CN113616942B - A real-time tracking method and device for lung tumors and radiotherapy equipment - Google Patents

Abstract

The invention discloses a lung tumor real-time tracking method, a device and radiotherapy equipment, wherein the lung tumor real-time tracking method specifically comprises the following steps: s1: acquiring a lung 4DCT image, acquiring a lung tumor sketch and a first breathing curve according to the lung 4DCT image, and simultaneously acquiring tumor position and shape data of different phases of the lung; s2: in the radiotherapy process, acquiring a liver ultrasonic image of a patient in real time, and acquiring a real-time second breathing curve according to the liver ultrasonic image; s3: phase matching is carried out on the first breathing curve obtained in the step S1 and the real-time second breathing curve obtained in the step S2, so that the lung tumor position and shape at the moment are obtained; s4: and (3) transmitting the information such as the lung tumor position, the lung tumor shape and the like obtained in the step (S3) to a grating driver, and controlling the grating to dynamically adjust. According to the invention, real-time ultrasound is combined with 4DCT, and an indirect tumor tracking model of phase matching is performed through a breathing curve, so that information such as lung tumor shape, three-dimensional coordinates and the like can be transmitted to the grating in real time, and the grating is regulated, thereby realizing dynamic accurate radiotherapy.

Description

A real-time tracking method and device for lung tumors and radiotherapy equipment

Technical Field

The present invention belongs to the technical field of radiotherapy, and in particular relates to a real-time tracking method and device for lung tumors and radiotherapy equipment.

Background technique

Before radiotherapy, patients are positioned using laser or IVS (Image Viewing System), and during radiotherapy, the tumor is considered static and motionless. However, lung tumors will shift and deform with breathing. Even with precise positioning, lung tumors will deviate from the target position due to breathing movement, resulting in the inability of all rays to act on the lung tumor target area during radiotherapy, causing a certain degree of damage to the surrounding critical organs, and the radiotherapy effect will be reduced.

Some existing treatment devices or treatment methods have certain problems in lung treatment, as follows:

Solution 1: ELEKTA's CLARITY ultrasound device uses ultrasound images to obtain three-dimensional images of the prostate. This device is only used for prostate treatment because it cannot provide information about lung tumors and cannot be used for real-time tracking of lung tumor targets. In addition, an infrared positioning device is installed on the ultrasound probe, which is very expensive and difficult to popularize in clinical practice.

Option 2, application number is CN201910258157.7, the applicant is the Affiliated Cancer Hospital of Fudan University, which discloses a liver radiotherapy target positioning technology based on ultrasound imaging, which is only used for real-time tracking of liver tumors, not chest tumors.

Solution 3: Accuray's CyberKnife achieves lung tumor radiotherapy by real-time tracking of lung gold markers. However, it uses the respiratory movement of the body surface to establish a respiratory movement model and uses two X-RAY devices for phase confirmation assistance to track the gold markers on the lung tumor. It is an invasive tracking solution with radiation.

Solution 4: Varian uses RPM (Real Time Position Management) technology to obtain human 4DCT (Four-Dimensional Computed Tomography) data. Varian RPM places marker blocks on the surface of the human chest, collects the movement information of the marker blocks with breathing through a camera, generates 4DCT, and dynamically tracks lung tumors. The cost is high, the operation is difficult, and there is a large error in the accuracy of tumor tracking due to body surface information.

Solution 5: Vision RT's SGRT (Surface Guided Radiation Therapy) technology uses three cameras to obtain the patient's body surface information. Vision RT uses three 3D stereo cameras to obtain the patient's body surface information, thereby dynamically guiding radiotherapy. The cost is high, and the accuracy of the body surface information in tumor tracking has a large error.

Summary of the invention

In order to solve the above technical problems, the present invention proposes a real-time tracking method, device and radiotherapy equipment for lung tumors, which solves the problem of decreased radiotherapy effect caused by the movement of the tumor target area with breathing during radiotherapy, and realizes dynamic and precise radiotherapy for lung tumors. It also reduces the cost increase caused by equipment upgrades and improves clinical popularity.

In order to achieve the above object, the technical solution of the present invention is as follows:

In one aspect, the present invention discloses a method for real-time tracking of lung tumors, which specifically comprises the following steps:

S1: Acquire lung 4DCT images, obtain lung tumor delineation and first respiratory curve based on the lung 4DCT images, and simultaneously obtain tumor location and shape data at different phases of the lungs;

S2: During radiotherapy, the patient's liver ultrasound image is collected in real time, and a real-time second respiratory curve is obtained based on the liver ultrasound image;

S3: performing phase matching on the first respiratory curve obtained by S1 and the real-time second respiratory curve obtained by S2 to obtain the position and shape of the lung tumor at that moment;

S4: The information such as the position and shape of the lung tumor obtained by S3 is transmitted to the grating driver to control the grating to perform dynamic adjustment.

On the basis of the above technical solution, the following improvements can be made:

As a preferred solution, in S1, obtaining the lung tumor outline according to the lung 4DCT image includes the following: outlining the tumor boundary in different phases of the lung 4DCT image to obtain the lung tumor outline.

As a preferred solution, in S2, the real-time second respiratory curve is obtained by:

Use AI deep learning models to identify features that need to be tracked in ultrasound images of the patient's liver;

The identified liver feature point set is processed using the optical flow tracking algorithm;

Output the second breathing curve in real time.

As a preferred solution, if the optical flow tracking algorithm cannot obtain a real-time second respiratory curve after processing the identified liver feature point set, the AI deep learning model re-identifies the features that need to be tracked in the patient's liver ultrasound image, and again uses the optical flow tracking algorithm to process the identified liver feature point set until a real-time second respiratory curve is obtained.

In another aspect, the present invention discloses a real-time tracking device for lung tumors, comprising:

A first respiratory curve acquisition device is used to acquire a lung 4DCT image, and obtain a lung tumor outline and a first respiratory curve based on the lung 4DCT image, and simultaneously obtain tumor position and shape data at different phases of the lung;

A second respiratory curve obtaining device is used to collect a patient's liver ultrasound image in real time and obtain a real-time second respiratory curve based on the liver ultrasound image;

A breathing curve matching device, used for performing phase matching between the first breathing curve obtained by the first breathing curve obtaining device and the real-time second breathing curve obtained by the second breathing curve obtaining device, so as to obtain the position and shape of the lung tumor at that moment;

The grating control device is used to transmit information such as the position and shape of the lung tumor obtained by the respiratory curve matching device to the grating driver to control the grating to perform dynamic adjustment.

As a preferred solution, the first respiratory curve obtaining device outlines the tumor boundary in different phases of the lung 4DCT image to obtain the lung tumor outline.

As a preferred solution, the second breathing curve obtaining device obtains the real-time second breathing curve by:

Use AI deep learning models to identify features that need to be tracked in ultrasound images of the patient's liver;

The identified liver feature point set is processed using the optical flow tracking algorithm;

Output the second breathing curve in real time.

In addition, the present invention also discloses a radiotherapy device, which is operated by using any of the above-mentioned real-time tracking methods for lung tumors; or includes any of the above-mentioned real-time tracking devices for lung tumors.

The present invention provides a real-time lung tumor tracking method, device and radiotherapy equipment that combines real-time ultrasound with 4DCT, and uses a respiratory curve to perform phase matching to form an indirect tumor tracking model. The human liver is located to the right below the diaphragm, and the respiratory movement of the lungs will drive the periodic movement of the diaphragm, thereby also driving the periodic movement of the liver. Therefore, the periodic movement obtained from the liver can reflect the periodicity of the respiratory motion curve. Using this method model, information such as the shape and three-dimensional coordinates of the lung tumor can be transmitted to the grating in real time, and the grating can be adjusted to achieve dynamic and precise radiotherapy.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

FIG1 is a flow chart of a method for real-time tracking of lung tumors provided by an embodiment of the present invention.

FIG. 2 is a matching diagram of a first breathing curve and a second breathing curve provided by an embodiment of the present invention.

Among them: 1-first breathing curve; 2-second breathing curve.

Detailed ways

The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Using ordinal numbers “first,” “second,” “third,” etc. to describe common objects merely indicates that different instances of similar objects are involved and is not intended to imply that the objects so described must have a given order in time, space, order, or in any other manner.

In addition, the expression of “comprising” an element is an “open” expression, which merely means that a corresponding component or method exists, and should not be interpreted as excluding additional components or methods.

In order to achieve the purpose of the present invention, in some embodiments of a method, device and radiotherapy equipment for real-time tracking of lung tumors, as shown in FIG1 , the method for real-time tracking of lung tumors specifically comprises the following steps:

S1: Acquire lung 4DCT images, obtain lung tumor delineation and first respiratory curve based on the lung 4DCT images, and simultaneously obtain tumor location and shape data at different phases of the lungs;

S2: During radiotherapy, the patient's liver ultrasound image is collected in real time, and a real-time second respiratory curve is obtained based on the liver ultrasound image;

S3: Phase matching is performed between the first breathing curve obtained by S1 and the real-time second breathing curve obtained by S2, as shown in FIG2 , so as to obtain the breathing phase of the patient at that moment, and then confirm the position and shape of the lung tumor according to the phase;

S4: The information such as the position and shape of the lung tumor obtained in S3 is transmitted to the grating driver to control the grating to perform dynamic adjustment, so that the grating can be adjusted according to the dynamic shape and position of the lung tumor.

In order to further optimize the implementation effect of the present invention, in some other embodiments, the remaining characteristic technologies are the same, except that, in S1, obtaining the lung tumor outline based on the lung 4DCT image includes the following contents: outlining the tumor boundary in different phases of the lung 4DCT image to obtain the lung tumor outline.

In order to further optimize the implementation effect of the present invention, in some other embodiments, the remaining characteristic technologies are the same, except that, in S2, the real-time second breathing curve is obtained by the following content:

Use AI deep learning models to identify features that need to be tracked in ultrasound images of the patient's liver;

The optical flow tracking algorithm is used to process the identified liver feature point set and quickly output it at each subsequent moment, so that the periodic law of the second respiratory curve can be obtained;

Output the second breathing curve in real time.

In order to further optimize the implementation effect of the present invention, in some other embodiments, the other feature technologies are the same, the difference is that if the optical flow tracking algorithm cannot obtain the real-time second respiratory curve after processing the identified liver feature point set, the AI deep learning model re-identifies the features that need to be tracked in the patient's liver ultrasound image, and again uses the optical flow tracking algorithm to process the identified liver feature point set until the real-time second respiratory curve is obtained.

The embodiment of the present invention further discloses a real-time tracking device for lung tumors, comprising:

A first respiratory curve acquisition device is used to acquire a lung 4DCT image, and obtain a lung tumor outline and a first respiratory curve based on the lung 4DCT image, and simultaneously obtain tumor position and shape data at different phases of the lung;

A second respiratory curve obtaining device is used to collect a patient's liver ultrasound image in real time and obtain a real-time second respiratory curve based on the liver ultrasound image;

A breathing curve matching device, used for performing phase matching between the first breathing curve obtained by the first breathing curve obtaining device and the real-time second breathing curve obtained by the second breathing curve obtaining device, so as to obtain the position and shape of the lung tumor at that moment;

The grating control device is used to transmit information such as the position and shape of the lung tumor obtained by the respiratory curve matching device to the grating driver to control the grating to perform dynamic adjustment.

In order to further optimize the implementation effect of the present invention, in some other implementations, the other characteristic technologies are the same, except that the first respiratory curve acquisition device outlines the tumor boundary in different phases of the lung 4DCT image to obtain the lung tumor outline.

In order to further optimize the implementation effect of the present invention, in some other embodiments, the remaining characteristic technologies are the same, except that the second breathing curve obtaining device obtains the real-time second breathing curve through the following contents:

Use AI deep learning models to identify features that need to be tracked in ultrasound images of the patient's liver;

The identified liver feature point set is processed using the optical flow tracking algorithm;

Output the second breathing curve in real time.

In addition, an embodiment of the present invention further discloses a radiotherapy device, which is operated using the real-time tracking method for lung tumors disclosed in any of the above embodiments; or includes the real-time tracking device for lung tumors disclosed in any of the above embodiments.

Compared with the current static treatment that assumes that the target area does not change, the real-time lung tumor tracking method based on liver ultrasound images and chest 4DCT tracks ultrasound images without adding additional radiation doses, and can relatively accurately infer the target area of lung tumors in real time, reducing damage to critical organs and improving radiotherapy effects. In addition, ultrasound equipment is inexpensive and easy to popularize in clinical practice.

Compared with solutions 1 to 5 in the background technology, the present invention has the following beneficial effects.

Compared with Solution 1: This invention is used for real-time tracking and radiotherapy of lung tumors. There are more lung tumor patients than prostate tumor patients, so it has more clinical practical value. It is low-cost and easy to popularize clinically.

Compared with the second solution, the present invention is used for real-time tracking and radiotherapy of lung tumors, while the second solution can only be used for tracking liver tumors.

Compared with Solution 3: The present invention is a non-invasive, radiation-free and low-cost lung tumor tracking solution.

Compared with Scheme 4: the liver features collected by the present invention through ultrasound imaging are in vivo features, so the respiratory curve tracked is more reliable, while reducing costs and operating difficulty.

Compared with Scheme 5: The present invention is a respiratory movement feature obtained through internal organ characteristics, which has smaller errors and higher credibility than the surface information of Scheme 5.

The method of the present invention uses ultrasound imaging, which is a medical imaging method that is harmless to the human body and can be used multiple times. The present invention tracks liver features and combines the phase information of lung 4DCT tumors. The position of the ultrasound probe does not affect the accelerator beam output and does not hinder treatment. The present invention uses the respiratory movement reflected by the liver and the respiratory curve of 4DCT to match the period and phase, and can quickly output phase information. The present invention uses ultrasound equipment, which has mature technology and low price, and is conducive to clinical popularization.

In summary, the present invention provides a real-time lung tumor tracking method, device and radiotherapy equipment that combines real-time ultrasound with 4DCT, and an indirect tumor tracking model that performs phase matching through the respiratory curve. The human liver is located to the right below the diaphragm, and the respiratory movement of the lungs will drive the periodic movement of the diaphragm, thereby also driving the periodic movement of the liver. Therefore, the periodic movement obtained from the liver can reflect the periodicity of the respiratory motion curve. Using this method model, information such as the shape and three-dimensional coordinates of the lung tumor can be transmitted to the grating in real time, and the grating can be adjusted to achieve dynamic and precise radiotherapy.

It should be understood that the various techniques described herein can be implemented in combination with hardware or software, or a combination thereof. Thus, the method and apparatus of the present invention, or certain aspects or portions of the method and apparatus of the present invention, can take the form of program code (i.e., instructions) embedded in a tangible medium, such as a floppy disk, a CD-ROM, a hard disk drive, or any other machine-readable storage medium, wherein when the program is loaded into a machine such as a computer and executed by the machine, the machine becomes a device for practicing the present invention.

The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable ordinary technicians in the field to understand the content of the present invention and implement it. They cannot be used to limit the protection scope of the present invention. Any equivalent changes or modifications made according to the spirit of the present invention should be included in the protection scope of the present invention.

Claims (3)

1. A real-time tracking device for lung tumors, comprising: A first respiratory curve acquisition device is used to acquire a lung 4DCT image, and obtain a lung tumor outline and a first respiratory curve based on the lung 4DCT image, and simultaneously obtain tumor position and shape data at different phases of the lung; A second respiratory curve obtaining device, used for collecting a patient's liver ultrasound image in real time, and obtaining a real-time second respiratory curve based on the liver ultrasound image; The second breathing curve obtaining device obtains the real-time second breathing curve by: Use AI deep learning models to identify features that need to be tracked in ultrasound images of the patient's liver; The identified liver feature point set is processed using the optical flow tracking algorithm; Outputting a second respiratory curve in real time; a respiratory curve matching device, used to phase match the first respiratory curve obtained by the first respiratory curve obtaining device with the real-time second respiratory curve obtained by the second respiratory curve obtaining device to obtain a real-time lung tumor position and shape; The grating control device is used to transmit the lung tumor position and shape information obtained by the respiratory curve matching device to the grating driver to control the grating to perform dynamic adjustment. 2. The real-time lung tumor tracking device according to claim 1 is characterized in that the first respiratory curve acquisition device outlines the tumor boundary in different phases of the lung 4DCT image to obtain the lung tumor outline. 3. A radiotherapy device, characterized in that it comprises the real-time tracking device for lung tumors as described in claim 1 or 2.