An image processing method, system, device, and medium for ocular B-mode ultrasound examination

Abstract

This invention belongs to the field of medical information technology, and its purpose is to provide an image processing method, system, device, and medium for ocular B-mode ultrasound examination. This invention eliminates the need to manually input L or R to label the eye type on each acquired B-mode ultrasound image. Instead, it obtains a set of eye key points using facial landmark detection technology. Then, it detects the probe position in the eye image acquired during B-mode ultrasound image acquisition and determines the distance between the probe and each set of eye key points. This allows for the determination of the eye key point index with the smallest distance from the probe. The left and right eye positions corresponding to this indexed set of eye key points are the eye type in the current B-mode ultrasound image, thus reducing the workload of the doctor's left hand.

Description

Technical Field

[0001] This invention belongs to the field of medical information technology, specifically relating to an image processing method, system, device, and medium for ocular B-mode ultrasound examination. Background Technology

[0002] Many eye diseases, especially those occurring inside the eyeball, are difficult to observe clearly with the naked eye. In such cases, ocular ultrasound (B-scan) examination can be used for diagnosis. Specifically, ocular ultrasound provides valuable diagnostic clues and is a non-invasive auxiliary examination that does not harm the eye. Ocular ultrasound can confirm whether there is swelling of the eye muscles, lens dislocation, vitreous opacities, retinal detachment, etc. It can also check for foreign bodies in the eyeball wall and determine their specific location. During an ocular ultrasound examination, an ultrasound probe is used to observe the internal structures of the eyeball through the eyelids. The probe transmits ultrasound waves to the eyeball, converting the reflected echoes from the internal interfaces of the eyeball into echo spots of varying brightness. This two-dimensional acoustic slice image, composed of numerous echo spots, is the ultrasound image.

[0003] Currently, when performing an ocular ultrasound examination, the doctor usually needs to hold the ultrasound probe in their right hand and move it back and forth around the patient's eyes to acquire ultrasound images. They then use their left hand to input a "L" (left) mark for the left eye or an "R" (right) mark for the right eye on the keyboard to identify the eye. In addition, the doctor usually needs to use their left hand to adjust parameters such as the ultrasound image gain to make the acquired ultrasound images clearer.

[0004] However, in using the prior art, the inventors discovered at least the following problems:

[0005] During an ocular ultrasound examination, doctors typically need to acquire a large number of ultrasound images. Their left hand frequently needs to input the "L" and "R" keys on the keyboard to label the eyes in the ultrasound images, resulting in a heavy workload for doctors. Furthermore, after acquiring the ultrasound images, current technology usually cannot further label which part of the eye the ultrasound image corresponds to. Therefore, when doctors review the patient's ultrasound images later, they cannot quickly and accurately determine the location of any eye lesions. Summary of the Invention

[0006] The present invention aims to at least partially solve the above-mentioned technical problems, and provides an image processing method, system, device and medium for ocular B-mode ultrasound examination.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides an image processing method for ocular B-mode ultrasound examination, comprising:

[0009] Obtain the user's facial region image, and obtain the set of key points around the eyes based on the facial region image;

[0010] The system acquires ultrasound images captured during an eye ultrasound examination, and simultaneously acquires an image of the user's eye region corresponding to the ultrasound image; wherein the acquisition time of the eye region image is the same as the acquisition time of the ultrasound image.

[0011] The key points of the ultrasound probe are obtained by performing ultrasound probe detection on the image of the eye region.

[0012] Based on the key points of the ultrasound probe and the set of key points of the eye, the eye key point that is closest to the key point of the ultrasound probe in the set of key points of the eye is obtained, and this closest eye key point is used as the eye key point index corresponding to the ultrasound image.

[0013] The eye type of the ultrasound image is obtained based on the eye key point index corresponding to the ultrasound image.

[0014] In one possible design, a set of key eye points is obtained from a facial region image, including:

[0015] Facial key points are obtained from the facial region image and then marked to obtain multiple marker symbols corresponding to the facial key points.

[0016] Obtain the marker symbols corresponding to the set of eye key points in the facial key points;

[0017] The set of eye key points is extracted from the facial key points based on the marker symbols corresponding to the set of eye key points in the facial key points.

[0018] In one possible design, the distance between any eye key point A in the set of eye key points and the B-mode ultrasound probe key point B is . Where (x1, y1) are the coordinates of the current key point A of the eye, and (x2, y2) are the coordinates of the key point B of the B-mode ultrasound probe.

[0019] In one possible design, after acquiring the ultrasound images taken during a user's eye ultrasound examination, the method further includes:

[0020] Gain adjustment is applied to the ultrasound image to improve its clarity.

[0021] In one possible design, after acquiring the ultrasound images taken during a user's eye ultrasound examination, the method further includes:

[0022] Obtain a specified region image from the ultrasound image, and calculate its area based on the specified region image.

[0023] In one possible design, after acquiring the ultrasound images taken during a user's eye ultrasound examination, the method further includes:

[0024] The axial length of the eye is calculated based on the ultrasound image.

[0025] In one possible design, after obtaining the eye classification of the ultrasound image, the method further includes:

[0026] The ultrasound image and the corresponding image of the user's eye area are paired and stored.

[0027] In a second aspect, the present invention provides an image processing system for ocular B-mode ultrasound examination, used to implement the image processing method for ocular B-mode ultrasound examination as described in any of the preceding claims; the image processing system for ocular B-mode ultrasound examination includes:

[0028] The eye key point detection module is used to acquire the user's facial region image and obtain the eye key point set based on the facial region image;

[0029] An eye image acquisition module is used to acquire ultrasound images of a user during an eye ultrasound examination, and simultaneously acquire an image of the user's eye region corresponding to the ultrasound image; wherein the acquisition time of the eye region image is the same as the acquisition time of the ultrasound image.

[0030] The probe key point detection module is communicatively connected to the eye image acquisition module and is used to perform B-ultrasound probe detection from the eye region image to obtain the key points of the B-ultrasound probe;

[0031] The key point index module is communicatively connected to the eye key point detection module and the probe key point detection module, respectively. It is used to obtain the eye key point in the eye key point set that is closest to the B-ultrasound probe key point based on the B-ultrasound probe key point and the eye key point set, and use the closest eye key point as the eye key point index corresponding to the B-ultrasound image.

[0032] The eye identification module is communicatively connected to the key point index module and is used to obtain the eye identification of the B-ultrasound image based on the eye key point index corresponding to the B-ultrasound image.

[0033] Thirdly, the present invention provides an electronic device, comprising:

[0034] Memory, used to store computer program instructions; and,

[0035] A processor for executing the computer program instructions to perform the operation of the image processing method for ocular B-mode ultrasound examination as described in any of the preceding claims.

[0036] Fourthly, the present invention provides a computer-readable storage medium for storing computer-readable computer program instructions configured to perform, at runtime, operations of the image processing method for ocular B-mode ultrasound examination as described in any of the preceding claims.

[0037] During the implementation of this embodiment, the following beneficial effects are observed:

[0038] 1) This allows doctors to identify the eye in a captured ultrasound image without needing to input "L" and "R" keys, reducing the workload on the doctor's left hand. Specifically, when performing an eye ultrasound, doctors no longer need to manually input "L" or "R" to label the eye on each captured ultrasound image. Instead, they use facial landmark detection technology to obtain a set of eye landmarks. Then, they detect the probe position in the eye image acquired during ultrasound image acquisition and determine the distance between the probe and each set of eye landmarks. This allows them to obtain the index of the eye landmark with the smallest distance from the probe. The left and right eye positions (L or R) corresponding to the set of eye landmarks with this index are the eye classification in the current ultrasound image.

[0039] 2) Since most of the acquired ultrasound images are of the internal area of ​​the eye, and the location of the lesion in the ultrasound images is not indicated, the ultrasound images of the eye are paired with the corresponding eye locations for storage when the images are acquired. This allows the ultrasound images and the corresponding eye locations to be displayed in pairs, enabling doctors to understand the specific location of the lesion in the ultrasound images of the eye, and thus facilitate doctors to quickly and accurately formulate treatment plans for patients. Attached Figure Description

[0040] Figure 1 This is a flowchart of an image processing method for ocular B-mode ultrasound examination in one embodiment;

[0041] Figure 2 This is a schematic diagram showing the key points of the eye and the key points of the ultrasound probe marked on the image of the eye region in the embodiment.

[0042] Figure 3 This is a block diagram of an image processing system for ocular B-mode ultrasound examination according to an embodiment;

[0043] Figure 4 This is a block diagram of an electronic device in one embodiment. Detailed Implementation

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0045] Example 1:

[0046] This embodiment discloses an image processing method for ocular B-mode ultrasound examination, which can be executed, but is not limited to, by a computer device or virtual machine with certain computing resources, such as by an electronic device like a personal computer, smartphone, personal digital assistant, or wearable device, or by a virtual machine.

[0047] like Figure 1 As shown, an image processing method for ocular B-mode ultrasound examination may include, but is not limited to, the following steps:

[0048] S1. Acquire the user's facial region image and obtain the eye key point set based on the facial region image; Specifically, in this embodiment, the user usually refers to a patient who is about to undergo an eye ultrasound examination. During this process, the patient needs to be instructed to lie flat on the examination bed, and medical staff will assist the patient in positioning their head so that their face is facing the doctor, and the patient will be told to gently close their eyes and not open them; Once the patient is ready to lie supine, the facial region image of the patient can be acquired in real time through the camera facing the patient, and facial key point detection can be performed on the acquired facial region image to obtain the eye key point set.

[0049] Specifically, in this embodiment, the set of key eye points is obtained based on the facial region image, including:

[0050] S101. Obtain facial key points from the facial region image and mark the facial key points to obtain multiple marker symbols corresponding to the facial key points; it should be noted that in this embodiment, the obtained facial key points include key points of eyebrows, eyes, nose, mouth, facial contours and other parts. In this process, each key point is numbered, so it is convenient to extract the left and right eye key points according to the number of the eye key point set.

[0051] In this embodiment, the Face Mesh algorithm is used to obtain facial key points from the facial region image. This algorithm can estimate 468 facial key points in the facial region image in real time. Specifically, obtaining facial key points from the facial region image includes: inputting the facial region image into the Face Mesh algorithm model to obtain 468 facial key points.

[0052] S102. Obtain the marker symbols corresponding to the set of eye key points in the facial key points.

[0053] S103. Extract the set of eye key points from the facial key points according to the marker symbols corresponding to the set of eye key points in the facial key points.

[0054] As an example, in this embodiment, Figure 2 The set of key points for the eyes shows 12 key points P1 to P12 corresponding to the left and right eyes respectively.

[0055] S2. Acquire ultrasound images captured during an ocular ultrasound examination, and simultaneously acquire an image of the user's eye region corresponding to the ultrasound image; wherein, the acquisition time of the eye region image is the same as the acquisition time of the ultrasound image; it should be noted that, in this embodiment, during the ocular ultrasound examination, an appropriate amount of coupling agent needs to be applied to the ultrasound probe, the ultrasound probe is first placed in the center of the eyelid, and vertical and horizontal axial scanning is performed to examine the lesion from multiple sections and angles. Then, the ultrasound detection image corresponding to the area with obvious lesion characteristics can be frozen by foot operation, but is not limited to the existing ultrasound examination techniques, thereby acquiring the ultrasound image; this will not be elaborated here. It should be noted that, in this embodiment, during the acquisition of ultrasound images, the camera facing the patient automatically takes a picture, thereby obtaining an image of the user's eye region corresponding to the ultrasound image.

[0056] S3. Perform ultrasound probe detection from the eye region image to obtain the key points of the ultrasound probe; it should be noted that in this embodiment, the position of the key points of the ultrasound probe is variable, and its position depends on the detection position of the ultrasound probe in different eye region images.

[0057] In this embodiment, ultrasound probe detection is performed from the image of the eye region to obtain key points of the ultrasound probe, including:

[0058] S301. Collect images of the eye region under different scenes and angles, and annotate the key points of the probe in the collected eye region images to obtain an annotated image; in this embodiment, all eye region images include B-ultrasound probe images;

[0059] S302. Build an initial probe detection model and enhance the labeled image to obtain a pre-processed image, so as to train the initial probe detection model with the pre-processed image and obtain a trained probe detection model with high accuracy; In this embodiment, the initial probe detection model is implemented using a YOLO V5 network model;

[0060] S303. Input the image of the eye region to be detected into the trained probe detection model to obtain the key points of the ultrasound probe.

[0061] S4. Based on the key points of the ultrasound probe and the set of key points of the eye, obtain the eye key point in the set of key points that is closest to the key point of the ultrasound probe, and use this closest eye key point as the index of the eye key point corresponding to the ultrasound image; in this embodiment, both the key points of the ultrasound probe and the eye key points in the set of key points of the eye are stored in the form of coordinates. When the coordinates of any eye key point A in the set of key points of the eye are (x1, y1) and the coordinates of the ultrasound probe key point B are (x2, y2), the distance between eye key point A and ultrasound probe key point B is... It should be noted that, in this embodiment, since the facial region image and the eye region image are both acquired by the same fixed camera (i.e., the camera facing the patient), the corresponding key points of the ultrasound probe and the key points of the eye are set in the same coordinate system.

[0062] S5. Obtain the eye classification of the ultrasound image based on the eye key point index corresponding to the ultrasound image. Specifically, in this embodiment, the eye classification of the ultrasound image is the eye position corresponding to the eye key point index of the ultrasound image, such as the L mark indicating the left eye or the R mark indicating the right eye.

[0063] S6. The ultrasound image and the corresponding eye region image of the user are paired and stored.

[0064] It should be noted that since most of the acquired ultrasound images are of the internal area of ​​the eye, and the location of the lesion is not indicated in the ultrasound images, the ocular ultrasound images are paired with the corresponding eye locations for storage. This allows the ultrasound images and corresponding eye locations to be displayed in pairs, enabling doctors to understand the specific location of the lesion in the ocular ultrasound images when reviewing them. This, in turn, allows doctors to quickly and accurately formulate treatment plans for patients.

[0065] Furthermore, in this embodiment, after acquiring the ultrasound images collected during the user's eye ultrasound examination, the method further includes:

[0066] Gain adjustment is applied to the ultrasound image to improve its clarity. It should be noted that the gain can be adjusted either during the ultrasound scan or after the image is captured (i.e., after the ultrasound image has been acquired); this is not limited to this method. In this embodiment, the gain can be adjusted, but is not limited to, by vertically moving the mouse cursor. This is also not a limitation.

[0067] A designated region of the ultrasound image is acquired, and its area is calculated based on the designated region image. Specifically, the area is the number of pixels within the corresponding contour of the designated region image. It should be noted that in this embodiment, after calculating the area of ​​the designated region image, the area can be labeled to allow doctors to quickly confirm the area of ​​the lesion.

[0068] And / or, the axial length is calculated based on the ultrasound image. Specifically, in this embodiment, when the ultrasound probe is perpendicular to the eyelid of the eye being measured and a horizontal axial scan is performed, the image is frozen when the lens and optic nerve are simultaneously displayed in the center of the sonogram to obtain the corresponding ultrasound image. Subsequently, a position 3 mm below the optic disc can be defined as the location of the macula. The distance from the anterior end to the macula is measured, and the eyelid thickness of 15-20 mm is subtracted. This measurement is repeated 3 times, and the average value is taken to obtain the axial length.

[0069] In this embodiment, doctors can identify the eye in a captured ultrasound image without needing to input "L" and "R" keys, thus reducing the workload of their left hand. Specifically, when performing an ocular ultrasound examination, doctors do not need to manually input "L" or "R" to label the eye on each captured ultrasound image. Instead, they use facial landmark detection technology to obtain a set of eye landmarks. Then, they detect the probe position in the eye images acquired during ultrasound image acquisition and determine the distance between the probe and each set of eye landmarks to obtain the index of the eye landmark with the smallest distance from the probe. The left and right eye positions (L or R) corresponding to the set of eye landmarks with this index are the eye classification of the current ultrasound image.

[0070] Example 2:

[0071] This embodiment discloses an image processing system for ocular B-mode ultrasound examination, used to implement the image processing method for ocular B-mode ultrasound examination in Embodiment 1; such as Figure 3 As shown, the image processing system for ocular B-mode ultrasound examination includes:

[0072] The eye key point detection module is used to acquire the user's facial region image and obtain the eye key point set based on the facial region image;

[0073] An eye image acquisition module is used to acquire ultrasound images of a user undergoing an eye ultrasound examination, and simultaneously acquire an image of the user's eye region corresponding to the ultrasound image; wherein, the acquisition time of the eye region image is the same as the acquisition time of the ultrasound image; it should be noted that, in this embodiment, the eye image acquisition module includes an eye ultrasound image acquisition module for acquiring ultrasound images of a user undergoing an eye ultrasound examination and an eye region image acquisition module for acquiring an image of the user's eye region corresponding to the ultrasound image;

[0074] The probe key point detection module is communicatively connected to the eye image acquisition module and is used to perform B-ultrasound probe detection from the eye region image to obtain the key points of the B-ultrasound probe;

[0075] The key point index module is communicatively connected to the eye key point detection module and the probe key point detection module, respectively. It is used to obtain the eye key point in the eye key point set that is closest to the B-ultrasound probe key point based on the B-ultrasound probe key point and the eye key point set, and use the closest eye key point as the eye key point index corresponding to the B-ultrasound image.

[0076] The eye identification module is communicatively connected to the key point index module and is used to obtain the eye identification of the B-ultrasound image based on the eye key point index corresponding to the B-ultrasound image.

[0077] Example 3:

[0078] Based on Embodiment 1 or 2, this embodiment discloses an electronic device, which may be a smartphone, tablet computer, laptop computer, or desktop computer, etc. The electronic device may be referred to as a terminal, portable terminal, desktop terminal, etc. Figure 4 As shown, the electronic device includes:

[0079] Memory, used to store computer program instructions; and,

[0080] A processor is configured to execute the computer program instructions to perform the operation of the image processing method for ocular B-mode ultrasound examination as described in any of Embodiment 1.

[0081] Specifically, processor 301 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 301 may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). Processor 301 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 301 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen.

[0082] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 302 are used to store at least one instruction, which is executed by the processor 301 to implement the image processing method for ocular B-mode ultrasound examination provided in Embodiment 1 of this application.

[0083] In some embodiments, the terminal may also optionally include a communication interface 303 and at least one peripheral device. The processor 301, memory 302, and communication interface 303 can be connected via a bus or signal line. Each peripheral device can be connected to the communication interface 303 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 304, a display screen 305, and a power supply 306.

[0084] The communication interface 303 can be used to connect at least one I / O (Input / Output) related peripheral device to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the communication interface 303 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0085] The radio frequency (RF) circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 304 communicates with communication networks and other communication devices via electromagnetic signals.

[0086] Display screen 305 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof.

[0087] Power supply 306 is used to supply power to various components in electronic devices.

[0088] Example 4:

[0089] Based on any one of the embodiments 1 to 3, this embodiment discloses a computer-readable storage medium for storing computer-readable computer program instructions, which are configured to perform the operation of the image processing method for ocular B-ultrasound examination as described in Embodiment 1 when executed.

[0090] Obviously, those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps as a single integrated circuit module. Thus, the present invention is not limited to any particular hardware and software combination.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An image processing method for ocular B-mode ultrasound examination, characterized in that: include: The process involves acquiring a user's facial region image and obtaining a set of key eye points based on the facial region image, including: obtaining facial key points based on the facial region image and marking the facial key points to obtain multiple marker symbols corresponding to the facial key points; obtaining the marker symbols corresponding to the set of key eye points among the facial key points; and extracting the set of key eye points from the facial key points based on the marker symbols corresponding to the set of key eye points among the facial key points. The system acquires ultrasound images captured during an eye ultrasound examination, and simultaneously acquires an image of the user's eye region corresponding to the ultrasound image; wherein the acquisition time of the eye region image is the same as the acquisition time of the ultrasound image. The key points of the ultrasound probe are obtained by performing ultrasound probe detection on the image of the eye region. Based on the key points of the ultrasound probe and the set of key points of the eye, the eye key point that is closest to the key point of the ultrasound probe in the set of key points of the eye is obtained, and this closest eye key point is used as the eye key point index corresponding to the ultrasound image. Based on the eye key point index corresponding to the simultaneously acquired B-ultrasound image, the eye classification of the B-ultrasound image is obtained. The eye classification of the B-ultrasound image is the marker symbol of the left or right eye corresponding to the eye key point index of the B-ultrasound image.

2. The image processing method for ocular B-mode ultrasound examination according to claim 1, characterized in that: The distance between any eye key point A in the set of key eye points and key point B of the B-mode ultrasound probe is: ; Where (x1, y1) are the coordinates of the current key point A of the eye, and (x2, y2) are the coordinates of the key point B of the B-mode ultrasound probe.

3. The image processing method for ocular B-mode ultrasound examination according to claim 1, characterized in that: After acquiring the ultrasound images taken during the user's eye ultrasound examination, the method further includes: Gain adjustment is applied to the ultrasound image to improve its clarity.

4. The image processing method for ocular B-mode ultrasound examination according to claim 1, characterized in that: After acquiring the ultrasound images taken during the user's eye ultrasound examination, the method further includes: Obtain a specified region image from the ultrasound image, and calculate its area based on the specified region image.

5. The image processing method for ocular B-mode ultrasound examination according to claim 1, characterized in that: After acquiring the ultrasound images taken during the user's eye ultrasound examination, the method further includes: The axial length of the eye is calculated based on the ultrasound image.

6. The image processing method for ocular B-mode ultrasound examination according to claim 1, characterized in that: After obtaining the eye classification of the ultrasound image, the method further includes: The ultrasound image and the corresponding image of the user's eye area are paired and stored.

7. An image processing system for ocular B-mode ultrasound examination, characterized in that: An image processing method for ocular B-mode ultrasound examination as described in any one of claims 1 to 6; The image processing system for ocular B-mode ultrasound examination includes: The eye key point detection module is used to acquire the user's facial region image and obtain the eye key point set based on the facial region image; An eye image acquisition module is used to acquire ultrasound images of a user during an eye ultrasound examination, and simultaneously acquire an image of the user's eye region corresponding to the ultrasound image; wherein the acquisition time of the eye region image is the same as the acquisition time of the ultrasound image. The probe key point detection module is communicatively connected to the eye image acquisition module and is used to perform B-ultrasound probe detection from the eye region image to obtain the key points of the B-ultrasound probe; The key point index module is communicatively connected to the eye key point detection module and the probe key point detection module, respectively. It is used to obtain the eye key point in the eye key point set that is closest to the B-ultrasound probe key point based on the B-ultrasound probe key point and the eye key point set, and use the closest eye key point as the eye key point index corresponding to the B-ultrasound image. The eye identification module is communicatively connected to the key point index module and is used to obtain the eye identification of the B-ultrasound image based on the eye key point index corresponding to the B-ultrasound image.

8. An electronic device, characterized in that: include: Memory is used to store computer program instructions; as well as, A processor for executing the computer program instructions to perform the operation of the image processing method for ocular B-mode ultrasound examination as described in any one of claims 1 to 6.

9. A computer-readable storage medium for storing computer-readable computer program instructions, characterized in that: The computer program instructions are configured to perform the operation of the image processing method for ocular B-mode ultrasound examination as described in any one of claims 1 to 6 when executed.

Images