Cerebral hemorrhage surgery planning system and method

Abstract

The present specification relates to the technical field of medical robots, and specifically discloses a cerebral hemorrhage surgery planning system and method, wherein the system comprises: an image storage device configured to store preoperative brain image data of a target object; an image processing device configured to read the preoperative brain image data of the target object from the image storage device; further configured to identify a cerebral hemorrhage type of the target object based on the preoperative brain image data; and further configured to determine a target cerebral hemorrhage surgery mode of the target object according to the preoperative brain image data and the cerebral hemorrhage type. The above scheme can realize automatic hematoma type identification and personalized surgery planning, and improve the efficiency and reliability of surgery planning.

Description

Technical Field

[0001] This manual relates to the field of medical robot technology, and in particular to a surgical planning system and method for cerebral hemorrhage. Background Technology

[0002] Currently, before surgery for cerebral hemorrhage, the brain tissue structures (e.g., skull, blood vessels, brain parenchyma, ventricles, etc.) and hematoma are usually segmented based on the patient's preoperative brain imaging. Then, surgical planning is performed based on the segmentation results, determining the puncture target and avoiding important functional areas and blood vessels in the brain.

[0003] Because the size, shape, and location of hematomas vary from patient to patient, the corresponding surgical approaches also differ. However, current surgical planning relies heavily on the doctor's experience, which is highly subjective. This is especially true in areas with relatively limited medical resources, where preoperative surgical planning is prone to errors.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This specification provides a surgical planning system and method for cerebral hemorrhage surgery to address the problem that the subjective nature of surgical planning for cerebral hemorrhage in the prior art affects the surgical outcome.

[0006] This specification provides an embodiment of a surgical planning system for cerebral hemorrhage, comprising:

[0007] Image storage device for storing preoperative brain imaging data of a target subject;

[0008] An image processing device is configured to read preoperative brain imaging data of the target object from the image storage device; to identify the type of cerebral hemorrhage of the target object based on the preoperative brain imaging data; and to determine the target cerebral hemorrhage surgical method for the target object based on the preoperative brain imaging data and the type of cerebral hemorrhage.

[0009] In one embodiment, the image processing apparatus is specifically used for:

[0010] The target segmentation and recognition model is used to segment and recognize brain organs and tissues and identify the type of cerebral hemorrhage in the preoperative brain imaging data, so as to obtain the segmented and recognized brain image data and the type of cerebral hemorrhage of the target object.

[0011] In one embodiment, the image processing apparatus is specifically used for:

[0012] Access to multiple surgical options for cerebral hemorrhage;

[0013] The various surgical methods for cerebral hemorrhage, the preoperative brain imaging data, and the type of cerebral hemorrhage are input into the target surgical outcome prediction model to obtain the surgical outcome indicators corresponding to the various surgical methods for cerebral hemorrhage.

[0014] Based on the surgical outcome indicators corresponding to the various surgical methods for cerebral hemorrhage, the target surgical method for cerebral hemorrhage of the target patient is determined.

[0015] In one embodiment, the brain hemorrhage surgery planning system further includes: a virtual reality device;

[0016] The image processing device is also used to retrieve the virtual surgical instrument model corresponding to the target brain hemorrhage surgical method, and send the segmented and identified brain image data and the virtual surgical instrument model to the virtual reality device;

[0017] The virtual reality device is used to perform three-dimensional reconstruction based on the segmented and recognized brain image data to obtain a model of brain tissue and organs. It is also used to reconstruct a surgical scene based on the model of brain tissue and organs and the model of virtual surgical instruments to obtain a simulated surgical scene.

[0018] In one embodiment, the brain hemorrhage surgery planning system further includes: an image acquisition device for acquiring user simulated surgical video data;

[0019] The image storage device is also used to store surgical standard data corresponding to various cerebral hemorrhage surgical methods;

[0020] The image processing device is also used to retrieve surgical standard data corresponding to the target cerebral hemorrhage surgical procedure from the image storage device; and to determine whether the current user's surgical operation procedure conforms to the surgical standard based on the user's simulated surgical video data and the surgical standard data corresponding to the target cerebral hemorrhage surgical procedure.

[0021] In one embodiment, the user-simulated surgical video data includes surgical procedure description audio data and surgical simulation operation image data;

[0022] The image processing device is specifically used for:

[0023] Based on the surgical procedure description voice data, determine whether the current surgical procedure conforms to the surgical procedure specification;

[0024] If the current surgical procedure is determined to comply with the surgical procedure specifications, the surgical operation image data is used to determine whether the current surgical operation complies with the surgical operation specifications.

[0025] If the current surgical procedure is confirmed to comply with the surgical procedure guidelines, then the current user's surgical procedure process is confirmed to comply with the surgical guidelines.

[0026] If it is determined that the current user's surgical procedure does not conform to the surgical standard, a prompt message is generated; the prompt message is used to guide the user to the correct surgical procedure.

[0027] In one embodiment, the image processing apparatus is specifically used for:

[0028] Retrieve standard surgical posture data corresponding to the current surgical procedure;

[0029] The surgical simulation operation image data is subjected to posture recognition to obtain the user's surgical operation posture data;

[0030] The user's surgical posture data is matched with the standard surgical posture data;

[0031] If a match is successful, the current surgical procedure is confirmed to comply with the surgical procedure guidelines.

[0032] In one embodiment, the image processing apparatus is further configured to:

[0033] The user's simulated surgical video data is sent to the virtual reality device; the virtual reality device updates the simulated surgical scene based on the user's simulated surgical video data.

[0034] This specification also provides an embodiment of a surgical planning method for cerebral hemorrhage, including:

[0035] Obtain preoperative brain imaging data of the target subject;

[0036] Based on the preoperative brain imaging data, the type of cerebral hemorrhage in the target subject was identified;

[0037] Based on the preoperative brain imaging data and the type of brain hemorrhage, the target surgical method for brain hemorrhage in the target patient is determined.

[0038] This specification also provides a computer device, including a processor and a memory for storing processor-executable instructions, wherein the processor executes the instructions to implement the steps of the brain hemorrhage surgical planning method described in any of the above embodiments.

[0039] This specification also provides a computer-readable storage medium storing computer instructions that, when executed, implement the steps of the brain hemorrhage surgical planning method described in any of the above embodiments.

[0040] This specification provides a brain hemorrhage surgery planning system that can acquire preoperative brain imaging data of a target subject, identify the type of brain hemorrhage based on the preoperative brain imaging data, and then determine the target brain hemorrhage surgery method based on the preoperative brain imaging data and the brain hemorrhage type. In this solution, the type of brain hemorrhage of the target subject can be identified based on the preoperative brain imaging data, and then a target brain hemorrhage surgery method can be recommended to the user based on the preoperative brain imaging data and the brain hemorrhage type. This allows for fully automated brain hemorrhage type identification and personalized surgical planning, improving the efficiency and reliability of surgical planning. Attached Figure Description

[0041] The accompanying drawings, which are included to provide a further understanding of this specification and form part of it, do not constitute a limitation thereof. In the drawings:

[0042] Figure 1 A schematic diagram illustrating an application scenario of the surgical planning method for cerebral hemorrhage according to one embodiment of this specification is shown;

[0043] Figure 2 A flowchart of a surgical planning method for cerebral hemorrhage according to one embodiment of this specification is shown;

[0044] Figure 3 This diagram illustrates the process of creating a training sample set for a target segmentation and recognition model according to one embodiment of this specification.

[0045] Figure 4 A schematic diagram illustrating the segmentation of multiple brain organs and the classification of brain hemorrhage types in one embodiment of this specification is shown;

[0046] Figure 5 A schematic diagram of the target segmentation and recognition model in one embodiment of this specification is shown;

[0047] Figure 6 This document illustrates a schematic diagram of the process for creating a training sample set for a target surgical outcome prediction model in one embodiment of this specification.

[0048] Figure 7 A schematic diagram illustrating the mapping relationship between surgical procedures for cerebral hemorrhage, hematoma type, and survival time in one embodiment of this specification is shown.

[0049] Figure 8 A schematic diagram of the structure of a target surgical outcome prediction model in one embodiment of this specification is shown;

[0050] Figure 9A schematic diagram of the Marching Cubes algorithm for constructing brain tissue and organ models is shown in one embodiment of this specification;

[0051] Figure 10 A flowchart illustrating the updating of a simulated surgical scenario in one embodiment of this specification is shown;

[0052] Figure 11 A schematic diagram of the simulated surgical procedure matching and feedback process in one embodiment of this specification is shown;

[0053] Figure 12 A flowchart of user action recognition in one embodiment of this specification is shown;

[0054] Figure 13 This specification shows a schematic diagram of ICP key point registration in one embodiment;

[0055] Figure 14 This specification shows a schematic diagram of the key point and standard template matching algorithm structure in one embodiment;

[0056] Figure 15 A flowchart of a surgical planning method for cerebral hemorrhage according to one embodiment of this specification is shown;

[0057] Figure 16 A schematic diagram of the surgical planning device for cerebral hemorrhage according to one embodiment of this specification is shown;

[0058] Figure 17 A schematic diagram of a computer device according to one embodiment of this specification is shown;

[0059] Figure 18 A schematic diagram of the surgical planning system for cerebral hemorrhage according to one embodiment of this specification is shown. Detailed Implementation

[0060] The principles and spirit of this specification will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are given merely to enable those skilled in the art to better understand and implement this specification, and are not intended to limit the scope of this specification in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0061] Those skilled in the art will recognize that the embodiments described in this specification can be implemented as a system, apparatus, method, or computer program product. Therefore, the disclosure of this specification can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0062] This specification provides an embodiment of a surgical planning method for cerebral hemorrhage. Figure 1 A schematic diagram illustrating an application scenario of the surgical planning method for cerebral hemorrhage according to one embodiment of this specification is shown. For example... Figure 1 As shown, the hardware equipment related to the surgical planning method for cerebral hemorrhage may include: image acquisition device 1, virtual display device 2, image display device 3, image processing device 4, and image storage device 5.

[0063] Image acquisition device 1 may include a 3D camera, for example, a binocular camera. Image acquisition device 1 can acquire user posture data and voice data. Image acquisition device 1 may also include a medical imaging device, which can acquire preoperative brain imaging data of the target object.

[0064] Image storage device 5 may include a hard disk or other storage device. Image storage device 5 can store preoperative brain imaging data of the target object, a three-dimensional brain model, a three-dimensional model used during surgery, posture and voice data from user-simulated surgery, and multi-organ segmentation models of the brain, etc.

[0065] Preoperative brain imaging data may include CT images, CTA images, and / or MRI images.

[0066] Image processing device 4 may include image processing equipment, etc. Image processing device 4 is used to acquire preoperative brain image data from image storage device 5, and to perform multi-organ segmentation and recognition of the brain and classification of cerebral hemorrhage on the preoperative brain image data. Image processing device 4 can also recommend target cerebral hemorrhage surgical methods to the user based on the type of cerebral hemorrhage and the preoperative brain image data. Image processing device 4 is also used to perform motion analysis and semantic analysis on the user's posture data and voice data during simulated surgery to determine whether the current surgical posture of the user conforms to the specifications. If so, the user proceeds to the next surgical procedure; otherwise, the user is prompted with the correct surgical posture.

[0067] Virtual reality device 2 may include wearable VR devices worn by the user. Virtual reality device 2 can reconstruct surgical scenes. It can utilize the segmented and identified multi-organ brain image data from image processing device 4, and can also retrieve surgical instrument models corresponding to the target brain hemorrhage surgical procedure. Then, based on the multi-organ brain image data and the surgical instrument models, it can simulate the surgical scene. Virtual reality device 2 can also acquire the user's posture data during the simulated surgery and update the surgical scene based on this posture data.

[0068] The image display device 3 may include a display screen. The image display device can be used to synchronously display images within the field of view of a virtual reality device.

[0069] Figure 2A flowchart of a surgical planning method for cerebral hemorrhage according to one embodiment of this specification is shown. While this specification provides method operation steps or apparatus structures as illustrated in the following embodiments or figures, more or fewer operation steps or module units may be included in the method or apparatus based on conventional or non-inventive effort. In steps or structures where there is no logically necessary causal relationship, the execution order of these steps or the module structure of the apparatus is not limited to the execution order or module structure described in the embodiments and figures of this specification. When the method or module structure is applied in actual devices or end products, it can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed processing environment) according to the method or module structure shown in the embodiments or figures.

[0070] Specifically, such as Figure 2 As shown, one embodiment of the surgical planning method for cerebral hemorrhage provided in this specification may include the following steps:

[0071] Step S201: Obtain preoperative brain imaging data of the target subject.

[0072] The surgical planning method for cerebral hemorrhage described in the embodiments of this specification can be applied to an image processing device. The image processing device may include an image processing host or a server.

[0073] The image processing device can acquire preoperative brain imaging data of a target subject. The target subject can be a patient or other surgical patient. The preoperative brain imaging data can include images of the target subject's head taken before brain surgery. The preoperative brain imaging data can include at least one of the following: CT images, CTA images, and MRI images.

[0074] Step S202: Based on the preoperative brain imaging data, identify the type of brain hemorrhage in the target subject.

[0075] After obtaining preoperative brain imaging data, the image processing host or server can identify the type of brain hemorrhage in the target subject based on the preoperative brain imaging data.

[0076] Specifically, the type of brain hemorrhage in the target patient can be identified based on preoperative brain imaging data. The type of brain hemorrhage can include at least one of the following: deep hemorrhage, lobar hemorrhage, brainstem hemorrhage, cerebellar hemorrhage, parenchymal hemorrhage, intraventricular hemorrhage, and hemorrhage in multiple sites.

[0077] In one embodiment, brain organ and tissue segmentation and identification can also be performed on the preoperative brain imaging data. Specifically, in some embodiments of this specification, identifying the type of cerebral hemorrhage of the target object based on the preoperative brain imaging data may include: using a target segmentation and identification model to perform brain organ and tissue segmentation and cerebral hemorrhage type identification on the preoperative brain imaging data, to obtain segmented and identified brain image data and the type of cerebral hemorrhage of the target object.

[0078] Brain organ and tissue segmentation and recognition refers to identifying different organs and / or tissues in the brain and segmenting them based on the identification results. Different organs and / or tissues in the brain can include, for example, the skull, blood vessels, hematoma, brain parenchyma, cerebrum, brainstem, cerebellum, etc. By utilizing deep learning models, brain organ and tissue segmentation and recognition, as well as the type of cerebral hemorrhage, can be automatically performed on preoperative brain imaging data.

[0079] The target segmentation and recognition model can be pre-trained. In one embodiment, the target segmentation and recognition model can be constructed by: obtaining a training sample set; and training the pre-defined segmentation and recognition model using the training sample set to obtain the target segmentation and recognition model.

[0080] The training sample set can include a sample set and a label set. The sample set can include multiple preoperative brain imaging data. The label set can include the segmented and identified brain image data corresponding to each sample in the sample set and the corresponding type of brain hemorrhage.

[0081] For details, please refer to Figure 3 This diagram illustrates the process of creating the training sample set for the target segmentation and recognition model in the embodiments of this specification. Figure 3 As shown, the creation of the training sample set may include the following steps:

[0082] Step S301: Acquire a large amount of preoperative brain imaging data. Preoperative brain imaging data may include CT images, CTA images, and / or MRI images.

[0083] Step S302 involves registering the image data of different modalities to the CT images. Registration facilitates subsequent processing.

[0084] Step S303 involves outlining brain tissues and organs on the registered image to obtain segmented and identified brain image data. The type of cerebral hemorrhage corresponding to this image can also be identified. Please refer to [link / reference]. Figure 4 This diagram illustrates the segmentation of multiple brain organs and the classification of brain hemorrhage types in embodiments of this specification. Figure 4 As shown, the left side is the input CT image, and the right side is the output brain image data after segmentation and recognition. The brain hemorrhage type is also marked as cerebral parenchymal hemorrhage.

[0085] Step S304: Save the labeled data as a training sample set.

[0086] After obtaining the training sample set, the preset segmentation and recognition model can be trained using the training sample set to obtain the target segmentation and recognition model.

[0087] Please refer to Figure 5 The diagram illustrates the structure of the target segmentation and recognition model in the embodiments of this specification. Figure 5 As shown, the input of the target segmentation and recognition model is preoperative brain imaging data, and the output consists of two parts: one is the predicted type of brain hemorrhage (Output1), and the other is the segmented and recognized brain image data (Output2). Figure 5 As shown, the operations included in each layer of a deep learning model are: DenseBlock, Conv (convolution operation), Avg Pooling (average pooling operation), Global Avg Pooling (global average pooling operation), FC (fully connected), Deconv (deconvolution operation), and Softmax (non-linear mapping).

[0088] Step S203: Based on the preoperative brain imaging data and the type of brain hemorrhage, determine the target surgical method for the target patient's brain hemorrhage.

[0089] After identifying the type of cerebral hemorrhage based on preoperative brain imaging data, the target surgical approach for the target patient can be determined based on the preoperative brain imaging data and the type of cerebral hemorrhage.

[0090] In one embodiment, preoperative brain imaging data, types of cerebral hemorrhage, and corresponding surgical methods for historical time periods can be obtained from a database. Then, the target patient's preoperative brain imaging data and cerebral hemorrhage type are matched with the preoperative brain imaging data and cerebral hemorrhage types from the historical time periods. The surgical methods corresponding to the successfully matched preoperative brain imaging data and cerebral hemorrhage types from the historical time periods are determined as the target cerebral hemorrhage surgical method for the target patient. For example, the target patient's preoperative brain imaging data can first be matched with preoperative brain imaging data from the historical time periods to obtain multiple matched preoperative brain imaging data. Then, the cerebral hemorrhage types corresponding to the multiple matched preoperative brain imaging data are matched with the target patient's cerebral hemorrhage type. The surgical methods corresponding to the successfully matched preoperative brain imaging data and cerebral hemorrhage types are determined as the target cerebral hemorrhage surgical method for the target patient.

[0091] In one embodiment, when multiple matching surgical methods exist, the user (i.e., the doctor) can determine the target surgical method for cerebral hemorrhage. In another embodiment, when multiple matching surgical methods exist, the server or image processing host can determine the surgical method with the best surgical outcome as the target cerebral hemorrhage surgical method based on the surgical effects corresponding to the multiple matching surgical methods.

[0092] In some embodiments of this specification, determining the target surgical method for brain hemorrhage of the target subject based on the preoperative brain imaging data and the type of brain hemorrhage may include: acquiring multiple brain hemorrhage surgical methods; inputting the various brain hemorrhage surgical methods, the preoperative brain imaging data, and the type of brain hemorrhage into a target surgical outcome prediction model to obtain surgical outcome indicators corresponding to the various brain hemorrhage surgical methods; and determining the target brain hemorrhage surgical method for the target subject based on the surgical outcome indicators corresponding to the various brain hemorrhage surgical methods.

[0093] Various surgical procedures for cerebral hemorrhage can include: craniotomy for hematoma evacuation, minimally invasive craniotomy for hematoma evacuation via small craniotomy window, stereotactic hematoma drainage, neuroendoscopic intracranial hematoma evacuation, and ventricular puncture and external drainage.

[0094] The target surgical outcome prediction model can be pre-trained. In one embodiment, the target surgical outcome prediction model can be constructed by: obtaining a training sample set; and training the pre-set surgical outcome prediction model using the training sample set to obtain a target segmentation and recognition model.

[0095] The training sample set may include a sample set and a label set. The sample set may include multiple preoperative brain imaging datasets, as well as the corresponding brain hemorrhage type and surgical procedure number for each preoperative brain imaging dataset. The label set may include surgical outcome indicators for each sample in the sample set. Surgical outcome indicators may include at least one of the following: survival time, quality of life, etc.

[0096] For details, please refer to Figure 6 This diagram illustrates the process of creating the training sample set for the target surgical outcome prediction model in the embodiments of this specification. Figure 6 As shown, the creation of the training sample set may include the following steps:

[0097] Step S601: Collect a large amount of preoperative brain imaging data and its corresponding surgical methods and surgical outcome indicators.

[0098] Step S602: The surgical methods are labeled on a large amount of preoperative brain imaging data, and the surgical methods are coded in sequence.

[0099] Step S603: Mark the types of cerebral hemorrhage in a large amount of preoperative brain imaging data, and encode the types of cerebral hemorrhage in sequence.

[0100] Step S604: Label the surgical outcome indicators on a large amount of preoperative brain imaging data and use the surgical outcome indicators as corresponding labels.

[0101] Step S605: Save the labeled data as a training sample set.

[0102] After obtaining the training sample set, the preset surgical outcome prediction model can be trained using the training sample set to obtain the target surgical outcome prediction model.

[0103] Please refer to Figure 7 This diagram illustrates the mapping relationship between surgical procedures for cerebral hemorrhage, hematoma type (i.e., type of cerebral hemorrhage), and survival time in the embodiments of this specification. Figure 7 As shown, ID is the number of the preoperative surgical imaging data of the brain.

[0104] Please refer to Figure 8 This diagram illustrates the structure of the target surgical outcome prediction model in an embodiment of this specification. Figure 8 As shown, the target segmentation and recognition model's input 1 (Input1) is the preoperative brain imaging data of the target object, input 2 (Input2) is the type of brain hemorrhage of the target object, input 3 (Input3) is the various brain hemorrhage surgical methods among multiple brain hemorrhage surgical methods, and the output (Output) is the surgical effect index corresponding to each brain hemorrhage surgical method. For example... Figure 7 As shown, the operations included in each layer of the target surgical outcome prediction model are: DenseBlock, Conv, AvgPooling, Global Avg Pooling, FC, Deconv, Softmax, and Normalization.

[0105] In this embodiment, the type of cerebral hemorrhage of the target object can be identified based on the preoperative brain imaging data of the target object. Then, the target cerebral hemorrhage surgical method can be recommended to the user based on the preoperative brain imaging data and the type of cerebral hemorrhage. Cerebral hemorrhage surgery can be performed on the target object according to the target cerebral hemorrhage surgical method. This can realize fully automatic hematoma type identification and personalized surgical planning, and improve the efficiency and reliability of surgical planning.

[0106] In some embodiments of this specification, the brain hemorrhage surgery planning method may further include: retrieving a virtual surgical instrument model corresponding to the target brain hemorrhage surgery method; sending the segmented and identified brain image data and the virtual surgical instrument model to a virtual reality device; the virtual reality device is used to perform three-dimensional reconstruction based on the segmented and identified brain image data to obtain a brain tissue and organ model, and to perform surgical scene reconstruction based on the brain tissue and organ model and the virtual surgical instrument model to obtain a simulated surgical scene.

[0107] The image storage device can also store virtual surgical instrument models corresponding to various surgical procedures for cerebral hemorrhage. The image processing device can retrieve the virtual surgical instrument model corresponding to the target cerebral hemorrhage surgical procedure for the target object. This virtual surgical instrument model can include model data of various surgical instruments. The image storage device can send the segmented and recognized brain image data and the virtual surgical instrument model corresponding to the target cerebral hemorrhage surgical procedure to a virtual reality device. The virtual reality device can perform 3D reconstruction based on the segmented and recognized brain image data to obtain a model of brain tissue and organs. Then, the virtual reality device can reconstruct the surgical scene based on the brain tissue and organ model and the virtual surgical instrument model to obtain a simulated surgical scene.

[0108] In one embodiment, the virtual reality device binarizes the segmented and identified brain image data to obtain a binarized organ segmentation mask, and then uses a three-dimensional discrete data field isosurface extraction algorithm (e.g., MarchingCubes) to reconstruct the organ morphology to obtain a brain tissue organ model.

[0109] Please refer to Figure 9 The diagram illustrates the structure of the Marching Cubes algorithm for constructing models of brain tissues and organs. Figure 9 As shown, the basic idea of ​​the algorithm is to process the cubes (voxels) in the data field one by one, separate the cubes that intersect with the isosurface, and use interpolation to calculate the intersection points of the isosurface and the cube edges. Based on the relative position of each vertex of the cube and the isosurface, the intersection points of the isosurface and the cube edges are connected in a certain way to generate the isosurface, which serves as an approximate representation of the isosurface within the cube.

[0110] Virtual surgical instrument models can be constructed using real-time 3D reconstruction algorithms (such as BundleFusion) based on the depth of the surgical instruments. Virtual reality devices can reconstruct surgical scenes based on brain tissue and organ models and virtual surgical instrument models to obtain simulated surgical scenarios. Simulating surgical scenarios through virtual reality devices allows users to intuitively observe the surgical environment, laying the foundation for subsequent simulated surgical operations.

[0111] In some embodiments of this specification, the brain hemorrhage surgery planning method may further include: sending user-simulated surgical video data to the virtual reality device; the virtual reality device updating the simulated surgical scene based on the user-simulated surgical video data. The user-simulated surgical video data can be acquired by an image acquisition device (e.g., a binocular camera). User-simulated surgical video data refers to video data acquired by the image acquisition device when a user performs a simulated surgical operation based on a simulated surgical scene in the virtual reality device. The virtual reality device can update the simulated surgical scene based on the user-simulated surgical video data, presenting a real-time virtual reality effect of objects. In this embodiment, by simulating the interaction process between instruments and tissues in a real surgical scene, the safety and reliability of the surgery can be improved.

[0112] Please refer to Figure 10 The flowchart illustrating the update of the simulated surgical scenario in an embodiment of this specification is shown. Figure 10 As shown, updating the simulated surgical scenario may include the following steps:

[0113] Step 1: Input the user's simulated surgical video data.

[0114] Step 2: The set of pixels at the edge of the scene is used as feature points for detection. The features of each feature point in the sampled frame are used for matching. Then, the consistency of the matched consecutive frames is verified.

[0115] Step 3: Optimize the camera pose locally using the matched consecutive frames.

[0116] Step 4: Perform global map optimization on the optimized local map data; then store the optimized global map data in the cache.

[0117] Step 5: When the user's head moves, after a new image is captured, the data in the buffer is fused with the new image data, and duplicate data is removed until the scene is established.

[0118] Step 6: After the environment scene is established, import the brain tissue and hematoma segmentation result model obtained in Step 2 into the VR device to establish the initial positional relationship between the model and the environment.

[0119] Step 7: When the user's head moves, the virtual reality device senses the current head position and feeds it back to the virtual reality visual effect, forming a virtual reality effect of the object at the current position.

[0120] In some embodiments of this specification, the brain hemorrhage surgery planning method may further include: acquiring user simulated surgical video data; retrieving surgical standard data corresponding to the target brain hemorrhage surgery method; and determining whether the current user surgical operation procedure conforms to the surgical standard based on the user simulated surgical video data and the surgical standard data corresponding to the target brain hemorrhage surgery method.

[0121] In this embodiment, after obtaining the target surgical procedure for cerebral hemorrhage, the user can perform a simulated surgical operation based on the target procedure. An image acquisition device collects the user's simulated surgical video data and stores the collected video data in an image storage device. An image processing device can read the user's simulated surgical video data from the image storage device. The image processing device can also obtain surgical specification data corresponding to the target cerebral hemorrhage surgical procedure from the image storage device or from a cloud server. The surgical specification data may include process specification data and operation specification data corresponding to the target cerebral hemorrhage surgical procedure. Process specification data describes the surgical procedure corresponding to the target cerebral hemorrhage surgical procedure. Operation specification data describes the surgical operations corresponding to each surgical procedure.

[0122] The image processing device can determine whether the current user's surgical procedure conforms to the surgical guidelines based on the user's simulated surgical video data and the surgical guidelines corresponding to the target intracranial hemorrhage surgical method. The method in this embodiment can determine whether the user's simulated surgical procedure conforms to the surgical guidelines.

[0123] In some embodiments of this specification, after determining whether the current user's surgical procedure conforms to the surgical guidelines, the method may further include: generating a prompt message if the current user's surgical procedure does not conform to the surgical guidelines; the prompt message is used to prompt the user for the correct surgical procedure.

[0124] In this embodiment, if the user's surgical procedure does not conform to the surgical specifications, the image processing device can generate prompt information. The prompt information can be used to guide the user to the correct surgical procedure, correct the user's surgical procedure until it meets the surgical specifications, and can improve the success rate and surgical quality of the subsequent formal surgery performed by the user.

[0125] In some embodiments of this specification, after determining whether the current user's surgical procedure conforms to the surgical guidelines, the procedure may further include: if the current user's surgical procedure conforms to the surgical guidelines, determining whether the current procedure is the final step; if so, ending the procedure; otherwise, reminding the user to proceed to the next step.

[0126] In some embodiments of this specification, the user-simulated surgical video data includes surgical procedure description voice data and surgical simulation operation image data; determining whether the current user's surgical operation procedure conforms to the surgical standard based on the user-simulated surgical video data and the surgical standard data corresponding to the target cerebral hemorrhage surgical method may include: determining whether the current surgical procedure conforms to the surgical procedure standard based on the surgical procedure description voice data; if the current surgical procedure is determined to conform to the surgical procedure standard, determining whether the current surgical operation conforms to the surgical operation standard based on the surgical simulation operation image data; if the current surgical operation is determined to conform to the surgical operation standard, determining that the current user's surgical operation procedure conforms to the surgical standard.

[0127] The surgical procedure description voice data can include the user's voice describing the surgical procedure. The image processing device can perform semantic recognition on the surgical procedure description voice data to obtain the surgical procedure description data. The image processing device can acquire the surgical specification data corresponding to the target intracranial hemorrhage surgical procedure. The surgical specification data is used to define the standard procedure operation for the target intracranial hemorrhage surgical procedure. The image processing device can match the surgical procedure description data with the surgical specification data to determine whether the current surgical procedure conforms to the surgical procedure specification.

[0128] The surgical simulation operation image data may include image data of the user simulating surgical procedures. The image processing device can determine whether the current surgical procedure conforms to surgical procedure guidelines based on the surgical simulation operation image data. If the current surgical procedure is determined to conform to the surgical procedure guidelines, the device further determines that the current user's surgical procedure flow conforms to the surgical procedure guidelines. In this embodiment, using both surgical procedure description voice data and surgical simulation operation image data to jointly determine whether the current surgical procedure flow conforms to the surgical procedure guidelines can improve the reliability and accuracy of the judgment.

[0129] In some embodiments of this specification, determining whether a current surgical operation conforms to surgical operation specifications based on the surgical simulation operation image data may include: retrieving standard surgical posture data corresponding to the current surgical procedure; performing posture recognition on the surgical simulation operation image data to obtain user surgical posture data; matching the user surgical posture data with the standard surgical posture data; and, if the match is successful, determining that the current surgical operation conforms to surgical operation specifications. Performing posture recognition on the surgical simulation operation image data to obtain user surgical posture data. The surgical specification data may include standard posture data corresponding to standard procedure operations. The image processing device can match the user surgical posture data with the standard posture data to determine whether the current surgical operation conforms to surgical operation specifications.

[0130] Please refer to Figure 11This diagram illustrates the flowchart of simulated surgical operation matching and feedback in an embodiment of this specification. Figure 11 As shown, the following steps may be included:

[0131] Step 1: The user verbally describes the current surgical procedure.

[0132] Step 2: The image processing device determines whether the current surgical step is correct based on the voice data describing the surgical procedure. If yes, proceed to step 4; otherwise, proceed to step 3.

[0133] Step 3: The image processing device prompts the user with the correct surgical procedure. Return to Step 1.

[0134] Step 4: The user simulates the current surgical procedure.

[0135] Step 5: The image processing device calculates the displacement field of the user's key human body points based on the surgical simulation operation image data.

[0136] Step 7: The image processing device identifies the current surgical operation based on the displacement field of the user's key human body points.

[0137] Step 8: The image processing device matches the current surgical operation with the standard surgical procedure. If the match is successful, proceed to step 9; otherwise, proceed to step 10.

[0138] Step 9: The user proceeds to the next surgical procedure.

[0139] Step 10: The image processing device prompts the user for the correct surgical posture.

[0140] In this embodiment, the current user's posture can be automatically identified and registered with the standard surgical posture. Based on the magnitude of the key point offset field, it can be determined whether the current surgical action meets the standard. If it does not meet the standard, the system will prompt the user to correct the correct surgical posture until it meets the standard.

[0141] Please refer to Figure 12 The flowchart illustrating the user action recognition process in an embodiment of this specification is shown. Figure 12 As shown, the steps may include the following.

[0142] Step S121: Use a binocular camera to acquire depth and RGB image data in real time.

[0143] Step S122: Use HRNet to identify the location of user key points.

[0144] Step S123: Combine the depth map to obtain the position and depth of each key point.

[0145] Step S124: Using the ICP registration method, the key points are registered with the standard template to obtain the displacement of each key point.

[0146] Step S125: Format the output action type.

[0147] Please refer to Figure 13 This diagram illustrates the ICP key point registration schematic in an embodiment of this specification. Figure 13 As shown, when determining whether the user's current action conforms to the specifications, the system first uses a depth camera to acquire the user's depth image and RGB image, then uses HRNet to identify the key points of the user's body, and finally combines the ICP algorithm to perform point cloud registration between the key points of the standard template example and the current key points, calculates the displacement field between the user and the standard template key points, and outputs the user's action type in a formatted manner based on the displacement field.

[0148] Please refer to Figure 14 The diagram shows the key points of the embodiments of this specification and the structural diagram of the standard template matching algorithm.

[0149] like Figure 14 As shown, the matching algorithm includes the following steps:

[0150] Step S141, input point cloud data.

[0151] Step S142: Perform initial transformation on the input point cloud data.

[0152] Step S143: Adjust the weights of some corresponding point pairs.

[0153] Step S144: Eliminate unreasonable corresponding point pairs.

[0154] Step S145: Calculate the loss, and solve for the current optimal transformation while minimizing the loss until the loss converges.

[0155] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. For details, please refer to the foregoing descriptions of the relevant processing embodiments; they will not be repeated here.

[0156] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0157] The above method will be described below with reference to a specific embodiment. However, it is worth noting that this specific embodiment is only for better illustration of this specification and does not constitute an improper limitation of this specification.

[0158] This specific embodiment provides a method for planning surgery for cerebral hemorrhage. Please refer to... Figure 15 A flowchart of a surgical planning method for cerebral hemorrhage according to an embodiment of this specification is shown. Figure 15 As shown, the surgical planning method in the embodiments of this specification includes the following steps:

[0159] Step 1: Collect preoperative brain imaging data of the target subject, which may include CT images, CTA images, and MRI images.

[0160] Step 2: Based on the collected preoperative brain imaging data, perform multi-organ and multi-tissue segmentation of the brain and classification of cerebral hemorrhage types.

[0161] Step 3: Perform 3D reconstruction based on the brain image data of the segmented tissues and organs to obtain a brain tissue and organ model.

[0162] Step 4: Based on the preoperative brain imaging data collected in Step 1 and the type of brain hemorrhage predicted in Step 2, predict the target brain hemorrhage surgical method for the target patient.

[0163] Step 5: Retrieve the virtual surgical instrument model corresponding to the target brain hemorrhage surgical method.

[0164] Step 6: Based on the brain tissue and organ model obtained in Step 3 and the virtual surgical instrument model obtained in Step 5, the surgical scene is reconstructed to obtain a simulated surgical scene.

[0165] Step 7: The doctor verbally describes the current surgical procedure.

[0166] Step 8: Determine if the surgical procedure complies with the standards. If the surgical procedure complies with the standards, proceed to step 10; otherwise, proceed to step 9.

[0167] Step 9: The image processing device indicates the correct surgical procedure.

[0168] Step 10: The user begins simulating the surgical procedure. The surgical procedure may include either operation instructions or medication instructions. Operation instructions may include instructions for operating a scalpel, surgical scissors, puncture needles, or other instruments related to brain hemorrhage surgery. Medication instructions may include the dosage of any type of drug administered via at least one of an infusion set, a micro-infusion pump, or a blood transfusion set.

[0169] Step 11: The system determines whether the current surgical posture of the executor conforms to the standard. If yes, proceed to step 13; otherwise, proceed to step 12.

[0170] Step 12: The image processing device indicates the correct surgical posture. Return to step 10.

[0171] Step 13: Determine if this is the final step of the current surgical procedure. If yes, the simulated surgery ends; otherwise, return to step 6.

[0172] The methods described in the above embodiments, by constructing a surgical plan recommendation and simulation method for patients with cerebral hemorrhage, can achieve fully automated identification of cerebral hemorrhage types and recommendation of surgical procedures, thereby improving the efficiency of surgical planning. By simulating the interaction process between instruments and tissues in a real surgical scenario, the safety and reliability of the surgery can be improved.

[0173] Based on the same inventive concept, this specification also provides a surgical planning device for cerebral hemorrhage, as described in the following embodiments. Since the principle by which the surgical planning device for cerebral hemorrhage solves the problem is similar to that of the surgical planning method for cerebral hemorrhage, the implementation of the surgical planning device for cerebral hemorrhage can refer to the implementation of the surgical planning method for cerebral hemorrhage, and repeated details will not be repeated. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated. Figure 16 This is a structural block diagram of a surgical planning device for cerebral hemorrhage according to an embodiment of this specification, such as... Figure 16 As shown, it includes: an acquisition module 1601, an identification module 1602, and a first determination module 1603. The structure is described below.

[0174] Module 1601 acquires preoperative brain imaging data of the target subject.

[0175] The identification module 1602 identifies the type of cerebral hemorrhage in the target subject based on the preoperative brain imaging data.

[0176] The first determining module 1603 determines the target surgical method for the target patient's brain hemorrhage based on the preoperative brain imaging data and the type of brain hemorrhage.

[0177] In some embodiments of this specification, the identification module may be specifically used to: use a target segmentation and identification model to segment and identify brain organ tissues and identify the type of cerebral hemorrhage in the preoperative brain image data, so as to obtain segmented and identified brain image data and the type of cerebral hemorrhage of the target object.

[0178] In some embodiments of this specification, the determining module may be specifically used to: acquire multiple surgical methods for cerebral hemorrhage; input various surgical methods for cerebral hemorrhage, the preoperative brain imaging data, and the type of cerebral hemorrhage into a target surgical effect prediction model to obtain surgical effect indicators corresponding to the various surgical methods for cerebral hemorrhage; and determine the target surgical method for cerebral hemorrhage of the target object based on the surgical effect indicators corresponding to the various surgical methods for cerebral hemorrhage.

[0179] In some embodiments of this specification, the brain hemorrhage surgery planning device may further include a retrieval module, which is specifically used to: retrieve a virtual surgical instrument model corresponding to the target brain hemorrhage surgery method; send the segmented and identified brain image data and the virtual surgical instrument model to a virtual reality device; the virtual reality device is used to perform three-dimensional reconstruction based on the segmented and identified brain image data to obtain a brain tissue and organ model, and to perform surgical scene reconstruction based on the brain tissue and organ model and the virtual surgical instrument model to obtain a simulated surgical scene.

[0180] In some embodiments of this specification, the brain hemorrhage surgery planning device may further include a second determining module, which may be specifically used to: acquire user simulated surgical video data; retrieve surgical standard data corresponding to the target brain hemorrhage surgery method; and determine whether the current user surgical operation procedure conforms to the surgical standard based on the user simulated surgical video data and the surgical standard data corresponding to the target brain hemorrhage surgery method.

[0181] In some embodiments of this specification, the user-simulated surgical video data includes surgical procedure description voice data and surgical simulation operation image data; the second determining module may be specifically used to: determine whether the current surgical procedure conforms to the surgical procedure specification based on the surgical procedure description voice data; if the current surgical procedure conforms to the surgical procedure specification, determine whether the current surgical operation conforms to the surgical operation specification based on the surgical simulation operation image data; if the current surgical operation conforms to the surgical operation specification, determine that the current user's surgical operation procedure conforms to the surgical specification.

[0182] In some embodiments of this specification, the second determining module may also be specifically used to: generate a prompt message when it is determined that the current user's surgical procedure does not conform to the surgical standard; the prompt message is used to prompt the user for the correct surgical procedure.

[0183] In some embodiments of this specification, determining whether the current surgical operation conforms to the surgical operation specifications based on the surgical simulation operation image data may include: retrieving standard surgical posture data corresponding to the current surgical procedure; performing posture recognition on the surgical simulation operation image data to obtain user surgical operation posture data; matching the user surgical operation posture data with the standard surgical posture data; and, if the matching is successful, determining that the current surgical operation conforms to the surgical operation specifications.

[0184] In some embodiments of this specification, the brain hemorrhage surgery planning device may further include an update module, which is specifically used to: send user simulated surgery video data to the virtual reality device; and the virtual reality device updates the simulated surgery scene based on the user simulated surgery video data.

[0185] This specification also provides a computer device, which can be found in the following description. Figure 17 The diagram shown illustrates the computer device structure based on the brain hemorrhage surgical planning method provided in the embodiments of this specification. Specifically, the computer device may include an input device 171, a processor 172, and a memory 173. The memory 173 stores processor-executable instructions. When the processor 172 executes the instructions, it implements the steps of the brain hemorrhage surgical planning method described in any of the above embodiments.

[0186] In this embodiment, the input device can specifically be one of the main devices for information exchange between the user and the computer system. The input device may include a keyboard, mouse, camera, scanner, light pen, handwriting input tablet, voice input device, etc.; the input device is used to input raw data and programs for processing these data into the computer. The input device can also receive data transmitted from other modules, units, and devices. The processor can be implemented in any suitable manner. For example, the processor can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, etc. The memory can specifically be a memory device used to store information in modern information technology. The memory can include multiple layers; in digital systems, anything that can store binary data can be considered memory; in integrated circuits, a circuit without physical form but with storage function is also called memory, such as RAM, FIFO, etc.; in a system, a storage device with physical form is also called memory, such as a memory stick, TF card, etc.

[0187] In this embodiment, the specific functions and effects implemented by the computer device can be explained in comparison with other embodiments, and will not be repeated here.

[0188] This specification also provides a computer storage medium based on a brain hemorrhage surgery planning method, wherein the computer storage medium stores computer program instructions that, when executed, implement the steps of the brain hemorrhage surgery planning method described in any of the above embodiments.

[0189] In this embodiment, the storage medium includes, but is not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), cache, hard disk drive (HDD), or memory card. The memory can be used to store computer program instructions. The network communication unit can be an interface configured according to standards specified in the communication protocol for network connection communication.

[0190] In this embodiment, the specific functions and effects implemented by the program instructions stored in the computer storage medium can be explained by comparison with other embodiments, and will not be repeated here.

[0191] This specification also provides a surgical planning system for cerebral hemorrhage. Please refer to... Figure 18 This diagram illustrates the structure of the brain hemorrhage surgical planning system as described in an embodiment of this specification. Figure 18 As shown, the brain hemorrhage surgical planning system 180 may include: an image storage device 181, an image processing device 182, and...

[0192] Image storage device 181 is used to store preoperative brain imaging data of the target subject.

[0193] The image processing device 182 is used to read preoperative brain imaging data of the target object from the image storage device; it is also used to identify the type of cerebral hemorrhage of the target object based on the preoperative brain imaging data; and it is also used to determine the target cerebral hemorrhage surgery method for the target object based on the preoperative brain imaging data and the type of cerebral hemorrhage.

[0194] In some embodiments of this specification, the image processing device 182 may be specifically used to: use a target segmentation and recognition model to perform brain organ and tissue segmentation and brain hemorrhage type recognition on the preoperative brain image data, so as to obtain segmented and recognized brain image data and the brain hemorrhage type of the target object.

[0195] In some embodiments of this specification, the image processing device 182 may be specifically used to: acquire multiple surgical methods for cerebral hemorrhage; input various surgical methods for cerebral hemorrhage, the preoperative brain imaging data, and the type of cerebral hemorrhage into a target surgical effect prediction model to obtain surgical effect indicators corresponding to the various surgical methods for cerebral hemorrhage; and determine the target surgical method for cerebral hemorrhage of the target object based on the surgical effect indicators corresponding to the various surgical methods for cerebral hemorrhage.

[0196] In some embodiments of this specification, the brain hemorrhage surgery planning system 180 may further include: a virtual reality device 183.

[0197] The image processing device 181 is also used to retrieve the virtual surgical instrument model corresponding to the target brain hemorrhage surgery method, and send the segmented and identified brain image data and the virtual surgical instrument model to the virtual reality device 183.

[0198] The virtual reality device 183 can be used to perform three-dimensional reconstruction based on brain image data after segmentation and recognition to obtain a brain tissue and organ model, and can also be used to reconstruct a surgical scene based on the brain tissue and organ model and the virtual surgical instrument model to obtain a simulated surgical scene.

[0199] In some embodiments of this specification, the brain hemorrhage surgery planning system may further include: an image acquisition device 184. The image acquisition device 184 is used to acquire video data of a user's simulated surgery. The image acquisition device 184 may include a 3D camera such as a binocular camera. The image acquisition device 184 may also include a medical image acquisition device for acquiring preoperative brain imaging data.

[0200] The image storage device 181 can also be used to store surgical standard data corresponding to various cerebral hemorrhage surgical methods.

[0201] The image processing device 182 can also be used to retrieve surgical standard data corresponding to the target cerebral hemorrhage surgery method from the image storage device; and can also be used to determine whether the current user's surgical operation procedure conforms to the surgical standard based on the user's simulated surgical video data and the surgical standard data corresponding to the target cerebral hemorrhage surgery method.

[0202] In some embodiments of this specification, the image processing device 182 can also be used to send user simulated surgical video data to the virtual reality device 183. The virtual reality device 183 can update the simulated surgical scene based on the user simulated surgical video data.

[0203] In some embodiments of this specification, the brain hemorrhage surgery planning system 18 may further include a communication device 185. The communication device 185 is used to complete data transmission between the virtual reality device 183 and the image processing device 182.

[0204] In some embodiments of this specification, the user-simulated surgical video data may include surgical procedure description voice data and surgical simulation operation image data; the image processing device 182 may be specifically used to: determine whether the current surgical procedure conforms to the surgical procedure specification based on the surgical procedure description voice data; if the current surgical procedure conforms to the surgical procedure specification, determine whether the current surgical operation conforms to the surgical operation specification based on the surgical simulation operation image data; if the current surgical operation conforms to the surgical operation specification, determine that the current user's surgical operation procedure conforms to the surgical specification; if the current user's surgical operation procedure does not conform to the surgical specification, generate prompt information; the prompt information is used to prompt the user for the correct surgical operation procedure.

[0205] In some embodiments of this specification, the image processing device 182 may be specifically used to: retrieve standard surgical posture data corresponding to the current surgical procedure; perform posture recognition on the surgical simulation operation image data to obtain user surgical operation posture data; match the user surgical operation posture data with the standard surgical posture data; and, if the match is successful, determine that the current surgical operation conforms to the surgical operation specifications.

[0206] In some embodiments of this specification, the image processing device 182 may also be used to: send user simulated surgical video data to the virtual reality device; and the virtual reality device updates the simulated surgical scene based on the user simulated surgical video data.

[0207] Obviously, those skilled in the art will understand that the modules or steps of the embodiments described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the embodiments of this specification are not limited to any particular combination of hardware and software.

[0208] It should be understood that the above description is for illustrative purposes and not for limitation. Many embodiments and applications beyond the provided examples will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this specification should not be determined by reference to the above description, but rather by reference to the foregoing claims and the full scope of their equivalents.

[0209] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to the embodiments described herein by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

Claims

1. A surgical planning system for cerebral hemorrhage, characterized in that, include: Image storage device for storing preoperative brain imaging data of a target subject; An image processing device is configured to read preoperative brain imaging data of the target object from the image storage device; further configured to perform brain organ and tissue segmentation and brain hemorrhage type identification on the preoperative brain imaging data to obtain segmented and identified brain image data and the brain hemorrhage type of the target object; further configured to input various brain hemorrhage surgical methods, the preoperative brain imaging data, and the brain hemorrhage type into a target surgical effect prediction model to obtain surgical effect indicators corresponding to the various brain hemorrhage surgical methods, and determine the target brain hemorrhage surgical method for the target object based on the surgical effect indicators corresponding to the various brain hemorrhage surgical methods; the image processing device is also configured to retrieve a virtual surgical instrument model corresponding to the target brain hemorrhage surgical method in response to determining the target brain hemorrhage surgical method; A virtual reality device, wherein the virtual reality device is used to receive the segmented and recognized brain image data and the virtual surgical instrument model sent by the image processing device, so as to simulate the surgical scene corresponding to the target brain hemorrhage surgical method.

2. The surgical planning system for cerebral hemorrhage according to claim 1, characterized in that, The image processing device is specifically used for: The target segmentation and recognition model is used to segment and recognize brain organs and tissues and identify the type of cerebral hemorrhage in the preoperative brain imaging data, so as to obtain the segmented and recognized brain image data and the type of cerebral hemorrhage of the target object.

3. The surgical planning system for cerebral hemorrhage according to claim 1, characterized in that, The image processing device is also specifically used for: Obtain a variety of surgical methods for cerebral hemorrhage.

4. The intracranial hemorrhage surgical planning system according to claim 1, characterized in that, The virtual reality device is used to perform three-dimensional reconstruction based on the segmented and recognized brain image data to obtain a model of brain tissue and organs. It is also used to reconstruct a surgical scene based on the model of brain tissue and organs and the model of virtual surgical instruments to obtain a simulated surgical scene.

5. The surgical planning system for cerebral hemorrhage according to claim 4, characterized in that, Also includes: Image acquisition device, used to acquire video data of user simulated surgery; The image storage device is also used to store surgical standard data corresponding to various cerebral hemorrhage surgical methods; The image processing device is also used to retrieve surgical standard data corresponding to the target cerebral hemorrhage surgical procedure from the image storage device; and to determine whether the current user's surgical operation procedure conforms to the surgical standard based on the user's simulated surgical video data and the surgical standard data corresponding to the target cerebral hemorrhage surgical procedure.

6. The surgical planning system for cerebral hemorrhage according to claim 5, characterized in that, The user-simulated surgical video data includes audio data describing the surgical procedure and image data of the simulated surgical operation. The image processing device is specifically used for: Based on the surgical procedure description voice data, determine whether the current surgical procedure conforms to the surgical procedure specification; If the current surgical procedure is determined to comply with the surgical procedure specifications, the surgical operation image data is used to determine whether the current surgical operation complies with the surgical operation specifications. If the current surgical procedure is confirmed to comply with the surgical procedure guidelines, then the current user's surgical procedure process is confirmed to comply with the surgical guidelines. If it is determined that the current user's surgical procedure does not conform to surgical standards, a prompt message will be generated. The prompts are used to guide users through the correct surgical procedure.

7. The surgical planning system for cerebral hemorrhage according to claim 6, characterized in that, The image processing device is specifically used for: Retrieve standard surgical posture data corresponding to the current surgical procedure; The surgical simulation operation image data is subjected to posture recognition to obtain the user's surgical operation posture data; The user's surgical posture data is matched with the standard surgical posture data; If a match is successful, the current surgical procedure is confirmed to comply with the surgical procedure guidelines.

8. The surgical planning system for cerebral hemorrhage according to claim 5, characterized in that, The image processing device is also used for: The user's simulated surgical video data is sent to the virtual reality device; the virtual reality device updates the simulated surgical scene based on the user's simulated surgical video data.

9. A surgical planning method for cerebral hemorrhage, characterized in that, include: Obtain preoperative brain imaging data of the target subject; The preoperative brain imaging data is used to segment and identify brain organs and tissues and identify the type of brain hemorrhage, resulting in segmented and identified brain image data and the type of brain hemorrhage of the target object. The various surgical methods for cerebral hemorrhage, the preoperative brain imaging data, and the type of cerebral hemorrhage are input into the target surgical outcome prediction model to obtain the surgical outcome indicators corresponding to the various surgical methods for cerebral hemorrhage. Based on the surgical outcome indicators corresponding to the various surgical methods for cerebral hemorrhage, the target surgical method for cerebral hemorrhage of the target object is determined. In response to determining the target brain hemorrhage surgical method, a virtual surgical instrument model corresponding to the target brain hemorrhage surgical method is retrieved, and the segmented and identified brain image data and the virtual surgical instrument model are sent to a virtual reality device. The virtual reality device is used to receive the segmented and identified brain image data and the virtual surgical instrument model sent by the image processing device to simulate the surgical scene corresponding to the target brain hemorrhage surgical method.

10. A computer-readable storage medium storing computer instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the steps of the method of claim 9.

Images