JP2010220775A - Apparatus, method, and program for medical image processing - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To detect a blood vessel with higher accuracy. <P>SOLUTION: A medical image processing apparatus 100 includes a dividing section 105 for dividing a blood vessel candidate area of an obtained image into a plurality of first areas, a setting section for setting the first area having the same thickness as or a larger thickness than a predetermined thickness of the blood vessel to the second area which is different from the blood vessel candidate area, and a determination section for determining whether each first and second area is the blood vessel or not, corresponding to whether the area adjacent to each first and second area is the blood vessel candidate area or not. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a technique for detecting a blood vessel in a medical image.

  Conventionally, there is a blood vessel detection technique for detecting a blood vessel from a medical image acquired by a medical image diagnostic apparatus (see Non-Patent Document 1). As a blood vessel detection technique, there is a region expansion method in which threshold processing is performed by utilizing the fact that the luminance value of a blood vessel is different from the luminance values of other portions. The region expansion method has a feature that even a blood vessel having a complicated three-dimensional shape that is robust to noise can be detected.

However, in a medical image, the luminance value may decrease in a blood vessel with a small blood flow. Therefore, it may be difficult to detect the entire blood vessel region by the region expansion method using simple threshold processing.

Hiroyuki Sekiguchi, Naozo Sugimoto, Shigeru Eiho, Takashi Hanakawa, Shinichi Urayama, “Detection of blood vessels from head MRA by branch unit region growing”, Science (D-II), Vol.J87-D-II, No. 1, pp.125-133, Jan.2004

In the method of Non-Patent Document 1, for example, when an organ or the like having a luminance value close to the luminance value of the blood vessel is in the vicinity of the blood vessel, these organs and the like are erroneously detected as blood vessels.

  The present invention has been made in view of the above points, and an object thereof is to detect a blood vessel with higher accuracy.

  A medical image processing apparatus according to an aspect of the present invention includes a dividing unit that divides a blood vessel candidate region in an acquired image into a plurality of first regions, and a predetermined blood vessel among the plurality of first regions. A setting unit that sets a first region having a thickness equal to or larger than the first candidate region to a second region different from the blood vessel candidate region, and a region adjacent to each of the first region and the second region Comprises a determination unit that determines whether each of the first region and the second region is a blood vessel according to whether or not it is the blood vessel candidate region.

  According to the present invention, a blood vessel can be detected with higher accuracy.

1 is a block diagram illustrating a configuration of a medical image processing apparatus according to an embodiment of the present invention. It is a flowchart which shows operation | movement of the medical image processing apparatus which concerns on embodiment of this invention. It is a figure which shows an example of a rejection process. It is a figure which shows an example of an acceptance process.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 1 is a block diagram showing a medical image processing apparatus 100 according to an embodiment of the present invention. The acquisition unit 101 acquires a medical image acquired by a medical image diagnostic apparatus or the like. The storage unit 103 stores the medical image acquired by the acquisition unit 101. The operation unit 102 is operated by an operator such as specifying a region, specifying a reference point, and changing an image display method. The dividing unit 105 detects, from the medical image acquired by the acquiring unit 101, for example, a blood vessel candidate region that becomes a blood vessel candidate by paying attention to a branch of a blood vessel or a length of the blood vessel region, and the detected blood vessel candidate region is detected. It is divided into a plurality of small areas (hereinafter referred to as “first areas”). The setting unit 106 excludes regions having a thickness greater than or equal to a predetermined blood vessel thickness from the candidate regions detected by the dividing unit 105 from the blood vessel candidate regions. The determination unit 107 redetects the blood vessel region excluded by the setting unit 106 or determines a region different from the blood vessel not excluded by the setting unit 106 depending on whether or not the adjacent region is a blood vessel candidate region. exclude. The output unit 104 outputs the determination result of the determination unit 107. The control unit 108 controls each unit of the medical image processing apparatus 100.

  Next, the operation of the medical image processing apparatus 100 will be described with reference to FIG. FIG. 2 is a flowchart showing the operation of the medical image processing apparatus 100.

  In step S201, the acquisition unit 101 acquires a medical image acquired by a medical image diagnostic apparatus or the like. The medical image may be acquired from a medical image diagnostic apparatus such as an ultrasonic diagnostic apparatus, an X-ray CT apparatus, or an MR apparatus, or may be acquired from a medical image stored in an image server or the like. The medical image may be a two-dimensional image or a three-dimensional image. The medical image acquired by the acquisition unit 101 is stored in the storage unit 103.

  In step S202, the dividing unit 105 detects a blood vessel candidate region that is a blood vessel candidate from the medical image stored in the storage unit 103, and divides the detected blood vessel candidate region into a plurality of first regions. An image processing procedure for detecting a blood vessel candidate region will be described below. First, the operator designates one point inside a blood vessel to be detected as a reference point in a medical image displayed on a display unit (not shown) by the operation unit 102. The reference point is not limited to the one designated by the operator using the operation unit 102, and may be configured so that the control unit 108 automatically designates the reference point. Next, the dividing unit 105 detects a blood vessel candidate region including the designated reference point, and divides the detected blood vessel candidate region into a plurality of first regions.

  As a method for detecting a blood vessel candidate region, for example, a well-known region expansion method (region growing method) can be used. The division into the first region is preferably performed by paying attention to the shape of the blood vessel such as a branch point or a region length at a portion where the blood vessel is branched. For example, it is preferable to divide the candidate blood vessel region into the first region in units of branches by performing region expansion while detecting a branch point of the blood vessel. The size of the first area may be changed depending on the subject or the area to be detected, or may be preset for each area to be detected, or automatically optimized when performing the detection process. You may set it to any size. For example, in regions such as the brain region and liver region, the length and thickness of the blood vessel, as well as the length and thickness of the portion that is different from the over-detected blood vessel may be different, so depending on the region to be detected, etc. The size of the first area may be changed.

  In step S203, the setting unit 106 determines whether or not the first region divided by the dividing unit 105 is a blood vessel with reference to a predetermined blood vessel thickness. The setting unit 106 sets a first region having a thickness greater than or equal to a predetermined blood vessel thickness to a region other than the blood vessel (hereinafter referred to as “second region”), and excludes it from the blood vessel candidate region. . The predetermined blood vessel thickness can be appropriately set by, for example, measuring the actual blood vessel thickness in advance. The predetermined blood vessel thickness can be appropriately changed according to the region of interest and the purpose. In determining the thickness of the blood vessel, the number of pixels in the first region may be used, or the physical blood vessel thickness may be used. The thickness of the first region is generally represented by an area in a three-dimensional image and represented by a width in a two-dimensional image, but the present embodiment is not limited to this. The thickness of the first region is obtained by a well-known method (for example, see Non-Patent Document 1). For example, as in Non-Patent Document 1, an area extracted by the area expansion method may be approximated using an average value of the number of pixels extracted in one expansion cycle for both the two-dimensional image and the three-dimensional image. .

  In step S204, the determination unit 107 performs blood vessel determination based on blood vessel connectivity (hereinafter referred to as “connection determination processing”). The connection determination process is divided into a rejection process and an acceptance process.

  In the rejection process, the determination unit 107 excludes, from the blood vessel candidate regions, regions that do not appear to be blood vessels, as determined from the information on the surrounding regions, among the first regions determined by the setting unit 106 as blood vessel candidate regions. . For example, there is no blood vessel candidate region around the first region of interest, and the isolated first region is excluded from the blood vessel candidate region, or compared with the surrounding region even if the surrounding is a blood vessel candidate region Then, the region where the thickness is rapidly changed is excluded from the blood vessel candidate region. For example, when a blood vessel overlaps with an organ, the organ can be excluded from the blood vessel candidate region.

  FIG. 3 is a diagram illustrating an example of the rejection process. FIG. 3A shows a case where the first region is excluded from the blood vessel candidate regions. FIG. 3B shows a case where the first region is not excluded from the blood vessel candidate regions. In FIG. 3, R1 to R4 indicate the first region or the second region. ○ indicates that the region is the first region set as the blood vessel candidate region. X indicates a second region excluded from the blood vessel candidate region.

  First, the rejection process will be described with reference to FIG. In the rejection process, the determination may be made by a majority vote based on a voting process from an area adjacent to the area targeted for the rejection process. For example, as illustrated in FIG. 3A, the setting unit 106 determines that the number of areas set as the first area among the areas subject to the rejection process and the areas adjacent thereto is the second. If it is less than the number of areas set as the area, the area to be subjected to the rejection process is set as the second area. In FIG. 3A, R3 is the target of the rejection process. R3 is set in the first area, but R1, R2, and R4 adjacent to R3 are set in the second area. In FIG. 3A, the number of areas set as the first area is one (that is, R3) and the number of areas set as the second area is three (that is, R1, R2, and R4). The setting unit 106 sets R3 as the second region and excludes it from the blood vessel candidate region.

 Next, the rejection process will be described with reference to FIG. In FIG. 3B, since there are two areas (R1, R3) set as the first area and two areas (R2, R4) set as the second area, the setting unit 106 The R3 to be rejected is set as the first region and is not excluded from the blood vessel candidate region.

  FIG. 4 is a diagram illustrating an example of the selection process. FIG. 4A shows a case where the second region is redetected as a blood vessel candidate region. FIG. 4B shows a case where the second region is not re-detected as a blood vessel candidate region. In FIG. 4, R1 to R4 indicate the first region or the second region. ○ indicates that the region is the first region set as the blood vessel candidate region. X indicates a second region excluded from the blood vessel candidate region.

    First, the selection process will be described with reference to FIG. Similarly, in the selection process, determination may be made by a majority vote by a voting process from an area adjacent to the area that is the target of the selection process. For example, as illustrated in FIG. 4A, the setting unit 106 determines that the number of areas set as the first area among the areas to be selected and the areas adjacent thereto is the second number. If the number of areas is equal to or greater than the number of areas set as the area, the area to be selected is reset to the first area. In FIG. 4A, R3 is the target of the selection process. R3 adjacent to R3 and R3 is set in the second region. R1 and R4 adjacent to R3 are set in the first region. In FIG. 4A, there are two areas set as the first area (that is, R1 and R4) and two areas set as the second area (that is, R2 and R3). The setting unit 106 sets R3 as the first region and resets it as the blood vessel candidate region.

  Next, the selection process will be described with reference to FIG. In FIG. 4B, since the area set as the first area is one (R1) and the area set as the second area is three (R2, R3, R4), the setting unit 106 The R3 to be adopted is set as the second region, and is not re-detected as a blood vessel candidate region.

  Further, in at least one of the rejection process and the selection process, for example, it may be determined whether or not the blood vessel candidate area is set in consideration of the traveling direction of the area that is the target of the selection process. Specifically, the medical image processing apparatus 100 further includes a detection unit 109 that detects the traveling direction of each region to be processed, and the determination unit 107 detects the traveling direction detected by the detecting unit 109. Depending on the amount of change, it may be determined whether each of the regions to be processed is a blood vessel. When the amount of change in the traveling direction detected by the detection unit 109 is greater than a preset value, that is, when the region is bent significantly, there is a high possibility that the blood vessel is not a blood vessel. In this case, the determination unit 107 may exclude the region that is the subject of the rejection process from the blood vessel candidate region in the rejection process, or the region and the blood vessel candidate that are the targets of the adoption process in the adoption process. It may not be re-detected as a region. The traveling direction of the area may be averaged for each area from the direction in which the area is expanded by the area expansion method, or the traveling direction may be obtained in a finer area. In the connection determination process, the order of the rejection process and the selection process may be switched.

  In this way, by performing the connection determination process, regions other than blood vessels that could not be excluded in the thickness determination in step S203 (for example, regions where the size of the region is small at the end of the organ) are excluded from the blood vessel candidate regions. Or a blood vessel region candidate that has been excluded by mistake can be redetected.

  In step S205, the output unit 104 outputs the region set as the first region (that is, the blood vessel region). For example, the output unit 104 preferably displays the blood vessel region in a color-coded manner on the image so that the blood vessel region can be distinguished from other regions.

    As described above, according to the medical image processing apparatus according to the embodiment of the present invention, for example, blood vessels can be effectively detected even in a region where the blood vessels and the organs appear in contact with each other. Therefore, the operator can make a blood vessel diagnosis of the region of interest without complicated work. It should be noted that the number of blood vessels branching is not limited to that shown in FIGS.

  The medical image processing apparatus according to the embodiment of the present invention can also be realized by using, for example, a general-purpose computer as hardware. That is, each unit of the medical image processing apparatus can be realized by causing the processor mounted on the computer to execute a program. At this time, the medical image processing apparatus may be realized by installing the above program in a computer in advance, or may be stored in a computer-readable storage medium or distributed through the network, You may implement | achieve by installing this program in a computer suitably.

In addition, this invention is not limited to the said embodiment, A component can be changed within the range which does not deviate from the summary. Moreover, various inventions can be formed by appropriately combining a plurality of constituent elements disclosed in the embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, constituent elements over different embodiments may be appropriately combined.

100 Medical Image Processing Device 105 Dividing Unit 106 Setting Unit 107 Determination Unit

Claims (9)

A dividing unit for dividing the blood vessel candidate region in the acquired image into a plurality of first regions;
A setting unit that sets a first region having a thickness greater than or equal to a predetermined blood vessel thickness among the plurality of first regions as a second region different from the blood vessel candidate region;
Whether each of the first region and the second region is a blood vessel, depending on whether the region adjacent to each of the first region and the second region is the blood vessel candidate region. A determination unit for determining whether or not,
A medical image processing apparatus comprising:   The determination unit is an area in which the number of areas set in the first area is set in the second area among the first area to be determined and an adjacent area. 2. The medical image processing apparatus according to claim 1, wherein the target area is set as the second area if the number is less than the number of the first and second areas.   The determination unit is an area in which the number of areas set in the first area is set in the second area among the second area to be determined and an adjacent area. 2. The medical image processing apparatus according to claim 1, wherein the area to be processed is reset to the first area if the number is equal to or greater than the number of the first and second areas. The determination unit
Of the first area to be determined and the adjacent areas, the number of areas set as the first area may be smaller than the number of areas set as the second area. For example, the target area is set as the second area,
Of the second area to be determined and the adjacent areas, the number of areas set as the first area is equal to or greater than the number of areas set as the second area. The medical image processing apparatus according to claim 1, wherein the region to be processed is reset to the first region. The blood vessel candidate region includes a branched portion,
5. The medical image processing apparatus according to claim 1, wherein the dividing unit divides the blood vessel candidate region at a branch point of the branched portion.   The medical image processing apparatus according to claim 1, wherein the division unit is capable of changing a size of the first region. A detection unit for detecting a traveling direction of each of the first region and the second region;
The said determination part determines whether each of the said 1st area | region and the said 2nd area | region is a blood vessel according to the variation | change_quantity of the said running direction. The medical image processing apparatus according to any one of the above. A dividing unit that divides the blood vessel candidate region in the acquired image into a plurality of first regions;
A setting unit that sets a first region having a thickness equal to or greater than a predetermined blood vessel thickness among the plurality of first regions as a second region different from the blood vessel candidate region; ,
The determination unit determines whether each of the first region and the second region is based on whether the region adjacent to each of the first region and the second region is the blood vessel candidate region. A procedure for determining whether or not it is a blood vessel;
A medical image processing method. On the computer,
A dividing unit that divides the blood vessel candidate region in the acquired image into a plurality of first regions;
A setting unit that sets a first region having a thickness equal to or greater than a predetermined blood vessel thickness among the plurality of first regions as a second region different from the blood vessel candidate region; ,
The determination unit determines whether each of the first region and the second region is based on whether the region adjacent to each of the first region and the second region is the blood vessel candidate region. A procedure for determining whether or not it is a blood vessel;
A program for running

Images