Radiation dose estimation method and device

Abstract

Embodiments of the present invention relate to a radiation dose estimation method and apparatus, comprising the following steps: scanning a target body according to a preset interval thickness to obtain scan data of different sections of the target body and parameters corresponding to the scan data; performing three-dimensional reconstruction and two-dimensional conversion on the scan data to obtain a registered dataset; performing tissue segmentation on the dataset to obtain a segmented dataset; comparing the segmented dataset with preset standard data to obtain the element types and densities contained in each tissue; and simulating the scanning imaging process using the target body parameters, scanning positioning parameters, and scanning setting parameters, along with the comparison results, to calculate the radiation dose received by each tissue during the scan. Embodiments of the present invention analyze data information obtained by CBCT to estimate the radiation dose, providing a data basis for parameter setting and dose usage during the CBCT scanning process.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of medical data processing, and in particular to a radiation dose estimation method and device. Background Art

[0002] The oral cavity is a vital component of the human body and the starting point of the digestive system. Composed primarily of the lips, cheeks, tongue, palate, salivary glands, teeth, and jaws, it performs functions such as chewing, swallowing, speech, and sensation, while maintaining the normal morphology of the maxillofacial region. In dentistry, oral cone-beam computed tomography (CBCT), which can present three-dimensional information, plays a crucial role in the diagnosis and treatment of common oral diseases.

[0003] The popularization of CBCT has led to an increase in radiation doses for the general public. How to reduce radiation doses and how to use CBCT data safely, accurately and efficiently have become urgent issues to be addressed. Summary of the Invention

[0004] Based on the above-mentioned situation of the prior art, the purpose of the embodiments of the present invention is to provide a radiation dose estimation method and device, which analyzes the data information obtained by CBCT and estimates the radiation dose to provide a data basis for parameter setting and dosage usage during the CBCT scanning process.

[0005] To achieve the above object, according to one aspect of the present invention, a radiation dose estimation method is provided, comprising the steps of:

[0006] Scanning the target body according to a preset interval thickness to obtain scanning data of different sections of the target body and target body parameters, scanning positioning parameters and scanning setting parameters corresponding to the scanning data;

[0007] Performing three-dimensional reconstruction and two-dimensional conversion on the scan data to obtain a registered data set;

[0008] Performing tissue segmentation on the data set to obtain a segmented data set;

[0009] Comparing the segmented data set with preset standard data to obtain the element types and densities contained in each tissue;

[0010] The target body parameters, scanning positioning parameters, scanning setting parameters and the comparison result are used to simulate the scanning imaging process to calculate the radiation dose received by each tissue in the scanning.

[0011] Furthermore, oral cone-beam CT is used to obtain scanning data of different sections of the target body.

[0012] Furthermore, the target body parameters include the soft tissue thickness of the target body; the scanning positioning parameters include the scanning field of view; the scanning setting parameters include the scanning mode, the beam energy level of the tube voltage, the function of the tube current and time, the automatic exposure time and the rotation time;

[0013] The scanning field of view is a cylinder or a portion of a cylinder, wherein the cylinder has at least one of a diameter of 4 cm to 20 cm and a height of 4 cm to 20 cm;

[0014] The scanning mode includes at least one of a high-definition mode, a normal mode and a low-dose mode.

[0015] Furthermore, a segmentation network is used to organize and segment the data set; the segmentation network is established according to the following steps:

[0016] Constructing an original segmentation network, wherein the original segmentation network includes an encoding module, a feature extraction module and N decoding modules;

[0017] The original segmentation network is trained using the scanned data set to obtain a segmentation network.

[0018] Furthermore, the encoding module is used to encode the input reconstruction data to obtain a semantic feature map;

[0019] The feature extraction module is used to process each semantic feature map obtained by the encoding module to obtain semantic feature maps of different resolutions;

[0020] The N decoding modules are respectively used to obtain prediction probability maps of different tissues based on the semantic feature map.

[0021] Furthermore, the tissues include enamel, dentin, periodontal ligament, alveolar ridge, maxillary sinus floor, bone lamina, trabeculae, root canals and other soft tissues.

[0022] Furthermore, the target body parameters, scanning positioning parameters, scanning setting parameters and the comparison results are used to adopt the Monte Carlo method to simulate the physical process of the interaction between the radiation rays and the body tissues during the scanning imaging process to obtain the radiation dose received by each tissue during the scanning process.

[0023] Furthermore, the radiation dose received by each tissue is output in the form of a distribution tomogram.

[0024] Furthermore, the intensity in the distribution tomogram indicates the radiation dose received by the location during the scanning imaging process.

[0025] According to another aspect of the present invention, a radiation dose estimation device is provided, comprising a data acquisition module, a registration module, a tissue segmentation module, a tissue analysis module and a radiation dose calculation module; wherein,

[0026] The data acquisition module is used to scan the target body according to the preset interval thickness to obtain scanning data of different sections of the target body and target body parameters, scanning positioning parameters and scanning setting parameters corresponding to the scanning data;

[0027] The registration module performs three-dimensional reconstruction and two-dimensional conversion on the scan data to obtain a registered data set;

[0028] The tissue segmentation module performs tissue segmentation on the data set to obtain a segmented data set;

[0029] The tissue analysis module compares the segmented data set with preset standard data to obtain the element types and densities contained in each tissue;

[0030] The radiation dose calculation module simulates the scanning imaging process using the target body parameters, scanning positioning parameters, scanning setting parameters and the comparison result to calculate the radiation dose received by each tissue in the scanning.

[0031] In summary, the present invention provides a radiation dose estimation method and apparatus, including the following steps:

[0032] The target body is scanned according to a preset interval thickness to obtain scanning data of different sections of the target body and target body parameters, scanning positioning parameters and scanning setting parameters corresponding to the scanning data; the scanning data are three-dimensionally reconstructed and two-dimensionally converted to obtain a registered data set; the data set is tissue segmented to obtain a segmented data set; the segmented data set is compared with the preset standard data to obtain the type and density of elements contained in each tissue; the target body parameters, scanning positioning parameters and scanning setting parameters and the comparison results are used to simulate the scanning imaging process to calculate the radiation dose received by each tissue in the scan. The solution of the embodiment of the present invention analyzes the data information obtained by CBCT and estimates the radiation dose to provide a data basis for the parameter setting and dosage of the CBCT scanning process. The technical solution provided by the present invention has the following beneficial technical effects:

[0033] (1) The radiation dose estimation method provided in the embodiment of the present invention takes into account various data influencing factors based on the actually acquired scanning data and the target body parameters, scanning positioning parameters, and scanning setting parameters corresponding to the scanning data. The radiation dose of each tissue is estimated through simulation to provide a data basis for the parameter setting and the used dose of the CBCT scanning process, thereby reducing the used radiation dose while improving the scanning quality by adjusting other parameters.

[0034] (2) The technical solution of the embodiment of the present invention performs three-dimensional segmentation of the dentition and alveolar bone data through a segmentation network, which has a good segmentation effect and can more accurately reflect the positions of different tissues in the image data, making the estimation more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate one or more embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only one or more embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 is a flow chart of a radiation dose estimation method according to an embodiment of the present invention;

[0037] Figure 2 This is a block diagram of a radiation dose estimation device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] To make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present invention.

[0039] It should be noted that, unless otherwise defined, the technical or scientific terms used in one or more embodiments of the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar terms used in one or more embodiments of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "include" or "comprise" mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0040] The radiation dose of CBCT is usually closely related to the scanning field of view, scanning parameters, scanning mode, voxel value size and the detector used. The medical radiation dose caused by CBCT is greater than that of traditional dental X-ray machines. The medical radiation dose caused to the examinee is tens to hundreds of times that of plain films taken by traditional dental X-ray machines. Moreover, the radiation dose varies greatly from device to device. At the same time, the characteristics of oral radiology examinations are that the diagnosis and treatment process requires repeated examinations, and secondly, there are many pediatric patients who are highly sensitive to ionizing radiation. This makes the radiation dose issue of cone beam CT a focus of attention. The method of the embodiment of the present invention estimates the radiation dose under actual scanning conditions, so that reasonable dose control can be achieved by using the estimation results, and the shooting area can be accurately positioned to reduce the patient's radiation dose.

[0041] The following is a detailed description of the technical solution of the present invention with reference to the accompanying drawings. According to an optional embodiment of the present invention, a radiation dose estimation method is provided, the flow chart of which is as follows: Figure 1 As shown, the following steps are included:

[0042] S1. Scan the target body according to a preset interval thickness to obtain scanning data of different sections of the target body and target body parameters, scanning positioning parameters, and scanning setting parameters corresponding to the scanning data. Scanning data of different sections of the target body are obtained using oral cone-beam CT (CBCT), wherein the target body parameters include, for example, the soft tissue thickness of the target body; the scanning positioning parameters include, for example, the scanning field of view; the scanning setting parameters include, for example, the scanning mode, the beam energy level of the tube voltage, the function of the tube current and time, the automatic exposure time, and the rotation time; the scanning field of view is a cylinder or a portion of a cylinder, wherein the cylinder has at least one of a diameter of 4 cm to 20 cm and a height of 4 cm to 20 cm; and the scanning mode is, for example, at least one of a high-definition mode, a normal mode, and a low-dose mode.

[0043] S2. Performing 3D reconstruction and 2D conversion on the scanned data to obtain a registered data set. The 3D reconstruction can be performed using a 3D reconstruction system provided by the scanning device, followed by 2D image separation to obtain a registered image set.

[0044] S3. Perform tissue segmentation on the dataset to obtain a segmented dataset. This embodiment can be used for oral radiation dose estimation, and the tissues involved include, but are not limited to, enamel, dentin, periodontal ligament, alveolar ridge, maxillary sinus floor, lamina, trabeculae, root canals, and other soft tissues. According to some embodiments, a segmentation network can be used to perform tissue segmentation on the dataset; the segmentation network is established according to the following steps:

[0045] S3.1. Construct an original segmentation network, which includes an encoding module, a feature extraction module and N decoding modules; wherein the encoding module is used to encode the input reconstructed data to obtain a semantic feature map; the feature extraction module is used to process each semantic feature map obtained by the encoding module to obtain semantic feature maps of different resolutions; and the N decoding modules are respectively used to obtain prediction probability maps of different tissues based on the semantic feature maps.

[0046] S3.2. Use the scanned data set to train the original segmentation network to obtain a segmentation network.

[0047] S4. Comparing the segmented data set with preset standard data to obtain the element types and densities contained in each tissue. The preset standard data can be from database information, including but not limited to ICRP, ICRU and other databases.

[0048] S5. Using the target body parameters, scan positioning parameters, scan setting parameters, and the comparison results, simulate the scanning imaging process to calculate the radiation dose received by each tissue during the scan. Using the target body parameters, scan positioning parameters, scan setting parameters, and the comparison results, a Monte Carlo method is used to simulate the physical process of the interaction between radiation rays and body tissues during the scanning imaging process to obtain the radiation dose received by each tissue during the scan. After obtaining the radiation dose received by each tissue during the scan, the radiation dose received by each tissue is output in the form of a distribution tomogram. Outputting in the form of a radiation dose distribution tomogram means displaying the radiation dose distribution received by each tissue in the form of a tomogram, similar to a tomographic image reconstructed from a CBCT scan. The intensity in the displayed image indicates the radiation dose received by the location and / or tissue during the CBCT scan.

[0049] According to another embodiment of the present invention, a radiation dose estimation device is provided. The block diagram of the radiation dose estimation device is as follows: Figure 2 As shown, the device includes a data acquisition module, a registration module, a tissue segmentation module, a tissue analysis module and a radiation dose calculation module.

[0050] A data acquisition module is used to scan the target body according to a preset interval thickness to obtain scanning data of different sections of the target body and target body parameters, scanning positioning parameters and scanning setting parameters corresponding to the scanning data;

[0051] A registration module, performing three-dimensional reconstruction and two-dimensional conversion on the scan data to obtain a registered data set;

[0052] a tissue segmentation module, performing tissue segmentation on the data set to obtain a segmented data set;

[0053] A tissue analysis module compares the segmented data set with preset standard data to obtain the type and density of elements contained in each tissue;

[0054] The radiation dose calculation module simulates the scanning imaging process using the target body parameters, scanning positioning parameters, scanning setting parameters and the comparison result to calculate the radiation dose received by each tissue in the scanning.

[0055] The specific process of each module in this embodiment of the present invention realizing its function is the same as the steps involved in the method in the above embodiment of the present invention, and will not be repeated here.

[0056] In summary, embodiments of the present invention relate to a radiation dose estimation method and apparatus, comprising the following steps: scanning a target body according to a preset interval thickness to obtain scan data of different sections of the target body, as well as target body parameters, scan positioning parameters, and scan setting parameters corresponding to the scan data; performing three-dimensional reconstruction and two-dimensional conversion on the scan data to obtain a registered dataset; performing tissue segmentation on the dataset to obtain a segmented dataset; comparing the segmented dataset with preset standard data to obtain the element types and densities contained in each tissue; and simulating the scanning imaging process using the target body parameters, scan positioning parameters, and scan setting parameters and the comparison results to calculate the radiation dose received by each tissue during the scan. The solution of the embodiments of the present invention analyzes the data information obtained by CBCT to estimate the radiation dose, providing a data basis for parameter setting and dose usage during the CBCT scanning process. The radiation dose estimation method provided by the embodiment of the present invention takes into account various data influencing factors based on the actually acquired scan data and the target body parameters, scan positioning parameters, and scan setting parameters corresponding to the scan data. The method estimates the radiation dose of each tissue through simulation, thereby providing a data basis for parameter setting and dose usage during the CBCT scan process. This method can improve the scan quality by adjusting other parameters while reducing the radiation dose. The method also performs three-dimensional segmentation of the dentition and alveolar bone data through a segmentation network, achieving good segmentation effect and more accurately reflecting the positions of different tissues in the image data, thereby achieving higher estimation accuracy.

[0057] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Those skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present invention (including claims) is limited to these examples; under the thinking of the present invention, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes in different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity. The embodiments of the present invention are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for estimating radiation dose of oral tissue, characterized in that: Including steps: Scanning the target body according to a preset interval thickness to obtain scanning data of different sections of the target body and target body parameters, scanning positioning parameters and scanning setting parameters corresponding to the scanning data; Performing three-dimensional reconstruction and two-dimensional conversion on the scan data to obtain a registered data set; Performing tissue segmentation on the data set to obtain a segmented data set; the tissues include enamel, dentin, periodontal ligament, alveolar ridge, maxillary sinus floor, lamina dura, trabeculae and root canals; Comparing the segmented data set with preset standard data to obtain the element types and densities contained in each tissue; Using the target body parameters, scanning positioning parameters, scanning setting parameters and the comparison result, simulate the scanning imaging process to calculate the radiation dose received by each tissue in the scanning; wherein the scanning data of different sections of the target body are acquired using oral cone-beam CT; the target body parameters include the soft tissue thickness of the target body; the scanning positioning parameters include the scanning field of view; the scanning setting parameters include the scanning mode, the beam energy level of the tube voltage, the function of the tube current and time, the automatic exposure time and the rotation time; the scanning field of view includes at least one of 360° scanning, 270° scanning and 180° scanning; the scanning mode includes at least one of high-definition mode, normal mode and low-dose mode; The step of organizing and segmenting the data set to obtain a segmented data set includes: The dataset is organized and segmented using a segmentation network; the segmentation network is established according to the following steps: Constructing an original segmentation network, wherein the original segmentation network includes an encoding module, a feature extraction module and N decoding modules; Using the scanned data set to train the original segmentation network to obtain a segmentation network; Among them, the encoding module is used to encode the input reconstructed data to obtain a semantic feature map; the feature extraction module is used to process each semantic feature map obtained by the encoding module to obtain semantic feature maps of different resolutions; the N decoding modules are respectively used to obtain prediction probability maps of different tissues based on the semantic feature maps.

2. The method according to claim 1, characterized in that Using the target body parameters, scanning positioning parameters, scanning setting parameters and the comparison result, simulating the scanning imaging process to calculate the radiation dose received by each tissue in the scanning includes: The target body parameters, scanning positioning parameters, scanning setting parameters and the comparison results are used to simulate the physical process of interaction between radiation rays and tissues during the scanning imaging process using the Monte Carlo method to obtain the radiation dose received by each tissue during the scanning process.

3. The method according to claim 2, characterized in that The method further comprises: The radiation dose received by each tissue is output in the form of a distribution tomogram.

4. The method according to claim 3, characterized in that The intensity value at a certain location in the distribution tomogram indicates the radiation dose received by the location during the scanning imaging process.

5. A device for estimating radiation dose of oral tissue, characterized in that: It includes data acquisition module, registration module, tissue segmentation module, tissue analysis module and radiation dose calculation module; among them, The data acquisition module is used to scan the target body according to the preset interval thickness to obtain scanning data of different sections of the target body and target body parameters, scanning positioning parameters and scanning setting parameters corresponding to the scanning data; The registration module performs three-dimensional reconstruction and two-dimensional conversion on the scan data to obtain a registered data set; The tissue segmentation module performs tissue segmentation on the data set to obtain a segmented data set; the tissues include enamel, dentin, periodontal ligament, alveolar ridge, maxillary sinus floor, lamina edulis, trabeculae and root canals; The tissue analysis module compares the segmented data set with preset standard data to obtain the element types and densities contained in each tissue; The radiation dose calculation module simulates the scanning imaging process using the target body parameters, scanning positioning parameters, scanning setting parameters and the comparison result to calculate the radiation dose received by each tissue in the scanning; wherein the scanning data of different sections of the target body are acquired using oral cone-beam CT; the target body parameters include the soft tissue thickness of the target body; the scanning positioning parameters include the scanning field of view; the scanning setting parameters include the scanning mode, the beam energy level of the tube voltage, the function of the tube current and time, the automatic exposure time and the rotation time; the scanning field of view includes at least one of 360° scanning, 270° scanning and 180° scanning; the scanning mode includes at least one of high-definition mode, normal mode and low-dose mode; The tissue segmentation module is further configured to: The dataset is organized and segmented using a segmentation network; the segmentation network is established according to the following steps: Constructing an original segmentation network, wherein the original segmentation network includes an encoding module, a feature extraction module and N decoding modules; Using the scanned data set to train the original segmentation network to obtain a segmentation network; Among them, the encoding module is used to encode the input reconstructed data to obtain a semantic feature map; the feature extraction module is used to process each semantic feature map obtained by the encoding module to obtain semantic feature maps of different resolutions; the N decoding modules are respectively used to obtain prediction probability maps of different tissues based on the semantic feature maps.

Images