A Method for Spinal Compression Fracture Healing Planning Based on Multimodal 3D Medical Images

Abstract

This application provides a method, system, device, and computer-readable storage medium for planning the healing of spinal compression fractures based on multimodal three-dimensional medical images. The method includes: acquiring spinal CT and MR images of the patient; identifying and segmenting the spinal CT and MR images to obtain CT and MR images of the fractured vertebral body at the site of the compression fracture; inputting the CT and MR images of the fractured vertebral body into a preset bone cement anti-leakage planning model to output a bone cement injection anti-leakage planning scheme; wherein the bone cement injection anti-leakage planning scheme includes at least: the viscosity of the bone cement, the injection volume, the injection location, the injection timing, and the injection rate. According to the embodiments of this application, bone cement injection anti-leakage planning can be performed quickly and accurately.

Description

Technical Field

[0001] This application belongs to the field of bone cement injection leakage prevention, and particularly relates to a method, system, device and computer-readable storage medium for spinal compression fracture healing planning based on multimodal three-dimensional medical images. Background Technology

[0002] The common treatment for vertebral compression fractures is percutaneous injection of bone cement into the affected vertebra using specialized instruments, thereby increasing the vertebral body's strength and stability. If the bone cement is injected correctly, the patient experiences a short recovery time after the compression fracture, and may even be able to restore the vertebral body to its previous height. However, if the injection technique is poor, leading to extravasation of the bone cement, it may cause pulmonary embolism or other complications.

[0003] Currently, related technologies use sensor modules to monitor and determine the injection volume and timing of the bone cement injection module, thereby reducing bone cement leakage.

[0004] However, monitoring via sensor modules is cumbersome and has poor accuracy.

[0005] Therefore, how to quickly and accurately plan for preventing leakage during bone cement injection is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] This application provides a method, system, device, and computer-readable storage medium for spinal compression fracture healing planning based on multimodal three-dimensional medical images, which can quickly and accurately plan for preventing leakage during bone cement injection.

[0007] In a first aspect, embodiments of this application provide a method for planning the healing of spinal compression fractures based on multimodal three-dimensional medical images, including:

[0008] Acquire the patient's spinal CT and spinal MR images;

[0009] Based on the identification and segmentation of spinal CT images and spinal MR images, respectively, the CT images and MR images of the fractured vertebral body at the site of compression fracture of the spinal vertebral body are obtained.

[0010] Input the CT and MR images of the fractured vertebral body into the preset bone cement anti-leakage planning model, and output the bone cement injection anti-leakage planning scheme.

[0011] The bone cement injection anti-leakage planning scheme includes at least the following: the viscosity of the bone cement, the injection volume, the injection location, the injection timing, and the injection rate.

[0012] Optionally, based on spinal CT images and spinal MR images, identification and segmentation are performed separately to obtain CT images and MR images of the fractured vertebral body at the site of compression fracture, including:

[0013] The spinal CT image and spinal MR image are respectively input into the preset segmentation network model. The initial convolutional layer has 16 filters, each of which is 3x3 in size, and outputs the first feature map.

[0014] By using multiple convolutional layers and max pooling layers, the spatial dimension of the first feature map is reduced to obtain the second feature map;

[0015] Based on the second feature map and skip connections, the output of the previous layer is directly connected to the next layer, reducing information loss and obtaining the third feature map.

[0016] Optionally, after obtaining the third feature map, the following may also be included:

[0017] The third feature map is upsampled to increase its spatial dimension, resulting in the fourth feature map;

[0018] The feature maps from different layers are fused to enhance the feature representation, resulting in the fifth feature map;

[0019] Multiple feature maps are merged to output the corresponding CT and MR images of the fractured vertebral body at the site of compression fracture of the vertebral body.

[0020] Optionally, also include:

[0021] Volume or surface rendering is performed on CT images of fractured vertebrae to obtain an initial three-dimensional model of the fractured vertebrae;

[0022] The initial three-dimensional model of the fractured vertebra was smoothed and filled to obtain the final three-dimensional model of the fractured vertebra.

[0023] Optional bone cement leakage prevention planning models include:

[0024] Some channels are reorganized, and the channel dimensions are divided into multiple sub-feature groups to achieve a uniform distribution of spatial semantic features;

[0025] Using two parallel branches at the front end to extract attention weights from feature maps has the advantage of better capturing the relationships between channels;

[0026] In the module backend, a cross-dimensional interaction method is used to process the features output by the two branches.

[0027] Optionally, the determination of the viscosity, injection volume, and injection location of the bone cement includes:

[0028] Choose the appropriate bone cement viscosity based on the type of fracture and the condition of the bone.

[0029] The amount of bone cement to be injected is calculated based on the volume and bone condition of the fracture area in the three-dimensional model.

[0030] By analyzing the three-dimensional model, the precise location of the fracture and the direction of the fracture crack are determined, and the injection site for bone cement is selected at the center of the fracture or at the largest crack.

[0031] Optionally, the determination of the timing and rate of bone cement injection includes:

[0032] The timing of bone cement injection is determined based on the diffusion of the bone cement.

[0033] The injection rate of bone cement is determined based on the diffusion of bone cement, the size of the fracture crack, and the hardness of the bone.

[0034] Secondly, embodiments of this application provide a spinal compression fracture healing planning system based on multimodal three-dimensional medical images, comprising:

[0035] The image acquisition module is used to acquire CT and MR images of the patient's spine.

[0036] The image segmentation module is used to identify and segment the spinal CT images and spinal MR images respectively, to obtain the CT images and MR images of the fractured vertebral body at the site of compression fracture of the spinal vertebral body.

[0037] The bone cement anti-leakage planning module is used to input CT images and MR images of fractured vertebrae into a preset bone cement anti-leakage planning model and output a bone cement injection anti-leakage planning scheme.

[0038] The bone cement injection anti-leakage planning scheme includes at least the following: the viscosity of the bone cement, the injection volume, the injection location, the injection timing, and the injection rate.

[0039] Thirdly, embodiments of this application provide an electronic device, which includes: a processor and a memory storing computer program instructions;

[0040] When the processor executes the computer program instructions, it implements a method for planning the healing of spinal compression fractures based on multimodal three-dimensional medical images.

[0041] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement a method for planning the healing of spinal compression fractures based on multimodal three-dimensional medical images.

[0042] The spinal compression fracture healing planning method, system, device, and computer-readable storage medium based on multimodal three-dimensional medical images in this application embodiment can perform bone cement injection leakage prevention planning quickly and accurately.

[0043] This method for spinal compression fracture healing planning based on multimodal three-dimensional medical images includes:

[0044] Acquire the patient's spinal CT and spinal MR images;

[0045] Based on the identification and segmentation of spinal CT images and spinal MR images, respectively, the CT images and MR images of the fractured vertebral body at the site of compression fracture of the spinal vertebral body are obtained.

[0046] Input the CT and MR images of the fractured vertebral body into the preset bone cement anti-leakage planning model, and output the bone cement injection anti-leakage planning scheme.

[0047] The bone cement injection anti-leakage planning scheme includes at least the following: the viscosity of the bone cement, the injection volume, the injection location, the injection timing, and the injection rate. Attached Figure Description

[0048] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating a method for planning the healing of spinal compression fractures based on multimodal three-dimensional medical images, provided in one embodiment of this application.

[0050] Figure 2 This is a schematic diagram of the structure of a segmentation network model provided in one embodiment of this application;

[0051] Figure 3 This is a schematic diagram of the structure of a bone cement anti-leakage planning model provided in one embodiment of this application;

[0052] Figure 4 This is a schematic diagram of the structure of a spinal compression fracture healing planning system based on multimodal three-dimensional medical images provided in one embodiment of this application;

[0053] Figure 5 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0054] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0055] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0056] To address the problems of existing technologies, embodiments of this application provide a method, system, device, and computer-readable storage medium for spinal compression fracture healing planning based on multimodal three-dimensional medical images. The method for spinal compression fracture healing planning based on multimodal three-dimensional medical images provided in this application will be described below.

[0057] Figure 1 This illustration shows a flowchart of a spinal compression fracture healing planning method based on multimodal three-dimensional medical images, according to an embodiment of this application. Figure 1 As shown, the spinal compression fracture healing planning method based on multimodal three-dimensional medical images includes:

[0058] S101. Obtain the patient's spinal CT and spinal MR images;

[0059] S102. Based on the spinal CT images and spinal MR images, the fractured vertebral body CT images and fractured vertebral body MR images of the compression fracture site of the spinal vertebral body are obtained respectively.

[0060] S103. Input the CT and MR images of the fractured vertebral body into the preset bone cement anti-leakage planning model, and output the bone cement injection anti-leakage planning scheme.

[0061] The bone cement injection anti-leakage planning scheme includes at least the following: the viscosity of the bone cement, the injection volume, the injection location, the injection timing, and the injection rate.

[0062] Figure 2 This is a schematic diagram of the structure of a segmentation network model provided in one embodiment of this application;

[0063] In one embodiment, based on spinal CT images and spinal MR images, identification and segmentation are performed respectively to obtain CT images and MR images of the fractured vertebral body at the site of a compression fracture of the spinal vertebral body, including:

[0064] The spinal CT image and spinal MR image are respectively input into the preset segmentation network model. The initial convolutional layer has 16 filters, each of which is 3x3 in size, and outputs the first feature map.

[0065] By using multiple convolutional layers and max pooling layers, the spatial dimension of the first feature map is reduced to obtain the second feature map;

[0066] Based on the second feature map and skip connections, the output of the previous layer is directly connected to the next layer, reducing information loss and obtaining the third feature map.

[0067] In one embodiment, after obtaining the third feature map, the method further includes:

[0068] The third feature map is upsampled to increase its spatial dimension, resulting in the fourth feature map;

[0069] The feature maps from different layers are fused to enhance the feature representation, resulting in the fifth feature map;

[0070] Multiple feature maps are merged to output the corresponding CT and MR images of the fractured vertebral body at the site of compression fracture of the vertebral body.

[0071] In one embodiment, it also includes:

[0072] Volume or surface rendering is performed on CT images of fractured vertebrae to obtain an initial three-dimensional model of the fractured vertebrae;

[0073] The initial three-dimensional model of the fractured vertebra was smoothed and filled to obtain the final three-dimensional model of the fractured vertebra.

[0074] Figure 3 This is a schematic diagram of the structure of a bone cement anti-leakage planning model provided in one embodiment of this application;

[0075] In one embodiment, the bone cement leakage prevention planning model includes:

[0076] Some channels are reorganized, and the channel dimensions are divided into multiple sub-feature groups to achieve a uniform distribution of spatial semantic features;

[0077] Using two parallel branches at the front end to extract attention weights from feature maps has the advantage of better capturing the relationships between channels;

[0078] In the module backend, a cross-dimensional interaction method is used to process the features output by the two branches.

[0079] In one embodiment, determining the viscosity, injection volume, and injection location of the bone cement includes:

[0080] Choose the appropriate bone cement viscosity based on the type of fracture and the condition of the bone.

[0081] The amount of bone cement to be injected is calculated based on the volume and bone condition of the fracture area in the three-dimensional model.

[0082] By analyzing the three-dimensional model, the precise location of the fracture and the direction of the fracture crack are determined, and the injection site for bone cement is selected at the center of the fracture or at the largest crack.

[0083] In one embodiment, determining the timing and rate of bone cement injection includes:

[0084] The timing of bone cement injection is determined based on the diffusion of the bone cement.

[0085] The injection rate of bone cement is determined based on the diffusion of bone cement, the size of the fracture crack, and the hardness of the bone.

[0086] Figure 4 This is a schematic diagram of a spinal compression fracture healing planning system based on multimodal three-dimensional medical images, provided in one embodiment of this application; the spinal compression fracture healing planning system based on multimodal three-dimensional medical images includes:

[0087] Image acquisition module 401 is used to acquire spinal CT images and spinal MR images of the patient;

[0088] The image segmentation module 402 is used to identify and segment the spinal CT image and spinal MR image respectively, and obtain the CT image and MR image of the fractured vertebral body at the site of compression fracture of the spinal vertebral body respectively.

[0089] The bone cement anti-leakage planning module 403 is used to input the fractured vertebral body CT image and fractured vertebral body MR image into the preset bone cement anti-leakage planning model and output the bone cement injection anti-leakage planning scheme.

[0090] The bone cement injection anti-leakage planning scheme includes at least the following: the viscosity of the bone cement, the injection volume, the injection location, the injection timing, and the injection rate.

[0091] Figure 5A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0092] The electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0093] Specifically, the processor 501 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0094] Memory 502 may include mass storage for data or instructions. For example, and not limitingly, memory 502 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 502 may include removable or non-removable (or fixed) media. Where appropriate, memory 502 may be internal or external to an electronic device. In a particular embodiment, memory 502 may be a non-volatile solid-state memory.

[0095] In one embodiment, memory 502 may be 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 flash memory, or a combination of two or more of these.

[0096] The processor 501 reads and executes computer program instructions stored in the memory 502 to implement any of the spinal compression fracture healing planning methods based on multimodal three-dimensional medical images in the above embodiments.

[0097] In one example, the electronic device may also include a communication interface 503 and a bus 510. Wherein, as... Figure 5 As shown, the processor 501, memory 502, and communication interface 503 are connected through bus 510 and complete communication with each other.

[0098] The communication interface 503 is mainly used to realize communication between various modules, systems, units and / or devices in the embodiments of this application.

[0099] Bus 510 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel 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 (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 510 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0100] Furthermore, in conjunction with the spinal compression fracture healing planning method based on multimodal three-dimensional medical images in the above embodiments, this application embodiment can provide a computer-readable storage medium for implementation. This computer-readable storage medium stores computer program instructions; when executed by a processor, these computer program instructions implement any of the spinal compression fracture healing planning methods based on multimodal three-dimensional medical images in the above embodiments.

[0101] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0102] 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, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" 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, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0103] 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 systems. 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 embodiments, or in a different order, or several steps can be performed simultaneously.

[0104] The aspects of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, systems, and computer program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing system to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing system, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. 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 is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0105] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for spinal compression fracture healing planning based on multimodal three-dimensional medical images, characterized in that, include: Acquire the patient's spinal CT and spinal MR images; Based on the identification and segmentation of spinal CT images and spinal MR images, respectively, the CT images and MR images of the fractured vertebral body at the site of compression fracture of the spinal vertebral body are obtained. Input the CT and MR images of the fractured vertebral body into the preset bone cement anti-leakage planning model, and output the bone cement injection anti-leakage planning scheme. The bone cement injection anti-leakage planning scheme includes at least the following: bone cement viscosity, injection volume, injection location, injection timing, and injection rate; the bone cement anti-leakage planning model includes: reorganizing some channels and dividing the channel dimensions into multiple sub-feature groups to achieve a uniform distribution of spatial semantic features; using two parallel branches at the front end to extract attention weights from the feature maps; and processing the features output by the two branches in a cross-dimensional interactive manner at the module back end; selecting an appropriate bone cement viscosity based on the fracture type and bone condition; calculating the bone cement injection volume based on the volume of the fracture area and bone condition in the 3D model; determining the precise location of the fracture and the direction of the fracture fissure by analyzing the 3D model, and selecting the central location of the fracture or the largest fissure as the bone cement injection location; determining the bone cement injection timing based on the bone cement diffusion; and determining the bone cement injection rate based on the bone cement diffusion, fracture fissure size, and bone hardness.

2. The method for spinal compression fracture healing planning based on multimodal three-dimensional medical images according to claim 1, characterized in that, Based on the identification and segmentation of spinal CT and MR images, CT and MR images of the fractured vertebral body at the site of compression fracture of the vertebral body are obtained, including: The spinal CT image and spinal MR image are respectively input into the preset segmentation network model. The initial convolutional layer has 16 filters, each of which is 3x3 in size, and outputs the first feature map. By using multiple convolutional layers and max pooling layers, the spatial dimension of the first feature map is reduced to obtain the second feature map; Based on the second feature map and skip connections, the output of the previous layer is directly connected to the next layer, reducing information loss and obtaining the third feature map.

3. The method for spinal compression fracture healing planning based on multimodal three-dimensional medical images according to claim 2, characterized in that, After obtaining the third feature map, the following is also included: The third feature map is upsampled to increase its spatial dimension, resulting in the fourth feature map; The feature maps from different layers are fused to enhance the feature representation, resulting in the fifth feature map; Multiple feature maps are merged to output the corresponding CT and MR images of the fractured vertebral body at the site of compression fracture of the vertebral body.

4. The method for spinal compression fracture healing planning based on multimodal three-dimensional medical images according to claim 1, characterized in that, Also includes: Volumetric or surface rendering is performed on the CT images of the fractured vertebral body to obtain an initial three-dimensional model of the fractured vertebral body; The initial three-dimensional model of the fractured vertebra was smoothed and filled to obtain the final three-dimensional model of the fractured vertebra.

5. A spinal compression fracture healing planning system based on multimodal three-dimensional medical images, characterized in that, The system includes: The image acquisition module is used to acquire CT and MR images of the patient's spine. The image segmentation module is used to identify and segment the spinal CT images and spinal MR images respectively, to obtain the CT images and MR images of the fractured vertebral body at the site of compression fracture of the spinal vertebral body. The bone cement anti-leakage planning module is used to input CT images and MR images of fractured vertebrae into a preset bone cement anti-leakage planning model and output a bone cement injection anti-leakage planning scheme. The bone cement injection anti-leakage planning scheme includes at least the following: bone cement viscosity, injection volume, injection location, injection timing, and injection rate; a bone cement anti-leakage planning model, used to: reorganize some channels, divide the channel dimensions into multiple sub-feature groups, and achieve a uniform distribution of spatial semantic features; use two parallel branches at the front end to extract attention weights from the feature maps; at the module back end, use a cross-dimensional interactive method to process the features output by the two branches; select an appropriate bone cement viscosity based on the fracture type and bone condition; calculate the bone cement injection volume based on the volume of the fracture area and bone condition in the 3D model; determine the precise location of the fracture and the direction of the fracture crack by analyzing the 3D model, and select the central location of the fracture or the largest crack as the bone cement injection location; determine the bone cement injection timing based on the bone cement diffusion; and determine the bone cement injection rate based on the bone cement diffusion, fracture crack size, and bone hardness.

6. An electronic device, characterized in that, The electronic device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the spinal compression fracture healing planning method based on multimodal three-dimensional medical images as described in any one of claims 1-4.

7. 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 spinal compression fracture healing planning method based on multimodal three-dimensional medical images as described in any one of claims 1-4.

Images