Spinal malformation correction preoperative planning method, device and equipment based on deep learning

Abstract

The invention provides a spinal malformation correction preoperative planning method, device and equipment based on deep learning and a computer readable storage medium. The method comprises the following steps: acquiring identity information of a patient, a spine CT image, a spine Cobb angle, a spine bone mineral density and a spine offset distance; wherein the identity information of the patient at least comprises gender and age; based on the identity information of the patient, the spine Cobb angle, the spine bone mineral density and the spine offset distance, a high-quality case which is most matched with the patient is screened out through big data; and inputting the high-quality case which is most matched with the patient, the spine CT image of the patient and the spine bone mineral density into a preset spine malformation correction preoperative planning model, and outputting a preoperative planning result. According to the embodiment of the invention, the preoperative planning of spinal malformation correction can be more accurately carried out.

Description

Technical Field

[0001] The present application belongs to the field of preoperative planning for spinal deformity correction, and in particular, relates to a preoperative planning method, device, equipment and computer-readable storage medium for spinal deformity correction based on deep learning. Background Art

[0002] At present, the preoperative planning of spinal deformity correction in the related technology is: calculating the feature point heat map of the pedicle screw channel and the CBCT spine image segmentation map based on the CBCT spine image through the segmentation planning neural network module; and using the feature extraction module to calculate the feature value of the pedicle screw channel based on the feature point heat map and the CBCT spine image segmentation map, wherein the feature value includes the entry point, target point, length and diameter of the pedicle screw channel, and the feature point heat map includes the midpoint heat map and the entry point heat map.

[0003] However, the accuracy of preoperative planning for spinal deformity correction based solely on CBCT spine images is not high enough.

[0004] Therefore, how to more accurately perform preoperative planning for spinal deformity correction is a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] The embodiments of the present application provide a method, device, equipment and computer-readable storage medium for preoperative planning of spinal deformity correction based on deep learning, which can more accurately perform preoperative planning of spinal deformity correction.

[0006] In a first aspect, an embodiment of the present application provides a method for preoperative planning of spinal deformity correction based on deep learning, comprising:

[0007] Obtaining the patient's identity information, spinal CT images, spinal Cobb angle, spinal bone density, and spinal offset distance; wherein the patient's identity information at least includes gender and age;

[0008] Based on the patient's identity information, spinal Cobb angle, spinal bone density and spinal offset distance, big data screens out high-quality cases that best match the patient; among them, the high-quality cases record the patient's identity information, preoperative spinal Cobb angle, spinal bone density, preoperative spinal offset distance, postoperative spinal Cobb angle, postoperative spinal offset distance, and the screw position, screw direction and screw model for surgical screw placement;

[0009] The best-matched high-quality case, the patient's spinal CT image, and spinal bone density are input into the preset preoperative planning model for spinal deformity correction, and the preoperative planning results are output.

[0010] Optionally, obtain the patient's identity information, spinal CT images, spinal Cobb angle, spinal bone density, and spinal offset distance, including:

[0011] Obtain the patient's identity information through the patient's medical card or ID card;

[0012] Scanning the patient's spinal region to obtain a spinal CT image of the patient;

[0013] Based on the patient's spinal CT image, the patient's spinal Cobb angle, spinal bone density and spinal offset distance were determined.

[0014] Optionally, based on the patient's spinal CT image, the patient's spinal bone density and spinal offset distance are determined, including:

[0015] Input the patient's spinal CT image into the preset bone density measurement and osteoporosis diagnosis model, and output the bone density value and osteoporosis diagnosis result;

[0016] Among them, the osteoporosis diagnosis results include: normal, osteopenia, and osteoporosis;

[0017] The bone density measurement and osteoporosis diagnosis model is obtained through model training, which includes multiple DenseNet networks. Each DenseNet network consists of multiple dense blocks. The input of each dense block is connected to the output of all previous dense blocks to form a dense connection to promote information and gradient flow and reduce gradient disappearance.

[0018] By analyzing the spinal CT images, the central axis of the spine was extracted as a reference line;

[0019] Based on the extracted spinal axis, the lateral displacement of each vertebra relative to the central axis was measured by calculating the offset distance of each spinal segment.

[0020] Optionally, based on the patient's identity information, spinal Cobb angle, spinal bone density, and spinal offset distance, big data screens out high-quality cases that best match the patient, including:

[0021] Based on the patient's identity information, spinal Cobb angle, spinal bone density and spinal offset distance, a multidimensional feature vector of the patient is constructed;

[0022] Similarity calculation is performed in the medical database based on the multidimensional feature vector of the patient;

[0023] Based on the similarity calculation results, the high-quality cases that best match the patient are determined.

[0024] Optionally, based on the similarity calculation results, the best quality cases that are determined to be the best match for the patient include:

[0025] According to the similarity calculation results, the cases with the highest similarity to the current patient are screened out;

[0026] A secondary screening is conducted based on the treatment effect, rehabilitation progress, and complication occurrence of the N cases with the highest similarity to the current patient, and the case with the best treatment effect and the best recovery status is selected as the high-quality case that best matches the patient.

[0027] Optionally, the best matching high-quality case, the patient's spinal CT image, and spinal bone density are input into the preset spinal deformity correction preoperative planning model to output preoperative planning results, including:

[0028] Integrate the best-matched high-quality medical records, the patient's spinal CT images, and spinal bone density into a multi-dimensional input vector;

[0029] Constructing a neural network model, wherein the neural network includes a convolution layer, a pooling layer, a copy layer of the convolution layer, and a feature layer corresponding to the copy layer;

[0030] The corresponding feature layer is obtained by upsampling and adding the copy layer and the corresponding layer in the convolution layer. A large feature layer is obtained by superimposing the feature layers, and the preoperative planning result is output.

[0031] Optionally, the preoperative planning results include: screw position, screw direction, and screw type for surgical screw placement;

[0032] Among them, the screw model includes screw type, screw diameter and screw length, all of which correspond to the patient's spinal bone density.

[0033] In a second aspect, an embodiment of the present application provides a preoperative planning device for spinal deformity correction based on deep learning, comprising:

[0034] An information acquisition module is used to acquire the patient's identity information, spinal CT images, spinal Cobb angle, spinal bone density, and spinal offset distance; wherein the patient's identity information includes at least gender and age;

[0035] The high-quality case screening module is used to screen out the best-matched high-quality cases for patients based on the patient's identity information, spinal Cobb angle, spinal bone density and spinal offset distance. The high-quality cases include the patient's identity information, preoperative spinal Cobb angle, spinal bone density, preoperative spinal offset distance, postoperative spinal Cobb angle, postoperative spinal offset distance, and the screw position, screw direction and screw model for surgical screw placement.

[0036] The preoperative planning module is used to input the best-matched high-quality case for the patient, the patient's spinal CT image, and spinal bone density into the preset preoperative planning model for spinal deformity correction, and output the preoperative planning results.

[0037] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;

[0038] When the processor executes the computer program instructions, a deep learning-based preoperative planning method for spinal deformity correction is implemented.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement a deep learning-based preoperative planning method for spinal deformity correction.

[0040] The deep learning-based preoperative planning method, device, equipment and computer-readable storage medium for spinal deformity correction in the embodiments of the present application can perform preoperative planning for spinal deformity correction more accurately.

[0041] The deep learning-based preoperative planning method for spinal deformity correction includes:

[0042] Obtaining the patient's identity information, spinal CT images, spinal Cobb angle, spinal bone density, and spinal offset distance; wherein the patient's identity information at least includes gender and age;

[0043] Based on the patient's identity information, spinal Cobb angle, spinal bone density and spinal offset distance, big data screens out high-quality cases that best match the patient; among them, the high-quality cases record the patient's identity information, preoperative spinal Cobb angle, spinal bone density, preoperative spinal offset distance, postoperative spinal Cobb angle, postoperative spinal offset distance, and the screw position, screw direction and screw model for surgical screw placement;

[0044] The best-matched high-quality case, the patient's spinal CT image, and spinal bone density are input into the preset preoperative planning model for spinal deformity correction, and the preoperative planning results are output. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a flowchart of a preoperative planning method for spinal deformity correction based on deep learning provided by an embodiment of the present application;

[0047] Figure 2 It is a flowchart of a method for bone density measurement and osteoporosis diagnosis provided by an embodiment of the present application;

[0048] Figure 3 It is a structural schematic diagram of a preoperative planning model for spinal deformity correction provided by an embodiment of the present application;

[0049] Figure 4 It is a structural schematic diagram of a preoperative planning device for spinal deformity correction based on deep learning provided by an embodiment of the present application;

[0050] Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0051] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0052] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0053] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, equipment and computer-readable storage medium for preoperative planning of spinal deformity correction based on deep learning. The following first introduces the preoperative planning method of spinal deformity correction based on deep learning provided by the embodiments of the present application.

[0054] Figure 1 FIG. 1 is a flow chart of a method for preoperative planning of spinal deformity correction based on deep learning provided by an embodiment of the present application. Figure 1As shown, the deep learning-based preoperative planning method for spinal deformity correction includes:

[0055] S101, obtaining the patient's identity information, spinal CT image, spinal Cobb angle, spinal bone density, and spinal offset distance; wherein the patient's identity information includes at least gender and age;

[0056] S102. Based on the patient's identity information, spinal Cobb angle, spinal bone density, and spinal offset distance, the big data screens out the best quality cases that match the patient; wherein the quality cases record the patient's identity information, preoperative spinal Cobb angle, spinal bone density, preoperative spinal offset distance, postoperative spinal Cobb angle, postoperative spinal offset distance, and the screw position, screw direction, and screw model of the surgical screw placement;

[0057] S103, inputting the best-matched high-quality case for the patient, the patient's spinal CT image, and spinal bone density into a preset preoperative planning model for spinal deformity correction, and outputting the preoperative planning results.

[0058] In one embodiment, obtaining the patient's identity information, spinal CT image, spinal Cobb angle, spinal bone density, and spinal offset distance includes:

[0059] Obtain the patient's identity information through the patient's medical card or ID card;

[0060] Scanning the patient's spinal region to obtain a spinal CT image of the patient;

[0061] Based on the patient's spinal CT image, the patient's spinal Cobb angle, spinal bone density and spinal offset distance were determined.

[0062] Figure 2 : is a flowchart of a bone density measurement and osteoporosis diagnosis method provided by an embodiment of the present application. In one embodiment, based on the patient's spine CT image, the patient's spine bone density and spine offset distance are determined, including:

[0063] Input the patient's spinal CT image into the preset bone density measurement and osteoporosis diagnosis model, and output the bone density value and osteoporosis diagnosis result;

[0064] Among them, the osteoporosis diagnosis results include: normal, osteopenia, and osteoporosis;

[0065] The bone density measurement and osteoporosis diagnosis model is obtained through model training, which includes multiple DenseNet networks. Each DenseNet network consists of multiple dense blocks. The input of each dense block is connected to the output of all previous dense blocks to form a dense connection to promote information and gradient flow and reduce gradient disappearance.

[0066] By analyzing the spinal CT images, the central axis of the spine was extracted as a reference line;

[0067] Based on the extracted spinal axis, the lateral displacement of each vertebra relative to the central axis was measured by calculating the offset distance of each spinal segment.

[0068] In one embodiment, based on the patient's identity information, spinal Cobb angle, spinal bone density, and spinal offset distance, big data screens out high-quality cases that best match the patient, including:

[0069] Based on the patient's identity information, spinal Cobb angle, spinal bone density and spinal offset distance, a multidimensional feature vector of the patient is constructed;

[0070] Similarity calculation is performed in the medical database based on the multidimensional feature vector of the patient;

[0071] Based on the similarity calculation results, the high-quality cases that best match the patient are determined.

[0072] In one embodiment, based on the similarity calculation result, the high-quality case that is determined to be the most matching with the patient includes:

[0073] According to the similarity calculation results, the cases with the highest similarity to the current patient are screened out;

[0074] A secondary screening is conducted based on the treatment effect, rehabilitation progress, and complication occurrence of the N cases with the highest similarity to the current patient, and the case with the best treatment effect and the best recovery status is selected as the high-quality case that best matches the patient.

[0075] Figure 3 It is a structural schematic diagram of a preoperative planning model for spinal deformity correction provided by an embodiment of the present application. In one embodiment, the best matching high-quality case for the patient, the patient's spinal CT image, and spinal bone density are input into a preset preoperative planning model for spinal deformity correction, and the preoperative planning results are output, including:

[0076] Integrate the best-matched high-quality medical records, the patient's spinal CT images, and spinal bone density into a multi-dimensional input vector;

[0077] Constructing a neural network model, wherein the neural network includes a convolution layer, a pooling layer, a copy layer of the convolution layer, and a feature layer corresponding to the copy layer;

[0078] The corresponding feature layer is obtained by upsampling and adding the copy layer and the corresponding layer in the convolution layer. A large feature layer is obtained by superimposing the feature layers, and the preoperative planning result is output.

[0079] In one embodiment, the preoperative planning results include: the screw position, screw direction and screw type of the surgical screw placement;

[0080] Among them, the screw model includes screw type, screw diameter and screw length, all of which correspond to the patient's spinal bone density.

[0081] Figure 4 It is a structural schematic diagram of a preoperative planning device for spinal deformity correction based on deep learning provided by an embodiment of the present application;

[0082] The deep learning-based preoperative planning device for spinal deformity correction includes:

[0083] The information acquisition module 401 is used to acquire the patient's identity information, spinal CT image, spinal Cobb angle, spinal bone density and spinal offset distance; wherein the patient's identity information at least includes gender and age;

[0084] The high-quality case screening module 402 is used to screen out the high-quality cases that best match the patient based on the patient's identity information, spinal Cobb angle, spinal bone density and spinal offset distance, and the high-quality cases record the patient's identity information, preoperative spinal Cobb angle, spinal bone density, preoperative spinal offset distance, postoperative spinal Cobb angle, postoperative spinal offset distance, and the screw position, screw direction and screw model of the surgical screw placement;

[0085] The preoperative planning module 403 is used to input the best-matched high-quality case for the patient, the patient's spinal CT image, and spinal bone density into a preset preoperative planning model for spinal deformity correction, and output the preoperative planning results.

[0086] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown.

[0087] The electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0088] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0089] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 502 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 502 may be inside or outside the electronic device. In a particular embodiment, the memory 502 may be a non-volatile solid-state memory.

[0090] In one embodiment, the memory 502 may be a read-only memory (ROM). In one embodiment, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0091] The processor 501 reads and executes computer program instructions stored in the memory 502 to implement any one of the deep learning-based preoperative planning methods for spinal deformity correction in the above-mentioned embodiments.

[0092] In one example, the electronic device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0093] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0094] Bus 510 includes hardware, software or both, and the parts of electronic equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0095] In addition, in combination with the deep learning-based preoperative planning method for spinal deformity correction in the above embodiments, the present application embodiment can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any of the deep learning-based preoperative planning methods for spinal deformity correction in the above embodiments is implemented.

[0096] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0097] The functional modules shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0098] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0099] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0100] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for preoperative planning of spinal deformity correction based on deep learning, characterized in that: include: Obtaining the patient's identity information, spinal CT images, spinal Cobb angle, spinal bone density, and spinal offset distance; wherein the patient's identity information at least includes gender and age; Based on the patient's identity information, spinal Cobb angle, spinal bone density and spinal offset distance, big data screens out high-quality cases that best match the patient; among them, the high-quality cases record the patient's identity information, preoperative spinal Cobb angle, spinal bone density, preoperative spinal offset distance, postoperative spinal Cobb angle, postoperative spinal offset distance, and the screw position, screw direction and screw model for surgical screw placement; The best-matched high-quality case, the patient's spinal CT image, and spinal bone density are input into the preset preoperative planning model for spinal deformity correction, and the preoperative planning results are output.

2. The method for preoperative planning of spinal deformity correction based on deep learning according to claim 1, characterized in that: Obtain the patient's identity information, spinal CT images, spinal Cobb angle, spinal bone density, and spinal offset distance, including: Obtain the patient's identity information through the patient's medical card or ID card; Scanning the patient's spinal region to obtain a spinal CT image of the patient; Based on the patient's spinal CT image, the patient's spinal Cobb angle, spinal bone density and spinal offset distance were determined.

3. The method for preoperative planning of spinal deformity correction based on deep learning according to claim 2, characterized in that: Based on the patient's spinal CT image, determine the patient's spinal bone density and spinal offset distance, including: Input the patient's spinal CT image into the preset bone density measurement and osteoporosis diagnosis model, and output the bone density value and osteoporosis diagnosis result; Among them, the osteoporosis diagnosis results include: normal, osteopenia, and osteoporosis; The bone density measurement and osteoporosis diagnosis model is obtained through model training, which includes multiple DenseNet networks. Each DenseNet network consists of multiple dense blocks. The input of each dense block is connected to the output of all previous dense blocks to form a dense connection to promote information and gradient flow and reduce gradient disappearance. By analyzing the spinal CT images, the central axis of the spine was extracted as a reference line; Based on the extracted spinal axis, the lateral displacement of each vertebra relative to the central axis was measured by calculating the offset distance of each spinal segment.

4. The method for preoperative planning of spinal deformity correction based on deep learning according to claim 1, characterized in that: Based on the patient's identity information, spinal Cobb angle, spinal bone density, and spinal offset distance, big data screens out high-quality cases that best match the patient, including: Construct a multidimensional feature vector of the patient based on the patient's identity information, spinal Cobb angle, spinal bone density, and spinal offset distance; Similarity calculation is performed in the medical database based on the multidimensional feature vector of the patient; Based on the similarity calculation results, the high-quality case that best matches the patient is determined.

5. The method for preoperative planning of spinal deformity correction based on deep learning according to claim 4, characterized in that: Based on the similarity calculation results, the best quality cases that match the patient are identified, including: According to the similarity calculation results, the cases with the highest similarity to the current patient are screened out; A secondary screening is conducted based on the treatment effect, rehabilitation progress, and complication occurrence of the N cases with the highest similarity to the current patient, and the case with the best treatment effect and the best recovery status is selected as the high-quality case that best matches the patient.

6. The method for preoperative planning of spinal deformity correction based on deep learning according to claim 1, characterized in that: The best matching case for the patient, the patient's spinal CT image, and spinal bone density are input into the preset spinal deformity correction preoperative planning model to output the preoperative planning results, including: Integrate the best matching high-quality medical records, the patient's spinal CT images, and spinal bone density into a multi-dimensional input vector; Constructing a neural network model, wherein the neural network includes a convolution layer, a pooling layer, a copy layer of the convolution layer, and a feature layer corresponding to the copy layer; The corresponding feature layer is obtained by upsampling and adding the copy layer and the corresponding layer in the convolution layer. A large feature layer is obtained by superimposing the feature layers, and the preoperative planning result is output.

7. The deep learning-based preoperative planning method for spinal deformity correction according to claim 6, characterized in that: Preoperative planning results include: surgical screw placement, screw direction, and screw type; Among them, the screw model includes screw type, screw diameter and screw length, all of which correspond to the patient's spinal bone density.

8. A preoperative planning device for spinal deformity correction based on deep learning, characterized in that: The device comprises: An information acquisition module is used to acquire the patient's identity information, spinal CT images, spinal Cobb angle, spinal bone density, and spinal offset distance; wherein the patient's identity information includes at least gender and age; The high-quality case screening module is used to screen out the best-matched high-quality cases for patients based on the patient's identity information, spinal Cobb angle, spinal bone density and spinal offset distance. The high-quality cases include the patient's identity information, preoperative spinal Cobb angle, spinal bone density, preoperative spinal offset distance, postoperative spinal Cobb angle, postoperative spinal offset distance, and the screw position, screw direction and screw model for surgical screw placement. The preoperative planning module is used to input the best-matched high-quality case for the patient, the patient's spinal CT image, and spinal bone density into the preset preoperative planning model for spinal deformity correction, and output the preoperative planning results.

9. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the deep learning-based preoperative planning method for spinal deformity correction as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the deep learning-based preoperative planning method for spinal deformity correction as described in any one of claims 1 to 7.

Images