Patient thickness acquisition method and x-ray imaging system

Abstract

The application provides a patient thickness acquisition method and an X-ray imaging system. The patient thickness acquisition method comprises acquiring optical image data and depth image data obtained by a camera, generating a point cloud based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views, extracting a target region in the point cloud, the target region comprising a region of interest of a patient, and acquiring a thickness value of the patient based on a thickness of at least one key region divided in the target region, or acquiring the thickness value of the patient based on a distance between a first surface and a second surface of the patient fitted.

Description

Technical Field

[0001] This invention relates to medical imaging technology, and more specifically to a method for obtaining patient thickness, an X-ray imaging system, and a non-transitory computer-readable storage medium. Background Technology

[0002] In an X-ray imaging system, radiation from an X-ray source is directed at a subject, typically a patient in medical diagnostic applications. A portion of the radiation passes through the patient and impacts a detector, which is divided into a matrix of discrete elements (e.g., pixels). The detector elements are read out to generate an output signal based on the amount or intensity of radiation impacting each pixel region. The signal can then be processed to produce a medical image that can be displayed for examination on the display device of the X-ray imaging system.

[0003] Typically, exposure protocols are selected based on the patient's body size. Larger patients usually require a higher dose, while smaller patients require a lower dose. However, some existing exposure protocol selections are based on one or more of the patient's age, gender, weight, height, etc. This is not accurate enough for selecting an exposure protocol, as it may result in the patient receiving an excessive dose or an insufficient dose to obtain a prepared image. Summary of the Invention

[0004] This invention provides a method for obtaining patient thickness, an X-ray imaging system, and a non-transitory computer-readable storage medium.

[0005] An exemplary embodiment of the present invention provides a method for obtaining patient thickness, the method comprising: acquiring optical image data and depth image data captured by a camera; generating a point cloud based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views; extracting a target region in the point cloud, the target region including the region of interest of the patient; and obtaining a thickness value of the patient based on the thickness of at least one key region divided within the target region, or obtaining a thickness value of the patient based on identifying the distance between a first face and a second face of the patient.

[0006] An exemplary embodiment of the present invention also provides an X-ray imaging method, the method comprising: acquiring optical image data and depth image data captured by a camera; generating a point cloud based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views; extracting a target region in the point cloud, the target region including a region of interest of the patient; obtaining a thickness value of the patient based on the thickness of at least one key region divided within the target region, or obtaining a thickness value of the patient based on identifying the distance between a first face and a second face of the patient; and selecting exposure parameters based on the thickness value to expose the patient.

[0007] An exemplary embodiment of the present invention also provides an X-ray imaging system, the X-ray imaging system including a control unit, and the control unit being capable of performing the patient thickness acquisition method.

[0008] An exemplary embodiment of the present invention also provides an X-ray imaging system, comprising a patient thickness acquisition device, the patient thickness acquisition device including an acquisition module, a generation module, an extraction module, and a calculation module; the acquisition module is used to acquire optical image data and depth image data captured by a camera; the generation module is used to generate a point cloud based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views; the extraction module is used to extract a target region in the point cloud, the target region including the patient's region of interest; and the calculation module is used to acquire the patient's thickness value based on the thickness of at least one key region divided within the target region, or based on the distance between a first face and a second face of the patient.

[0009] An exemplary embodiment of the present invention also provides a non-transitory computer-readable storage medium for storing a computer program that, when executed by a computer, causes the computer to perform a patient thickness acquisition method.

[0010] Other features and aspects will become clear from the following detailed description, accompanying drawings, and claims. Attached Figure Description

[0011] The invention can be better understood by describing exemplary embodiments of the invention in conjunction with the accompanying drawings, in which:

[0012] Figure 1 This is a schematic diagram of an X-ray imaging system according to some embodiments of the present invention;

[0013] Figure 2 This is a schematic diagram of the control logic of a control unit in an X-ray imaging system according to some embodiments of the present invention;

[0014] Figure 3 These are the output results of a classification learning model according to some embodiments of the present invention;

[0015] Figure 4 This is a schematic diagram of fitting the first and second surfaces of a patient according to some embodiments of the present invention;

[0016] Figure 5 This is a flowchart of a patient thickness acquisition method according to some embodiments of the present invention;

[0017] Figure 6 yes Figure 5 The flowchart shown illustrates the specific process of generating point clouds in the method for obtaining patient thickness.

[0018] Figure 7 This is a flowchart of a patient thickness acquisition method according to some embodiments of the present invention; and

[0019] Figure 8 This is a flowchart of a method for obtaining patient thickness according to other embodiments of the present invention. Detailed Implementation

[0020] The following describes specific embodiments of the present invention. It should be noted that, in order to provide a concise description, this specification cannot exhaustively describe all features of the actual embodiments. It should be understood that, in the actual implementation of any embodiment, just as in any engineering or design project, various specific decisions are often made to achieve the developer's specific goals and to meet system-related or business-related constraints, and this can change from one embodiment to another. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this invention, some design, manufacturing, or production modifications based on the technical content disclosed herein are merely conventional technical means and should not be construed as insufficient content of this disclosure.

[0021] Unless otherwise defined, the technical or scientific terms used in the claims and description shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in the patent application description and claims of this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. The terms "an" or "a" and similar terms do not indicate a quantity limitation, but rather indicate the presence of at least one. The terms "comprising" or "including" and similar terms mean that the element or object preceding "comprising" or "including" encompasses the element or object listed following "comprising" or "including" and its equivalents, and do not exclude other elements or objects. The terms "connected" or "linked" and similar terms are not limited to physical or mechanical connections, nor are they limited to direct or indirect connections.

[0022] Figure 1 An X-ray imaging system 100 according to some embodiments of the present invention is shown. Figure 2 It shows Figure 1 A schematic diagram of the collimator in the X-ray imaging system is shown. Figure 1 As shown, the X-ray imaging system 100 includes a suspension device OTS 110, a wall stand device 120, and a test bed device 130. The suspension device OTS 110 includes a longitudinal guide rail 111, a transverse guide rail 112, a telescopic cylinder 113, a trolley 114, an X-ray tube assembly 115, and an OTS control device 116.

[0023] For ease of description, in this application, the x-axis, y-axis and z-axis are defined as follows: the x-axis and y-axis are located in the horizontal plane and are perpendicular to each other, and the z-axis is perpendicular to the horizontal plane. Specifically, the direction of the longitudinal guide rail 111 is defined as the x-axis, the direction of the transverse guide rail 112 is defined as the y-axis, and the extension direction of the telescopic cylinder 113 is defined as the z-axis, which is the vertical direction.

[0024] The longitudinal guide rail 111 and the transverse guide rail 112 are vertically arranged. The longitudinal guide rail 111 is mounted on the ceiling, and the transverse guide rail 112 is mounted on the longitudinal guide rail 111. A telescopic cylinder 113 is used to support the X-ray tube assembly 115. A trolley 114 is disposed between the transverse guide rail 112 and the telescopic cylinder 113. The trolley 114 may include a rotating shaft, a motor, and a drum, etc. The motor can drive the drum to rotate around the rotating shaft, thereby causing the telescopic cylinder 113 to move along the z-axis and / or slide relative to the transverse guide rail. The trolley 114 can slide relative to the transverse guide rail 112, that is, the trolley 114 can drive the telescopic cylinder 113 and / or the X-ray tube assembly 115 to move along the y-axis. Furthermore, the transverse guide rail 112 can slide relative to the longitudinal guide rail 111, thereby driving the telescopic cylinder 113 and / or the X-ray tube assembly 115 to move along the x-axis.

[0025] The telescopic cylinder 113 comprises multiple cylindrical sections with different inner diameters, which can be fitted into the upper cylinder from bottom to top to achieve telescopic movement. The telescopic cylinder 113 is vertically telescopic (or movable), meaning it can drive the X-ray tube assembly 115 to move along the z-axis. A rotating part is also provided at the lower end of the telescopic cylinder 113, which can drive the X-ray tube assembly 115 to rotate. The size of the opening of the collimator 117 determines the X-ray irradiation range, i.e., the size of the field of view (FOV). X-rays can pass through the opening of the collimator to irradiate the patient's region of interest (ROI), while other X-rays are absorbed by the blades to prevent the patient from receiving excessive unnecessary doses. The lateral positions of the X-ray source and the collimator 117 determine the position of the FOV on the patient.

[0026] The OTS control device (console) 116 is mounted on the X-ray tube assembly 115. The OTS control device 116 includes a user interface such as a display screen and control buttons for pre-shooting preparations, such as patient selection, protocol selection, and positioning.

[0027] The column assembly 120 includes a first detector 121, a column 122, and a connecting portion 123. The connecting portion 123 includes a support arm perpendicularly connected to the height direction of the column 122 and a rotating bracket mounted on the support arm. The first detector 121 is mounted on the rotating bracket. The column assembly 120 further includes a detector driving device disposed between the rotating bracket and the first detector 121. Driven by the detector driving device, the detector 121 moves along a direction parallel to the height direction of the column 122 on the plane supported by the rotating bracket. The first detector 121 can also further rotate relative to the support arm, forming a certain angle with the column. The first detector 121 has a plate-like structure with a variable orientation, so that the X-ray incident surface can be made vertical or horizontal depending on the incident direction of the X-rays.

[0028] The examination bed device 130 includes a second detector 131. The selection or use of the first detector 121 and the second detector 131 can be determined based on the patient's imaging site and / or imaging protocol, or based on the patient's position obtained by the camera, to perform imaging examinations in a supine or standing position. Figure 1 Only one example diagram of the column and testing bed is shown. Those skilled in the art should understand that any form or arrangement of the column and / or testing bed can be selected, or only the column can be installed. The column and / or testing bed are not limited to the overall scheme of this application.

[0029] During imaging, the center of the X-ray source, i.e., the central ray of the X-ray beam, often needs to be aligned with the center of the detector. In some embodiments, the X-ray source and detector can be controlled in tandem. For example, the position and angle of the X-ray source can be controlled by adjusting the movement of the suspension device. Then, based on the monitoring information of the X-ray source on the detector, the detector can be automatically moved or rotated to a position aligned with the X-ray source, thus achieving coordinated control between the two. Conversely, the movement or rotation of the detector can be controlled, and then, based on the monitoring information on the X-ray source, the X-ray source can be automatically moved or rotated to a position aligned with the detector.

[0030] In some embodiments, the X-ray imaging system 100 further includes a camera unit 140 aligned with a detector for acquiring real-time images of the patient. Additionally, the camera can also acquire images of the detector, etc. The real-time images can be used to acquire at least one of the patient's thickness, height, position, posture, etc.

[0031] Specifically, camera unit 140 is mounted on suspension device 110, and more specifically, on the side of collimator 117. In other embodiments, camera unit 140 can also be fixedly mounted at any position in the scanning room, for example, mounted on a wall, and further, mounted on the wall of the detector of the alignment column. Of course, multiple camera units can also be installed in the scanning room, which can be fixedly mounted, mounted on a movable bracket, or mounted on the X-ray imaging system, as long as it can assist the user in positioning and protocol selection.

[0032] The camera unit may include one or more cameras, such as digital cameras, analog cameras, depth cameras, infrared cameras, or ultraviolet cameras, or 3D cameras, 3D scanners, or red-green-blue (RGB) sensors, RGB-depth (RGB-D) sensors, or other devices capable of capturing color image data of a target object, wherein "RGB" represents the three color channels of red, green, and blue, and "D" represents the depth channel. In some embodiments, the camera unit 140 is further provided with a control module that can control the rotation of the camera unit to adjust the shooting range of the camera unit. In other embodiments, the camera unit is a panoramic camera that can capture images of the patient's entire body. In some embodiments, the optical images acquired by the camera unit are not limited to a single optical image, but may also include a dynamic real-time video stream, i.e., a series of real-time optical images.

[0033] In some embodiments, the camera unit is capable of acquiring RGB optical images and depth images. In this implementation, the camera image not only records the color information of the scene, but also includes the depth or distance information of each pixel relative to the camera.

[0034] RGB color information refers to the color data of each pixel in a camera image, represented by different intensities of the red, green, and blue color channels. RGB color information enables visible light cameras to capture color details in a scene, thus generating a color image. Depth information records the physical distance between each pixel in the scene and the visible light camera. In RGB-D cameras, depth information can be obtained through various techniques, such as structured light, time-of-flight (ToF), or stereo vision. Of course, a head-mounted infrared (IR) sensor can also be used to improve ranging performance and enhance the accuracy of depth data acquisition. Depth maps can be represented as grayscale images, where each pixel value corresponds to the actual distance, rather than brightness or color information.

[0035] The X-ray imaging system 100 further includes a display unit 150. Specifically, the display unit 150 can include any type of display screen, such as a main display screen located in the control room, a display screen of the OTS control device 116 located in the scanning room, or a portable display, such as a tablet computer or mobile phone. The display unit 150 is operatively connected to the camera unit. The display unit 150 includes a user interface 151, which is used to display real-time optical images and depth images, etc. Of course, it can also display any view of the generated point cloud or the calculated thickness value of the patient.

[0036] The X-ray imaging system further includes an input unit 160 for receiving user operations. The input unit 160 may include a touch screen, keyboard, mouse, voice-activated control unit, or any other suitable input device. The user can input operation signals / control signals to the control unit through the input unit 160.

[0037] The X-ray imaging system 100 further includes a control unit (not shown), which may be a main control unit located in the control room, an OTS control unit mounted on a suspension device, a mobile or portable control unit, or any combination thereof. The control unit may include a source control unit and a detector control unit. The source control unit commands the X-ray source to emit X-rays for image exposure. The detector control unit is used to select a suitable detector from among multiple detectors and to coordinate the control of various detector functions, such as automatically selecting the corresponding detector based on the patient's position or posture, or performing various signal processing and filtering functions, specifically for initial adjustment of dynamic range, interleaving of digital image data, etc. In some embodiments, the control unit may provide power and timing signals for controlling the operation of the X-ray source and detector.

[0038] In some embodiments, the control unit may also be configured to use digital signals to reconstruct one or more desired images and / or determine useful diagnostic information corresponding to the patient, wherein the control unit may include one or more dedicated processors, graphics processing units, digital signal processors, microcomputers, microcontrollers, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other suitable processing devices.

[0039] Of course, the X-ray imaging system may also include other numbers, configurations, or forms of control units. For example, the control units may be local (e.g., located in the same location as one or more X-ray imaging systems 100, such as within the same facility and / or the same local network); in other implementations, the control units may be remote and therefore accessible only via a remote connection (e.g., via the Internet or other available remote access technologies). In certain implementations, the control units may also be configured in a cloud-like manner and may be accessed and / or used in a manner substantially similar to accessing and using other cloud-based systems.

[0040] In typical X-ray imaging system exposure control, for example, determining exposure parameters often requires obtaining the patient's thickness to determine the exposure dose. Previous methods for obtaining patient thickness typically involved directly estimating the thickness from depth images acquired by the camera unit. Specifically, this was done by directly obtaining the patient's thickness through depth information within the patient's region of interest, or by estimating the thickness based on the transformation relationship between the camera unit's mounting angle and image source distance. However, this estimation method has a drawback: when there is a large distance between the patient and the detector, the estimated thickness value will have a significant error, leading to substantial deviations in the selection of subsequent exposure doses. Therefore, accurately obtaining the patient's thickness is crucial for the exposure control of X-ray imaging systems.

[0041] Based on the aforementioned problems, this application proposes a method to accurately obtain the patient's thickness by dividing the target region based on the point cloud obtained from the RGB image and depth image acquired by the camera, and by obtaining the average thickness of the thickness in the target region or by obtaining the thickness value through plane fitting based on at least one key region related to the shooting location in the target region, so that the thickness acquisition no longer depends on the distance between the patient and the detector.

[0042] Specifically, Figure 2 A schematic diagram of the patient thickness acquisition device 200 of this application is shown. (As...) Figure 2As shown, the patient thickness acquisition device 200 includes an acquisition module 210, a generation module 220, an extraction module 230, and a calculation module 240. The acquisition module 210 acquires optical image data 212 and depth image data 211 captured by a camera. The generation module 220 generates a point cloud based on the optical image data 212 and depth image data 211, wherein the point cloud can be displayed in one or more views. The extraction module 230 extracts a target region from the point cloud, the target region including at least the patient's region of interest. The calculation module 240 acquires the patient's thickness value based on the thickness of at least one key region divided within the target region, or based on the fitted distance between the patient's first and second faces.

[0043] Specifically, the acquisition module 210 can be connected to the camera unit of an X-ray imaging system (e.g., Figure 1 The camera unit 140 shown is connected to acquire real-time optical images 212 and depth images 211.

[0044] The generation module 220 is further used to register based on optical image data 212 and depth image data 211 and generate an initial point cloud, and to post-process the initial point cloud to obtain a final point cloud.

[0045] A point cloud is a data set consisting of a large number of points, each with its own specific coordinates (x, y, z) in three-dimensional space. These points are typically used to represent the three-dimensional shape and features of objects or environments.

[0046] In some embodiments, since the optical image data and depth image data are of different sizes, they typically need to be registered first, for example, using rigid registration. Alternatively, non-rigid registration can be used to ensure the optical and depth image data have the same size. Then, an initial point cloud without color elements is obtained based on the registered depth image. Finally, the optical image data is applied to this initial point cloud to give it color elements (i.e., colors corresponding to those in the optical image data). Of course, this method is not limited to the steps mentioned above; any other suitable method for generating point clouds based on optical and depth images can be used.

[0047] Specifically, post-processing includes hole filling and downsampling. Hole filling can fill blank pixels generated by 2D to 3D transformation, while downsampling can reduce the amount of image data and reduce the image processing cost of subsequent steps.

[0048] During the process of generating the initial point cloud, due to the spatial transformation from 2D to 3D, many pixels will have no pixel value. At this time, it is necessary to fill the holes in the initial point cloud to fill the blank points caused by the spatial transformation. Of course, this hole filling can be done using any existing method or filling rule. For example, it can be filled using the pixel value of the left-hand pixel adjacent to the blank pixel, or using the maximum pixel value among the adjacent pixels, or using the minimum pixel value among the adjacent pixels. Of course, there can also be any other suitable filling rule.

[0049] After hole filling, the initial point cloud can be downsampled to reduce the number of points, making the data easier to process and analyze, and improving the efficiency of subsequent image processing. Any suitable method or rule can be used for downsampling. For example, different downsampling factors can be set. For instance, averaging adjacent pixels or signal points can reduce data resolution, or the maximum value within each region can be selected as the representative value for that region. Specifically, different methods can be chosen based on the number of points in the point cloud. Alternatively, the downsampling factor can be selected or customized by the user. For example, the factor can be displayed on the user interface for selection, or it can be set according to the camera parameters in the X-ray imaging system, or it can be matched to the user's shooting type. For example, for medical examination-type imaging, where particularly high image quality is not required, a larger downsampling factor can be chosen to reduce the amount of data as much as possible.

[0050] In some embodiments, since the point cloud is 3D, one or more views of the point cloud can be presented to the user. For example, a front view 221, a side view 222, and a top view 223 can be presented to the user. Of course, any other view required by the user can also be presented. The presented views can be selected and switched by the user. For example, when presenting a 3D point cloud to the user, the user can select any view they want to display on the 3D point cloud. This at least one view will also be used in the subsequent fitting of the plane, which will be described in detail later.

[0051] Since the camera images captured by the camera generally have a large field of view, they include not only the patient's region of interest and the detector area, but also the background, such as the environment around the detector and the environment between scans. Therefore, after the point cloud is generated, which also includes the background and the imaging part, the extraction module 230 needs to extract the target area in the point cloud so that the extracted target area includes only the patient's region of interest as much as possible.

[0052] Specifically, extraction module 230 is further used to remove the background portion from the point cloud to obtain the target region 231. Specifically, removing the background portion from the point cloud includes identifying the classification map corresponding to the point cloud based on a classification learning model, and extracting the target region based on the classification map, or removing the background portion based on the source-image distance (SID). Specifically, after removing the background portion, extraction module 230 also includes separating the detector region and retaining only the patient's region of interest, as shown in image 232.

[0053] Specifically, point clouds include a large area of ​​background environment. Therefore, to calculate the thickness more accurately, the background environment needs to be removed first. In some embodiments, the background portion can be extracted and removed based on the source-image distance (SID). For example, with an SID of 1.8m, the distance between the X-ray source and the detector is 1.8m, while the distance between the X-ray source and the patient is definitely less than 1.8m. The distance between the X-ray source and the background environment is certainly much greater than 1.8m. The distance and angle between the camera and the X-ray source are fixed and depend on the camera's installation position. Therefore, the background portion can be separated based on the thickness exceeding a threshold value in the point cloud. This threshold depends on the source-image distance (SID). Thus, the environmental background portion can be easily removed using the SID.

[0054] In other embodiments, a classification learning model can be used to identify the classification map corresponding to the point cloud, and the target region can be extracted based on the classification map. Specifically, the learning model can be a classification model, for example, classifying the depth values ​​in the point cloud. Specifically, the depth values ​​of the point cloud can be classified according to the size of the field of view (FOV) (43*43). The depth values ​​can be classified into 2, 3, or more classes. By inputting the point cloud into the classification learning model, a corresponding classification map can be output. This classification map can show the classification level corresponding to each FOV-sized block, and then the target region can be extracted based on this classification map. Figure 3 The output results of classification learning models according to some embodiments of the present invention are shown. For example... Figure 3 As shown, the front view of the entire point cloud is divided into 3 rows and 4 columns according to the FOV size. The thickness value of each block is classified to output its corresponding level. Figure 3 Two high-confidence blocks, 301 and 302, are shown, indicating that the patient's region of interest (ROI) lies within these blocks to extract the imaging portion. Of course, to further subdivide the imaging portion, blocks 301 and 302 can be further divided into smaller blocks and then input into the classification model. Through continuous iteration, the patient's ROI can be obtained. Alternatively, the point cloud can be divided not initially using FOV, but using any other suitable size to divide the image.

[0055] In some other embodiments, any other suitable method may be used to remove the environmental background portion, as long as the region of interest is preserved.

[0056] Please return to the reference. Figure 2 After removing the background, image 231 includes the patient's region of interest (ROI) and the detector region. To further separate the detector region, retaining only the patient's ROI 232, in some embodiments, the extraction module 230 further segments the patient's ROI based on the histogram of the imaging portion in the point cloud. In other embodiments, the extraction module 230 further segments the patient's ROI based on the difference or contrast between the patient's clothing color and the detector color. In still other embodiments, the extraction module 230 may also segment the patient's ROI based on the identified patient boundaries or the identified patient's anatomical structure. Of course, the patient's ROI can also be extracted based on any other suitable segmentation or extraction method so that the target region includes only the patient's ROI.

[0057] Although the above describes a method of separating the background portion first and then segmenting the detector region, those skilled in the art should understand that these two steps can be combined, for example, by directly segmenting the patient's region of interest from the point cloud based on histograms, etc.

[0058] Although the above describes generating a point cloud before extracting the target region, those skilled in the art should understand that it is also possible to first register optical image data and depth image data, then extract the target region, which includes the patient's region of interest (ROI) and the detector region. Then, a point cloud can be generated based on the target region in the optical image data and the target region in the depth image data; that is, the generated point cloud will also only include the ROI and the detector region. Then, the point cloud image containing only the ROI can be identified using the method described above.

[0059] In some embodiments, the calculation module 240 can divide at least one key region 241 in the target area based on the patient's imaging site, and calculate the mean thickness value in each of the at least one key region. When the target area is divided into multiple key regions, the patient's thickness value in each key region is calculated, and the overall thickness value 242 of the patient is calculated based on the weight of each key region.

[0060] Specifically, the calculation module 240 can be connected to the control unit or processor of the exposure protocol of the X-ray imaging system to receive the patient's exposure protocol, which includes information such as the patient's imaging site, imaging position, age, weight, and medical history. The calculation module 240 is further used to delineate key areas based on the patient's imaging site.

[0061] Specifically, when there are multiple key regions, the thickness value of each key region is calculated separately. This thickness value can be the average or maximum thickness within the key region. After obtaining the thickness value of each key region, the patient's overall thickness value can be calculated based on the weight of each key region. Alternatively, the average or maximum thickness of each key region can be used as the patient's overall thickness value.

[0062] Specifically, taking a chest X-ray as an example, the primary goal is to calculate or obtain the thickness of the chest, not the thickness of the neck. Adding or considering the neck thickness to the final thickness calculation would result in an underestimation of the chest thickness. Therefore, one or more key regions can be divided within the target area based on the imaging site. For example, three key regions could be defined: the first region for the shoulder, the second for the central lung, and the third for the abdomen. The thickness value for each key region can then be calculated separately. Of course, when the imaging site is the spine, the key regions should be the vertebral body and the back, or they can be defined according to specific definitions. For each imaging site, its corresponding key regions and their positions in the image can be predefined. These definitions can be stored in the X-ray imaging system in the form of a lookup table or database.

[0063] Specifically, in some embodiments, identifying specific anatomical structures typically requires moving the detector panel to the area being photographed on the patient. This makes the position of the photographed area relatively fixed in the optical image. Therefore, within the target area extracted from the point cloud, the positions of different anatomical structures within the target area are also relatively fixed. For example, the top one-fifth to two-fifths of the target area can cover the shoulder, the two-fifths to four-fifths can completely cover the lung, and the remaining one-fifth is the abdomen. Therefore, key regions can be delineated based on the position of the anatomical structures within the target area.

[0064] In other embodiments, the patient's anatomical structures can be identified based on image recognition or learning models, and the required anatomical structures can be selected according to the imaging location to determine key areas. Of course, this method will calculate the thickness more accurately, but will also require more computation.

[0065] The method described above for calculating thickness values ​​by dividing key regions is relatively simple and straightforward. However, because the patient and detector cannot be completely separated in the thickness direction (the direction of X-ray emission), especially when there is a certain distance between the patient and the detector, the calculated thickness value includes not only the patient's own thickness but also the distance between the patient and the detector. Therefore, the calculated thickness value will have a large error. Therefore, this application also proposes a method based on two surfaces obtained through planar fitting of the patient (e.g., ...). Figure 2 (As shown in 245) to calculate the patient's thickness.

[0066] Specifically, Figure 4 A simplified schematic diagram illustrating the fitting of the first and second faces of a patient according to some embodiments of the present invention is shown. Figure 4 As shown, the calculation module 240 can fit the first and second faces of the patient based on the side or top view of the point cloud, although Figure 4 The image shows a side view of the point cloud. Of course, a top view of the point cloud can also be used for fitting, or any other suitable view can be used.

[0067] like Figure 4 As shown, the calculation module 240 can identify the first side 410 of the patient away from the detector based on the thickness value in the target area, fit and identify the second side 420 of the patient closer to the detector, and obtain the patient's thickness value based on the distance between the first side 410 and the second side 420. The first side can be either the front chest or the back, and the second side is either the front chest or the back. Specifically, for PA position imaging, the patient's back is the first side, and the patient's front chest is the second side.

[0068] Specifically, identifying the first face 410 away from the detector is a common and conventional practice. For example, the first face of the patient can be identified based on the maximum thickness within the target area. Specifically, since the thickness values ​​within the extracted target area are known, the layer containing the maximum thickness value (perpendicular to the X-ray emission direction) is defined as the patient's first face by determining the location or layer number of the layer with the maximum thickness value. Of course, any other suitable method can be used to define the plane of the patient away from the detector, such as boundary recognition or by mounting or setting cameras on the side (the surface perpendicular to the detector).

[0069] After obtaining the patient's first face 410, the most important step is to obtain the patient's second face. Specifically, multiple planes close to the detector can be fitted, including the detector's face. Then, the second face is identified among these planes based on the continuity of the histogram of the target region. Since the patient's second face is close to the detector, even with a certain distance, spatial transformations in the point cloud can cause difficulties in easily identifying both the detector and the patient's second face. Therefore, multiple planes can be fitted in the area close to the detector, including both the detector's faces and the face where the patient is located. The patient's second face can then be identified based on the continuity of the histogram. Alternatively, the detector's face can be removed from the multiple planes based on the detector's thickness, and the face closest to the detector can be defined as the second face.

[0070] Specifically, the histogram of a point cloud can describe the local features of the point cloud data. Specifically, the histogram corresponding to the patient's point cloud is a curve with peaks, while the histogram corresponding to the detector is a straight line with constant values. Therefore, based on the differences between the histograms corresponding to different elements, the boundary between the detector and the patient can be segmented based on the continuity of the histograms, thereby accurately identifying the patient's second face.

[0071] After obtaining the two faces of the patient, the patient's thickness value can be obtained based on the distance between the two faces. Of course, the two faces of the patient are not necessarily parallel. When they are not parallel, the maximum or average distance between the two faces can be used as the patient's thickness value.

[0072] In some embodiments, the patient thickness acquisition device described above is performed by multiple different modules. However, those skilled in the art should understand that the multiple modules described above can also be integrated together, or the functions described above can be directly performed by the control unit.

[0073] In some embodiments, after the X-ray imaging system acquires the patient's thickness through the aforementioned patient thickness acquisition device or control unit, the X-ray imaging system can control the exposure dose based on the calculated thickness, and then perform the exposure.

[0074] Figure 5 A flowchart of a patient thickness acquisition method 500 according to some embodiments of the present invention is shown. For example... Figure 5 As shown, the X-ray imaging method 500 includes steps 510, 520, 530 and 540.

[0075] In step 510, optical image data and depth image data captured by the camera are acquired.

[0076] In step 520, a point cloud is generated based on optical image data and depth image data, wherein the point cloud can be displayed in one or more views.

[0077] Specifically, Figure 6 It shows Figure 5 The flowchart shown illustrates the specific process of generating point cloud 520 in the patient thickness acquisition method. (See attached flowchart.) Figure 6 As shown, step 520 further includes steps 521, 522 and 523.

[0078] In step 521, the optical image data and the depth image data are registered. Specifically, the optical image data and the depth image data can be registered in a rigid or non-rigid manner to ensure that the optical image data and the depth image data have the same size and dimensions.

[0079] In step 522, an initial point cloud is generated based on the registered optical image data and depth image data. Specifically, an initial point cloud without color elements is obtained based on the registered depth image, and then the optical image data is applied to the initial point cloud to give the initial point cloud color elements.

[0080] In step 523, the initial point cloud is post-processed to obtain a new point cloud. Specifically, the post-processing includes hole filling and downsampling. Hole filling fills blank pixels generated by the 2D-to-3D transformation, while downsampling reduces the amount of image data, lowering the image processing cost in subsequent steps.

[0081] For the point cloud obtained based on steps 521-523, since the point cloud is 3D, it can be accessed through a graphical user interface (e.g., ...). Figure 1 The display interface shown (151 or 116) presents one or more views of the point cloud to the user, including a front view, a side view, a top view, etc.

[0082] In step 530, the target region in the point cloud is extracted, including the patient's region of interest.

[0083] Specifically, extracting the target region from the point cloud includes removing the background portion of the point cloud to obtain the target region, which includes the patient's region of interest.

[0084] More specifically, in some embodiments, removing the background from the point cloud includes identifying the corresponding classification map of the point cloud based on a classification learning model, and extracting the target region based on the classification map. Specifically, the target region can be divided into multiple blocks according to a preset size (e.g., the size of the field of view). Each block is input into the classification learning model, and the classification level of the thickness value in the block is output. Then, one or more blocks with high confidence are obtained. These one or more blocks are then further divided and input into the classification learning model until the patient's region of interest is obtained.

[0085] In other embodiments, background removal from the point cloud includes removing the background portion based on the source-image distance (SID). Specifically, the distance between the X-ray source and the patient is certainly less than the source-image distance, while the distance between the X-ray source and the background environment is certainly much greater than the source-image distance. Since the distance and angle between the camera and the X-ray source are fixed, the background portion can be separated based on the thickness of the point cloud exceeding the SID threshold.

[0086] In some other embodiments, any other suitable method may be used to remove the environmental background portion of the point cloud, as long as the region of interest is preserved.

[0087] After removing the background portion of the point cloud, the detector region can be removed based on the histogram of the imaging portion, the difference or contrast between the patient's clothing color and the detector color, the boundaries of the identified patient, or the anatomical results of the identified patient, so that the target region only includes the patient's region of interest.

[0088] Of course, before generating the point cloud, the target region can be divided into the depth image and optical image first, and then the point cloud can be generated based on the target region in the optical image data and the target region in the depth image data.

[0089] In step 540, the thickness value of the patient is obtained based on at least one key region divided within the target area, or based on the fitted first and second faces of the patient.

[0090] In some embodiments, Figure 7 A flowchart of a patient thickness acquisition method 600 according to some embodiments of the present invention is shown. For example... Figure 7 As shown, step 640 of obtaining the patient's thickness includes steps 641 and 642.

[0091] In step 641, at least one key region is delineated within the target area based on the patient's imaging site. Specifically, the patient's exposure protocol includes information such as the imaging site, imaging position, age, weight, and medical history. One or more key regions can be delineated based on the patient's imaging site. For example, taking a chest X-ray as an example, the target area can be divided into three key regions: the shoulder, lung, and abdomen, while the neck is excluded from the key regions, and its thickness is not calculated when calculating the thickness value. Specifically, key regions can be delineated based on the location of anatomical structures within the target area, or they can be determined based on the identified anatomical results of the patient.

[0092] In step 642, the mean thickness value within at least one key region is calculated. When the target region is divided into multiple key regions, the patient's thickness value within each key region is calculated, and the overall patient thickness value is calculated based on the weight of each key region. Alternatively, the mean or maximum thickness of each key region can be used as the overall patient thickness value.

[0093] In other embodiments, Figure 8 A flowchart of a patient thickness acquisition method 700 according to other embodiments of the present invention is shown. For example... Figure 8 As shown, step 740 of obtaining the patient's thickness includes steps 741, 742 and 743.

[0094] In step 741, the first side of the patient away from the detector is identified based on the thickness value in the target area. Specifically, for PA position imaging, the patient's back is the first side, and the patient's chest is the second side. Specifically, the identification of the first and second sides of the patient can be based on a point cloud or a side or top view of the target area in the point cloud.

[0095] Specifically, the location of the maximum thickness in the target area is determined, and the face containing that location is defined as the patient's first face. More specifically, by determining the location or layer of the maximum thickness value in the target area, the layer containing that maximum thickness value (perpendicular to the X-ray emission direction or thickness direction) is defined as the patient's first face.

[0096] In step 742, the second side of the patient near the detector is fitted and identified.

[0097] Specifically, step 742 further includes: fitting multiple planes of the patient near the detector, the multiple planes including the face of the detector, and identifying a second face in the multiple planes based on the continuity of the histogram of the target region.

[0098] In step 743, the patient's thickness value is obtained based on the distance between the first and second surfaces.

[0099] In some embodiments, for the patient's thickness obtained by the above method, the system can control the exposure dose based on the calculated thickness before performing exposure.

[0100] In some embodiments, in addition to the method described in section 2 above for calculating thickness based on the target region, the two methods can be used in combination. For example, the key region can be divided into one or more key regions, and then the detector region can be completely separated in the thickness direction (i.e., the X-ray emission direction) based on plane fitting, and then the thickness value of each key region can be calculated. Another example is that, in addition to the camera mounted on the side of the collimator, a movable camera can be mounted on the side perpendicular to the detector surface. When the patient stands in front of the detector, the patient's thickness can be calculated based on the side camera, as there is no interference from the detector in the patient's thickness direction, and the calculated thickness is extremely accurate. Of course, if it is not desirable to mount a camera on the side, one can consider first moving the X-ray source to align with the patient's side to obtain the patient's thickness, and then moving the X-ray source to align with the detector. This only adds one step to the entire process. Alternatively, during positioning, the patient can first stand sideways, and after obtaining the thickness value through the camera, the patient can then stand facing forward or backward for the formal exposure. Of course, the thickness measurement method of this application does not only refer to the distance between the front and back. When it is necessary to measure the patient's spine, the patient may also stand sideways. In this case, the patient's thickness refers to the distance between the two sides of the patient. The patient's thickness measurement method can also be applied in the same way.

[0101] The patient thickness acquisition method and X-ray imaging system of some embodiments of the present invention utilize a target region obtained by dividing a point cloud from an optical image and a depth image acquired by a camera. This target region includes the patient's region of interest. The patient's thickness can then be calculated in two ways. The first method involves dividing the target region into one or more key regions based on the imaging site, and then calculating the overall patient thickness based on the thickness value of each key region. This method is relatively simple and requires minimal computation; however, it is limited by the distance between the patient and the detector. When the distance between the patient and the detector is large, the accuracy of the calculated thickness value decreases. The second method involves fitting two faces of the patient (e.g., the chest and back) based on a side view or top view of the point cloud, resulting in a more accurate patient thickness value.

[0102] An exemplary embodiment of the present invention also provides a method for obtaining patient thickness, the method comprising: acquiring optical image data and depth image data captured by a camera; generating a point cloud based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views; extracting a target region in the point cloud, the target region including the region of interest of the patient; and obtaining the thickness value of the patient based on at least one key region divided within the target region, or based on identifying a first face and a second face of the patient.

[0103] An exemplary embodiment of the present invention also provides an X-ray imaging method, the method comprising: acquiring optical image data and depth image data captured by a camera; generating a point cloud based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views; extracting a target region in the point cloud, the target region including a region of interest of the patient; acquiring a thickness value of the patient based on at least one key region divided within the target region, or based on identifying a first face and a second face of the patient; and selecting exposure parameters based on the thickness value to expose the patient.

[0104] An exemplary embodiment of the present invention also provides an X-ray imaging system including a control unit, which is capable of performing the patient thickness acquisition method described above.

[0105] An exemplary embodiment of the present invention also provides an X-ray imaging system, comprising a patient thickness acquisition device, the patient thickness acquisition device including an acquisition module, a generation module, an extraction module, and a calculation module; the acquisition module is used to acquire optical image data and depth image data captured by a camera; the generation module is used to generate a point cloud based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views; the extraction module is used to extract a target region in the point cloud, the target region including the patient's region of interest; and the calculation module is used to acquire the patient's thickness value based on at least one key region divided within the target region, or based on identifying a first face and a second face of the patient.

[0106] The present invention may also provide a non-transitory computer-readable storage medium for storing an instruction set and / or a computer program that, when executed by a computer, causes the computer to perform the image processing allocation method described above. The computer executing the instruction set and / or the computer program may be a computer of a medical imaging system or other devices / modules of a medical imaging system. In one embodiment, the instruction set and / or the computer program may be programmed into the processor / control device of the computer.

[0107] Specifically, when this instruction set and / or computer program is executed by the computer, it causes the computer to:

[0108] Acquire optical and depth image data captured by a camera;

[0109] A point cloud is generated based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views;

[0110] Extract the target region from the point cloud, the target region including the patient's region of interest; and

[0111] The thickness value of the patient is obtained based on at least one key region divided within the target area, or based on the fitted first and second faces of the patient.

[0112] As described above, instructions can be combined into a single instruction for execution, or any instruction can be split into multiple instructions for execution. Furthermore, the execution order of instructions is not limited to that described above.

[0113] As used herein, the term "computer" can include any processor-based or microprocessor-based system, including systems that use microcontrollers, reduced instruction set computers (RISCs), application-specific integrated circuits (ASICs), logic circuits, and any other circuitry or processors capable of performing the functions described herein. The examples above are merely illustrative and are not intended to limit the definition and / or meaning of the term "computer" in any way.

[0114] The instruction set may include various commands that instruct a computer or processor, acting as a processor, to perform specific operations, such as methods and processes according to various embodiments. The instruction set may take the form of a software program, which may be part of one or more tangible, non-transitory computer-readable media. The software may take various forms, such as system software or application software. Furthermore, the software may take the form of a collection of independent programs or modules, a program module within a larger program, or part of a program module. The software may also include modular programming in the form of object-oriented programming. Input data processing by the processor may be in response to operator commands, previous processing results, or requests made by another processor.

[0115] As used herein, the term "computer" can include any processor-based or microprocessor-based system, including systems that use microcontrollers, reduced instruction set computers (RISCs), application-specific integrated circuits (ASICs), logic circuits, and any other circuitry or processors capable of performing the functions described herein. The examples above are merely illustrative and are not intended to limit the definition and / or meaning of the term "computer" in any way.

[0116] Some exemplary embodiments have been described above; however, it should be understood that various modifications can be made. For example, suitable results may be achieved if the described techniques are performed in a different order and / or if components in the described system, architecture, device, or circuit are combined in a different manner and / or replaced or supplemented by other components or their equivalents. Accordingly, other embodiments also fall within the scope of the claims.

Claims

1. A method for obtaining patient thickness, comprising: Acquire optical and depth image data captured by a camera; A point cloud is generated based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views; Extract the target region from the point cloud, the target region including the patient's region of interest; as well as The patient's thickness value is obtained based on the thickness value of at least one key region divided within the target area, or the patient's thickness value is obtained based on the fitted distance between the first and second faces of the patient.

2. The patient thickness acquisition method as described in claim 1, wherein, Generating a point cloud based on the optical image data and the depth image data includes registering the optical image data and the depth image data to generate an initial point cloud, and then post-processing the initial point cloud to obtain the final point cloud.

3. The patient thickness acquisition method as described in claim 2, wherein, The post-processing includes void filling and downsampling.

4. The patient thickness acquisition method as described in claim 1, wherein, The extraction of the target region from the point cloud includes: removing the background portion of the point cloud to obtain a target region that includes the patient's region of interest.

5. The patient thickness acquisition method as described in claim 4, wherein, Removing the background portion from the point cloud includes: The point cloud is identified using a classification learning model, and the target region is extracted based on the classification map. The background portion is removed based on the source image distance SID.

6. The patient thickness acquisition method as described in claim 1, wherein, Obtaining the patient's thickness value based on the thickness of one or more key regions divided within the target area includes: Based on the patient's imaging location, at least one key region is divided within the target area; and The mean thickness value within each of the at least one key region is calculated. When the target region is divided into multiple key regions, the patient thickness value within each key region is calculated, and the overall thickness value of the patient is calculated based on the weight of each key region.

7. The patient thickness acquisition method as described in claim 1, wherein, The thickness value of the patient is obtained by fitting the distance between the first and second surfaces of the patient, including: The first side of the patient away from the detector is identified based on the thickness value in the target area; Fit and identify the second side of the patient near the detector; The thickness value of the patient is obtained based on the distance between the first surface and the second surface.

8. The patient thickness acquisition method as described in claim 7, wherein, The second aspect of fitting and identifying the patient includes: Fitting the patient to multiple planes near the detector, the multiple planes including the surface of the detector; and The second surface is identified among the plurality of planes based on the continuity of the histogram of the target region.

9. The patient thickness acquisition method as described in claim 7, wherein, Identifying the first face of the patient away from the detector includes: determining the location of the maximum thickness in the target region, and defining the face where the location is located as the first face of the patient.

10. An X-ray imaging method, comprising: Acquire optical and depth image data captured by a camera; A point cloud is generated based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views; Extract the target region from the point cloud, the target region including the patient's region of interest; The thickness value of the patient is obtained based on the thickness of at least one key region divided within the target area, or the thickness value of the patient is obtained based on the fitted distance between the first and second faces of the patient; as well as Exposure parameters are selected based on the thickness value to expose the patient.

11. An X-ray imaging system comprising a control unit, wherein the control unit is capable of performing the patient thickness acquisition method as described in any one of claims 1-9.

12. An X-ray imaging system comprising a patient thickness acquisition device, the patient thickness acquisition device comprising: The acquisition module is used to acquire optical image data and depth image data captured by the camera. A generation module is used to generate a point cloud based on the optical image data and the depth image data, wherein the point cloud can be displayed in one or more views; An extraction module is used to extract a target region from the point cloud, the target region including the patient's region of interest; as well as A calculation module is used to obtain the thickness value of the patient based on the thickness of at least one key region divided within the target area, or to obtain the thickness value of the patient based on the distance between the first and second faces of the patient.

13. A non-transitory computer-readable storage medium for storing a computer program that, when executed by a computer, causes the computer to perform the patient thickness acquisition method according to any one of claims 1-9.

Images