JP2009045110A - Apparatus, method, and program for image processing - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an apparatus, method, and a program for image processing, which accurately extract a region belonging to a predetermined component part from an image of a subject. <P>SOLUTION: The image processing apparatus includes an image acquiring section for acquiring a tomographic image of a subject and a region searching section for searching a region having an image homogeneity corresponding to homogeneity of a cross-section of a predetermined component part among various component parts composing the subject. Because a region having an image homogeneity corresponding to the homogeneity of a cross-section of a predetermined component part is searched in the tomographic image of a subject, a blood vessel region belonging to a blood vessel or a bone region belonging to a bone is searched accurately even when the tomographic image is of a part where blood vessels and bones are tangled complexly. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an image processing apparatus, an image processing method, and an image processing program for searching a region belonging to a predetermined constituent part constituting a subject from a cross-sectional image of the subject.

  In the medical field, a medical image obtained by imaging the inside of a subject using radiation or the like is widely used for diagnosis of a medical condition of the subject. By using medical images for diagnosis, it is possible to grasp the progress of the medical condition of the subject without damaging the subject externally, and easily obtain information necessary for determining the treatment policy. be able to.

  In recent years, a CR (Computed Radiography) apparatus that obtains a digital medical image using radiation, a CT apparatus (Computerized Tomography) that obtains a tomographic image of a subject using radiation, and a subject using a strong magnetic field. An MRI apparatus (Magnetic Resonance Imaging) for obtaining a tomographic image has been widely used, and a digital medical image is generally used instead of a medical image using a conventional X-ray film or the like. Digitalization of medical images makes it easy to perform image processing on medical images, and displays a plurality of medical images taken at different times for the same subject on a monitor or displayed on a medical image. An image portion estimated to be a lesion has been widely displayed.

  Here, in a medical image obtained from a CT apparatus or the like, a bone region belonging to a bone generally has a considerably higher image density than a region other than the bone region, and a lesion is included in the medical image. Even if it exists, there is a problem that it is difficult to find because it is lost in the bones. For this reason, a diagnosis is performed using a bone image extracted from a medical image and a removed image obtained by removing the extracted bone. As a bone extraction method for extracting bones in a medical image, an area having an image density equal to or higher than a reference density is determined from the medical image by using the fact that the image density of the bone area is higher than the image density of other areas. The extraction method is widely known. However, in a contrast image taken by injecting a contrast medium onto a subject, the blood vessel region belonging to the blood vessel also has a high image density in the same manner as the bone region. When extracted, the blood vessel region is extracted together with the bone region.

  In this regard, Patent Document 1 discloses that a high reference density in a medical image is obtained using a high reference density that is close to the maximum value of the image density in the bone region and a low reference density that is close to the maximum value of the image density in the blood vessel region. A technique is described in which a high density area having an image density higher than the density is removed, and an overlapping area having an image density higher than the low reference density and overlapping the high density area is also removed. According to the technique described in Patent Literature 1, it is possible to remove a high-concentration region that is reliably estimated to be a bone and an overlapping region that is unclear whether it is a bone or a blood vessel and overlaps the high-concentration region. Therefore, it is possible to reduce the problem that the blood vessel region is removed in addition to the bone region.

In addition, an area in which it is unclear whether it is a bone or a blood vessel is classified into a bone area and a blood vessel area using an anatomical structure or the like. Patent Document 2 describes a technique for projecting a plurality of rays on a medical image and detecting the start position or end position of a blood vessel region or a bone region based on the characteristics of the gradient of the image density on the ray. ing. According to the technique described in Patent Document 2, it is possible to accurately detect a boundary between a blood vessel region and a bone region.
JP 11-318883 A JP 2002-301051 A

  However, in contrast images obtained by imaging the chest and abdomen of a subject, some blood vessel regions may have a higher image density than bone regions. With the technique described in Patent Document 1, the image density is higher than the blood vessel region. There is a problem that a bone region having a low height cannot be extracted.

  Further, since both the bone region and the blood vessel region have high image density and the contact portion where they are in contact has a low density gradient, the technique described in Patent Document 2 classifies the adjacent blood vessel region and bone region. There is a problem that can not be. For example, bones and blood vessels are intricately intertwined at the shoulder and neck, and there is a need to develop an image processing apparatus that can classify bone regions and blood vessel regions with high accuracy even in medical images of such sites.

  In view of the above circumstances, an object of the present invention is to provide an image processing apparatus, an image processing method, and an image processing program capable of accurately extracting a region belonging to a predetermined component from a medical image of a subject. .

An image processing apparatus of the present invention that achieves the above object includes an image acquisition unit that acquires a cross-sectional image of a subject,
Region search for searching for a region having image uniformity corresponding to the uniformity of the cross-section of a predetermined component among various components constituting the subject with respect to the cross-sectional image acquired by the image acquisition unit And a section.

  Since the blood vessel is filled with blood, the blood vessel region in which the blood vessel is shown on the cross-sectional image of the subject often has a uniform and high image density. On the other hand, since a cancellous bone exists in the center of the bone, the bone region where the bone is shown on the cross-sectional image of the subject generally has a non-uniform image density. According to the image processing apparatus of the present invention, a region having image uniformity corresponding to the uniformity of the cross-section of a predetermined component is searched for the cross-sectional image of the subject. Even in a cross-sectional image of a complexly intertwined region, a blood vessel region belonging to a blood vessel or a bone region belonging to a bone can be searched with high accuracy.

Moreover, in the image processing apparatus of the present invention, the constituent part is a constituent part other than bone,
It is preferable that the region search unit searches for a region having a uniformity that is relatively higher than the uniformity of the image density of the bone image.

  By utilizing the fact that the image density of bone images is non-uniform, by searching for a region with relatively high uniformity from cross-sectional images, regions belonging to components other than bone are extracted with high accuracy. be able to.

  Further, in the image processing apparatus of the present invention, based on the search result in the area search unit, an extracted image obtained by extracting the constituent parts in the cross-sectional image and / or an image for creating a removal image obtained by removing the constituent parts from the cross-sectional image It is preferable that a preparation unit is provided.

  For example, a region belonging to a bone is extracted from a cross-sectional image, and the extracted bone is removed, thereby making it easy to see a lesion or the like in the cross-sectional image.

In the image processing apparatus of the present invention, the image processing apparatus further includes an auxiliary extraction unit that extracts each region having an image characteristic corresponding to the feature of the constituent part from each region searched by the region search unit,
It is preferable that the image creation unit creates a removed image and / or an extracted image based on each region extracted by the auxiliary extraction unit.

  According to this preferred image processing apparatus, it is possible to extract a region belonging to a predetermined component in a cross-sectional image with higher accuracy.

  In the image processing apparatus of the present invention, it is preferable that the auxiliary extraction unit uses an extraction condition that defines a high image density.

  For example, a region belonging to a bone in a cross-sectional image of a subject generally has a higher image density than a region other than the bone. By using the extraction condition in which the auxiliary extraction unit defines the height of the image density, it is possible to reliably extract a region belonging to a predetermined component in the cross-sectional image.

  In the image processing apparatus of the present invention, it is also preferable that the auxiliary extraction unit uses an extraction condition that defines a density distribution on the image.

  For example, by preparing a typical density distribution of the constituent parts and extracting a region having a density distribution similar to the typical density distribution in the cross-sectional image to a predetermined extent, A region belonging to a predetermined component can be extracted with high accuracy.

The image processing method of the present invention that achieves the above object includes an image acquisition process for acquiring a cross-sectional image of a subject,
Region search for searching for a region having image uniformity corresponding to the uniformity of the cross-section of a predetermined component among various components constituting the subject with respect to the cross-sectional image acquired in the image acquisition process And a process.

  According to the image processing method of the present invention, a blood vessel region belonging to a blood vessel or a bone region belonging to a bone can be searched with high accuracy even in a cross-sectional image of a site where blood vessels and bones are intricately intertwined.

  As for the image processing method, only those basic forms are shown here, but this is only for avoiding duplication, and the image processing method referred to in the present invention is not limited to the above basic form. Various forms corresponding to each form of the image processing apparatus described above are included.

The image processing program of the present invention that achieves the above object is executed in a computer,
An image acquisition unit for acquiring a cross-sectional image of the subject;
Region search for searching for a region having image uniformity corresponding to the uniformity of the cross-section of a predetermined component among various components constituting the subject with respect to the cross-sectional image acquired by the image acquisition unit It is characterized by building a part.

  According to the image processing program of the present invention, it is possible to construct an image processing apparatus that accurately extracts a region belonging to a predetermined component from an image of a subject.

  Note that only the basic forms of the image processing program are shown here, but this is only for avoiding duplication, and the image processing program according to the present invention is not limited to the above basic form. Various forms corresponding to each form of the image processing apparatus described above are included.

  Furthermore, the elements such as the image acquisition unit constructed on the computer system by the image processing program of the present invention may be one element constructed by one program part, and a plurality of elements are one program part. It may be constructed by. In addition, these elements may be constructed so as to execute such actions by themselves, or constructed by giving instructions to other programs and program components incorporated in the computer system. May be.

  According to the present invention, it is possible to accurately extract a region belonging to a predetermined component from an image of a subject.

  Embodiments of the present invention will be described below with reference to the drawings.

  FIG. 1 is a schematic configuration diagram of a medical diagnosis system to which an embodiment of the present invention is applied.

  The medical diagnostic system shown in FIG. 1 includes an image generation device group 10 that captures a body of a subject and generates a medical image, a management server 20 that stores medical images and medical records, and a diagnostic device 30 that displays a medical image. The image generation device group 10 and the management server 20, and the management server 20 and the diagnostic device 30 are connected via a network line.

  In this medical diagnosis system, an identification number for identifying each subject is assigned to the subject at the first visit, and the identification number corresponds to a medical record indicating the name, age, medical history, etc. of the subject. And registered in the management server 20.

  The image generation device group 10 generates a digital medical image by irradiating a subject with radiation and reading the radiation transmitted through the subject, or generates a tomographic image of the subject using radiation. There are a CT apparatus 12, an MRI apparatus (not shown) that generates a tomographic image of a subject using a strong magnetic field and radio waves, an ultrasonic apparatus (not shown) that generates a medical image by reading ultrasonic echoes, and the like. included. The medical image generated by the image generation device group 10 is sent to the management server 20 together with an identification number for identifying the subject that is the subject of the medical image.

  When the medical image and the identification number are sent from the image generation device group 10, the management server 20 stores the medical image in association with the identification number. That is, the management server 20 registers the identification number, the medical chart of the subject to which the identification number is assigned, and the medical image of the subject in association with each other.

  The diagnostic device 30 has various types of information corresponding to key operations on the main body device 31, an image display device 32 that displays an image on the monitor 32 a according to an instruction from the main body device 31, and the main body device 31. An input keyboard 33 and a mouse 34 for inputting an instruction corresponding to, for example, an icon or the like displayed at that position by designating an arbitrary position on the monitor 32a are provided.

  When the user inputs the name or identification number of the subject using the mouse 34 or the like of the diagnostic apparatus 30, the input content is transmitted to the management server 20. The management server 20 acquires the name and identification number of the subject from the diagnostic device 30, and sends the medical image and medical chart associated therewith to the diagnostic device 30. In the diagnostic device 30, by performing image processing on the medical image, a bone removal image from which the bone in the medical image has been removed is generated, and the medical image and the bone removal image before processing are displayed on the monitor 32a. . By confirming various medical images displayed on the monitor 32a of the diagnostic device 30, the user can diagnose the medical condition of the subject without causing external damage to the subject.

  The user looks at the medical image displayed on the monitor 32 a of the diagnostic device 30 to diagnose the medical condition of the subject, and edits the medical chart using the mouse 34 and the keyboard 33. The edited chart is sent to the management server 20, and the chart stored in the management server 20 is updated to a new chart sent from the diagnostic device 30.

  The medical diagnosis system shown in FIG. 1 is basically configured as described above.

  Hereinafter, the diagnostic device 30 will be described in detail.

  FIG. 2 is a hardware configuration diagram of the diagnostic device 30.

  As shown in FIG. 2, the main unit 31 of the diagnostic device 30 includes a CPU 101 that executes various programs, a main memory 102 that reads programs stored in the hard disk device 103 and develops them for execution by the CPU 101, A hard disk device 103 in which various programs, data, and the like are stored, an FD (flexible disk) 41 are loaded, an FD drive 104 that accesses the FD 41, a CD-ROM drive 105 that accesses the CD-ROM 42, and image data from the management server 20 Etc. and an I / O interface 106 for sending various instruction data to the management server 20 is built-in. These various elements and the image display device 32, keyboard 33, and mouse 34 shown in FIG. Are connected to each other.

  Here, in the CD-ROM 42, an image display program 200 (see FIG. 3) which is an embodiment of the image processing program of the present invention for constructing an embodiment of the image processing apparatus of the present invention in the diagnostic device 30. ) Is stored.

  FIG. 3 is a conceptual diagram showing the CD-ROM 42.

  As shown in FIG. 3, the image display program 200 stored in the CD-ROM 42 includes an image acquisition unit 210, a region search unit 220, an auxiliary extraction unit 230, a middle line / branch detection unit 240, a region determination unit 250, The image generation unit 260 and the image display unit 270 are configured.

  The CD-ROM 42 is loaded into the CD-ROM drive 105 of the diagnostic device 30, and the image display program 200 stored in the CD-ROM 42 is uploaded to the diagnostic device 30 and stored in the hard disk device 103. Then, when the image display program 200 is activated and executed, a medical image display apparatus 300 (see FIG. 4) having a function as an embodiment of the image processing apparatus of the present invention is built in the diagnostic apparatus 30. Is done.

  In the above, the CD-ROM 42 is exemplified as the storage medium for storing the image display program 200, but the storage medium for storing the image display program 200 is not limited to the CD-ROM, and other optical discs, It may be a storage medium such as MO, FD, or magnetic tape. Further, the image display program 200 may be directly supplied to the diagnostic apparatus 30 via the I / O interface 106 without using a storage medium.

  Details of each part of the image display program 200 will be described together with the operation of each part of the medical image display apparatus 300.

  FIG. 4 is a functional block diagram of the medical image display apparatus 300.

  The medical image display apparatus 300 includes an image acquisition unit 310, an area search unit 320, an auxiliary extraction unit 330, a middle line / branch detection unit 340, an area determination unit 350, an image generation unit 360, and an image display. Part 370.

  An image acquisition unit 310, an area search unit 320, an auxiliary extraction unit 330, a middle line / branch detection unit 340, an area determination unit 350, an image generation unit 360, which constitute the medical image display apparatus 300, The image display unit 370 includes the image acquisition unit 210, the region search unit 220, the auxiliary extraction unit 230, the middle line / branch detection unit 240, the region determination unit 250, and the image generation unit that constitute the image display program 200 of FIG. 260 and the image display unit 270, respectively.

  Each element in FIG. 4 is composed of a combination of computer hardware and an OS or application program executed on the computer, whereas each element of the image display program 200 shown in FIG. The difference is that it is configured only by application programs.

  FIG. 5 is a flowchart showing a flow of a series of processes from acquiring a medical image from the management server 20 to extracting a bone in the acquired medical image in the medical image display apparatus 300 shown in FIG.

  Hereinafter, by describing the operation of each element of the medical image display apparatus 300 shown in FIG. 4 according to the flowchart of FIG. 5, each element of the image display program 200 shown in FIG.

  When the user inputs the name and identification number of the subject to be diagnosed using the mouse 34 and keyboard 33 shown in FIG. 1, the input content is transmitted to the management server 20 via the I / O interface 106 of FIG. . In the management server 20, when the name and identification number of the subject are acquired, the medical image and medical chart of the subject are sent to the diagnostic apparatus 30.

  The medical image sent from the management server 20 is acquired by the image acquisition unit 310 shown in FIG. 4 (step S1 in FIG. 5).

  FIG. 6 is a diagram showing the concept of a medical image sent from the management server 20.

  In the present embodiment, in the CT apparatus 12 shown in FIG. 1, each cross section when the subject is cut from the chest to the base of the foot at a plurality of cutting positions X0 to Xn is photographed, and a plurality of sections at each of the plurality of cutting positions is taken. A cross-sectional image 400 is generated.

  FIG. 7 is a diagram showing a cross-sectional image at one cutting position Xm.

  FIG. 7 shows a cross-sectional image 400 at one cutting position Xm among a plurality of cutting positions X0 to Xn shown in FIG. In practice, a plurality of cross-sectional images 400 are acquired by the image acquisition unit 310 shown in FIG. 4. In the following, description will be made using the cross-sectional image 410 shown in FIG. 7 as a representative of them.

  The cross-sectional image 410 includes bones in addition to organs and blood vessels, and there is a problem that even if a lesion exists, the cross-sectional images 410 are mixed with bones and are difficult to find.

  The cross-sectional image 410 acquired by the image acquisition unit 310 in FIG. 4 is transmitted to the region search unit 320, the midline / branch detection unit 340, and the image generation unit 360.

  The area search unit 320 is provided with a uniform filter 320a for extracting an area having a uniform density in the image. The area search unit 320 uses the uniform filter 320a to search for an area having a uniform image density in the cross-sectional image 410 transmitted from the image acquisition unit 310 (step S2 in FIG. 5). In the present embodiment, the uniform filter 320a describes density conditions such as a maximum density value, a minimum density value, a dynamic range (density range), and a density gradient between adjacent areas in the area. The search unit 320 searches for an area in the cross-sectional image 410 that satisfies the density condition indicated by the uniform filter 320a.

  Here, since the cancellous bone exists in the center of the bone, the bone region belonging to the bone in the cross-sectional image 410 of the subject has a non-uniform image density. Since the uniform filter 320a describes density conditions for searching for a region having a uniform image density, the region search unit 320 directly selects non-bone regions belonging to organs or blood vessels other than bones. Explored. However, since the bone region can be easily extracted by removing the non-bone region from the cross-sectional image 410, the region searching unit 320 indirectly searches for the bone region.

  FIG. 8 is a diagram illustrating an extracted image obtained by extracting a region directly searched by the region searching unit 320 from the cross-sectional image 410.

  The first extracted image 420 includes non-bone regions belonging to blood vessels other than bone in the cross-sectional image 410 shown in FIG. In this example, the area search unit 320 searches the areas 51, 61, 62, 71, 81, 82, 83, 84, and 85 having a uniform image density in the first extracted image 420.

  Conventionally, a region having a high image density in the cross-sectional image 410 is searched, and the searched region is determined as a bone region belonging to the bone, or a bone region and a non-bone region are determined based on the gradient of the image density. Classification was done. However, according to these methods, in addition to the bone region, a blood vessel region whose image density is increased by administration of a contrast agent is also extracted, or in a portion where the bone and the blood vessel are intertwined, the bone region and the blood vessel region are extracted. There was a problem that could not be classified. According to the medical image display apparatus 300 of the present embodiment, since a region is searched from the cross-sectional image 410 based on the uniformity of the image density, even if the bone region and the blood vessel region are intertwined with each other, Non-bone regions can be easily classified.

  However, at the time shown in FIG. 8, in addition to the non-bone region, a small bone region in which the uniformity of the image density cannot be analyzed has been searched together. In the medical image display apparatus 300 of the present embodiment, based on the height of the image density of each region on the cross-sectional image 410, the change in the image density in the continuous direction across the plurality of cross-sectional images 400 shown in FIG. Further, the area is classified finely. The area search unit 320 transmits the cross-sectional image 410 and the search result to the auxiliary extraction unit 330.

  The auxiliary extraction unit 330 extracts a region having an image density higher than a predetermined first threshold in the first extracted image 420 illustrated in FIG. 8 (Step S3 in FIG. 5). In the present embodiment, the minimum value of the image density of each of the regions 51, 61, 62, 71, 81, 82, 83, 84, and 85 constituting the first extracted image 420 is used as the first threshold value, and the first extraction is performed. In the image 420, an area having an image density higher than the first threshold is set to “1”, and an area having an image density lower than the first threshold is set to “0”. It is priced.

  FIG. 9 is a diagram illustrating a binarized extracted image.

  The binarized extracted image 430 shown in FIG. 9 includes areas corresponding to the areas 51, 61, 62, 71, 81, 82, 83, 84, and 85 constituting the first extracted image 420 shown in FIG. 51a, 61a, 62a, 71a, 81a, 82a, 83a, 84a, 85a are included.

  Further, the auxiliary extraction unit 330 expands each region 51a, 61a, 62a, 71a, 81a, 82a, 83a, 84a, 85a in the binarized extracted image 430 by a predetermined size. For example, when the size of the cross-sectional image 410 is 512 pixels × 512 pixels, the extended size is preferably about 2 to 4 pixels.

  FIG. 10 is a diagram illustrating a binarized extracted image in which each region is expanded.

  The binarized extracted image 431 shown in FIG. 10 includes areas 51b, 61b, 62b, 71b, 81b, which are expanded from the areas 51a, 61a, 62a, 71a, 81a, 82a, 83a, 84a, and 85a shown in FIG. 82b, 83b, 84b, 85b. Each of the regions 51b, 61b, 62b, 71b, 81b, 82b, 83b, 84b, and 85b included in the binarized extracted image 431 has a high image density uniformity among the cross-sectional images 410 shown in FIG. A region having a large target area is extracted, and is likely to be a non-bone region belonging to a blood vessel or an organ.

  The auxiliary extraction unit 330 generates a removed image obtained by removing the binarized extracted image 431 from the cross-sectional image 410.

  FIG. 11 is a diagram illustrating a removal image generated by the auxiliary extraction unit 330.

  A removed image 440 illustrated in FIG. 11 is an image obtained by removing only a region that is highly likely to be a non-bone region from the cross-sectional image 410 illustrated in FIG. 7. The removed image 440 includes a non-bone in addition to the bone region. Part of the area is included.

  The auxiliary extraction unit 330 further extracts each region having an image density equal to or higher than a predetermined second threshold value from the removed image 440 shown in FIG. 11 (step S4 in FIG. 5). In the present embodiment, as the second threshold value, a bone value and contrast blood in the image are extracted, and a value that does not extract blood vessel walls, organs, and lesions other than the contrast blood (CT value of about 280 to 320) is applied. In the removed image 440, since the non-bone region having a large area has already been removed, the bone region is mainly extracted in step S4 of FIG.

  FIG. 12 is a diagram illustrating a second extracted image in which a region having an image density equal to or higher than the second threshold is extracted from the removed image 440.

  The second extracted image 450 shown in FIG. 12 includes a small area group 98 in which a large number of small areas are collected in addition to the large areas 91, 92, 93, 94, 95, 96, and 97.

  The auxiliary extraction unit 330 removes an area having a predetermined size or less from the second extracted image 450. In the present embodiment, a third extracted image 451 (see FIG. 13) from which the microregion group 98 has been removed is generated by removing a region that is equal to or smaller than the general bone size from the second extracted image 450. .

  FIG. 13 is a diagram illustrating a third extracted image.

  The regions 91, 92, 93, 94, 95, 96, and 97 in the third extracted image 451 shown in FIG. 13 include bone regions that belong to bones and non-bone regions that have high image density and a small area. Therefore, it is difficult to classify these regions 91, 92, 93, 94, 95, 96, and 97 into bone regions and non-bone regions based on image density height and uniformity. The third extracted image 451 is transmitted from the auxiliary extraction unit 330 illustrated in FIG. 4 to the middle line / branch detection unit 340.

  The middle line / branch detection unit 340 has a predetermined size (smaller than a general spine size) among the regions 91, 92, 93, 94, 95, 96, and 97 included in the third extracted image 451. The center position is detected for each of the small size areas 91, 92, 94, 95, 96, and 97 excluding the area 93 having a size of (size) or more (step S5 in FIG. 5). At this point, since the non-bone region having a large area has already been removed, the region having a large size is considered to be a bone region. By removing the region considered to be a bone region in advance, the processing speed can be improved.

  FIG. 14 is a diagram illustrating the center position of the region.

  FIG. 4 shows the center positions O1, O2, and O3 in the three dense regions 94, 96, and 97 in the third extracted image 451 shown in FIG.

  The middle line / branch detection unit 340 detects the center positions of the small size regions 91, 92, 94, 95, 96, and 97 for the plurality of cross-sectional images 400 at the plurality of cutting positions X0 to Xn shown in FIG. To do.

  FIG. 15 is a conceptual diagram showing the center positions O1, O2, and O3 of the three regions 94, 96, and 97 in each of the plurality of cross-sectional images 400.

  The middle line / branch detection unit 340 extracts center lines connecting the center positions of the small size regions 91, 92, 94, 95, 96, and 97 from the plurality of cross-sectional images 400. In the example shown in FIG. 15, among the center positions O1, O2, and O3 of the three small size regions 94, 96, and 97, the center position O1 shown at the top is the three center positions O1_1, O1_2, and O1_3. The center lines L1, L2, and L3 connecting the center positions O1, O2, and O3, and the branch lines L1_1 that branch from the center line L1 and connect the center positions O1_1, O1_2, and O1_3, respectively. L1_3 and L1_3 are extracted. The middle line / branch detection unit 340 transmits information on the position on each cross-sectional image 400 representing the extracted center line to the region determination unit 350.

  The area determination unit 350 analyzes each center line and a series of image density features on each branch line transmitted from the middle line / branch detection unit 340 in the plurality of cross-sectional images 400 to thereby obtain each small size area. 91, 92, 94, 95, 96, 97, and each separation region separated from each small size region 91, 92, 94, 95, 96, 97 when the plurality of cross-sectional images 400 are analyzed along the body axis direction. Are classified into a bone region and a non-bone region (step S6 in FIG. 5). In the example shown in FIG. 15, the characteristics of the image density on each of the center lines L1, L2, and L3 and each of the branch lines L1_1, L1_3, and L1_3 are analyzed.

  FIG. 16 is a graph showing the image density in each of the bone image and the contrasted blood vessel image.

  Part (A) of FIG. 16 is a graph in which the image density of the central portion of the bone at each position is plotted in a plurality of cross-sectional images obtained by photographing cross-sections at a plurality of positions along the body axis direction of the subject. is there. Since cancellous bone exists in the center of the bone, when the image density at the center of the bone is plotted along the body axis direction, the image density greatly increases and decreases as shown in part (A) of FIG. There is also a position where the image density value is 100 or less in CT value.

  In part (B) of FIG. 16, the image density of the central portion of the contrasted blood vessel at each position is plotted in a plurality of cross-sectional images obtained by photographing cross-sections at a plurality of positions along the body axis direction of the subject. It is a graph. Since the inside of the blood vessel is filled with contrasted blood, when the image density at the central portion of the contrasted blood vessel is plotted along the body axis direction, the image density is substantially constant as shown in part (B) of FIG. In addition, there is almost no position where the CT value is 100 or less.

  The area determination unit 350 determines the image density at the center position of each of the small size areas 91, 92, 94, 95, 96, and 97 shown in FIG. The characteristics when continuously analyzed along each center line connecting the above center positions are compared with the characteristics of the image density of each of the two graphs shown in FIG. Further, among the small size areas 91, 92, 94, 95, 96, 97 and the separation area, when the image density at the center position is viewed along the center line, it is close to the graph of part (A) of FIG. A region having a density change is classified as a bone region, and a region having a density change close to the graph of part (B) in FIG. 16 is classified as a non-bone region. For example, in the example shown in FIG. 15, the image density on each of the center positions O1, O2, O3, O1_1, O1_2, and O1_3 is respectively along the center lines L1, L2, and L3, and three branch lines L1_1, L1_3, and L1_3. The feature when continuously analyzed is compared with the feature of the image density of each of the two graphs shown in FIG. In this example, only the change in image density along the lowermost center line L3 among the center lines L1, L2, L3 and the three branch lines L1_1, L1_3, and L1_3 is shown in the graph of part (A) of FIG. The small-size area 94 having a density change close to that and including the point on the center line L3 is classified as a bone area, and is separated from the other small-size areas 96 and 97 and the first small-size area 96. Each separation region is classified as a non-bone region.

  In this way, by continuously analyzing the image density on the center position of each small size region and each separation region along each center line connecting the center positions on the plurality of cross-sectional images 400, Even if the bone and the blood vessel are intricately intertwined, the bone region and the non-bone region can be classified with high accuracy.

  As described above, the bone region in the cross-sectional image 410 is extracted. The extraction result of the bone region is transmitted from the region determination unit 350 in FIG. 5 to the image generation unit 360.

  The image generation unit 360 removes the bone region transmitted from the region determination unit 350 from the cross-sectional image 410 shown in FIG. 7, and generates a bone removal image. The generated bone removal image is transmitted to the image display unit 370 and displayed on the monitor 32a shown in FIG.

  FIG. 17 is a diagram showing a cross-sectional image display screen 500 displayed on the monitor 32a.

  In the cross-sectional image display screen 500 shown in FIG. 17, in addition to the bone removal image 510, the name of the subject, the cutting position “Xm”, the date of photographing, and the like are also displayed. The bone removal image 510 is an image obtained by removing the bone region from the cross-sectional image 410 shown in FIG. 7, and the user can accurately recognize the size and position of the lesion by checking the bone removal image 510. Can do.

  Above, description of 1st Embodiment of this invention is complete | finished and 2nd Embodiment of this invention is described. Since the second embodiment of the present invention has the same configuration as that of the first embodiment except for the processing contents in the auxiliary extraction unit 330, the drawings used in the first embodiment are also used in the second embodiment. Only the differences from the first embodiment will be described.

  In the present embodiment, in the CT apparatus 12 shown in FIG. 1, a medical image of a healthy human body is acquired in advance, and the distribution of image density in the bone region in the medical image is easily mistaken for the bone region. The image density distribution in the image is analyzed. This analysis method has been widely known as a learning method or a principal component analysis method, and will not be described in detail in this specification. The analysis result is stored in the hard disk device 103 shown in FIG.

  Also in this embodiment, the area search unit 320 shown in FIG. 4 searches for an area having a uniform image density from the cross-sectional image 410 shown in FIG. The area search unit 320 transmits the cross-sectional image 410 and the search result (first extraction image 420 shown in FIG. 8) to the auxiliary extraction unit 330.

  The auxiliary extraction unit 330 analyzes the distribution of the image density for each of the regions 51, 61, 62, 71, 81, 82, 83, 84, and 85 constituting the first extracted image 420 shown in FIG. It is determined how much the result is similar to the analysis result of each of the bone region and the contrasted blood vessel stored in the hard disk device 103. In the present embodiment, the similarity between the analysis result of each divided region and the analysis result of each of the bone region and the contrasted blood vessel is a five-level determination value (1 to 5. The larger the value, the higher the similarity with the bone region, If the value is smaller, the similarity to the contrasted blood vessel is higher). If the similarity is “5”, the divided region is classified as a bone region, and if the similarity is “1” If the divided area is classified as a non-bone area and the similarity is “2”, “3”, or “4”, the divided area is not classified as a bone area or a non-bone area. The classification result is transmitted to the middle line / branch detection unit.

  As described above, the bone region and the non-bone region can be easily classified by using the image density distribution.

  Above, description of 2nd Embodiment of this invention is complete | finished and the Example of this invention is described. In this example, the bone region and the blood vessel region in the cross-sectional image are classified using the medical image display apparatus 300 of the first embodiment shown in FIG.

  18 to 25 are cross-sectional images obtained by photographing each cross section when the vicinity of the shoulder of the subject is cut at eight cutting positions along the body axis direction.

  FIG. 18 shows a cross-sectional image 601 at the first cutting position. A region A in the cross-sectional image 601 is a bone region belonging to a bone, and a region B is a blood vessel region belonging to a blood vessel. In the cross-sectional image 601, since the region A and the region B are separated, it is considered that the bone region and the blood vessel region can be classified using an image density gradient or the like.

  19 to 25 show cross-sectional images 602 to 608 at the second to eighth cutting positions, respectively. When the cutting position changes, the area A and the area B approach each other, and in the cross-sectional image 606 at the sixth cutting position shown in FIG. 23, the areas A and B are completely adhered. Since both the area A and the area B have high image density, the density gradient at the contact portion between these areas is low, and the area A and the area B are classified into the bone area and the blood vessel area using the density gradient. It is difficult.

  In the medical image display apparatus 300 of the present embodiment, based on the uniformity of the image density of each of the regions A and B and the characteristics of the image density of each of the regions A and B in the direction along the cutting position, the region A , B could be accurately classified into a bone region and a blood vessel region.

  From the above results, the usefulness of the present invention was confirmed.

  Here, an example of extracting a bone region from a medical image has been described above. However, the image processing apparatus of the present invention may determine a region belonging to a constituent part other than a bone from a medical image. It may be applied to an image of a subject other than the image.

  In the above description, an example in which a region having a uniform image density is extracted using a maximum density value, a minimum density value, a dynamic range (density range), a density gradient between adjacent areas, and the like has been described. The image processing apparatus of the present invention may determine a region having a uniform image density by using a statistical quantity such as a local density average value, density dispersion value, moment, cumulant, or the like. In addition, about the determination method using these statistics, the determination method described in signal processing (Akira Morishita, Hidefumi Obata, Society of Instrument and Control Engineers, 1982) etc. can be used.

1 is a schematic configuration diagram of a medical diagnosis system to which an embodiment of the present invention is applied. It is a hardware block diagram of a diagnostic apparatus. It is a conceptual diagram which shows CD-ROM. It is a functional block diagram of a medical image display apparatus. FIG. 5 is a flowchart showing a flow of a series of processing until a medical image is acquired from a management server and a bone in the acquired medical image is extracted in the medical image display apparatus shown in FIG. 4. It is a figure which shows the concept of the medical image sent from the management server. It is a figure which shows the cross-sectional image in one cutting position Xm. It is a figure which shows the extraction image which extracted the area | region directly searched by the area | region search part from the cross-sectional image. It is a figure which shows the binarized extraction image. It is a figure which shows the binarization extraction image by which each area | region was expanded. It is a figure which shows the removal image produced | generated by the auxiliary extraction part. It is a figure which shows the 2nd extraction image from which the area | region which has an image density more than a 2nd threshold value was extracted from the removal image. It is a figure which shows a 3rd extraction image. It is a figure which shows the center position of an area | region. It is a conceptual diagram which shows the center position of three area | regions in each of several cross-sectional image. It is a graph which shows the image density in each of the image of a bone, and the image of a contrast blood vessel. It is a figure which shows the cross-sectional image display screen displayed on the monitor. It is a figure which shows the cross-sectional image in the 1st cutting position. It is a figure which shows the cross-sectional image in the 2nd cutting position. It is a figure which shows the cross-sectional image in the 3rd cutting position. It is a figure which shows the cross-sectional image in the 4th cutting position. It is a figure which shows the cross-sectional image in the 5th cutting position. It is a figure which shows the cross-sectional image in the 6th cutting position. It is a figure which shows the cross-sectional image in the 7th cutting position. It is a figure which shows the cross-sectional image in the 8th cutting position.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Image generation apparatus group 11 CR apparatus 12 CT apparatus 20 Management server 30 Diagnosis apparatus 31 Main body apparatus 32 Image display apparatus 33 Keyboard 34 Mouse 101 CPU
DESCRIPTION OF SYMBOLS 102 Main memory 103 Hard disk drive 104 FD drive 105 CD-ROM drive 106 I / O interface 200 Image display program 210 Image acquisition part 220 Area search part 230 Auxiliary extraction part 240 Middle line / branch detection part 250 Area determination part 260 Image Generation unit 270 Image display unit 300 Medical image display device 310 Image acquisition unit 320 Region search unit 330 Auxiliary extraction unit 340 Middle line / branch detection unit 350 Region determination unit 360 Image generation unit 370 Image display unit

Claims (8)

An image acquisition unit for acquiring a cross-sectional image of the subject;
The cross-sectional image acquired by the image acquisition unit is searched for an area having image uniformity corresponding to the uniformity of the cross-section of a predetermined constituent part among various constituent parts constituting the subject. An image processing apparatus comprising an area search unit. The component is a component other than bone;
The image processing apparatus according to claim 1, wherein the region search unit searches for a region having a higher uniformity than an image density uniformity of a bone image. .   An image creating unit that creates an extracted image obtained by extracting the constituent parts in the cross-sectional image and / or a removed image obtained by removing the constituent parts from the cross-sectional image based on a search result in the region searching unit; The image processing apparatus according to claim 1, wherein An auxiliary extraction unit that extracts each region having an image feature corresponding to the feature of the component from each region searched by the region search unit;
The image processing apparatus according to claim 3, wherein the image creating unit creates the removed image and / or the extracted image based on each region extracted by the auxiliary extracting unit. .   The image processing apparatus according to claim 4, wherein the auxiliary extraction unit uses an extraction condition that defines a height of image density.   The image processing apparatus according to claim 4, wherein the auxiliary extraction unit uses an extraction condition that defines a density distribution on the image. An image acquisition process for acquiring a cross-sectional image of the subject;
With respect to the cross-sectional image acquired in the image acquisition process, a search is made for a region having image uniformity corresponding to the uniformity of the cross-section of a predetermined constituent part among various constituent parts constituting the subject. An image processing method comprising: an area search process. Executed in a computer, on the computer,
An image acquisition unit for acquiring a cross-sectional image of the subject;
The cross-sectional image acquired by the image acquisition unit is searched for an area having image uniformity corresponding to the uniformity of the cross-section of a predetermined constituent part among various constituent parts constituting the subject. An image processing program for constructing an area search unit.