KR-102961664-B1 - Medical image processing device, medical image processing method, computer-readable memory medium, and radiation therapy device

KR102961664B1KR 102961664 B1KR102961664 B1KR 102961664B1KR-102961664-B1

Abstract

A medical image processing device of an embodiment comprises a first image acquisition unit, a second image acquisition unit, a first likelihood distribution calculation unit, a tracking capability determination unit, and a tracking unit. The first image acquisition unit acquires a first image, which is a projection image of a patient. The second image acquisition unit acquires a second image, which is a projection image of the patient generated at a different time from the first image. The first likelihood distribution calculation unit calculates a first likelihood distribution representing a distribution of likelihoods indicating object features in the first image. The tracking capability determination unit determines whether tracking of the object is possible based on the first likelihood distribution. The tracking unit tracks the position of the object in the second image according to the result of this determination.

Inventors

히라이 류스케
사카타 유키노부
다니자와 아키유키
오카야 게이코
모리 신이치로

Assignees

도시바 에너지시스템즈 가부시키가이샤

Dates

Publication Date: 20260508
Application Date: 20220222
Priority Date: 20210312

Claims (11)

It is a medical image processing device that tracks the location of objects inside a patient's body, and A first image acquisition unit that acquires a plurality of first images with different shooting directions as fluoroscopic images of the above-mentioned patient, and A second image acquisition unit that acquires a plurality of second images with different shooting directions, as projection images of the patient generated at a different time from the first image above, and A first likelihood distribution calculation unit that, for each of the plurality of first images acquired by the first image acquisition unit, calculates the similarity at each pixel location for the object as a likelihood indicating the features of the object, and calculates a first likelihood distribution indicating the distribution of the likelihood in the first image; A tracking approval/disapproval determination unit that determines whether tracking of the object is possible based on the first likelihood distribution calculated by the first likelihood distribution calculation unit, and A second likelihood distribution calculation unit that, for each of the plurality of second images acquired by the second image acquisition unit, calculates the similarity at each pixel location for the object as the likelihood, and calculates a second likelihood distribution representing the distribution of the likelihood in the second images; A medical image processing device having a tracking unit that determines the position of the object in the second image and tracks the position of the object based on the second likelihood distribution calculated by the second likelihood distribution calculation unit when it is determined that tracking is possible by the tracking determination unit.
In paragraph 1, A medical image processing device wherein, when there exists a first likelihood distribution determined to be traceable by the tracking ability determination unit and a first likelihood distribution determined to be untraceable, the second image having the same shooting direction as the first image corresponding to the first likelihood distribution determined to be traceable is acquired, and the second image having the same shooting direction as the first image corresponding to the first likelihood distribution determined to be untraceable is not acquired.
In paragraph 2, A medical image processing device in which the second image acquisition unit determines the shooting direction of the second image used for tracking the position of the object by the tracking unit before treatment is performed on the patient.
In paragraph 1, A medical image processing device in which the tracking unit determines a tracking area, which is an area for tracking the position of the object, based on the determination result of the tracking approval/disapproval unit.
In paragraph 4, A medical image processing device wherein the tracking unit, when specifying the position of the object in one of the plurality of second images, geometrically limits the position of the object in another of the plurality of second images to an area on an epipolar line.
In paragraph 1, The above object is a medical image processing device, which is a metal marker.
In any one of paragraphs 1 through 6, The first image is a projection image generated based on a three-dimensional image of the patient taken during the treatment planning phase, or a projection image taken from the same shooting direction as the second image immediately before treatment. The above second image is a medical image processing device, which is a fluoroscopic image taken during treatment of the patient.
It is a medical image processing method for tracking the location of objects inside a patient's body, and A first image acquisition process for acquiring a plurality of first images with different shooting directions as fluoroscopic images of the above-mentioned patient, and A second image acquisition process for acquiring a plurality of second images with different shooting directions, wherein the second images are fluoroscopic images of the patient generated at a different time from the first image, and A first likelihood distribution calculation process for each of the plurality of first images acquired by the first image acquisition process, calculating the similarity at each pixel location for the object as a likelihood indicating the features of the object, and calculating a first likelihood distribution indicating the distribution of the likelihood in the first image; A tracking determination process for determining whether tracking of the object is possible based on the first likelihood distribution calculated by the first likelihood distribution calculation process, and A second likelihood distribution calculation process for each of the plurality of second images acquired by the second image acquisition process, calculating the similarity at each pixel location for the object as the likelihood, and calculating a second likelihood distribution representing the distribution of the likelihood in the second images; A medical image processing method comprising a tracking process that, when it is determined that tracking is possible by the tracking possibility determination process, determines the position of the object in the second image based on the second likelihood distribution calculated by the second likelihood distribution calculation process, and tracks the position of the object.
It is a computer-readable storage medium storing a medical image processing program that tracks the location of objects inside a patient's body, and on the computer, A first image acquisition process for acquiring a plurality of first images with different shooting directions as fluoroscopic images of the above-mentioned patient, and A second image acquisition process for acquiring a plurality of second images with different shooting directions, wherein the second images are fluoroscopic images of the patient generated at a different time from the first image, and A first likelihood distribution calculation process for each of the plurality of first images acquired by the first image acquisition process, calculating the similarity at each pixel location for the object as a likelihood indicating the features of the object, and calculating a first likelihood distribution indicating the distribution of the likelihood in the first image; A tracking determination process for determining whether tracking of the object is possible based on the first likelihood distribution calculated by the first likelihood distribution calculation process, and A second likelihood distribution calculation process for each of the plurality of second images acquired by the second image acquisition process, calculating the similarity at each pixel location for the object as the likelihood, and calculating a second likelihood distribution representing the distribution of the likelihood in the second images; If it is determined that tracking is possible by the tracking possibility determination process above, the position of the object in the second image is determined based on the second likelihood distribution calculated by the second likelihood distribution calculation process above, and a tracking process for tracking the position of the object is executed. A computer-readable storage medium storing a medical image processing program.
A radiation therapy device that irradiates the patient while tracking the location of an object inside the patient's body, and A first image acquisition unit that acquires a plurality of first images with different shooting directions as fluoroscopic images of the above-mentioned patient, and A second image acquisition unit that acquires a plurality of second images with different shooting directions, as projection images of the patient generated at a different time from the first image above, and A first likelihood distribution calculation unit that, for each of the plurality of first images acquired by the first image acquisition unit, calculates the similarity at each pixel location for the object as a likelihood indicating the features of the object, and calculates a first likelihood distribution indicating the distribution of the likelihood in the first image; A tracking approval/disapproval determination unit that determines whether tracking of the object is possible based on the first likelihood distribution calculated by the first likelihood distribution calculation unit, and A second likelihood distribution calculation unit that, for each of the plurality of second images acquired by the second image acquisition unit, calculates the similarity at each pixel location for the object as the likelihood, and calculates a second likelihood distribution representing the distribution of the likelihood in the second images; When it is determined that tracking is possible by the tracking capability determination unit, a tracking unit that 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, and A radiation therapy device having an irradiation control unit that controls the irradiation of the radiation according to the position of the object tracked by the tracking unit.
delete

Description

Medical image processing device, medical image processing method, computer-readable memory medium, and radiation therapy device Embodiments of the present invention relate to a medical image processing device, a medical image processing method, a medical image processing program, and a radiation therapy device. Radiation therapy is a treatment method that destroys lesions within a patient's body by irradiating them with radiation. In this process, the radiation must be delivered precisely to the location of the lesion. This is because if radiation is directed at normal tissues within the patient's body, it may affect those healthy tissues as well. Therefore, when performing radiation therapy, a Computed Tomography (CT) scan is first conducted during the treatment planning stage to determine the location of the lesion within the patient's body in three dimensions. Based on the identified location of the lesion, the direction and intensity of the radiation are planned to minimize exposure to normal tissues. Subsequently, during the treatment stage, the patient's position is aligned with that of the planning stage, and radiation is delivered to the lesion according to the direction and intensity determined during the planning phase. In the patient position alignment phase of the treatment, 3D CT data is virtually placed within the treatment room, and the position of the bed is adjusted so that the actual position of the patient lying on the mobile bed within the treatment room aligns with the position of this 3D CT data. More specifically, the misalignment of the patient's position between the two images is determined by comparing two images: an X-ray fluoroscopic image of the patient's body taken while lying on the bed, and a Digitally Reconstructed Radiograph (DRR) image, which is a virtual X-ray fluoroscopic image reconstructed from the 3D CT image taken during the treatment planning phase. Then, based on the misalignment of the patient's position obtained through image comparison, the bed is moved to align the position of the lesion or bone within the patient's body with that of the treatment planning phase. Subsequently, radiation is irradiated onto the lesion while comparing the X-ray fluoroscopic image and the DRR image taken again. When a patient's lesion is located in organs such as the lungs or liver that shift due to respiration or heartbeats, it is necessary to pinpoint the location of the lesion being irradiated. For example, the location of the lesion can be tracked by taking X-ray fluoroscopic images of the patient being irradiated. If the lesion is not clearly visible in the X-ray fluoroscopic image, its location can be indirectly tracked by tracing markers implanted within the patient's body. As for methods of irradiation, there are tracking irradiation, which irradiates by following the location of the lesion, and impacted irradiation, which irradiates when the lesion reaches the planned treatment location. These irradiation methods are referred to as respiration-synchronized irradiation. However, for example, if objects such as lesions or markers overlap with organs such as the liver, which have low X-ray transmittance, the lesions or markers may not be clearly captured in the X-ray fluoroscopy image. Additionally, there may be patterns within the X-ray fluoroscopy image that are difficult to distinguish from markers, such as ribs. In such cases, there is a possibility that the location of objects such as lesions or markers cannot be tracked. FIG. 1 is a block diagram showing the schematic configuration of a treatment system according to a first embodiment. FIG. 2 is a block diagram showing the schematic configuration of a medical image processing device according to a first embodiment. FIG. 3 is a drawing showing an example of a first image relating to a first embodiment. FIG. 4 is a drawing showing an example of a template used in calculating a separation diagram regarding the first embodiment. FIG. 5 is a flowchart showing the operation of a medical image processing device in the pre-treatment stage of a patient according to the first embodiment. FIG. 6 is a flowchart showing the operation of a medical image processing device during the treatment of a patient according to the first embodiment. FIG. 7 is a block diagram showing the schematic configuration of a medical image processing device according to a second embodiment. FIG. 8 is a flowchart showing the operation of a medical image processing device in the pre-treatment stage of a patient according to a second embodiment. FIG. 9 is a block diagram showing the schematic configuration of a radiation therapy device according to a third embodiment. FIG. 10 is a flowchart showing the operation of a radiation therapy device during patient treatment according to a third embodiment. Hereinafter, an embodiment of a medical image processing device, a medical image processing method, a medical image processing program, and a radiation therapy de