Spinal cord lesion positioning method and device and medium

Abstract

The invention relates to the technical field of image processing, in particular to a spinal cord lesion positioning method and device and a medium, and the method comprises the steps: obtaining a standardized spinal cord MR template and a spinal cord anatomy image marking map; acquiring a spinal cord PET image and a spinal cord MR image of the target patient through the PET / MR all-in-one machine; obtaining a spinal cord PET image and a spinal cord MR image; fusing the spinal cord PET image and the spinal cord MR image to obtain a fused image; performing spatial standardization conversion on the spinal cord MR image according to the standardized MR template to obtain conversion parameters; based on the conversion parameters, affine the standardized spinal cord MR template and the spinal cord anatomical image marking atlas to the spinal cord PET image of the patient so as to finely mark the spinal cord PET image of the patient to obtain a marked image; and based on the marked image and the fused image, spinal cord lesion position positioning is performed on the PET image part in the fused image, and accurate positioning of spinal cord lesion is realized through accurate fusion of the PET image and the MR image of the patient, so that the diagnosis efficiency is improved, and the burden of a clinician is reduced.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a spinal cord lesion positioning method, device and medium. Background Art

[0002] Among existing imaging technologies, PET imaging can provide functional information on tissue metabolic activity and molecular levels, and is widely used clinically in the diagnosis of various neurological diseases. However, PET imaging has relatively low spatial and tissue resolution. Furthermore, given that the spinal cord diameter is typically less than 1 cm, PET imaging alone cannot distinguish gray matter, white matter, and finer structural divisions within the spinal cord, limiting its application in the diagnosis of spinal cord lesions.

[0003] Magnetic resonance imaging (MR), another important structural imaging technique, offers high spatial and tissue resolution, clearly demonstrating the structures and fine divisions within the spinal cord. In theory, it is possible to match and fuse the two modalities, guiding the MR imaging to identify the specific structure and precise divisions of spinal cord lesions in PET images.

[0004] However, traditional PET / MR image fusion technology has the following defects:

[0005] PET images and MR images are acquired by different devices at different time points. The resulting spinal cord images differ in shape and bending angles at different stages, making them difficult to accurately match. Therefore, the positioning of spinal cord lesions in PET images is highly subjective and inefficient, and is heavily dependent on the operator's knowledge and experience.

[0006] Therefore, how to accurately fuse PET images and MR images to achieve accurate positioning of spinal cord lesions in PET images is a technical problem that needs to be solved urgently. Summary of the Invention

[0007] In view of the above problems, the present invention provides a method, device and apparatus for locating spinal cord lesions that overcome the above problems or at least partially solve the above problems.

[0008] In a first aspect, the present invention provides a method for localizing a spinal cord lesion, comprising:

[0009] Obtain standardized spinal cord MR templates and spinal cord anatomical imaging markers;

[0010] Acquire a spinal cord PET image and a spinal cord MR image of a target patient, wherein the spinal cord PET image and the spinal cord MR image are acquired based on a PET / MR all-in-one machine;

[0011] fusing the spinal cord PET image and the spinal cord MR image to obtain a fused image;

[0012] Performing spatial standardization transformation on the spinal cord MR image according to the standardized spinal cord MR template to obtain transformation parameters;

[0013] Based on the conversion parameters, the spinal cord anatomical image labeling atlas is affine-mapped onto the spinal cord MR image to finely label the spinal cord MR image of the target patient to obtain a labeled image;

[0014] Based on the marked image and the fused image, the spinal cord lesion position is located on the PET portion in the fused image.

[0015] Preferably, obtaining a standardized spinal cord MR template includes:

[0016] A standardized spinal cord MR template was established based on adult MR spinal cord imaging data.

[0017] Preferably, obtaining a spinal cord anatomical image labeling atlas includes:

[0018] Based on the standardized spinal cord MR template, a spinal cord anatomical image labeling atlas is established.

[0019] Preferably, a spinal cord anatomical image labeling atlas is established based on the standardized spinal cord MR template, comprising:

[0020] Based on the standardized spinal cord MR template, the key areas of each layer of the image were outlined, segmented and labeled according to the spinal cord anatomical atlas to establish a spinal cord anatomical image labeling atlas.

[0021] Preferably, the spinal cord PET image and the spinal cord MR image are fused to obtain a fused image, comprising:

[0022] The rigid body transformation technology is used to transform the spinal cord PET image and the spinal cord MR image through translation transformation and rotation transformation, so that the spinal cord PET image and the spinal cord MR image are fused to obtain a fused image.

[0023] Preferably, the spinal cord MR image is subjected to spatial standardization transformation according to the standardized spinal cord MR template to obtain transformation parameters, including:

[0024] The spinal cord MR image is aligned with the overall direction, position and scale of the standardized spinal cord MR template, and is converted by correcting the rotation, translation and scaling differences to obtain conversion parameters, wherein the conversion parameters include the corrected rotation amount, translation amount and scaling difference amount.

[0025] Preferably, based on the conversion parameters, the spinal cord anatomical image labeling atlas is affine-mapped onto the spinal cord MR image to finely label the spinal cord MR image to obtain a labeled image, comprising:

[0026] The spinal cord anatomical image labeling atlas is affine-projected onto the spinal cord PET image through inverse transformation according to the conversion parameters, so as to finely label the patient's spinal cord MR image and obtain a labeled image.

[0027] Preferably, based on the marked image and the fused image, locating the spinal cord lesion position on the PET image portion in the fused image comprises:

[0028] Based on the marked image and the fused image, obtaining a spinal cord anatomical marker on the fused image;

[0029] Based on the spinal cord anatomical markers on the fused image, the structure of the spinal cord is automatically identified at the voxel level, and the abnormal area of ​​radioactivity distribution is analyzed on the spinal cord anatomical markers on the fused image, and the position of the spinal cord lesion is located in the PET image part of the fused image.

[0030] In a second aspect, the present invention further provides a spinal cord lesion localization device, comprising:

[0031] The first acquisition module is used to obtain a standardized spinal cord MR template and a spinal cord anatomical image labeling atlas;

[0032] A second acquisition module is used to acquire a spinal cord PET image and a spinal cord MR image of the patient, wherein the spinal cord PET image and the spinal cord MR image are acquired based on a PET / MR integrated machine;

[0033] A first obtaining module is used to fuse the spinal cord PET image and the spinal cord MR image to obtain a fused image;

[0034] a second obtaining module, configured to perform spatial standardization conversion on the spinal cord MR image according to the standardized spinal cord MR template to obtain conversion parameters;

[0035] a third obtaining module, configured to affine-project the standardized spinal cord MR template and the spinal cord anatomical image labeling atlas onto the patient's spinal cord PET image based on the conversion parameters, so as to finely label the patient's spinal cord MR image and obtain a labeled image;

[0036] A positioning module is used to locate the position of the spinal cord lesion on the PET image part in the fused image based on the marked image and the fused image.

[0037] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the method described in the first aspect when the program is executed by a processor.

[0038] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0039] The present invention provides a method for locating a spinal cord lesion, comprising: acquiring a standardized spinal cord MR template and a spinal cord anatomical image marking atlas; acquiring a spinal cord PET image and a spinal cord MR image of a target patient, wherein the spinal cord PET image and the spinal cord MR image are acquired based on a PET / MR integrated machine; fusing the spinal cord PET image and the spinal cord MR image to obtain a fused image; performing spatial standardization conversion on the spinal cord MR image according to the standardized MR template to obtain conversion parameters; based on the conversion parameters, affine-projecting the standardized spinal cord MR template and the spinal cord anatomical image marking atlas onto the patient's spinal cord PET image to finely mark the patient's spinal cord PET image to obtain a marked image; based on the marked image and the fused image, locating the position of the spinal cord lesion on the PET image portion of the fused image, and achieving precise positioning of the spinal cord lesion by precisely fusing the patient's PET image and MR image, thereby improving diagnostic efficiency and reducing the burden on clinicians. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. Throughout the drawings, the same reference figures denote the same components. In the drawings:

[0041] Figure 1 A schematic diagram showing the steps of a method for locating spinal cord lesions according to an embodiment of the present invention is shown;

[0042] Figure 2 A schematic diagram of a process for processing a target patient's spinal cord PET image and a spinal cord MR image in an embodiment of the present invention is shown;

[0043] Figure 3 A schematic structural diagram of a spinal cord lesion localization device in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0044] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0045] Example 1:

[0046] The embodiment of the present invention provides a method for locating spinal cord lesions, such as Figure 1 Shown, including:

[0047] S101, obtain standardized spinal cord MR template and spinal cord anatomical imaging labeling atlas;

[0048] S102, obtaining a spinal cord PET image and a spinal cord MR image of a target patient, wherein the spinal cord PET image and the spinal cord MR image are acquired based on a PET / MR all-in-one machine;

[0049] S103, fusing the spinal cord PET image and the spinal cord MR image to obtain a fused image;

[0050] S104, performing spatial standardization transformation on the spinal cord MR image according to the standardized spinal cord MR template to obtain transformation parameters;

[0051] S105, based on the conversion parameters, affine-projecting the standardized spinal cord MR template and the spinal cord anatomical image labeling atlas onto the patient's spinal cord PET image to finely label the target patient's spinal cord MR image to obtain a labeled image;

[0052] S106 , based on the marked image and the fused image, the spinal cord lesion position is located in the PET image portion of the fused image.

[0053] In a specific embodiment, in order to accurately locate the spinal cord lesion position of the target patient's PET image portion, the positioning can be performed by combining the target patient's PET image and MR image.

[0054] PET imaging, short for Positron Emission Tomography, is an advanced medical imaging technology that detects positrons emitted by radioactive tracers injected into the body to generate three-dimensional images of the human body, revealing the metabolic, functional, and biochemical information of human tissues. However, the relatively low spatial and tissue resolution of spinal cord PET imaging limits its use in the diagnosis of spinal cord lesions.

[0055] MR imaging is a non-invasive medical examination technique that uses magnetic fields and radiofrequency pulses to produce high-resolution images of the human body's internal structures. Its core is to detect the resonance signals of hydrogen nuclei in the human body in a strong magnetic field, and then process them through a computer to produce multi-dimensional anatomical images. Its high resolution makes it suitable for the precise assessment of neurological and soft tissue diseases.

[0056] In the present invention, specifically Figure 2 As shown, S101 is first executed to obtain a standardized spinal cord MR template 201 and a spinal cord anatomical image labeling atlas 202. First, the standardized spinal cord MR template 201 is obtained. Specifically, the standardized spinal cord MR template 201 is established based on adult MR spinal cord image data.

[0057] Specifically, the adult MR spinal cord image database is registered and homogenized in the same spatial system to establish a standardized spinal cord MR template 201. The images in the adult MR spinal cord image database are TIWI images, 3D, high resolution, and each axial voxel is ≤1mm*1mm*1mm.

[0058] Next, a spinal cord anatomical image labeling atlas 202 is obtained. Specifically, based on the standardized spinal cord MR template 201, a spinal cord anatomical image labeling atlas 202 is established.

[0059] More specifically, based on the standardized spinal cord MR template 201 , the key areas of each layer of the image are outlined, segmented and labeled by referring to the spinal cord anatomical atlas to establish a spinal cord anatomical image labeling atlas 202 .

[0060] The standardized spinal cord MR template 201 is positioned in a grid format, and each grid intersection is labeled with a corresponding spinal cord anatomical name, thereby obtaining the spinal cord anatomical image labeling atlas 202 .

[0061] Next, S102 is executed to obtain a spinal cord PET image 203 and a spinal cord MR image 204 of the target patient.

[0062] In a specific embodiment, in order to avoid temporal and spatial differences caused by different machines acquiring images, a PET / MR integrated machine is used to acquire the target patient's spinal cord PET image 203 and spinal cord MR image 204 .

[0063] Then, S103 is executed to fuse the spinal cord PET image 203 and the spinal cord MR image 204 to obtain a fused image 205 .

[0064] Specifically, the spinal cord PET image 203 and the spinal cord MR image 204 are fused by translation and rotation transformation using rigid body transformation technology to obtain a fused image 205 .

[0065] Among them, rigid body transformation technology specifically refers to a transformation composed of translation and rotation in a plane or space, which keeps the distance and angle between any two points unchanged and does not change the shape and size of the object.

[0066] Specifically, the rigid body transformation technology is used to obtain the fused image 205 .

[0067] Next, step S104 is executed to perform spatial standardization transformation on the spinal cord MR image 204 according to the standardized spinal cord MR template 201 to obtain transformation parameters.

[0068] Specifically, the spinal cord MR image 204 is aligned with the overall direction, position and scale of the standardized spinal cord MR template 201, and is converted by correcting the rotation, translation and scaling differences to obtain conversion parameters, which include positive rotation, translation and scaling differences.

[0069] When the spinal cord MR image 204 is converted to align with the standardized spinal cord MR template 201 , the spinal cord anatomical image labeling atlas 202 corresponding to the standardized MR template 201 can be converted in the reverse direction of the conversion to label the spinal cord MR image 204 with spinal cord anatomy.

[0070] Execute S105 to affine-project the spinal cord anatomical image labeling atlas 202 onto the spinal cord MR image 204 based on the conversion parameters, so as to finely label the spinal cord MR image 204 and obtain a labeling image 206 .

[0071] Specifically, the spinal cord anatomical image labeling atlas 202 is affine-projected onto the spinal cord MR image through inverse transformation according to the conversion parameters, so as to finely label the patient's spinal cord MR image 204 and obtain a labeled image 206 .

[0072] To label spinal cord anatomy on a spinal cord MR image, the spinal cord anatomy labeling atlas 202 must first be affine-transformed onto the spinal cord MR image using inverse transformation parameters. This spinal cord MR image 204 has high resolution and clearer labeling. The resulting labeled image 206 can already locate lesions in soft tissues and other areas. To further localize lesions based on tissue metabolic activity and molecular-level functional information, subsequent steps are required.

[0073] Execute S106 to locate the spinal cord lesion position on the PET image portion in the fused image based on the marked image 206 and the fused image 205 .

[0074] Specifically, based on the marked image 206 and the fused image 205 , a spinal cord anatomical mark 207 on the fused image 205 is obtained;

[0075] Based on the spinal cord anatomical marker 207 on the fused image 205 , the structure of the spinal cord is automatically identified at the voxel level, and the abnormal radioactive distribution area is analyzed on the spinal cord anatomical marker 207 on the fused image 205 , and the position of the spinal cord lesion is located in the PET image part of the fused image.

[0076] First, the labeled image 206 carries a spinal cord anatomical marker. However, for the spinal cord PET image, a corresponding marker is also required. At this time, the labeled image 206 is overlapped with the fused image 205. In this way, the spinal cord marker can also mark the spinal cord anatomical part of the spinal cord PET image in the fused image 205. Thus, the fused image 205 has a spinal cord anatomical marker. Finally, on the spinal cord anatomical marker 207 of the fused image 205, the abnormal radioactive distribution area is analyzed through automatic recognition at the voxel level, thereby obtaining the metabolic abnormality area and the molecular level functional abnormality area, thereby locating the spinal cord lesion position in the PET image part in the fused image. That is, for example, Figure 2 The image 208 (ie, the fused spinal cord PET image) is analyzed to obtain the location of the spinal cord lesion in the peripheral PET image portion.

[0077] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0078] The present invention provides a method for locating a spinal cord lesion, comprising: acquiring a standardized spinal cord MR template and a spinal cord anatomical image marking atlas; acquiring a spinal cord PET image and a spinal cord MR image of a target patient, wherein the spinal cord PET image and the spinal cord MR image are acquired based on a PET / MR integrated machine; fusing the spinal cord PET image and the spinal cord MR image to obtain a fused image; performing spatial standardization conversion on the spinal cord MR image according to the standardized MR template to obtain conversion parameters; based on the conversion parameters, affine-projecting the standardized spinal cord MR template and the spinal cord anatomical image marking atlas onto the patient's spinal cord PET image to finely mark the spinal cord PET image of the target patient to obtain a marked image; based on the marked image and the fused image, locating the position of the spinal cord lesion on the PET image portion of the fused image, and achieving precise positioning of the spinal cord lesion by precisely fusing the PET image and MR image of the target patient, thereby improving diagnostic efficiency and reducing the burden on clinicians.

[0079] Example 2

[0080] Based on the same inventive concept, the present invention also provides a spinal cord lesion positioning device, such as Figure 3 Shown, including:

[0081] The first acquisition module 301 is used to acquire a standardized spinal cord MR template and a spinal cord anatomical image labeling atlas;

[0082] A second acquisition module 302 is configured to acquire a spinal cord PET image and a spinal cord MR image of the patient, wherein the spinal cord PET image and the spinal cord MR image are acquired based on a PET / MR integrated machine;

[0083] A first obtaining module 303 is configured to fuse the spinal cord PET image and the spinal cord MR image to obtain a fused image;

[0084] The second obtaining module 304 is configured to perform spatial standardization conversion on the spinal cord MR image according to the standardized spinal cord MR template to obtain conversion parameters;

[0085] a third obtaining module 305 for affine-mapping the standardized spinal cord MR template and the spinal cord anatomical image labeling atlas onto the patient's spinal cord PET image based on the conversion parameters, so as to finely label the spinal cord MR image of the target patient and obtain a labeled image;

[0086] The positioning module 306 is configured to locate the spinal cord lesion on the PET image portion in the fused image based on the marked image and the fused image.

[0087] In an optional implementation, the first acquisition module 301 is configured to:

[0088] A standardized spinal cord MR template was established based on adult MR spinal cord imaging data.

[0089] In an optional implementation, the first acquisition module 301 is configured to:

[0090] Based on the standardized spinal cord MR template, a spinal cord anatomical image labeling atlas is established.

[0091] In an optional implementation, the first acquisition module 301 is specifically configured to:

[0092] Based on the standardized spinal cord MR template, the key areas of each layer of the image were outlined, segmented and labeled according to the spinal cord anatomical atlas to establish a spinal cord anatomical image labeling atlas.

[0093] In an optional implementation, the first obtaining module 303 is configured to:

[0094] The rigid body transformation technology is used to transform the spinal cord PET image and the spinal cord MR image through translation transformation and rotation transformation, so that the spinal cord PET image and the spinal cord MR image are fused to obtain a fused image.

[0095] In an optional embodiment, the second obtaining module 304 is configured to:

[0096] The spinal cord MR image is aligned with the overall direction, position and scale of the standardized spinal cord MR template, and is converted by correcting the rotation, translation and scaling differences to obtain conversion parameters, wherein the conversion parameters include the corrected rotation amount, translation amount and scaling difference amount.

[0097] In an optional implementation, the third obtaining module 305 is configured to:

[0098] The spinal cord anatomical image labeling atlas is affine-projected onto the spinal cord PET image through inverse transformation according to the conversion parameters, so as to finely label the patient's spinal cord MR image and obtain a labeled image.

[0099] In an optional implementation, the positioning module 306 is configured to:

[0100] Based on the marked image and the fused image, obtaining a spinal cord anatomical marker on the fused image;

[0101] Based on the spinal cord anatomical markers on the fused image, the structure of the spinal cord is automatically identified at the voxel level, and the abnormal area of ​​radioactivity distribution is analyzed on the spinal cord anatomical markers on the fused image, and the position of the spinal cord lesion is located in the PET image part of the fused image.

[0102] Example 3:

[0103] Based on the same inventive concept, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned spinal cord lesion localization method when executed by a processor.

[0104] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general-purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing this type of system. In addition, the present invention is not directed to any specific programming language. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0105] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0106] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed invention requires more features than those explicitly recited in each embodiment. Rather, as reflected in each embodiment, inventive aspects lie in fewer than all the features of the individual embodiments previously disclosed. Accordingly, the claims that follow the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the present invention.

[0107] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition may be divided into multiple submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed herein may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0108] Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in a specific embodiment, any one of the claimed embodiments may be used in any combination.

[0109] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the spinal cord lesion localization device or computer equipment according to an embodiment of the present invention. The present invention can also be implemented as a device or device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0110] It should be noted that the above embodiments illustrate rather than limit the invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A method for locating spinal cord lesions, characterized in that: include: Obtain standardized spinal cord MR templates and spinal cord anatomical imaging markers; Acquire a spinal cord PET image and a spinal cord MR image of a target patient, wherein the spinal cord PET image and the spinal cord MR image are acquired based on a PET / MR all-in-one machine; fusing the spinal cord PET image and the spinal cord MR image to obtain a fused image; Performing spatial standardization transformation on the spinal cord MR image according to the standardized spinal cord MR template to obtain transformation parameters; Based on the conversion parameters, the spinal cord anatomical image labeling atlas is affine-mapped onto the spinal cord MR image to finely label the spinal cord MR image of the target patient to obtain a labeled image; Based on the marked image and the fused image, the spinal cord lesion position is located on the PET image portion in the fused image.

2. The method according to claim 1, wherein Obtain a standardized spinal cord MR template, including: A standardized spinal cord MR template was established based on adult MR spinal cord imaging data.

3. The method according to claim 2, wherein Access a labeled atlas of spinal cord anatomy, including: Based on the standardized spinal cord MR template, a spinal cord anatomical image labeling atlas is established.

4. The method according to claim 3, wherein A spinal cord anatomical imaging labeling atlas is established based on the standardized spinal cord MR template, including: Based on the standardized spinal cord MR template, the key areas of each layer of the image were outlined, segmented and labeled according to the spinal cord anatomical atlas to establish a spinal cord anatomical image labeling atlas.

5. The method according to claim 1, wherein The spinal cord PET image and the spinal cord MR image are fused to obtain a fused image, including: The rigid body transformation technology is used to transform the spinal cord PET image and the spinal cord MR image through translation transformation and rotation transformation, so that the spinal cord PET image and the spinal cord MR image are fused to obtain a fused image.

6. The method according to claim 1, wherein The spinal cord MR image is spatially normalized and transformed according to the standardized spinal cord MR template to obtain transformation parameters, including: The spinal cord MR image is aligned with the overall direction, position and scale of the standardized spinal cord MR template, and is converted by correcting the rotation, translation and scaling differences to obtain conversion parameters, wherein the conversion parameters include the corrected rotation amount, translation amount and scaling difference amount.

7. The method according to claim 1, wherein Based on the conversion parameters, the spinal cord anatomical image labeling atlas is affine-mapped onto the spinal cord MR image to finely label the spinal cord MR image to obtain a labeled image, including: The spinal cord anatomical image labeling atlas is affine-projected onto the spinal cord PET image through inverse transformation according to the conversion parameters, so as to finely label the patient's spinal cord MR image and obtain a labeled image.

8. The method according to claim 1, wherein Based on the marked image and the fused image, the spinal cord lesion position is located on the PET image portion in the fused image, including: Based on the marked image and the fused image, obtaining a spinal cord anatomical marker on the fused image; Based on the spinal cord anatomical markers on the fused image, the structure of the spinal cord is automatically identified at the voxel level, and the abnormal area of ​​radioactivity distribution is analyzed on the spinal cord anatomical markers on the fused image, and the position of the spinal cord lesion is located in the PET image part of the fused image.

9. A spinal cord lesion localization device, characterized in that: include: The first acquisition module is used to obtain a standardized spinal cord MR template and a spinal cord anatomical image labeling atlas; A second acquisition module is used to acquire a spinal cord PET image and a spinal cord MR image of the patient, wherein the spinal cord PET image and the spinal cord MR image are acquired based on a PET / MR integrated machine; A first obtaining module is used to fuse the spinal cord PET image and the spinal cord MR image to obtain a fused image; a second obtaining module, configured to perform spatial standardization conversion on the spinal cord MR image according to the standardized spinal cord MR template to obtain conversion parameters; a third obtaining module, configured to affine-project the standardized spinal cord MR template and the spinal cord anatomical image labeling atlas onto the patient's spinal cord PET image based on the conversion parameters, so as to finely label the patient's spinal cord MR image and obtain a labeled image; A positioning module is used to locate the position of the spinal cord lesion on the PET image part in the fused image based on the marked image and the fused image.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images