An acquisition method, system and storage medium for an ear mold three-dimensional model

Abstract

The present application relates to the technical field of image processing, and especially relates to a method and system for acquiring a three-dimensional model of an ear mold and a storage medium. The method comprises the following steps: if the acquisition parameter of an acquisition probe is lower than a preset acquisition parameter threshold, the acquisition probe is inserted into the entrance of an ear canal to acquire an image of a concha cavity; the contour boundary of the concha cavity is recognized by using the image of the concha cavity, an entrance reference surface is generated, and an anti-tragus fitting point is determined; the outer ear canal region is recognized according to the contour boundary of the concha cavity, an image of the outer ear canal is acquired, a center line of the ear canal is extracted and a cross-sectional dimension is measured, and an eardrum curved surface is constructed; the eardrum curved surface is subjected to hole repair and smoothing processing, the rationality of the eardrum structure is verified, and a standard three-dimensional ear mold file is exported. The present application realizes the automatic generation of a standard three-dimensional ear mold based on image processing technology, and improves the reconstruction accuracy and matching rate of the ear mold.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to a method and system for acquiring a three-dimensional ear mold model and a storage medium. BACKGROUND

[0002] Traditional ear mold acquisition methods mostly rely on manual mold taking or single two-dimensional image measurement to construct ear molds. However, in complex ear canal structures, the morphology of the concha cavity and the external auditory canal is quite different, and manual or two-dimensional measurement is difficult to provide high-precision three-dimensional geometric information. Existing ear mold three-dimensional modeling methods mostly use fixed cross-sections or simple interpolation strategies, lack adaptive processing capabilities for changes in ear canal depth and surface continuity, and thus the model is prone to have holes, sharp edges or geometric distortions in complex eardrum and external auditory canal structures. In the boundary recognition process, traditional methods mostly rely on manual annotation or global thresholding, which cannot accurately capture the details and texture changes of the concha cavity profile, and may result in incomplete profile extraction, thereby affecting the accuracy of subsequent three-dimensional surface construction. The surface generation link is usually based on static cross-section fitting, which lacks joint constraints on continuity between cross-sections and local curvature changes, and is prone to local non-smoothness or error accumulation. Existing systems lack automated hole filling, smoothing optimization and morphological reasonableness detection mechanisms in eardrum surface repair and structure verification, and it is difficult to balance model integrity and anatomical accuracy. The overall three-dimensional ear mold acquisition accuracy and reliability need to be improved. SUMMARY

[0003] Therefore, it is necessary to provide a method and system for acquiring a three-dimensional ear mold model and a storage medium to solve at least one of the above technical problems.

[0004] To achieve the above-mentioned purpose, a method for acquiring a three-dimensional ear mold model includes the following steps:

[0005] Step S1: If the acquisition parameters of the acquisition probe are lower than the preset acquisition parameter threshold, control the acquisition probe to be inserted into the entrance of the ear canal to acquire a concha cavity image;

[0006] Step S2: Identify the concha cavity profile boundary using the concha cavity image, generate an entrance reference surface, and determine the retroconcha fitting point;

[0007] Step S3: Identify the external auditory canal region according to the concha cavity profile boundary, acquire an external auditory canal image, extract the ear canal centerline and measure the cross-sectional size, and construct an eardrum surface;

[0008] Step S4: Perform hole repair and smoothing processing on the eardrum surface, verify the eardrum structure rationality, and export a standard three-dimensional ear mold file.

[0009] Preferably, the present specification also provides a computer readable storage medium storing a computer program, the computer program being executed by a processor to implement any one of the methods for obtaining an ear mold three-dimensional model.

[0010] Preferably, the present specification also provides a system for obtaining an ear mold three-dimensional model for executing the method for obtaining an ear mold three-dimensional model as described above, the system for obtaining an ear mold three-dimensional model comprising:

[0011] An image acquisition module is configured to control the acquisition probe to be inserted into the entrance of the ear canal to acquire an image of the concha cavity if the acquisition parameter of the acquisition probe is lower than the preset acquisition parameter threshold;

[0012] A fitting point determination module is configured to identify the contour boundary of the concha cavity by using the image of the concha cavity, generate an entrance reference plane, and determine the antihelix fitting point;

[0013] An eardrum curved surface construction module is configured to identify the outer ear canal region according to the contour boundary of the concha cavity, acquire an image of the outer ear canal, extract an ear canal center line and measure a cross-sectional dimension, and construct an eardrum curved surface;

[0014] An ear mold file export module is configured to perform hole repair and smoothing processing on the eardrum curved surface, verify the rationality of the eardrum structure, and export a standard three-dimensional ear mold file.

[0015] The present application has the following advantages:

[0016] (1) By using the multi-stage three-dimensional reconstruction method based on the images of the concha cavity and the outer ear canal, the accurate spatial positioning of the ear canal and the eardrum is realized, the continuity and anatomical structure alignment of the ear mold three-dimensional model in the depth direction are ensured, and the accuracy and reliability of the three-dimensional ear mold construction are improved;

[0017] (2) By using the contour recognition strategy of fusing edge features and texture features, the contour of the concha cavity is weighted and scored and noise is removed, the accurate boundary extraction of the complex ear canal structure is realized, the contour recognition accuracy is improved, and the error caused by image noise is reduced;

[0018] (3) In the process of constructing the cross-sectional sequence of the outer ear canal and generating the eardrum curved surface, the cross-sectional continuity and curved surface smoothness are effectively maintained by combining the depth reference line and the curvature change constraint, the accurate restoration of the eardrum micro-geometric features is realized, and the limitations of the traditional cross-sectional fitting method that is prone to holes and sharp distortion are broken through;

[0019] (4) By performing automatic hole repair, smoothing processing and structure rationality verification on the eardrum curved surface, it is ensured that the final three-dimensional ear mold model is complete and conforms to the anatomical specification, high-quality data basis is provided for personalized ear mold design, hearing aid devices or ear medical research, and the applicability and repeatability of the ear mold acquisition method are effectively improved. BRIEF DESCRIPTION OF DRAWINGS

[0020] Other features, objects, and advantages of the application will become more apparent from the following detailed description when read in connection with the following drawings:

[0021] Fig. 1 A schematic diagram of a step flow for a method for obtaining a three-dimensional model of an ear mold according to the present application;

[0022] Fig. 2 A schematic diagram of a module for a system for obtaining a three-dimensional model of an ear mold according to the present application;

[0023] Fig. 3 A schematic diagram of a three-dimensional model of an ear mold according to the present application;

[0024] The object, features, and advantages of the present application will be further illustrated by the following embodiments, with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The technical method of the present application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all the other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0026] In addition, the accompanying drawings are only schematic illustrations of the present application, and are not necessarily drawn to scale. Identical reference numerals in the drawings represent identical or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0027] It should be understood that although the terms "first", "second", etc. can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the example embodiments, a first element can be called a second element, and similarly, a second element can be called a first element. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0028] To achieve the above object, there is provided Figs. 1 to 3 The present application provides a method for obtaining a three-dimensional model of an ear mold, the method comprising the following steps:

[0029] Step S1: If the acquisition parameter of the acquisition probe is lower than the preset acquisition parameter threshold, control the acquisition probe to be inserted into the entrance of the ear canal to acquire the concha cavity image;

[0030] In an embodiment, when the acquisition parameter of the acquisition probe is lower than the preset threshold, the probe is controlled to be inserted into the entrance of the ear canal, a stable pushing posture is maintained, and the concha cavity image is acquired frame by frame through an endoscope or a high-definition optical camera, so as to ensure that each frame of image is consistent in time domain and clear, thereby providing basic data for subsequent contour boundary identification. During the acquisition process, the probe is kept axially aligned with the ear canal to avoid image distortion or obstruction.

[0031] In another embodiment, assuming that the resolution of the acquisition probe is 1920x1080, the frame rate is 30 Hz, 60 frames are continuously acquired, the acquisition time of each frame is about 33 ms, the acquisition depth does not exceed 25 mm, and the acquisition distance is about 15 mm, high-quality original image data is generated, which is used for subsequent fine boundary analysis.

[0032] Step S2: Identify the concha cavity contour boundary by using the concha cavity image, generate an entrance reference plane, and determine the ear return fitting point;

[0033] In an embodiment, the acquired concha cavity image is converted into a gray-scale image, the gray-scale gradient amplitude is extracted as an edge feature, the gray-scale difference is calculated in each pixel neighborhood, the direction of the line connecting the maximum and minimum points of the gray-scale difference is taken as a texture feature, the edge feature and the texture feature are fused to generate a weighted score, high-score pixel points are screened and connected into a continuous curve, and meanwhile, isolated noise points are removed, so as to obtain a complete concha cavity contour boundary. The contour boundary is equidistantly sampled, an initial plane is fitted, a normal vector is calculated and is rotated and corrected in the ear canal depth direction, so as to form an entrance reference plane; the contour is projected onto the reference plane, and a point with the smallest curvature and facing the ear canal opening is identified as an ear return fitting point.

[0034] In another embodiment, assuming that there are about 1500 contour candidate points, 1200 points are reserved after scoring and noise removal; the normal deviation of the initial reference plane is about 3°, and the deviation after rotation correction is less than 1° in the ear canal depth direction; finally, 3 ear return fitting points are identified, which are located at the front, middle and rear segments of the concha cavity entrance respectively, and the three-dimensional coordinate accuracy of each point is about 0.2 mm.

[0035] Step S3: Identify the outer ear canal region according to the concha cavity contour boundary, acquire the outer ear canal image, extract the ear canal centerline and measure the cross-sectional size, and construct the eardrum curved surface;

[0036] In one embodiment, spatial extension analysis is performed on the concha cavity contour boundary. Layer-by-layer depth image slices are extracted along the boundary normal, and the gray level and closure of each cross section are calculated to determine the extension direction of the external auditory canal. The cross section contour is tracked frame by frame along the depth direction, the cross section size and centroid position are measured, and continuous cross sections are connected by spline interpolation. The tympanic end identifies the closed cross section contour and seals it to construct a continuous and smooth tympanic surface.

[0037] In another embodiment, it is assumed that 20 slices are extracted vertically, each slice has a cross-sectional diameter of 6–8 mm, and the centroid offset does not exceed 0.5 mm; there are 4 closed cross-sections at the eardrum end, and the total number of points on the surface after spline interpolation is approximately 12,000, with a maximum cross-sectional curvature change of approximately 0.15 mm. -1 This ensures that the curvature of the eardrum is continuous and conforms to the anatomical shape.

[0038] Step S4: Repair the holes in the curved surface of the eardrum and smooth it out. Verify the rationality of the eardrum structure and export the standard three-dimensional ear mold file.

[0039] In one embodiment, the missing area of ​​the eardrum surface is identified, the hole is locally filled with triangles, and then Laplacian smoothing is used to make the local curvature continuous. The eardrum thickness, surface continuity and normal direction are checked by the structural rationality verification module. After confirming that the structure is reasonable, a standard three-dimensional ear mold file (such as STL format) is exported for ear mold production or product design.

[0040] In another embodiment, six holes were detected on the curved surface, with the largest hole diameter being approximately 2 mm; the smoothing process was iterated three times, with a window radius of 1.5 mm each time, resulting in a maximum normal deviation of less than 0.3 mm after smoothing; the exported 3D ear mold file contained approximately 15,000 triangular facets, with a total volume of approximately 1.2 cm³. 3 It can be used directly for 3D printing or digital analysis.

[0041] Of particular importance, step S4, which involves repairing the hole in the curved surface of the eardrum, includes:

[0042] Identify unclosed regions in the tympanic membrane surface; construct boundary loops at the boundary points of the unclosed regions, and generate triangular mesh fragments based on the boundary loops to fill the holes;

[0043] In one embodiment, boundary detection is performed on the constructed eardrum surface to mark the set of boundary points of the unclosed regions. For sets Closed boundary loops are constructed sequentially to generate triangular mesh fragments to fill the unclosed hole areas. After filling, the triangular mesh fragments are merged with the original eardrum surface to form a continuous and complete eardrum surface, providing a foundation for subsequent smoothing and export of the 3D model.

[0044] In another embodiment, it is assumed that five boundary unclosed regions are detected, and the number of boundary points of each region is [18, 24, 15, 20, 22], respectively. A corresponding triangular mesh segment is generated for each boundary ring, and the number of segments is [12, 16, 10, 14, 13], respectively. While generating the triangular mesh segment, the normal of the segment vertex is interpolated to obtain an interpolated normal vector set, and the interpolated triangular mesh segment is checked for topological consistency, including boundary continuity, vertex connection integrity, and face normal consistency. The checking result shows that the five filling regions all pass the topological consistency detection, and a complete eardrum surface is successfully constructed.

[0045] In the filling process, the normal of the triangular mesh segment is interpolated, and the topological consistency of the triangular mesh segment after normal interpolation is checked.

[0046] In an embodiment, the normal of each newly generated vertex is calculated by linear weight interpolation, and the normals of the neighboring vertices are weighted and averaged to ensure smooth transition of the filling region normal and the original curved surface. Then, the topology of the generated triangular mesh is checked, including vertex repetition, boundary closure, and triangular face direction consistency, to confirm the integrity of the topological structure.

[0047] In another embodiment, it is assumed that the triangular mesh segment after filling generates 75 triangular faces, and the average deviation of the normal interpolation result of each vertex in the x, y, and z directions is not more than 0.02. After topological checking, it is found that there are 2 vertices with slight abnormalities. After adjusting the position of the vertices locally, all segments meet the topological consistency requirements, thereby completing the eardrum surface hole repair and smoothing process.

[0048] Especially important is that verifying the rationality of the eardrum structure in step S4 includes:

[0049] Based on the smoothed eardrum surface, the geometric continuity index of the eardrum surface is calculated to detect whether there is an abnormal sharp angle;

[0050] In an embodiment, the smoothed eardrum surface is divided into a plurality of small facets, the angle between the vertices of each facet and the change rate of the facet normal are calculated, and the continuity index is generated If the continuity index is greater than a preset threshold (such as 30°), it is determined that there is an abnormal sharp angle. By traversing all the facets, the abnormal sharp region is marked, providing a basis for subsequent shape checking and hole repair.

[0051] In another embodiment, it is assumed that the eardrum surface is composed of about 1200 triangular facets, and the continuity index of each facet is calculated , and the range is [5°, 28°], of which only 8 facets have The angles are slightly higher than the threshold value 30°, and are located at the edge area of the eardrum, indicating that the overall surface continuity is good, and there is no obvious sharp abnormality.

[0052] The consistency of the eardrum surface and the longitudinal direction of the ear canal is judged by calculating the included angle between the center line of the ear canal and the normal vector of the eardrum surface; the curvature distribution of the eardrum surface is globally analyzed, if the curvature changes smoothly and is within the preset curvature threshold range, the shape is determined to be reasonable; otherwise, return to hole repair.

[0053] In an embodiment, the sampling points are uniformly sampled along the center line of the ear canal, and the normal vectors are calculated on the corresponding eardrum surface. The included angle between the normal vector and the direction of the center line is calculated for each sampling point , if ≤ (such as 15°), the direction of the point is determined to be reasonable. Then the curvature distribution is calculated, if the global curvature changes smoothly and is within the preset curvature range , the eardrum shape is determined to be reasonable; otherwise, return to step S1 or perform hole repair.

[0054] In another embodiment, assuming that 100 points are sampled along the center line, the range of the included angle is [2°, 14°], and the global average included angle is about 8°, which meets the requirement of direction consistency; the range of the curvature distribution is , and the average is about , which is smooth and within the preset threshold range, so the eardrum surface shape is determined to be reasonable and does not need further repair.

[0055] Preferably, the earch cavity image recognition of the earch cavity contour boundary in step S2 comprises:

[0056] The earch cavity image is converted into a gray scale image, and the gray scale gradient amplitude is extracted as an edge feature;

[0057] In an embodiment, the collected earch cavity image is converted into a gray scale image; the gray scale gradient amplitude of each pixel point in the gray scale image is calculated as an edge feature for preliminary contour recognition. The edge feature can reflect the high gray scale change area of the earch cavity contour in the image, thereby providing candidate points for texture feature calculation.

[0058] In another embodiment, assuming that the resolution of the collected image is 1024x1024, a total of about 1048576 pixels of the gray scale gradient amplitude are calculated for each frame. Set the gradient threshold to 0.2, and only select about 250,000 high gradient pixel points as edge candidate points to reduce noise interference; further remove about 50,000 isolated points according to connectivity analysis to obtain about 200,000 continuous edge pixels, which provide a basis for subsequent texture feature calculation.

[0059] For any pixel point in the gray scale image, the gray scale difference between each pixel point in the neighborhood and the center pixel point is calculated; the direction of the line connecting the pixel point with the largest gray scale difference to the pixel point with the smallest gray scale difference in the neighborhood is taken as the texture feature of the center pixel point.

[0060] In an embodiment, a neighborhood (for example, 5x5 pixels) is selected with any pixel point in the gray scale image as the center, the gray scale difference between each pixel point in the neighborhood and the center pixel point is calculated; the direction of the line connecting the pixel point with the largest gray scale difference to the pixel point with the smallest gray scale difference in the neighborhood is taken as the texture feature of the center pixel point. The texture feature can enhance the reliability of the edge profile and provide auxiliary information for the sensitive points of the curved surface change.

[0061] In another embodiment, it is assumed that the neighborhood is 7x7 pixels, and the texture feature vectors of about 800,000 pixel points are calculated for each frame. The texture direction is normalized, and about 500,000 pixel points with a deviation of less than 15° from the average direction of the neighborhood are screened. In combination with the edge points in step S1, only about 3,000,000 pixel points with both edge features and consistent texture directions are retained, which are used for subsequent profile fusion and spatial mapping to improve the three-dimensional profile accuracy.

[0062] The edge features and the texture features are used to determine the profile boundary of the concha cavity.

[0063] In an embodiment, the edge features and the texture features are weighted and fused according to the proportion of 60% edge features + 40% texture features, and the profile reliability of each pixel point is evaluated; then the pixel points are screened to remove isolated or low-confidence points, and a complete profile boundary is generated through connectivity analysis. In another embodiment, it is assumed that the number of pixel points of the edge features and the texture features is about 350,000 and 300,000 respectively, and about 500,000 pixel points are determined as reliable profile points after weighting, about 100,000 isolated points are removed, and finally a profile of about 400,000 continuous pixel points is formed, with a spatial accuracy of 0.15 mm.

[0064] In another embodiment, it is assumed that the resolution of the concha cavity image is 1024x1024, and each pixel corresponds to a spatial size of about 0.1 mm x 0.1 mm; after the edge features and the texture features are weighted according to the proportion of 60% / 40%, the high-confidence pixel points account for about 4.8% of the total pixel points in the profile reliability map generated; after the isolated points and the noise points are removed through connectivity analysis, a profile of about 400,000 continuous pixel points is finally formed. Refinement processing can be performed on the key points of the profile, such as adding neighborhood interpolation and smoothing operations to the corners and curved areas, so that the continuity and smoothness of the profile curve in the tortuous area are improved, and the overall spatial accuracy is maintained within 0.15 mm.

[0065] Preferably, the edge features and the texture features are used to determine the profile boundary of the concha cavity, comprising:

[0066] The weighted results of the edge feature and the texture feature are fused to generate an edge intensity score; in the edge intensity score, pixel points satisfying a preset edge intensity threshold are selected as ear cavity contour candidate points, and are connected into a continuous edge curve to remove noise points, to serve as an ear cavity contour boundary.

[0067] In an embodiment, the edge feature and the texture feature are weighted and fused according to proportions of 60% and 40%, and a contour credibility score is calculated for each pixel point; subsequently, pixel points with scores higher than a threshold of 0.7 are selected as candidate points. Connectivity analysis is performed on the candidate points to remove isolated points and noise points less than 5 pixels, and then a complete continuous contour is formed through curve connection. The final contour is composed of about 350,000 continuous pixel points, and the spatial accuracy can reach 0.15 mm, and the main curve and concave-convex structure of the ear cavity can be clearly displayed.

[0068] In another embodiment, assuming that the resolution of the original ear cavity gray image is 1024x1024, the edge feature pixel points are about 350,000, and the texture feature pixel points are about 300,000. In the edge intensity score generated after weighted fusion, high credibility pixel points account for about 15% of the total pixels, and about 500,000 points are determined as candidate contour points. After removing about 100,000 isolated points and small clusters, a contour curve of about 400,000 continuous pixel points is finally formed. Further local smoothing processing is performed on the contour key regions (such as the ear cavity tip and the curved inner corner), so that the contour continuity and smoothness are improved, and the overall spatial accuracy is still maintained at about 0.15 mm, which can be used for subsequent three-dimensional modeling or dissection analysis.

[0069] Preferably, the step S2 of generating the inlet reference surface comprises:

[0070] After the ear cavity contour boundary is obtained, equidistant sampling is performed to obtain discrete boundary coordinates; an initial reference surface is fitted using the discrete boundary coordinates, and a normal vector of the plane is calculated;

[0071] In an embodiment, the extracted ear cavity contour curve is sampled every 0.5 mm to obtain about 500 discrete boundary coordinate points. The least square plane fitting method is used to fit these discrete points into a plane to obtain an initial reference surface. By calculating the normal vector N0 of the fitted plane, the overall direction of the ear cavity contour can be represented. The initial reference surface is used for subsequent inlet correction and ear return fitting point positioning, and provides a stable reference for maintaining spatial accuracy.

[0072] In another embodiment, assuming the total length of the concha cavity profile is about 250 mm, equidistant sampling is performed at a 0.5 mm interval to obtain 500 discrete points. The initial reference plane is fitted by fitting, and the normal vector thereof has an angle of about 12° with the axial reference line of the ear canal, which exceeds the preset threshold of 10°, and thus rotation correction is required. During the fitting process, the distribution of local residual points can be recorded for subsequent optimization of the smoothness of the reference plane.

[0073] The normal vector is compared with the axial reference line of the ear canal. If the deviation between the two exceeds the preset angle threshold, the initial reference plane is corrected by rotation to maintain an orthogonal relationship with the longitudinal direction of the ear canal, so as to form the inlet reference plane;

[0074] In an embodiment, the angle θ between the normal vector N0 of the initial reference plane and the longitudinal direction vector A of the ear canal is calculated. When θ is greater than 10°, the initial reference plane is rotated by an angle of θ around the normal vector projection axis, so that the normal vector is orthogonal to the longitudinal direction of the ear canal, and a corrected inlet reference plane is obtained. After rotation correction, local smoothing processing is performed on the sampling points near the profile on the reference plane to ensure that the inlet plane is continuous and has no protrusions.

[0075] In another embodiment, the deviation between the normal vector of the initial fitted reference plane and the axial direction of the ear canal is 12°, and the deviation is reduced to about 1° after rotation correction. During the correction process, about 50 sampling points on the inlet profile are locally fine-tuned to ensure that the plane closely fits the profile while maintaining continuity and smoothness. The corrected inlet reference plane can be used to determine the position of the ear return fitting point, and the spatial accuracy is controlled to be ≤0.2 mm.

[0076] The inlet reference plane is used to determine the ear return fitting point.

[0077] In an embodiment, the profile points projected on the inlet reference plane are used to analyze the local smooth area, and the smooth area close to the profile surface is selected as the fitting point to ensure the stability of the fitting and maximize the coverage area. A final set of fitting points is determined for ear return installation or further analysis.

[0078] In another embodiment, assuming that there are about 400 profile points projected on the inlet reference plane, 50 points with the smallest local convexity are selected as candidate fitting points through curvature analysis, and finally about 30 ear return fitting points are determined through uniformity screening. The set of fitting points covers about 85%-90% of the area of the concha cavity inlet, ensures the stability and repeatability of the fitting, and facilitates subsequent ear return customization or assembly.

[0079] Preferably, the determination of the ear return fitting point using the inlet reference plane comprises:

[0080] Projecting the concha cavity profile boundary to the inlet reference plane to form a closed projection curve;

[0081] In one embodiment, a three-dimensional boundary point set (about 500 sampling points) of the concha cavity profile is first acquired, the points are projected onto the entrance reference plane along the normal vector direction to obtain a closed projection curve. Then the curve is smoothed to eliminate local spikes or noise points, ensuring that the closed curve is continuous and smooth in shape. The closed curve is used to determine the opening area of the concha cavity and the convex-concave structure, providing a stable two-dimensional reference for the selection of the fitting point.

[0082] In another embodiment, assuming that the total length of the concha cavity profile is about 250 mm, the closed projection curve obtained after projection has 500 points, and the closed curve is elliptical with a major axis of about 20 mm and a minor axis of about 15 mm. To improve accuracy, the closed curve is smoothed by cubic spline smoothing, so that the local maximum curvature of the curve does not change by more than 0.5 mm. The closed projection curve serves as the basis for subsequent fitting point determination.

[0083] The point in the closed projection curve with the smallest curvature radius and pointing towards the ear canal opening direction is identified as the antihelix fitting point, and the position coordinates of the point in the three-dimensional coordinate system are output.

[0084] In one embodiment, the local curvature radius of each point of the closed projection curve is calculated, and in combination with the projection direction of the curve point to the ear canal axis, the point with the smallest curvature radius and pointing towards the ear canal opening direction is selected as the antihelix fitting point. Then the point is mapped back to the three-dimensional space along the inverse normal vector to obtain the final position coordinates in the three-dimensional coordinate system, which are used for antihelix installation or further analysis.

[0085] In another embodiment, assuming that there are 500 points on the closed projection curve, about 5 minimum curvature points are obtained by calculating the local curvature. In combination with the screening condition of pointing towards the ear canal opening direction, the point with the smallest curvature is finally selected as the antihelix fitting point. The three-dimensional coordinates of the point are (X, Y, Z) ≈ (12.4 mm, -8.7 mm, 6.3 mm). To enhance stability, the average position of the neighboring points (±2 mm) with the smallest curvature can also be calculated to obtain the smoothed fitting point coordinates (12.5 mm, -8.6 mm, 6.2 mm), which are used for antihelix design or custom fitting devices.

[0086] Preferably, the identification of the external ear canal region according to the concha cavity profile boundary in step S3 comprises:

[0087] The concha cavity profile boundary is subjected to spatial extension analysis to determine the boundary contraction direction; in this direction, continuous image slices are extracted to the longitudinal region, and the cross-sectional gray scale of the continuous image slices is calculated; if the cross-sectional gray scale continuously decreases in the longitudinal direction, it is determined that the direction is the extension direction of the external ear canal;

[0088] In one embodiment, a three-dimensional boundary point set (approximately 500 sampling points) of the concha cavity contour is first acquired, and its local contraction / protrusion trend in three-dimensional space is analyzed. Image slices are continuously extracted into the depth region along the contraction direction, with each slice having a resolution of approximately 0.1 mm × 0.1 mm, and continuous cross-sectional grayscale values ​​are obtained. By analyzing the change in grayscale value of each cross-section with the depth direction, if the grayscale value continuously decreases, the direction is determined to be the extension direction of the external auditory canal. This method can be used to automatically identify the spatial relationship between the ear canal entrance and the depth, providing directional reference for the subsequent construction of cross-sectional sequences.

[0089] In another embodiment, assuming the concha cavity contour length is approximately 25 mm, 50 consecutive image slices are extracted along the depth direction. The average grayscale value of each slice is [200, 195, 189, 183, 178, 172, 168, 162, 158, ..., 40] (unit grayscale value 0–255). Analysis of the grayscale changes reveals a monotonically decreasing trend in grayscale values, thus determining that this direction is the extension direction of the external auditory canal. This direction allows for clear depth localization, providing an accurate benchmark for constructing the slice sequence.

[0090] Using the conchae contour boundary as the starting section, the section contour is traced frame by frame along the extension direction of the external auditory canal to establish a section sequence. In the section sequence, the centroid position of each section is calculated and connected to form a depth reference line. At the same time, the section closure around the section is monitored, and discontinuous boundary points are eliminated. The section sequence and the depth reference line are defined together as the external auditory canal region.

[0091] In one embodiment, the concha contour boundary is used as the starting section, and the section contour is traced frame by frame along the extension direction of the external auditory canal to obtain a continuous section sequence. For each section, its centroid coordinates are calculated, and the centroids are connected to form a depth reference line. Simultaneously, the closure of the section contour is monitored, and areas with incomplete section boundaries or isolated points are discarded to ensure the continuity and accuracy of the sequence. Finally, the section sequence and the depth reference line are jointly defined as the external auditory canal region for subsequent analysis of the resonator contact point or ear canal morphology.

[0092] In another embodiment, it is assumed that 50 frames of a cross-sectional sequence are acquired along the extension direction of the external auditory canal, with each frame containing approximately 100–120 sampling points. The centroid position of each cross-section is calculated and connected sequentially to form a depth reference line. Monitoring the closure of the cross-section reveals isolated points or broken boundaries in approximately 5 frames; after removing these points, the sequence remains at 45 frames. The three-dimensional length of the external auditory canal region formed by this sequence is approximately 25 mm, and the average cross-sectional diameter is approximately 6–8 mm, providing a clear spatial definition for subsequent in-ear localization or simulation modeling.

[0093] Preferably, spatial extension analysis is performed on the conchae contour boundary to determine the direction of boundary contraction, including:

[0094] Sample points are selected on the contour boundary of the concha cavity, and an extending vector in the normal direction of each sample point is calculated; during the advancing of the extending vector, image slices are extracted layer by layer, and the cross-sectional area of each slice is calculated;

[0095] In an embodiment, sample points are first selected uniformly on the contour boundary of the concha cavity (about 200), and the local normal direction of each sample point is calculated as the initial direction of the extending vector. Along the extending vector, image slices are extracted layer by layer in the longitudinal direction (each layer has a thickness of about 0.1 mm), and the cross-sectional area of each slice is calculated. By analyzing the trend of the cross-sectional area with the extending depth, the spatial extending characteristics of each sample point can be obtained, which provides a basis for subsequent boundary contraction direction determination.

[0096] In another embodiment, it is assumed that 10 image slices are extended along the normal direction of a sample point, each layer has a thickness of 0.1 mm, and the corresponding cross-sectional areas are [35, 33, 30, 28, 25, 23, 21, 19, 17, 15] respectively. By observing that the cross-sectional area gradually decreases in the longitudinal direction, it is determined that the boundary in the extending direction of the sample point is the preliminary contraction direction. The process is repeated for 200 sample points, and if the preliminary contraction directions of most sample points (about 160) are consistent, the direction is determined as the boundary contraction direction of the overall concha cavity contour.

[0097] If the cross-sectional area gradually decreases with the extending depth, it is determined that the extending direction is the preliminary contraction direction of the boundary. In the extending vector results of multiple sample points, if the preliminary contraction directions of most vectors are consistent, the direction is determined as the boundary contraction direction.

[0098] In an embodiment, the extending vectors of all sample points and the corresponding cross-sectional area variation trends are counted, and the area reduction rate of each vector in the normal direction is calculated. If the area continuously decreases with the depth in most sample points, it is determined that the directions of these vectors are the preliminary contraction directions of the boundary. Through the statistical analysis and clustering of the preliminary contraction directions, the vector direction with the highest consistency is selected as the overall boundary contraction direction of the concha cavity, which provides a clear direction reference for subsequent outer ear canal extending tracking or cross-sectional sequence construction.

[0099] In another embodiment, it is assumed that the extending vectors of 160 sample points out of 200 sample points have a continuous decrease in the cross-sectional area in the normal direction, and the average area reduction rate is per layer; the remaining 40 sample points have intermediate local increases or noise fluctuations. After direction clustering analysis, it is found that the directions of the 160 sample points differ within ± 5°, and the direction is determined as the overall boundary contraction direction of the concha cavity. The contraction direction can be used to guide the subsequent extraction of cross sections in the direction of the outer ear canal and the construction of the ear canal region.

[0100] Preferably, the ear canal image is collected in step S3, the ear canal centerline is extracted and the cross-sectional size is measured, and the eardrum curved surface is constructed, including:

[0101] The ear canal image is collected, the ear canal centerline is extracted, and the cross-sectional fitting is performed on the ear canal image. The cross-sectional contour is extracted and the cross-sectional size is calculated. The cross-sectional contour is connected by spline interpolation in the order of depth, and the closed contour with high change in curvature at the eardrum end is identified. The closed contour is sealed to construct the eardrum curved surface.

[0102] In an embodiment, a high-resolution ear canal endoscope or CT image (resolution about 0.1 mm) is used to continuously collect the external ear canal, generating a sequence of continuous images in the depth direction. The ear canal centerline is extracted by image processing algorithms (such as gray centroid tracking or pipeline fitting), and a cross-sectional image is taken every 0.2 mm along the centerline to ensure cross-sectional continuity and reconstruction accuracy. Threshold segmentation (such as Canny) is applied to each cross-section to extract the closed contour, calculate the contour area, perimeter, and major and minor axis dimensions, and other cross-sectional parameters. The cross-sectional contour is connected by spline interpolation in the order of depth to ensure smooth transition between adjacent cross-sections. For the eardrum end cross-section, the closed contour with a prominent change in curvature is identified, and sealing is performed at necessary locations to construct a complete eardrum curved surface. The point cloud of all cross-sectional contours along the ear canal centerline is connected by spline interpolation and spatial registration to generate a continuous three-dimensional eardrum curved surface mesh. The smoothness of the eardrum end closed contour and the continuity of the curved surface are verified by calculating the normal and curvature of the curved surface.

[0103] In another embodiment, it is assumed that the collected external ear canal image has a depth range of 20 mm, and 100 cross-sections are taken every 0.2 mm. A smooth curve is obtained by centerline fitting, with a three-dimensional coordinate range of , ensuring that the centerline is smooth and continuous in the depth direction. Among the 100 cross-sectional contours, frames 95 to 100 are located at the eardrum end, with cross-sectional areas of and perimeters of . The high change point in curvature appears as a sharp peak at frame 98, and the closed contour is completed by local sealing. After spline interpolation connection, the eardrum curved surface has a height of about 5 mm, ensuring continuous curved surface reconstruction from the external ear canal to the eardrum end. It is assumed that the eardrum curved surface mesh after spline interpolation connection contains about 1200 vertices, with a maximum local normal deviation of 2.1° and an average normal deviation of 0.8°. The curved surface continuity and smoothness meet the requirements of eardrum shape reconstruction, and can be used for subsequent three-dimensional ear canal modeling or surgical navigation simulation.

[0104] Preferably, the present specification also provides an acquisition system for a three-dimensional eardrum model for executing the acquisition method for a three-dimensional eardrum model as described above, the acquisition system for a three-dimensional eardrum model comprising:

[0105] The image acquisition module 101 is configured to control the insertion of the acquisition probe into the entrance of the ear canal to acquire the concha cavity image if the acquisition parameter of the acquisition probe is lower than the preset acquisition parameter threshold.

[0106] The fitting point determination module 102 is configured to recognize the contour boundary of the concha cavity by using the concha cavity image, generate an entrance reference plane, and determine the anti-helix fitting point.

[0107] The eardrum surface construction module 103 is configured to recognize the outer ear canal region according to the contour boundary of the concha cavity, acquire the outer ear canal image, extract the ear canal center line and measure the cross-sectional size, and construct the eardrum surface.

[0108] The ear mold file export module 104 is configured to perform hole repair and smoothing processing on the eardrum surface, verify the rationality of the eardrum structure, and export a standard three-dimensional ear mold file.

[0109] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, the scope of the present application being defined by the appended claims and not by the above description, and it is intended to encompass all variations falling within the meaning and the scope of the equivalent elements of the claims of the application.

[0110] The above description is merely one specific implementation of the present application, which enables those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for acquisition of a three-dimensional model of an ear mold, characterized in that, The method comprises the following steps: Step S1: If the acquisition parameter of the acquisition probe is lower than the preset acquisition parameter threshold, the acquisition probe is controlled to be inserted into the entrance of the ear canal to acquire an image of the concha cavity; Step S2: The contour boundary of the concha cavity is recognized by using the image of the concha cavity to generate an entrance reference surface and determine a reentrant point, comprising: After the contour boundary of the concha cavity is acquired, equidistant sampling is performed to obtain discrete boundary coordinates; the initial reference surface is fitted by using the discrete boundary coordinates, and the normal vector of the initial reference surface is calculated; The normal vector is compared with the axial reference line of the ear canal, and if the deviation between the two exceeds the preset angle threshold, the initial reference surface is rotated and corrected so that it is orthogonal to the longitudinal direction of the ear canal to form the entrance reference surface; The reentrant point is determined by using the entrance reference surface, comprising: The contour boundary of the concha cavity is projected onto the entrance reference surface to form a closed projection curve; The point with the smallest radius of curvature in the closed projection curve and oriented towards the opening direction of the ear canal is recognized as the reentrant point, and the position coordinates of the reentrant point in the three-dimensional coordinate system are output. Step S3: The outer ear canal region is recognized according to the contour boundary of the concha cavity, the image of the outer ear canal is acquired, the ear canal centerline is extracted and the cross-sectional size is measured, and the eardrum curved surface is constructed, wherein the outer ear canal region is recognized according to the contour boundary of the concha cavity in step S3, comprising: The spatial extension analysis is performed on the contour boundary of the concha cavity to determine the boundary contraction direction; in this direction, continuous image slices are extracted towards the longitudinal region, and the cross-sectional gray scale of the continuous image slices is calculated; if the cross-sectional gray scale continuously decreases along the longitudinal direction, it is determined that the direction is the extension direction of the outer ear canal; The contour boundary of the concha cavity is taken as the starting cross section, and the cross section contour is tracked frame by frame along the extension direction of the outer ear canal to establish a cross section sequence; in the cross section sequence, the centroid position of each cross section is calculated and connected to form a longitudinal reference line, and the cross-sectional closedness of the cross section periphery is monitored to remove non-continuous boundary points; the cross section sequence and the longitudinal reference line are collectively defined as the outer ear canal region; Step S4: The eardrum curved surface is hole-repaired and smoothed, the rationality of the eardrum structure is verified, and a standard three-dimensional ear mold file is derived.

2. The method for acquiring an ear mold three-dimensional model according to claim 1, wherein, In step S2, the contour boundary of the concha cavity is recognized by using the image of the concha cavity, comprising: The image of the concha cavity is converted into a gray-scale image, and the gray-scale gradient amplitude is extracted as an edge feature; For any pixel point in the gray-scale image, the gray-scale difference between each pixel point in the neighborhood and the center pixel point is calculated in the neighborhood centered on the pixel point; the direction of the line connecting the pixel point with the maximum gray-scale difference in the neighborhood to the pixel point with the minimum gray-scale difference is taken as the texture feature of the center pixel point; The contour boundary of the concha cavity is determined by using the edge feature and the texture feature.

3. The method for acquiring an ear mold three-dimensional model according to claim 2, wherein, The contour boundary of the concha cavity is determined by using the edge feature and the texture feature, comprising: The weighted results of the edge feature and the texture feature are fused to generate an edge intensity score; in the edge intensity score, the pixel points satisfying the preset edge intensity threshold are selected as the concha cavity contour candidate points, connected into a continuous edge curve, and the noise points are removed to serve as the contour boundary of the concha cavity.

4. The method for acquiring an ear mold three-dimensional model according to claim 1, wherein, The spatial extension analysis is performed on the contour boundary of the concha cavity to determine the boundary contraction direction, comprising: Sample points are selected on the contour boundary of the concha cavity, and an extending vector in the normal direction of each sample point is calculated; during the advancing of the extending vector, image slices are extracted layer by layer and the cross-sectional area of the slice is calculated; If the cross-sectional area gradually decreases with the extending depth, it is determined that the extending direction is the preliminary contraction direction of the boundary; in the extending vector results of multiple sample points, if the preliminary contraction directions of most vectors are consistent, the direction is determined as the contraction direction of the boundary.

5. The method for acquiring an ear mold three-dimensional model according to claim 1, wherein, The ear canal image is collected in step S3, the ear canal center line is extracted and the cross-sectional size is measured, and the eardrum curved surface is constructed, including: The ear canal image is collected, the ear canal center line is extracted, and the cross-sectional fitting of the ear canal image is performed, the cross-sectional contour is extracted and the cross-sectional size is calculated; the cross-sectional contour is connected by spline interpolation in the order of depth, and the closed contour with high curvature change at the eardrum end is identified, and the closed contour is sealed, so as to construct the eardrum curved surface.

6. A computer readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to realize the acquisition method of the ear mold three-dimensional model as claimed in any one of claims 1 to 5.

7. An acquisition system for a three-dimensional model of an ear mold, characterized in that, The acquisition system of the ear mold three-dimensional model for executing the acquisition method of the ear mold three-dimensional model as claimed in claim 1, comprising: An image acquisition module is configured to control the collection probe to be inserted into the entrance of the ear canal if the collection parameter of the collection probe is lower than the preset collection parameter threshold, and to acquire the concha cavity image; A fitting point determination module is configured to identify the contour boundary of the concha cavity by using the concha cavity image, to generate an entrance reference surface, and to determine the retroconcha fitting point; An eardrum curved surface construction module is configured to identify the outer ear canal region according to the contour boundary of the concha cavity, to collect the outer ear canal image, to extract the ear canal center line and measure the cross-sectional size, and to construct the eardrum curved surface; An ear mold file export module is configured to perform hole repair and smoothing processing on the eardrum curved surface, to verify the rationality of the eardrum structure, and to export a standard three-dimensional ear mold file.

Images