Method of processing ct data and processing device

Abstract

This invention provides a method and apparatus for processing CT data. The method includes: for each target structure of a target object, determining the corresponding intraoperative structural data of the target structure based on the intraoperative cone-beam CT three-dimensional data of the target object; generating two-dimensional representation data of the target structure corresponding to the X-ray imaging viewpoint based on the intraoperative structural data of the target structure; performing two-dimensional registration processing between the two-dimensional representation data of the target structure and the real-time acquired X-ray perspective view of the target object to determine the two-dimensional deformation field used for two-dimensional overlay; and overlaying the two-dimensional representation data of the target structure and the X-ray perspective view based on the two-dimensional deformation field to generate and display the overlaid perspective view. This invention can improve the generation efficiency of the overlaid perspective view and meet the practical processing requirements of high real-time performance.

Description

Technical Field

[0001] This invention relates to the field of medical image processing, and more specifically to a method for processing CT data and a device for processing CT data. Background Technology

[0002] A bronchoscope can be inserted into the body of a subject to observe or perform procedures on parts of the lungs, bronchi, etc. For example, a bronchoscope can be used for procedures such as biopsy sampling and ablation therapy.

[0003] In existing technologies, the head of a bronchoscope equipped with an electromagnetic device is typically positioned electromagnetically to guide the patient's path based on preoperative CT three-dimensional data (CT stands for Computed Tomography). However, electromagnetic positioning is susceptible to electromagnetic interference from metal instruments or other electrical appliances, which can affect its accuracy. Furthermore, using preoperative CT three-dimensional data for intraoperative observation or manipulation of the subject can easily lead to mismatches between the preoperative CT data and the actual condition of the subject during surgery. Therefore, a more accurate method for processing CT three-dimensional data is urgently needed. Summary of the Invention

[0004] The present invention was proposed in view of the above-mentioned problems. The present invention provides a method for processing CT data and a device for processing CT data.

[0005] According to one aspect of the present invention, a method for processing CT data is provided. The method includes: for each of a plurality of target structures of a target object, determining the intraoperative structural data of the target structure corresponding to the target structure based on the intraoperative cone-beam CT three-dimensional data of the target object, wherein the plurality of target structures include anatomical structures and / or medical device structures, and the intraoperative structural data of the target structure corresponding to the target structure is mask data for representing the spatial position of the target structure in the intraoperative cone-beam CT three-dimensional data, or the three-dimensional data corresponding to the target structure in the intraoperative cone-beam CT three-dimensional data; generating two-dimensional representation data of the target structure corresponding to the X-ray imaging view based on the intraoperative structural data of the target structure; performing two-dimensional registration processing on the two-dimensional representation data of the target structure and the real-time acquired X-ray perspective view of the target object to determine a two-dimensional deformation field for two-dimensional overlay; and performing overlay processing on the two-dimensional representation data of the target structure and the X-ray perspective view based on the two-dimensional deformation field to generate and display the overlay perspective view.

[0006] For example, determining the intraoperative structural data of the target structure based on the intraoperative cone-beam CT three-dimensional data of the target object includes: obtaining the target structure mask data corresponding to the target structure through the target detection model corresponding to the target structure based on the intraoperative cone-beam CT three-dimensional data of the target object; and determining the intraoperative structural data of the target structure based on the target structure mask data.

[0007] For example, based on the intraoperative cone-beam computed tomography (CBCT) 3D data of the target object, the target structure mask data corresponding to the target structure is obtained through the target detection model corresponding to the target structure. This includes: inputting the processed intraoperative CBCT 3D data into the target detection model corresponding to the target structure to obtain the target structure mask data corresponding to the target structure. The processed intraoperative CBCT 3D data is obtained by 3D noise reduction and / or contrast enhancement processing based on the intraoperative CBCT 3D data.

[0008] For example, the two-dimensional representation data of the target structure is generated by one of the following methods: perspective projection of the intraoperative structural data of the target structure; maximum intensity projection of the intraoperative structural data of the target structure; or virtual X-ray projection of the intraoperative structural data of the target structure based on imaging geometry parameters.

[0009] For example, the two-dimensional registration process includes: two-dimensional rigid registration based on rigid transformation, and two-dimensional non-rigid registration based on rigid transformation.

[0010] For example, in two-dimensional rigid registration processing, different target structures have their own registration weights, which are related to at least one of the following: the distance between the target structure and the medical device in the X-ray fluoroscopy image; the anatomical category or structural category of the target structure.

[0011] For example, in two-dimensional non-rigid registration processing, the anatomical substructures in the target structure are assigned corresponding substructure weights, which are related to the substructure category of the anatomical substructure.

[0012] For example, the two-dimensional registration process is completed based on a single X-ray fluoroscopic view.

[0013] For example, the processing method further includes: displaying target data, wherein the target data includes at least one of intraoperative cone-beam CT three-dimensional data, intraoperative structural data of the target structure, and X-ray perspective view; after the acquisition angle of the C-arm of the C-arm cone-beam CT imaging device used to acquire intraoperative cone-beam CT three-dimensional data and X-ray perspective view is adjusted, the superimposed perspective view and target data are adjusted accordingly and displayed based on the adjusted acquisition angle.

[0014] For example, the processing method further includes: determining a main region in the intraoperative cone-beam CT three-dimensional data, wherein the main region includes a medical device region and a tracheal region; determining a first position in the main region that is closest to the target lesion selected by the user; determining a second position in the medical device region that is closest to the first position; sequentially connecting the second position, the first position and the target lesion to obtain a target path; and overlaying and displaying the target path with the intraoperative cone-beam CT three-dimensional data.

[0015] According to another aspect of the present invention, a CT data processing apparatus is also provided, the CT data processing apparatus including a memory and a processor, wherein the memory is used to store a computer program; and the processor is used to execute the computer program to implement the above-described CT data processing method.

[0016] According to the above-described scheme of the present invention, for each of the multiple target structures of a target object, intraoperative structural data of the target structure can be determined based on the intraoperative cone-beam CT three-dimensional data of the target object. Then, based on the intraoperative structural data of the target structure, two-dimensional representation data of the target structure corresponding to the X-ray imaging viewpoint is generated. Next, the two-dimensional representation data of the target structure is registered with the real-time acquired X-ray perspective view of the target object to determine the two-dimensional deformation field used for two-dimensional overlay. Finally, based on the two-dimensional deformation field, the two-dimensional representation data of the target structure is overlaid with the X-ray perspective view to generate and display the overlaid perspective view. The above scheme has relatively low difficulty in performing two-dimensional registration based on the intraoperative structural data of the target structure, and using two-dimensional registration also helps to improve the efficiency of the registration process, thereby improving the generation efficiency of the overlaid perspective view, which can meet the actual processing requirements of high real-time performance. Attached Figure Description

[0017] The above and other objects, features, and advantages of the present invention will become more apparent from the more detailed description of the embodiments of the invention in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same parts or steps.

[0018] Figure 1 A schematic flowchart of a method for processing CT data according to an embodiment of the present invention is shown;

[0019] Figure 2 A schematic flowchart of a method for processing CT data according to an embodiment of the present invention is shown;

[0020] Figure 3 A schematic flowchart of a method for processing CT data according to an embodiment of the present invention is shown;

[0021] Figure 4 A schematic flowchart of a method for processing CT data according to an embodiment of the present invention is shown;

[0022] Figure 5 A schematic diagram of an overlay perspective view according to an embodiment of the present invention is shown;

[0023] Figure 6 A schematic block diagram of a CT data processing apparatus according to an embodiment of the present invention is shown. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of the present invention, and not all of the embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of the present invention.

[0025] To at least partially solve the above problems, embodiments of the present invention provide a method for processing CT data. Figure 1 A schematic flowchart illustrating a method for processing CT data according to an embodiment of the present invention is shown. Figure 1 As shown, the method may include steps S110 to S140.

[0026] In step S110, for each of the multiple target structures of the target object, the intraoperative structural data of the target structure corresponding to that target structure is determined based on the intraoperative cone-beam CT three-dimensional data of the target object.

[0027] Multiple target structures include anatomical structures and / or medical device structures.

[0028] The target subject can be any subject requiring observation or treatment via bronchoscopy. The anatomical structures of the target subject can be observable structures present in the subject preoperatively. For example, this could include the subject's anatomy, pathological structures, or medical implants within the subject. The target subject's anatomy can include innate structures found in healthy individuals, such as the airway, blood vessels, lung parenchyma, and bones. The target subject's pathological structures can include acquired structures found in diseased individuals, such as diseased tissues and organs. Medical implants within the target subject can be medical devices already implanted, such as pulmonary valve stents, lung fixation titanium screws, or artificial lungs.

[0029] Medical device structures can be structures that need to be inserted into the body of a target, such as bronchoscopes, instruments and tools (such as biopsy forceps, ablation probes, laser fibers, etc.).

[0030] In some embodiments, intraoperative cone-beam computed tomography (CBCT) 3D data may be CT 3D data directly acquired during bronchoscopy using an intraoperative CT device. In some alternative embodiments, intraoperative CBCT 3D data may be obtained through data enhancement processing of the directly acquired CT 3D data. Specifically, data enhancement processing may include 3D noise reduction processing, contrast enhancement processing, and other processing to enhance the display effect of the data.

[0031] Intraoperative CT equipment can be, for example, a C-arm CT (or C Arm CT) device, a sliding rail CT device, or other equipment that can acquire cone-beam CT three-dimensional data.

[0032] The intraoperative structural data corresponding to the target structure is either mask data representing the spatial position of the target structure in the intraoperative cone-beam CT 3D data, or the corresponding 3D data of the target structure in the intraoperative cone-beam CT 3D data. It is understood that the intraoperative structural data of the target structure in this embodiment is not used to estimate the pose of the imaging device, but rather for structure-aware driven perspective enhancement display. Related schemes in the art that only utilize a portion of the 3D data to estimate the pose of the imaging device are irrelevant to the embodiments of this application.

[0033] In one example, the intraoperative structural data of the target structure is the three-dimensional data of the target structure in the intraoperative cone-beam CT three-dimensional data. In other words, the intraoperative structural data of the target structure may include the voxel values ​​corresponding to some voxels in the intraoperative cone-beam CT three-dimensional data. In another example, the intraoperative structural data of the target structure may also be mask data used to represent the position of the target structure in the intraoperative cone-beam CT three-dimensional data, which may be three-dimensional mask data.

[0034] In some embodiments, image processing algorithms or machine learning models can be used to determine the intraoperative structural data of each target structure in the intraoperative cone-beam CT 3D data. Other regions in the intraoperative cone-beam CT 3D data are then filtered out.

[0035] In some other embodiments, intraoperative structural data of the target structure can be determined based on the user's manual segmentation of intraoperative cone-beam CT 3D data.

[0036] In step S120, based on the intraoperative structural data of the target structure, two-dimensional representation data of the target structure corresponding to the X-ray imaging viewpoint is generated.

[0037] The intraoperative structural data of the target structure may include the bronchial tree. The intraoperative structural data of the target structure can be converted into a two-dimensional representation of the target structure using a two-dimensional mapping algorithm or model.

[0038] In step S130, the two-dimensional representation data of the target structure is registered with the real-time acquired X-ray perspective view of the target object to determine the two-dimensional deformation field for two-dimensional superposition.

[0039] X-ray fluoroscopy can be obtained using intraoperative CT equipment. For example, a real-time fluoroscopic video of the target object can be acquired via X-ray, and the current frame image from that video can then be used as the aforementioned X-ray fluoroscopy. The X-ray imaging angle is the same as the X-ray imaging angle. The aforementioned X-ray fluoroscopy can display dense areas within the target object, such as the area where the bronchoscope is located or the area containing bones. The location of the bronchoscope can be determined in real time using the X-ray fluoroscopy.

[0040] Two-dimensional registration processing can be performed on the two-dimensional representation data of the target structure and the X-ray perspective view to obtain a two-dimensional deformation field. The above two-dimensional registration processing can be rigid registration processing and / or non-rigid registration processing.

[0041] In one example, both the two-dimensional representation data of the target structure and the X-ray perspective view can include dense structures such as bronchoscopes and bones, so registration can be performed based on the regions where the above dense structures are located.

[0042] In a specific example, the two-dimensional representation of the target structure can be a binary image. Since the pixel value range of a binary image is smaller, the registration of the two-dimensional representation of the target structure with an X-ray perspective view is easier, thereby improving the efficiency of two-dimensional registration processing.

[0043] In step S140, based on the two-dimensional deformation field, the two-dimensional representation data of the target structure is superimposed with the X-ray perspective view to generate and display the superimposed perspective view.

[0044] The two-dimensional representation data of the target structure and the X-ray perspective view are superimposed based on the two-dimensional deformation field to obtain a superimposed perspective view. For example, the two-dimensional representation data of the target structure can be transformed based on the two-dimensional deformation field and then superimposed onto the X-ray perspective view. Alternatively, the X-ray perspective view can be transformed based on the two-dimensional deformation field and then superimposed onto the two-dimensional representation data of the target structure.

[0045] Optionally, the two-dimensional representation data of the target structure and the X-ray perspective view can be directly determined and displayed by two-dimensional registration and overlay processing. Alternatively, the two-dimensional representation data of the target structure and the X-ray perspective view can be preprocessed, and then further determined and displayed by two-dimensional registration and overlay processing. The above image preprocessing may include resolution adjustment, color adjustment, size adjustment, etc., which are not limited in this embodiment of the invention.

[0046] In some embodiments, the two-dimensional representation data of the target structure and the X-ray perspective image can be directly superimposed using a two-dimensional deformation field to obtain a superimposed perspective image. In other embodiments, the two-dimensional representation data of the target structure after image enhancement processing and the X-ray perspective image after image enhancement processing can also be superimposed using a two-dimensional deformation field to obtain a superimposed perspective image. When the mask data of the X-ray perspective image and the two-dimensional representation data of the target structure represented as a binary image are used for the two-dimensional registration processing described above, the two-dimensional representation data of the target structure represented as a binary image and the X-ray perspective image can be superimposed based on the two-dimensional deformation field.

[0047] The overlay perspective view can be displayed on a single interface. This interface can be user-interactive, capable of receiving user actions such as moving, rotating, and scaling the overlay perspective view. In some embodiments, the interface can simultaneously display vital signs parameters of the target object, such as heart rate, blood pressure, and blood oxygen saturation. The specific content displayed on the interface can be determined according to the actual needs of the developers or users, and this embodiment of the invention does not impose any limitations.

[0048] In practical scenarios, when acquiring preoperative 3D structural data, the target subject is typically awake, lying on an arc-shaped imaging bed with their hands raised (to move out of the imaging field of view). At this time, the thoracic muscles are tense, the scapulae are elevated, and the spine exhibits a specific physiological curvature. During intraoperative perspective imaging, the target subject is usually under anesthesia with relaxed muscles. Their hands may be placed at their sides or fixed in a specific position, lying on a relatively firm and flat operating table. Due to differences in the target subject's posture and the type of bed used, the curvature of the spine changes, increasing the difficulty of registration. Using vertebrae or ribs as anchor points can easily lead to overall deviation. This embodiment of the invention does not involve the use of preoperative 3D structural data, therefore, there is no error caused by changes in the target subject's posture between preoperative and intraoperative periods. In other words, because this embodiment of the invention uses intraoperative structural data of the target structure, it can reduce the difficulty of registration, improve the accuracy of registration, and meet the requirements for real-time overlay perspective image display.

[0049] According to the above-described scheme of the present invention, for each of the multiple target structures of a target object, intraoperative structural data of the target structure can be determined based on the intraoperative cone-beam CT three-dimensional data of the target object. Then, based on the intraoperative structural data of the target structure, two-dimensional representation data of the target structure corresponding to the X-ray imaging viewpoint is generated. Next, the two-dimensional representation data of the target structure is registered with the real-time acquired X-ray perspective view of the target object to determine the two-dimensional deformation field used for two-dimensional overlay. Finally, based on the two-dimensional deformation field, the two-dimensional representation data of the target structure is overlaid with the X-ray perspective view to generate and display the overlaid perspective view. The above scheme has relatively low difficulty in performing two-dimensional registration based on the intraoperative structural data of the target structure, and using two-dimensional registration also helps to improve the efficiency of the registration process, thereby improving the generation efficiency of the overlaid perspective view, which can meet the actual processing requirements of high real-time performance.

[0050] For example, Figure 2 A schematic flowchart illustrating a method for processing CT data according to an embodiment of the present invention is shown. Figure 2 As shown, in step S110, based on the intraoperative cone-beam CT three-dimensional data of the target object, the intraoperative structural data of the target structure corresponding to the target structure is determined, including steps S111 and S112.

[0051] In step S111, based on the intraoperative cone-beam CT three-dimensional data of the target object, the target structure mask data corresponding to the target structure is obtained through the target detection model corresponding to the target structure.

[0052] In some embodiments, intraoperative cone-beam computed tomography (CBCT) three-dimensional data can be directly input into the target detection model corresponding to the target structure to obtain the target structure mask data corresponding to the target structure.

[0053] In some embodiments, voxels whose voxel values ​​in the intraoperative cone-beam CT 3D data are outside the voxel value range corresponding to the target structure can be screened out to obtain the first preprocessed data corresponding to the target structure. The first preprocessed data corresponding to the target structure can be input into the target detection model corresponding to the target structure to obtain the target structure mask data. Specifically, since different target structures absorb X-rays differently, the voxel value ranges corresponding to different target structures may be different. For each target structure, voxels whose voxel values ​​are outside the voxel value range corresponding to the target structure can be screened out in the intraoperative cone-beam CT 3D data, and the intraoperative cone-beam CT 3D data after partially screening out voxels can be used as the first preprocessed data corresponding to the target structure.

[0054] This invention provides an example for reference: Intraoperative cone-beam computed tomography (CBCT) 3D data can be denoised and resampled to unify the size of the data to a preset dimension. In this example, the target structure can be lung parenchyma, and the voxel value range (unit: HU) of lung parenchyma can be -976 to 307. Voxels with voxel values ​​outside this range can be filtered out to obtain the first preprocessed data corresponding to the lung parenchyma. It is understood that the specific value of the voxel value range corresponding to the target structure can be determined according to the actual situation, and this invention does not impose any limitations on this.

[0055] The first preprocessed data can be input into the target detection model corresponding to the target structure to obtain the target structure mask data. Preprocessing can be performed by first using the voxel value range corresponding to the target structure to filter out some voxels in the intraoperative cone-beam CT 3D data, which helps reduce the classification difficulty of the target detection model and thus improves processing efficiency.

[0056] It is understandable that the first preprocessed data can be further processed before being input into the object detection model. For example, the first preprocessed data can be standardized to reduce the classification difficulty of the object detection model. Alternatively, the first preprocessed data can be augmented to improve the accuracy of the object detection model's output.

[0057] It is understood that the target detection model can directly output target structure mask data (e.g., composed of 0 and 1, where 0 indicates that the voxel at the corresponding position is not the target structure, and 1 indicates that the voxel at the corresponding position is the target structure) as the intraoperative structural data of the target structure. It is also understood that the above mask data can be used for registration processing to improve registration efficiency. The specific structure and training method of the above target detection model will not be elaborated here in this embodiment of the invention. Different target structures may correspond to different target detection models, and the intraoperative structural data of the target structure obtained accordingly has high accuracy.

[0058] In step S112, the intraoperative structural data of the target structure is determined based on the target structure mask data.

[0059] In one example, to improve the comprehensiveness of the display, target structure mask data can be used to filter voxels in intraoperative cone-beam computed tomography (CBCT) 3D data to obtain intraoperative structural data of the target structure. In other words, the intraoperative structural data of the target structure can be data with voxel values ​​from the intraoperative CBCT 3D data. The resulting overlay perspective view can be used to display structures included in the intraoperative CBCT 3D data with greater adaptability.

[0060] According to the above-described scheme of the present invention, target structure mask data corresponding to the target structure can be obtained based on the intraoperative cone-beam computed tomography (CBCT) three-dimensional data of the target object and through the target detection model corresponding to the target structure. Then, based on the target structure mask data, the intraoperative structural data of the target structure is determined. The above scheme, using a target detection model, can improve the accuracy of the obtained intraoperative structural data of the target structure, which is beneficial to improving the accuracy of the superimposed perspective view obtained accordingly.

[0061] For example, step S111 involves obtaining target structure mask data corresponding to the target structure based on the intraoperative cone-beam CT three-dimensional data of the target object and the target detection model corresponding to the target structure.

[0062] In step S1111, the processed intraoperative cone-beam CT three-dimensional data is input into the target detection model corresponding to the target structure to obtain the target structure mask data corresponding to the target structure.

[0063] The processed intraoperative cone-beam computed tomography (CBCT) 3D data is obtained by 3D noise reduction and / or contrast enhancement processing based on the intraoperative CBCT 3D data.

[0064] The data after noise reduction and / or contrast enhancement can be input into the target detection model mentioned above to obtain the target structure mask data corresponding to the target structure, and then determine the intraoperative structural data of the target structure. Alternatively, the relevant content in step S111 above can be used to perform preprocessing, standardization, and other operations before inputting the data into the target detection model. The embodiments of the present invention will not be elaborated here.

[0065] According to the above-described scheme of the present invention, the processed intraoperative cone-beam computed tomography (CBCT) three-dimensional data can be input into the target detection model corresponding to the target structure to obtain the target structure mask data corresponding to the target structure. This scheme can improve the data quality of the intraoperative CBCT three-dimensional data, which is beneficial to improving the accuracy of the final superimposed perspective view.

[0066] For example, the two-dimensional representation data of the target structure is generated by perspective projection of the intraoperative structural data of the target structure.

[0067] In some embodiments, perspective projection can be used to simulate a full-angle (-92 degrees to 92 degrees) perspective view of the target structure intraoperative structural data as a two-dimensional representation of the target structure.

[0068] For example, the two-dimensional representation data of the target structure is generated by maximum intensity projection onto the intraoperative structural data of the target structure.

[0069] In some embodiments, the target structure's intraoperative structural data can be input into the maximum intensity projection model to obtain two-dimensional representation data of the target structure.

[0070] For example, the two-dimensional representation data of the target structure is generated by virtual X-ray projection of the intraoperative structural data of the target structure based on imaging geometry parameters.

[0071] In some embodiments, the positional information in the structural data of the target structure can be converted into positional information in a local coordinate system with the viewpoint as the origin, and virtual X-ray projection can be achieved through matrix transformation (such as a 4×4 homogeneous coordinate matrix) to determine the two-dimensional representation data of the target structure.

[0072] According to the above-described scheme of the present invention, two-dimensional representation data of the target structure is generated based on the intraoperative structural data of the target structure. The two-dimensional representation data of the target structure obtained by the above scheme is less difficult to register in two dimensions, which is beneficial to improving the efficiency of the registration process.

[0073] For example, the two-dimensional registration process includes: two-dimensional rigid registration based on rigid transformation, and two-dimensional non-rigid registration based on rigid transformation.

[0074] If rigid registration is performed solely using intraoperative structural data of the target structure and X-ray images, an overall average error will occur, leading to deviations in subsequent calculations of the areas of focus for the surgeon. To address this, this invention employs both two-dimensional rigid registration and two-dimensional non-rigid registration, thereby reducing the aforementioned average error and significantly minimizing potential deviations in subsequent calculations.

[0075] Based on the two-dimensional representation data of the target structure and the real-time acquired X-ray perspective view of the target object, a rigid registration deformation field can be determined through two-dimensional rigid registration processing to perform rigid transformation. Rigid transformation can include translation transformation, rotation transformation, etc. The rigid registration deformation field is used to perform rigid transformation on the two-dimensional data.

[0076] In some embodiments, the intraoperative structural data of the target structure includes target structure mask data. Specifically, for example, the two-dimensional representation data of the target structure can also be a binary image. Since the pixel value range of a binary image is smaller, the registration of the two-dimensional representation data of the target structure with the X-ray perspective is easier, thereby improving the efficiency of registration and overlay processing, and thus improving the overall efficiency of determining the overlay perspective.

[0077] It is understandable that the two-dimensional representation of the target structure can be a binary image. Alternatively, multiple target structures in an X-ray perspective view can be masked to obtain a single, unified binary image, which can then be used as the mask data for the X-ray perspective view. Then, the binarized two-dimensional representation of the target structure can be rigidly registered with the X-ray perspective view, which is represented as a binary image. Specifically, this can be achieved by rigidly registering the two-dimensional representation of the target structure in the binary image with the mask data of the X-ray perspective view.

[0078] In some embodiments, the two-dimensional representation data of the target structure and the X-ray perspective image can be directly rigidly registered. In other embodiments, at least one of the two-dimensional representation data of the target structure and the X-ray perspective image can be image enhanced before rigid registration.

[0079] Based on the two-dimensional representation data of the target structure, the first intraoperative two-dimensional data of the target structure can be determined. Based on X-ray perspective images, the second intraoperative two-dimensional data of the target structure can be determined.

[0080] For each of multiple target structures, the difference between the first intraoperative two-dimensional data of the target structure and the second intraoperative two-dimensional data of the target structure can be determined. Then, with the goal of minimizing all differences, a rigid registration deformation field is determined. In one example, the rigid registration deformation field can also be determined by combining the overall grayscale difference between the two-dimensional representation data of the target structure and the X-ray perspective view. The above differences can be multiplied by the registration weight of the target structure to obtain a first value. The rigid registration deformation field is determined by combining the first values ​​of each target structure. For example, the first values ​​of all target structures can be summed, and then gradient descent can be used until the sum reaches a first preset threshold. The specific value of the first preset threshold is not limited in this embodiment of the invention. The registration weight can be determined according to the actual needs of the user or developer. For example, the larger the registration weight, the stronger the representativeness of the registration based on its corresponding target structure. Specifically, for example, the target structure with a larger registration weight is less susceptible to respiratory deformation.

[0081] It is understandable that the mask data from intraoperative cone-beam computed tomography (CBCT) 3D data can be used to determine the first intraoperative 2D data of the target structure, thereby identifying the aforementioned differences and improving registration efficiency. Specifically, for example, the mask data can be projected onto a 2D plane representing the target structure's 2D data, and the resulting binary data can be used as the first intraoperative 2D data of the target structure. In this example, both the first and second intraoperative 2D data of the target structure can be binary data.

[0082] The rigid registration deformation field can be determined using the registration weights corresponding to the target structures within a preset range from the medical device in the X-ray fluoroscopy image. In a specific example, the rigid registration deformation field can also be determined using the anatomical structure weights corresponding to the anatomical structures within the target structures. In other words, the anatomical structure can be any anatomical structure among multiple target structures within a preset range from the medical device in the X-ray fluoroscopy image. The specific values ​​of the preset range are not limited in this embodiment of the invention. By setting the preset range, local registration between the two-dimensional representation data of the target structure and the X-ray fluoroscopy image can be achieved, thereby improving registration efficiency and ultimately improving the efficiency of determining the superimposed fluoroscopy image.

[0083] Based on the two-dimensional representation data of the target structure, X-ray perspective view, and rigid registration deformation field, the total registration deformation field can be determined through non-rigid registration processing to perform rigid and non-rigid transformations.

[0084] Non-rigid transformations can include scaling, shearing, polynomial transformations, etc. The total registration deformation field is used to perform rigid and non-rigid transformations on two-dimensional data. It can be understood that the rigid registration deformation field can serve as the basis for non-rigid registration processing, reducing the registration difficulty of non-rigid registration.

[0085] In some embodiments, the two-dimensional representation data of the target structure and the X-ray perspective image can be directly non-rigidly registered. In other embodiments, image enhancement processing can be performed on at least one of the two-dimensional representation data of the target structure and the X-ray perspective image, followed by non-rigid registration processing. The aforementioned non-rigid registration processing can be performed on the two-dimensional representation data of the target structure in the binary image and the mask data of the X-ray perspective image.

[0086] In some embodiments, the overall registration deformation field is determined based on the anatomical substructure weights corresponding to the anatomical substructures of the anatomical structures within a preset range of distance from the bronchoscope in the X-ray fluoroscopy image of multiple target structures. The target substructures (which may be anatomical substructures of the target structure) can be different parts of the target structure. The target substructure weights corresponding to the target substructures can be preset weights, for example, determined using a Euclidean distance plot. In one example, the anatomical structures within the target structure can be used to determine the overall registration deformation field. The anatomical structure weights corresponding to the anatomical structures are related to the endotracheal instrument distance and the structure category corresponding to the anatomical structure. In this example, the endotracheal instrument distance is used to represent the closest distance between the anatomical structure and the bronchoscope in the X-ray fluoroscopy image. For example, preliminary registration can be performed on the two-dimensional representation data of the target structure and the X-ray fluoroscopy image, and then the anatomical structure weights corresponding to each target structure can be adjusted using the aforementioned closest distance. The calculation method of the above distances is not limited in this embodiment of the invention; for example, Euclidean distance can be used. Specifically, for example, the anatomical structure weights corresponding to the anatomical structures are negatively correlated with the endotracheal instrument distance. In other words, the closer the endotracheal instruments are to the anatomical structure, the greater the weight of the anatomical structure. It can be understood that the above structure categories are used to represent the categories of anatomical structures; for example, the structure category of an anatomical structure can be airway, blood vessels, bone, etc. The influence of structure category on the weight of anatomical structures is not limited in this embodiment of the invention and can be determined by the developer's practical experience.

[0087] In the above scheme, since the weight of the anatomical structure is related to the distance of the endotracheal instrument and the structural category corresponding to the anatomical structure, the two-dimensional representation data of the target structure and the X-ray perspective view can achieve local and targeted registration of the target structure near the bronchoscope, which is related to the structural category. This is beneficial to improve the registration efficiency and thus improve the overall determination efficiency of the superimposed perspective view.

[0088] In some embodiments, based on the first and second intraoperative two-dimensional data of the target structure, the first intraoperative two-dimensional data of the target substructure in the first intraoperative two-dimensional data of the target structure can be determined, and the second intraoperative two-dimensional data of the target substructure in the second intraoperative two-dimensional data of the target structure can be determined. The difference between the first and second intraoperative two-dimensional data of the target substructure corresponding to the target substructure can be determined. Then, with the goal of minimizing the above differences of all target substructures of all target structures, the total registration deformation field is determined. It can be understood that both the first and second intraoperative two-dimensional data of the target substructure can be represented as binary data. The above differences can be multiplied by the target substructure weight of the target substructure to obtain a second value. The total registration deformation field is determined by combining the second values ​​of all target substructures of all target structures. For example, all second values ​​can be summed, and then the conjugate gradient descent method can be used until the sum reaches a second preset threshold. The specific value of the above second preset threshold is not limited in this embodiment of the invention. The aforementioned target substructure weights can be determined based on the actual needs of users or developers. For example, the larger the target substructure weight, the stronger the representativeness of the registration based on its corresponding target substructure. Specifically, for example, the target substructure with a larger target substructure weight is less susceptible to respiratory deformation.

[0089] The overall registration deformation field can be determined using the registration weights corresponding to the target substructures within the target structure that are within a preset range of the bronchoscope in the X-ray fluoroscopy image. In a specific example, the overall registration deformation field can also be determined using the weights corresponding to the anatomical substructures of the anatomical structures within multiple target structures. In other words, the anatomical structure can be any anatomical structure within a preset range of the bronchoscope in the X-ray fluoroscopy image among multiple target structures. The specific values ​​of the preset range are not limited in this embodiment of the invention. By setting the preset range, local registration between the two-dimensional representation data of the target structure and the X-ray fluoroscopy image can be achieved, thereby improving registration efficiency and ultimately improving the efficiency of determining the superimposed fluoroscopy image.

[0090] According to the above-described scheme of the present invention, two-dimensional registration processing can be performed based on rigid transformation and two-dimensional non-rigid registration processing based on rigid transformation. By performing rigid registration processing first and then non-rigid registration processing, the above scheme can reduce the registration difficulty of non-rigid registration processing, which is beneficial to improving registration efficiency and accuracy, and thus improving the accuracy of the obtained superimposed perspective view.

[0091] For example, in two-dimensional rigid registration processing, different target structures have their own registration weights, which are related to at least one of the following: the distance between the target structure and the medical device in the X-ray fluoroscopy image; the anatomical category or structural category of the target structure.

[0092] In one example, the medical device distance can be used to represent the closest distance between the target structure and the bronchoscope in the X-ray fluoroscopy image. Specifically, for example, the registration weight corresponding to the target structure is negatively correlated with the distance to the endotracheal device. That is, the closer the endotracheal device is, the greater the registration weight. It can be understood that the above anatomical category is used to represent the category of anatomical structure; for example, the anatomical category of an anatomical structure can be airway, blood vessel, bone, etc. The above structural category is used to represent the category of medical device structure; for example, the structural category of a medical device structure can be bronchoscope. The influence of anatomical category and structural category on the registration weight is not limited in this embodiment of the invention and can be determined by the developer's practical experience. The specific classification rules for anatomical category and structural category are also not limited in this embodiment of the invention. It can be understood that the above distance can be two-dimensional or three-dimensional, and this embodiment of the invention is not limited thereto.

[0093] For example, in two-dimensional non-rigid registration processing, the anatomical substructures in the target structure are assigned corresponding substructure weights, which are related to the substructure category of the anatomical substructure.

[0094] The substructure categories of the aforementioned target substructures can be used to represent different target substructures. For example, if the structure category of the target structure is trachea, then the substructure categories of the target substructures included in this target structure can be main bronchus, branch trachea, terminal trachea, etc. The specific classification rules for substructure categories are not limited in this embodiment of the invention. Combining the examples above, the anatomical substructure weights corresponding to the anatomical substructures in the target structure, which is represented as an anatomical structure, can also be used to determine the overall registration deformation field mentioned above. Specifically, for example, the overall registration deformation field is determined based on the anatomical substructure weights corresponding to the anatomical substructures of the anatomical structures within a preset range of the bronchoscope in the X-ray fluoroscopy image among multiple target structures. The anatomical substructure weights corresponding to each anatomical substructure are related to the substructure category corresponding to the anatomical substructure.

[0095] Based on the preceding text, the weights of anatomical structures are related to the distance to endotracheal instruments and the corresponding structural category. Since an anatomical structure comprises multiple substructures, and the weights of each substructure are related to its category, a more accurate overall registration deformation field can be determined by combining the distance to endotracheal instruments, the structural category of the anatomical structure, and the substructure categories of each substructure included in the anatomical structure. This improves the accuracy of the overlay perspective view. Using the example of binary feature information from the target structure's two-dimensional representation data, determining the rigid registration deformation field using anatomical structures within a preset range of the bronchoscope in the X-ray fluoroscopy image, and determining the overall registration deformation field using anatomical substructures within a preset range of the bronchoscope in the X-ray fluoroscopy image, the overall generation time of the overlay perspective view can be less than 200ms, meeting real-time requirements.

[0096] For example, the two-dimensional registration process is completed based on a single X-ray fluoroscopic view.

[0097] It is understandable that the two-dimensional representation data of the target structure corresponds to the X-ray imaging viewpoint, and the two-dimensional registration process performed between the two-dimensional representation data of the target structure and the X-ray perspective view also corresponds to the X-ray imaging viewpoint.

[0098] The two-dimensional registration process described above according to embodiments of the present invention is completed based on a single X-ray fluoroscopic viewpoint. This method improves registration accuracy by using the same viewpoint for registration.

[0099] For example, Figure 3 A schematic flowchart illustrating a method for processing CT data according to an embodiment of the present invention is shown. Figure 3 As shown, the above processing method further includes steps S210 and S220.

[0100] In step S210, the target data is displayed.

[0101] The target data includes at least one of the following: intraoperative cone-beam computed tomography (CBCT) 3D data, intraoperative structural data of the target structure, and X-ray fluoroscopy.

[0102] The system can display at least one of the following on the display interface: intraoperative cone-beam CT 3D data, intraoperative structural data of the target structure, and X-ray perspective view, for user reference.

[0103] In some embodiments, the system may receive user switching operations on target data, and switch the displayed target data during bronchoscopy.

[0104] In step S220, after the acquisition angle of the C-arm of the C-arm cone-beam CT imaging device used to acquire intraoperative cone-beam CT three-dimensional data and X-ray perspective is adjusted, the superimposed perspective and target data are adjusted and displayed accordingly based on the adjusted acquisition angle.

[0105] The C-arm cone-beam CT imaging system is used to acquire intraoperative cone-beam CT three-dimensional data and X-ray perspective images.

[0106] When the acquisition angle of the C-arm of the C-arm cone-beam CT imaging device is not adjusted, the display angle of the superimposed perspective view and the target data is consistent.

[0107] It is understandable that if the acquisition angle of the C-arm of the C-arm cone-beam CT imaging device is adjusted, the X-ray perspective image acquired by the C-arm cone-beam CT imaging device will also change in real time with the change of acquisition angle.

[0108] The display angle of intraoperative cone-beam CT 3D data can be adjusted based on the adjusted acquisition angle, so that users can obtain display content adapted to the current acquisition angle.

[0109] For intraoperative structural data of a target structure that has already been determined, adjustments can also be made based on the adjusted acquisition angle.

[0110] According to the above-described solution of the present invention, target data can be displayed. After the acquisition angle of the C-arm of the C-arm cone-beam CT imaging device used to acquire intraoperative cone-beam CT three-dimensional data and X-ray perspective images is adjusted, the superimposed perspective image and target data are adjusted accordingly based on the adjusted acquisition angle and then displayed. This solution can display target data for user reference and avoids inconsistencies in display angles between the target data and the superimposed perspective image, or between the target data and other target data, after changes in the acquisition angle of the C-arm in the C-arm cone-beam CT imaging device. This provides users with a more comprehensive and accurate reference.

[0111] For example, Figure 4 A schematic flowchart illustrating a method for processing CT data according to an embodiment of the present invention is shown. Figure 4 The above-described processing method further includes steps S310 to S350.

[0112] In step S310, the main region in the intraoperative cone-beam CT three-dimensional data is determined.

[0113] The main area includes the medical device area and the trachea area. The trachea area is the region corresponding to at least part of the target object's trachea in the intraoperative cone-beam CT 3D data, and the medical device area is the region corresponding to the medical device in the intraoperative cone-beam CT 3D data.

[0114] In some embodiments, the main region in intraoperative cone-beam CT 3D data can be determined using a machine learning model. In some alternative embodiments, user actions such as dividing or modifying the medical device region or tracheal region can be received to determine the main region.

[0115] In step S320, the first location closest to the target lesion selected by the user is determined in the main region.

[0116] The target lesion is obtained based on the user's selection of the target lesion in the intraoperative cone-beam CT 3D data. Specifically, the target lesion can be the tissue, organ, trachea, etc., that the user needs to operate on.

[0117] In step S330, a second location closest to the first location is determined in the medical device area.

[0118] If the first position is located outside the medical device area, the position of the voxel with the shortest line connecting it to the first position can be used as the second position.

[0119] In step S340, the second location, the first location, and the target lesion are connected sequentially to obtain the target path.

[0120] The aforementioned target path can be used to guide users in moving the bronchoscope or instruments within it.

[0121] In step S350, the target path is overlaid with the intraoperative cone-beam CT three-dimensional data and displayed.

[0122] The specific operation of the overlay process can be referred to above, and the embodiments of the present invention will not be described in detail here.

[0123] According to the above-described solution of the present invention, in response to the user's selection of the target lesion, the target path can be planned and displayed in the intraoperative cone-beam CT three-dimensional data. The superimposed perspective view obtained therefrom can also include the target path, which can better assist the user in moving the bronchoscope or the instruments therein.

[0124] See Figure 5 , Figure 5 A schematic diagram of an overlay perspective view according to an embodiment of the present invention is shown. (In conjunction with...) Figure 5The overlaid perspective image can display the bronchoscope in the X-ray perspective view (i.e., the real-time bronchoscope in the perspective view in the image, which can be referenced near the blue area and the black area that intersects with the blue area), the bronchoscope mask data in the registered intraoperative cone-beam CT 3D data (i.e., the registered bronchoscope mask data in the image, which can be referenced in the blue area in the image), the airway mask data in the registered intraoperative cone-beam CT 3D data (e.g., the registered airway mask data), and the lesion, which can provide users with real-time intraoperative reference.

[0125] According to another aspect of the present invention, a CT data processing apparatus is also provided. Figure 6 A schematic block diagram of a CT data processing apparatus 400 according to an embodiment of the present invention is shown. Figure 6 As shown, the processing device 400 includes a processor 410 and a memory 420. The memory 420 stores a computer program, and the computer program instructions are executed by the processor 410 to perform the above-described CT data processing method.

[0126] Furthermore, according to another aspect of the present invention, a storage medium is provided, on which program instructions are stored, which, when executed by a computer or processor, cause the computer or processor to perform corresponding steps of the CT data processing method described in the embodiments of the present invention. The storage medium may, for example, include a memory card of a smartphone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media. According to yet another aspect of the present invention, a computer program product is also provided, comprising computer program instructions, which, when executed by a computer or processor, cause the computer or processor to perform corresponding steps of the CT data processing method described above.

[0127] Those skilled in the art can understand the specific implementation scheme of the above-mentioned processing device and storage medium by reading the relevant description of the CT data processing method. For the sake of brevity, it will not be described in detail here.

[0128] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of the invention. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of the invention. All such changes and modifications are intended to be included within the scope of the invention as claimed in the appended claims.

[0129] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0130] In the several embodiments provided by this invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0131] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0132] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of the invention. However, this approach should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with fewer features than all of those in a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0133] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or elements of any method or apparatus so disclosed may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0134] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0135] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules in the CT data processing device according to embodiments of the present invention. The present invention can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0136] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0137] The above description is merely a specific embodiment of the present invention or an explanation of that embodiment. The scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method of processing CT data, characterized by, The method includes: For each of the multiple target structures of a target object, based on the intraoperative cone-beam CT three-dimensional data of the target object, the intraoperative structural data of the target structure corresponding to that target structure is determined. The multiple target structures include anatomical structures and / or medical device structures. The intraoperative structural data of the target structure corresponding to the target structure is mask data used to represent the spatial position of the target structure in the intraoperative cone-beam CT three-dimensional data, or the three-dimensional data corresponding to the target structure in the intraoperative cone-beam CT three-dimensional data. Based on the intraoperative structural data of the target structure, generate two-dimensional representation data of the target structure corresponding to the X-ray imaging perspective; The two-dimensional representation data of the target structure is registered with the real-time acquired X-ray perspective view of the target object to determine the two-dimensional deformation field for two-dimensional superposition. Based on the two-dimensional deformation field, the two-dimensional representation data of the target structure is superimposed with the X-ray perspective view to generate and display the superimposed perspective view.

2. The method of claim 1, wherein, The determination of intraoperative target structure data based on the intraoperative cone-beam computed tomography (CBCT) three-dimensional data of the target object includes: Based on the intraoperative cone-beam CT three-dimensional data of the target object, the target structure mask data corresponding to the target structure is obtained through the target detection model corresponding to the target structure. Based on the target structure mask data, the intraoperative structural data of the target structure are determined.

3. The method of claim 2, wherein, The intraoperative cone-beam computed tomography (CBCT) 3D data based on the target object, through the target detection model corresponding to the target structure, yields target structure mask data corresponding to the target structure, including: The processed intraoperative cone-beam computed tomography (CBCT) 3D data is input into the target detection model corresponding to the target structure to obtain the target structure mask data corresponding to the target structure. The processed intraoperative CBCT 3D data is obtained by 3D noise reduction and / or contrast enhancement processing based on the intraoperative CBCT 3D data.

4. The method as described in claim 1, characterized in that, The two-dimensional representation data of the target structure is generated in one of the following ways: Perspective projection is performed on the intraoperative structural data of the target structure; Maximum intensity projection is performed on the intraoperative structural data of the target structure; Virtual X-ray projection is performed on the intraoperative structural data of the target structure based on imaging geometric parameters.

5. The method as described in claim 1, characterized in that, The two-dimensional registration process includes: two-dimensional rigid registration based on rigid transformation, and two-dimensional non-rigid registration based on the rigid transformation.

6. The method as described in claim 5, characterized in that, In the two-dimensional rigid registration process, different target structures have their own registration weights, which are related to at least one of the following: the distance between the target structure and the medical device in the X-ray fluoroscopy image; the anatomical category or structural category of the target structure.

7. The method as described in claim 6, characterized in that, In the two-dimensional non-rigid registration process, the anatomical substructures in the target structure are assigned corresponding substructure weights, which are related to the substructure category of the anatomical substructure.

8. The method as described in claim 1, characterized in that, The two-dimensional registration process is completed based on a single X-ray perspective.

9. The method as described in claim 1, characterized in that, The method further includes: Display target data, wherein the target data includes at least one of the following: intraoperative cone-beam CT three-dimensional data, intraoperative structural data of the target structure, and X-ray perspective view; After the acquisition angle of the C-arm of the C-arm cone-beam CT imaging device used to acquire the intraoperative cone-beam CT three-dimensional data and the X-ray perspective is adjusted, the superimposed perspective and the target data are adjusted and displayed accordingly based on the adjusted acquisition angle.

10. The method as described in claim 1, characterized in that, The method further includes: The main region in the intraoperative cone-beam CT three-dimensional data is determined, wherein the main region includes the medical device region and the tracheal region; Determine the first location closest to the target lesion selected by the user within the main body region; Determine the second location closest to the first location within the medical device area; The second position, the first position, and the target lesion are connected sequentially to obtain the target path; The target path is overlaid with the intraoperative cone-beam CT three-dimensional data and displayed.

11. A CT data processing device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the CT data processing method as described in any one of claims 1-10.

Images