Tumor imaging data processing method, device, electronic device and storage medium

Abstract

The present invention provides a method, apparatus, electronic device, and storage medium for processing tumor image data, comprising: obtaining a tumor image dataset of a target object, and determining target tumor boundary information based on the tumor image dataset; generating a tumor resection model corresponding to the target object based on the target tumor boundary information; wherein the tumor resection model includes multiple tumor resection sections, each used to represent an estimated resection position and / or estimated resection direction; and generating a tumor resection guidance image corresponding to the target object based on the tumor resection model. The present invention can provide tumor resection guidance images with higher accuracy and greater objectivity.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method, device, electronic device and storage medium for processing tumor image data. Background Art

[0002] With the development of computer-assisted technology and medical imaging, bone and soft tissue tumor specialists have gained a clearer understanding of bone tumor imaging. They can now preoperatively define tumor resection boundaries based on the tumor's biological characteristics and perform complex bone tumor resections according to preoperative plans. However, currently, patients' imaging data can only be displayed on smart devices (such as personal computers). Doctors customize tumor resection plans based on their clinical experience and imaging data, resulting in a high degree of subjectivity in tumor resection plans. Summary of the Invention

[0003] In view of this, an object of the present invention is to provide a method, device, electronic device and storage medium for processing tumor image data, which can provide tumor resection guidance images with higher accuracy and greater objectivity.

[0004] In a first aspect, an embodiment of the present invention provides a method for processing tumor image data, comprising: obtaining a tumor image dataset of a target object, and determining target tumor boundary information based on the tumor image dataset; generating a tumor resection model corresponding to the target object based on the target tumor boundary information; wherein the tumor resection model comprises multiple tumor resection sections, and the tumor resection sections are used to represent an estimated resection position and / or an estimated resection direction; and generating a tumor resection guidance image corresponding to the target object based on the tumor resection model.

[0005] In one embodiment, the step of generating a tumor resection model corresponding to the target object based on the target tumor boundary information includes: obtaining tumor category information corresponding to the target object, and determining the target resection distance corresponding to the tumor category information based on a preset tumor staging principle; wherein the preset tumor staging principle is used to characterize the mapping relationship between tumor category information and resection distance; based on the target tumor boundary information and the target resection distance, determining the target resection area and the estimated resection boundary information of the target resection area; and generating the tumor resection model corresponding to the target object based on the estimated resection boundary information.

[0006] In one embodiment, the step of determining the target resection area and the estimated resection boundary information of the target resection area based on the target tumor boundary information and the target resection distance includes: determining the initial resection area corresponding to the target object; for each pixel point in the initial resection area, calculating the first distance value between the pixel point and the target tumor boundary information, if the first distance value is less than or equal to the target resection distance, determining the pixel point as the target pixel point; based on each target pixel point, determining the target resection area and the estimated resection boundary information of the target resection area.

[0007] In one embodiment, the step of determining the target tumor boundary information based on the tumor image data set includes: extracting the initial tumor boundary information of each tumor image data in the tumor image data set through a pre-trained boundary extraction network; fusing the initial tumor boundary information corresponding to each tumor image data to obtain fused tumor boundary information, and determining the fused tumor boundary information with the largest area as the target tumor boundary information.

[0008] In one embodiment, the step of generating a tumor resection guidance image corresponding to the target object based on the tumor resection model includes: obtaining a preoperative image dataset of the target object; aligning the preoperative image dataset with the tumor resection guidance image to obtain a tumor resection guidance image corresponding to the target object, so that the surgical navigation device determines the actual resection position based on the tumor resection guidance image.

[0009] In one embodiment, after the step of generating a tumor resection guidance image corresponding to the target object based on the tumor resection model, the method further includes: obtaining a postoperative image dataset of the target object; aligning the postoperative image dataset with the tumor image dataset to obtain actual resection boundary information; and determining a risk assessment result based on the actual resection boundary information; wherein the risk assessment result includes risk points.

[0010] In one embodiment, the step of determining the risk assessment result based on the actual resection boundary information includes: for each boundary point in the actual resection boundary information, calculating a second distance value between the boundary point and the estimated resection boundary information; if the second distance value is greater than a preset distance threshold, determining that the boundary point is a risk point.

[0011] In a second aspect, an embodiment of the present invention further provides a device for processing tumor image data, comprising: a tumor boundary determination module, configured to obtain a tumor image data set of a target object, and determine the target tumor boundary information based on the tumor image data set; a model generation module, configured to generate a tumor resection model corresponding to the target object according to the target tumor boundary information; wherein the tumor resection model comprises a plurality of tumor resection sections, and the tumor resection sections are used to represent an estimated resection position and / or an estimated resection direction; and a guidance image generation module, configured to generate a tumor resection guidance image corresponding to the target object based on the tumor resection model.

[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement any one of the methods provided in the first aspect.

[0013] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.

[0014] The embodiments of the present invention provide a method, device, electronic device, and storage medium for processing tumor image data. The method first acquires a tumor image dataset of a target object and determines the target tumor boundary information based on the tumor image dataset. Then, based on the target tumor boundary information, a tumor resection model corresponding to the target object is generated (including multiple tumor resection sections, which are used to characterize the estimated resection position and / or estimated resection direction). Finally, based on the tumor resection model, a tumor resection guidance image corresponding to the target object is generated. The above method determines the target tumor boundary information based on the tumor image dataset and generates a tumor resection model based on the target tumor boundary information. Based on the tumor resection model, a tumor resection guidance image with higher accuracy and greater objectivity can be obtained.

[0015] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A schematic flow chart of a method for processing tumor image data provided by an embodiment of the present invention;

[0019] Figure 2 A functional block diagram of a method for processing tumor image data provided by an embodiment of the present invention;

[0020] Figure 3 A schematic structural diagram of a device for processing tumor image data provided by an embodiment of the present invention;

[0021] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] At present, existing technologies usually allow doctors to customize corresponding tumor resection plans based on their own clinical experience and imaging data. There are at least the following problems: (1) It is impossible to systematically compare and analyze various imaging data of bone tumor patients, and the preoperative planning plan formulated by surgeons only remains in their own minds; (2) There is a lack of visual guidance during the operation, and surgeons can only perform tumor resection according to the preoperative plan based on their own clinical experience; (3) There is a lack of objective evaluation after bone tumor resection, which is not conducive to surgeons accurately grasping the patient's surgical completion status and formulating personalized follow-up arrangements for them.

[0024] Based on this, the present invention provides a method, device, electronic device and storage medium for processing tumor image data, which can provide tumor resection guidance images with higher accuracy and greater objectivity.

[0025] To facilitate understanding of this embodiment, a method for processing tumor image data disclosed in an embodiment of the present invention is first described in detail. Figure 1FIG. 1 is a flow chart of a method for processing tumor image data, which can be applied to electronic devices such as computers. The method mainly includes the following steps S102 to S106:

[0026] Step S102: Obtain a tumor image dataset of the target subject and determine target tumor boundary information based on the tumor image dataset. The target subject is the patient, and the tumor image dataset is the modal image data of the patient's lesion site. This can include X-ray DR (digital radiography), enhanced CT (computed tomography), enhanced MR (magnetic resonance imaging), ECT (emission computed tomography), PE-TCT (positron emission tomography), etc. of the patient's lesion site. The target tumor boundary information can be the three-dimensional boundary of the tumor. In one embodiment, the patient's tumor image dataset can be stored in a computer storage module, and the user can read the required tumor image data from the computer storage module to determine the target tumor boundary information using image processing algorithms or manual delineation.

[0027] Step S104 generates a tumor resection model corresponding to the target object based on the target tumor boundary information. The tumor resection model includes multiple tumor resection sections, which are used to represent the estimated resection location and / or estimated resection direction. In one embodiment, the corresponding target resection region and its estimated resection boundary information can be determined based on the target tumor boundary information. The tumor resection model can be generated by adding the tumor resection sections to the estimated resection boundary.

[0028] Step S106: Generate a tumor resection guidance image corresponding to the target object based on the tumor resection model. The tumor resection guidance image, also known as a tumor resection plan, is used to guide the user in performing the tumor resection operation. In one embodiment, the patient's image dataset can be re-collected before surgery. By registering and aligning the tumor resection model with the image dataset, a tumor resection guidance image can be generated. The tumor resection guidance image then guides the user in performing the tumor resection operation, using the resection location and direction represented by the tumor resection guidance image.

[0029] The method for processing tumor image data provided by an embodiment of the present invention determines the boundary information of the target tumor based on the tumor image data set, and generates a tumor resection model based on the target tumor boundary information. Based on the tumor resection model, a tumor resection guidance image with higher accuracy and greater objectivity can be obtained.

[0030] In one embodiment, the method for processing tumor image data provided by an embodiment of the present invention is applied to a tumor image data processing system, which includes a computer acquisition and storage unit, a computer data analysis unit, a computer data calculation unit, a computer navigation unit, and a computer comprehensive evaluation unit. Among them, the computer acquisition and storage unit is used to store tumor image data sets such as X-ray DR plain films, enhanced CT, enhanced MR, ECT, PETCT, etc. of the patient's lesion site for subsequent surgical planning and evaluation. The computer data analysis unit is used to provide the patient's tumor image data set, allowing the user to compare and analyze the performance characteristics of the tumor in different images. The computer data calculation unit is used to determine the tumor resection model, thereby providing the clinic with a preoperative tumor resection plan with precise surgical tumor sections. It is also used to align the postoperative image data set with the original tumor image data set after bone tumor resection to intuitively and accurately display the actual surgical resection effect relative to the original preoperative plan. The computer navigation unit is used to perform bone tumor resection according to the preoperative tumor resection plan under image guidance. The computer comprehensive evaluation unit is used to statistically analyze the error between the actual resection boundary information and the estimated resection boundary information, and to propose possible risk points. For problems with insufficient surgical quality, the unit analyzes the causes to the patients and formulates subsequent treatment follow-up plans for them.

[0031] Based on the above embodiment, the embodiment of the present invention provides an implementation of step S102. When performing the step of determining target tumor boundary information based on the tumor image dataset, refer to the following (1) to (2):

[0032] (1) Extracting initial tumor boundary information for each tumor image data in the tumor image dataset using a pre-trained boundary extraction network. In one embodiment, the neural network can be pre-trained, and the training set includes tumor image data and tumor boundary labels, so that the neural network can be trained using the training set to obtain a boundary extraction network with higher accuracy. In practical applications, by inputting each tumor image data in the tumor image dataset into the boundary extraction network, the boundary extraction network can output the corresponding initial tumor boundary information.

[0033] (2) The initial tumor boundary information corresponding to each tumor image data is fused to obtain fused tumor boundary information, and the fused tumor boundary information with the largest area is determined as the target tumor boundary information. In practical applications, considering that the initial tumor boundary information determined by different image data may have slight differences, the initial tumor boundary information corresponding to each tumor image data can be fused, and the tumor boundary information with the largest area is selected as the target tumor boundary information.

[0034] In another embodiment, the target tumor boundary can also be manually drawn. Optionally, in the computer data analysis unit, the user draws the tumor boundary layer by layer in the coronal, axial, and sagittal planes of the lesion image, and uses the tumor range drawn from the CT image and the MR image as the three-dimensional tumor boundary.

[0035] Regarding the aforementioned step S104, the embodiment of the present invention provides an implementation method for generating a tumor resection model corresponding to the target object based on the target tumor boundary information, as shown in steps 1 to 3 below:

[0036] Step 1: Obtain the tumor category information corresponding to the target object and determine the target resection distance corresponding to the tumor category information based on the preset tumor staging principle. The preset tumor staging principle (abbreviated as the surgical staging principle for bone and soft tissue tumors) is used to characterize the mapping relationship between tumor category information and resection distance. The tumor category information is used to characterize the severity of the tumor, such as benign or malignant tumors. In one embodiment, the target resection distance ds between the estimated resection boundary information and the target tumor boundary information can be set based on the surgical staging principle for bone and soft tissue tumors.

[0037] Step 2: Based on the target tumor boundary information and the target resection distance, determine the target resection area and the estimated resection boundary information of the target resection area. In one embodiment, see steps 2.1 to 2.3 below:

[0038] Step 2.1: Determine the initial resection region corresponding to the target object. In one embodiment, the anisotropic distance transform algorithm of the computer data calculation unit can be used to obtain a three-dimensional distance image Dt of the tumor range, which is also the initial resection region.

[0039] In step 2.2, for each pixel in the initial resection area, a first distance value is calculated between the pixel and the target tumor boundary information. If the first distance value is less than or equal to the target resection distance, the pixel is determined as the target pixel. In one embodiment, a three-dimensional region Dc located within the three-dimensional distance image Dt and less than the target resection distance ds can be further determined. This three-dimensional region Dc is also the target resection area, and the edge of this three-dimensional region Dc is the three-dimensional surgical resection boundary of the tumor that must be resected during surgery.

[0040] In step 2.3, based on each target pixel, determine the target resection area and the estimated resection boundary information of the target resection area. It can be understood that the area where each target pixel is located is the target resection area to be resected. By connecting the target pixels on the edge of the target resection area, the estimated resection boundary information can be obtained.

[0041] Step 3: Generate a tumor resection model corresponding to the target object based on the estimated resection boundary information. In one embodiment, the user can manually place an appropriate number of tumor resection planes outside the generated estimated resection boundary information based on the importance of different anatomical structures of the tumor, thereby providing a preoperative tumor resection plan with precise surgical resection planes.

[0042] To facilitate understanding of the aforementioned step S106, an embodiment of the present invention further provides an implementation method for generating a tumor resection guidance image corresponding to a target object based on a tumor resection model, as shown in steps a to b below:

[0043] Step a: Acquire a pre-operative image dataset of the target object. In one embodiment, before performing the surgery, an image dataset of the target object may be acquired again.

[0044] Step b: performing registration and alignment processing on the preoperative image dataset and the tumor resection guidance image to obtain the tumor resection guidance image corresponding to the target object, so that the surgical navigation device can determine the actual resection position based on the tumor resection guidance image.

[0045] Furthermore, considering the lack of objective evaluation after bone tumor resection in the prior art, an embodiment of the present invention provides a risk assessment method, specifically: (1) obtaining a postoperative image dataset of the target object, optionally, using a CT device to scan the surgical specimen to obtain a CT image of the specimen, and storing the CT image in a computer storage unit; (2) performing registration and alignment processing on the postoperative image dataset and the tumor image dataset to obtain actual resection boundary information, optionally, performing registration and alignment processing on the specimen CT image and the original CT image in the preoperative plan in the computer data analysis unit to obtain actual resection boundary information; (3) determining a risk assessment result based on the actual resection boundary information; wherein the risk assessment result includes a risk point. In one embodiment, for each boundary point in the actual resection boundary information, a second distance value between the boundary point and the estimated resection boundary information is calculated. If the second distance value is greater than a preset distance threshold, the boundary point is determined to be a risk point, thereby being able to intuitively and accurately display the actual surgical resection effect relative to the original preoperative plan.

[0046] After bone tumor resection, the surgical specimen is scanned using a CT device to obtain a CT image of the specimen. The specimen CT data is then stored in the device of the present invention via 1. a computer storage backup acquisition module. The specimen CT image is then registered and aligned with the original CT image in the preoperative plan in the computer data analysis module. Finally, the device of the present invention can intuitively and accurately display the actual surgical resection effect relative to the original preoperative plan.

[0047] To facilitate understanding of the aforementioned embodiments, the present invention provides an application example of a method for processing tumor image data, see Figure 2 A functional block diagram of a method for processing tumor image data is shown. Figure 2 Shows:

[0048] (1) First, multimodal imaging data of bone tumor patients is collected before surgery. The doctor then analyzes the morphological manifestations of the tumor in various modal imaging data using a computer data analysis unit and depicts the tumor range separately. The tumor areas depicted in the multimodal imaging data are then merged to determine the maximum boundary of the tumor. The minimum safe distance between the resection boundary and the tumor boundary (i.e., the target resection distance) is then set based on the surgical staging rules for the tumor. The three-dimensional area to be resected during surgery is then determined using a three-dimensional anisotropic distance transform algorithm. Finally, the computer analysis unit manually designs an appropriate number of tumor sections based on the importance of the anatomical structure, and forms a visual digital multidimensional image for user reference. This can even provide remote technical support and technical consultation to hospitals with relatively backward bone tumor expertise.

[0049] (2) The patient's multimodal imaging data and the designed preoperative tumor resection plan are imported into a computer navigation unit or a robot or other equipment to guide the user to accurately perform the bone tumor resection surgery according to the preoperatively designed resection plan during the operation.

[0050] (3) After surgery, the CT image of the tumor specimen is scanned and then input back into the computer data analysis unit. Finally, the specimen CT image is aligned with the original CT image of the patient in the preoperative planning.

[0051] (IV) Accurately calculate surgical errors in bone tumor resection surgery in the computer comprehensive evaluation unit and analyze possible risk points after bone tumor resection, thereby customizing personalized postoperative rehabilitation treatment plans and follow-up plans for patients

[0052] In summary, the method for processing tumor image data provided by the embodiments of the present invention has at least the following characteristics:

[0053] (1) Provide an accurate digital preoperative planning platform for designing professional and accurate preoperative planning and intraoperative guidance plans;

[0054] (2) By accurately registering the digital images of postoperative specimens with the preoperative plan, doctors can accurately analyze the completion accuracy of bone tumor surgery and point out the risk points after the surgery is completed, which helps surgeons accurately and objectively grasp the results of the patient's surgical treatment and avoid blind optimism;

[0055] (3) It can provide technical support to bone and soft tissue tumor specialists in various regions, thereby helping to narrow the professional and technical gap between different hospitals in remote areas and different cities, and ultimately enable bone tumor patients in various regions to enjoy high-level medical resources.

[0056] Regarding the method for processing tumor image data provided in the above embodiment, the present invention provides a device for processing tumor image data, see Figure 3 The schematic diagram of the structure of a tumor image data processing device shown in FIG. 1 mainly includes the following parts:

[0057] A tumor boundary determination module 302 is configured to obtain a tumor image dataset of a target object and determine target tumor boundary information based on the tumor image dataset;

[0058] The model generation module 304 is configured to generate a tumor resection model corresponding to the target object based on the target tumor boundary information; wherein the tumor resection model includes multiple tumor resection sections, and the tumor resection sections are used to represent the estimated resection position and / or estimated resection direction;

[0059] The guidance image generation module 306 is configured to generate a tumor resection guidance image corresponding to the target object based on the tumor resection model.

[0060] The tumor image data processing device provided in an embodiment of the present invention determines the target tumor boundary information based on the tumor image data set, and generates a tumor resection model based on the target tumor boundary information. Based on the tumor resection model, a tumor resection guidance image with higher accuracy and greater objectivity can be obtained.

[0061] In one embodiment, the model generation module 304 is further used to: obtain tumor category information corresponding to the target object, and determine the target resection distance corresponding to the tumor category information based on a preset tumor staging principle; wherein the preset tumor staging principle is used to characterize the mapping relationship between the tumor category information and the resection distance; based on the target tumor boundary information and the target resection distance, determine the target resection area and the estimated resection boundary information of the target resection area; and generate a tumor resection model corresponding to the target object based on the estimated resection boundary information.

[0062] In one embodiment, the model generation module 304 is further used to: determine an initial resection area corresponding to the target object; for each pixel point in the initial resection area, calculate a first distance value between the pixel point and the target tumor boundary information; if the first distance value is less than or equal to the target resection distance, determine the pixel point as the target pixel point; based on each target pixel point, determine the target resection area and the estimated resection boundary information of the target resection area.

[0063] In one embodiment, the tumor boundary determination module 302 is further used to: extract the initial tumor boundary information of each tumor image data in the tumor image data set through a pre-trained boundary extraction network; fuse the initial tumor boundary information corresponding to each tumor image data to obtain fused tumor boundary information, and determine the fused tumor boundary information with the largest area as the target tumor boundary information.

[0064] In one embodiment, the guidance image generation module 306 is further used to: obtain a preoperative image dataset of the target object; align the preoperative image dataset with the tumor resection guidance image to obtain a tumor resection guidance image corresponding to the target object, so that the surgical navigation device determines the actual resection position based on the tumor resection guidance image.

[0065] In one embodiment, the above-mentioned device also includes a risk assessment module, which is used to: obtain a postoperative imaging dataset of the target object; align the postoperative imaging dataset with the tumor imaging dataset to obtain actual resection boundary information; determine a risk assessment result based on the actual resection boundary information; wherein the risk assessment result includes risk points.

[0066] In one embodiment, the risk assessment module is further used to: for each boundary point in the actual resection boundary information, calculate a second distance value between the boundary point and the estimated resection boundary information; if the second distance value is greater than a preset distance threshold, determine that the boundary point is a risk point.

[0067] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those in the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding content in the aforementioned method embodiment.

[0068] An embodiment of the present invention provides an electronic device. Specifically, the electronic device includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0069] Figure 4 This is a structural diagram of an electronic device provided in an embodiment of the present invention. The electronic device 100 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43. The processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0070] The memory 41 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage. The system network element communicates with at least one other network element via at least one communication interface 43 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0071] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0072] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0073] Processor 40 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in processor 40. The above processor 40 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or the like. The storage medium is located in the memory 41 , and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0074] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the previous method embodiment. The specific implementation can be referred to the previous method embodiment and will not be repeated here.

[0075] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0076] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for processing tumor image data, characterized in that: include: Acquiring a tumor image dataset of a target object, and determining target tumor boundary information based on the tumor image dataset; Generate a tumor resection model corresponding to the target object based on the target tumor boundary information; wherein the tumor resection model includes multiple tumor resection sections, and the tumor resection sections are used to represent the estimated resection position and / or the estimated resection direction; generating a tumor resection guidance image corresponding to the target object based on the tumor resection model; The step of generating a tumor resection model corresponding to the target object according to the target tumor boundary information includes: Obtaining tumor category information corresponding to the target object, and determining a target resection distance corresponding to the tumor category information according to a preset tumor staging principle; wherein the preset tumor staging principle is used to characterize a mapping relationship between the tumor category information and the resection distance; Determining a target resection area and estimated resection boundary information of the target resection area based on the target tumor boundary information and the target resection distance, including: determining an initial resection area corresponding to the target object; for each pixel point in the initial resection area, calculating a first distance value between the pixel point and the target tumor boundary information, and if the first distance value is less than or equal to the target resection distance, determining the pixel point as a target pixel point; determining a target resection area and estimated resection boundary information of the target resection area based on each target pixel point; A tumor resection model corresponding to the target object is generated based on the estimated resection boundary information.

2. The method according to claim 1, characterized in that The step of determining target tumor boundary information based on the tumor image dataset includes: extracting initial tumor boundary information of each tumor image data in the tumor image dataset through a pre-trained boundary extraction network; The initial tumor boundary information corresponding to each tumor image data is fused to obtain fused tumor boundary information, and the fused tumor boundary information with the largest area is determined as the target tumor boundary information.

3. The method according to claim 1, characterized in that The step of generating a tumor resection guidance image corresponding to the target object based on the tumor resection model includes: Acquiring a preoperative imaging dataset of the target object; The preoperative image dataset is registered and aligned with the tumor resection guidance image to obtain a tumor resection guidance image corresponding to the target object, so that a surgical navigation device determines an actual resection position based on the tumor resection guidance image.

4. The method according to claim 1, wherein After the step of generating a tumor resection guidance image corresponding to the target object based on the tumor resection model, the method further includes: Acquiring a postoperative imaging dataset of the target object; Performing registration and alignment processing on the postoperative image dataset and the tumor image dataset to obtain actual resection boundary information; A risk assessment result is determined based on the actual resection boundary information; wherein the risk assessment result includes risk points.

5. The method according to claim 4, characterized in that The step of determining the risk assessment result based on the actual resection boundary information includes: For each boundary point in the actual resection boundary information, a second distance value between the boundary point and the estimated resection boundary information is calculated. If the second distance value is greater than a preset distance threshold, the boundary point is determined to be a risk point.

6. A device for processing tumor image data, characterized in that: include: a tumor boundary determination module, configured to obtain a tumor image dataset of a target object and determine target tumor boundary information based on the tumor image dataset; a model generation module, configured to generate a tumor resection model corresponding to the target object based on the target tumor boundary information; wherein the tumor resection model includes a plurality of tumor resection sections, each of which is used to represent an estimated resection position and / or an estimated resection direction; a guidance image generation module, configured to generate a tumor resection guidance image corresponding to the target object based on the tumor resection model; The model generation module is specifically used for: Obtaining tumor category information corresponding to the target object, and determining a target resection distance corresponding to the tumor category information according to a preset tumor staging principle; wherein the preset tumor staging principle is used to characterize a mapping relationship between the tumor category information and the resection distance; Determining a target resection area and estimated resection boundary information of the target resection area based on the target tumor boundary information and the target resection distance, including: determining an initial resection area corresponding to the target object; for each pixel point in the initial resection area, calculating a first distance value between the pixel point and the target tumor boundary information, and if the first distance value is less than or equal to the target resection distance, determining the pixel point as a target pixel point; determining a target resection area and estimated resection boundary information of the target resection area based on each target pixel point; A tumor resection model corresponding to the target object is generated based on the estimated resection boundary information.

7. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 5.

Images