Human body positioning method for X-ray transmission examination

Abstract

The invention provides a human body positioning method for X-ray transmission examination. The method comprises the steps that a visible light image of a patient on a sickbed and a preoperative medical image of the patient obtained through fluoroscopy equipment are obtained; a corresponding patient parameterized model is obtained based on the visible light image, and a standard skeleton model is obtained based on fitting of the patient parameterized model; segmenting and reconstructing the preoperative medical image to obtain a personalized skeleton model; and based on the target bone mark point, fusing the personalized bone model with a standard bone model to obtain a target fusion image so as to realize target organ positioning of the patient. By means of the method, the target organ can be rapidly positioned according to the target bone mark point before an operation.

Description

Technical Field

[0001] The invention relates to the intersection of medicine and engineering, and in particular to a human body positioning method for X-ray transmission inspection. Background Art

[0002] During surgery, common methods of X-ray transmission examination include: 1) Fluoroscopic X-ray imaging: Fluoroscopic X-ray equipment is used during surgery to guide doctors through real-time imaging of penetrating X-rays. This method is usually used for orthopedic surgery and the placement of internal fixations. 2) Digital subtraction angiography (DSA): During interventional surgery, doctors can introduce contrast agents into the patient's blood vessels and combine them with X-ray imaging technology to monitor the situation in the blood vessels in real time to guide the interventional surgery. These methods can provide real-time X-ray transmission imaging information during surgery, assisting doctors in accurate positioning and operation, and play an important auxiliary role in some surgeries that require precise positioning and operation.

[0003] Fluoroscopic X-ray devices (also called X-ray fluoroscopy devices) are commonly used for real-time dynamic imaging during surgery, mainly including C-arms, O-arms and G-arms. C-arm X-ray devices usually consist of a fixed articulated arm and a movable X-ray detector, and are shaped like the letter "C". This device is widely used in surgical and treatment procedures such as orthopedic surgery, trauma surgery, and cardiac catheter intervention to provide real-time X-ray imaging. O-arm X-ray devices are X-ray devices that rotate around the patient and are usually used for imaging and guided surgery in the operating room. O-arm devices can provide high-resolution 3D imaging, which helps doctors accurately position and plan surgeries during complex surgeries. G-arm X-ray devices are similar to C-arms, but have slightly different structures and are also usually used for X-ray imaging and guided surgery in the operating room. It can provide multi-angle X-ray imaging to help doctors observe and guide in real time during surgery.

[0004] X-ray radiography hopes to obtain prior information about the position and shape of the organ to be examined. Due to the radiation damage problem of X-ray radiography, the maximum number of scans that a patient can safely accept in a specific time period is limited. Due to this limitation, doctors must carefully plan the imaging plan before surgery. Any solution that helps to quickly and accurately locate the target organ without excessive beam imaging will greatly help clinicians and reduce the risk of radiation damage to patients. For example, in radiotherapy (a cancer treatment method such as using high-dose radiation to kill cancer cells and shrink tumors), it is common practice to use patient-specific molds (usually made of plastic or plaster) to keep the patient in exactly the same posture during preoperative organ scans and subsequent treatment. This customized mold helps to accurately target the target organ area without rescanning the patient and relocating the tumor before each treatment. However, this method limits the clinician's operating space and has considerable time and money costs. In the prior art, an in vivo organ deformation model based on different postures of the subject is also proposed, which can extract the organ shape representation of a specific patient and predict its deformed shape based on different posture parameters. However, this method uses FEM (Finite element method) to simulate posture-related organ deformation, and its accuracy and generalization ability for different organs need to be verified. Summary of the invention

[0005] The present invention aims to solve one of the technical problems in the related art at least to a certain extent.

[0006] To this end, the first object of the present invention is to provide a human body positioning method for X-ray transmission examination, so as to quickly locate the target organ according to the target bone landmarks before the operation.

[0007] The second object of the present invention is to provide a human body positioning system for X-ray transmission inspection.

[0008] A third objective of the present invention is to provide an electronic device.

[0009] A fourth object of the present invention is to provide a computer-readable storage medium.

[0010] To achieve the above object, the present invention provides a human body positioning method for X-ray transmission inspection in a first aspect, comprising:

[0011] Obtaining a visible light image of a patient on a bed and a preoperative medical image of the patient obtained using a fluoroscopic examination device;

[0012] Obtaining a corresponding patient parameterized model based on the visible light image, and fitting a standard bone model based on the patient parameterized model;

[0013] Segmenting and reconstructing the preoperative medical image to obtain a personalized bone model;

[0014] Based on the target bone landmarks, the personalized bone model is fused with the standard bone model to obtain a target fused image, so as to realize the target organ positioning of the patient.

[0015] In the method of the first aspect of the present invention, the standard bone model is obtained based on the patient's parameterized model, including: generating bone package surface data, and obtaining skin surface data based on the patient's parameterized model; and obtaining a standard bone model based on the bone package surface data and the skin surface data.

[0016] In the method of the first aspect of the present invention, the standard bone model is obtained by fitting the bone envelope data and the skin surface data using nonlinear least squares method.

[0017] In the method of the first aspect of the present invention, the standard skeleton model is obtained by fitting based on the skeleton surface data and the skin surface data using the nonlinear least squares method, including: setting deformation surface parameters, obtaining energy based on the deformation surface parameters, the skeleton surface data and the skin surface data, and minimizing the energy using the nonlinear least squares method to obtain the standard skeleton model.

[0018] In the method of the first aspect of the present invention, the personalized skeleton model is fused with the standard skeleton model based on the target bone landmark points to obtain the target fused image, including: selecting a first target bone landmark point set of the personalized skeleton model in a preset order and a preset number; selecting a second target bone landmark point set of the standard skeleton model in a preset order and a preset number; fusing the first target bone landmark point set and the second target bone landmark point set in a corresponding order to obtain the target fused image.

[0019] In the method of the first aspect of the present invention, the first target bone landmark set and the second target bone landmark set are fused in a corresponding order to obtain the target fused image, including: one-to-one correspondence between each first target bone landmark point in the first target bone landmark set and the second target bone landmark point set in a corresponding order; obtaining a spatial transformation combination, and adjusting the personalized skeleton model based on the spatial transformation combination so that the adjusted personalized skeleton model is consistent with the coordinate system of the standard skeleton model, thereby obtaining the target fused image.

[0020] To achieve the above object, the second aspect of the present invention provides a human body positioning system for X-ray transmission inspection, comprising:

[0021] An image acquisition module, used to acquire a visible light image of a patient on a hospital bed and a preoperative medical image of the patient obtained by a fluoroscopic examination device;

[0022] A bone modeling module, used for obtaining a corresponding patient parameterized model based on the visible light image, and fitting a standard bone model based on the patient parameterized model;

[0023] A reconstruction module, used for segmenting and reconstructing the preoperative medical image to obtain a personalized bone model;

[0024] A fusion module is used to fuse the personalized bone model with the standard bone model based on target bone landmarks to obtain a target fusion image to achieve target organ positioning of the patient.

[0025] In the system of the second aspect of the present invention, the skeleton modeling module, when used to obtain a standard skeleton model based on the patient's parameterized model, is specifically used to: generate skeleton package surface data, and obtain skin surface data based on the patient's parameterized model; and obtain a standard skeleton model based on the skeleton package surface data and the skin surface data.

[0026] To achieve the above-mentioned purpose, the third aspect of the present invention proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method proposed in the first aspect of the present invention.

[0027] To achieve the above-mentioned purpose, the fourth aspect of the present invention proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method proposed in the first aspect of the present invention.

[0028] The human body positioning method, system, electronic device and storage medium for X-ray transmission inspection provided by the present invention are obtained by obtaining a visible light image of a patient on a hospital bed and a preoperative medical image of the patient obtained by using a perspective inspection device; obtaining a corresponding patient parameterized model based on the visible light image, and obtaining a standard bone model based on the fitting of the patient parameterized model; segmenting and reconstructing the preoperative medical image to obtain a personalized bone model; based on the target bone landmarks, the personalized bone model is fused with the standard bone model to obtain a target fusion image to achieve the patient's target organ positioning. In this case, the standard bone model obtained by using the visible light image and the personalized bone model obtained by using the preoperative medical image are combined, and based on the target bone landmarks, the personalized bone model is fused with the standard bone model to obtain a target fusion image, and the target organ position and shape under the patient's human body posture corresponding to the visible light image can be obtained based on the bone position in the target fusion image, thereby achieving the rapid positioning of the target organ according to the target bone landmarks before surgery, thereby better assisting doctors in formulating imaging plans before surgery, and reducing the scanning radiation dose during intraoperative X-ray transmission inspection.

[0029] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0031] Figure 1 A schematic flow chart of a method for positioning a human body for X-ray transmission inspection provided by an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of a shooting scene provided by an embodiment of the present invention;

[0033] Figure 3 A schematic diagram of a visible light image and a SMPL patient three-dimensional model provided in an embodiment of the present invention;

[0034] Figure 4 A schematic diagram of the skeletal landmarks and body surface three-dimensional model provided in an embodiment of the present invention;

[0035] Figure 5 A schematic diagram of fitting a standard bone model according to a SMPL patient three-dimensional model provided in an embodiment of the present invention;

[0036] Figure 6 A schematic diagram of a preoperative medical image and a segmentation and reconstruction result provided by an embodiment of the present invention;

[0037] Figure 7A schematic diagram of selecting bone landmarks provided in an embodiment of the present invention;

[0038] Figure 8 A schematic diagram of the effect of fusing the reconstructed spine model provided by an embodiment of the present invention with the standard skeleton model;

[0039] Fig. 9 A block diagram of a human body positioning system for X-ray transmission inspection provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0041] The following describes a method and system for positioning a human body for X-ray transmission inspection according to an embodiment of the present invention with reference to the accompanying drawings.

[0042] The embodiment of the present invention provides a human body positioning method for X-ray transmission inspection, so as to quickly locate the target organ according to the target bone landmark point before the operation.

[0043] Figure 1 A schematic flow chart of a method for positioning a human body for X-ray transmission inspection provided by an embodiment of the present invention.

[0044] like Figure 1 As shown, the human body positioning method for X-ray transmission inspection includes the following steps:

[0045] Step S101, obtaining a visible light image of a patient on a hospital bed and a preoperative medical image of the patient obtained by using a fluoroscopic examination device.

[0046] In step S101, the visible light image can be obtained by taking a visible light camera arranged on the X-ray fluoroscopic examination equipment. Specifically, a visible light camera is installed near the detector plane of the X-ray fluoroscopic examination equipment, and the visible light image of the patient on the bed is taken by the visible light camera.

[0047] In step S101, preoperative medical images can be obtained by scanning with a fluoroscopic examination device. The scanning methods of preoperative medical images mainly include: computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET-CT), ultrasound imaging, etc.

[0048] Figure 2Schematic diagram of a shooting scene provided by an embodiment of the present invention. Figure 2 As shown, the fluoroscopic examination device is an X-ray fluoroscopic examination device. The X-ray fluoroscopic examination device obtains preoperative medical images of the patient on the bed through an X-ray source and a detector. A visible light camera is installed near the detector plane of the X-ray fluoroscopic examination device, and the visible light image of the patient on the bed is captured by the visible light camera.

[0049] Step S102, obtaining a corresponding patient parameterized model based on the visible light image, and obtaining a standard bone model based on fitting of the patient parameterized model.

[0050] It is easy to understand that there are many parametric expressions for 3D human modeling. SMPL (Skinned Multi-Person Linear) is a parametric 3D human model that efficiently describes and generates 3D human morphology with a small number of parameters. SMPL can convert input posture parameters and shape parameters into the posture and shape of a 3D human model. Specifically, SMPL is defined as a parameterized human model M(β,θ), which maps the shape parameter vector β and the posture parameter vector θ to the vertices of the human body, where β is used to control the shape of the human body and θ is used to control the posture of the human body. SMPL-H is a variant of the SMPL model, which adds the details of the hand bones on the basis of SMPL, making the generated human model more realistic. SMPL-X is an extended version of the SMPL model, suitable for people of various body types, muscle mass and body shape characteristics, and can simulate more realistic human shapes and movements. STAR (Sparse Trained Articulated Human BodyRegressor) is a framework for body pose reconstruction and animation generation. It combines the technologies of SMPL and BlendSCAPE. It converts pose-related deformation factors into a set of sparse spatial local pose correction blend shape functions, where each joint only affects a sparse subset of mesh vertices. It can reconstruct 3D human pose from a single image or video, and perform animation generation and editing.

[0051] In the embodiment of the present invention, taking the SMPL model as an example when performing three-dimensional modeling of a patient, the patient parameterized model obtained based on the visible light image in step S102 is the SMPL patient three-dimensional model.

[0052] The specific steps of obtaining the corresponding SMPL patient 3D model based on the visible light image include: (1) posture estimation: using computer vision and deep learning technology to estimate the joint position and posture of the patient in the visible light image to obtain the joint position and posture estimation results; (2) shape modeling: using the joint position and posture estimation results and adopting the existing human body shape modeling method to estimate the patient's 3D shape, thereby obtaining the patient's shape parameter vector β and posture parameter vector θ; (3) alignment and matching: obtaining the learned SMPL, and inputting the obtained patient's shape parameter vector β and posture parameter vector as input data into the learned SMPL output patient's vertices, all of which constitute the SMPL patient 3D model, thereby realizing the alignment and matching of the estimated patient's 3D shape with the SMPL model.

[0053] Figure 3 Schematic diagram of a visible light image and a SMPL patient three-dimensional model provided in an embodiment of the present invention. Figure 3 (a) is a visible light image of the patient, (b) and (c) are the front view and side view of the SMPL patient three-dimensional model obtained by the method of the present invention, respectively.

[0054] In step S102, a standard bone model is obtained based on the patient's parameterized model, including: generating bone package surface data, and obtaining skin surface data based on the patient's parameterized model; and obtaining a standard bone model based on the bone package surface data and the skin surface data. The standard bone model is obtained by fitting the bone package surface data and the skin surface data using a nonlinear least squares method.

[0055] A standard bone model is obtained by fitting the bone package surface data and the skin surface data using the nonlinear least squares method, including: setting deformation surface parameters, obtaining energy based on the deformation surface parameters, the bone package surface data and the skin surface data, and minimizing the energy using the nonlinear least squares method to obtain a standard bone model.

[0056] Specifically, taking the SMPL patient 3D model as an example, the process of fitting the standard bone model based on the SMPL patient 3D model is as follows:

[0057] Figure 4 A schematic diagram of the skeletal landmarks and body surface three-dimensional model provided in an embodiment of the present invention; Figure 5 A schematic diagram of fitting a standard bone model according to an SMPL patient three-dimensional model provided in an embodiment of the present invention.

[0058] The generated SMPL patient 3D model and the camera parameters corresponding to the visible light camera are used to project the 3D posture onto the 2D image plane. In the projected 2D image, certain specific joint points or bone landmarks (referred to as bone landmarks) are extracted, such as the 2D bone landmarks of the head, shoulders, elbows, and wrists. Figure 4 As shown in (a), there are multiple bone landmarks located at the head, shoulder, elbow, wrist, hip, knee, ankle, etc. These bone landmarks are connected to form the initial spatial configuration of the skeleton of the standard skeleton model. For the initial spatial configuration of the skeleton, a watertight Genus-0 surface is first generated to wrap the initial spatial configuration of the skeleton, referred to as the skeleton wrapping surface W (i.e., the skeleton wrapping surface data). The skeleton wrapping surface is a smooth, impermeable two-dimensional manifold surface, which does not include areas such as the inside of the ribs, nor does it include the pelvis or the small holes between the ulna and radius.

[0059] Based on the generated SMPL patient 3D model, a body surface 3D model (such as Figure 4 In (b), the body surface 3D model is the skin surface data, also called skin surface M. Based on the skin surface M, the standard bone model B is generated. First, the initial vertex configuration of the deformation surface X (i.e., deformation surface parameters) is set. The energy is then minimized using a nonlinear least squares method, which consists of a fitting term and a regularization term. The fitting term is used to attract the deformed surface X to the bone wrapping surface W; the regularization term is used to prevent the deformed surface X from moving away from its initial vertex configuration. Deformed in physically implausible ways:

[0060]

[0061] Where B is the standard skeleton model (also called energy), ω fit is the fitting term weight, ω reg is the regularization term weight.

[0062] The regularization is formulated as a discrete curvature energy that penalizes changes in the mean curvature:

[0063]

[0064] In the formula, x i and Represent the deformed surface X and the initial vertex configuration respectively The vertex of R i ∈SO(3) means to convert the vertex Laplace Δx i and The optimal rotation matrix for alignment, A i Represents the Voronoi area.

[0065] Fit term to vertex xi ∈X and the target position t i ∈W squared distance penalty:

[0066]

[0067] Where, the target position t i It is a point on the skeleton wrapping surface W. There are three types: closest point correspondence, fixed correspondence or collision target. Weight ω i From the target position t i The type of (the closest point corresponds to 0.1, the fixed point corresponds to 1, and the collision target is 100). After minimizing formula (1), the final standard skeleton model B is obtained. The standard skeleton model is a three-dimensional skeleton model. Figure 5 (a) shows a 3D model of a SMPL patient with bone landmarks. Figure 5 The standard skeleton model B obtained is shown in (b).

[0068] Step S103, segmenting and reconstructing the preoperative medical image to obtain a personalized skeleton model.

[0069] In step S103, the preoperative medical image can be targeted at the human spine, so the obtained personalized bone model is a reconstructed spine model. It should be noted that the preoperative medical image can also be targeted at different parts such as arms, head, pelvis, etc. as needed to obtain a reconstructed model of the bones of the corresponding parts.

[0070] In the embodiment of the present invention, taking the CT scan image of the human spine as an example, Figure 6 Schematic diagram of preoperative medical images and segmentation and reconstruction results provided by an embodiment of the present invention. Figure 6 (a) shows a CT scan image of the human spine taken before surgery. The CT scan image is segmented and reconstructed to obtain Figure 6 The reconstructed spine model shown in (b) includes lumbar vertebrae, thoracic vertebrae and cervical vertebrae.

[0071] Step S104, based on the target bone landmarks, the personalized skeleton model is fused with the standard skeleton model to obtain a target fused image to achieve the target organ positioning of the patient.

[0072] In step S104, based on the target bone landmarks, the personalized bone model is fused with the standard bone model to obtain a target fused image, including: selecting the first target bone landmark set of the personalized bone model in a preset order and a preset number; selecting the second target bone landmark set of the standard bone model in a preset order and a preset number; fusing the first target bone landmark set and the second target bone landmark set in a corresponding order to obtain a target fused image. Among them, fusing the first target bone landmark set and the second target bone landmark set in a corresponding order to obtain a target fused image includes: one-to-one correspondence of each first target bone landmark in the first target bone landmark set and the second target bone landmark set in a corresponding order; obtaining a spatial transformation combination, and adjusting the personalized bone model based on the spatial transformation combination so that the adjusted personalized bone model is consistent with the coordinate system of the standard bone model, thereby obtaining a target fused image.

[0073] In step S104, taking the reconstruction of the spinal column model as an example, the target bone landmarks are selected from the lumbar vertebrae, thoracic vertebrae and cervical vertebrae. The preset number is, for example, 5, and the preset order is, for example, the first cervical vertebra, the seventh cervical vertebra, the seventh thoracic vertebra, the fourth lumbar vertebra and the fifth lumbar vertebra.

[0074] Figure 7 Schematic diagram of bone landmark selection provided by an embodiment of the present invention. Figure 7 As shown, the reconstructed spinal column model includes lumbar vertebrae, thoracic vertebrae, cervical vertebrae and sacral vertebrae, among which the cervical vertebrae include the first cervical vertebra C1, the second cervical vertebra C2, the third cervical vertebra C3, ..., and the seventh cervical vertebra C7. The thoracic vertebrae include the first thoracic vertebra T1, the second thoracic vertebra T2, ..., the seventh thoracic vertebra T7, ..., the eleventh thoracic vertebra T11, and the twelfth thoracic vertebra T12. The lumbar vertebrae include the first lumbar vertebra L1, the second lumbar vertebra L2, ..., the fourth lumbar vertebra L4, and the fifth lumbar vertebra L5. The sacral vertebrae include the first sacral vertebra S1, etc. The center point m1 of the first cervical vertebra C1, the center point m2 of the seventh cervical vertebra C7, the center point m3 of the seventh thoracic vertebra T7, the center point m4 of the fourth lumbar vertebra L4 and the center point m5 of the fifth lumbar vertebra L5 in the reconstructed spine model are selected as five first target bone landmarks to obtain a first target bone landmark set, recorded as the first target bone landmark set LM1 = {m1, m2, m3, m4, m5 These first target bone landmarks are selected mainly because of their anatomical specificity and identifiability. For example, the seventh cervical vertebra C7 is the lowest one among the cervical vertebrae, characterized by a prominent spinous process, which is called a significant vertebra.

[0075] For the standard skeleton model, the second target bone landmark point set is obtained according to a preset order and a preset quantity, and the second target bone landmark point set LM2 = {n1, n2, n3, n4, n5}, where the five second target bone landmark points n1, n2, n3, n4, n5 are respectively the center point of the first cervical vertebra C1′, the center point of the seventh cervical vertebra C7′, the center point of the seventh thoracic vertebra T7′, the center point of the fourth lumbar vertebra L′4 and the center point of the fifth lumbar vertebra L′5 in the standard skeleton model.

[0076] The target bone landmark points in the two sets of target bone landmark points are listed in a one-to-one correspondence relationship: i=1,2,3,4,5,m i ∈LM1,n i ∈LM2,. Then we have n i =lRm i +t+∈ i ,i=1,2,3,4,5. Where l>0, is the scaling factor; R∈SO(3) is the three-dimensional rotation matrix; is the three-dimensional translation vector; Model the unknown additive noise, assuming that the noise follows a zero-mean isotropic Gaussian distribution with a standard deviation of σ i Under the condition of maximum likelihood estimation, the scaling factor l is optimized. * , the rotation matrix R * and the translation vector t * :

[0077]

[0078] In the formula, l * ,R * ,t * The spatial transformation combination is formed. The spatial transformation combination obtained by the optimization solution is applied to the reconstructed spine model to adjust the coordinate system of the reconstructed spine model, so that the adjusted reconstructed spine model is consistent with the coordinate system of the standard bone model.

[0079] Figure 8 This is a schematic diagram of the effect of fusing the reconstructed spine model provided by the embodiment of the present invention with the standard skeleton model. Figure 8 (a) shows the fusion image obtained by fusing the reconstructed spine model with the standard skeleton model. Figure 8 (b) and (c) show the side view and front view of the fused image of the SMPL patient 3D model corresponding to the reconstructed spine model and the standard skeletal model.

[0080] In step S104, the target fusion image may include a first fusion image obtained by fusing the personalized skeleton model with the standard skeleton model. The target fusion image may also include a second fusion image of the patient's parameterized model corresponding to the personalized skeleton model and the standard skeleton model, a third fusion image of the preoperative medical image corresponding to the personalized skeleton model and the standard skeleton model, etc.

[0081] In step S104, since the relative positions of the bones and target organs in the personalized bone model are fixed, after the personalized bone model is fused with the standard bone model, the relative positions of the bones and target organs are mapped to the standard bone model, so that the target fusion image includes the position and shape information of the target organ under the patient's body posture in the visible light image. Therefore, based on the target fusion image, the position and shape of the human body, especially the target organ, can be quickly located during the X-ray transmission examination. Assist doctors to formulate imaging plans before surgery and reduce scanning radiation dose.

[0082] In order to implement the above embodiment, the present invention also provides a human body positioning system for X-ray transmission inspection.

[0083] Fig. 9 A block diagram of a human body positioning system for X-ray transmission inspection provided by an embodiment of the present invention.

[0084] like Fig. 9 As shown, the human body positioning system for X-ray transmission inspection includes an image acquisition module, a bone modeling module, a reconstruction module and a fusion module, wherein:

[0085] An image acquisition module, used to acquire a visible light image of a patient on a hospital bed and a preoperative medical image of the patient obtained by a fluoroscopic examination device;

[0086] A bone modeling module, used for obtaining a corresponding patient parameterized model based on a visible light image, and obtaining a standard bone model based on the patient parameterized model fitting;

[0087] The reconstruction module is used to segment and reconstruct preoperative medical images to obtain a personalized bone model;

[0088] The fusion module is used to fuse the personalized bone model with the standard bone model based on the target bone landmarks to obtain a target fusion image to achieve the target organ positioning of the patient.

[0089] Furthermore, in a possible implementation of an embodiment of the present invention, in a skeleton modeling module, a standard skeleton model is obtained based on the patient's parameterized model fitting, including: generating skeleton package surface data, and obtaining skin surface data based on the patient's parameterized model; and obtaining a standard skeleton model based on the skeleton package surface data and the skin surface data fitting.

[0090] Furthermore, in a possible implementation manner of the embodiment of the present invention, in the skeleton modeling module, a standard skeleton model is obtained by fitting the skeleton package surface data and the skin surface data using a nonlinear least squares method.

[0091] Furthermore, in a possible implementation of an embodiment of the present invention, in a skeleton modeling module, a standard skeleton model is obtained by fitting based on the skeleton package surface data and the skin surface data using the nonlinear least squares method, including: setting deformation surface parameters, obtaining energy based on the deformation surface parameters, the skeleton package surface data and the skin surface data, and minimizing the energy using the nonlinear least squares method to obtain a standard skeleton model.

[0092] Furthermore, in a possible implementation manner of the embodiment of the present invention, in the fusion module, the target bone landmarks are selected from the lumbar vertebrae, thoracic vertebrae and cervical vertebrae.

[0093] Furthermore, in a possible implementation method of an embodiment of the present invention, the fusion module is specifically used to: select a first target bone landmark point set of a personalized skeleton model according to a preset order and a preset quantity; select a second target bone landmark point set of a standard skeleton model according to a preset order and a preset quantity; and fuse the first target bone landmark point set and the second target bone landmark point set in a corresponding order to obtain a target fused image.

[0094] Furthermore, in a possible implementation method of an embodiment of the present invention, in a fusion module, the first target bone landmark point set and the second target bone landmark point set are fused in a corresponding order to obtain a target fused image, including: one-to-one correspondence between each first target bone landmark point in the first target bone landmark point set and the second target bone landmark point set in a corresponding order; obtaining a spatial transformation combination, and adjusting the personalized skeleton model based on the spatial transformation combination so that the adjusted personalized skeleton model is consistent with the coordinate system of the standard skeleton model, thereby obtaining the target fused image.

[0095] It should be noted that the above explanation of the embodiment of the human body positioning method for X-ray transmission inspection is also applicable to the human body positioning system for X-ray transmission inspection of this embodiment, and will not be repeated here.

[0096] In an embodiment of the present invention, a visible light image of a patient on a hospital bed and a preoperative medical image of the patient obtained by a fluoroscopic examination device are obtained; a corresponding patient parameterized model is obtained based on the visible light image, and a standard bone model is obtained based on the fitting of the patient parameterized model; the preoperative medical image is segmented and reconstructed to obtain a personalized bone model; based on the target bone landmarks, the personalized bone model is fused with the standard bone model to obtain a target fusion image, so as to achieve the positioning of the patient's target organ. In this case, the standard bone model obtained by using the visible light image and the personalized bone model obtained by using the preoperative medical image are combined, and based on the target bone landmarks, the personalized bone model is fused with the standard bone model to obtain a target fusion image, and the position and shape of the target organ in the patient's human body posture corresponding to the visible light image can be obtained based on the bone position in the target fusion image, thereby achieving the rapid positioning of the target organ according to the target bone landmarks before surgery, thereby better assisting doctors in formulating imaging plans before surgery, and reducing the scanning radiation dose during subsequent intraoperative X-ray transmission examinations.

[0097] In order to implement the above embodiments, the present invention also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0098] In order to implement the above embodiments, the present invention further proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0099] In order to implement the above embodiments, the present invention further provides a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0100] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0101] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0102] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0103] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0104] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0105] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0106] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0107] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A human body positioning method for X-ray transmission inspection, characterized in that: include: Obtaining a visible light image of a patient on a bed and a preoperative medical image of the patient obtained using a fluoroscopic examination device; Obtaining a corresponding patient parameterized model based on the visible light image, and fitting a standard bone model based on the patient parameterized model; Segmenting and reconstructing the preoperative medical image to obtain a personalized bone model; Based on the target bone landmarks, the personalized bone model is fused with the standard bone model to obtain a target fused image, so as to realize the target organ positioning of the patient.

2. The human body positioning method for X-ray transmission inspection according to claim 1, characterized in that: The step of obtaining a standard bone model based on the patient's parameterized model fitting comprises: Generate bone wrapping surface data, and obtain skin surface data based on the patient parameterized model; A standard bone model is obtained by fitting based on the bone wrapping surface data and the skin surface data.

3. The human body positioning method for X-ray transmission inspection according to claim 2, characterized in that: The standard bone model is obtained by fitting the bone envelope data and the skin surface data using the nonlinear least squares method.

4. The method for positioning a human body for X-ray transmission inspection according to claim 3, characterized in that: The method of obtaining the standard bone model by fitting the bone package surface data and the skin surface data using a nonlinear least square method comprises: Deformation surface parameters are set, energy is obtained based on the deformation surface parameters, the bone wrapping surface data and the skin surface data, and the energy is minimized using a nonlinear least squares method, thereby obtaining the standard bone model.

5. The human body positioning method for X-ray transmission inspection according to claim 1, characterized in that: The method of fusing the personalized skeleton model with the standard skeleton model based on the target bone landmark to obtain a target fused image includes: Selecting a first target bone landmark point set of the personalized skeleton model in a preset order and a preset quantity; Selecting a second target bone landmark point set of the standard skeleton model in a preset order and a preset number; The first target bone landmark point set and the second target bone landmark point set are fused in a corresponding order to obtain the target fused image.

6. The method for positioning a human body for X-ray transmission inspection according to claim 5, characterized in that: The step of fusing the first target bone landmark point set and the second target bone landmark point set in a corresponding order to obtain the target fused image includes: One-to-one correspondence is made between each first target bone landmark point in the first target bone landmark point set and each first target bone landmark point in the second target bone landmark point set in a corresponding order; A spatial transformation combination is obtained, and the personalized skeleton model is adjusted based on the spatial transformation combination so that the coordinate system of the adjusted personalized skeleton model is consistent with that of the standard skeleton model, thereby obtaining the target fused image.

7. A human body positioning system for X-ray transmission inspection, characterized in that: include: An image acquisition module, used to acquire a visible light image of a patient on a hospital bed and a preoperative medical image of the patient obtained by a fluoroscopic examination device; A bone modeling module, used for obtaining a corresponding patient parameterized model based on the visible light image, and fitting a standard bone model based on the patient parameterized model; A reconstruction module, used for segmenting and reconstructing the preoperative medical image to obtain a personalized bone model; A fusion module is used to fuse the personalized bone model with the standard bone model based on target bone landmarks to obtain a target fusion image to achieve target organ positioning of the patient.

8. The human body positioning system for X-ray transmission inspection according to claim 7, characterized in that: The skeleton modeling module, when used to obtain a standard skeleton model based on the patient parameterized model, is specifically used to: generate skeleton package surface data and obtain skin surface data based on the patient parameterized model; and obtain a standard skeleton model based on the skeleton package surface data and the skin surface data.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

Images