Multi-mode scoliosis 3D image correction method and system based on three-dimensional malformation parameters
Through the multimodal scoliosis 3D image correction method based on three-dimensional deformity parameters, three-dimensional correction is performed using 3D image data, which solves the problems of brace treatment failure and surgical complications in the prior art, and improves the correction of scoliosis Effects and patient quality of life.
Patent Information
- Application Number
- CN202411241693.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-12
AI Technical Summary
Among the existing scoliosis correction techniques, brace treatment failure rate is high and surgical complications are frequent, which fails to effectively solve the complex three-dimensional deformity correction problem of scoliosis, resulting in long-term health damage and degradation of quality of life of patients.
Using multimodal scoliosis 3D image correction method based on three-dimensional deformity parameters, the 3D image data of the patient under different postures is obtained and input into the pre-trained correction model, and the correction data includes correction load, correction displacement and orthopedic force to achieve Three-dimensional correction to improve the efficacy.
This method can provide accurate and dynamic corrections to patients with different postures, improve the success rate of scoliosis treatment, reduce the surgical rate, maintain long-term correction effects, and reduce the risk of complications.
Smart Images

Figure CN118941752A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of scoliosis correction, and in particular to a multimodal scoliosis 3D image correction method based on three-dimensional deformity parameters, a multimodal scoliosis 3D image correction system, a computer device and a computer-readable storage medium. Background Art
[0002] Scoliosis, commonly known as scoliosis, is a complex three-dimensional deformity involving the coronal, sagittal and transverse planes of the spine. Scoliosis is a common disease that endangers the health of children and adolescents. Studies have shown that untreated scoliosis continues to progress in adulthood and leads to spinal degeneration, osteoarthritis, nerve compression, etc., which endangers the patient's physical health and seriously affects the patient's quality of life. At the same time, the severe appearance deformity will cause the patient to have an inferiority complex and trigger a series of family and social problems. From the perspective of clinical classification, idiopathic scoliosis is the type with the highest incidence, accounting for about 80% of all scoliosis. The specific cause of the disease is unknown. According to the age of onset, it can be divided into three categories: infantile type (0-3 years old); 2 juvenile type (4-10 years old); adolescent type (>10 years old to skeletal maturity). Among the above three types, the adolescent type is the most common, accounting for 3% of all musculoskeletal deformities in adolescents under 16 years old. The diagnosis of scoliosis should be made by an experienced spinal surgeon based on medical history, physical examination, spinal flexion test and necessary imaging examinations. In imaging, according to the definition of the Scoliosis Research Society (SRS): the lateral curvature angle (Cobb angle) is measured on the full-length X-ray of the spine taken in the anteroposterior (frontal) position in the standing X-ray, and a Cobb angle of >10° is diagnosed as scoliosis. In treatment, skeletally immature patients with scoliosis Cobb angles of 20° to 40° are still at risk of deformity progression, and conservative treatment with braces is used, but the failure rate is still as high as 28%. For patients with scoliosis Cobb angles of thoracic curvature >45°-50°, thoracolumbar curvature / lumbar curvature >40° accompanied by trunk imbalance and failure of conservative brace treatment, surgical treatment is the last choice. Existing scoliosis correction is generally performed through internal fixation. Although the technology is mature, there are still the following potential risks of surgical complications:
[0003] 1) After implantation of the internal fixation device, as the spine grows over time, fusion-related complications such as "crankshaft" phenomenon and "superposition" phenomenon may occur, and internal fixation failure and breakage may require secondary or even multiple surgical revisions;
[0004] 2) After the deformity is corrected by internal fixation and fusion, new spinal problems such as accelerated degeneration of adjacent segments and secondary osteoarthritis are prone to occur at the proximal and distal ends of the fusion, requiring surgical intervention.
[0005] Currently, no effective solutions have been proposed for the problems of brace treatment failure and surgery-related complications in related technologies. From the fundamental perspective of disease prevention and treatment, how to improve the success rate and efficacy of conservative brace treatment and reduce the surgery rate is still the key to treatment. Summary of the invention
[0006] The purpose of the present invention is to address the deficiencies in the prior art and to provide a multimodal scoliosis 3D image correction method based on three-dimensional deformity parameters, a multimodal scoliosis 3D image correction system, a computer device and a computer-readable storage medium to solve the problems of brace treatment failure and surgery-related complications existing in the related art.
[0007] To achieve the above object, the technical solution adopted by the present invention is:
[0008] In a first aspect, the present invention provides a multimodal scoliosis 3D imaging correction method based on three-dimensional deformity parameters, comprising:
[0009] Obtain 3D imaging data of the patient's scoliosis;
[0010] The scoliosis 3D image data is input into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data, wherein the correction data includes correction load, correction displacement, and correction force.
[0011] In some embodiments, obtaining 3D image data of scoliosis of a patient includes:
[0012] Acquire standing scoliosis 3D image data of the patient in a standing posture.
[0013] In some embodiments, obtaining 3D image data of scoliosis of a patient includes:
[0014] Obtain supine scoliosis 3D image data of the patient in a supine position.
[0015] In some embodiments, obtaining 3D image data of scoliosis of a patient includes:
[0016] Acquire 3D image data of sitting scoliosis of the patient in a sitting posture.
[0017] In some embodiments, obtaining 3D image data of scoliosis of a patient includes:
[0018] Obtaining the patient's frontal scoliosis imaging data;
[0019] Obtaining lateral scoliosis imaging data of the patient;
[0020] The frontal scoliosis image data and the lateral scoliosis image data are fused to obtain scoliosis 3D image data.
[0021] In some of the embodiments, after acquiring the scoliosis 3D image data of the patient, the method further includes:
[0022] Segmenting the scoliosis 3D image data to obtain a scoliosis image;
[0023] The scoliosis image is analyzed to obtain the scoliosis curve type, Cobb angle, and the number of scoliosis segments.
[0024] In some of the embodiments, it also includes:
[0025] Segmenting the scoliosis image to obtain vertebral images of several vertebrae;
[0026] Analyzing the vertebral image of each vertebra to obtain longitudinal axis data, coronal axis data, and sagittal axis data of each vertebra;
[0027] The longitudinal axis data, the coronal axis data, and the sagittal axis data of each vertebra are fused to obtain vertebral deformity data.
[0028] In some embodiments, inputting the scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data includes:
[0029] The standing scoliosis 3D image data is input into a pre-trained multimodal scoliosis 3D image correction model to obtain standing correction data.
[0030] In some embodiments, inputting the scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data includes:
[0031] The supine scoliosis 3D image data is input into a pre-trained multimodal scoliosis 3D image correction model to obtain supine correction data.
[0032] In some embodiments, inputting the scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data includes:
[0033] The sitting scoliosis 3D image data is input into a pre-trained multimodal scoliosis 3D image correction model to obtain the sitting correction data.
[0034] In a second aspect, the present invention provides a multimodal scoliosis 3D imaging correction system, comprising:
[0035] An acquisition unit, used for acquiring 3D image data of scoliosis of the patient;
[0036] An auxiliary computing unit is used to input the scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data, wherein the correction data includes correction load, correction displacement, and correction force.
[0037] In some embodiments, the acquiring unit includes:
[0038] The first acquisition module is used to acquire standing scoliosis 3D image data of a patient in a standing posture.
[0039] In some embodiments, the acquiring unit includes:
[0040] The second acquisition module is used to acquire supine scoliosis 3D image data of the patient in a supine position.
[0041] In some embodiments, the acquiring unit includes:
[0042] The third acquisition module is used to acquire the 3D image data of the sitting scoliosis of the patient in a sitting posture.
[0043] In some embodiments, the acquiring unit includes:
[0044] A fourth acquisition module is used to acquire frontal scoliosis image data of the patient;
[0045] A fifth acquisition module, used for acquiring lateral scoliosis image data of the patient;
[0046] A fusion module is used to fuse the frontal scoliosis image data and the lateral scoliosis image data to obtain scoliosis 3D image data.
[0047] In some of the embodiments, it also includes:
[0048] A first image segmentation unit, configured to segment the scoliosis 3D image data to obtain a scoliosis image;
[0049] The first image analysis unit is used to analyze the scoliosis image to obtain the scoliosis curve type, Cobb angle, and the number of scoliosis segments.
[0050] In some of the embodiments, it also includes:
[0051] A second image segmentation unit is used to segment the scoliosis image to obtain vertebral images of a plurality of vertebrae;
[0052] A second image analysis unit, configured to analyze the vertebral image of each vertebra to obtain longitudinal axis data, coronal axis data, and sagittal axis data of each vertebra;
[0053] The fusion unit is used to fuse the longitudinal axis data, the coronal axis data, and the sagittal axis data of each vertebra to obtain vertebral deformity data.
[0054] In some of the embodiments, the auxiliary computing unit includes:
[0055] The first auxiliary calculation module is used to input the standing scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain standing correction data.
[0056] In some of the embodiments, the auxiliary computing unit includes:
[0057] The second auxiliary calculation module is used to input the supine scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain supine correction data.
[0058] In some of the embodiments, the auxiliary computing unit includes:
[0059] The third auxiliary calculation module is used to input the sitting scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain sitting correction data.
[0060] In a third aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the multimodal scoliosis 3D imaging correction method as described in the first aspect is implemented.
[0061] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the multimodal scoliosis 3D imaging correction method as described in the first aspect.
[0062] The present invention adopts the above technical solution, and has the following technical effects compared with the prior art:
[0063] The present invention provides a multimodal scoliosis 3D image correction method, a multimodal scoliosis 3D image correction system, a computer device and a computer-readable storage medium. The scoliosis 3D image data can be used to obtain correction data for standing posture, supine posture and sitting posture, and correction can be performed on patients in different postures. The correction data is distributed in three dimensions, which is convenient for three-dimensional correction, maintains accurate dynamic correction, and improves the therapeutic effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] Figure 1 is a flow chart of a multimodal scoliosis 3D imaging correction method according to an embodiment of the present invention (I);
[0065] Figure 2 is a flow chart of a multimodal scoliosis 3D imaging correction method according to an embodiment of the present invention (II);
[0066] Figure 3 is a flow chart of a multimodal scoliosis 3D imaging correction method according to an embodiment of the present invention (III);
[0067] Figure 4 4 is a framework diagram of a multimodal scoliosis 3D imaging correction system according to an embodiment of the present invention.
[0068] The figures are marked as follows: 400, multimodal scoliosis 3D imaging correction system; 410, acquisition unit; 420, auxiliary computing unit; 430, first image segmentation unit; 440, first image analysis unit; 450, second image segmentation unit; 460, second image analysis unit; 470, fusion unit. DETAILED DESCRIPTION
[0069] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.
[0070] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.
[0071] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.
[0072] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or units (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships, for example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.
[0073] Example 1
[0074] This embodiment relates to the multimodal scoliosis 3D imaging correction method of the present invention.
[0075] Figure 1 FIG. 1 is a flow chart of a multi-modal scoliosis 3D imaging correction method according to an embodiment of the present invention (I). Figure 1 As shown, a multimodal scoliosis 3D imaging correction method based on three-dimensional deformity parameters includes:
[0076] Step S102, obtaining 3D image data of the patient's scoliosis;
[0077] Step S104: input the scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data, wherein the correction data includes correction load, correction displacement, and correction force.
[0078] Wherein, in step S102, obtaining the patient's scoliosis 3D image data includes:
[0079] Step S1021, acquiring standing scoliosis 3D image data of the patient in a standing posture;
[0080] Step S1022, obtaining supine scoliosis 3D image data of the patient in a supine position;
[0081] Step S1023: Acquire sitting scoliosis 3D image data of the patient in a sitting posture.
[0082] Among them, step S1021 to step S1023 are parallel steps, and there is no order of precedence. In addition, step S1021 to step S1023 are non-essential steps, that is, any one or more combinations of steps S1021 to step S1023 can be performed.
[0083] Wherein, in step S102, obtaining the patient's scoliosis 3D image data further includes:
[0084] Step S1024, obtaining the patient's frontal scoliosis image data;
[0085] Step S1025, obtaining the patient's lateral scoliosis image data;
[0086] Step S1026: Fusing the frontal scoliosis image data and the lateral scoliosis image data to obtain scoliosis 3D image data.
[0087] Among them, step S1024 to step S1026 are before step S1021 to step S1023. Specifically, taking the acquisition of the patient's standing scoliosis 3D image data as an example for explanation. Specifically, the acquisition of the patient's standing scoliosis 3D image data includes:
[0088] Acquire standing frontal scoliosis imaging data with the patient in a standing posture;
[0089] Acquire standing lateral scoliosis imaging data of the patient in a standing posture;
[0090] The standing frontal scoliosis image data and the standing lateral scoliosis image data are fused to obtain the standing scoliosis 3D image data.
[0091] Among them, the method for obtaining the supine scoliosis 3D image data and the sitting scoliosis 3D image data is the same as the method for obtaining the standing scoliosis 3D image data, which will not be repeated here.
[0092] Wherein, in step S104, the scoliosis 3D image data is input into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data, including:
[0093] Step S1041, inputting the standing scoliosis image data into a pre-trained multi-modal scoliosis 3D image correction model to obtain standing correction data;
[0094] Step S1042, inputting the supine scoliosis image data into a pre-trained multimodal scoliosis 3D image correction model to obtain supine correction data;
[0095] Step S1043: input the sitting scoliosis image data into a pre-trained multimodal scoliosis 3D image correction model to obtain sitting correction data.
[0096] Among them, step S1041 to step S1043 are parallel steps, and there is no order of precedence. In addition, step S1041 to step S1043 are non-essential steps, that is, any one or more combinations of steps S1041 to step S1043 can be performed.
[0097] Among them, step S1041 is executed after step S1021, step S1042 is executed after step S1022, and step S1043 is executed after step S1023.
[0098] Among them, in step S104, the correction load includes the correction force and the correction torque, the correction displacement includes the correction translation and the correction rotation, and the correction force includes the lateral correction force and the longitudinal correction force.
[0099] Furthermore, in step S104, the correction data includes left correction data, right correction data, front correction data, and back correction data. The left correction data refers to the correction data applied from the left side of the spine, the right correction data refers to the correction data applied from the right side of the spine, the front correction data refers to the correction data applied from the front side of the spine, and the back correction data refers to the correction data applied from the back side of the spine.
[0100] In addition, the left side correction data, the right side correction data, the front side correction data, and the back side correction data are in parallel, and any one or more combinations of the above data can be obtained. For example, only the left side correction data can be obtained, or the left side correction data and the right side correction data can be obtained, or the left side correction data, the right side correction data, the front side correction data, and the back side correction data can be obtained at the same time.
[0101] In addition, the left-side correction data, the right-side correction data, the front-side correction data, and the back-side correction data all include correction load, correction displacement, and correction force.
[0102] Furthermore, the correction data may be one or more. Specifically, the correction data is left correction data, and the left correction data is a plurality of data. The plurality of left correction data corresponds to a plurality of vertebrae of the spine, that is, the plurality of left correction data are distributed and arranged along the vertical direction; the plurality of left correction data may be the same or different, that is, specific adjustments may be made for different vertebrae.
[0103] Among them, the quantity and distribution of the right-side correction data, the front-side correction data, and the back-side correction data are the same as the quantity and distribution of the left-side correction data, and will not be repeated here.
[0104] In addition, different vertebrae have different corresponding correction data. For example, a vertebra may correspond to right correction data and left correction data, and its adjacent vertebra may correspond to front correction data and back correction data. That is, for the spine, its correction data is distributed in three dimensions.
[0105] In step S104, the multimodal scoliosis 3D image correction model is a deep neural network model, a self-organizing map model, etc.
[0106] Furthermore, the multimodal scoliosis 3D imaging correction method also includes:
[0107] Step S106: Generate a control instruction based on the correction data so that the multimodal scoliosis 3D imaging correction brace can correct the scoliosis patient.
[0108] Furthermore, the multimodal scoliosis 3D imaging correction method also includes:
[0109] Step S108, obtaining the patient's posture, wherein the posture includes standing posture, supine posture, and sitting posture;
[0110] Step S110, selecting correction data corresponding to the posture;
[0111] Step S112: Generate a control instruction based on the correction data so that the multimodal scoliosis 3D imaging correction brace can correct the scoliosis patient in a specific posture.
[0112] In step S108, obtaining the patient's posture includes:
[0113] Get acceleration data;
[0114] Calculated based on acceleration data to obtain the patient's posture.
[0115] Among them, acceleration data includes gravity angular velocity data, angular velocity data, etc.
[0116] Through steps S102 to S104, the correction data of standing posture, supine posture and sitting posture can be obtained using the scoliosis 3D image data, and correction can be performed on patients in different postures. The correction data is distributed in three dimensions, which is convenient for three-dimensional correction, maintaining accurate dynamic correction and improving therapeutic effect.
[0117] Figure 2 FIG. 2 is a flow chart of a multi-modal scoliosis 3D imaging correction method according to an embodiment of the present invention. Figure 2 As shown, after obtaining the patient's scoliosis 3D imaging data, it also includes:
[0118] Step S202, segmenting the scoliosis 3D image data to obtain a scoliosis image;
[0119] Step S204: Analyze the scoliosis image to obtain the scoliosis curve type, Cobb angle, and the number of scoliosis segments.
[0120] In step S202, the scoliosis image segmentation model is used to perform segmentation processing on the scoliosis 3D image data.
[0121] In step S204, the scoliosis curve type includes angular scoliosis and arcuate scoliosis.
[0122] In step S204, the angle ratio can be calculated by Cobb angle and the number of scoliosis spanning segments. Wherein, angle ratio=Cobb angle / number of scoliosis spanning segments. The purpose of calculating the angle ratio is to determine whether the scoliosis is obvious by the angle ratio.
[0123] Furthermore, after step S204, the method further includes:
[0124] Step S206, inputting the scoliosis 3D image data, scoliosis curve type, Cobb angle, and scoliosis spanning segments into the multimodal scoliosis 3D image correction model to obtain correction data.
[0125] Among them, step S206 is basically the same as step S104, and will not be repeated here.
[0126] Through steps S202 to S206, the correction data can be further optimized and the precision of the correction data can be improved by using the scoliosis curve type, Cobb angle, and the number of scoliosis segments.
[0127] Figure 3 FIG. 3 is a flow chart of a multi-modal scoliosis 3D imaging correction method according to an embodiment of the present invention. Figure 2As shown, after step S202, the following further includes:
[0128] Step S302, segmenting the scoliosis image to obtain vertebral images of several vertebrae;
[0129] Step S304, analyzing the vertebral image of each vertebra to obtain longitudinal axis data, coronal axis data, and sagittal axis data of each vertebra;
[0130] Step S306: fuse the longitudinal axis data, coronal axis data, and sagittal axis data of each vertebra to obtain vertebral deformity data.
[0131] In step S302, the vertebral segmentation model is used to perform segmentation processing on the scoliosis image.
[0132] In step S304 , the longitudinal axis data includes longitudinal axis displacement data and longitudinal axis load data. The longitudinal axis displacement data includes longitudinal axis translation data and longitudinal axis rotation data. The longitudinal axis load data includes longitudinal axis force data and longitudinal axis moment data.
[0133] In step S304, the coronary axis data includes coronary axis displacement data and coronary axis load data. The coronary axis displacement data includes coronary axis translation data and coronary axis rotation data. The coronary axis load data includes coronary axis force data and coronary axis moment data.
[0134] In step S304, the sagittal axis data includes sagittal axis displacement data and sagittal axis load data. The sagittal axis displacement data includes sagittal axis translation data and sagittal axis rotation data. The sagittal axis load data includes sagittal axis force data and sagittal axis moment data.
[0135] In step S306, the vertebral deformity data refers to axial compression of the vertebral body around the longitudinal axis, traction or rotation around the longitudinal axis, flexion and extension around the coronal axis, left-right translation around the coronal axis, left-right lateral bending around the sagittal axis, and anterior-posterior translation around the sagittal axis.
[0136] Furthermore, after step S306, the method further includes:
[0137] Step S308: input the scoliosis 3D image data and a plurality of vertebral deformity data into the multimodal scoliosis 3D image correction model to obtain correction data.
[0138] Among them, step S308 is basically the same as step S104, and will not be repeated here.
[0139] In addition, step S308 and step S206 can be combined, that is, the scoliosis 3D image data, scoliosis curve type, Cobb angle, number of scoliosis segments, and several vertebral deformity data are input into the multimodal scoliosis 3D image correction model to obtain correction data.
[0140] Through steps S302 to S308, the vertebral deformity data can be used to further optimize the correction data and improve the precision of the correction data.
[0141] In addition, the multimodal scoliosis 3D image correction method of the embodiment of the present application can be implemented by a computer device. The components of the computer device may include but are not limited to a processor and a memory storing computer program instructions.
[0142] In some embodiments, the processor 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.
[0143] In some embodiments, the memory may include a large capacity memory for data or instructions. By way of example and not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), 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 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory may be inside or outside a data processing device. In a specific embodiment, the memory is a non-volatile memory. In a specific embodiment, the memory includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable ProgrammableRead-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable ProgrammableRead-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.
[0144] The memory may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor.
[0145] The processor implements any one of the multimodal scoliosis 3D imaging correction methods in the above embodiments by reading and executing computer program instructions stored in the memory.
[0146] In some embodiments, the computer device may further include a communication interface and a bus, wherein the processor, the memory, and the communication interface are connected via the bus and communicate with each other.
[0147] The communication interface is used to realize the communication between each unit, device, unit and / or device in the embodiment of the present application. The communication interface can also realize data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.
[0148] The bus includes hardware, software or both, and couples the components of the computer device to each other. The bus includes but is not limited to at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.
[0149] The computer device can execute the multimodal scoliosis 3D image correction method in the embodiment of the present application.
[0150] In addition, in combination with the multimodal scoliosis 3D image correction method in the above embodiment, 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 multimodal scoliosis 3D image correction method in the above embodiment is implemented.
[0151] Example 2
[0152] This embodiment relates to the multimodal scoliosis 3D imaging correction system of the present invention.
[0153] Figure 4 is a framework diagram of a multi-modal scoliosis 3D imaging correction system according to an embodiment of the present invention. Figure 4 As shown, a multimodal scoliosis 3D image correction system 400 includes an acquisition unit 410 and an auxiliary calculation unit 420. The acquisition unit 410 is used to acquire the scoliosis 3D image data of the patient; the auxiliary calculation unit 420 is used to input the scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data, wherein the correction data includes correction load, correction displacement, and correction force.
[0154] Furthermore, the acquisition unit 410 includes a first acquisition module, a second acquisition module and a third acquisition module. The first acquisition module is used to acquire standing scoliosis image data of the patient in a standing posture; the second acquisition module is used to acquire supine scoliosis image data of the patient in a supine posture; and the third acquisition module is used to acquire sitting scoliosis image data of the patient in a sitting posture.
[0155] Furthermore, the acquisition unit 410 includes a fourth acquisition module, a fifth acquisition module and a fusion module. The fourth acquisition module is used to acquire the patient's frontal scoliosis image data; the fifth acquisition module is used to acquire the patient's lateral scoliosis image data; and the fusion module is used to fuse the frontal scoliosis image data and the lateral scoliosis image data to obtain scoliosis 3D image data.
[0156] Furthermore, the multimodal scoliosis 3D image correction system 400 also includes a first image segmentation unit 430 and a first image analysis unit 440. The first image segmentation unit 430 is used to segment the scoliosis 3D image data to obtain a scoliosis image; the first image analysis unit 440 is used to analyze the scoliosis image to obtain the scoliosis curve type, Cobb angle, and scoliosis span segment number.
[0157] Furthermore, the multimodal scoliosis 3D image correction system 400 also includes a second image segmentation unit 450, a second image analysis unit 460 and a fusion unit 470. The second image segmentation unit 450 is used to segment the scoliosis image to obtain vertebral images of several vertebrae; the second image analysis unit 460 is used to analyze the vertebral image of each vertebra to obtain longitudinal axis data, coronal axis data, and sagittal axis data of each vertebra; the fusion unit 470 is used to fuse the longitudinal axis data, coronal axis data, and sagittal axis data of each vertebra to obtain vertebral deformity data.
[0158] Furthermore, the auxiliary calculation unit 420 includes a first auxiliary calculation module, a second auxiliary calculation module and a third auxiliary calculation module. The first auxiliary calculation module is used to input the standing scoliosis image data into a pre-trained multimodal scoliosis 3D image correction model to obtain standing correction data; the second auxiliary calculation module is used to input the supine scoliosis image data into a pre-trained multimodal scoliosis 3D image correction model to obtain supine correction data; the third auxiliary calculation module is used to input the sitting scoliosis image data into a pre-trained multimodal scoliosis 3D image correction model to obtain sitting correction data.
[0159] The technical effects of this embodiment are basically the same as those of Embodiment 1 and will not be described in detail here.
[0160] Example 3
[0161] This embodiment relates to a specific embodiment of the present invention.
[0162] A multimodal scoliosis 3D imaging correction method, comprising:
[0163] Acquire standing frontal scoliosis imaging data with the patient in a standing posture;
[0164] Acquire standing lateral scoliosis imaging data of the patient in a standing posture;
[0165] fusing the standing frontal scoliosis image data and the standing lateral scoliosis image data to obtain the first scoliosis 3D image data;
[0166] Segmenting the first scoliosis 3D image data to obtain a first scoliosis image;
[0167] Analyze the first scoliosis image to obtain the first scoliosis curve type, the first Cobb angle, and the number of segments spanned by the first scoliosis;
[0168] performing segmentation processing on the first scoliosis image to obtain first vertebral images of a plurality of vertebrae;
[0169] Analyzing the first vertebral image of each vertebra to obtain first longitudinal axis data, first coronal axis data, and first sagittal axis data of each vertebra;
[0170] The first longitudinal axis data, the first coronal axis data, and the first sagittal axis data of each vertebra are fused to obtain the first vertebra deformity data;
[0171] Inputting the first scoliosis 3D image data, the first scoliosis curve type, the first Cobb angle, the number of first scoliosis segments, and a plurality of first vertebral deformity data into the multimodal scoliosis 3D image correction model to obtain the first correction data;
[0172] A first control instruction is generated according to the first correction data so that the multimodal scoliosis 3D imaging correction brace corrects the scoliosis patient in a standing posture.
[0173] The first correction data includes first left correction data, first right correction data, first front correction data, and first back correction data.
[0174] The first left-side correction data includes a first left-side correction load, a first left-side correction displacement, and a first left-side correction force.
[0175] The first right side correction data includes the first right side correction load, the first right side correction displacement, and the first right side correction force.
[0176] The first anterior correction data includes a first anterior correction load, a first anterior correction displacement, and a first anterior correction force.
[0177] The first posterior correction data includes a first posterior correction load, a first posterior correction displacement, and a first posterior correction force.
[0178] Example 4
[0179] This embodiment relates to a specific embodiment of the present invention.
[0180] A multimodal scoliosis 3D imaging correction method, comprising:
[0181] Obtain supine frontal scoliosis imaging data with the patient in a supine position;
[0182] Obtaining supine lateral scoliosis imaging data with the patient in a supine position;
[0183] fusing the supine frontal scoliosis image data and the supine lateral scoliosis image data to obtain the second scoliosis 3D image data;
[0184] Segmenting the second scoliosis 3D image data to obtain a second scoliosis image;
[0185] Analyze the second scoliosis image to obtain the second scoliosis curve type, the second Cobb angle, and the number of segments spanned by the second scoliosis;
[0186] performing segmentation processing on the second scoliosis image to obtain second vertebral images of a plurality of vertebrae;
[0187] Analyzing the second vertebral body image of each vertebral body to obtain second longitudinal axis data, second coronal axis data, and second sagittal axis data of each vertebral body;
[0188] The second longitudinal axis data, the second coronal axis data, and the second sagittal axis data of each vertebra are fused to obtain the second vertebra deformity data;
[0189] Inputting the second scoliosis 3D image data, the second scoliosis curve type, the second Cobb angle, the second scoliosis spanning segments, and a plurality of second vertebral deformity data into the multimodal scoliosis 3D image correction model to obtain second correction data;
[0190] A second control instruction is generated according to the second correction data so that the multimodal scoliosis 3D imaging correction brace corrects the scoliosis patient in the supine position.
[0191] The second correction data includes second left correction data, second right correction data, second front correction data, and second back correction data.
[0192] The second left-side correction data includes the second left-side correction load, the second left-side correction displacement, and the second left-side correction force.
[0193] The second right side correction data includes the second right side correction load, the second right side correction displacement, and the second right side correction force.
[0194] The second anterior correction data includes a second anterior correction load, a second anterior correction displacement, and a second anterior correction force.
[0195] The second posterior correction data includes a second posterior correction load, a second posterior correction displacement, and a second posterior correction force.
[0196] Example 5
[0197] This embodiment relates to a specific embodiment of the present invention.
[0198] A multimodal scoliosis 3D imaging correction method, comprising:
[0199] Acquire sitting frontal scoliosis imaging data with the patient in a sitting position;
[0200] Acquire sitting lateral scoliosis imaging data of the patient in a sitting posture;
[0201] fusing the sitting frontal scoliosis image data and the sitting lateral scoliosis image data to obtain the third scoliosis 3D image data;
[0202] Segmenting the third scoliosis 3D image data to obtain a third scoliosis image;
[0203] Analyze the third scoliosis image to obtain the third scoliosis curve type, the third Cobb angle, and the number of segments spanned by the third scoliosis;
[0204] Segmenting the third scoliosis image to obtain third vertebral images of a plurality of vertebrae;
[0205] Analyze the third vertebral image of each vertebra to obtain the third longitudinal axis data, the third coronal axis data, and the third sagittal axis data of each vertebra;
[0206] The third longitudinal axis data, the third coronal axis data, and the third sagittal axis data of each vertebra are fused to obtain the third vertebra deformity data;
[0207] Inputting the third scoliosis 3D image data, the third scoliosis curve type, the third Cobb angle, the third scoliosis spanning segments, and a plurality of third vertebral deformity data into the multimodal scoliosis 3D image correction model to obtain third correction data;
[0208] A third control instruction is generated according to the third correction data so that the multimodal scoliosis 3D imaging correction brace corrects the scoliosis patient in a sitting posture.
[0209] The third correction data includes third left correction data, third right correction data, third front correction data, and third back correction data.
[0210] Among them, the third left-side correction data includes the third left-side correction load, the third left-side correction displacement, and the third left-side correction force.
[0211] Among them, the third right side correction data includes the third right side correction load, the third right side correction displacement, and the third right side correction force.
[0212] The third anterior correction data includes a third anterior correction load, a third anterior correction displacement, and a third anterior correction force.
[0213] Among them, the third posterior correction data includes a third posterior correction load, a third posterior correction displacement, and a third posterior correction force.
[0214] Example 6
[0215] This embodiment relates to a specific embodiment of the present invention.
[0216] A multimodal scoliosis 3D imaging correction method, comprising:
[0217] Acquire the patient's frontal scoliosis image data, wherein the frontal scoliosis image data includes standing frontal scoliosis image data, supine frontal scoliosis image data, and sitting frontal scoliosis image data;
[0218] Acquiring lateral scoliosis image data of the patient, wherein the lateral scoliosis image data includes standing lateral scoliosis image data, supine lateral scoliosis image data, and sitting lateral scoliosis image data;
[0219] fusing the frontal scoliosis image data and the lateral scoliosis image data to obtain scoliosis 3D image data, wherein the scoliosis 3D image data includes first scoliosis 3D image data, second scoliosis 3D image data, and third scoliosis 3D image data;
[0220] Segmenting the scoliosis 3D image data to obtain scoliosis images, wherein the scoliosis images include a first scoliosis image, a second scoliosis image, and a third scoliosis image;
[0221] Analyze scoliosis images to obtain the scoliosis curve type, Cobb angle, and the number of scoliosis segments;
[0222] Segmenting the scoliosis image to obtain vertebral images of a plurality of vertebrae, wherein the vertebral images include a first vertebral image, a second vertebral image, and a third vertebral image;
[0223] Analyze the vertebral images of each vertebra to obtain the longitudinal axis data, coronal axis data, and sagittal axis data of each vertebra;
[0224] fusing the longitudinal axis data, the coronal axis data, and the sagittal axis data of each vertebra to obtain vertebral deformity data, wherein the vertebral deformity data includes the first vertebral deformity data, the second vertebral deformity data, and the third vertebral deformity data;
[0225] Inputting scoliosis 3D image data, scoliosis curve type, Cobb angle, number of scoliosis spanning segments, and several vertebral deformity data into a multimodal scoliosis 3D image correction model to obtain correction data, wherein the correction data includes first correction data, second correction data, and third correction data;
[0226] Get acceleration data;
[0227] Calculate according to the acceleration data to obtain the patient's posture, wherein the posture includes standing posture, supine posture, and sitting posture;
[0228] According to the posture, select the correction data corresponding to the posture;
[0229] Based on the correction data, control instructions are generated to enable the multimodal scoliosis 3D imaging correction brace to correct scoliosis patients in a specific posture, wherein the control instructions include a first control instruction, a second control instruction, and a third control instruction.
[0230] Furthermore, the multimodal scoliosis 3D imaging correction method also includes:
[0231] Determine if the patient's posture has changed;
[0232] When the patient's posture changes, switching is performed among the first control command, the second control command, and the third control command.
[0233] The above description is only a preferred embodiment of the present invention, and does not limit the implementation mode and protection scope of the present invention. For those skilled in the art, it should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the description and illustrations of the present invention should be included in the protection scope of the present invention.
Claims
1. A multimodal scoliosis 3D imaging correction method based on three-dimensional deformity parameters, characterized in that: include: Obtain 3D imaging data of the patient's scoliosis; The scoliosis 3D image data is input into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data, wherein the correction data includes correction load, correction displacement, and correction force.
2. The multimodal scoliosis 3D imaging correction method according to claim 1, characterized in that: Acquiring 3D imaging data of the patient's scoliosis includes: Acquire standing scoliosis 3D image data of the patient in a standing posture; and / or Acquiring supine scoliosis 3D image data with the patient in a supine position; and / or Acquire 3D image data of sitting scoliosis of the patient in a sitting posture.
3. The multimodal scoliosis 3D imaging correction method according to claim 1 or 2, characterized in that: Acquiring 3D imaging data of the patient's scoliosis includes: Obtaining the patient's frontal scoliosis imaging data; Obtaining lateral scoliosis imaging data of the patient; The frontal scoliosis image data and the lateral scoliosis image data are fused to obtain scoliosis 3D image data.
4. The multimodal scoliosis 3D imaging correction method according to claim 1, characterized in that: After obtaining the patient's scoliosis 3D imaging data, it also includes: Segmenting the scoliosis 3D image data to obtain a scoliosis image; The scoliosis image is analyzed to obtain the scoliosis curve type, Cobb angle, and the number of scoliosis segments.
5. The multimodal scoliosis 3D imaging correction method according to claim 4, characterized in that: Also includes: Segmenting the scoliosis image to obtain vertebral images of several vertebrae; Analyzing the vertebral image of each vertebra to obtain longitudinal axis data, coronal axis data, and sagittal axis data of each vertebra; The longitudinal axis data, the coronal axis data, and the sagittal axis data of each vertebra are fused to obtain vertebral deformity data.
6. The multimodal scoliosis 3D imaging correction method according to claim 1, characterized in that: Inputting the scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data includes: Inputting the standing scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain standing correction data; and / or Inputting the supine scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain supine correction data; and / or The sitting scoliosis 3D image data is input into a pre-trained multimodal scoliosis 3D image correction model to obtain the sitting correction data.
7. A multimodal scoliosis 3D imaging correction system, characterized in that: include: An acquisition unit, used for acquiring 3D image data of scoliosis of the patient; An auxiliary computing unit is used to input the scoliosis 3D image data into a pre-trained multimodal scoliosis 3D image correction model to obtain correction data, wherein the correction data includes correction load, correction displacement, and correction force.
8. The multimodal scoliosis 3D image correction system according to claim 7, characterized in that: Also includes: A first image segmentation unit, configured to segment the scoliosis 3D image data to obtain a scoliosis image; The first image analysis unit is used to analyze the scoliosis image to obtain the scoliosis curve type, Cobb angle, and the number of scoliosis segments.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the multimodal scoliosis 3D imaging correction method as described in any one of claims 1 to 6 is implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the multimodal scoliosis 3D imaging correction method as described in any one of claims 1 to 6 is implemented.
