Methods, devices and related equipment for identifying abnormalities in ocular ultrasound images

Abstract

This application provides a method, apparatus, and related equipment for determining anomalies in ocular ultrasound images. By identifying artifact features in pre-acquired ultrasound images, and based on these artifact features, determining whether the ultrasound image meets preset requirements for a non-artifact image; if the ultrasound image meets the preset requirements, then the corneal region, iris region, lens region, and ciliary body region in the ultrasound image are identified respectively; the boundary clarity features of the corneal region, iris region, lens region, and ciliary body region are acquired respectively; the positional features of the boundary between the iris region and the lens region are acquired; based on the boundary clarity features of the corneal region, iris region, lens region, and ciliary body region, and the positional features of the boundary between the iris region and the lens region, whether the ultrasound image is abnormal is determined. This improves the accuracy of determining anomalies in ocular ultrasound images.

Description

Technical Field

[0001] This application relates to the field of assistive medical technology, specifically to a method, apparatus, and related equipment for determining abnormalities in ocular ultrasound images. Background Technology

[0002] Ultrasound biomicroscope (UBM) is a commonly used basic examination instrument in ophthalmology, primarily used to examine the anterior chamber angle. It utilizes high-frequency ultrasound imaging technology and is a contact examination. During the procedure, a topical anesthetic is used, and the probe touches the corneal surface to measure the location of the anterior chamber angle. It is a non-invasive examination, does not cause significant damage to the eye, and does not affect the patient's vision or ocular physiological function.

[0003] However, the inventors of this application have found that UBM images are prone to distortion and abnormalities, which can have a certain impact on the diagnostic results of ophthalmologists. Summary of the Invention

[0004] This application provides a method, apparatus, and related equipment for determining abnormalities in ocular ultrasound images, aiming to solve the technical problem of how to efficiently and accurately determine whether ocular ultrasound images are abnormal.

[0005] On one hand, this application provides a method for determining abnormalities in ocular ultrasound images, the method comprising:

[0006] The artifact features of a pre-acquired ultrasound image are identified, and based on the artifact features, it is determined whether the ultrasound image meets the preset requirements for a non-artifact image. The ultrasound image is an ultrasound image of a target area of ​​a patient examined by ultrasound biological microscopy, and the target area is the eye.

[0007] If the ultrasound image meets the preset requirements for a non-artifact image, then the corneal region, iris region, lens region, and ciliary body region in the ultrasound image are identified respectively.

[0008] The boundary clarity features of the corneal region, iris region, lens region, and ciliary body region are obtained respectively.

[0009] Obtain the positional features of the boundary between the iris region and the boundary between the lens region;

[0010] Based on the boundary clarity characteristics of the corneal region, iris region, lens region, and ciliary body region, and the positional characteristics of the boundary of the iris region and the boundary of the lens, it is determined whether the ultrasound image is abnormal.

[0011] In one possible implementation of this application, obtaining the clear boundary features of the corneal region includes:

[0012] The corneal region is cropped using a first rectangular frame of a preset size as the boundary to obtain a first corneal image;

[0013] The first corneal image is binarized to obtain the processed second corneal image;

[0014] Based on the connected components, the area of ​​each connected component in the second corneal image is calculated respectively;

[0015] Based on the area and a preset area threshold, each of the connected regions is filtered to obtain a target connected region, which includes the front elastic layer connected region and the rear elastic layer connected region.

[0016] The first center line of the connected domain of the front elastic layer and the second center line of the connected domain of the rear elastic layer are obtained respectively, and multiple target distances between the first center line and the second center line are obtained;

[0017] Calculate the variance of the multiple target distances, and determine the clarity features of the corneal region based on the variance and a preset variance threshold.

[0018] In one possible implementation of this application, the iris region includes two sub-iris regions, and obtaining the clear boundary features of the iris region includes:

[0019] Obtain the boundary perimeter of each sub-iris region in the two sub-iris regions respectively;

[0020] Binarize all pixels on the boundary of each sub-iris region and obtain the set of pixel values ​​of all pixels after processing.

[0021] Based on the preset pixel value threshold and the set of pixel values, all processed pixels are filtered to obtain the target pixel set on the boundary of the sub-iris region.

[0022] The number of pixels in the target pixel set on the boundary of each sub-iris region is compared with the perimeter of the boundary of each sub-iris region to obtain the target boundary ratio of each sub-iris region.

[0023] Based on the target boundary ratio of each sub-iris region and a preset boundary ratio threshold, the clear boundary features of the iris region are determined.

[0024] In one possible implementation of this application, obtaining the clear boundary features of the lens region includes:

[0025] Obtain the perimeter of the boundary of the lens region;

[0026] Binarize all pixels on the boundary of the lens region and obtain the set of pixel values ​​of all pixels after processing.

[0027] Based on the preset pixel value threshold and the set of pixel values, all processed pixels are filtered to obtain the target pixel set on the boundary of the lens region.

[0028] The target pixel set on the boundary of the lens region is compared with the perimeter of the lens region to obtain the target boundary ratio of the lens region.

[0029] Based on the target boundary ratio of the lens region and a preset boundary ratio threshold, the clear boundary characteristics of the lens region are determined.

[0030] In one possible implementation of this application, obtaining the well-defined boundary features of the ciliary body region includes:

[0031] The ciliary body region is cropped using a second rectangular frame of a preset size as the boundary to obtain a first ciliary body image;

[0032] Obtain the first boundary line of the ciliary body region in the first ciliary body image, and the first centroid of the first boundary line;

[0033] The first ciliary body image is binarized to obtain the processed second ciliary body image;

[0034] Obtain the second boundary line of the ciliary body region in the second ciliary body image, and the second centroid of the second boundary line;

[0035] Calculate the Euclidean distance between the first centroid and the second centroid, and determine the clear boundary features of the ciliary body region based on the Euclidean distance.

[0036] In one possible implementation of this application, the iris region includes two sub-iris regions, and the step of obtaining the positional features of the boundary between the iris region and the boundary between the lens region includes:

[0037] The first and second overlap degrees between the boundaries of the two sub-iris regions and the boundary of the lens region are obtained respectively;

[0038] Based on the first overlap, the second overlap, and a preset overlap threshold, the positional characteristics of the boundary between the iris region and the lens region are determined.

[0039] In one possible implementation of this application, determining whether the ultrasound image is abnormal based on the boundary clarity features of the corneal region, iris region, lens region, and ciliary body region, and the positional features of the boundary of the iris region and the boundary of the lens, includes:

[0040] The abnormality parameters of the ultrasound image are obtained by weighted fitting of the boundary clarity features of the corneal region, iris region, lens region and ciliary body region, and the positional features of the boundary of the iris region and the boundary of the lens.

[0041] Based on the abnormality level parameter and the preset abnormality level threshold, it is determined whether the ultrasound image is abnormal.

[0042] On the other hand, this application provides an apparatus for determining abnormalities in ocular ultrasound images, the apparatus comprising:

[0043] The first identification unit is used to identify the artifact features of the pre-acquired ultrasound image and, based on the artifact features, determine whether the ultrasound image meets the preset non-artifact image requirements. The ultrasound image is an ultrasound image of a patient's target area examined by ultrasound biological microscopy, and the target area is the eye.

[0044] The second identification unit is used to identify the corneal region, iris region, lens region and ciliary body region in the ultrasound image if the ultrasound image meets the preset non-artifact image requirements.

[0045] The first acquisition unit is used to acquire the boundary clarity features of the corneal region, iris region, lens region and ciliary body region respectively.

[0046] The second acquisition unit is used to acquire the positional features of the boundary between the iris region and the boundary between the lens region;

[0047] The first determining unit is used to determine whether the ultrasound image is abnormal based on the boundary clarity characteristics of the corneal region, iris region, lens region and ciliary body region, and the positional characteristics of the boundary of the iris region and the boundary of the lens.

[0048] In one possible implementation of this application, the first acquisition unit is specifically used for:

[0049] The corneal region is cropped using a first rectangular frame of a preset size as the boundary to obtain a first corneal image;

[0050] The first corneal image is binarized to obtain the processed second corneal image;

[0051] Based on the connected components, the area of ​​each connected component in the second corneal image is calculated respectively;

[0052] Based on the area and a preset area threshold, each of the connected regions is filtered to obtain a target connected region, which includes the front elastic layer connected region and the rear elastic layer connected region.

[0053] The first center line of the connected domain of the front elastic layer and the second center line of the connected domain of the rear elastic layer are obtained respectively, and multiple target distances between the first center line and the second center line are obtained;

[0054] Calculate the variance of the multiple target distances, and determine the clarity features of the corneal region based on the variance and a preset variance threshold.

[0055] In one possible implementation of this application, the iris region includes two sub-iris regions, and the first acquisition unit is further configured to:

[0056] Obtain the boundary perimeter of each sub-iris region in the two sub-iris regions respectively;

[0057] Binarize all pixels on the boundary of each sub-iris region and obtain the set of pixel values ​​of all pixels after processing.

[0058] Based on the preset pixel value threshold and the set of pixel values, all processed pixels are filtered to obtain the target pixel set on the boundary of the sub-iris region.

[0059] The number of pixels in the target pixel set on the boundary of each sub-iris region is compared with the perimeter of the boundary of each sub-iris region to obtain the target boundary ratio of each sub-iris region.

[0060] Based on the target boundary ratio of each sub-iris region and a preset boundary ratio threshold, the clear boundary features of the iris region are determined.

[0061] In one possible implementation of this application, the first acquiring unit is further configured to:

[0062] Obtain the perimeter of the boundary of the lens region;

[0063] Binarize all pixels on the boundary of the lens region and obtain the set of pixel values ​​of all pixels after processing.

[0064] Based on the preset pixel value threshold and the set of pixel values, all processed pixels are filtered to obtain the target pixel set on the boundary of the lens region.

[0065] The target pixel set on the boundary of the lens region is compared with the perimeter of the lens region to obtain the target boundary ratio of the lens region.

[0066] Based on the target boundary ratio of the lens region and a preset boundary ratio threshold, the clear boundary characteristics of the lens region are determined.

[0067] In one possible implementation of this application, the first acquiring unit is further configured to:

[0068] The ciliary body region is cropped using a second rectangular frame of a preset size as the boundary to obtain a first ciliary body image;

[0069] Obtain the first boundary line of the ciliary body region in the first ciliary body image, and the first centroid of the first boundary line;

[0070] The first ciliary body image is binarized to obtain the processed second ciliary body image;

[0071] Obtain the second boundary line of the ciliary body region in the second ciliary body image, and the second centroid of the second boundary line;

[0072] Calculate the Euclidean distance between the first centroid and the second centroid, and determine the clear boundary features of the ciliary body region based on the Euclidean distance.

[0073] In one possible implementation of this application, the iris region includes two sub-iris regions, and the second acquisition unit is specifically used for:

[0074] The first and second overlap degrees between the boundaries of the two sub-iris regions and the boundary of the lens region are obtained respectively;

[0075] Based on the first overlap, the second overlap, and a preset overlap threshold, the positional characteristics of the boundary between the iris region and the lens region are determined.

[0076] In one possible implementation of this application, the first determining unit is specifically used for:

[0077] The abnormality parameters of the ultrasound image are obtained by weighted fitting of the boundary clarity features of the corneal region, iris region, lens region and ciliary body region, and the positional features of the boundary of the iris region and the boundary of the lens.

[0078] Based on the abnormality level parameter and the preset abnormality level threshold, it is determined whether the ultrasound image is abnormal.

[0079] On the other hand, this application also provides a computer device, the computer device comprising:

[0080] One or more processors;

[0081] Memory; and

[0082] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method for determining anomalies in ocular ultrasound images.

[0083] On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps in the method for determining anomalies in ocular ultrasound images.

[0084] The method for determining abnormalities in ocular ultrasound images provided in this application identifies artifact features in pre-acquired ultrasound images and, based on these artifact features, determines whether the ultrasound image meets preset requirements for a non-artifact image. The ultrasound image is an ultrasound image obtained by performing an ultrasound biological microscope examination on a target area of ​​the patient, with the target area being the eye. If the ultrasound image meets the preset requirements for a non-artifact image, the corneal region, iris region, lens region, and ciliary body region in the ultrasound image are identified respectively. The boundary clarity features of the corneal region, iris region, lens region, and ciliary body region are obtained respectively. The positional features of the boundary between the iris region and the lens region are obtained. Based on the boundary clarity features of the corneal region, iris region, lens region, and ciliary body region, and the positional features of the boundary between the iris region and the lens region, the abnormality of the ultrasound image is determined. Compared to traditional methods, where existing ocular ultrasound images are prone to abnormalities and ophthalmologists cannot accurately diagnose them, leading to misdiagnosis, this application creatively performs artifact detection on ultrasound images first for preliminary screening, ensuring the accuracy of subsequent images. Furthermore, by comprehensively analyzing the boundary clarity characteristics of the corneal region, iris region, lens region, and ciliary body region, as well as the positional characteristics of the boundary between the iris region and the lens region, it is possible to more accurately determine whether the ultrasound image is abnormal, thereby improving the accuracy of determining abnormalities in ocular ultrasound images. Attached Figure Description

[0085] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0086] Figure 1 This is a schematic diagram of a scenario for an abnormality determination system for ocular ultrasound images provided in an embodiment of this application;

[0087] Figure 2 This is a schematic flowchart of an embodiment of the method for determining abnormalities in ocular ultrasound images provided in this application.

[0088] Figure 3 This is a schematic diagram of an ocular ultrasound image provided in an embodiment of this application;

[0089] Figure 4 This is a schematic diagram of the connected components of the corneal region after binarization provided in the embodiments of this application;

[0090] Figure 5 This is a schematic diagram of obtaining the center line of a connected component according to an embodiment of this application;

[0091] Figure 6 This is a schematic diagram of an embodiment of the device for determining abnormalities in ocular ultrasound images provided in this application.

[0092] Figure 7 This is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation

[0093] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0094] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0095] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0096] This application provides a method, apparatus, and related equipment for determining abnormalities in ocular ultrasound images, which will be described in detail below.

[0097] like Figure 1 As shown, Figure 1 This is a schematic diagram of a scenario for an ocular ultrasound image anomaly determination system provided in an embodiment of this application. The ocular ultrasound image anomaly determination system may include a computer device 100, which integrates an ocular ultrasound image anomaly determination device, such as... Figure 1 Computer equipment 100.

[0098] In this embodiment, the computer device 100 is mainly used to identify artifact features of pre-acquired ultrasound images and, based on these artifact features, determine whether the ultrasound images meet preset non-artifact image requirements. The ultrasound images are ultrasound images obtained by performing ultrasound biological microscopy on a target area of ​​the patient, with the target area being the eye. If the ultrasound images meet the preset non-artifact image requirements, the corneal region, iris region, lens region, and ciliary body region in the ultrasound images are identified respectively. The boundary clarity features of the corneal region, iris region, lens region, and ciliary body region are obtained respectively. The positional features of the boundary between the iris region and the lens region are obtained. Based on the boundary clarity features of the corneal region, iris region, lens region, and ciliary body region, and the positional features of the boundary between the iris region and the lens region, it is determined whether the ultrasound image is abnormal.

[0099] In this embodiment, the computer device 100 can be a terminal or a server. When the computer device 100 is a server, it can be a standalone server, a server network, or a server cluster. For example, the computer device 100 described in this embodiment includes, but is not limited to, computers, network hosts, single network servers, multiple sets of network servers, or cloud servers constructed from multiple servers. The cloud server is constructed from a large number of computers or network servers based on cloud computing.

[0100] It is understood that when the computer device 100 in this embodiment is a terminal, the terminal used can be a device that includes both receiving and transmitting hardware, that is, a device with receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. Such a device may include: cellular or other communication devices, which have a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. Specifically, the computer device 100 may be a desktop terminal or a mobile terminal, and the computer device 100 may also be one of a mobile phone, tablet computer, laptop computer, medical auxiliary instrument, etc.

[0101] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario for the solution in this application and is not intended to limit the application scenario of the solution in this application. Other application environments may include more than one. Figure 1 The number of computer devices shown is more or less, for example Figure 1 Only one computer device is shown in the image. It is understood that the system for determining abnormalities in ocular ultrasound images may also include one or more other computer devices, which are not specified here.

[0102] In addition, such as Figure 1 As shown, the ocular ultrasound image anomaly determination system may further include a memory 200 for storing data, such as storing ultrasound images of the patient's eye and ocular ultrasound image anomaly determination data, for example, ocular ultrasound image anomaly determination data during the operation of the ocular ultrasound image anomaly determination system.

[0103] It should be noted that, Figure 1 The schematic diagram of the ocular ultrasound image anomaly determination system shown is merely an example. The ocular ultrasound image anomaly determination system and scenario described in this application embodiment are for the purpose of more clearly illustrating the technical solutions of this application embodiment and do not constitute a limitation on the technical solutions provided in this application embodiment. As those skilled in the art will know, with the evolution of ocular ultrasound image anomaly determination systems and the emergence of new business scenarios, the technical solutions provided in this application embodiment are also applicable to similar technical problems.

[0104] Next, we will introduce the method for determining abnormalities in ocular ultrasound images provided in the embodiments of this application.

[0105] In this embodiment of the method for determining anomalies in ocular ultrasound images, an ocular ultrasound image anomaly determination device is used as the execution subject. For the sake of simplicity and ease of description, the execution subject will be omitted in subsequent method embodiments. The ocular ultrasound image anomaly determination device is applied to a computer device.

[0106] Please see Figures 2 to 7 , Figure 2 This is a schematic flowchart of an embodiment of the method for determining anomalies in ocular ultrasound images provided in this application. The method for determining anomalies in ocular ultrasound images includes steps 201 to 205:

[0107] 201. Identify the artifact features of the pre-acquired ultrasound images, and based on the artifact features, determine whether the ultrasound images meet the preset requirements for non-artifact images.

[0108] The ultrasound image is an ultrasound image obtained by performing an ultrasound biological microscope examination on a target area of ​​the patient, and the target area is the eye.

[0109] Among them, the requirement for non-artifact images is that the confidence level of the artifact features of the ultrasound image is less than a preset artifact confidence threshold. This artifact confidence threshold can be adjusted according to actual needs, and there is no specific limitation.

[0110] In this embodiment of the application, artifact features of pre-acquired ultrasound images can be identified in various ways. For example, a pre-trained artifact image recognition model can be used to identify artifact features of pre-acquired ultrasound images. The artifact feature can be the confidence level of the presence of artifact features in the ultrasound image. Then, based on the artifact feature and a preset artifact confidence threshold, it is determined whether the ultrasound image meets the preset non-artifact image requirements. If the confidence level of the artifact feature of the ultrasound image is less than the artifact confidence threshold, it can be determined that the ultrasound image meets the preset non-artifact image requirements; otherwise, it does not meet the preset non-artifact image requirements.

[0111] 202. If the ultrasound image meets the preset requirements for a non-artifact image, then identify the corneal region, iris region, lens region, and ciliary body region in the ultrasound image respectively.

[0112] Specifically, the corneal region, iris region, lens region, and ciliary body region in the ultrasound image can be identified in various ways. For example, the corneal region can be identified based on a pre-trained YOLOv3 image object detection neural network model; the iris region can be identified based on a pre-trained UNet++ image segmentation neural network model; the lens region can be identified based on a pre-trained UNet++ image segmentation neural network model; and the ciliary body region can be identified based on a pre-trained YOLOv3 image object detection neural network model. It should be noted that the models in the above examples are preferred embodiments, but other models can also be used, and the specific settings and adjustments can be made according to actual needs.

[0113] In another embodiment of this application, if the ultrasound image does not meet the preset non-artifact image requirements, the ultrasound image is deleted, and a new ultrasound image is acquired. This ultrasound image is also an ultrasound image of the target area of ​​the same patient examined by ultrasound biomicroscopy, and the target area is the eye. Then, step 201 is repeated until an ultrasound image that meets the preset non-artifact image requirements is found, and then step 202 and subsequent steps of step 202 are performed.

[0114] 203. Obtain the boundary clarity features of the corneal region, iris region, lens region, and ciliary body region respectively;

[0115] Among them, the boundary sharpness feature of each object region is a feature that evaluates the level of boundary sharpness of the object region. This feature can be reflected by the confidence level of the boundary sharpness feature corresponding to each object region.

[0116] In this embodiment, the boundary clarity features of the corneal region, iris region, lens region, and ciliary body region can be obtained in various ways.

[0117] Exemplary examples, in some embodiments of this application, obtaining the clear boundary features of the corneal region may include the following steps A1 to A6:

[0118] A1. Cropping the corneal region with a first rectangular frame of a preset size as the boundary to obtain a first corneal image;

[0119] The preset size can be set according to the actual situation. In this application, it is preferred that the size can be cut out to the size of the complete corneal area.

[0120] A2. Binarize the first corneal image to obtain the processed second corneal image;

[0121] A3. Based on the connected components, calculate the area of ​​each connected component in the second corneal image;

[0122] A4. Based on the area and the preset area threshold, each of the connected components is filtered to obtain the target connected component;

[0123] Specifically, based on the area and a preset area threshold, each connected component is filtered to obtain a target connected component. For example, the area can be compared with the preset area threshold, and connected components with areas smaller than the preset area threshold are filtered out, leaving the target connected components, as follows: Figure 3 As shown, Figure 3 The area within the rectangle at the top center represents the corneal region. After filtering, the resulting connected components are as follows: Figure 4 As shown, the target connected domain includes the front elastic layer connected domain and the rear elastic layer connected domain.

[0124] A5. Obtain the first center line of the connected domain of the front elastic layer and the second center line of the connected domain of the rear elastic layer respectively, and obtain multiple target distances between the first center line and the second center line;

[0125] In this embodiment of the application, the first center line of the front elastic layer connected domain and the second center line of the rear elastic layer connected domain can be obtained in a variety of ways.

[0126] For example, in some embodiments of this application, a skeletonization process can be used to obtain the first center line of the connected domain of the front elastic layer and the second center line of the connected domain of the rear elastic layer.

[0127] In this embodiment of the application, multiple target distances between the first centerline and the second centerline can be obtained in various ways.

[0128] For example, as follows Figure 5 As shown, it can be set according to the preset pixel distance. Δ x, draw multiple vertical and parallel dividing lines in sequence (e.g. Figure 5 The four vertical dividing lines in the diagram are used to intersect the two center lines, resulting in two sets of intersection points. The distances between each set of intersection points are then calculated sequentially to obtain the multiple target distances between the first center line and the second center line.

[0129] A6. Calculate the variance of the multiple target distances, and determine the clarity characteristics of the corneal region based on the variance and a preset variance threshold.

[0130] The variance threshold can be set according to actual needs.

[0131] In one specific embodiment, the clarity feature of the corneal region is determined based on the variance value and a preset variance threshold. This can be achieved by comparing the variance value with the preset variance threshold. If the variance value is less than the variance threshold, the clarity feature of the corneal region is determined to be 1 or clear. If the variance value is not less than the variance threshold, the clarity feature of the corneal region is determined to be 0 or blurry.

[0132] For example, in some embodiments of this application, the iris region includes two sub-iris regions, and obtaining the clear boundary features of the iris region may include the following steps B1 to B5:

[0133] B1. Obtain the boundary perimeter of each sub-iris region in the two sub-iris regions respectively;

[0134] In this embodiment of the application, the boundary perimeter of each sub-iris region in the two sub-iris regions can be obtained in a variety of ways.

[0135] For example, the boundary perimeter of each sub-iris region in the two sub-iris regions can be obtained through a preset image perimeter detection program, or the boundary perimeter of each sub-iris region in the two sub-iris regions can be calculated based on the pixel information of each sub-iris region in the two sub-iris regions through a preset perimeter calculation strategy.

[0136] B2. Binarize all pixels on the boundary of each sub-iris region and obtain the set of pixel values ​​of all pixels after processing.

[0137] B3. Based on the preset pixel value threshold and the set of pixel values, all processed pixels are filtered to obtain the set of target pixels on the boundary of the sub-iris region.

[0138] The preset pixel value threshold can be set according to actual needs, and this application preferably sets the pixel value threshold to 150.

[0139] In one specific implementation, pixels in the set of pixel values ​​less than the pixel value threshold of 150 can be removed, thereby retaining the pixel points that constitute the target pixel point set on the boundary of the sub-iris region.

[0140] B4. Compare the number of target pixels in the set of target pixels on the boundary of each sub-iris region with the perimeter of the boundary of each sub-iris region to obtain the target boundary ratio of each sub-iris region.

[0141] In one specific embodiment, assuming that the number of target pixels on the boundary of the two sub-iris regions are N1 and N2 respectively, and the perimeters of the two sub-iris regions are C1 and C2 respectively, then the target boundary ratios of the two sub-iris regions are: &1 = N1 / C1, &2 = N2 / C2 respectively.

[0142] B5. Based on the target boundary ratio of each sub-iris region and a preset boundary ratio threshold, determine the clear boundary features of the iris region.

[0143] The preset boundary ratio threshold σ can be set according to the actual situation.

[0144] In one specific embodiment, when &1 is greater than σ and &2 is greater than σ, the boundary clarity feature of the iris region is determined to be 1 or clear; otherwise, the boundary clarity feature of the iris region is determined to be 0 or blurry.

[0145] Exemplary, in some embodiments of this application, obtaining the clear boundary features of the lens region may include the following steps C1 to C5:

[0146] C1. Obtain the perimeter of the boundary of the lens region;

[0147] C2. Binarize all pixels on the boundary of the lens region and obtain the set of pixel values ​​of all pixels after processing.

[0148] C3. Based on the preset pixel value threshold and the set of pixel values, all processed pixels are filtered to obtain the target pixel set on the boundary of the lens region.

[0149] C4. Compare the set of target pixels on the boundary of the lens region with the perimeter of the lens region to obtain the target boundary ratio of the lens region.

[0150] C5. Based on the target boundary ratio of the lens region and the preset boundary ratio threshold, determine the clear boundary characteristics of the lens region.

[0151] The calculation principles of each step in steps C1 to C5 correspond to those of each step in steps B1 to B5 above. Therefore, they will not be repeated here. For details, please refer to steps B1 to B5 above.

[0152] In some embodiments of this application, obtaining the well-defined boundary features of the ciliary body region may include the following steps D1 to D5:

[0153] D1. The ciliary body region is cropped using a second rectangular frame of a preset size as the boundary to obtain a first ciliary body image;

[0154] The preset size can be set according to actual needs.

[0155] D2. Obtain the first boundary line of the ciliary body region in the first ciliary body image, and the first centroid of the first boundary line;

[0156] In this embodiment of the application, the first boundary line of the ciliary body region in the first ciliary body image and the first centroid of the first boundary line can be obtained in a variety of ways.

[0157] For example, the first boundary line of the ciliary region in the first ciliary body image can be found by using a preset Canny algorithm, and then the first centroid of the first boundary line can be calculated.

[0158] D3. Binarize the first ciliary body image to obtain the processed second ciliary body image;

[0159] D4. Obtain the second boundary line of the ciliary body region in the second ciliary body image, and the second centroid of the second boundary line;

[0160] The method for obtaining the second boundary line and the second centroid is the same as in step D2 above, and can be referred to in step D2 above, so it will not be repeated here.

[0161] D5. Calculate the Euclidean distance between the first centroid and the second centroid, and determine the clear boundary features of the ciliary body region based on the Euclidean distance.

[0162] In this application embodiment, there are multiple ways to determine the clear boundary features of the ciliary body region based on the Euclidean distance.

[0163] For example, the Euclidean distance L is compared with a preset Euclidean distance threshold λ. If L <= λ, then the boundary clarity feature of the ciliary body region is determined to be 1 or clear; otherwise, the boundary clarity feature of the ciliary body region is determined to be 0 or blurred.

[0164] 204. Obtain the positional characteristics of the boundary between the iris region and the lens region;

[0165] Among them, the positional feature is the feature that the boundary of the iris region and the boundary of the lens region have a certain preset positional relationship. For example, the positional feature is the feature that the boundaries of the two regions have a certain preset positional relationship, or the feature that there is no preset positional relationship.

[0166] Specifically, the positional characteristics of the boundary between the iris region and the lens region can be obtained through various methods.

[0167] Exemplarily, in some embodiments of the present application, the iris region includes two sub-iris regions. Obtaining the position characteristics of the boundary of the iris region and the boundary of the lens region may include the following steps D1 and D2:

[0168] D1. Respectively obtain the first overlap degree and the second overlap degree between the boundaries of the two sub-iris regions and the boundary of the lens region;

[0169] Where the overlap degree is the ratio of the first area of the intersection of the two regions to the second area of the union of the two regions.

[0170] Therefore, to obtain the first overlap degree and the second overlap degree between the boundaries of the two sub-iris regions and the boundary of the lens region, first sequentially obtain the first area of the intersection of the boundary of each sub-iris region and the boundary of the lens region, then sequentially obtain the second area of the union of the boundary of each sub-iris region and the boundary of the lens region, and finally sequentially compare the first area of the intersection of the boundary of each sub-iris region and the boundary of the lens region with the second area of the union of the boundary of each sub-iris region and the boundary of the lens region, so as to obtain the first overlap degree and the second overlap degree between the boundary of each iris region and the boundary of the lens region.

[0171] D2. Based on the first overlap degree, the second overlap degree, and a preset overlap degree threshold, determine the position characteristics of the boundary of the iris region and the boundary of the lens region.

[0172] Exemplarily, in some embodiments of the present application, the first overlap degree IOU1 and the second overlap degree IOU2 can be respectively compared with a preset overlap degree threshold β. Where, if 0 < IOU1 <= β and 0 < IOU2 <= β, then determine that the position characteristic of the boundary of the iris region and the boundary of the lens region is 1 or tangent; otherwise, determine that the position characteristic of the boundary of the iris region and the boundary of the lens region is 0 or not tangent. [[ID=]17]

[0173] 205. Based on the boundary clarity characteristics of the corneal region, the iris region, the lens region, and the ciliary body region, and the position characteristics of the boundary of the iris region and the boundary of the lens, determine whether the ultrasonic image is abnormal.

[0174] In the embodiments of the present application, there can be various determination methods for determining whether the ultrasonic image is abnormal based on the boundary clarity characteristics of the corneal region, the iris region, the lens region, and the ciliary body region, and the position characteristics of the boundary of the iris region and the boundary of the lens.

[0175] For example, in some embodiments of this application, determining whether the ultrasound image is abnormal based on the boundary clarity characteristics of the corneal region, iris region, lens region, and ciliary body region, and the positional characteristics of the boundary of the iris region and the boundary of the lens, may include steps E1 and E2:

[0176] E1. The boundary clarity features of the corneal region, iris region, lens region and ciliary body region, and the positional features of the boundary of the iris region and the boundary of the lens are weighted and fitted to obtain the abnormality parameter of the ultrasound image.

[0177] The weights of each feature can be obtained in various ways. For example, they can be pre-acquired using a pre-defined neural network model.

[0178] E2. Based on the abnormality level parameter and the preset abnormality level threshold, determine whether the ultrasound image is abnormal.

[0179] In this embodiment of the application, the abnormality of the ultrasound image is determined based on the abnormality degree parameter θ and the preset abnormality degree threshold ω. Specifically, if the abnormality degree parameter θ is greater than the abnormality degree threshold ω, the ultrasound image is determined to be abnormal or distorted; otherwise, the ultrasound image is determined to be normal or not distorted.

[0180] The solution disclosed in this application, compared to traditional methods, addresses the common problem of abnormalities in existing ocular ultrasound images, which can lead to misdiagnosis as ophthalmologists struggle to accurately diagnose them. This application creatively performs artifact detection on the ultrasound images first, thus conducting preliminary screening to ensure the accuracy of subsequent images. Furthermore, by comprehensively analyzing the boundary clarity characteristics of the corneal, iris, lens, and ciliary body regions, as well as the positional characteristics of the iris boundary and the lens boundary, it can more accurately determine whether the ultrasound image is abnormal, thereby improving the accuracy of identifying abnormalities in ocular ultrasound images.

[0181] To better implement the method for determining anomalies in ocular ultrasound images in the embodiments of this application, this application also provides a device for determining anomalies in ocular ultrasound images, based on the method for determining anomalies in ocular ultrasound images, such as... Figure 6 As shown, the anomaly determination device 600 for ocular ultrasound images includes:

[0182] The first identification unit 601 is used to identify the artifact features of the pre-acquired ultrasound image and, based on the artifact features, determine whether the ultrasound image meets the preset non-artifact image requirements. The ultrasound image is an ultrasound image of a patient's target area examined by ultrasound biological microscopy, and the target area is the eye.

[0183] The second identification unit 602 is used to identify the corneal region, iris region, lens region and ciliary body region in the ultrasound image if the ultrasound image meets the preset non-artifact image requirements.

[0184] The first acquisition unit 603 is used to acquire the boundary clarity features of the corneal region, iris region, lens region and ciliary body region respectively.

[0185] The second acquisition unit 604 is used to acquire the positional features of the boundary between the iris region and the boundary between the lens region;

[0186] The first determining unit 605 is used to determine whether the ultrasound image is abnormal based on the boundary clarity characteristics of the corneal region, iris region, lens region and ciliary body region, and the positional characteristics of the boundary of the iris region and the boundary of the lens.

[0187] In some embodiments of this application, the first acquisition unit 603 is specifically used for:

[0188] The corneal region is cropped using a first rectangular frame of a preset size as the boundary to obtain a first corneal image;

[0189] The first corneal image is binarized to obtain the processed second corneal image;

[0190] Based on the connected components, the area of ​​each connected component in the second corneal image is calculated respectively;

[0191] Based on the area and a preset area threshold, each of the connected regions is filtered to obtain a target connected region, which includes the front elastic layer connected region and the rear elastic layer connected region.

[0192] The first center line of the connected domain of the front elastic layer and the second center line of the connected domain of the rear elastic layer are obtained respectively, and multiple target distances between the first center line and the second center line are obtained;

[0193] Calculate the variance of the multiple target distances, and determine the clarity features of the corneal region based on the variance and a preset variance threshold.

[0194] In some embodiments of this application, the iris region includes two sub-iris regions, and the first acquisition unit 603 is further configured to:

[0195] Obtain the boundary perimeter of each sub-iris region in the two sub-iris regions respectively;

[0196] Binarize all pixels on the boundary of each sub-iris region and obtain the set of pixel values ​​of all pixels after processing.

[0197] Based on the preset pixel value threshold and the set of pixel values, all processed pixels are filtered to obtain the target pixel set on the boundary of the sub-iris region.

[0198] The number of pixels in the target pixel set on the boundary of each sub-iris region is compared with the perimeter of the boundary of each sub-iris region to obtain the target boundary ratio of each sub-iris region.

[0199] Based on the target boundary ratio of each sub-iris region and a preset boundary ratio threshold, the clear boundary features of the iris region are determined.

[0200] In some embodiments of this application, the first acquisition unit 603 is further configured to:

[0201] Obtain the perimeter of the boundary of the lens region;

[0202] Binarize all pixels on the boundary of the lens region and obtain the set of pixel values ​​of all pixels after processing.

[0203] Based on the preset pixel value threshold and the set of pixel values, all processed pixels are filtered to obtain the target pixel set on the boundary of the lens region.

[0204] The target pixel set on the boundary of the lens region is compared with the perimeter of the lens region to obtain the target boundary ratio of the lens region.

[0205] Based on the target boundary ratio of the lens region and a preset boundary ratio threshold, the clear boundary characteristics of the lens region are determined.

[0206] In some embodiments of this application, the first acquisition unit 603 is further configured to:

[0207] The ciliary body region is cropped using a second rectangular frame of a preset size as the boundary to obtain a first ciliary body image;

[0208] Obtain the first boundary line of the ciliary body region in the first ciliary body image, and the first centroid of the first boundary line;

[0209] The first ciliary body image is binarized to obtain the processed second ciliary body image;

[0210] Obtain the second boundary line of the ciliary body region in the second ciliary body image, and the second centroid of the second boundary line;

[0211] Calculate the Euclidean distance between the first centroid and the second centroid, and determine the clear boundary features of the ciliary body region based on the Euclidean distance.

[0212] In some embodiments of this application, the iris region includes two sub-iris regions, and the second acquisition unit 604 is specifically used for:

[0213] The first and second overlap degrees between the boundaries of the two sub-iris regions and the boundary of the lens region are obtained respectively;

[0214] Based on the first overlap, the second overlap, and a preset overlap threshold, the positional characteristics of the boundary between the iris region and the lens region are determined.

[0215] In some embodiments of this application, the first determining unit 605 is specifically used for:

[0216] The abnormality parameters of the ultrasound image are obtained by weighted fitting of the boundary clarity features of the corneal region, iris region, lens region and ciliary body region, and the positional features of the boundary of the iris region and the boundary of the lens.

[0217] Based on the abnormality level parameter and the preset abnormality level threshold, it is determined whether the ultrasound image is abnormal.

[0218] The method for determining abnormalities in ocular ultrasound images provided in this application includes a first identification unit 601, used to identify artifact features of a pre-acquired ultrasound image and, based on the artifact features, determine whether the ultrasound image meets preset non-artifact image requirements. The ultrasound image is an ultrasound image obtained by performing ultrasound biological microscopy on a target area of ​​a patient, where the target area is the eye. A second identification unit 602 is used to identify the corneal region, iris region, lens region, and ciliary body region in the ultrasound image if the ultrasound image meets the preset non-artifact image requirements. A first acquisition unit 603 is used to acquire the boundary clarity features of the corneal region, iris region, lens region, and ciliary body region, respectively. A second acquisition unit 604 is used to acquire the positional features of the boundary between the iris region and the lens region. A first determination unit 605 is used to determine whether the ultrasound image is abnormal based on the boundary clarity features of the corneal region, iris region, lens region, and ciliary body region, and the positional features of the boundary between the iris region and the lens region. Compared to traditional methods, where existing ocular ultrasound images are prone to abnormalities and ophthalmologists cannot accurately diagnose them, leading to misdiagnosis, this application creatively performs artifact detection on ultrasound images first for preliminary screening, ensuring the accuracy of subsequent images. Furthermore, by comprehensively analyzing the boundary clarity characteristics of the corneal region, iris region, lens region, and ciliary body region, as well as the positional characteristics of the boundary between the iris region and the lens region, it is possible to more accurately determine whether the ultrasound image is abnormal, thereby improving the accuracy of determining abnormalities in ocular ultrasound images.

[0219] In addition to the above-described methods and apparatus for determining anomalies in ocular ultrasound images, embodiments of this application also provide a computer device that integrates any of the ocular ultrasound image anomaly determination apparatuses provided in the embodiments of this application. The computer device includes:

[0220] One or more processors;

[0221] Memory; and

[0222] One or more applications, wherein the one or more applications are stored in the memory and configured by the processor to perform the operation of any of the methods described in any of the embodiments of the above-described methods for determining anomalies in ocular ultrasound images.

[0223] This application also provides a computer device that integrates any of the ocular ultrasound image anomaly determination devices provided in this application. For example... Figure 7 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0224] The computer device may include components such as a processor 701 with one or more processing cores, a storage unit 702 with one or more computer-readable storage media, a power supply 703, and an input unit 704. Those skilled in the art will understand that... Figure 7 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0225] The processor 701 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the storage unit 702, and by calling data stored in the storage unit 702, thereby providing overall monitoring of the computer device. Optionally, the processor 701 may include one or more processing cores; preferably, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 701.

[0226] Storage unit 702 can be used to store software programs and modules. Processor 701 executes various functional applications and data processing by running the software programs and modules stored in storage unit 702. Storage unit 702 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, storage unit 702 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, storage unit 702 may also include a memory controller to provide processor 701 with access to storage unit 702.

[0227] The computer device also includes a power supply 703 that supplies power to the various components. Preferably, the power supply 703 can be logically connected to the processor 701 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 703 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0228] The computer device may also include an input unit 704, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0229] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in the embodiments of this application, the processor 701 in the computer device loads the executable files corresponding to the processes of one or more application programs into the storage unit 702 according to the following instructions, and the processor 701 runs the application programs stored in the storage unit 702 to realize various functions, as follows:

[0230] The system identifies artifact features in pre-acquired ultrasound images and, based on these features, determines whether the ultrasound images meet preset requirements for non-artifact images. The ultrasound images are taken from ultrasound biomicroscopy examinations of the target area of ​​the patient, specifically the eye. If the ultrasound images meet the preset requirements for non-artifact images, the corneal, iris, lens, and ciliary body regions in the ultrasound images are identified. The system also acquires the boundary clarity features of these regions and the positional features of the iris and lens boundaries. Based on the boundary clarity features and the positional features of the iris and lens boundaries, the system determines whether the ultrasound images are abnormal.

[0231] This application provides a method for determining abnormalities in ocular ultrasound images. Compared to traditional methods, where existing ocular ultrasound images are prone to abnormalities and ophthalmologists cannot accurately diagnose them, leading to misdiagnosis, this application creatively performs artifact detection on the ultrasound images first, thus conducting preliminary screening to ensure the accuracy of subsequent images. Furthermore, by comprehensively analyzing the boundary clarity characteristics of the corneal region, iris region, lens region, and ciliary body region, as well as the positional characteristics of the boundary between the iris region and the lens region, it is possible to more accurately determine whether the ultrasound image is abnormal, thereby improving the accuracy of determining abnormalities in ocular ultrasound images.

[0232] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. The computer-readable storage medium stores multiple instructions, which can be loaded by a processor to execute steps in any of the methods for determining abnormalities in ocular ultrasound images provided in embodiments of this application. For example, the instructions can execute the following steps:

[0233] The system identifies artifact features in pre-acquired ultrasound images and, based on these features, determines whether the ultrasound images meet preset requirements for non-artifact images. The ultrasound images are taken from ultrasound biomicroscopy examinations of the target area of ​​the patient, specifically the eye. If the ultrasound images meet the preset requirements for non-artifact images, the corneal, iris, lens, and ciliary body regions in the ultrasound images are identified. The system also acquires the boundary clarity features of these regions and the positional features of the iris and lens boundaries. Based on the boundary clarity features and the positional features of the iris and lens boundaries, the system determines whether the ultrasound images are abnormal.

[0234] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0235] The above provides a detailed description of the method, apparatus, and related equipment for determining anomalies in ocular ultrasound images provided by the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for determining abnormalities in ocular ultrasound images, characterized in that, The method includes: The artifact features of a pre-acquired ultrasound image are identified, and based on the artifact features, it is determined whether the ultrasound image meets the preset requirements for a non-artifact image. The ultrasound image is an ultrasound image of a target area of ​​a patient examined by ultrasound biological microscopy, and the target area is the eye. If the ultrasound image meets the preset requirements for a non-artifact image, then the corneal region, iris region, lens region, and ciliary body region in the ultrasound image are identified respectively. The boundary clarity features of the corneal region, iris region, lens region, and ciliary body region are obtained respectively. Obtain the positional features of the boundary between the iris region and the boundary between the lens region; Based on the boundary clarity characteristics of the corneal region, iris region, lens region, and ciliary body region, and the positional characteristics of the boundary of the iris region and the boundary of the lens, it is determined whether the ultrasound image is abnormal. The step of determining whether the ultrasound image is abnormal based on the boundary clarity characteristics of the corneal region, iris region, lens region, and ciliary body region, and the positional characteristics of the boundary of the iris region and the boundary of the lens, includes: The abnormality parameters of the ultrasound image are obtained by weighted fitting of the boundary clarity features of the corneal region, iris region, lens region and ciliary body region, and the positional features of the boundary of the iris region and the boundary of the lens. Based on the abnormality level parameter and the preset abnormality level threshold, it is determined whether the ultrasound image is abnormal.

2. The method for determining abnormalities in ocular ultrasound images according to claim 1, characterized in that, Obtaining the clear boundary features of the corneal region includes: The corneal region is cropped using a first rectangular frame of a preset size as the boundary to obtain a first corneal image; The first corneal image is binarized to obtain the processed second corneal image; Based on the connected components, the area of ​​each connected component in the second corneal image is calculated respectively; Based on the area and a preset area threshold, each of the connected regions is filtered to obtain a target connected region, which includes the front elastic layer connected region and the rear elastic layer connected region. The first center line of the connected domain of the front elastic layer and the second center line of the connected domain of the rear elastic layer are obtained respectively, and multiple target distances between the first center line and the second center line are obtained; Calculate the variance of the multiple target distances, and determine the clarity features of the corneal region based on the variance and a preset variance threshold.

3. The method for determining abnormalities in ocular ultrasound images according to claim 1, characterized in that, The iris region includes two sub-iris regions. Obtaining clear boundary features of the iris region includes: Obtain the boundary perimeter of each sub-iris region in the two sub-iris regions respectively; Binarize all pixels on the boundary of each sub-iris region and obtain the set of pixel values ​​of all pixels after processing. Based on the preset pixel value threshold and the set of pixel values, all processed pixels are filtered to obtain the target pixel set on the boundary of the sub-iris region. The number of pixels in the target pixel set on the boundary of each sub-iris region is compared with the perimeter of the boundary of each sub-iris region to obtain the target boundary ratio of each sub-iris region. Based on the target boundary ratio of each sub-iris region and a preset boundary ratio threshold, the clear boundary features of the iris region are determined.

4. The method for determining abnormalities in ocular ultrasound images according to claim 1, characterized in that, Obtaining the clear boundary features of the lens region includes: Obtain the perimeter of the boundary of the lens region; Binarize all pixels on the boundary of the lens region and obtain the set of pixel values ​​of all pixels after processing. Based on the preset pixel value threshold and the set of pixel values, all processed pixels are filtered to obtain the target pixel set on the boundary of the lens region. The target pixel set on the boundary of the lens region is compared with the perimeter of the lens region to obtain the target boundary ratio of the lens region. Based on the target boundary ratio of the lens region and a preset boundary ratio threshold, the clear boundary characteristics of the lens region are determined.

5. The method for determining abnormalities in ocular ultrasound images according to claim 1, characterized in that, Obtaining the well-defined boundary features of the ciliary body region includes: The ciliary body region is cropped using a second rectangular frame of a preset size as the boundary to obtain a first ciliary body image; Obtain the first boundary line of the ciliary body region in the first ciliary body image, and the first centroid of the first boundary line; The first ciliary body image is binarized to obtain the processed second ciliary body image; Obtain the second boundary line of the ciliary body region in the second ciliary body image, and the second centroid of the second boundary line; Calculate the Euclidean distance between the first centroid and the second centroid, and determine the clear boundary features of the ciliary body region based on the Euclidean distance.

6. The method for determining abnormalities in ocular ultrasound images according to claim 1, characterized in that, The iris region includes two sub-iris regions, and the acquisition of the positional features of the boundary between the iris region and the boundary between the lens region includes: The first and second overlap degrees between the boundaries of the two sub-iris regions and the boundary of the lens region are obtained respectively; Based on the first overlap, the second overlap, and a preset overlap threshold, the positional characteristics of the boundary between the iris region and the lens region are determined.

7. A device for determining abnormalities in ocular ultrasound images, characterized in that, The device includes: The first identification unit is used to identify the artifact features of the pre-acquired ultrasound image and, based on the artifact features, determine whether the ultrasound image meets the preset non-artifact image requirements. The ultrasound image is an ultrasound image of a patient's target area examined by ultrasound biological microscopy, and the target area is the eye. The second identification unit is used to identify the corneal region, iris region, lens region and ciliary body region in the ultrasound image if the ultrasound image meets the preset non-artifact image requirements. The first acquisition unit is used to acquire the boundary clarity features of the corneal region, iris region, lens region and ciliary body region respectively. The second acquisition unit is used to acquire the positional features of the boundary between the iris region and the boundary between the lens region; The first determining unit is used to determine whether the ultrasound image is abnormal based on the boundary clarity characteristics of the corneal region, iris region, lens region and ciliary body region, and the positional characteristics of the boundary of the iris region and the boundary of the lens. The first determining unit is further configured to perform weighted fitting of the boundary clarity features of the corneal region, iris region, lens region and ciliary body region, and the positional features of the boundary of the iris region and the boundary of the lens region to obtain the abnormality parameter of the ultrasound image; and determine whether the ultrasound image is abnormal based on the abnormality parameter and a preset abnormality threshold.

8. A computer device, characterized in that, The computer device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method for determining anomalies in ocular ultrasound images according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It contains a computer program that is loaded by a processor to perform the steps of the method for determining anomalies in ocular ultrasound images according to any one of claims 1 to 6.

Images