Ossicular chain size measurement method and system, equipment, storage medium and program product

Abstract

The embodiment of the invention provides an ossicular chain size measurement method and system, equipment, a storage medium and a program product, segmentation results corresponding to a bone hammering object, an incus object and a stapedius object are obtained through segmentation from a collected medical image including an ossicular chain object, and based on the segmentation results, the size of the ossicular chain is measured. And establishing three-dimensional surfaces corresponding to the hammered bone object, the incus object and the stapes object respectively, determining feature points corresponding to the anatomical part from the three-dimensional surfaces, and calculating the size to be measured based on the feature points according to the corresponding relationship between the anatomical part and the size to be measured. According to the scheme of the embodiment of the invention, the measurement efficiency and accuracy of the size of the ossicular chain are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of medical data processing, and in particular to a method and system, device, storage medium and program product for measuring the size of the ossicular chain. Background Art

[0002] The ossicular chain, the smallest group of bones in the human body, consists of the malleus, incus, and stapes. These three interconnected members form the ossicular chain, a vital part of the middle ear and play a crucial role in sound conduction. Abnormalities in this chain can lead to conductive hearing loss, which is typically treated by creating an ossicular chain prosthesis. Clinically, doctors typically manually measure the ossicular chain from two-dimensional CT images to tailor the size of the prosthesis. Therefore, accurately, quickly, and automatically measuring the size of large quantities of ossicular chains has become a pressing challenge. Summary of the Invention

[0003] The embodiments of the present application provide a method and system, device, storage medium and program product for measuring the size of the ossicular chain, so as to improve the efficiency and accuracy of measuring the size of the ossicular chain.

[0004] In a first aspect, the present application provides a method for measuring the size of an ossicular chain, comprising:

[0005] Acquire a medical image acquired by capturing an ear object of a target user, wherein the medical image includes an ossicular chain object, and the ossicular chain object includes a malleus object, an incus object, and a stapes object;

[0006] Obtaining segmentation results corresponding to the malleus object, the incus object, and the stapes object respectively from the medical image segmentation;

[0007] Based on the segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively, a first three-dimensional surface corresponding to the malleus object, a second three-dimensional surface corresponding to the incus object, and a third three-dimensional surface corresponding to the stapes object are established; wherein the first three-dimensional surface, the second three-dimensional surface, and the third three-dimensional surface constitute a fourth three-dimensional surface corresponding to the ossicular chain object;

[0008] determining first feature points corresponding to a plurality of first anatomical parts respectively from the first three-dimensional surface, determining second feature points corresponding to a plurality of second anatomical parts respectively from the second three-dimensional surface, and determining third feature points corresponding to a plurality of third anatomical parts respectively from the third three-dimensional surface;

[0009] According to the correspondence between the multiple first anatomical parts and the first size to be measured in the malleus object, the first size to be measured is calculated based on multiple first feature points, and according to the correspondence between the multiple second anatomical parts and the second size to be measured in the incus object, the second size to be measured is calculated based on multiple second feature points, and according to the correspondence between the multiple third anatomical parts and the third size to be measured in the stapes object, the third size to be measured is calculated based on multiple third feature points; wherein, the ossicular chain size includes the first size to be measured, the second size to be measured and the third size to be measured.

[0010] In a second aspect, an embodiment of the present application provides an ossicular chain measurement system, comprising a segmentation module, a reconstruction module, a feature point determination module, and a measurement module;

[0011] The segmentation module is used to obtain segmentation results corresponding to the malleus object, the incus object and the stapes object respectively from the medical image segmentation; wherein the medical image is obtained by collecting ear objects for the target user, the medical image includes ossicular chain objects, and the ossicular chain objects include the malleus object, the incus object and the stapes object;

[0012] The reconstruction module is used to establish a first three-dimensional surface corresponding to the malleus object, a second three-dimensional surface corresponding to the incus object, and a third three-dimensional surface corresponding to the stapes object based on the segmentation results corresponding to the malleus object, the incus object, and the stapes object respectively; wherein the first three-dimensional surface, the second three-dimensional surface, and the third three-dimensional surface constitute a fourth three-dimensional surface corresponding to the ossicular chain object;

[0013] The feature point determination module is configured to determine first feature points corresponding to a plurality of first anatomical parts respectively from the first three-dimensional surface, determine second feature points corresponding to a plurality of second anatomical parts respectively from the second three-dimensional surface, and determine third feature points corresponding to a plurality of third anatomical parts respectively from the third three-dimensional surface;

[0014] The measurement module is used to calculate the first size to be measured based on a plurality of first feature points according to the correspondence between the plurality of first anatomical parts and the first size to be measured in the malleus object, and to calculate the second size to be measured based on a plurality of second feature points according to the correspondence between the plurality of second anatomical parts and the second size to be measured in the incus object, and to calculate the third size to be measured based on a plurality of third feature points according to the correspondence between the plurality of third anatomical parts and the third size to be measured in the stapes object; wherein the ossicular chain size includes the first size to be measured, the second size to be measured and the third size to be measured.

[0015] In a third aspect, the present application provides a computing device comprising a storage component and a processing component; the storage component stores one or more computer program instructions, the computer program instructions are called and executed by the processing component, and the processing component executes the one or more computer program instructions to implement the ossicular chain size measurement method as described in the first aspect.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, wherein the computer program is executed by a computer to implement the ossicular chain size measurement method as described in the first aspect.

[0017] In a fifth aspect, the present application provides a computer program product storing a computer program, which, when executed by a computer, implements the method for measuring the size of the ossicular chain as described in the first aspect.

[0018] In an embodiment of the present application, segmentation results corresponding to the malleus object, the incus object and the stapes object are obtained from a medical image including the ossicular chain object, and based on the segmentation results, three-dimensional surfaces corresponding to the malleus object, the incus object and the stapes object are established, feature points corresponding to the anatomical parts are determined from the three-dimensional surfaces, and according to the correspondence between the anatomical parts and the dimensions to be measured, the dimensions to be measured are calculated based on the feature points, thereby realizing automatic measurement of the ossicular chain dimensions and improving measurement efficiency and accuracy.

[0019] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 A flow chart of an embodiment of a method for measuring the size of an ossicular chain provided by the present application is shown;

[0022] Figure 2 A schematic structural diagram of a first three-dimensional surface, a second three-dimensional surface, a third three-dimensional surface, and a fourth three-dimensional surface in a practical application is shown;

[0023] Figure 3 A schematic structural diagram of an ossicular chain size measurement system in practical application is shown;

[0024] Figure 4 A schematic structural diagram of an embodiment of an ossicular chain size measuring device provided by the present application is shown;

[0025] Figure 5A schematic structural diagram of an embodiment of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0026] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0028] The technical solution of the embodiment of the present application is applicable to medical data processing scenarios, especially to the scenario of measuring the size of the ossicular chain. Currently, the measurement of the size of the ossicular chain is often achieved by in vitro measurement or manual measurement on two-dimensional CT images, which is inefficient and not very accurate.

[0029] Therefore, in order to improve the measurement efficiency and accuracy of the size of the ossicular chain, the inventors proposed the technical solution of the present application, including: obtaining a medical image collected from the ear object of the target user, the medical image including the ossicular chain object, and the ossicular chain object including the malleus object, the incus object and the stapes object; obtaining segmentation results corresponding to the malleus object, the incus object and the stapes object respectively from the medical image segmentation; establishing a first three-dimensional surface corresponding to the malleus object, a second three-dimensional surface corresponding to the incus object, and a third three-dimensional surface corresponding to the stapes object based on the segmentation results corresponding to the malleus object, the incus object and the stapes object respectively; wherein the first three-dimensional surface, the second three-dimensional surface and the third three-dimensional surface constitute the fourth three-dimensional surface corresponding to the ossicular chain object; determining from the first three-dimensional surface the fourth three-dimensional surface corresponding to the plurality of first anatomical parts. and determining, from the second three-dimensional surface, second feature points respectively corresponding to a plurality of second anatomical parts, and third feature points respectively corresponding to a plurality of third anatomical parts, from the third three-dimensional surface; calculating, based on the plurality of first feature points, the first size to be measured according to the correspondence between the plurality of first anatomical parts and the first size to be measured in the malleus object, and calculating, based on the plurality of second feature points, the second size to be measured according to the correspondence between the plurality of second anatomical parts and the second size to be measured in the incus object, and calculating, based on the plurality of third feature points, the third size to be measured according to the correspondence between the plurality of third anatomical parts and the third size to be measured in the stapes object; wherein, the ossicular chain size includes the first size to be measured, the second size to be measured and the third size to be measured.

[0030] By segmenting the medical image including the ossicular chain object, segmentation results corresponding to the malleus object, incus object and stapes object are obtained, and based on the segmentation results, three-dimensional surfaces corresponding to the malleus object, incus object and stapes object are established, feature points corresponding to the anatomical parts are determined from the three-dimensional surfaces, and according to the correspondence between the anatomical parts and the dimensions to be measured, the dimensions to be measured are calculated based on the feature points, thereby realizing automatic measurement of the ossicular chain dimensions and improving measurement efficiency and accuracy.

[0031] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0032] The technical solutions of the embodiments of the present application can be applied to a system architecture including a client and a server, where the client and the server are connected via a network. The network provides a medium for the communication link between the client and the server. The network can include various connection types, such as wired or wireless communication links or fiber optic cables.

[0033] The client can interact with the server through the network to send medical images or receive measurement results, etc.

[0034] Among them, the client can be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5, Hypertext Markup Language 5th Edition) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The client can be deployed in an electronic device and needs to rely on the device to run or certain apps in the device to run, etc. The electronic device can, for example, have a display screen and support information browsing, etc., such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. For ease of understanding, various other types of applications can usually be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0035] The server side may include servers that provide various services, such as servers that segment medical images and reconstruct based on segmentation results.

[0036] It should be noted that the server can be implemented as a distributed server cluster consisting of multiple servers or a single server. The server can also be a server in a distributed system or a server integrated with blockchain. The server can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host equipped with artificial intelligence technology.

[0037] It should be noted that the ossicular chain size measurement method provided in the embodiments of the present application is generally performed by the server. However, in other embodiments of the present application, the client may also have similar functions to the server, thereby performing the ossicular chain size measurement method provided in the embodiments of the present application. In other embodiments, the ossicular chain size measurement method provided in the embodiments of the present application may also be performed jointly by the client and the server.

[0038] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0039] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0040] Figure 1 This is a flow chart of an embodiment of a method for measuring the size of an ossicular chain provided in the present application. The method may include the following steps.

[0041] 101: Obtain a medical image of an ear object of a target user.

[0042] In an embodiment of the present application, the medical image can be acquired by using CT scanning (Computed Tomography) technology, such as U-HRCT scanning (Ultra-High Resolution Computed Tomography) technology, to collect the ear object of the target user. The ear object can be the left ear or the right ear. The medical image can include an ossicular chain object. The ossicular chain object can include a malleus object, an incus object, and a stapes object, and the three are connected to each other.

[0043] In a practical application, a U-HRCT scanner may be used to capture the ear of a target user to obtain multiple medical images, wherein the slice thickness and interval may both be set to 0.1 mm.

[0044] 102: Segment the medical image to obtain segmentation results corresponding to the malleus object, the incus object, and the stapes object.

[0045] Among them, various image segmentation algorithms such as level set method and deep learning method can be used to segment the medical image to obtain segmentation results corresponding to the malleus object, incus object and stapes object respectively.

[0046] In a practical application, the TransUnet segmentation algorithm (a hybrid encoding and decoding segmentation network that combines Transformer (a neural network architecture based on the self-attention mechanism) and CNN (convolutional neural network)) can be used as the backbone network model to implement it, which will be explained in subsequent embodiments.

[0047] 103: Based on the segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively, a first three-dimensional surface corresponding to the malleus object, a second three-dimensional surface corresponding to the incus object, and a third three-dimensional surface corresponding to the stapes object are established.

[0048] Specifically, a plurality of 3D reconstruction algorithms, such as surface rendering algorithms and volume rendering algorithms, can be used to reconstruct a first 3D surface of the malleus object based on the segmentation results of the malleus object; a second 3D surface of the incus object based on the segmentation results of the incus object; and a third 3D surface of the stapes object based on the segmentation results of the stapes object. Furthermore, based on the connection between the first 3D surface, the second 3D surface, and the third 3D surface, a fourth 3D surface corresponding to the ossicular chain object can be formed from the first 3D surface, the second 3D surface, and the third 3D surface.

[0049] For ease of understanding, Figure 2 FIG1 shows a schematic diagram of the structure of a first three-dimensional surface, a second three-dimensional surface, a third three-dimensional surface and a fourth three-dimensional surface in an actual application. Figure 2 As shown, the first three-dimensional surface 201 is the three-dimensional surface of the malleus object, the second three-dimensional surface 202 is the three-dimensional surface of the incus object, the third three-dimensional surface 203 is the three-dimensional surface of the stapes object, and the fourth three-dimensional surface 204 is the three-dimensional surface of the ossicular chain object.

[0050] 104: Determine first feature points corresponding to multiple first anatomical parts from the first three-dimensional surface, determine second feature points corresponding to multiple second anatomical parts from the second three-dimensional surface, and determine third feature points corresponding to multiple third anatomical parts from the third three-dimensional surface.

[0051] The anatomical part can be pre-set based on the size to be measured. For example, the size to be measured of the malleus object can include the length of the malleus handle, that is, the maximum distance from the lateral process of the malleus to the tip of the malleus handle, and the first anatomical part can include the lateral process of the malleus and the tip of the malleus handle. For another example, the size to be measured of the incus object can include the width of the incus, that is, the farthest distance from the tip of the short crus of the incus to the protruding part of the hammer-anvil articular surface (the hammer head and the incus body form a joint), and the second anatomical part can include the tip of the short crus of the incus and the location of the protruding part of the hammer-anvil articular surface, etc., which can be set according to actual needs.

[0052] Based on a pre-defined anatomical location, corresponding feature points can be detected from the reconstructed 3D surface. For example, feature points can be detected based on the curvature values ​​of the 3D surface mesh vertices or local shape information of the 3D surface, such as protrusions and tips. The specific implementation will be described in subsequent embodiments.

[0053] 105: According to the correspondence between the multiple first anatomical parts and the first size to be measured in the malleus object, based on the multiple first feature points, calculate the first size to be measured; according to the correspondence between the multiple second anatomical parts and the second size to be measured in the incus object, based on the multiple second feature points, calculate the second size to be measured; and according to the correspondence between the multiple third anatomical parts and the third size to be measured in the stapes object, based on the multiple third feature points, calculate the third size to be measured.

[0054] The ossicular chain size may include a first size to be measured, a second size to be measured, and a third size to be measured.

[0055] Based on the feature points detected in the above steps, geometric information can be calculated to measure the dimensions of the malleus, incus, and stapes. Specifically, based on the correspondence between the dimensions to be measured and the anatomical parts, distance, angle, and volume calculations can be performed on the feature points corresponding to the anatomical parts to obtain the corresponding dimensions to be measured.

[0056] For example, if the dimensions to be measured for a malleus object include the length of the malleus handle, and the corresponding first anatomical part includes the lateral process of the malleus and the tip of the malleus handle, then the distance between the first feature point corresponding to the lateral process of the malleus and the first feature point corresponding to the tip of the malleus handle can be calculated, and the calculated result can be used as the length of the malleus handle. For another example, if the dimensions to be measured for an incus object include the width of the incus, and the second anatomical part includes the tip of the short crus of the incus and the protrusion of the anvil-hammer articular surface, then the distance between the second feature point corresponding to the tip of the short crus of the incus and the second feature point corresponding to the protrusion of the anvil-hammer articular surface can be calculated, and the calculated result can be used as the width of the incus, and so on.

[0057] Optionally, considering the connection relationship between the incus object and the stapes object in the ossicular chain, the fourth dimension to be measured can also be calculated based on the corresponding relationship between the plurality of second anatomical parts and the third anatomical parts and the fourth dimension to be measured between the incus object and the stapes object, based on the plurality of second characteristic points and the plurality of third characteristic points. For example, the fourth dimension to be measured can be the angle of the joint between the incus object and the stapes object. The ossicular chain size may include the fourth dimension to be measured, the first dimension to be measured, the second dimension to be measured, and the third dimension to be measured. This will be described in subsequent embodiments.

[0058] Of course, the connection relationship between the malleus object and the incus object in the ossicular chain can also be considered to calculate the connection parameters of the joint between the malleus object and the incus object, such as the angle, etc., which can be set according to actual needs, and this application does not limit this.

[0059] In this embodiment, segmentation results corresponding to the malleus object, incus object and stapes object are obtained from a medical image including the ossicular chain object, and based on the segmentation results, three-dimensional surfaces corresponding to the malleus object, incus object and stapes object are established, and feature points corresponding to the anatomical parts are determined from the three-dimensional surfaces. According to the correspondence between the anatomical parts and the dimensions to be measured, the dimensions to be measured are calculated based on the feature points, thereby realizing automatic measurement of the ossicular chain dimensions and improving measurement efficiency and accuracy.

[0060] The image segmentation process is described below.

[0061] To improve segmentation accuracy and thus measurement accuracy, a multi-view fusion algorithm can be used. In some embodiments, the medical image may include a coronal image of the ear, a sagittal image of the ear, and a cross-sectional image of the ear. The coronal image of the ear may refer to a CT image acquired based on a coronal scan, the sagittal image of the ear may refer to a CT image acquired based on a sagittal scan, and the cross-sectional image of the ear may refer to a CT image acquired based on a cross-sectional scan.

[0062] Based on this, the segmentation results corresponding to the malleus object, the incus object, and the stapes object respectively obtained from the medical image segmentation may include:

[0063] Using an image segmentation model, segmenting the ear coronal image to obtain first-perspective segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively; segmenting the ear sagittal image to obtain second-perspective segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively; and segmenting the ear transverse image to obtain third-perspective segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively;

[0064] Based on the first perspective segmentation result, second perspective segmentation result and third perspective segmentation result corresponding to the malleus object, the segmentation result of the malleus object is obtained, and based on the first perspective segmentation result, second perspective segmentation result and third perspective segmentation result corresponding to the incus object, the segmentation result of the incus object is obtained, and based on the first perspective segmentation result, second perspective segmentation result and third perspective segmentation result corresponding to the stapes object, the segmentation result of the stapes object is obtained.

[0065] Among them, the image segmentation model is pre-trained based on training samples and training labels. The training samples may include the sample user's ear coronal image, ear sagittal image and ear cross-sectional image. The training labels may include the sample user's malleus object segmentation results, incus object segmentation results and stapes object segmentation results.

[0066] In this embodiment, the image segmentation model can use the TransUnet segmentation algorithm (a hybrid encoder-decoder segmentation network that combines the Transformer (a neural network architecture based on the self-attention mechanism) and the CNN (convolutional neural network)) as the backbone network model. The image segmentation model can include a CNN feature encoder, a Transformer encoder, and a CNN decoder.

[0067] Specifically, the coronal, sagittal, and cross-sectional images of the ear can be fed into the image segmentation model. A CNN feature encoder is used to extract detailed features from the input image, a Transformer encoder is used to extract global context features, and a CNN decoder is used to restore the image to its original input size to obtain the segmentation results for the corresponding viewpoints. For multi-view segmentation results, voxel point category probabilities can be predicted for each viewpoint. The probability prediction results from multiple views are then accumulated and maximum likelihood estimated to obtain a multi-view fusion segmentation result.

[0068] Optionally, before segmentation, the captured image may be subjected to a region of interest extraction process, and segmentation may be performed based on the region of interest image. The region of interest extraction process may be implemented by reference to conventional techniques, and this application does not impose any limitation thereto.

[0069] In this embodiment, the coronal image, sagittal image and cross-sectional image of the ear are used to segment and fuse the ossicular chain from the coronal plane, sagittal plane and cross-sectional plane, respectively, to obtain the segmentation results corresponding to the malleus object, incus object and stapes object, respectively. By adopting a multi-perspective fusion algorithm, the complementary information between different perspectives is effectively utilized, the segmentation accuracy is improved, the accuracy of the three-dimensional surface reconstructed based on the segmentation results is further improved, and the accuracy of the ossicular chain size measurement based on the feature points in the three-dimensional surface is improved.

[0070] In practical applications, due to the complex shape of stapes object, segmentation difficulty is larger, in order to improve the segmentation accuracy of stapes object, in some embodiments, active contour loss function (Active Contour Loss) can be introduced, namely, contour length constraint and boundary fitting condition are introduced in loss function, above-mentioned image segmentation model is trained, to improve the precision of this image segmentation model, thus improve the accuracy of the stapes object obtained by utilizing image segmentation model segmentation.Wherein, the loss function of this image segmentation model can be constructed jointly based on Dice loss function (a kind of loss function for image segmentation task, is intended to maximize the similarity between segmentation result and true label), cross entropy loss function and active contour loss function.

[0071] By introducing active contour loss as a constraint, together with Dice loss and cross entropy loss to guide the training of the image segmentation model, the accuracy of the image segmentation model is improved, thereby improving the accuracy and completeness of stapes segmentation using the image segmentation model.

[0072] After the segmentation is completed, the ossicular chain object can be reconstructed in three dimensions based on the segmentation results. The reconstruction process is described below.

[0073] In some embodiments, based on the segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively, establishing a first three-dimensional surface corresponding to the malleus object, a second three-dimensional surface corresponding to the incus object, and a third three-dimensional surface corresponding to the stapes object may include:

[0074] Based on the subvoxel data in the segmentation results of the malleus object, an isosurface extraction algorithm is used to establish a first three-dimensional surface corresponding to the malleus object; based on the subvoxel data in the segmentation results of the incus object, an isosurface extraction algorithm is used to establish a second three-dimensional surface corresponding to the incus object; based on the subvoxel data in the segmentation results of the stapes object, an isosurface extraction algorithm is used to establish a third three-dimensional surface corresponding to the stapes object.

[0075] Among them, the marching cubes algorithm is a voxel-level reconstruction method, which has been widely used in medical fields such as reconstructing the external contours of the human body and internal tissues and organs.

[0076] In the present embodiment, the subvoxel data in the segmentation result of malleus object can be obtained by using, for example, level set method, wherein, subvoxel can refer to the volume element smaller than voxel.Based on the subvoxel data, the isosurface extraction algorithm is utilized to reconstruct the first three-dimensional surface of malleus object.In like manner, the subvoxel data in the segmentation result of incus object can be based on the isosurface extraction algorithm to set up the second three-dimensional surface of incus object, and the subvoxel data in the segmentation result of stapes object can be based on the isosurface extraction algorithm to set up the third three-dimensional surface of stapes object.Specific process can be with reference to the isosurface extraction in the traditional scheme and reconstruct the realization of three-dimensional surface, and the application does not go into details about this.

[0077] Optionally, the reconstructed three-dimensional surface may be smoothed using, for example, a low-pass filter (a windowed sinc function interpolation kernel) to improve the reconstruction accuracy of the three-dimensional surface and facilitate subsequent feature point recognition and size measurement.

[0078] After the three-dimensional surface reconstruction is completed, the ossicular chain size can be measured based on the feature points in the three-dimensional surface. The measurement process is described below. In some embodiments, determining first feature points corresponding to multiple first anatomical parts from the first three-dimensional surface may include:

[0079] Selecting a plurality of first candidate points whose curvature values ​​meet a first curvature requirement from a plurality of mesh vertices of the first three-dimensional surface;

[0080] Selecting, from the plurality of first candidate points, a plurality of first feature points whose distances from the boundary of the first three-dimensional surface meet a first distance requirement;

[0081] A correspondence between the plurality of first characteristic points and the plurality of first anatomical parts is established, and based on the correspondence, first characteristic points respectively corresponding to the plurality of first anatomical parts are determined.

[0082] Similarly, determining second feature points corresponding to the plurality of second anatomical parts respectively from the second three-dimensional surface may include:

[0083] Selecting a plurality of second candidate points whose curvature values ​​meet a second curvature requirement from a plurality of mesh vertices of the second three-dimensional surface;

[0084] Selecting, from the plurality of second candidate points, a plurality of second feature points whose distances from the boundary of the second three-dimensional surface meet a second distance requirement;

[0085] A second correspondence between the plurality of second characteristic points and the plurality of second anatomical parts is established, and based on the second correspondence, second characteristic points respectively corresponding to the plurality of second anatomical parts are determined.

[0086] Similarly, determining third feature points corresponding to the third anatomical parts from the third three-dimensional surface may include:

[0087] selecting a plurality of third candidate points whose curvature values ​​meet a third curvature requirement from a plurality of mesh vertices of the third three-dimensional surface;

[0088] selecting, from the plurality of third candidate points, a plurality of third feature points whose distances from the boundary of the third three-dimensional surface satisfy a third distance requirement;

[0089] A third correspondence between the plurality of third characteristic points and the plurality of third anatomical parts is established, and based on the third correspondence, third characteristic points respectively corresponding to the plurality of third anatomical parts are determined.

[0090] In the embodiment of the present application, it is considered that in the actual measurement process, the shape characteristics of the anatomical part corresponding to the size to be measured are usually protrusions, tips, etc., and the local surface curvature is relatively high. Therefore, the curvature parameters describing the local shape characteristics of the surface, such as Gaussian curvature, mean curvature, etc., corresponding to the multiple mesh vertices of the three-dimensional surface can be calculated. Based on the curvature values, candidate points that conform to the anatomical part characteristics in shape, that is, the curvature values ​​meet the curvature requirements, can be selected. For example, the curvature requirements can be met by a curvature value greater than a preset curvature threshold. In addition, the boundary information of the three-dimensional surface can also be determined. For example, the boundary information of the three-dimensional surface of a single bone can be extracted using a bounding box technique. From the above candidate points, feature points located near the boundary, that is, the distance between the feature points and the boundary meets the distance requirements, can be selected. The distance requirements can be met by a distance less than a preset distance threshold. After determining the feature points, a correspondence between the feature points and the anatomical part can be established, so that based on the correspondence, the feature points corresponding to the anatomical part can be determined.

[0091] Taking the malleus object as an example, curvature values ​​corresponding to multiple mesh vertices of a first three-dimensional surface can be calculated. From these, multiple first candidate points are selected whose curvature values ​​meet a first curvature requirement. Meeting the first curvature requirement can mean that the curvature value is greater than a first curvature threshold. Then, from these multiple first candidate points, multiple first feature points are selected whose distances from the boundary of the first three-dimensional surface meet a first distance requirement. Meeting the first distance requirement can mean that the distances are less than a first distance threshold. Based on these multiple first feature points, first feature points corresponding to multiple first anatomical parts can be determined.

[0092] Similarly, multiple second characteristic points corresponding to the second anatomical parts and multiple third characteristic points corresponding to the third anatomical parts can be determined, which will not be repeated.

[0093] It should be noted that satisfying the second curvature requirement may mean that the curvature value is greater than the second curvature threshold, and satisfying the second distance requirement may mean that the distance is less than the second distance threshold. Satisfying the third curvature requirement may mean that the curvature value is greater than the third curvature threshold, and satisfying the third distance requirement may mean that the distance is less than the third distance threshold. Furthermore, the first, second, and third curvature thresholds may be the same or different, and the first, second, and third distance thresholds may be the same or different, and can be set according to actual needs.

[0094] By combining the curvature value and boundary information describing the local shape information, the feature points on the three-dimensional surface of any bone are extracted, which helps in the subsequent size measurement based on the feature points.

[0095] In some embodiments, establishing the correspondence between the plurality of first feature points and the plurality of first anatomical parts may include:

[0096] Calculating a first distance value between any two first feature points, and establishing a correspondence between a plurality of first distance values ​​and a plurality of first distance ranges; wherein any first distance range is determined based on two first anatomical parts;

[0097] For two first feature points corresponding to any first distance value, a correspondence between the two first feature points and two first anatomical parts corresponding to the first distance range corresponding to the first distance value is established based on the curvature values ​​respectively corresponding to the two first feature points.

[0098] Similarly, establishing a second correspondence between the plurality of second feature points and the plurality of second anatomical parts may include:

[0099] Calculating a second distance value between any two second feature points, and establishing a correspondence between the plurality of second distance values ​​and a plurality of second distance ranges; wherein any second distance range is determined based on the two second anatomical parts;

[0100] For two second feature points corresponding to any second distance value, a correspondence between the two second feature points and two second anatomical parts corresponding to the second distance range corresponding to the second distance value is established based on the curvature values ​​respectively corresponding to the two second feature points.

[0101] Similarly, establishing a third correspondence between the plurality of third feature points and the plurality of third anatomical parts may include:

[0102] Calculating a third distance value between any two third feature points, and establishing a correspondence between a plurality of third distance values ​​and a plurality of third distance ranges; wherein any third distance range is determined based on two third anatomical parts;

[0103] For two third feature points corresponding to any third distance value, a correspondence between the two third feature points and two third anatomical parts corresponding to the third distance range corresponding to the third distance value is established based on the curvature values ​​respectively corresponding to the two third feature points.

[0104] For ease of understanding, combined Figure 2 The following diagram is used for explanation. Figure 2 As shown, taking the malleus object as an example, the first anatomical part corresponding to the malleus object may include, for example, the malleus head part, the malleus handle tip part, and the malleus lateral process part, wherein the distance between any two first anatomical parts may be within a pre-set distance range. From the first three-dimensional surface 201 of the malleus object, three feature points, such as a first feature point A, a first feature point B, and a first feature point C, may be determined. The first distance value between any two first feature points may be calculated to obtain a plurality of first distance values ​​L AB 、L AC 、L BC Among them, LAB Indicates the first distance value between the first feature points A and B, L AC Indicates the first distance value between the first feature points A and C, L BC represents the first distance value between the first feature points B and C. For example, the first distance value L AB Within the distance range between the head of the malleus and the lateral process of the malleus, it can be determined that the first characteristic points A and B have a corresponding relationship with the head of the malleus and the lateral process of the malleus. At this time, based on the curvature values ​​corresponding to the first characteristic points A and B respectively, it can be determined that the first characteristic point A corresponds to the head of the malleus and the first characteristic point B corresponds to the lateral process of the malleus, thereby establishing a corresponding relationship between the first characteristic point A and the head of the malleus, and a corresponding relationship between the first characteristic point B and the lateral process of the malleus. For example, the first distance value L AC Within the distance range between the head of the malleus and the tip of the handle of the malleus, it can be determined that the first characteristic points A and C have a corresponding relationship with the head of the malleus and the tip of the handle of the malleus. At this time, based on the curvature values ​​corresponding to the first characteristic points A and C respectively, it can be determined that the first characteristic point A corresponds to the head of the malleus, and the first characteristic point C corresponds to the tip of the handle of the malleus, thereby establishing a corresponding relationship between the first characteristic point and the first anatomical part.

[0105] Similarly, a corresponding relationship between the second characteristic point and the second anatomical part, and a corresponding relationship between the third characteristic point and the third anatomical part can be established, which will not be repeated here.

[0106] Of course, the correspondence between the feature points and the anatomical parts may also be established based on the curvature value of each feature point and the predetermined curvature range corresponding to each anatomical part.

[0107] By combining the distance between each feature point and the curvature value that can describe the local shape information, a correspondence between the feature points and the anatomical part is established, so that the size to be measured can be measured based on the feature points corresponding to the anatomical part.

[0108] After determining the characteristic points corresponding to the anatomical part, the size can be measured based on the characteristic points. Specifically, the size to be measured can be calculated based on the characteristic points corresponding to the anatomical part according to the corresponding relationship between the anatomical part and the size to be measured.

[0109] In a practical application, the first dimension to be measured may include the height of the malleus, the length of the malleus handle, the distance between the malleus head and the tip of the malleus handle, and the volume of the malleus. The second dimension to be measured may include the height, width, distance between the long and short crus of the incus, and the volume of the incus. The third dimension to be measured may include the height of the stapes, the length of the stapes base plate, and the volume of the stapes. The fourth dimension to be measured may include the angle between the incus object and the stapes object joint. The first anatomical part may include the malleus head, the tip of the malleus handle, and the lateral process of the malleus. The second anatomical part may include the upper part of the incus body, the tip of the long crus of the incus, the tip of the short crus of the incus, and the protruding part of the hammer-anvil joint surface. The third anatomical part may include the stapes head, the two ends of the long diameter of the stapes base plate, and the vertical mapping part of the stapes head in the stapes base plate.

[0110] For ease of explanation, Figure 2 As shown, according to the correspondence between the first anatomical parts and the first dimensions to be measured, the distance between the first characteristic point A corresponding to the head of the malleus and the first characteristic point C corresponding to the tip of the handle of the malleus can be calculated as the height L of the malleus. AC Calculate the distance between the first feature point B corresponding to the lateral process of the malleus and the first feature point C corresponding to the tip of the malleus handle as the length L of the malleus handle. BC Calculate the distance between the first feature point A corresponding to the head of the malleus and the first feature point B corresponding to the lateral process of the malleus as the distance L between the head of the malleus and the tip of the handle of the malleus. AB Furthermore, the volume of the malleus is calculated based on the number of voxels occupied by the malleus and the size of the unit voxel in the segmentation result.

[0111] Similarly, according to the correspondence between the second anatomical parts and the second dimensions to be measured, the distance between the second characteristic point D corresponding to the upper part of the incus body and the second characteristic point G corresponding to the tip of the long foot of the incus can be calculated as the height L of the incus. DG Calculate the distance between the second feature point F corresponding to the tip of the short foot of the incus and the second feature point E corresponding to the protruding part of the hammer anvil joint surface as the width L of the incus EF Calculate the distance between the second feature point F corresponding to the tip of the short incus and the second feature point G corresponding to the tip of the long incus as the distance L between the long and short incus. FG Furthermore, the volume of the incus is calculated based on the number of voxels occupied by the incus in the segmentation result and the size of the unit voxel.

[0112] Similarly, according to the correspondence between the third anatomical parts and the third dimensions to be measured, the distance between the third characteristic point G corresponding to the stapes head part and the stapes head vertical mapping part I in the stapes base plate can be calculated as the stapes height L GICalculate the distance between the third characteristic points H and J at the two ends of the long diameter of the stapes base plate as the length L of the stapes base plate HJ The volume of the stapes is calculated based on the number of voxels occupied by the stapes in the segmentation result and the size of the unit voxel. In addition, the angle ∠DGI between the incus object and the stapes object joint is calculated based on the second feature point D, the third feature point G, and I.

[0113] Optionally, considering that the shape of the stapes baseplate is complex and the local shape differences are large, the endpoints of the long diameter of the baseplate may have different degrees of deviation. The lengths of multiple candidate long diameters of the stapes baseplate can be calculated, and the longest one can be selected as the long diameter of the stapes baseplate, so as to accurately determine the endpoints of the long diameter.

[0114] This enables automatic measurement of the ossicular chain size, improving measurement efficiency and accuracy.

[0115] Figure 3 FIG. 1 shows a schematic diagram of the structure of an ossicular chain size measurement system in a practical application. Figure 3 As shown, the system may include a segmentation module 301 , a reconstruction module 302 , a feature point determination module 303 and a measurement module 304 .

[0116] The segmentation module 302 may segment and obtain segmentation results corresponding to the malleus object, the incus object, and the stapes object from the collected multi-view ossicular chain images (including the ear coronal image, the ear sagittal image, and the ear transverse image).

[0117] Based on the segmentation results, the reconstruction module 302 can create a first three-dimensional surface corresponding to the malleus object, a second three-dimensional surface corresponding to the incus object, and a third three-dimensional surface corresponding to the stapes object. The first three-dimensional surface, the second three-dimensional surface, and the third three-dimensional surface constitute a fourth three-dimensional surface corresponding to the ossicular chain object.

[0118] The feature point determination module 303 can determine first feature points corresponding to multiple first anatomical parts from the first three-dimensional surface, determine second feature points corresponding to multiple second anatomical parts from the second three-dimensional surface, and determine third feature points corresponding to multiple third anatomical parts from the third three-dimensional surface.

[0119] The measurement module 304 can calculate the height of the malleus, the length of the malleus handle, the distance between the malleus head and the malleus handle tip, the volume of the malleus, the height and width of the incus, the distance between the long and short crus of the incus, the volume of the incus, the height of the stapes, the length of the stapes base plate, the volume of the stapes, and the angle between the incus object and the stapes object joint based on the correspondence between the characteristic points and the anatomical parts, as well as the correspondence between the anatomical parts and the dimensions to be measured. This enables automatic measurement of the ossicular chain dimensions and improves measurement efficiency and accuracy.

[0120] like Figure 4 FIG. 1 is a schematic structural diagram of an embodiment of a device for measuring the size of an ossicular chain provided by the present application. The device may include the following units.

[0121] The acquisition unit 401 is configured to acquire a medical image obtained by capturing an ear object of a target user, where the medical image includes an ossicular chain object, and the ossicular chain object includes a malleus object, an incus object, and a stapes object.

[0122] The segmentation unit 402 is configured to obtain segmentation results corresponding to the malleus object, the incus object, and the stapes object from the medical image segmentation.

[0123] The reconstruction unit 403 is configured to establish a first 3D surface corresponding to the malleus object, a second 3D surface corresponding to the incus object, and a third 3D surface corresponding to the stapes object based on the segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively.

[0124] The determination unit 404 is used to determine first feature points corresponding to multiple first anatomical parts from the first three-dimensional surface, determine second feature points corresponding to multiple second anatomical parts from the second three-dimensional surface, and determine third feature points corresponding to multiple third anatomical parts from the third three-dimensional surface.

[0125] The first measurement unit 405 is used to calculate the first size to be measured based on the multiple first feature points according to the correspondence between the multiple first anatomical parts and the first size to be measured in the malleus object, calculate the second size to be measured based on the multiple second feature points according to the correspondence between the multiple second anatomical parts and the second size to be measured in the incus object, and calculate the third size to be measured based on the multiple third feature points according to the correspondence between the multiple third anatomical parts and the third size to be measured in the stapes object.

[0126] In some embodiments, the apparatus may further comprise:

[0127] The second measuring unit is configured to calculate a fourth size to be measured based on the second feature points and the third feature points according to the correspondence between the fourth size to be measured between the second and third anatomical parts and the incus object and the stapes object.

[0128] In some embodiments, the determination unit 404 can be specifically used to select a plurality of first candidate points whose curvature values ​​meet a first curvature requirement from a plurality of mesh vertices of the first three-dimensional surface; select a plurality of first feature points whose distances from the boundary of the first three-dimensional surface meet a first distance requirement from the plurality of first candidate points; establish a first correspondence between the plurality of first feature points and a plurality of first anatomical parts, and determine the first feature points corresponding to the plurality of first anatomical parts respectively based on the first correspondence; select a plurality of second candidate points whose curvature values ​​meet a second curvature requirement from a plurality of mesh vertices of the second three-dimensional surface; select a plurality of first feature points whose distances from the boundary of the second three-dimensional surface meet a first distance requirement from the plurality of second candidate points; A plurality of second feature points whose distances between the plurality of second feature points satisfy a second distance requirement; a second correspondence between the plurality of second feature points and the plurality of second anatomical parts is established, and based on the second correspondence, the second feature points respectively corresponding to the plurality of second anatomical parts are determined; a plurality of third candidate points whose curvature values ​​satisfy a third curvature requirement are selected from the plurality of mesh vertices of the third three-dimensional surface; a plurality of third feature points whose distances to the boundary of the third three-dimensional surface satisfy a third distance requirement are selected from the plurality of third candidate points; a third correspondence between the plurality of third feature points and the plurality of third anatomical parts is established, and based on the third correspondence, the third feature points respectively corresponding to the plurality of third anatomical parts are determined.

[0129] In some embodiments, the determination unit 404 can be specifically used to calculate a first distance value between any two first feature points, and establish a correspondence between multiple first distance values ​​and multiple first distance ranges; wherein, any first distance range is determined based on two first anatomical parts; for two first feature points corresponding to any first distance value, based on the curvature values ​​respectively corresponding to the two first feature points, establish a correspondence between the two first feature points and the two first anatomical parts corresponding to the first distance range corresponding to the first distance value; calculate a second distance value between any two second feature points, and establish a correspondence between multiple second distance values ​​and multiple second distance ranges; wherein, any second distance range is determined based on the two second anatomical parts. The method comprises the following steps: determining the anatomical part of the anatomical structure of the anatomical structure; for two second feature points corresponding to any second distance value, establishing a correspondence between the two second feature points and the two second anatomical parts corresponding to the second distance range corresponding to the second distance value based on the curvature values ​​corresponding to the two second feature points; calculating the third distance value between any two third feature points, and establishing a correspondence between multiple third distance values ​​and multiple third distance ranges; wherein, any third distance range is determined based on two third anatomical parts; for two third feature points corresponding to any third distance value, establishing a correspondence between the two third feature points and the two third anatomical parts corresponding to the third distance range corresponding to the third distance value based on the curvature values ​​corresponding to the two third feature points.

[0130] In some embodiments, the segmentation unit 402 can be specifically used to use an image segmentation model to segment and obtain first-perspective segmentation results corresponding to the malleus object, incus object and stapes object from the coronal image of the ear, segment and obtain second-perspective segmentation results corresponding to the malleus object, incus object and stapes object from the sagittal image of the ear, and segment and obtain third-perspective segmentation results corresponding to the malleus object, incus object and stapes object from the cross-sectional image of the ear; obtain the segmentation result of the malleus object based on the first-perspective segmentation result, the second-perspective segmentation result and the third-perspective segmentation result corresponding to the malleus object, and obtain the segmentation result of the incus object based on the first-perspective segmentation result, the second-perspective segmentation result and the third-perspective segmentation result corresponding to the incus object, and obtain the segmentation result of the stapes object based on the first-perspective segmentation result, the second-perspective segmentation result and the third-perspective segmentation result corresponding to the stapes object.

[0131] In some embodiments, the reconstruction unit 403 can be specifically used to establish a first three-dimensional surface corresponding to the malleus object based on the subvoxel data in the segmentation result of the malleus object using an isosurface extraction algorithm, establish a second three-dimensional surface corresponding to the incus object based on the subvoxel data in the segmentation result of the incus object using an isosurface extraction algorithm, and establish a third three-dimensional surface corresponding to the stapes object based on the subvoxel data in the segmentation result of the stapes object using an isosurface extraction algorithm.

[0132] like Figure 5 FIG. 5 is a schematic diagram of a structure of an embodiment of a computing device provided by the present application. The device may include a storage component 501 and a processing component 502.

[0133] The storage component 501 can be used to store one or more computer program instructions, wherein the one or more computer program instructions are called and executed by the processing component 502 to implement Figure 1 Method for measuring ossicular chain size shown.

[0134] Of course, the above computing device may also include other components, such as input / output interfaces, communication components, etc.

[0135] The input / output interface provides an interface between the processing component and peripheral interface modules, which may be output devices, input devices, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices.

[0136] It should be noted that the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. It can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device.

[0137] Alternatively, the computing device may be implemented as an electronic device. An electronic device may be a device used by a user that has the necessary functions for internet access, computing, and communication, such as a mobile phone, tablet computer, personal computer, or wearable device. It is understood that the electronic device may also include a display component, input / output interface, communication component, and other components, which will not be detailed here.

[0138] In one or more of the above embodiments, the processing component may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0139] The storage component is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0140] The display component may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a direct retinal display or a similar laser scanning display.

[0141] The present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed, the computer program can realize Figure 1 The computer readable medium may be included in the computing device described in the above embodiment, or may exist independently without being assembled into the computing device.

[0142] The computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.

[0143] The present application also provides a computer program product, which includes a computer program carried on a computer-readable storage medium, and when the computer program is executed by a computer, it can achieve Figure 1 Method for measuring ossicular chain size shown.

[0144] In such an embodiment, the computer program may be downloaded and installed from a network, and / or installed from a removable medium. When the computer program is executed by a processor, various functions defined in the system of the present application are performed.

[0145] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0146] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0147] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0148] Finally, it should be noted that the above are merely examples of the present application and are not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A method for measuring the size of the ossicular chain, characterized in that: include: Acquire a medical image acquired by capturing an ear object of a target user, wherein the medical image includes an ossicular chain object, and the ossicular chain object includes a malleus object, an incus object, and a stapes object; Obtaining segmentation results corresponding to the malleus object, the incus object, and the stapes object respectively from the medical image segmentation; Based on the segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively, a first three-dimensional surface corresponding to the malleus object, a second three-dimensional surface corresponding to the incus object, and a third three-dimensional surface corresponding to the stapes object are established; wherein the first three-dimensional surface, the second three-dimensional surface, and the third three-dimensional surface constitute a fourth three-dimensional surface corresponding to the ossicular chain object; determining first feature points corresponding to a plurality of first anatomical parts respectively from the first three-dimensional surface, determining second feature points corresponding to a plurality of second anatomical parts respectively from the second three-dimensional surface, and determining third feature points corresponding to a plurality of third anatomical parts respectively from the third three-dimensional surface; According to the correspondence between the multiple first anatomical parts and the first size to be measured in the malleus object, the first size to be measured is calculated based on multiple first feature points, and according to the correspondence between the multiple second anatomical parts and the second size to be measured in the incus object, the second size to be measured is calculated based on multiple second feature points, and according to the correspondence between the multiple third anatomical parts and the third size to be measured in the stapes object, the third size to be measured is calculated based on multiple third feature points; wherein, the ossicular chain size includes the first size to be measured, the second size to be measured and the third size to be measured.

2. The method according to claim 1, characterized in that Also includes: According to the correspondence between the multiple second anatomical parts and the third anatomical parts and the fourth dimension to be measured between the incus object and the stapes object, the fourth dimension to be measured is calculated based on the multiple second feature points and the multiple third feature points; wherein the ossicular chain size includes the fourth dimension to be measured, the first dimension to be measured, the second dimension to be measured and the third dimension to be measured.

3. The method according to claim 1, characterized in that The determining of first feature points corresponding to a plurality of first anatomical parts respectively from the first three-dimensional surface comprises: Selecting a plurality of first candidate points whose curvature values ​​meet a first curvature requirement from a plurality of mesh vertices of the first three-dimensional surface; Selecting, from the plurality of first candidate points, a plurality of first feature points whose distances from the boundary of the first three-dimensional surface meet a first distance requirement; establishing a first correspondence between the plurality of first characteristic points and the plurality of first anatomical parts, and determining first characteristic points corresponding to the plurality of first anatomical parts respectively based on the first correspondence; The determining of second feature points respectively corresponding to a plurality of second anatomical parts from the second three-dimensional surface comprises: Selecting a plurality of second candidate points whose curvature values ​​meet a second curvature requirement from a plurality of mesh vertices of the second three-dimensional surface; Selecting, from the plurality of second candidate points, a plurality of second feature points whose distances from the boundary of the second three-dimensional surface meet a second distance requirement; establishing a second correspondence between the plurality of second characteristic points and the plurality of second anatomical parts, and determining, based on the second correspondence, second characteristic points corresponding to the plurality of second anatomical parts respectively; The determining of third feature points respectively corresponding to a plurality of third anatomical parts from the third three-dimensional surface comprises: Selecting a plurality of third candidate points whose curvature values ​​meet a third curvature requirement from a plurality of mesh vertices of the third three-dimensional surface; selecting, from the plurality of third candidate points, a plurality of third feature points whose distances from the boundary of the third three-dimensional surface meet a third distance requirement; A third correspondence between the plurality of third characteristic points and the plurality of third anatomical parts is established, and based on the third correspondence, third characteristic points respectively corresponding to the plurality of third anatomical parts are determined.

4. The method according to claim 3, characterized in that The establishing of a first correspondence between the plurality of first feature points and the plurality of first anatomical parts includes: Calculating a first distance value between any two first feature points, and establishing a correspondence between a plurality of first distance values ​​and a plurality of first distance ranges; wherein any first distance range is determined based on two first anatomical parts; For two first feature points corresponding to any first distance value, establishing a correspondence between the two first feature points and two first anatomical parts corresponding to a first distance range corresponding to the first distance value based on the curvature values ​​respectively corresponding to the two first feature points; The establishing of a second correspondence between the plurality of second feature points and the plurality of second anatomical parts includes: Calculating a second distance value between any two second feature points, and establishing a correspondence between the plurality of second distance values ​​and a plurality of second distance ranges; wherein any second distance range is determined based on the two second anatomical parts; For two second feature points corresponding to any second distance value, establishing a correspondence between the two second feature points and two second anatomical parts corresponding to a second distance range corresponding to the second distance value based on the curvature values ​​respectively corresponding to the two second feature points; The establishing of a third correspondence between the plurality of third feature points and the plurality of third anatomical parts includes: Calculating a third distance value between any two third feature points, and establishing a correspondence between a plurality of third distance values ​​and a plurality of third distance ranges; wherein any third distance range is determined based on two third anatomical parts; For two third feature points corresponding to any third distance value, a correspondence between the two third feature points and two third anatomical parts corresponding to the third distance range corresponding to the third distance value is established based on the curvature values ​​respectively corresponding to the two third feature points.

5. The method according to claim 2, characterized in that The first dimension to be measured includes the height of the malleus, the length of the malleus handle, the distance between the malleus head and the tip of the malleus handle, and the volume of the malleus; the second dimension to be measured includes the height, width, the distance between the long and short legs of the incus, and the volume of the incus; the third dimension to be measured includes the height, length, and volume of the stapes; and the fourth dimension to be measured includes the angle between the incus object and the stapes object joint.

6. The method according to claim 1, characterized in that The medical images include a coronal image of the ear, a sagittal image of the ear, and a transverse image of the ear; The obtaining of segmentation results corresponding to the malleus object, the incus object, and the stapes object respectively from the medical image segmentation includes: Using an image segmentation model, segmenting the ear coronal image to obtain first-perspective segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively; segmenting the ear sagittal image to obtain second-perspective segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively; and segmenting the ear transverse image to obtain third-perspective segmentation results corresponding to the malleus object, the incus object, and the stapes object, respectively; Based on the first perspective segmentation result, the second perspective segmentation result and the third perspective segmentation result corresponding to the malleus object, obtaining a segmentation result of the malleus object; based on the first perspective segmentation result, the second perspective segmentation result and the third perspective segmentation result corresponding to the incus object, obtaining a segmentation result of the incus object; and based on the first perspective segmentation result, the second perspective segmentation result and the third perspective segmentation result corresponding to the stapes object, obtaining a segmentation result of the stapes object; The image segmentation model is pre-trained based on training samples and training labels, wherein the training samples include the sample user's ear coronal plane image, ear sagittal plane image and ear cross-sectional image, and the training labels include the sample user's malleus object segmentation result, incus object segmentation result and stapes object segmentation result.

7. The method according to claim 1, characterized in that The step of establishing a first three-dimensional surface corresponding to the malleus object, a second three-dimensional surface corresponding to the incus object, and a third three-dimensional surface corresponding to the stapes object based on the segmentation results corresponding to the malleus object, the incus object, and the stapes object respectively comprises: Based on the subvoxel data in the segmentation result of the malleus object, an isosurface extraction algorithm is used to establish a first three-dimensional surface corresponding to the malleus object; based on the subvoxel data in the segmentation result of the incus object, an isosurface extraction algorithm is used to establish a second three-dimensional surface corresponding to the incus object; and based on the subvoxel data in the segmentation result of the stapes object, an isosurface extraction algorithm is used to establish a third three-dimensional surface corresponding to the stapes object.

8. A system for measuring the size of an ossicular chain, characterized in that: It includes segmentation module, reconstruction module, feature point determination module and measurement module; The segmentation module is used to obtain segmentation results corresponding to the malleus object, the incus object and the stapes object respectively from the medical image segmentation; wherein the medical image is obtained by collecting ear objects for the target user, the medical image includes ossicular chain objects, and the ossicular chain objects include the malleus object, the incus object and the stapes object; The reconstruction module is used to establish a first three-dimensional surface corresponding to the malleus object, a second three-dimensional surface corresponding to the incus object, and a third three-dimensional surface corresponding to the stapes object based on the segmentation results corresponding to the malleus object, the incus object, and the stapes object respectively; wherein the first three-dimensional surface, the second three-dimensional surface, and the third three-dimensional surface constitute a fourth three-dimensional surface corresponding to the ossicular chain object; The feature point determination module is configured to determine first feature points corresponding to a plurality of first anatomical parts respectively from the first three-dimensional surface, determine second feature points corresponding to a plurality of second anatomical parts respectively from the second three-dimensional surface, and determine third feature points corresponding to a plurality of third anatomical parts respectively from the third three-dimensional surface; The measurement module is used to calculate the first size to be measured based on a plurality of first feature points according to the correspondence between the plurality of first anatomical parts and the first size to be measured in the malleus object, and to calculate the second size to be measured based on a plurality of second feature points according to the correspondence between the plurality of second anatomical parts and the second size to be measured in the incus object, and to calculate the third size to be measured based on a plurality of third feature points according to the correspondence between the plurality of third anatomical parts and the third size to be measured in the stapes object; wherein the ossicular chain size includes the first size to be measured, the second size to be measured and the third size to be measured.

9. A computing device, characterized in that It comprises a storage component and a processing component; the storage component stores one or more computer program instructions, the computer program instructions are called and executed by the processing component, and the processing component executes the one or more computer program instructions to implement the ossicular chain size measurement method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that A computer program is stored, and the computer program is executed by a computer to implement the method for measuring the size of the ossicular chain according to any one of claims 1 to 7.

11. A computer program product, characterized in that A computer program is stored, and when the computer program is executed by a computer, the method for measuring the size of the ossicular chain according to any one of claims 1 to 7 is implemented.

Images