A radiotherapy-assisted positioning method, terminal device, and storage medium

Abstract

The present invention relates to a radiotherapy-assisted positioning method, a terminal device, and a storage medium. The method includes: collecting a template two-dimensional planar image and a template depth image of a patient in a CT room, and extracting template contour data, body posture features, and template depth data of radiotherapy region features; collecting a real-time two-dimensional planar image and a real-time depth image of the patient in a radiotherapy room, and extracting real-time contour data, body posture features, and real-time depth data of radiotherapy region features; displaying the template image and the real-time image on the same image, and calculating and annotating deviation values on the image; and medical staff adjusting the patient's body posture based on the displayed image and the deviation values. The present invention can assist medical staff in accurately positioning radiotherapy patients and improving the positioning efficiency.

Description

Technical Field

[0001] The present invention relates to the field of precision radiotherapy, and in particular to a radiotherapy auxiliary positioning method, terminal equipment and storage medium. Background Art

[0002] Tumor radiotherapy (abbreviated as radiotherapy) is a local treatment method that uses radiation to treat tumors. It is an important method of tumor treatment. Precision radiotherapy is an important development direction in the field of radiotherapy. Radiotherapy positioning products mainly assist patients in aligning and fixing their body positions during radiotherapy to ensure that the radiotherapy rays can accurately act on the lesion site. In the current market, radiotherapy positioning products mainly include radiotherapy positioning films, radiotherapy fixation frames, vacuum negative pressure bags, etc. Against the background of an aging population, the number of cancer patients continues to grow, and the demand for radiotherapy continues to rise, which has promoted the rapid development of the radiotherapy positioning product industry.

[0003] Because medical staff do not have intuitive images or materials such as film and television pictures to assist in the repeated positioning process, the pass rate of CBCT (cone beam computed tomography) scanning verification after positioning is relatively low, and repeated positioning is required. In terms of development, with the development of high-end medical equipment, the radiotherapy positioning industry is gradually moving towards intelligence, high operability, reliability and comfort. Therefore, how to accurately obtain the patient's three-dimensional body surface information in real time before radiotherapy and quickly capture the patient's posture information, and then determine whether the patient's position has moved, is currently the focus of research in this field. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes a radiotherapy assisted positioning method, a terminal device and a storage medium.

[0005] The specific plan is as follows:

[0006] A radiotherapy auxiliary positioning method comprises the following steps:

[0007] S1: Collect the template 2D plane image and template depth image of the patient when being tested in the CT room;

[0008] S2: extracting a template contour image of the patient based on the template two-dimensional plane image; extracting template depth data of the patient's body features and template depth data of the radiotherapy area features based on the template depth image, and generating a corresponding template human body side contour image based on the template depth data of the body features;

[0009] S3: Acquire real-time two-dimensional planar images and real-time depth images of patients in the radiotherapy room while preparing for radiotherapy;

[0010] S4: After extracting the real-time contour image of the patient based on the real-time two-dimensional planar image and calculating the contour image deviation value between the real-time contour image and the template contour image corresponding to the patient, display the real-time contour image and the template contour image on the same image, and mark the calculated contour image deviation value therein.

[0011] Extract the real-time depth data of the patient's body posture characteristics and the real-time depth data of the radiotherapy area characteristics based on the real-time depth image, and generate the corresponding real-time human side contour image; calculate the body posture characteristics deviation value between the real-time human side contour image and the template human side contour image corresponding to the patient, and at the same time calculate the radiotherapy area characteristics deviation value between the real-time depth data of the real-time radiotherapy area characteristics and the template depth data corresponding to the patient. After that, display the real-time human side contour image and the template human side contour image on the same image, and mark the corresponding body posture characteristics deviation value and radiotherapy area characteristics deviation value therein.

[0012] S5: Medical staff adjust the patient's body posture based on the image and deviation value displayed in step S4 to make the deviation value less than the threshold.

[0013] Furthermore, the two-dimensional planar image is collected by an RGB camera.

[0014] Furthermore, the depth image is collected by a structured light camera composed of a projector and an infrared lens. After projecting specific light information onto the human body surface and the background by the projector, the reflected structured light is collected by the infrared lens to obtain the depth image.

[0015] Furthermore, before extracting the contour image of the patient, it also includes: performing filtering processing and grayscale processing on the two-dimensional planar image and converting it into a grayscale image.

[0016] Furthermore, the depth data of the body posture characteristics are the depth data corresponding to multiple feature points on the central axis of the human body contour in the depth image.

[0017] Furthermore, the depth data of the radiotherapy area characteristics are the depth data corresponding to the pixel points where the radiotherapy area characteristics are located in the depth image.

[0018] Furthermore, in the calculation of the radiotherapy area characteristics deviation value between the real-time depth data of the real-time radiotherapy area characteristics and the template depth data, directly take the difference between the depth data corresponding to each feature point as the deviation value of each feature point.

[0019] A radiotherapy-assisted positioning terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method in the above embodiments of the present invention.

[0020] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method in the above embodiments of the present invention are implemented.

[0021] By adopting the above technical solution, the present invention can assist medical staff in accurately positioning radiotherapy patients and improve the positioning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 The flowchart of Embodiment 1 of the present invention is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] To further illustrate the embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, mainly used to illustrate the embodiments, and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation manners and the advantages of the present invention.

[0024] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0025] Embodiment 1:

[0026] The embodiment of the present invention provides a radiotherapy-assisted positioning method. As Figure 1 shown, the method includes the following steps:

[0027] S1: Collect the two-dimensional plane image and the depth image of the patient during the detection in the CT room as the template two-dimensional plane image and the template depth image respectively.

[0028] Before radiotherapy, the patient needs to first locate the tumor in the CT room. The detection is to detect the tumor. At this time, the patient lies flat on the bed.

[0029] In this embodiment, the two-dimensional plane image is collected by an RGB camera; the depth image is collected by a structured light camera composed of a projector and an infrared (IR) lens. After the projector projects specific light information onto the human body surface and the background, the reflected structured light is collected by the infrared lens to obtain the depth image.

[0030] S2: Extract the template contour image of the patient based on the template two-dimensional plane image; extract the template depth data of the body posture characteristics and the template depth data of the radiotherapy area characteristics of the patient based on the template depth image, and generate the corresponding template human side contour image based on the template depth data of the body posture characteristics.

[0031] When extracting the template contour image of a patient from a two-dimensional planar image, since the collected two-dimensional planar image is an RGB color image and color information is not required for contour extraction, therefore, before extracting the contour image of the patient in the embodiment, it further includes: performing filtering processing and grayscale processing on the two-dimensional planar image to convert it into a grayscale image, and then extracting the human contour image from the grayscale image.

[0032] Any existing algorithm can be used for the contour extraction algorithm, which is not limited here. In this embodiment, the Roberts gradient operator is used for edge contour detection.

[0033] The depth data of the body posture features is the depth data corresponding to multiple feature points on the central axis of the human body contour in the depth image. The multiple feature points can be set by taking values at intervals on the central axis, such as setting a feature point every 5 cm on the central axis.

[0034] Different diseases (tumor locations) correspond to different radiotherapy regions, and the radiotherapy regions can be divided into different positions of the human body such as the chest and abdomen, neck, and limbs. The radiotherapy region features are the easily recognizable feature points in the radiotherapy region, which can be set manually or automatically recognized by a third-party algorithm. If the radiotherapy region has obvious features such as the head, chest, and abdomen, its radiotherapy region can be obtained by training a neural network model. If the radiotherapy region has less obvious features such as the limbs, its radiotherapy region can be set manually.

[0035] The depth data of the radiotherapy region features is the depth data corresponding to the pixel points where the radiotherapy region features are located in the depth image.

[0036] Based on the depth data of the body posture features, a human body side contour image can be obtained by fitting with an existing algorithm.

[0037] Since the template contour image, the template human body side contour image, and the template depth data of the radiotherapy region features need to be used later, these images and data need to be saved.

[0038] S3: Collect the two-dimensional planar image and the depth image of the patient when preparing for radiotherapy in the radiotherapy room as the real-time two-dimensional planar image and the real-time depth image respectively.

[0039] The radiotherapy room is used to perform radiotherapy on the patient. The acquisition methods of the two-dimensional planar image and the depth image are the same as those in step S1, which will not be elaborated here.

[0040] S4: Based on the real-time two-dimensional planar image, extract the real-time contour image of the patient. After calculating the contour image deviation value between the real-time contour image and the template contour image corresponding to this patient, display the real-time contour image and the template contour image on the same image, and mark the calculated contour image deviation value on the displayed image. Based on the real-time depth image, extract the real-time depth data of the patient's body posture characteristics and the real-time depth data of the radiotherapy area characteristics, and generate the corresponding real-time human side contour image; calculate the body posture characteristics deviation value between the real-time human side contour image and the template human side contour image corresponding to this patient, and at the same time calculate the radiotherapy area characteristics deviation value between the real-time depth data of the real-time radiotherapy area characteristics and the template depth data corresponding to this patient. After that, display the real-time human side contour image and the template human side contour image on the same image, and mark the corresponding body posture characteristics deviation value and radiotherapy area characteristics deviation value on the displayed image.

[0041] The deviation value between the real-time image and the template image (including the contour image and the human side contour image) can be obtained by using existing similarity calculation algorithms, which are not limited here. In this embodiment, the SSIM algorithm is used.

[0042] In the calculation of the radiotherapy area characteristics deviation value between the real-time depth data of the real-time radiotherapy area characteristics and the template depth data, directly take the difference of the depth data corresponding to each feature point as the deviation value of each feature point.

[0043] By displaying the real-time image and the template image (including the contour image and the human side contour image) on the same image, it can help medical staff intuitively view the deviation situation between the two; through the calculation and display of the deviation value, it can help medical staff accurately know the deviation size; through the combination of the two, it can better help medical staff adjust the position and body posture of the patient.

[0044] S5: Medical staff adjust the patient's body posture based on the image and deviation value displayed in step S4 to make the deviation value less than the threshold.

[0045] For each deviation value (contour image deviation value, body posture characteristics deviation value, radiotherapy area characteristics deviation value), its corresponding threshold needs to be set. Those skilled in the art can set the threshold size according to requirements, which are not limited here.

[0046] In this embodiment, two deviation values, namely the body posture characteristics deviation value and the radiotherapy area characteristics corresponding to the human side contour image, are set. First, the position of the whole body can be roughly adjusted based on the body posture characteristics deviation value corresponding to the human side contour image, and then the body position of the area to be radiated can be finely adjusted based on the radiotherapy area characteristics deviation value, making the adjustment more effective and accurate.

[0047] Through the method of this embodiment, the body posture correction of the patient in three-dimensional directions can be achieved, and the purpose of radiotherapy-assisted positioning can be achieved.

[0048] In the radiotherapy stage of the embodiment of the present invention, the radiotherapy positioning of the patient can be directly achieved without CT detection and positioning, which solves the disadvantages in the prior art that the patient needs to be re-detected and positioned by CT in the radiotherapy room and then radiotherapy is carried out, and avoids the damage to human health caused by multiple CT detections during multiple radiotherapy sessions.

[0049] Embodiment 2:

[0050] The present invention also provides a radiotherapy-assisted positioning terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above method embodiment of Embodiment 1 of the present invention are implemented.

[0051] Further, as an executable solution, the radiotherapy-assisted positioning terminal device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The radiotherapy-assisted positioning terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the composition structure of the above radiotherapy-assisted positioning terminal device is only an example of the radiotherapy-assisted positioning terminal device, and does not constitute a limitation on the radiotherapy-assisted positioning terminal device. It may include more or fewer components than the above, or combine some components, or different components. For example, the radiotherapy-assisted positioning terminal device may further include input / output devices, network access devices, buses, etc. The embodiments of the present invention do not make limitations in this regard.

[0052] Further, as an executable solution, the so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the radiotherapy-assisted positioning terminal device, and connects various parts of the entire radiotherapy-assisted positioning terminal device through various interfaces and lines.

[0053] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory, the processor realizes various functions of the radiotherapy-assisted positioning terminal device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

[0054] The present invention also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method in the above embodiments of the present invention are realized.

[0055] If the modules / units integrated in the radiotherapy-assisted positioning terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to realize all or part of the processes in the above method embodiments of the present invention, it can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc.

[0056] Although the present invention is specifically shown and described in combination with the preferred embodiments, those skilled in the art should understand that various changes can be made to the present invention in form and detail without departing from the spirit and scope of the present invention defined by the appended claims, and all are within the protection scope of the present invention.

Claims

1. A radiotherapy-assisted positioning method, characterized in that, it includes the following steps: S1: Collect the template two-dimensional planar image and the template depth image of the patient when being examined in the CT room; S2: Extract the template contour image of the patient based on the template two-dimensional planar image; extract the template depth data of the body posture characteristics and the template depth data of the radiotherapy region characteristics of the patient based on the template depth image, and generate the corresponding template human side contour image based on the template depth data of the body posture characteristics; S3: Collect the real-time two-dimensional planar image and the real-time depth image of the patient when preparing for radiotherapy in the radiotherapy room; S4: Extract the real-time contour image of the patient based on the real-time two-dimensional planar image, and after calculating the contour image deviation value between the real-time contour image and the corresponding template contour image of this patient, display the real-time contour image and the template contour image on the same image, and mark the calculated contour image deviation value therein; Extract the real-time depth data of the body posture characteristics and the real-time depth data of the radiotherapy region characteristics of the patient based on the real-time depth image, and generate the corresponding real-time human side contour image; calculate the body posture characteristics deviation value between the real-time human side contour image and the corresponding template human side contour image of this patient, and at the same time calculate the radiotherapy region characteristics deviation value between the real-time depth data of the real-time radiotherapy region characteristics and the corresponding template depth data of this patient, and then display the real-time human side contour image and the template human side contour image on the same image, and mark the corresponding body posture characteristics deviation value and radiotherapy region characteristics deviation value therein; S5: Medical staff adjust the patient's body posture based on the images and deviation values displayed in step S4 so that the deviation value is less than the threshold.

2. The radiotherapy-assisted positioning method according to claim 1, characterized in that: The two-dimensional planar image is collected by an RGB camera.

3. The radiotherapy-assisted positioning method according to claim 1, characterized in that: The depth image is collected by a structured light camera composed of a projector and an infrared lens. After the projector projects specific light information onto the human body surface and the background, the reflected structured light is collected by the infrared lens to obtain the depth image.

4. The radiotherapy-assisted positioning method according to claim 1, characterized in that: Before extracting the contour image of the patient, it further includes: performing filtering processing and grayscale processing on the two-dimensional planar image and converting it into a grayscale image.

5. The radiotherapy-assisted positioning method according to claim 1, characterized in that: The depth data of the body posture characteristics are the depth data corresponding to multiple feature points on the central axis of the human body contour in the depth image.

6. The radiotherapy-assisted positioning method according to claim 1, characterized in that: The depth data of the radiotherapy region characteristics are the depth data corresponding to the pixel points where the radiotherapy region characteristics are located in the depth image.

7. The radiotherapy-assisted positioning method according to claim 1, characterized in that: In the calculation of the radiotherapy region characteristics deviation value between the real-time depth data of the real-time radiotherapy region characteristics and the template depth data, directly take the difference between the depth data corresponding to each feature point as the deviation value of each feature point.

8. A radiotherapy-assisted positioning terminal device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images