Medical image processing apparatus, medical image processing method, medical image processing program, and radiation therapy apparatus

Abstract

To provide a medical image processing device, a medical image processing method, a medical image processing program, and a radiation therapy device that allow an object inside the body of a patient to be accurately tracked from a transparent image of the patient.SOLUTION: A medical image processing device includes a first image acquisition unit, a second image acquisition unit, a first likelihood distribution calculation unit, a tracking propriety determination unit, and a tracking unit. The first image acquisition unit acquires a first image which is a transparent image of a patient. The second image acquisition unit acquires a second image which is a transparent image of the patient generated at the time different from the time that the first image is generated. The first likelihood distribution calculation unit calculates first likelihood distribution that indicates likelihood distribution indicating object likelihood in the first image. The tracking propriety determination unit determines the propriety of the object tracking on the basis of the first likelihood distribution. The tracking unit tracks a position of the object in the second image according to the determination result.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] Embodiments of the present invention relate to a medical image processing apparatus, a medical image processing method, a medical image processing program, and a radiation therapy apparatus.

Background Art

[0002] Radiation therapy is a treatment method of destroying a lesion in a patient's body by irradiating the lesion with radiation. At this time, the radiation needs to be accurately irradiated to the position of the lesion. This is because if the normal tissue in the patient's body is irradiated with radiation, it may affect the normal tissue. Therefore, when performing radiation therapy, first, at the treatment planning stage, computed tomography (CT) is performed in advance, and the position of the lesion in the patient's body is grasped three-dimensionally. Then, based on the grasped position of the lesion, the direction of irradiation and the intensity of the irradiated radiation are planned so as to reduce the irradiation to normal tissue. After that, at the treatment stage, the patient's position is adjusted to the position of the patient at the treatment planning stage, and the radiation is irradiated to the lesion according to the irradiation direction and irradiation intensity planned at the treatment planning stage.

[0003] In the patient positioning at the treatment stage, three-dimensional CT data is virtually placed in the treatment room, and the position of the bed on which the patient is actually lying in the treatment room is adjusted so that it coincides with the position of the three-dimensional CT data. More specifically, the deviation of the patient's position between the two images is obtained by comparing an X-ray fluoroscopic image of the patient's body taken while lying on the bed and a digitally reconstructed radiograph (DRR) image obtained by virtually reconstructing an X-ray fluoroscopic image from a three-dimensional CT image taken during treatment planning. Then, the bed is moved based on the deviation of the patient's position obtained by image comparison, and the positions of the lesion and bone in the patient's body are aligned with those at the treatment planning time. After that, while comparing the X-ray fluoroscopic image and the DRR image taken again, radiation is irradiated to the lesion.

[0004] When the lesion of a patient is in an organ that moves due to the movement of breathing or heartbeat, such as the lungs or liver, it is necessary to identify the position of the lesion during irradiation. For example, by taking a fluoroscopic image of the patient being irradiated with radiation, the position of the lesion can be tracked. When the lesion does not appear clearly in the fluoroscopic image, the position of the lesion can be indirectly tracked by tracking a marker placed in the patient's body. As methods of irradiating radiation, there are tracking irradiations that track the position of the lesion and irradiate, and ambush irradiations that irradiate when the lesion comes to the position at the time of treatment planning. These irradiation methods are called respiratory synchronization irradiation methods.

[0005] However, for example, when an object such as a lesion or a marker overlaps with an organ such as the liver with a low X-ray transmittance, the lesion or the marker may not appear clearly in the fluoroscopic image. Also, in the fluoroscopic image, there may be a pattern that is difficult to distinguish from a marker, such as a rib. In these cases, it may become impossible to track the position of an object such as a lesion or a marker.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0007] The problem to be solved by the present invention is to provide a medical image processing apparatus, a medical image processing method, a medical image processing program, and a radiation therapy apparatus that can accurately track an object in a patient's body from a fluoroscopic image of the patient.

Means for Solving the Problems

[0008] The medical image processing apparatus according to the embodiment is an apparatus for tracking the position of an object in a patient's body, and includes a first image acquisition unit, a second image acquisition unit, a first likelihood distribution calculation unit, a tracking determination unit, and a tracking unit. The first image acquisition unit acquires a plurality of first images of the patient's fluoroscopic image with different imaging directions. The second image acquisition unit acquires a plurality of second images of the patient's fluoroscopic image generated at a different time from the first image with different imaging directions. The first likelihood distribution calculation unit calculates a first likelihood distribution indicating the distribution of likelihoods representing the object-likeness in each of the plurality of first images acquired by the first image acquisition unit. The tracking determination unit determines whether or not the object can be tracked based on the first likelihood distribution calculated by the first likelihood distribution calculation unit. The tracking unit tracks the position of the object in the second image acquired by the second image acquisition unit according to the determination result of the tracking determination unit.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiments for Carrying Out the Invention

[0010] Hereinafter, a medical image processing apparatus, a medical image processing method, a medical image processing program, and a radiation therapy apparatus according to embodiments will be described with reference to the drawings.

[0011] (First Embodiment) FIG. 1 is a block diagram showing the schematic configuration of a treatment system according to the first embodiment. The treatment system 1 includes, for example, a treatment table 10, a couch control unit 11, two radiation sources 20 (radiation source 20-1 and radiation source 20-2), two radiation detectors 30 (radiation detector 30-1 and radiation detector 30-2), a treatment beam irradiation door 40, an irradiation control device 50, and a medical image processing apparatus 100.

[0012] Note that the “-” and the subsequent number attached to each reference numeral shown in FIG. 1 are for identifying the correspondence. More specifically, in the correspondence between the radiation source 20 and the radiation detector 30, it indicates that the radiation source 20-1 and the radiation detector 30-1 correspond to form one set, and the radiation source 20-2 and the radiation detector 30-2 correspond to form another set. In the following description, when representing a plurality of identical components without distinction, they are represented without showing the “-” and the subsequent number.

[0013] The treatment table 10 is a couch for fixing a subject (patient) P who receives treatment by radiation. The couch control unit 11 is a control unit that controls the translation mechanism and the rotation mechanism provided on the treatment table 10 in order to change the direction in which the treatment beam B is irradiated to the patient P fixed on the treatment table 10. The couch control unit 11 controls each of the translation mechanism and the rotation mechanism of the treatment table 10 in three axial directions, that is, in six axial directions, for example.

[0014] The radiation source 20-1 irradiates the radiation r-1 for fluoroscoping the inside of the patient P from a predetermined angle. The radiation source 20-2 irradiates the radiation r-2 for fluoroscoping the inside of the patient P from a predetermined angle different from that of the radiation source 20-1. The radiation r-1 and the radiation r-2 are, for example, X-rays. FIG. 1 shows a case where X-ray imaging is performed on the patient P fixed on the treatment table 10 from two directions. In FIG. 1, illustration of a control unit that controls irradiation of the radiation r by the radiation source 20 is omitted.

[0015] The radiation detector 30-1 detects the radiation r-1 that has been irradiated from the radiation source 20-1, passed through the inside of the patient P, and reached, and generates an X-ray fluoroscopic image of the inside of the patient P according to the magnitude of the energy of the detected radiation r-1. The radiation detector 30-2 detects the radiation r-2 that has been irradiated from the radiation source 20-2, passed through the inside of the patient P, and reached, and generates an X-ray fluoroscopic image of the inside of the patient P according to the magnitude of the energy of the detected radiation r-2.

[0016] The radiation detector 30 has X-ray detectors arranged in a two-dimensional array, and generates a digital image representing the magnitude of the energy of the radiation r that has reached each X-ray detector as a digital value as an X-ray fluoroscopic image. The radiation detector 30 is, for example, a Flat Panel Detector (FPD), an image intensifier, or a color image intensifier. In the following description, it is assumed that each radiation detector 30 is an FPD. The radiation detector 30 (FPD) outputs each generated X-ray fluoroscopic image to the medical image processing apparatus 100. In FIG. 1, illustration of a control unit that controls generation of the X-ray fluoroscopic image by the radiation detector 30 is omitted.

[0017] In FIG. 1, the configuration of the treatment system 1 including two imaging devices (a set of a radiation source 20 and a radiation detector 30) is shown. However, the number of imaging devices included in the treatment system 1 is not limited to two. For example, the treatment system 1 may include three or more imaging devices (three or more sets of a radiation source 20 and a radiation detector 30).

[0018] The treatment beam irradiation port 40 irradiates the radiation for destroying the lesion in the patient P's body as the treatment beam B. The treatment beam B is, for example, X-ray, γ-ray, electron beam, proton beam, neutron beam, heavy particle beam, or the like. The treatment beam B is irradiated linearly from the treatment beam irradiation port 40 to the patient P (more specifically, the lesion in the patient P's body).

[0019] The irradiation control device 50 controls the irradiation of the treatment beam B by the treatment beam irradiation port 40. The irradiation control device 50 causes the treatment beam B to be irradiated from the treatment beam irradiation port 40 to the patient P in accordance with an irradiation instruction signal that indicates the irradiation timing of the treatment beam B output from the medical image processing device 100.

[0020] In FIG. 1, the configuration of the treatment system 1 including one fixed treatment beam irradiation port 40 is shown, but it is not limited thereto, and the treatment system 1 may include a plurality of treatment beam irradiation ports. For example, the treatment system 1 may further include a treatment beam irradiation port that irradiates the treatment beam to the patient P from the horizontal direction. Also, the treatment system 1 may be configured such that one treatment beam irradiation port rotates around the patient P to irradiate the treatment beam to the patient P from various directions. More specifically, the treatment beam irradiation port 40 shown in FIG. 1 may be configured to be rotatable 360 degrees with respect to the rotation axis in the horizontal direction Y shown in FIG. 1. The treatment system 1 having such a configuration is called a rotating gantry type treatment system. In the rotating gantry type treatment system, the radiation source 20 and the radiation detector 30 also rotate 360 degrees simultaneously with respect to the same axis as the rotation axis of the treatment beam irradiation port 40.

[0021] The medical image processing device 100 tracks the position of an object within the body of patient P that moves due to the movement of patient P's respiration or heartbeat, such as the lungs or liver, and determines the irradiation timing for irradiating the lesion of patient P with the treatment beam B. The object within the body of patient P is not limited to a metal marker placed within the body of patient P. For example, the object within the body of patient P may be a lesion within the body of patient P. In the following description, an example where the object is a marker will be described.

[0022] The medical image processing device 100 automatically determines the irradiation timing of the treatment beam B to be irradiated to the lesion by tracking the image of the marker in the fluoroscopic X-ray image of patient P taken in real time by each radiation detector 30. At this time, the medical image processing device 100 determines whether or not the position of the image of the marker placed within the body of the tracked patient P is within a predetermined range for performing radiation therapy. Then, when the position of the image of the marker is within the predetermined range, the medical image processing device 100 outputs an irradiation instruction signal for instructing the irradiation of the treatment beam B to the irradiation control device 50. Thereby, the irradiation control device 50 irradiates the treatment beam B to the treatment beam irradiation door 40 in accordance with the irradiation instruction signal output by the medical image processing device 100.

[0023] Also, the medical image processing device 100 performs image processing for positioning to align the current position of patient P with a position predetermined in a planning stage before performing radiation therapy, such as in the treatment planning stage. The medical image processing device 100 automatically searches for a position of patient P suitable for performing radiation therapy by comparing a DRR image obtained by virtually reconstructing a fluoroscopic X-ray image from a three-dimensional CT image or the like taken in advance before performing radiation therapy with the current fluoroscopic X-ray image output by each radiation detector 30. Then, the medical image processing device 100 obtains the movement amount of the treatment table 10 for moving the current position of patient P fixed to the treatment table 10 to a suitable position predetermined for performing radiation therapy. Details regarding the configuration and processing of the medical image processing device 100 will be described later.

[0024] Note that the medical image processing apparatus 100 and the radiation detector 30 may be connected by a LAN (Local Area Network) or a WAN (Wide Area Network).

[0025] Next, the configuration of the medical image processing apparatus 100 that constitutes the treatment system 1 will be described. FIG. 2 is a block diagram showing a schematic configuration of a medical image processing apparatus according to the first embodiment. The medical image processing apparatus 100 shown in FIG. 2 includes a first image acquisition unit 101, a first likelihood distribution calculation unit 102, a tracking feasibility determination unit 103, a tracking unit 104, a second image acquisition unit 105, and a second likelihood distribution calculation unit 106.

[0026] The first image acquisition unit 101 acquires a plurality of first images with different imaging directions, which are fluoroscopic images of the patient P. The first image may be an X-ray fluoroscopic image taken by the radiation detector 30 during the positioning of the patient P described above, or a DRR image obtained by virtually reconstructing an X-ray fluoroscopic image from a three-dimensional CT image taken in advance before performing radiation therapy.

[0027] The first likelihood distribution calculation unit 102 calculates a first likelihood distribution indicating the distribution of likelihoods representing the marker (object) -likeness in each of the plurality of first images 60 acquired by the first image acquisition unit 101.

[0028] FIG. 3 is a diagram showing an example of a first image according to the first embodiment. The first image 60 includes an image of a marker 62 placed in the body of the patient P and an image of a lesion 63 in the body of the patient P. The first likelihood distribution calculation unit 102 calculates the likelihood distribution not for the entire first image 60 but for the tracking region 61. The tracking region 61 is a region for tracking the position of the marker 62 and is a region that includes the range within which the marker 62 moves due to the movement of the patient P's respiration and heartbeat. By thus limiting the target for calculating the first likelihood distribution to a part (tracking region 61) in the first image 60, the processing load on the first likelihood distribution calculation unit 102 can be reduced.

[0029] For example, the tracking area 61 is determined based on the position of the marker 62 specified in the CT image during treatment planning. Also, the tracking area 61 is determined considering a margin based on possible errors that may occur during actual treatment. For example, the tracking area 61 may be an area projected onto the first image, which is a three-dimensional area with a margin added centered on the position of the marker 62 on the CT image. Also, the tracking area 61 may be determined according to a margin determined considering the state of the patient immediately before treatment.

[0030] In addition, in FIG. 3, although the marker 62 is assumed to be a rod-shaped marker, the shape of the marker 62 is not limited to this. For example, it may be a spherical marker.

[0031] Next, a method for calculating the likelihood by the first likelihood distribution calculation unit 102 will be described. The first likelihood distribution calculation unit 102 calculates the likelihood by calculating the similarity between the first image 60 and a template image, which is an image pattern when the marker 62 is projected, and holding the template image in advance.

[0032] When the shape of the shadow of the marker 62 can be predicted in advance, as in the case where the marker 62 is spherical, an image with the shadow drawn may be used as the template image. When the shadow of the marker 62 changes according to the posture of the marker 62 when it is placed inside the patient P, a plurality of template images with the shadow drawn according to the posture of the marker 62 may be generated, and one of the plurality of template images may be selected and used.

[0033] The similarity, which is a numerical value of the likelihood, is represented by the pixel values and spatial correlation values of the template image and the first image 60. For example, the similarity may be the reciprocal of the difference in pixel values at each corresponding pixel position. Also, the similarity may be the cross-correlation value at the corresponding pixel positions.

[0034] Further, the first likelihood distribution calculation unit 102 may generate a discriminator by a machine learning method using a template image including the marker 62 as learning data, and calculate the likelihood using the generated discriminator. For example, a plurality of template images including the marker 62 and first images 60 at positions where the marker 62 is not included are prepared, and a discriminator is generated by learning these by a machine learning method. By using the generated discriminator, it is possible to identify whether or not the marker 62 is included.

[0035] Note that, as the machine learning method, support vector machine, random forest, deep learning, or the like may be used. The first likelihood distribution calculation unit 102 calculates a real value calculated by these machine learning methods as the likelihood. As the real value, for example, the distance to the discrimination boundary, the ratio of the discriminator determined to include the object, or the output value of Softmax may be used.

[0036] Further, the first likelihood distribution calculation unit 102 may calculate the likelihood using the separation degree. FIG. 4 is a diagram showing an example of a template used for calculating the separation degree according to the first embodiment. In an example of the template 70 shown in FIG. 4, it is classified into a first region 71 where the bar-shaped marker 62 exists and a second region 72 other than the first region 71. That is, the second region 72 is a region where the bar-shaped marker 62 does not exist.

[0037] In the calculation of the separation degree, when a region similar to the template 70 exists in the first image 60, the histogram of the pixel values included in the first image 60 is classified into the histogram of the pixel values belonging to the first region 71 and the histogram of the pixel values belonging to the second region 72, respectively. This is because when the image of the marker 62 captured in the first image 60 overlaps the first region 71, the histogram of the pixel values belonging to the first region 71 has a high frequency of pixel values of dark pixels, and the histogram of the pixel values belonging to the second region 72 has a high frequency of pixel values of bright pixels.

[0038] The first likelihood distribution calculation unit 102 quantifies the separability of the histogram of pixel values as described above using Fisher's discrimination criterion. Then, the first likelihood distribution calculation unit 102 calculates the ratio of the average of the variances of the pixel values of the pixels belonging to each region (intra-class variance) to the variance of the pixel values between the respective regions (inter-class variance), and calculates this ratio as the separation degree. In this way, the first likelihood distribution calculation unit 102 calculates the separation degree calculated using the template 70 as the likelihood. The first likelihood distribution calculation unit 102 calculates a first likelihood distribution indicating the likelihood distribution in each of the plurality of first images 60 acquired by the first image acquisition unit 101 using the calculated likelihood.

[0039] The tracking feasibility determination unit 103 determines whether or not the marker 62 can be tracked based on the first likelihood distribution calculated by the first likelihood distribution calculation unit 102. Specifically, the tracking feasibility determination unit 103 calculates the tracking difficulty level in each shooting direction of the first image 60 based on the first likelihood distribution calculated by the first likelihood distribution calculation unit 102. Further, when the tracking difficulty level is higher than a predetermined threshold value, the tracking feasibility determination unit 103 determines that it is impossible to track the marker 62.

[0040] The tracking feasibility determination unit 103 calculates the tracking difficulty level based on the statistic of the first likelihood distribution. The statistic is, for example, a first-order statistic such as the average value of the first likelihood distribution or the variance of the first likelihood distribution, but is not limited thereto. For example, the statistic may be the maximum value of the first likelihood distribution, or may be a value calculated by a first-order expression integrating these numerical values. Further, when the position of the marker 62 corresponding to the first likelihood distribution can be obtained, the tracking feasibility determination unit 103 may calculate the tracking difficulty level by narrowing down to the statistic of the first likelihood distribution around the position of the marker 62. The tracking feasibility determination unit 103 outputs the determination result of whether or not the marker 62 can be tracked for each shooting direction to the tracking unit 104 and the second image acquisition unit 105.

[0041] The tracking unit 104 tracks the position of the marker 62 in the second image acquired by the second image acquisition unit 105 according to the determination result of the tracking feasibility determination unit 103. Details of the tracking process by the tracking unit 104 will be described later.

[0042] The second image acquisition unit 105 acquires a plurality of second fluoroscopic images of the patient P generated at a time different from that of the first image and having different imaging directions. The aforementioned first image is a fluoroscopic image generated based on a three-dimensional image of the patient P taken at the time of treatment planning or a fluoroscopic image taken from the same imaging direction as the second image immediately before treatment. However, the second image is a fluoroscopic image taken by the radiation detector 30 during the treatment of the patient P. In order to track the marker 62, the second image is repeatedly taken at a predetermined time interval.

[0043] It is desirable that the imaging direction of the first image is the same as that of the second image. For example, when the second image is taken from a direction different from that at the time of positioning of the patient P, the first image may be a DRR image simulating a fluoroscopic image taken in the same direction as the second image instead of a fluoroscopic image taken at the time of positioning of the patient P. Also, the first image may be a second image taken at the previous treatment, or an image taken from the same direction as the second image immediately before treatment. Further, the first image may be a moving image of one or more respiratory cycles.

[0044] Note that before treatment by irradiating the treatment beam B on the patient P, the second image acquisition unit 105 determines the imaging direction of the second image used for tracking the position of the marker 62 by the tracking unit 104 based on the determination result of the tracking availability determination unit 103. For example, when the determination result for the first image in the imaging direction of the radiation detector 30-1 is "trackable" and the determination result for the first image in the imaging direction of the radiation detector 30-2 is "trackable", the second image acquisition unit 105 acquires both the second image captured by the radiation detector 30-1 and the second image captured by the radiation detector 30-2. Also, when the determination result for the first image in the imaging direction of the radiation detector 30-1 is "trackable" and the determination result for the first image in the imaging direction of the radiation detector 30-2 is "not trackable", the second image acquisition unit 105 acquires only the second image captured by the radiation detector 30-1. Further, when the determination result for the first image in the imaging direction of the radiation detector 30-1 is "not trackable" and the determination result for the first image in the imaging direction of the radiation detector 30-2 is "trackable", the second image acquisition unit 105 acquires only the second image captured by the radiation detector 30-2.

[0045] In this way, the second image acquisition unit 105 can suppress the exposure of the patient P and improve the success rate of tracking the marker 62 by not acquiring the second image in the imaging direction for which it is determined that the marker 62 cannot be tracked.

[0046] The second likelihood distribution calculation unit 106 calculates a second likelihood distribution indicating the distribution of likelihoods in the second image acquired by the second image acquisition unit 105. Here, the second likelihood distribution calculation unit 106 calculates the second likelihood distribution not for the entire second image but for the tracking region 61 in the second image. Since the method for calculating the second likelihood distribution is the same as the method for calculating the first likelihood distribution, the description is omitted.

[0047] The tracking unit 104 determines the position of the marker 62 in the second image based on the second likelihood distribution calculated by the second likelihood distribution calculation unit 106. For example, the tracking unit 104 determines that the position where the maximum value appears in the second likelihood distribution is the position of the marker 62.

[0048] When the second image is acquired from two directions, once the position of the marker 62 in one of the second images is specified, the position of the marker 62 in the other second image is geometrically limited to the epipolar line. Therefore, the tracking unit 104 may determine that the position where the maximum value appears in the likelihood distribution on the epipolar line in the second likelihood distribution of the other second image is the position of the marker 62. When the second image is acquired from two directions, the tracking unit 104 may geometrically convert and calculate the position of the marker 62 into three-dimensional coordinates.

[0049] The tracking unit 104 determines the irradiation timing of the treatment beam B based on the determined position of the marker 62. The positional relationship between the marker 62 and the lesion 63 can be specified from the fluoroscopic image of the patient P acquired during treatment planning. For this reason, when the position of the lesion 63 in the body of the patient P specified based on the position of the marker 62 is within a predetermined range, the tracking unit 104 transmits an irradiation instruction signal for instructing the irradiation of the treatment beam B to the irradiation control device 50.

[0050] The irradiation control device 50 irradiates the treatment beam B from the treatment beam irradiation door 40 in response to the irradiation instruction signal received from the medical image processing device 100. Thereby, the treatment beam B can be irradiated to the lesion 63 in the body of the patient P.

[0051] On the other hand, when the position of the lesion 63 in the body of the patient P specified based on the position of the marker 62 is not within a predetermined range, the tracking unit 104 does not transmit an irradiation instruction signal to the irradiation control device 50. Thereby, it is possible to suppress the treatment beam B from irradiating a site other than the lesion 63.

[0052] Note that some or all of the functions of the components provided in the medical image processing apparatus 100 described above may be realized by, for example, a hardware processor such as a CPU (Central Processing Unit) and a storage device (a storage device including a non-transitory storage medium) storing a program (software), and various functions may be realized when the processor executes the program. Further, some or all of the functions of the components provided in the medical image processing apparatus 100 described above may be realized by hardware (including a circuit unit; circuitry) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), etc., or various functions may be realized by the cooperation of software and hardware. Further, some or all of the functions of the components provided in the medical image processing apparatus 100 described above may be realized by a dedicated LSI.

[0053] Here, the program (software) may be stored in advance in a storage device (a storage device including a non-transitory storage medium) provided in the treatment system 1 such as a ROM (Read Only Memory), RAM (Random Access Memory), HDD (Hard Disk Drive), flash memory, etc., or may be stored in a removable storage medium (non-transitory storage medium) such as a DVD or CD-ROM, and may be installed in the storage device provided in the treatment system 1 when the storage medium is mounted on a drive device provided in the treatment system 1. Further, the program (software) may be downloaded in advance from another computer device via a network and installed in the storage device provided in the treatment system 1.

[0054] FIG. 5 is a flowchart showing the operation of the medical image processing apparatus in the stage prior to treating a patient according to the first embodiment. The processing according to this flowchart is executed by the medical image processing apparatus 100 at a stage prior to performing treatment by irradiating the treatment beam B to the patient P.

[0055] First, the first image acquisition unit 101 acquires a plurality of first images with different imaging directions, which are fluoroscopic images of the patient P (S101). As described above, the first image may be an X-ray fluoroscopic image taken by the radiation detector 30 during the positioning of the patient P, or a DRR image obtained by virtually reconstructing an X-ray fluoroscopic image from a three-dimensional CT image taken in advance before performing radiation therapy.

[0056] Next, the first likelihood distribution calculation unit 102 calculates a first likelihood distribution indicating the distribution of likelihoods representing the marker (object) -likeness in each of the plurality of first images 60 acquired by the first image acquisition unit 101 (S102). Here, the first likelihood distribution calculation unit 102 calculates the likelihood distribution not for the entire first image 60, but for the likelihood distribution in the tracking region 61 shown in FIG. 3.

[0057] Next, the tracking feasibility determination unit 103 determines the feasibility of tracking the marker 62 based on the first likelihood distribution calculated by the first likelihood distribution calculation unit 102 (S103). For example, the tracking feasibility determination unit 103 calculates the tracking difficulty level in each imaging direction of the first image 60 based on the first likelihood distribution calculated by the first likelihood distribution calculation unit 102. Also, when the tracking difficulty level is higher than a predetermined threshold value, the tracking feasibility determination unit 103 determines that it is impossible to track the marker 62.

[0058] Thereafter, the second image acquisition unit 105 determines the imaging direction of the second image based on the determination result of the tracking feasibility determination unit 103 (S104), and ends the processing according to this flowchart. When performing treatment by irradiating the treatment beam B to the patient P, tracking of the marker 62 is performed based on the second image corresponding to the imaging direction determined in step S104.

[0059] FIG. 6 is a flowchart showing the operation of the medical image processing apparatus during the treatment of a patient according to the first embodiment. The processing according to this flowchart is repeatedly executed by the medical image processing apparatus 100 at predetermined time intervals in the stage where treatment by irradiating the treatment beam B is performed on the patient P.

[0060] First, the second image acquisition unit 105 acquires a second image corresponding to the imaging direction determined in step S104 (S201). The second image is an image captured by the radiation detector 30 during the treatment of the patient P. Specifically, the second image acquisition unit 105 does not acquire a second image for an imaging direction in which the tracking difficulty is higher than a predetermined threshold, and acquires only a second image in which the tracking difficulty is equal to or lower than the predetermined threshold.

[0061] Next, the second likelihood distribution calculation unit 106 calculates a second likelihood distribution indicating the distribution of likelihoods in the second image acquired by the second image acquisition unit 105 (S202). The method for calculating the second likelihood distribution is the same as the method for calculating the first likelihood distribution.

[0062] Next, the tracking unit 104 determines the position of the marker 62 (object) in the second image based on the second likelihood distribution calculated by the second likelihood distribution calculation unit 106 (S203). For example, the tracking unit 104 determines that the position where the maximum value appears in the second likelihood distribution is the position of the marker 62.

[0063] Thereafter, the tracking unit 104 determines the irradiation timing of the treatment beam B based on the determined position of the marker 62 (object) (S204). For example, when the position of the lesion 63 in the patient P specified based on the position of the marker 62 is within a predetermined range, the tracking unit 104 transmits an irradiation instruction signal for instructing the irradiation of the treatment beam B to the irradiation control device 50. The irradiation control device 50 irradiates the treatment beam B from the treatment beam irradiation gate 40 in response to the irradiation instruction signal received from the medical image processing apparatus 100.

[0064] As described above, in the first embodiment, the first image acquisition unit 101 acquires a plurality of first images that are fluoroscopic images of the patient P and have different imaging directions. The second image acquisition unit 105 acquires a plurality of second images that are fluoroscopic images of the patient P generated at a time different from the first images and have different imaging directions. The first likelihood distribution calculation unit 102 calculates a first likelihood distribution indicating the distribution of likelihoods representing object-likeness in each of the plurality of first images acquired by the first image acquisition unit 101. The tracking possibility determination unit 103 determines whether or not an object can be tracked based on the first likelihood distribution calculated by the first likelihood distribution calculation unit 102. The tracking unit 104 tracks the position of the object in the second images acquired by the second image acquisition unit 105 according to the determination result of the tracking possibility determination unit 103. As a result, an object in the patient's body can be tracked with high accuracy from the fluoroscopic images of the patient.

[0065] (Second Embodiment) In the first embodiment, the second image acquisition unit 105 determines the imaging direction of the second images based on the determination result of the tracking possibility determination unit 103. In contrast, in the second embodiment, the tracking unit 104 determines a tracking region, which is a region for tracking the position of the object, based on the determination result of the tracking possibility determination unit 103. As a result, an object in the patient's body can be tracked with higher accuracy. Hereinafter, the second embodiment will be described in detail.

[0066] FIG. 7 is a block diagram showing a schematic configuration of a medical image processing apparatus according to the second embodiment. In FIG. 7, parts corresponding to the parts in FIG. 2 are denoted by the same reference numerals, and the description thereof is omitted.

[0067] The tracking feasibility determination unit 103 determines the feasibility of tracking the marker 62 based on the first likelihood distribution calculated by the first likelihood distribution calculation unit 102. Specifically, the tracking feasibility determination unit 103 calculates the tracking difficulty level in each imaging direction of the first image 60 based on the first likelihood distribution calculated by the first likelihood distribution calculation unit 102. Since the method for calculating the tracking difficulty level is the same as that in the first embodiment, the description thereof is omitted. Also, when the tracking difficulty level is higher than a predetermined threshold value, the tracking feasibility determination unit 103 determines that it is impossible to track the marker 62. Thereafter, the tracking feasibility determination unit 103 outputs the determination results of the feasibility of tracking the marker 62 for each imaging direction to the tracking unit 104. On the other hand, different from the first embodiment, the tracking feasibility determination unit 103 does not output the determination results to the second image acquisition unit 105.

[0068] The second image acquisition unit 105 acquires a plurality of second images of the patient P generated at a time different from that of the first image and having different imaging directions. For example, the second image is an image taken by the radiation detector 30 during the treatment of the patient P. Specifically, the second image acquisition unit 105 acquires both the fluoroscopic image taken by the radiation detector 30-1 and the fluoroscopic image taken by the radiation detector 30-2 as the second images.

[0069] The second likelihood distribution calculation unit 106 calculates a second likelihood distribution indicating the distribution of likelihoods in the second images acquired by the second image acquisition unit 105. Specifically, the second likelihood distribution calculation unit 106 calculates, as the second likelihood distribution, the distribution of likelihoods in the fluoroscopic image (second image) taken by the radiation detector 30-1 and the distribution of likelihoods in the fluoroscopic image (second image) taken by the radiation detector 30-2. Here, the second likelihood distribution calculation unit 106 calculates the second likelihood distribution for the tracking region 61 in the second image, rather than for the entire second image. Since the method for calculating the second likelihood distribution is the same as the method for calculating the first likelihood distribution, the description thereof is omitted.

[0070] The tracking unit 104 determines a tracking area 61 (Fig. 3), which is an area for tracking the position of the marker 62, based on the determination result of the trackability determination unit 103. Specifically, the tracking unit 104 limits the tracking area 61 to an area on the epipolar line for the second image in the shooting direction in which the trackability of the marker 62 is determined by the trackability determination unit 103 to be higher than a predetermined threshold value.

[0071] For example, assume that the trackability for the shooting direction of the radiation detector 30-1 is higher than a predetermined threshold value, and the trackability for the shooting direction of the radiation detector 30-2 is equal to or lower than the predetermined threshold value. In this case, when the position of the marker 62 is specified from the second image taken by the radiation detector 30-2, the position of the marker 62 in the second image taken by the radiation detector 30-1 is geometrically limited to the area on the epipolar line. Therefore, the tracking unit 104 limits the tracking area 61 to an area on the epipolar line for the second image taken by the radiation detector 30-1.

[0072] In this way, a shooting direction in which it is easy to track the marker 62 is determined based on the trackability, and from the second image in the shooting direction in which tracking is difficult, the tracking area 61 is limited to the area on the epipolar line to track the marker 62. Thereby, the medical image processing apparatus 200 of the present embodiment can improve the tracking accuracy of the marker 62.

[0073] Fig. 8 is a flowchart showing the operation of the medical image processing apparatus in the stage before treating a patient according to the second embodiment. The processing according to this flowchart is executed by the medical image processing apparatus 200 at a stage before the treatment by irradiating the treatment beam B to the patient P. Note that steps S301 to S303 in Fig. 8 are the same as steps S101 to S103 in Fig. 5, and thus the description thereof is omitted.

[0074] The tracking feasibility determination unit 103 determines whether there is a tracking difficulty level higher than a predetermined threshold among the tracking difficulty levels of each imaging direction calculated in step S303 (S304). If there is no tracking difficulty level higher than the predetermined threshold (S304: NO), the tracking unit 104 ends the processing according to this flowchart without changing the tracking area 61. On the other hand, if there is a tracking difficulty level higher than the predetermined threshold (S304: YES), the tracking unit 104 calculates a straight line connecting the position of the marker 62 in the imaging direction with the lowest tracking difficulty level and the imaging position (the position of the radiation detector 30) in the imaging direction with the lowest tracking difficulty level as an epipolar line (S305). Then, the tracking unit 104 limits the tracking area 61 in the imaging direction where the tracking difficulty level is higher than the predetermined threshold to the area on the epipolar line calculated in step S305 (S306), and ends the processing according to this flowchart.

[0075] In this way, the tracking unit 104 does not change the tracking area 61 for the second image in the imaging direction where the tracking difficulty level is determined to be below the predetermined threshold. On the other hand, for the second image in the imaging direction where the tracking difficulty level is determined to be higher than the predetermined threshold, the tracking unit 104 limits the tracking area 61 to the area on the epipolar line calculated based on the position of the marker 62 in the imaging direction with the lowest tracking difficulty level. Thereby, the medical image processing apparatus 200 of the present embodiment can improve the tracking accuracy of the marker 62.

[0076] (Third Embodiment) In the first and second embodiments, it is assumed that the irradiation control device 50 for controlling the treatment beam irradiation gate 40 is provided. In contrast, in the third embodiment, the irradiation control device 50 is not provided in the treatment system 1, and the radiation treatment device 300 has a function of controlling the treatment beam irradiation gate 40. Hereinafter, the third embodiment will be described in detail.

[0077] FIG. 9 is a block diagram showing a schematic configuration of a radiation therapy apparatus according to a third embodiment. In FIG. 9, parts corresponding to the respective parts in FIG. 2 are denoted by the same reference numerals, and the description thereof is omitted. The radiation therapy apparatus 300 according to the third embodiment includes an irradiation control unit 301.

[0078] The tracking unit 104 determines the position of the marker 62 in the second image based on the second likelihood distribution calculated by the second likelihood distribution calculation unit 106. For example, the tracking unit 104 determines that the position at which the maximum value occurs in the second likelihood distribution is the position of the marker 62.

[0079] The tracking unit 104 determines the irradiation timing of the treatment beam B based on the determined position of the marker 62. The positional relationship between the marker 62 and the lesion 63 can be specified from the fluoroscopic image of the patient P acquired at the time of treatment planning. Therefore, when the position of the lesion 63 in the body of the patient P specified based on the position of the marker 62 is within a predetermined range, the tracking unit 104 outputs an irradiation instruction signal for instructing the irradiation of the treatment beam B to the irradiation control unit 301.

[0080] The irradiation control unit 301 irradiates the treatment beam B from the treatment beam irradiation gate 40 in response to the irradiation instruction signal output from the tracking unit 104. Thereby, the treatment beam B can be irradiated to the lesion 63 in the body of the patient P.

[0081] On the other hand, when the position of the lesion 63 in the body of the patient P specified based on the position of the marker 62 is not within a predetermined range, the tracking unit 104 does not output an irradiation instruction signal to the irradiation control unit 301. Thereby, it is possible to suppress the treatment beam B from being irradiated to a site other than the lesion 63.

[0082] FIG. 10 is a flowchart showing the operation of the radiation therapy apparatus during the treatment of a patient according to the third embodiment. The processing according to this flowchart is repeatedly executed at predetermined time intervals by the radiation therapy apparatus 300 at the stage where treatment by irradiating the treatment beam B is performed on the patient P. Since steps S401 to S403 in FIG. 10 are the same as steps S201 to S203 in FIG. 6, the description thereof is omitted.

[0083] The irradiation control unit 301 causes the treatment beam B to be irradiated from the treatment beam irradiation gate 40 according to the position of the marker 62 (object) determined by the tracking unit 104 in step S403. For example, the irradiation control unit 301 causes the treatment beam B to be irradiated from the treatment beam irradiation gate 40 when the position of the lesion 63 in the body of the patient P specified based on the position of the marker 62 is within a predetermined range.

[0084] As described above, the radiation therapy apparatus 300 according to the third embodiment includes an irradiation control unit 301 that controls the treatment beam irradiation gate 40 in addition to the functions of the medical image processing apparatus 100 according to the first embodiment. Also with the radiation therapy apparatus 300 of the present embodiment, the tracking accuracy of the marker 62 can be improved in the same manner as in the first embodiment.

[0085] In the above embodiment, the object tracked by the tracking unit 104 is assumed to be a metal marker placed in the body of the patient P, but it may be a lesion in the body of the patient P. In this case, an image including the entire lesion or a part of the lesion may be cut out from the first image and used as a template image. When the first image is a DRR image generated from a CT image including treatment plan information, since the position of the lesion in the CT image is included in the treatment plan information, an image in which this lesion is projected may be used as the template image. When the first image is an X-ray fluoroscopic image taken by the radiation detector 30 during the positioning of the patient P, since the DRR image and the position of the patient P match, the position of the above-mentioned lesion may be diverted, and the surrounding X-ray fluoroscopic image may be cut out and used as the template image.

[0086] In addition, the tracking feasibility determination unit 103 may present the tracking difficulty level in each imaging direction to the user using a notification unit (not shown). For example, when the user plans the imaging direction, the tracking feasibility determination unit 103 may notify the imaging direction with a low tracking difficulty level. Thereby, the user can estimate the success rate of the respiration synchronization irradiation method and determine whether to limit the tracking of the marker 62 to only the second image in one imaging direction.

[0087] Note that the above-described medical image processing apparatuses 100, 200, and radiation treatment apparatus 300 can also be realized, for example, by using a general-purpose computer apparatus as the basic hardware. That is, the first image acquisition unit 101, the first likelihood distribution calculation unit 102, the tracking feasibility determination unit 103, the tracking unit 104, the second image acquisition unit 105, the second likelihood distribution calculation unit 106, and the irradiation control unit 301 can be realized by causing a processor mounted on the above-described computer apparatus to execute a program. At this time, the medical image processing apparatuses 100, 200, and radiation treatment apparatus 300 may be realized by pre-installing the above-described program in the computer apparatus, or may be stored in a storage medium such as a CD-ROM, or the above-described program may be distributed via a network and the program may be appropriately installed in the computer apparatus. Further, B and C can be realized by appropriately using a memory built in or externally attached to the above-described computer apparatus, a hard disk, or a storage medium such as a CD-R, CD-RW, DVD-RAM, or DVD-R.

[0088] So far, several embodiments of the present invention have been described, but these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalent scope thereof.

Description of Reference Numerals

[0089] 1 ··· Treatment system 100 ··· Medical image processing device 101 ··· First image acquisition unit 102 ··· First likelihood distribution calculation unit 103 ··· Tracking feasibility determination unit 104 ··· Tracking unit 105 ··· Second image acquisition unit 106 ··· Second likelihood distribution calculation unit 200 ··· Medical image processing device 300 ··· Radiation therapy device 301 ··· Irradiation control unit

Claims

1. A medical image processing apparatus for tracking the position of an object within a patient, comprising: a first image acquisition unit that acquires a plurality of first images of the patient, which are fluoroscopic images of the patient and have different imaging directions with respect to the patient; a second image acquisition unit that acquires a plurality of second images of the patient, which are fluoroscopic images of the patient generated at a time different from the first images and have different imaging directions with respect to the patient; for each of the plurality of first images acquired by the first image acquisition unit, calculating a similarity at each pixel position with respect to the object as a likelihood representing object-likeness, and calculating a first likelihood distribution indicating the distribution of the likelihood in the first image; a tracking feasibility determination unit that determines whether tracking of the object is feasible based on the first likelihood distribution calculated by the first likelihood distribution calculation unit; for each of the plurality of second images acquired by the second image acquisition unit, calculating a similarity at each pixel position with respect to the object as the likelihood, and calculating a second likelihood distribution indicating the distribution of the likelihood in the second image; a tracking unit that, when it is determined by the tracking feasibility determination unit that tracking is feasible, determines the position of the object in the second image based on the second likelihood distribution calculated by the second likelihood distribution calculation unit, and tracks the position of the object; A medical image processing apparatus comprising the above components.

2. The medical image processing apparatus according to claim 1, wherein when there exist a first likelihood distribution determined to be trackable and a first likelihood distribution determined to be non-trackable by the tracking feasibility determination unit, the second image acquisition unit acquires a second image having the same imaging direction as the first image corresponding to the first likelihood distribution determined to be trackable, and does not acquire a second image having the same imaging direction as the first image corresponding to the first likelihood distribution determined to be non-trackable.

3. The medical image processing apparatus according to claim 2, wherein the second image acquisition unit determines the imaging direction of the second image to be used for tracking the position of the object by the tracking unit before treatment is performed on the patient.

4. The medical image processing apparatus according to claim 1, wherein the tracking unit determines a tracking region, which is a region for tracking the position of the object, based on the determination result of the tracking feasibility determination unit.

5. When the tracking unit identifies the position of the object in one of the plurality of second images, the position of the object in the other images among the plurality of second images is geometrically limited to a region on the epipolar line. The medical image processing apparatus according to claim 4.

6. The object is a metal marker. The medical image processing apparatus according to any one of claims 1 to 5.

7. The first image is a fluoroscopic image generated based on a three-dimensional image of the patient taken during treatment planning, or a fluoroscopic image taken from the same imaging direction as the second image immediately before treatment. The second image is a fluoroscopic image taken during treatment of the patient. The medical image processing apparatus according to any one of claims 1 to 6.

8. A medical image processing method for tracking the position of an object in a patient's body, comprising: a first image acquisition step of acquiring a plurality of first images of the patient that are fluoroscopic images and have different imaging directions with respect to the patient; a second image acquisition step of acquiring a plurality of second images of the patient that are fluoroscopic images generated at a time different from the first images and have different imaging directions with respect to the patient; for each of the plurality of first images acquired in the first image acquisition step, calculating a similarity at each pixel position with respect to the object as a likelihood representing object-likeness, and calculating a first likelihood distribution indicating the distribution of the likelihood in the first image; a first likelihood distribution calculation step; a tracking feasibility determination step of determining whether tracking of the object is feasible based on the first likelihood distribution calculated in the first likelihood distribution calculation step; for each of the plurality of second images acquired in the second image acquisition step, calculating a similarity at each pixel position with respect to the object as the likelihood, and calculating a second likelihood distribution indicating the distribution of the likelihood in the second image; a second likelihood distribution calculation step; a tracking step of, when it is determined in the tracking feasibility determination step that tracking is feasible, determining the position of the object in the second image based on the second likelihood distribution calculated in the second likelihood distribution calculation step, and tracking the position of the object; A medical image processing method comprising the steps of:

9. A medical image processing program for tracking the position of an object in a patient's body, causing a computer to: On a computer, A first image acquisition step of acquiring a plurality of first images of the patient's fluoroscopic image with different imaging directions with respect to the patient; A second image acquisition step of acquiring a plurality of second images of the patient's fluoroscopic image generated at a time different from the first image with different imaging directions with respect to the patient; For each of the plurality of first images acquired by the first image acquisition step, calculating the similarity at each pixel position with respect to the object as a likelihood representing the object-likeness, and calculating a first likelihood distribution indicating the distribution of the likelihood in the first image; A tracking feasibility determination step of determining whether or not the object can be tracked based on the first likelihood distribution calculated by the first likelihood distribution calculation step; For each of the plurality of second images acquired by the second image acquisition step, calculating the similarity at each pixel position with respect to the object as the likelihood, and calculating a second likelihood distribution indicating the distribution of the likelihood in the second image; A tracking step of determining the position of the object in the second image based on the second likelihood distribution calculated by the second likelihood distribution calculation step and tracking the position of the object when it is determined by the tracking feasibility determination step that tracking is possible; A medical image processing program for causing the above to be executed.

10. A radiation therapy apparatus that irradiates a patient with radiation while tracking the position of an object in the patient's body, A first image acquisition unit that acquires a plurality of first images of the patient's fluoroscopic image with different imaging directions with respect to the patient; A second image acquisition unit that acquires a plurality of second images of the patient's fluoroscopic image generated at a time different from the first image with different imaging directions with respect to the patient; For each of the plurality of first images acquired by the first image acquisition unit, calculating the similarity at each pixel position with respect to the object as a likelihood representing the object-likeness, and calculating a first likelihood distribution indicating the distribution of the likelihood in the first image; A tracking feasibility determination unit that determines whether or not the object can be tracked based on the first likelihood distribution calculated by the first likelihood distribution calculation unit; For each of the plurality of second images acquired by the second image acquisition unit, calculating the similarity at each pixel position with respect to the object as the likelihood, and calculating a second likelihood distribution indicating the distribution of the likelihood in the second image; a second likelihood distribution calculation unit; When it is determined by the tracking determination unit that tracking is possible, based on the second likelihood distribution calculated by the second likelihood distribution calculation unit, determining the position of the object in the second image, and a tracking unit that tracks the position of the object; An irradiation control unit that controls the irradiation of the radiation according to the position of the object tracked by the tracking unit; A radiation therapy apparatus comprising the above.

Images