Method and device for acquiring ear parameters

Abstract

The invention discloses an ear parameter acquisition method and device, and relates to the technical field of image processing. According to the method, a three-dimensional head image of a scanned object can be obtained, and then ear parameters of ears are output based on ear tissues included in the ears of the scanned object in the three-dimensional head image. Compared with a mode of manually detecting the ear through a tool to obtain the ear parameters, the method provided by the invention can effectively improve the acquisition efficiency of the ear parameters, and improves the acquisition flexibility of the ear parameters.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method and device for acquiring ear parameters. Background Art

[0002] Ear diseases (such as ear deformities) can affect people's health and quality of life, so it is particularly important to detect and treat ear diseases. The premise of detecting ear diseases is to obtain ear parameters.

[0003] In the related art, doctors can manually detect the patient's ears through tools to obtain ear parameters. However, the efficiency of obtaining ear parameters in the related art is low. Summary of the invention

[0004] The present application provides a method and device for obtaining ear parameters, which can solve the problem of low efficiency in obtaining ear parameters in related technologies. The technical solution is as follows:

[0005] In one aspect, a method for obtaining ear parameters is provided, the method comprising:

[0006] Acquire a three-dimensional head image of a scanned object, wherein the scanned object has ears;

[0007] outputting ear parameters of the ear based on ear tissue included in the ear in the three-dimensional head image;

[0008] The ear parameters include: ear tissues included in the ears of the scanned object.

[0009] Optionally, outputting ear parameters of the ear based on ear tissue included in the ear in the three-dimensional head image includes:

[0010] Based on the three-dimensional head image, acquiring a target ear image of the scanned object, wherein the target ear image is annotated with ear tissues included in the ear of the scanned object;

[0011] Based on the target ear image, ear parameters of the ear are output.

[0012] Optionally, the ear includes: an inner ear, a middle ear and an outer ear; and acquiring a target ear image of the scanned object based on the three-dimensional head image includes:

[0013] Based on the three-dimensional head image, acquiring a first ear image, a first inner ear sub-image, and a first middle ear sub-image of the scanned object, wherein the first ear image is at least annotated with ear tissue included in the outer ear, the first inner ear sub-image is annotated with ear tissue included in the inner ear, and the first middle ear sub-image is annotated with ear tissue included in the middle ear;

[0014] A target ear image is acquired based on the first ear image, the first inner ear sub-image, and the first middle ear sub-image.

[0015] Optionally, acquiring a first ear image, a first inner ear sub-image, and a first middle ear sub-image of the scanned object based on the three-dimensional head image includes:

[0016] Based on the three-dimensional head image, acquiring a second inner ear sub-image and a second middle ear sub-image of the scanned object, wherein the second inner ear sub-image does not mark the ear tissue included in the inner ear, and the second middle ear sub-image does not mark the ear tissue included in the middle ear;

[0017] splicing the second inner ear sub-image, the second middle ear sub-image, and the outer ear sub-image to obtain a second ear image;

[0018] acquiring a first ear image based on the second ear image;

[0019] Based on the second inner ear sub-image, acquiring a first inner ear sub-image;

[0020] Based on the second middle ear sub-image, a first middle ear sub-image is acquired.

[0021] Optionally, acquiring a first inner ear sub-image based on the second inner ear sub-image includes:

[0022] The second inner ear sub-image is input into an inner ear segmentation model to obtain a first inner ear sub-image output by the inner ear segmentation model.

[0023] Optionally, acquiring a first middle ear sub-image based on the second middle ear sub-image includes:

[0024] The second middle ear sub-image is input into a middle ear segmentation model to obtain a first middle ear sub-image output by the middle ear segmentation model.

[0025] Optionally, acquiring the first ear image based on the second ear image includes:

[0026] The second ear image is input into an ear segmentation model to obtain a first ear image output by the ear segmentation model.

[0027] Optionally, acquiring a second inner ear sub-image and a second middle ear sub-image of the scanned object based on the three-dimensional head image includes:

[0028] Determine the positions of the inner ear key points of the inner ear and the middle ear key points of the middle ear in the three-dimensional head image;

[0029] Based on the positions of the inner ear key points, sampling the three-dimensional head image to obtain a second inner ear sub-image of the scanned object;

[0030] Based on the positions of the middle ear key points, the three-dimensional head image is sampled to obtain a second middle ear sub-image of the scanned object.

[0031] In another aspect, a device for obtaining ear parameters is provided, the device comprising:

[0032] An acquisition module, used for acquiring a three-dimensional head image of a scanned object, wherein the scanned object has ears;

[0033] an output module, configured to output ear parameters of the ear based on ear tissue included in the ear in the three-dimensional head image;

[0034] The ear parameters include: ear tissues included in the ears of the scanned object.

[0035] Optionally, the device further comprises:

[0036] The ear diagnosis module is used to determine the diagnosis result of the ear based on the ear parameters.

[0037] On the other hand, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for obtaining ear parameters as described in the above aspects is implemented.

[0038] On the other hand, a computer program product is provided, which includes a computer program or computer instructions, and when the computer program or the computer instructions are executed by a processor, the method for obtaining ear parameters as described in the above aspects is implemented.

[0039] The beneficial effects brought about by the technical solution provided by this application include at least:

[0040] The present application provides a method and device for obtaining ear parameters, which can obtain a three-dimensional head image of a scanned object, and then output the ear parameters of the ear based on the ear tissue included in the ear of the scanned object in the three-dimensional head image. Compared with the method of manually detecting the ear through tools to obtain ear parameters, the method provided by the present application can effectively improve the efficiency of obtaining ear parameters and improve the flexibility of obtaining ear parameters.

[0041] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1is a flow chart of a method for obtaining ear parameters provided in an embodiment of the present application;

[0043] Figure 2 is a flow chart of another method for obtaining ear parameters provided in an embodiment of the present application;

[0044] Figure 3 is a flow chart of a method for acquiring a target ear image of a scanned object based on a three-dimensional head image provided by an embodiment of the present application;

[0045] Figure 4 It is a structural schematic diagram of a device for obtaining ear parameters provided in an embodiment of the present application;

[0046] Figure 5 is a schematic structural diagram of another device for acquiring ear parameters provided in an embodiment of the present application;

[0047] Figure 6 It is a structural diagram of a parameter acquisition device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0049] The embodiment of the present application provides a method for obtaining ear parameters, which is applied to an ear parameter obtaining device. Optionally, the ear parameter obtaining device (hereinafter referred to as the parameter obtaining device) can be a medical imaging device, a mobile terminal or a fixed terminal. The medical imaging device can be a computed tomography (CT) device or a magnetic resonance imaging (MRI) device. Figure 1 , the method comprising:

[0050] Step 101: Acquire a three-dimensional head image of a scanned object.

[0051] When it is necessary to obtain the ear parameters of the scanned object, the head of the scanned object can be scanned by a CT device to obtain a three-dimensional head image of the scanned object. The scanned object can be a human body, an animal body or a phantom. The scanned object has an ear, which includes multiple ear regions, each of which includes ear tissue. The multiple ear regions are the outer ear, the middle ear and the inner ear.

[0052] Step 102: output ear parameters of the ear based on the ear tissue included in the ear in the three-dimensional head image.

[0053] The ear parameters include: a plurality of ear tissues included in the ear of the scanned object. For example, the ear parameters may include: a plurality of ear tissues included in the ear, tissue parameters (such as diameter, height, and length, etc.) of a first ear tissue among the plurality of ear tissues, and a connection state of at least two second ear tissues among the plurality of ear tissues. The connection state includes: one of connection and non-connection.

[0054] In an embodiment of the present application, the parameter acquisition device pre-stores a parameter acquisition model. The parameter acquisition device can input the three-dimensional head image into the parameter acquisition model to obtain the ear parameters of the scanned object output by the parameter acquisition model. It is understandable that before inputting the three-dimensional head image into the parameter acquisition model, the parameter acquisition device can perform model training based on multiple auxiliary training data to obtain the parameter acquisition model. Each auxiliary training data may include: a sample head image, and ear parameters of a sample ear obtained based on the sample head image.

[0055] Alternatively, the parameter acquisition device may identify ear tissues included in the ear of the scanned object from the three-dimensional head image, and then the parameter acquisition device may output ear parameters of the ear based on the ear tissues included in the ear.

[0056] Alternatively, the ear tissue included in the ear can be reflected by the target ear image. In this case, the parameter acquisition device can first acquire the target ear image of the scanned object based on the three-dimensional head image. The target ear image is annotated with the ear tissue included in the ear of the scanned object. Then, the parameter acquisition device can output the ear parameters of the ear based on the target ear image.

[0057] In summary, the embodiment of the present application provides a method for obtaining ear parameters, which can obtain a three-dimensional head image of a scanned object, and then output the ear parameters of the ear based on the ear tissue included in the ear of the scanned object in the three-dimensional head image. Compared with the method of manually detecting the ear through tools to obtain ear parameters, the method provided by the embodiment of the present application can effectively improve the efficiency of obtaining ear parameters and improve the flexibility of obtaining ear parameters.

[0058] It should be understood that the scanned object generally has two ears. For each ear, the parameter acquisition device can adopt the method provided in the embodiment of the present application to acquire the ear parameters of the ear.

[0059] In the embodiment of the present application, the method for obtaining ear parameters provided in the embodiment of the present application is exemplified by taking the example that the parameter obtaining device first obtains the target ear image based on the three-dimensional head image and then outputs the ear parameters based on the target ear image. Figure 2 , the method may include:

[0060] Step 201: Acquire a three-dimensional head image of a scanned object.

[0061] When it is necessary to obtain the ear parameters of the scanned object, the head of the scanned object can be scanned by a medical imaging device to obtain a three-dimensional head image of the scanned object. The scanned object can be a human body, an animal body or a phantom.

[0062] Optionally, the medical imaging device can be a photon counting CT device. Compared with ordinary CT devices, the layer thickness of the photon counting CT device can reach 0.1 to 0.3 millimeters (mm), so it has a higher spatial resolution and better imaging quality. Therefore, through the photon counting CT device, the micro anatomical structures included in the outer ear, middle ear and inner ear of the ear can be obtained more clearly, so as to obtain more comprehensive and accurate ear parameters. Among them, the layer thickness of the photon counting CT device refers to: when scanning, the thickness of the image layer obtained by each scan. That is, the thickness of the image obtained by each scan is the thickness of the image obtained.

[0063] Step 202: Based on the three-dimensional head image, a target ear image of the scanned object is acquired.

[0064] The target ear image is annotated with various ear tissues included in the ear of the scanned object, that is, ear tissues included in various ear regions of the outer ear, middle ear and inner ear of the scanned object.

[0065] It should be understood that the outer ear of a normal (i.e. non-deformed) ear includes: the auricle and the external auditory canal. The middle ear includes: the tympanic membrane, the middle ear cavity, the auditory ossicles and the Eustachian tube, and the auditory ossicles include: the malleus, the incus and the stapes. The inner ear includes: the internal auditory canal, the facial nerve, the auditory nerve, the cochlea, the vestibule, the vestibular aqueduct and the semicircular canals, etc., and the semicircular canals include: the lateral semicircular canal, the anterior semicircular canal (also referred to as the superior semicircular canal) and the posterior semicircular canal. The ear of the scanned object in the embodiment of the present application may be normal, or may suffer from an ear disease (such as a deformed one), that is, it may not include certain ear tissues in the above-mentioned ear area.

[0066] Optionally, the target ear image may also be labeled with various ear regions of the scanned object's ear. In other words, the target ear image may be labeled with various ear regions of the ear and ear tissues included in the ear regions.

[0067] In the embodiment of the present application, the parameter acquisition device can mark each ear region and each ear tissue in the target ear image by multi-color drawing, label setting, text addition, transparency adjustment, etc., so that the target ear image can represent the ear tissue included in the ear and the position of each ear tissue. For example, the parameter acquisition device can mark each ear region and each ear tissue with different colors.

[0068] In an optional implementation, the parameter acquisition device may pre-store an image acquisition model. The parameter acquisition device may input the three-dimensional head image into the image acquisition model to obtain the target ear image output by the image acquisition model.

[0069] It is understandable that the parameter acquisition device can acquire multiple first training data, each of which can include: a sample head image, and a target sample ear image obtained based on the sample head image. The target sample ear image is at least annotated with various ear tissues included in the ear of the scanned object. For example, the target sample ear image is annotated with various ear regions and various ear tissues included in the ear. Then, the parameter acquisition device can perform model training on the first training data to obtain an image acquisition model.

[0070] In another alternative implementation, see Figure 3 The process of the parameter acquisition device executing step 202 may include:

[0071] Step 2021: Based on the three-dimensional head image, a first ear image, a first inner ear sub-image, and a first middle ear sub-image of the scanned object are acquired.

[0072] The first ear image is at least labeled with ear tissues included in the outer ear of the scanned object. The first inner ear sub-image is labeled with ear tissues included in the inner ear of the scanned object, and the first middle ear sub-image is labeled with ear tissues included in the middle ear of the scanned object.

[0073] It is understandable that, since the ear tissue included in the external ear is relatively simple, the ear tissue included in the external ear of the scanned object can be directly marked in the first ear image. Optionally, the first ear image can also be marked with each ear region included in the scanned object's ear. That is, the first ear image is marked with each ear region included in the ear, and the ear tissue included in each ear region.

[0074] Step 2022: Acquire a target ear image based on the first ear image, the first inner ear sub-image, and the first middle ear sub-image.

[0075] The parameter acquisition device may extract annotation information from the first ear image, the first inner ear sub-image, and the first middle ear sub-image, and fuse the first ear image, the first inner ear sub-image, and the first middle ear sub-image to obtain a fused image. Then, the parameter acquisition device may annotate the fused image based on the annotation information to obtain a target ear image.

[0076] The annotation information includes: the names of each ear region and each ear tissue, and the positions in the three-dimensional coordinate system where the three-dimensional head image is located. The three-dimensional coordinate system can be a three-dimensional coordinate system established based on the head of the scanned object. For example, the origin of the three-dimensional coordinate system can be any point on the head, the X-axis direction can be the front-to-back direction of the head, the Y-axis direction can be the left-to-right direction of the head, and the Z-axis can be perpendicular to the X-axis and the Y-axis respectively. The position of the ear region (or ear tissue) can include: the positions of each point constituting the ear region (or ear tissue) in the three-dimensional coordinate system.

[0077] In the embodiment of the present application, the process of the parameter acquisition device executing step 221 may include:

[0078] Step S1: based on the three-dimensional head image, obtaining a second inner ear sub-image and a second middle ear sub-image of the scanned object.

[0079] The second inner ear sub-image does not mark the ear tissues included in the inner ear of the scanned object. The second middle ear sub-image does not mark the ear tissues included in the middle ear of the scanned object.

[0080] As an optional example, the parameter acquisition device may determine the positions of the inner ear key points of the inner ear and the middle ear key points of the middle ear in the three-dimensional head image. Then, the parameter acquisition device may sample the three-dimensional head image based on the positions of the inner ear key points to obtain a second inner ear sub-image of the scanned object, and may sample the three-dimensional head image based on the positions of the middle ear key points to obtain a second middle ear sub-image of the scanned object.

[0081] The position of each of the inner ear key points and the middle ear key points in the three-dimensional head image refers to the coordinates of the key point in the three-dimensional coordinate system where the three-dimensional head image is located. Optionally, the inner ear key point may include the center point of the cochlea. The middle ear key point may include the center point of the auditory ossicle.

[0082] In the embodiment of the present application, taking the example of the parameter acquisition device sampling the three-dimensional head image based on the center point of the cochlea to obtain the second inner ear sub-image, the process of the parameter acquisition device acquiring the second inner ear sub-image and the second middle ear sub-image is exemplarily described:

[0083] The parameter acquisition device can determine the region of interest image of the inner ear from the three-dimensional head image based on the position of the center point of the cochlea. The region of interest image can refer to: an image containing the inner ear region centered on the center point of the inner ear (such as the center point of the cochlea). Then, the parameter acquisition device can take the center point of the cochlea as the sampling starting point and sample the region of interest image with a preset sampling step size, thereby obtaining a second inner ear sub-image.

[0084] The sampling step may refer to the distance between adjacent sampling points when sampling an image. The size of the sampling step may determine the resolution of the acquired second inner ear sub-image. For example, the sampling step may be smaller than the layer thickness of the medical imaging device. In this way, it is ensured that the acquired second inner ear sub-image has a high resolution.

[0085] Optionally, the parameter acquisition device can extract features from the three-dimensional head image to obtain relevant features of the inner ear (or middle ear), and predict the positions of key points of the inner ear (or middle ear) in the three-dimensional head image through a regression network based on the relevant features.

[0086] Alternatively, the parameter acquisition device determines the position of the inner ear key point in the three-dimensional head image in response to the marking operation of the inner ear key point. In addition, the parameter acquisition device can also determine the position of the middle ear key point in the three-dimensional head image in response to the marking operation of the middle ear key point.

[0087] As another optional example, the parameter acquisition device pre-stores a target detection segmentation model. The parameter acquisition device can input the three-dimensional head image into the target detection segmentation model to obtain the second inner ear sub-image and the second middle ear sub-image output by the target detection segmentation model.

[0088] It should be understood that the parameter acquisition device may acquire multiple second training data before inputting the three-dimensional head image into the target detection segmentation model. Each second training data includes: a sample head image, a first inner ear sample sub-image cropped from the sample head image, and a first middle ear sample sub-image cropped from the sample head image. Then, the parameter acquisition device may perform model training on the multiple second training data to obtain the target detection segmentation model. The first inner ear sample sub-image does not mark the ear tissue of the inner ear, and the first middle ear sample sub-image does not mark the ear tissue of the middle ear.

[0089] Step S2: splicing the second inner ear sub-image, the second middle ear sub-image and the outer ear sub-image to obtain a second ear image.

[0090] The parameter acquisition device can splice the second inner ear sub-image, the second middle ear sub-image and the outer ear sub-image according to the relative positions of the outer ear, the middle ear and the inner ear, so as to obtain a second ear image. That is, the second ear image can include: the second inner ear sub-image, the second middle ear sub-image and the outer ear sub-image. The outer ear sub-image does not mark the ear tissue included in the outer ear of the scanned object.

[0091] In the embodiment of the present application, the parameter acquisition device may acquire the outer ear sub-image through a pre-stored target detection segmentation model before executing step 2022. That is, after the parameter acquisition device inputs the three-dimensional head image of the scanned object into the target detection segmentation model, the target detection segmentation model may also output the outer ear sub-image of the scanned object. At this time, each second training data mentioned above may also include: a sample outer ear sub-image cropped from the sample head image.

[0092] Step S3: Acquire the first ear image based on the second ear image.

[0093] The first ear image includes a second inner ear sub-image, a second middle ear sub-image and an outer ear sub-image, and each ear region is marked in the first ear image.

[0094] As an optional embodiment, the parameter acquisition device may pre-store an ear segmentation model. The parameter acquisition device may input the second ear image into the ear segmentation model to obtain the first ear image output by the ear segmentation model.

[0095] In an embodiment of the present application, the parameter acquisition device may acquire multiple third training data and perform model training on the multiple third training data to obtain an ear segmentation model. Each third training data may include: a first ear sample image without ear tissue labeled with the external ear, and a second ear sample image with the ear tissue labeled with the external ear.

[0096] Optionally, the second ear sample image may also be annotated with various ear regions.

[0097] As another optional embodiment, the parameter acquisition device may respond to a labeling operation on the ear tissue included in the external ear in the second ear image by labeling at least the ear tissue included in the external ear in the second ear image, thereby obtaining the first ear image.

[0098] Step S4: acquiring a first inner ear sub-image based on the second inner ear sub-image.

[0099] Optionally, the parameter acquisition device further stores an inner ear segmentation model. The parameter acquisition device may input the second inner ear sub-image into the inner ear segmentation model to obtain the first inner ear sub-image output by the inner ear segmentation model.

[0100] It should be understood that the parameter acquisition device can acquire multiple fourth training data and perform model training on the fourth training data to obtain the inner ear segmentation model. Each fourth training data includes: a first inner ear sample sub-image and a second inner ear sample sub-image with each ear tissue of the inner ear marked.

[0101] Step S5: acquiring a first middle ear sub-image based on the second middle ear sub-image.

[0102] Optionally, the parameter acquisition device further stores a middle ear segmentation model. The parameter acquisition device may input the second inner ear sub-image into the middle ear segmentation model to obtain the first inner ear sub-image output by the middle ear segmentation model.

[0103] It should be understood that the parameter acquisition device can acquire multiple fifth training data and perform model training on the fifth training data to obtain a middle ear segmentation model. Each fifth training data includes: a first middle ear sample sub-image and a second middle ear sample sub-image with various ear tissues of the middle ear marked.

[0104] In an embodiment of the present application, before training the ear segmentation model, the inner ear segmentation model, and the middle ear segmentation model, the parameter acquisition device may acquire a large number of first ear sample images, first inner ear sample sub-images, and first middle ear sample sub-images, and pre-process the acquired sample images (i.e., the first ear sample images, the first inner ear sample sub-images, and the first middle ear sample sub-images). Then, the parameter acquisition device may acquire labeled sample images in response to the labeling operation for each pre-processed sample image.

[0105] Specifically, the external auditory canal and auricle (such as the external auditory canal, auricle and various ear regions) can be annotated in the first ear sample image to obtain a second ear sample image. The internal auditory canal, facial nerve, auditory nerve, cochlea, vestibule, vestibular aqueduct, external semicircular canal, anterior semicircular canal and posterior semicircular canal, etc. are annotated in the first inner ear sample sub-image to obtain a second inner ear sample sub-image. The tympanic membrane, middle ear cavity and Eustachian tube are annotated in the first middle ear sample sub-image, and the ossicles are annotated in the middle ear cavity to obtain a second middle ear sample sub-image.

[0106] The preprocessing of the sample images may include at least one of: removing sample images with lower definition, removing sample images outside the ear, performing artifact removal processing on the sample images, and adjusting the window width and window position of the sample images.

[0107] Each sample image is a three-dimensional image, which can be reconstructed from a two-dimensional image obtained by scanning the sample object. Each two-dimensional image includes at least 512*512 pixels, and the layer thickness when scanning the sample object is less than or equal to 0.3mm. In this way, the quality of the sample image obtained can be ensured to be high, and each ear tissue can be displayed more clearly.

[0108] It is understandable that the labeling work can be completed by doctors or experts with professional knowledge and experience, thereby ensuring the accuracy and consistency of the labeling, thereby ensuring that the trained ear segmentation model, inner ear segmentation model and middle ear segmentation model have high reliability.

[0109] Step 203: output ear parameters of the scanned object based on the target ear image.

[0110] The ear parameters may at least include: a plurality of ear tissues included in the ear of the scanned object. For example, the ear parameters may also include: a plurality of ear tissues included in the ear of the scanned object, tissue parameters (such as diameter, height, and length, etc.) of a first ear tissue among the plurality of ear tissues, and at least one of the connection states of at least two second ear tissues among the plurality of ear tissues. The connection state includes: one of connection and non-connection.

[0111] The first ear tissue may include at least one of the external ear, the middle ear cavity, the malleus, the incus, the stapes, the internal auditory canal, the cochlea, the vestibular aqueduct, the semicircular canal, the facial nerve and the auditory nerve. Among them, the tissue parameters of the external ear may include the lumen diameter of the external auditory canal. The tissue parameters of the middle ear cavity may include the average density, volume, maximum diameter and minimum diameter of the middle ear cavity. The average density of the middle ear cavity refers to the average of the gray values ​​of all pixels in the sub-image of the middle ear cavity included in the target ear image. The tissue parameters of each bone tissue in the malleus, the incus and the stapes may include the long axis, volume, maximum diameter, minimum diameter and average density of the bone tissue. The tissue parameters of the internal auditory canal may include the diameter of the internal auditory canal. The tissue parameters of the cochlea may include the vertical height, horizontal width, length, number of turns, diameter (such as effective diameter, maximum diameter and minimum diameter), area and grayscale of the cochlea. The cochlea is a spiral structure, and the length of the cochlea refers to the length of the path that is sequentially expanded from the center of the cochlea to the outside. The number of turns is the number of turns of the spiral structure. The grayscale of the cochlea refers to: the average grayscale value of all pixels in the sub-image of the cochlea included in the target ear image. The tissue parameters of the vestibular aqueduct may include: the length, diameter (such as effective diameter, maximum diameter and minimum diameter), area and grayscale of the vestibular aqueduct. The tissue parameters of the semicircular canals may include: the length, height, diameter (such as effective diameter, maximum diameter and minimum diameter), area and grayscale of each semicircular canal in the external semicircular canal, the anterior semicircular canal and the posterior semicircular canal. The tissue parameters of the facial nerve may include: the center line, diameter, area and grayscale of the facial nerve. The tissue parameters of the auditory nerve may include: the center line, diameter, area and grayscale of the auditory nerve. The grayscale of each ear tissue in the vestibular aqueduct, semicircular canals, facial nerve and auditory nerve refers to: the average grayscale value of all pixels in the sub-image of the ear tissue included in the target ear image.

[0112] The second ear tissue may include: tympanic membrane, malleus, incus and stapes. The ear parameters may include: connection status of tympanic membrane and other tissues. The other tissues are ear tissues other than tympanic membrane among the multiple ear tissues. The connection status of malleus and incus, and the connection status of incus and stapes.

[0113] It can be understood that, for the first ear tissue, the parameter acquisition device can determine the image area where the ear tissue is located in the target ear image based on the position of the ear tissue, and then acquire the tissue parameters of the first ear tissue based on the image area.

[0114] For example, the parameter acquisition device can identify the centerline of the external auditory canal in the image area where the external ear is located in the target ear image, and then acquire the lumen diameter of the external auditory canal based on the centerline of the external auditory canal. The centerline of the external auditory canal is the centerline between the center of the external auditory canal opening and the center of the tympanic membrane of the middle ear.

[0115] The parameter acquisition device can identify the centerline of the middle ear cavity in the image area where the middle ear is located in the target ear image, and determine the tissue parameters of the middle ear cavity based on the centerline of the middle ear cavity. In addition, the parameter acquisition device can obtain the tissue parameters of each bone tissue based on the marked bone tissues in the malleus, incus and stapes. In this process, the parameter acquisition device can also identify the centerline of the Eustachian tube in the target ear image.

[0116] The parameter acquisition device can identify the center and centerline of the cochlea, the centerline of the vestibular aqueduct, the centerline of the external semicircular canal, the centerline of the anterior semicircular canal, and the centerline of the posterior semicircular canal in the image area where the inner ear is located in the target ear image. Then, the parameter acquisition device can calculate the tissue parameters of the cochlea based on the center and centerline of the cochlea, calculate the tissue parameters of the vestibular aqueduct based on the centerline of the vestibular aqueduct, and calculate the tissue parameters of the corresponding semicircular canal based on the centerline of each semicircular canal among the external semicircular canal, the anterior semicircular canal, and the posterior semicircular canal.

[0117] Optionally, after the parameter acquisition device acquires the target ear image and ear parameters, it can also display the target ear image and ear parameters so that clinicians can have a deeper and more intuitive understanding of the anatomical structure of the ear and the range, morphology and adjacent relationships of the lesions, thereby facilitating doctors' diagnosis and formulating correct surgical plans.

[0118] It is understandable that the order of the steps of the method for obtaining ear parameters provided in the embodiment of the present application can be appropriately adjusted, and the steps can be increased or decreased accordingly according to the situation. For example, step 202 can be deleted according to the situation. Any technician familiar with the technical field can easily think of a method of variation within the technical scope disclosed in the present application, which should be included in the protection scope of the present application, so it will not be repeated.

[0119] In summary, the embodiment of the present application provides a method for obtaining ear parameters, which can obtain a three-dimensional head image of a scanned object, and then output the ear parameters of the ear based on the ear tissue included in the ear of the scanned object in the three-dimensional head image. Compared with the method of manually detecting the ear through tools to obtain ear parameters, the method provided by the embodiment of the present application can effectively improve the efficiency of obtaining ear parameters and improve the flexibility of obtaining ear parameters.

[0120] The embodiment of the present application provides a device for obtaining ear parameters, which can be applied to a parameter obtaining device. Figure 4 , the device 300 comprises:

[0121] The acquisition module 301 is used to acquire a three-dimensional head image of a scanned object, where the scanned object has ears.

[0122] An output module 302, configured to output ear parameters of the ear based on the ear tissue included in the ear in the three-dimensional head image;

[0123] The ear parameters include: ear tissue included in the ear of the scanned object.

[0124] Figure 5 is a schematic diagram of the structure of another device for obtaining ear parameters provided in an embodiment of the present application. Figure 5 , the device may also include:

[0125] The ear diagnosis module 303 is used to determine the diagnosis result of the ear based on the ear parameters of the scanned object, wherein the diagnosis result includes at least one of: external auditory canal deformity, tympanic membrane deformity, auditory ossicle deformity, inflammation or tumor in the middle ear cavity, internal auditory canal deformity, cochlear deformity, vestibular aqueduct deformity, and semicircular canal deformity.

[0126] Optionally, the ear parameters may include: a plurality of ear tissues included in the ear of the scanned object, a tissue parameter of a first ear tissue among the plurality of ear tissues, and a connection state of at least two second ear tissues among the plurality of ear tissues.

[0127] In the embodiment of the present application, when the ear parameter includes the lumen diameter of the external auditory canal, the ear diagnosis module 303 can be used to determine that the external auditory canal is deformed if it is determined that the lumen diameter of the external auditory canal is less than a first diameter threshold.

[0128] Specifically, external auditory canal malformation includes: external auditory canal atresia and external auditory canal stenosis. If the ear diagnosis module 303 determines that the lumen diameter of the external auditory canal is less than the first diameter threshold and greater than the auxiliary diameter threshold, it can be determined that the external auditory canal of the ear is stenotic. If the ear diagnosis module 303 determines that the lumen diameter is less than or equal to the auxiliary diameter threshold, it can be determined that the external auditory canal of the ear is atresia.

[0129] The first diameter threshold is greater than the auxiliary diameter threshold, and both the first diameter threshold and the auxiliary diameter threshold may be pre-stored by the ear diagnosis module 303. For example, the first diameter threshold may be 4 mm, and the auxiliary diameter threshold may be 0.

[0130] In the case where the ear parameter includes: the connection status between the eardrum and other tissues, the ear diagnosis module 303 can be used to determine that the eardrum of the ear is deformed if the connection status is determined to be connected.

[0131] In the case where the ear parameters include: ear tissues included in the middle ear of the scanned object, the connection state between the malleus and the incus, the connection state between the incus and the stapes, and the connection state between each bone tissue in the malleus, the incus and the stapes and the cavity wall of the middle ear cavity, the ear diagnosis module 303 can be used to:

[0132] If it is determined that the ossicles of the scanned object do not include at least one of the malleus, incus and stapes, and / or the malleus is not connected to the incus, and / or the incus is not connected to the stapes, and / or at least one bone tissue among the malleus, incus and stapes is connected to the wall of the middle ear cavity, then it is determined that the ossicles of the ear are deformed.

[0133] When the ear parameter includes the average density of the middle ear cavity, the ear diagnosis module 303 may be used to determine that there is inflammation or a tumor in the middle ear cavity if the average density of the middle ear cavity is higher than a density threshold. The density threshold may be pre-stored by the ear diagnosis module.

[0134] In the case where the ear parameter includes: the diameter of the internal auditory canal, the ear diagnosis module 303 can be used to: if it is determined that the diameter of the internal auditory canal is less than the second diameter threshold, or greater than the third diameter threshold, then determine that the internal auditory canal is deformed. The third diameter threshold is greater than the second diameter threshold, and both can be pre-stored by the ear diagnosis module. For example, the third diameter threshold can be 8 mm, and the second diameter threshold can be 3 mm.

[0135] In the case where the ear parameters include: the ear tissue included in the inner ear and the tissue parameters of the cochlea, the ear diagnosis module 303 can be used for: if it is determined that the inner ear does not include the cochlea, and / or the height of the cochlea is less than the height threshold, and / or the length of the cochlea is less than the length threshold, and / or the number of turns of the cochlea is less than the number of turns threshold, then cochlear deformity can be determined.

[0136] The height threshold, length threshold and number of turns threshold may all be pre-stored by the ear diagnosis module 303. For example, the height threshold may be 5 mm, the length threshold may be 31 mm, and the number of turns threshold may be 3 turns.

[0137] In the case where the ear parameter includes the diameter of the vestibular aqueduct, the ear diagnosis module 303 can be used to: if it is determined that the diameters of the middle and distal segments of the vestibular aqueduct are both greater than a fourth diameter threshold, it can be determined that the vestibular aqueduct is malformed. Specifically, the scanned object suffers from large vestibular aqueduct syndrome.

[0138] When the ear parameters include the ear tissue included in the inner ear, and the diameters of each of the external semicircular canal, the anterior semicircular canal and the posterior semicircular canal, the ear diagnosis module 303 can be used: if it is determined that the inner ear does not include at least one of the semicircular canal, the anterior semicircular canal and the posterior semicircular canal, and / or the diameter of any semicircular canal is less than the fifth diameter threshold, and / or the diameter of any semicircular canal is greater than the sixth diameter threshold, then a semicircular canal malformation can be determined.

[0139] Specifically, semicircular canal malformation includes: semicircular canal absence, semicircular canal dysplasia or semicircular canal enlargement. If the ear diagnosis module 303 determines that the inner ear does not include the external semicircular canal, and / or, the anterior semicircular canal, and / or, the posterior semicircular canal, it can be determined that the semicircular canal is absent. If the ear diagnosis module 303 determines that the diameter of any semicircular canal is less than the fifth diameter threshold, it can be determined that any semicircular canal is dysplastic. If the ear diagnosis module 303 determines that the diameter of any semicircular canal is greater than the sixth diameter threshold, it can be determined that any semicircular canal is enlarged.

[0140] The fifth diameter threshold may be less than or equal to the first value, which may be less than or equal to 2 / 3 of the diameter of a normally developed semicircular canal. The fifth diameter threshold may be greater than or equal to the second value, which may be greater than or equal to 1.5 times the diameter of a normally developed semicircular canal.

[0141] Optionally, the output module 302 may be used to:

[0142] Based on the three-dimensional head image, a target ear image of the scanned object is acquired, wherein the target ear image is annotated with ear tissues included in the ear of the scanned object;

[0143] Based on the target ear image, ear parameters of the ear are output.

[0144] Optionally, the ear includes: the inner ear, the middle ear and the outer ear. The output module 302 can be used for:

[0145] Based on the three-dimensional head image, a first ear image, a first inner ear sub-image, and a first middle ear sub-image of the scanned object are acquired, wherein the first ear image is labeled with at least ear tissue included in the outer ear, the first inner ear sub-image is labeled with ear tissue included in the inner ear, and the first middle ear sub-image is labeled with ear tissue included in the middle ear;

[0146] A target ear image is acquired based on the first ear image, the first inner ear sub-image, and the first middle ear sub-image.

[0147] Optionally, the output module 302 may be used to:

[0148] Based on the three-dimensional head image, a second inner ear sub-image and a second middle ear sub-image of the scanned object are acquired, wherein the second inner ear sub-image does not mark the ear tissue included in the inner ear, and the second middle ear sub-image does not mark the ear tissue included in the middle ear;

[0149] splicing the second inner ear sub-image, the second middle ear sub-image, and the outer ear sub-image to obtain a second ear image;

[0150] acquiring a first ear image based on the second ear image;

[0151] Based on the second inner ear sub-image, acquiring a first inner ear sub-image;

[0152] Based on the second middle ear sub-image, a first middle ear sub-image is acquired.

[0153] Optionally, the output module 302 may be used to:

[0154] The second inner ear sub-image is input into the inner ear segmentation model to obtain a first inner ear sub-image output by the inner ear segmentation model.

[0155] Optionally, the output module 302 may be used to:

[0156] The second middle ear sub-image is input into the middle ear segmentation model to obtain the first middle ear sub-image output by the middle ear segmentation model.

[0157] Optionally, the output module 302 may be used to:

[0158] The second ear image is input into the ear segmentation model to obtain the first ear image output by the ear segmentation model.

[0159] Optionally, the output module 302 may be used to:

[0160] determining positions of inner ear key points of the inner ear and middle ear key points of the middle ear in the three-dimensional head image;

[0161] Based on the positions of the key points of the inner ear, the three-dimensional head image is sampled to obtain a second inner ear sub-image of the scanned object;

[0162] Based on the positions of the middle ear key points, the three-dimensional head image is sampled to obtain a second middle ear sub-image of the scanned object.

[0163] According to the above description, the ear parameter acquisition device provided in the embodiment of the present application can fully automatically segment, identify, measure ear tissue and diagnose ear diseases, thereby effectively reducing manual operations and improving the efficiency of ear parameter acquisition.

[0164] In summary, the embodiment of the present application provides a device for acquiring ear parameters, which can acquire a three-dimensional head image of a scanned object, and then output ear parameters of the ear based on the ear tissue included in the ear of the scanned object in the three-dimensional head image. Compared with the method of manually detecting the ear through tools to obtain ear parameters, the device provided by the embodiment of the present application can effectively improve the efficiency of acquiring ear parameters and improve the flexibility of acquiring ear parameters.

[0165] Figure 6 Schematic diagram of a parameter acquisition device provided in an embodiment of the present application. Figure 6As shown, the parameter acquisition device 400 includes: a processor 401 and a memory 403. The processor 401 and the memory 403 are connected, such as through a bus 402. Optionally, the parameter acquisition device 400 may also include a transceiver 404. It should be noted that in actual applications, the transceiver 404 is not limited to one, and the structure of the parameter acquisition device 400 does not constitute a limitation on the embodiments of the present application.

[0166] Processor 401 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 401 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0167] The bus 402 may include a path to transmit information between the above components. The bus 402 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 402 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0168] The memory 403 is used to store a computer program corresponding to the method for obtaining ear parameters in the above embodiment of the present application, and the computer program is controlled and executed by the processor 401. The processor 401 is used to execute the computer program stored in the memory 403 to implement the content shown in the above method embodiment.

[0169] The present application embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for obtaining ear parameters provided in the above method embodiment is implemented. For example, Figure 1 or Figure 2 The method shown.

[0170] The present application embodiment provides a computer program product, which includes a computer program or a computer instruction, and when the computer program or the computer instruction is executed by a processor, the method for obtaining ear parameters provided in the above method embodiment is implemented. For example, Figure 1 or Figure 2 The method shown.

[0171] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0172] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0173] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0174] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0175] In this application, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0176] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for obtaining ear parameters, characterized in that: The method comprises: Acquire a three-dimensional head image of a scanned object, wherein the scanned object has ears; outputting ear parameters of the ear based on ear tissue included in the ear in the three-dimensional head image; The ear parameters include: ear tissues included in the ears of the scanned object.

2. The method according to claim 1, characterized in that: Outputting ear parameters of the ear based on ear tissue included in the ear in the three-dimensional head image includes: Based on the three-dimensional head image, acquiring a target ear image of the scanned object, wherein the target ear image is annotated with ear tissues included in the ear of the scanned object; Based on the target ear image, ear parameters of the ear are output.

3. The method according to claim 2, characterized in that The ear includes: an inner ear, a middle ear and an outer ear; based on the three-dimensional head image, acquiring a target ear image of the scanned object includes: Based on the three-dimensional head image, acquiring a first ear image, a first inner ear sub-image, and a first middle ear sub-image of the scanned object, wherein the first ear image is at least annotated with ear tissue included in the outer ear, the first inner ear sub-image is annotated with ear tissue included in the inner ear, and the first middle ear sub-image is annotated with ear tissue included in the middle ear; A target ear image is acquired based on the first ear image, the first inner ear sub-image, and the first middle ear sub-image.

4. The method according to claim 3, characterized in that Acquiring a first ear image, a first inner ear sub-image, and a first middle ear sub-image of the scanned object based on the three-dimensional head image includes: Based on the three-dimensional head image, acquiring a second inner ear sub-image and a second middle ear sub-image of the scanned object, wherein the second inner ear sub-image does not mark the ear tissue included in the inner ear, and the second middle ear sub-image does not mark the ear tissue included in the middle ear; splicing the second inner ear sub-image, the second middle ear sub-image, and the outer ear sub-image to obtain a second ear image; acquiring a first ear image based on the second ear image; Based on the second inner ear sub-image, acquiring a first inner ear sub-image; Based on the second middle ear sub-image, a first middle ear sub-image is acquired.

5. The method according to claim 4, characterized in that Acquiring a first inner ear sub-image based on the second inner ear sub-image includes: The second inner ear sub-image is input into an inner ear segmentation model to obtain a first inner ear sub-image output by the inner ear segmentation model.

6. The method according to claim 4, characterized in that Acquiring a first middle ear sub-image based on the second middle ear sub-image includes: The second middle ear sub-image is input into a middle ear segmentation model to obtain a first middle ear sub-image output by the middle ear segmentation model.

7. The method according to claim 4, characterized in that Acquiring a first ear image based on the second ear image includes: The second ear image is input into an ear segmentation model to obtain a first ear image output by the ear segmentation model.

8. The method according to any one of claims 4 to 7, characterized in that: Acquiring a second inner ear sub-image and a second middle ear sub-image of the scanned object based on the three-dimensional head image includes: Determine the positions of the inner ear key points of the inner ear and the middle ear key points of the middle ear in the three-dimensional head image; Based on the positions of the inner ear key points, sampling the three-dimensional head image to obtain a second inner ear sub-image of the scanned object; Based on the positions of the middle ear key points, the three-dimensional head image is sampled to obtain a second middle ear sub-image of the scanned object.

9. A device for obtaining ear parameters, characterized in that: The device comprises: An acquisition module, used for acquiring a three-dimensional head image of a scanned object, wherein the scanned object has ears; an output module, configured to output ear parameters of the ear based on ear tissue included in the ear in the three-dimensional head image; The ear parameters include: ear tissues included in the ears of the scanned object.

10. The device according to claim 9, characterized in that The device also includes: The ear diagnosis module is used to determine the diagnosis result of the ear based on the ear parameters.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that The computer program product comprises a computer program or a computer instruction, and when the computer program or the computer instruction is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images