Methods, devices, electronic equipment, and storage media for lung segment reconstruction

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for lung segment reconstruction. It calls a preset algorithm to reconstruct lung segments from lung imaging data, generating initial lung segment reconstruction data. The reconstructed data is then validated to identify deviated lung segments with reconstruction deviations at their junctions. Based on the reconstruction instructions for these deviated lung segments, a lung segment assembly is reconstructed. Based on the data collected from the lung segment assembly, the junctions of each lung segment within the assembly are reconstructed and repaired to obtain the final lung segment reconstruction data. Compared to related technologies, this disclosure, by calling a preset algorithm for lung segment reconstruction, can utilize advanced algorithmic technology to initially outline the lung segment structure. Then, by validating the reconstructed data, it can accurately identify deviated lung segments with reconstruction deviations at their junctions. For these deviated lung segments, a lung segment assembly is reconstructed according to their specific reconstruction instructions, ensuring accurate reconstruction when dealing with problematic areas.

Description

Technical Field

[0001] This disclosure relates to the field of image processing technology, and in particular to a method and apparatus, electronic device and storage medium for lung segment reconstruction. Background Technology

[0002] In the medical fields of lung disease diagnosis, treatment planning, and surgical simulation, three-dimensional lung segment reconstruction technology is of great significance. Accurate three-dimensional lung segment models help doctors better understand the anatomical structure of the lungs, improve the accuracy of disease diagnosis, and provide a precise basis for surgical planning. However, traditional three-dimensional lung segment reconstruction methods have significant limitations, mainly in the following two aspects:

[0003] While fully automated reconstruction methods theoretically improve efficiency, in practical applications, their technical limitations lead to unsatisfactory reconstruction results when dealing with complex lung structures. Lung structures are complex and diverse, with significant individual variations, making it difficult for automated algorithms to adapt to various special cases and complex variations, thus affecting the accuracy of the reconstruction results. For example, when dealing with the complex relationships between pulmonary vessels, bronchi, and lung parenchyma, problems such as inaccurate identification or missing reconstructions of some structures may occur, failing to meet the clinical demand for high-precision 3D models. While manually creating 3D lung segment models can guarantee a certain level of accuracy, this method is excessively time-consuming. The process requires a significant investment of time and effort from skilled technicians, demanding extremely high technical expertise from operators. Every step, from data acquisition and image segmentation to model construction, relies on manual operation and professional judgment, leading to a substantial increase in labor costs and low efficiency, hindering widespread clinical application and failing to meet the needs of large-scale clinical diagnosis and treatment.

[0004] Traditional methods for 3D lung segment reconstruction struggle to balance efficiency and accuracy, limiting their widespread clinical application. Therefore, there is an urgent need for a new reconstruction method that combines the advantages of automation and human interaction to overcome the shortcomings of existing technologies and improve the efficiency and accuracy of 3D lung segment reconstruction to meet the growing clinical demands. Summary of the Invention

[0005] This disclosure provides a method, apparatus, electronic device, and storage medium for lung segment reconstruction. Its main purpose is to address the problems of low efficiency and accuracy in traditional three-dimensional lung segment reconstruction methods.

[0006] According to a first aspect of this disclosure, a method for lung segment reconstruction is provided, comprising:

[0007] The preset algorithm is invoked to reconstruct lung segments from lung imaging data, generating initial lung segment reconstruction data.

[0008] The initial lung segment reconstruction data is examined to identify deviated lung segments with reconstruction deviations at the lung segment junctions, and lung segment assemblies are reconstructed and generated according to the lung segment reconstruction instructions of the deviated lung segments.

[0009] Based on the sampling data of the lung segment assembly, the boundaries of each lung segment in the lung segment assembly are reconstructed and repaired to obtain lung segment reconstruction data.

[0010] In some embodiments, after invoking a preset algorithm to perform lung segment reconstruction on lung imaging data and generate initial lung segment reconstruction data, the method further includes:

[0011] The initial lung segment reconstruction data is sent to a human-computer interaction device for display, so as to verify the initial lung segment reconstruction data and receive the lung segment reconstruction command sent by the human-computer interaction device.

[0012] In some embodiments, the process of reconstructing and repairing the boundaries between lung segments in the lung segment assembly based on the sampling data of the lung segment assembly to obtain lung segment reconstruction data includes:

[0013] Receive the data collected from the human-computer interaction device;

[0014] Based on the collected data, a fitting boundary surface for each lung segment in the lung segment assembly is generated.

[0015] The lung segment assembly is segmented using the fitted boundary surface to obtain the lung segment reconstruction data.

[0016] In some embodiments, the step of fitting and generating the fitting boundary surface of each lung segment in the lung segment assembly based on the sampling data includes:

[0017] The surface fitting algorithm is invoked to perform surface fitting on the sampled data, generating a fitted surface;

[0018] The fitted surface is subjected to surface smoothing, surface scaling, surface direction automation, and surface refinement processes to obtain the fitted boundary surfaces at the junctions of each lung segment in the lung segment assembly.

[0019] In some embodiments, segmenting the lung segment assembly using the fitted boundary surface to obtain the lung segment reconstruction data includes:

[0020] Based on the fitted boundary surface and the data model of the lung segment assembly, the segmentation position of the fitted boundary surface in the lung segment assembly is calculated and determined;

[0021] The fitted boundary surface is used to cut lung segments at the segmentation location, and the surface closure algorithm is called to perform surface closure processing on the segmented lung segments to obtain the lung segment reconstruction data.

[0022] In some embodiments, before sending the initial lung segment reconstruction data to a human-computer interaction device for display, the method further includes:

[0023] If the number of deviation surfaces in the lung segment assembly does not exceed the number threshold, a preset repair and reconstruction algorithm is invoked to reconstruct the lung segments and obtain lung segment reconstruction data.

[0024] According to a second aspect of this disclosure, an apparatus for lung segment reconstruction is provided, comprising:

[0025] The first reconstruction unit is used to call a preset algorithm to reconstruct lung segments from lung imaging data and generate initial lung segment reconstruction data.

[0026] The second reconstruction unit is used to examine the initial lung segment reconstruction data to identify the deviated lung segments with reconstruction deviations at the lung segment junctions, and to reconstruct and generate a lung segment assembly according to the lung segment reconstruction instructions of the deviated lung segments.

[0027] The repair unit is used to reconstruct and repair the junctions of each lung segment in the lung segment assembly based on the sampling data of the lung segment assembly, so as to obtain lung segment reconstruction data.

[0028] In some embodiments, the apparatus further includes:

[0029] The display unit is used to send the initial lung segment reconstruction data to a human-computer interaction device for display after calling a preset algorithm to reconstruct lung segments from lung imaging data and generate initial lung segment reconstruction data, so as to verify the initial lung segment reconstruction data and receive the lung segment reconstruction command sent by the human-computer interaction device.

[0030] In some embodiments, the repair unit includes:

[0031] A receiving module is used to receive the data collected from the human-computer interaction device.

[0032] The fitting module is used to fit and generate the fitting boundary surface of each lung segment in the lung segment assembly based on the sampling data.

[0033] The segmentation module is used to segment the lung segment assembly using the fitted boundary surface to obtain the lung segment reconstruction data.

[0034] In some embodiments, the fitting module is further configured to:

[0035] The surface fitting algorithm is invoked to perform surface fitting on the sampled data, generating a fitted surface;

[0036] The fitted surface is subjected to surface smoothing, surface scaling, surface direction automation, and surface refinement processes to obtain the fitted boundary surfaces at the junctions of each lung segment in the lung segment assembly.

[0037] In some embodiments, the segmentation module is further configured to:

[0038] Based on the fitted boundary surface and the data model of the lung segment assembly, the segmentation position of the fitted boundary surface in the lung segment assembly is calculated and determined;

[0039] The fitted boundary surface is used to cut lung segments at the segmentation location, and the surface closure algorithm is called to perform surface closure processing on the segmented lung segments to obtain the lung segment reconstruction data.

[0040] In some embodiments, the apparatus further includes:

[0041] The third reconstruction unit is used to call a preset repair and reconstruction algorithm to reconstruct the lung segments of the lung segment assembly before sending the initial lung segment reconstruction data to the human-computer interaction device for display. If the number of deviation surfaces in the lung segment assembly does not exceed the number threshold, the unit will obtain lung segment reconstruction data.

[0042] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0043] At least one processor; and

[0044] A memory communicatively connected to the at least one processor; wherein,

[0045] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0046] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0047] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0048] This disclosure provides a method, apparatus, electronic device, and storage medium for lung segment reconstruction. It calls a preset algorithm to reconstruct lung segments from lung imaging data, generating initial lung segment reconstruction data. The initial lung segment reconstruction data is then examined to identify deviated lung segments with reconstruction deviations at the segmental boundaries. Based on the lung segment reconstruction instructions for these deviated lung segments, a lung segment assembly is reconstructed. Based on the data collected from the lung segment assembly, the boundaries of each lung segment within the assembly are reconstructed and repaired to obtain lung segment reconstruction data. Compared to related technologies, this disclosure, by calling a preset algorithm for lung segment reconstruction, can utilize advanced algorithmic technology to initially outline the lung segment structure, providing a foundation for subsequent precise processing. Then, by examining the reconstructed data, it can accurately identify deviated lung segments with reconstruction deviations at the segmental boundaries. For these deviated lung segments, a lung segment assembly is reconstructed according to their specific reconstruction instructions, ensuring accurate reconstruction when processing problematic areas.

[0049] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0050] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0051] Figure 1 A schematic flowchart illustrating a lung segment reconstruction method provided in this embodiment of the disclosure;

[0052] Figure 2 A schematic flowchart of another lung segment reconstruction method provided in this embodiment of the disclosure;

[0053] Figure 3 This is a schematic diagram of a lung segment assembly with reconstruction bias.

[0054] Figure 4 This is a schematic diagram of a lung segment that automatically reconstructs lung segments;

[0055] Figure 5 This is a schematic diagram of a surface fitting generation process;

[0056] Figure 6 This is an image showing the effect of a lung segment cutting.

[0057] Figure 7 A schematic diagram of a lung segment reconstruction device provided in an embodiment of this disclosure;

[0058] Figure 8 A schematic diagram of another lung segment reconstruction device provided in an embodiment of this disclosure;

[0059] Figure 9 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0060] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0061] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for lung segment reconstruction according to embodiments of the present disclosure.

[0062] Figure 1 This is a schematic flowchart of a lung segment reconstruction method provided in an embodiment of the present disclosure.

[0063] like Figure 1 As shown, the method includes the following steps:

[0064] Step 101: Call the preset algorithm to reconstruct lung segments from the lung imaging data and generate initial lung segment reconstruction data.

[0065] In the embodiments of this disclosure, the acquired lung image data is preprocessed before lung segment reconstruction. Lung image data typically originates from equipment such as CT (computed tomography) scanners, and this data may contain noise, artifacts, and varying degrees of resolution differences. Therefore, a series of advanced data processing techniques are required, such as noise filtering algorithms to remove random noise from the images and improve image clarity; and grayscale correction algorithms to adjust the grayscale value distribution of the images, enhancing the contrast between different tissues and making the structures of the lungs, such as bronchi, blood vessels, and lung parenchyma, more clearly distinguishable. Simultaneously, the uniformity and compatibility of the data format are ensured by converting it into a format suitable for subsequent algorithm processing, such as converting the common DICOM (Digital Imaging and Communication in Medicine) format into a computationally convenient three-dimensional volumetric data format.

[0066] The pre-defined algorithm for lung segment reconstruction can be an artificial intelligence algorithm based on deep learning and image processing, including but not limited to the following types: segmentation algorithms based on convolutional neural networks (CNNs), classification algorithms utilizing point cloud features, and the classic Marching cubes algorithm. During algorithm preparation, the algorithm parameters are optimized and adjusted according to the characteristics of the lung imaging data and the requirements of the reconstruction task. For example, for the segmentation algorithm, it is trained with a large amount of lung sample data to determine appropriate parameters such as convolutional kernel size, number of layers, and learning rate, enabling it to accurately identify different tissue regions in the lung images; for the point cloud classification algorithm, the point cloud feature extraction method is optimized to improve the classification accuracy of point cloud data of key structures such as bronchi and blood vessels.

[0067] Based on the anatomical structure and spatial relationships of different lung segments, the shape and interconnections of each lung segment are accurately constructed, generating detailed and geometrically accurate lung segment reconstruction data. This data is presented in the form of a three-dimensional model, including the vertex coordinates, patch information, and topological structure of each lung segment, providing a foundation for subsequent testing, analysis, and application.

[0068] Step 102: The initial lung segment reconstruction data is examined to identify deviated lung segments with reconstruction deviations at the lung segment junctions, and a lung segment assembly is reconstructed according to the lung segment reconstruction instructions of the deviated lung segments.

[0069] In the embodiments of this disclosure, after obtaining the initial lung segment reconstruction data, a comprehensive data verification process is required to ensure its accuracy and reliability. Deviated lung segments with reconstruction deviations at the lung segment junctions can be verified manually or using deep learning algorithms. This embodiment does not limit how to verify these segments. For example, during manual verification, visualization tools can be used to present the lung segment reconstruction data in a three-dimensional visualization, allowing for intuitive observation and analysis of the lung segment morphology, size, and spatial relationships between segments, providing a clear basis for subsequent deviation judgment. Furthermore, deep learning-based automatic detection algorithms can be used to learn from a large amount of accurately labeled lung segment image data, enabling the identification of discontinuities, ambiguities, or abnormal morphologies at the boundaries of the lung segment reconstruction data.

[0070] Multiple verification methods were used to meticulously analyze the lung segment reconstruction data. On one hand, based on anatomical knowledge and pre-defined standards, the manual examination team carefully observed the shape, size, location, and boundaries with adjacent lung segments using visualization tools. They focused on the smoothness, continuity, and conformity to normal anatomical relationships at the lung segment boundaries. For example, under normal circumstances, the boundary between adjacent lung segments should be a naturally transitioning curved surface. If obvious jagged, concave, or convex abnormalities were found at the boundary in the reconstruction data, reconstruction deviations may exist.

[0071] On the other hand, an automatic detection algorithm is used to quantitatively analyze the lung segment reconstruction data. The algorithm calculates the geometric parameters of the lung segment, such as volume, surface area, and curvature, and compares them with normal ranges. If these parameters of a lung segment exceed the predetermined normal range, or if the proportional relationship between the lung segment and adjacent lung segments is abnormal, it will be marked as a suspected deviation lung segment. For example, if the volume of a lung segment is significantly smaller than the normal range, it may mean that there is partial loss or compression of the lung segment during reconstruction; or if the curvature difference between adjacent lung segments is too large, it may indicate that the reconstruction at the junction is inaccurate.

[0072] In other embodiments of this disclosure, the results of manual inspection and automatic detection can be combined to identify deviated lung segments with reconstruction deviations at the lung segment junctions. For suspected deviated lung segments, further comparative analysis with the original lung imaging data is conducted to trace possible sources of error in the reconstruction process, such as motion artifacts during data acquisition and limitations of the algorithm when processing specific areas, to ensure the accuracy of deviation judgment.

[0073] In the process of three-dimensional reconstruction of lung structures, such as when reconstructing the apical-posterior segment of the left upper lobe, a certain degree of deviation was found. This deviation is not isolated but has a chain reaction effect on other closely adjacent lung segments. Specifically, the apical-posterior segment of the left upper lobe is anatomically adjacent to the anterior segment, superior lingular segment, and inferior lingular segment of the left upper lobe, collectively forming the relatively independent and complete functional region of the left upper lobe. From an anatomical perspective, the deviation of the apical-posterior segment of the left upper lobe can manifest in various forms. For example, its boundary definition may be inaccurate, leading to partial overlap or excessive gaps at the junctions with adjacent lung segments. This inaccurate boundary delineation directly interferes with the reconstruction results of adjacent lung segments because, when reconstructing based on overall lung imaging data, the relationships between lung segments are interdependent and mutually restrictive.

[0074] Once the deviated lung segment is identified, corresponding lung segment reconstruction instructions are generated based on its specific circumstances. These instructions are formulated based on the analysis results of the type and degree of deviation and are designed to guide subsequent reconstruction work. If the deviation is caused by the partial loss of the lung segment boundary, the reconstruction instructions may include inserting new boundary points at specific locations and performing interpolation calculations based on the morphological characteristics of the surrounding tissues to restore the missing boundary portion; if it is caused by deformation of the overall shape of the lung segment, the instructions may involve geometric transformations of the entire lung segment, such as stretching, twisting, or rotating, to restore its normal shape.

[0075] Based on these lung segment reconstruction instructions, advanced 3D modeling technology is used to reconstruct and generate a lung segment assembly. This process first creates a new 3D model space in computer memory, incorporating the deviated lung segment and its adjacent related lung segments (because lung segments are interconnected, a deviation in one segment may affect the reconstruction accuracy of adjacent segments, so they are processed together). Then, the geometry and topology of the deviated lung segment and its adjacent lung segments are progressively adjusted and modified according to the reconstruction instructions. During the modification process, the physical characteristics and physiological constraints of lung tissue are fully considered, such as maintaining the continuity of lung tissue and avoiding the tortuosity of blood vessels and bronchi, ensuring that the generated lung segment assembly is not only geometrically accurate but also physiologically reasonable.

[0076] Finally, the generated lung segment composite was validated and optimized. Data validation tools and algorithms were used again to check whether the boundaries between lung segments in the composite were smooth and natural, whether the overall morphology of the lung segments conformed to anatomical standards, and the degree of consistency with the original image data. Based on the validation results, necessary fine-tuning was performed on the lung segment composite until a satisfactory reconstruction effect was achieved, providing a high-quality basic model for subsequent processing (such as boundary reconstruction and repair based on the data collected from the lung segment composite).

[0077] Step 103: Based on the sampling data of the lung segment assembly, the boundaries of each lung segment in the lung segment assembly are reconstructed and repaired to obtain lung segment reconstruction data.

[0078] In the embodiments of this disclosure, for a defined lung segment assembly (e.g., the left upper lobe, including the apical-posterior segment, anterior segment, superior lingular segment, and inferior lingular segment, etc.), specialized data acquisition techniques are used to obtain its sampling data. This process involves a high-precision three-dimensional coordinate measurement system, which can collect a large amount of discrete point data on the surface and key internal locations of the lung segment assembly. These points not only contain spatial location information (x, y, z coordinates) but may also contain other related attribute information, such as tissue density and normal vector direction at the point. This attribute information is of great significance for the subsequent accurate reconstruction of the lung segment junction.

[0079] The massive amount of collected data will be processed in depth. Pre-set algorithms will be used to classify and cluster these data points. Based on the spatial distribution characteristics and attribute similarity of the points, points belonging to the same lung segment surface or boundary area will be grouped and identified.

[0080] For discontinuous, irregular, or inaccurate areas at the lung segment junctions, appropriate repair methods are selected based on the specific circumstances. For example, if small depressions or protrusions at the junction cause an uneven surface, a surface fitting-based repair method is used. By selecting data points within a certain range around the junction, a mathematical model (such as a polynomial surface model or a spline surface model) is used for fitting to calculate the optimal surface parameters that will smooth the junction surface. The fitted surface is then applied to repair the uneven area, making the transition at the junction more natural and smooth.

[0081] If tissue loss or structural ambiguity is found in the junctional region, interpolation repair is performed by referencing the structural characteristics and anatomical relationships of adjacent normal lung segments. Using known sampling data and geometric information from the normal lung segments, interpolation algorithms (such as linear interpolation and spline interpolation) are used to calculate the point data of the missing portion, thereby filling the gap and restoring the integrity of the junctional region. Simultaneously, during the repair process, it is crucial to ensure that the connection between the repaired junctional region and adjacent lung segments is physiologically sound, does not impair normal lung functions such as airflow and blood circulation, and conforms to biomechanical principles, capable of withstanding normal respiratory movements and physiological pressure.

[0082] Based on the established boundary reconstruction and repair strategy, specific repair operations are implemented using advanced 3D modeling and image processing technologies. For boundary areas that require adjustment, a lung segment boundary model that meets the requirements is gradually constructed by modifying the coordinate positions of relevant points, adding or deleting some point data, and adjusting the connection relationships between points.

[0083] Throughout this process, visualization tools are continuously used to monitor and adjust the repair process in real time. The changes in the lung segmental junction before and after repair are displayed in 3D visualization, allowing for a direct assessment of whether the repair effect has achieved the expected goals. If any issues are found with the repaired junction, such as an unnatural transition to surrounding tissues or abnormal local curvature, the previous step is immediately revisited to optimize the repair strategy and parameters until a satisfactory junctional reconstruction result is achieved.

[0084] This disclosure provides a method for lung segment reconstruction. It involves invoking a preset algorithm to reconstruct lung segments from lung imaging data, generating initial lung segment reconstruction data. The initial lung segment reconstruction data is then examined to identify deviated lung segments with reconstruction deviations at the segmental junctions. Based on the reconstruction instructions for these deviated lung segments, a lung segment assembly is reconstructed. Based on the data collected from the lung segment assembly, the junctions of each lung segment within the assembly are reconstructed and repaired to obtain the final lung segment reconstruction data. Compared to related technologies, this disclosure, by invoking a preset algorithm for lung segment reconstruction, can utilize advanced algorithmic technology to initially outline the lung segment structure, providing a foundation for subsequent precise processing. The verification of the reconstructed data can then accurately identify deviated lung segments with reconstruction deviations at the segmental junctions. For these deviated lung segments, a lung segment assembly is reconstructed according to their specific reconstruction instructions, ensuring accurate reconstruction when dealing with problematic areas.

[0085] To clearly illustrate the embodiments of this disclosure, this embodiment provides a schematic flowchart of another lung segment reconstruction method.

[0086] like Figure 2 As shown, the method includes the following steps:

[0087] Step 201: Call the preset algorithm to reconstruct lung segments from the lung imaging data and generate initial lung segment reconstruction data.

[0088] Specifically, in step 201, after the lung imaging data is input into the system, it is first comprehensively analyzed by a trained segmentation algorithm. This algorithm scans the image data pixel-by-pixel or voxel-by-voxel, quickly identifying the bronchial region based on pre-learned feature patterns. In images, the bronchi typically appear as regions with a specific grayscale range and tubular structural features; the segmentation algorithm can accurately delineate the bronchial contours, separating them from the entire lung image. Simultaneously, for the arterial and venous regions, the algorithm can also accurately segment them based on their unique grayscale values, texture, and contrast with surrounding tissues. The lung region is determined by excluding the remaining portion after excluding the bronchial and arterial / venous regions, thus achieving the initial division of the bronchi, arterial / venous, and lung regions.

[0089] Next, the point cloud classification algorithm processes the segmented point cloud data of the bronchial and arteriovenous regions. It deeply analyzes the geometric features and attribute information of each point, such as local density variations and the consistency of normal vector directions, further subdividing the bronchial point cloud into different branch levels and classifying the arteriovenous point cloud according to its vessel type (artery, vein) and size. This precise classification provides a crucial basis for the subsequent accurate construction of lung segment models, as the division of lung segments is closely related to the branching structure of the bronchi and blood vessels.

[0090] Finally, the Marching cubes algorithm uses the results from the previous two algorithms to construct lung segment models in three-dimensional space. Based on the segmented lung region boundaries and the branching locations of bronchi and blood vessels, it determines the position and shape of isosurfaces, and then generates a large number of triangular patches by connecting isosurface points, gradually constructing a three-dimensional surface model of the lung segment. In this process, the algorithm fully considers the variations in lung structure in different cases, such as differences in bronchial branch morphology and changes in lung parenchyma density. By adaptively adjusting the model construction parameters, it ensures that the generated initial lung segment reconstruction data accurately reflects the anatomical features of the lungs in different cases, providing a reliable foundation for further processing and analysis. Figure 3 This is a schematic diagram of a lung segment assembly with reconstruction bias. After a series of complex algorithmic processes, initial lung segment reconstruction data was generated. This data is presented in the form of a three-dimensional model, containing rich information. Each lung segment's 3D model consists of numerous vertex coordinates, triangular facet information, and topological relationships, detailing the segment's geometry and spatial relationships. Simultaneously, the model also labels the branching structures of bronchi and blood vessels, clarifying their distribution and direction within the lung segment. This information is crucial for accurately understanding lung physiological function and pathological changes.

[0091] Step 202: Send the initial lung segment reconstruction data to the human-computer interaction device for display, so as to verify the initial lung segment reconstruction data and receive the lung segment reconstruction command sent by the human-computer interaction device.

[0092] Specifically, in step 202, the initial lung segment reconstruction data is sent to a human-computer interaction device for display, allowing for verification of the initial lung segment reconstruction data. Before receiving the initial lung segment reconstruction data, the human-computer interaction device performs a series of preparatory tasks. By activating the relevant graphics rendering engine, the engine can quickly convert the received 3D reconstruction data into a visualized image and display it intuitively on the device screen. For example, for a 3D model of a lung segment, the rendering engine calculates the projection position and color information of each facet on the screen based on the model's vertex coordinates, facet information, and topological relationships, thereby generating a realistic 3D image that allows the user to observe the morphology and structure of the lung segment from different angles and levels.

[0093] After the initial lung segment reconstruction data is displayed on the human-computer interface, professionals (such as radiologists and pulmonary surgeons) begin to examine it. Drawing on their extensive medical knowledge and clinical experience, they carefully observe the morphology, size, positional relationships, and proximity to surrounding tissues (such as bronchi, blood vessels, and pleura) of the lung segments. During the examination, they assess various aspects, such as whether the lung segment boundaries are clear and smooth, whether the branches of the bronchi and blood vessels are completely and accurately reconstructed, and whether the connections between the lung segments conform to normal anatomical relationships.

[0094] To assist laboratory personnel in making more accurate judgments, the human-computer interaction device provides a series of interactive tools. For example, the zoom tool allows personnel to zoom in or out of images to view the fine structure of lung segments; the rotation tool allows images to be freely rotated in three-dimensional space to observe lung structures from different perspectives; and the slicing tool can simulate the slicing effect of a CT scan, displaying cross-sectional images of lung segments at different levels, helping personnel to gain a more comprehensive understanding of the internal structure of lung segments.

[0095] When inspectors discover problems or areas requiring further optimization in the initial lung segment reconstruction data, they input corresponding lung segment reconstruction instructions through a human-computer interaction device. These instructions are generated based on the analysis results of the type and degree of deviation and are specifically targeted. For example, if a lung segment's boundary is found to be missing, the reconstruction instructions may include adding new boundary points at specific locations and specifying the coordinates and connectivity of these points to repair the missing boundary; if the overall shape of the lung segment is deformed, the instructions may involve setting parameters for geometric transformations (such as translation, rotation, scaling, etc.) of the entire lung segment to restore its normal shape; if the connectivity between lung segments is incorrect, the instructions will clearly indicate the location and method of connection points that need to be adjusted to ensure that the connections between lung segments conform to anatomical standards.

[0096] Determine whether the number of deviation surfaces in the lung segment assembly exceeds a threshold. If the number of deviation surfaces in the lung segment assembly does not exceed the threshold, proceed to step 203; otherwise, proceed to step 204.

[0097] Step 203: Invoke the preset repair and reconstruction algorithm to reconstruct the lung segments of the lung segment assembly to obtain lung segment reconstruction data.

[0098] Specifically in step 203 Figure 4This is a schematic diagram of a lung segment reconstruction system. After the lung segment assembly is constructed, the primary task is to conduct a comprehensive evaluation to determine the number of deviated surfaces. Advanced surface detection algorithms can be used, but are not limited to, to perform a detailed scan and analysis of each surface in the lung segment assembly. This algorithm calculates the geometric characteristic parameters of the surfaces, such as curvature, flatness, and continuity, and compares them with a pre-defined standard template to determine whether each surface exhibits deviation.

[0099] After comprehensive testing, the number of deviation surfaces is counted. This number is then compared to a pre-set threshold. This threshold, determined based on extensive clinical trial data and lung anatomy studies, represents the maximum number of deviation surfaces allowed without affecting the overall lung segment reconstruction effect and the accuracy of clinical application. If the number of deviation surfaces does not exceed this threshold, the system determines that the current lung segment assembly meets the conditions for automatic repair and reconstruction, and then initiates the preset repair and reconstruction algorithm.

[0100] Step 204: Receive the data collected from the human-computer interaction device.

[0101] Step 205: Based on the collected data, fit and generate the fitting boundary surface of each lung segment in the lung segment assembly.

[0102] Step 2051: Call the surface fitting algorithm to perform surface fitting on the sampled data and generate a fitted surface.

[0103] Step 2052: Perform surface smoothing, surface scaling, surface direction automation, and surface refinement on the fitted surface to obtain the fitted boundary surface at the junction of each lung segment in the lung segment assembly.

[0104] Specifically, in steps 204 and 205, the system receives data collected from the human-computer interaction device. After the human-computer interaction device completes the data collection operation on the lung segment assembly, it sends the collected data to the back-end processing system through a stable and efficient data transmission channel. Before receiving the data, the back-end system initializes and configures the data receiving module to ensure that it can accurately identify and receive the data format from the human-computer interaction device.

[0105] Figure 5This diagram illustrates a surface fitting process. The system invokes a pre-designed surface fitting algorithm, which, based on mathematical models and computational geometry principles, performs surface fitting on the processed data points. The algorithm first selects an appropriate fitting method based on the distribution characteristics and quantity of the data points. If the data points are relatively regular and of moderate quantity, a polynomial surface fitting method may be used; if the data distribution is more complex and the quantity is larger, a more flexible method such as spline surface fitting may be chosen.

[0106] Taking polynomial surface fitting as an example, the algorithm constructs a polynomial function based on the coordinate information of the collected data points. It then uses optimization algorithms such as the least squares method to solve for the coefficients of the polynomial, ensuring that the surface represented by the polynomial function approximates all the collected points as closely as possible. During the solution process, the algorithm needs to consider the influence weight of each point on the surface shape; typically, points that are closer together have a larger weight to ensure that the fitted surface accurately reflects the surface features of the lung segment combination represented by the collected data points. After a series of complex calculations and iterations, a preliminary fitted surface is generated. This surface is represented in the form of a mathematical function and contains the geometric shape information of the surface, but further optimization may be needed in terms of smoothness and accuracy.

[0107] The generated fitted surface undergoes multi-faceted optimization to obtain the fitted boundary surfaces at the junctions of each lung segment in the lung segment assembly. First, surface smoothing is performed using a filtering algorithm (such as Gaussian filtering) to calculate a weighted average of the points on the fitted surface. By setting appropriate filtering parameters, the position of each point is adjusted based on the coordinates and attributes of its neighboring points, effectively removing local bumps and noise from the surface, resulting in a smoother, more continuous surface that better reflects the natural morphology of the lung tissue surface. Next, surface scaling is performed, calculating a suitable scaling factor based on the actual size and anatomical proportions of the lung segment assembly. Then, matrix multiplication is performed on the coordinates of each point on the fitted surface based on the scaling matrix, achieving precise scaling of the surface along each coordinate axis to ensure that the fitted boundary surface is proportionally consistent with the surrounding tissues and structures. For automated surface orientation processing, the system analyzes the normal vector distribution of the fitted surface according to the standard orientation of the lung anatomy and predefined rules. By calculating the deviation between the surface normal vector and the ideal direction, geometric transformations such as rotation matrices are used to rotate the surface, ensuring that the surface direction matches the normal anatomical direction of the lung segments and that the surface direction at the junctions of each lung segment conforms to physiological structural requirements. Finally, the surface is refined using a subdivision algorithm (such as the Catmull-Clark subdivision algorithm) to locally refine the fitted surface. This algorithm inserts new points on the surface and adjusts their positions based on the positions of surrounding points and the normal vector, adding more detail while maintaining the overall shape. This more accurately depicts the complex morphological features at the junctions of lung segments, such as minute depressions, convexities, and subtle changes in transition areas. After this series of optimization processes, the resulting fitted junction surface accurately represents the geometry and spatial relationships at the junctions of each lung segment in the lung segment assembly, providing a high-quality surface model foundation for subsequent lung segment cutting and reconstruction.

[0108] Step 206: Using the fitted boundary surface, the lung segment assembly is segmented to obtain the lung segment reconstruction data.

[0109] Step 2061: Based on the fitted boundary surface and the data model of the lung segment assembly, calculate and determine the segmentation position of the fitted boundary surface in the lung segment assembly.

[0110] Step 2062: The fitted boundary surface is used to cut lung segments at the segmentation positions, and the surface closure algorithm is called to perform surface closure processing on the segmented lung segments to obtain the lung segment reconstruction data.

[0111] Specifically, in step 206, in order to accurately segment the lung segment assembly, it is first necessary to calculate and determine the segmentation position of the fitted boundary surface in the lung segment assembly based on the fitted boundary surface and the data model of the lung segment assembly. This process involves complex geometric calculations and model analysis.

[0112] The system performs an in-depth analysis of the lung segment assembly's data model, which includes the 3D geometry, topological relationships, and detailed information about each lung segment. By analyzing the vertex coordinates, patch information, and connectivity between lung segments, and combining the mathematical expression and geometric features of the fitted boundary surface, the system calculates the location where the fitted boundary surface intersects with the lung segment assembly.

[0113] Specifically, for each facet (usually a triangle or quadrilateral facet) in the lung segment assembly, its intersection with the fitted boundary surface is calculated. This requires solving the equation of the intersection line between the plane containing the facet and the fitted boundary surface. By solving the simultaneous equations, the coordinates of the points on the intersection line are obtained; these points are the intersection points of the fitted boundary surface and the lung segment assembly. Then, based on the position of the intersection points on the facets and the distribution of the facets in the lung segment assembly, the segmentation path of the fitted boundary surface in the lung segment assembly is determined. For example, if the intersection point is located at the edge of the facet, it may indicate that the edge is part of the segmentation path; if the intersection point is inside the facet, further analysis of its relationship with surrounding facets is needed to determine the complete segmentation path. Through the calculation and analysis of all relevant facets, the precise segmentation position of the fitted boundary surface in the lung segment assembly is finally determined, providing an accurate basis for subsequent cutting operations.

[0114] Based on the calculated segmentation location, the fitted boundary surface is used to perform lung segmentation on the lung segment assembly at that location. This process requires modifying the data model of the lung segment assembly to separate the lung segment located on one side of the fitted boundary surface from the segment on the other side.

[0115] Figure 6 This is an example of a lung segment cutting diagram. During the cutting process, the system reorganizes the geometric elements such as faces and vertices in the lung segment assembly along a defined segmentation path. For faces that intersect with the segmentation path, they are divided into two or more new faces based on the intersection point, the vertex connections of the faces are updated, and the coordinates of the relevant vertices are adjusted to ensure that the cut lung segments are geometrically independent and complete.

[0116] After segmentation, since the lung segment assembly is usually a hollow 3D model, the cut surfaces will form gaps. Therefore, a surface closure algorithm is needed to close the surface of the segmented lung segments. This surface closure algorithm employs a special strategy: using the remaining surface inside the lung segment assembly, obtained by cutting the fitted boundary surface, as the gap-closing surface. By analyzing the geometry and boundary conditions of the remaining surface, it is matched and stitched with the edges of the segmented lung segments, thus closing the gaps and forming a complete lung segment model.

[0117] During surface closure, the algorithm needs to ensure the continuity and smoothness of the closed surface with the surrounding lung segment surfaces, avoiding discontinuous or sharp transition areas. This involves adjusting and optimizing the shape of the closed surface, such as by adjusting the control point positions or performing local surface fitting, to ensure a natural connection with the adjacent lung segment surfaces, while guaranteeing the correctness of the geometric structure and topological relationships of the closed lung segment model. After surface closure, the resulting lung segment reconstruction data contains complete lung segment models with accurate geometry and topological relationships. This data can be used for subsequent clinical diagnosis, surgical planning, and medical research, providing important support for the diagnosis and treatment of lung diseases.

[0118] It should be noted that the embodiments of this disclosure may include multiple steps. For ease of description, these steps are numbered, but these numbers are not a limitation on the execution time slots or execution order between the steps; these steps can be implemented in any order, and the embodiments of this disclosure do not limit this.

[0119] Corresponding to the aforementioned lung segment reconstruction method, this invention also proposes a lung segment reconstruction apparatus. Since the apparatus embodiments of this invention correspond to the aforementioned method embodiments, details not disclosed in the apparatus embodiments can be referred to the aforementioned method embodiments, and will not be repeated here.

[0120] Figure 7 This is a schematic diagram of the structure of a lung segment reconstruction device provided in an embodiment of the present disclosure, as shown below. Figure 7 As shown, it includes:

[0121] The first reconstruction unit 31 is used to call a preset algorithm to reconstruct lung segments from lung imaging data and generate initial lung segment reconstruction data.

[0122] The second reconstruction unit 32 is used to examine the initial lung segment reconstruction data to identify the deviated lung segments with reconstruction deviations at the lung segment junctions, and to reconstruct and generate a lung segment assembly according to the lung segment reconstruction instructions of the deviated lung segments.

[0123] Repair unit 33 is used to reconstruct and repair the junctions of each lung segment in the lung segment assembly based on the sampling data of the lung segment assembly, and obtain lung segment reconstruction data.

[0124] This disclosure provides a lung segment reconstruction apparatus. It invokes a preset algorithm to reconstruct lung segments from lung imaging data, generating initial lung segment reconstruction data. The initial lung segment reconstruction data is then examined to identify deviated lung segments with reconstruction deviations at the segmental junctions. Based on the lung segment reconstruction instructions for these deviated lung segments, a lung segment assembly is reconstructed. Based on the data collected from the lung segment assembly, the junctions of each lung segment within the assembly are reconstructed and repaired to obtain lung segment reconstruction data. Compared to related technologies, this disclosure, by invoking a preset algorithm for lung segment reconstruction, can utilize advanced algorithmic technology to initially outline the lung segment structure, providing a foundation for subsequent precise processing. Then, by examining the reconstructed data, it can accurately identify deviated lung segments with reconstruction deviations at the segmental junctions. For these deviated lung segments, a lung segment assembly is reconstructed according to their specific reconstruction instructions, ensuring accurate reconstruction when processing problematic areas.

[0125] Furthermore, in one possible implementation of this embodiment, such as Figure 8 As shown, the device further includes:

[0126] The display unit 34 is used to send the initial lung segment reconstruction data to a human-computer interaction device for display after calling a preset algorithm to reconstruct lung segments from lung imaging data and generate initial lung segment reconstruction data, so as to verify the initial lung segment reconstruction data and receive the lung segment reconstruction command sent by the human-computer interaction device.

[0127] Furthermore, in one possible implementation of this embodiment, such as Figure 8 As shown, the repair unit 33 includes:

[0128] The receiving module 331 is used to receive the sampling data sent by the human-computer interaction device;

[0129] The fitting module 332 is used to fit and generate the fitting boundary surface of each lung segment in the lung segment assembly based on the sampling data.

[0130] The segmentation module 333 is used to segment the lung segment assembly using the fitted boundary surface to obtain the lung segment reconstruction data.

[0131] Furthermore, in one possible implementation of this embodiment, the fitting module 332 is also used for:

[0132] The surface fitting algorithm is invoked to perform surface fitting on the sampled data, generating a fitted surface;

[0133] The fitted surface is subjected to surface smoothing, surface scaling, surface direction automation, and surface refinement processes to obtain the fitted boundary surfaces at the junctions of each lung segment in the lung segment assembly.

[0134] Furthermore, in one possible implementation of this embodiment, the segmentation module 333 is also used for:

[0135] Based on the fitted boundary surface and the data model of the lung segment assembly, the segmentation position of the fitted boundary surface in the lung segment assembly is calculated and determined;

[0136] The fitted boundary surface is used to cut lung segments at the segmentation location, and the surface closure algorithm is called to perform surface closure processing on the segmented lung segments to obtain the lung segment reconstruction data.

[0137] Furthermore, in one possible implementation of this embodiment, such as Figure 8 As shown, the device further includes:

[0138] The third reconstruction unit 35 is used to call a preset repair and reconstruction algorithm to reconstruct the lung segments of the lung segment assembly before sending the initial lung segment reconstruction data to the human-computer interaction device for display. If the number of deviation surfaces in the lung segment assembly does not exceed the number threshold, the unit will obtain lung segment reconstruction data.

[0139] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0140] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0141] Figure 9 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0142] like Figure 9As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0143] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0144] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the lung segment reconstruction method. For example, in some embodiments, the lung segment reconstruction method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned lung segment reconstruction method by any other suitable means (e.g., by means of firmware).

[0145] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0146] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0147] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0148] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0149] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0150] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0151] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0152] The various numerical designations such as "first," "second," etc., used in this disclosure are merely for ease of description and are not intended to limit the scope of the embodiments of this disclosure, nor do they indicate a sequential order.

[0153] At least one of the features described in this disclosure can also be described as one or more, and multiple features can be two, three, four or more, and this disclosure does not impose any limitations. In the embodiments of this disclosure, for a technical feature, the technical features in that technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no sequential order or size order among the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0154] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0155] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for lung segment reconstruction, characterized in that, include: The preset algorithm is invoked to reconstruct lung segments from lung imaging data, generating initial lung segment reconstruction data. The initial lung segment reconstruction data is examined to identify deviated lung segments with reconstruction deviations at the lung segment junctions, and lung segment assemblies are reconstructed and generated according to the lung segment reconstruction instructions of the deviated lung segments. Based on the sampling data of the lung segment assembly, the boundaries of each lung segment in the lung segment assembly are reconstructed and repaired to obtain lung segment reconstruction data; Based on the data collected from the lung segment assembly, the boundaries between the lung segments in the lung segment assembly are reconstructed and repaired to obtain lung segment reconstruction data, including: Receive the data collected from the human-computer interaction device; Based on the collected data, a fitting boundary surface for each lung segment in the lung segment assembly is generated. The lung segment assembly is segmented using the fitted boundary surface to obtain the lung segment reconstruction data; The process of segmenting the lung segment assembly using the fitted boundary surface to obtain the lung segment reconstruction data includes: Based on the fitted boundary surface and the data model of the lung segment assembly, the segmentation position of the fitted boundary surface in the lung segment assembly is calculated and determined; The fitted boundary surface is used to cut lung segments at the segmentation location, and the surface closure algorithm is called to perform surface closure processing on the segmented lung segments to obtain the lung segment reconstruction data.

2. The method according to claim 1, characterized in that, After invoking a preset algorithm to perform lung segment reconstruction on lung imaging data and generate initial lung segment reconstruction data, the method further includes: The initial lung segment reconstruction data is sent to a human-computer interaction device for display, so as to verify the initial lung segment reconstruction data and receive the lung segment reconstruction command sent by the human-computer interaction device.

3. The method according to claim 1, characterized in that, The step of fitting and generating the fitting boundary surface of each lung segment in the lung segment assembly based on the collected data includes: The surface fitting algorithm is invoked to perform surface fitting on the sampled data, generating a fitted surface; The fitted surface is subjected to surface smoothing, surface scaling, surface direction automation, and surface refinement processes to obtain the fitted boundary surfaces at the junctions of each lung segment in the lung segment assembly.

4. The method according to claim 2, characterized in that, Before sending the initial lung segment reconstruction data to a human-computer interaction device for display, the method further includes: If the number of deviation surfaces in the lung segment assembly does not exceed the number threshold, a preset repair and reconstruction algorithm is invoked to reconstruct the lung segments and obtain lung segment reconstruction data.

5. A device for lung segment reconstruction, characterized in that, include: The first reconstruction unit is used to call a preset algorithm to reconstruct lung segments from lung imaging data and generate initial lung segment reconstruction data. The second reconstruction unit is used to examine the initial lung segment reconstruction data to identify the deviated lung segments with reconstruction deviations at the lung segment junctions, and to reconstruct and generate a lung segment assembly according to the lung segment reconstruction instructions of the deviated lung segments. The repair unit is used to reconstruct and repair the junctions of each lung segment in the lung segment assembly based on the sampling data of the lung segment assembly, and obtain lung segment reconstruction data. Based on the data collected from the lung segment assembly, the boundaries between the lung segments in the lung segment assembly are reconstructed and repaired to obtain lung segment reconstruction data, including: Receive the data collected from the human-computer interaction device; Based on the collected data, a fitting boundary surface for each lung segment in the lung segment assembly is generated. The lung segment assembly is segmented using the fitted boundary surface to obtain the lung segment reconstruction data; The process of segmenting the lung segment assembly using the fitted boundary surface to obtain the lung segment reconstruction data includes: Based on the fitted boundary surface and the data model of the lung segment assembly, the segmentation position of the fitted boundary surface in the lung segment assembly is calculated and determined; The fitted boundary surface is used to cut lung segments at the segmentation location, and the surface closure algorithm is called to perform surface closure processing on the segmented lung segments to obtain the lung segment reconstruction data.

6. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

7. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-4.

8. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-4.

Images