the division reference figure (in the example shown in FIG. 4, the radius of the concentric circle) or the direction (example shown in FIG. 4). If so, it may be determined according to the declination).
By dividing according to the distance or direction from the center of gravity of the division reference figure, the division condition is uniformly defined regardless of individual differences in organ size or shape caused by gender, age, etc. Can be remembered.

FIG. 5 shows a division condition table 51 that stores the aforementioned division conditions for each organ. The division condition table 51 is stored in the storage device 13. In the division condition table 51, one record is defined by an organ name, a division method, and a specific condition. In FIG. 5, the data contents are schematically shown as “organ 1, division method 1, specific condition 1”, etc. However, in actuality, in the example shown in FIG. The method is defined as “the division reference point is the center of gravity 21a of the abdominal region and the division line passes through the division reference point and is divided by two orthogonal straight lines 22a and 23a”, and the specific condition is defined as “division region B”.
Note that the division method may be common to a plurality of organs. Further, when the division method is common to a plurality of organs, the specific condition may be defined so that some regions overlap between the organs.

Next, an organ region extraction process performed by the medical image processing apparatus 3 will be described with reference to FIGS.
The organ region extraction process shown in FIGS. 6 and 7 executes the organ region extraction process by receiving the organ name of a desired extraction target organ.
As shown in FIG. 6, the CPU 11 of the medical image processing device 3 displays the medical image 2 on the display device 17 and also displays the organ list 61.
As shown in FIG. 7, the user moves the mouse pointer 62 displayed on the display device 17 using the mouse 18 or the like, and clicks one of the organ names from the organ list 61 to thereby obtain a desired extraction target. An organ name of the organ is input (S71).

Next, the CPU 11 searches the division condition table 51 of the storage device 13 using the organ name of the desired extraction target organ input in S71 as a search condition, and determines the division condition (division method and specific condition) (S72). .
Next, the CPU 11 has the maximum number of pixels included in the first divided region and / or included in the second divided region with respect to the medical image 2 divided based on the division condition determined in S72. A threshold for extracting an organ region is determined so that the number of pixels is minimized (S73).

Next, the CPU 11 performs threshold processing according to the threshold determined in S73, and extracts the organ region of the medical image 2 (S74).
Next, the CPU 11 stores the organ region extracted in S74 in the storage device 13 (S75).
Based on the stored organ area, the CPU 11 displays an outline of the organ area superimposed on the medical image 2 on the display device 17 or colors the organ area so that a desired extraction target organ area can be visually recognized. Or display. Further, the CPU 11 uses the stored organ area for other image processing.

The organ region extraction process shown in FIGS. 8 and 9 receives the position information of the extraction target organ in the medical image 2 to execute the organ region extraction process.
As shown in FIG. 8, the CPU 11 of the medical image processing device 3 displays the medical image 2 on the display device 17.
As illustrated in FIG. 9, the user moves the mouse pointer 81 displayed on the display device 17 using the mouse 18 or the like, and clicks in the medical image 2, whereby position information (x coordinate) of the extraction target organ , Y coordinate) is input (S91).

Next, the CPU 11 searches the division condition table 51 of the storage device 13 using the position information of the extraction target organ input in S91 as a search condition, and specifies the extraction target organ (S92). Specifically, the CPU 11 divides the medical image 2 based on the division condition stored in the division condition table 51, and the position information of the extraction target organ input in S91 is specified based on the specific condition. An organ name included in one divided region is specified as an extraction target organ.
Depending on the position information input in S91, a plurality of extraction target organs may be specified.

Next, the CPU 11 displays the organ name of the extraction target organ specified in S92 on the display device 17 (S93). When a plurality of extraction target organs are specified in S92, the CPU 11 displays a plurality of organ names.
Next, the user selects a desired extraction target organ by moving the mouse pointer displayed on the display device 17 using the mouse 18 or the like, and clicking the displayed organ name (S94).
Henceforth, S95-S98 is the same as that of S72-75 of FIG.

As described above, in the embodiment of the present invention, the medical image processing apparatus 3 determines, for each organ, the first divided region and the first divided region that are regions associated with the organ in the region of the medical image 2. The division condition to be divided into the second divided area which is the excluded area is stored, and the medical image 2 divided based on the division condition has the maximum number of pixels included in the first divided area, and / or Alternatively, the threshold for extracting the organ region is determined so that the number of pixels included in the second divided region is minimized, and the threshold processing is performed according to the determined threshold to extract the organ region of the medical image 2.
The medical image processing apparatus 3 according to the embodiment of the present invention can reduce the amount of data to be stored for extracting an organ region and accurately extract the organ region.

  In the above description, the threshold value is determined based on the number of pixels included in the first divided region and the number of pixels included in the second divided region, but the embodiment of the present invention is not limited to this example. The embodiment of the present invention generally determines the threshold value according to a statistic based on a set of pixels included in the first divided area and / or a statistic based on a set of pixels included in the second divided area. Can be That is, the threshold determination conditions formulated are the average, variance, and minimum value based on the set of pixels included in the first and second divided regions in addition to the number of pixels included in the first and second divided regions. The maximum value may be included.

In the above description, the division conditions (division method and specific condition) are all stored in the storage unit 13, but a part or all of the conditions may be input by the user.
For example, the user may directly specify the first divided area with the mouse 18 or the like for the medical image 2 displayed on the display device 17. Also, the user may directly specify division reference points such as the center of gravity of the abdomen and the center of gravity of the spine with a mouse or the like. Further, the user may directly specify the dividing line. The user may determine a division reference graphic that approximates the abdomen and the like. Further, the user may directly specify the size of the division reference graphic.

  The preferred embodiments of the medical image processing apparatus and the like according to the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to such examples. It will be apparent to those skilled in the art that various changes or modifications can be conceived within the scope of the technical idea disclosed in the present application, and these naturally belong to the technical scope of the present invention. Understood.

DESCRIPTION OF SYMBOLS 1 ......... Medical image processing system 2 ......... Medical image 3 ......... Medical image processing apparatus 5 ......... Medical image imaging device 7 ......... Image database 9 ......... Network 11 ......... CPU
12 ......... Main memory 13 ......... Storage device 14 ......... Communication I / F
15 ......... Display memory 16 ......... Controller 17 ......... Display device 18 ......... Mouse 19 ......... Keyboard 20 ......... Bus 21a, 31, 41 ......... Center of gravity of abdominal region 21b ......... Spine region Center of gravity 22a, 22b, 23a, 23b, 32, 33, 42, 43, 44 ......... Line 34 ......... Solid line 35 ......... Dotted line 45, 46 ......... Concentric circle 51 ......... Division condition table 61 ... … Organ list 62, 81 ……… mouse pointer

Claims (7)

A medical image processing apparatus for extracting an organ region from a medical image,
A division for each organ divided into a first divided region that is a region associated with the organ and a second divided region that is a region excluding the first divided region in the region of the medical image. Storage means for storing conditions;
For the medical image divided based on the division condition , the organ is arranged such that the number of pixels included in the first divided region is maximum and the number of pixels included in the second divided region is minimum. Determining means for determining a threshold for extracting the region;
Extraction means for performing threshold processing according to the threshold determined by the determination means and extracting an organ region of the medical image;
A medical image processing apparatus comprising: A medical image processing apparatus for extracting an organ region from a medical image,
A division for each organ divided into a first divided region that is a region associated with the organ and a second divided region that is a region excluding the first divided region in the region of the medical image. Storage means for storing conditions;
A value obtained by dividing the number of pixels included in the first divided region by the number of pixels included in the second divided region with respect to the medical image divided based on the dividing condition is maximized. Determining means for determining a threshold for extracting an organ region;
Extraction means for performing threshold processing according to the threshold determined by the determination means and extracting an organ region of the medical image;
A medical image processing apparatus comprising: Receiving means for displaying the medical image and receiving position information of an extraction target organ in the medical image;
Searching for the division condition based on the position information, and specifying means for specifying the extraction target organ;
The medical image processing apparatus according to claim 1 or claim 2, characterized in that it comprises a. The dividing condition, the center of gravity of the pixel group indicating the center of gravity or spinal pixel group indicating the subject and dividing the reference point, 1 to claim, characterized in that is to divide by a straight line passing through the division reference point The medical image processing apparatus according to claim 3 . The division condition is an angle division based on a polar coordinate system with a centroid of a pixel group indicating a subject or a centroid of a pixel group indicating a spinal cord as a division reference point and the division reference point as an origin. The medical image processing apparatus according to any one of claims 1 to 3 . The division condition is such that a pixel group indicating a subject is approximated by a circle, an ellipse, or a polygon to form a division reference graphic, and the division is performed according to the distance or direction from the center of gravity of the division reference graphic the medical image processing apparatus according to any one of claims 1 to 3, characterized in that it. A medical image processing method for extracting an organ region from a medical image,
A division for each organ divided into a first divided region that is a region associated with the organ and a second divided region that is a region excluding the first divided region in the region of the medical image. For the medical image divided based on the condition , the organ region is set so that the number of pixels included in the first divided region is maximum and the number of pixels included in the second divided region is minimum. A determination step for determining a threshold for extraction;
An extraction step of performing threshold processing according to the threshold determined by the determination step and extracting an organ region of the medical image;
A medical image processing method comprising: