ICL implantation surgery monitoring method and surgical microscope system
By acquiring and analyzing eye images during ICL implantation surgery in real time, automatically identifying the incision location and performing OCT scans, the surgical burden and safety issues of existing technologies are resolved, achieving a more efficient and safer ICL implantation surgery.
Patent Information
- Application Number
- PCT/CN2026/096746
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-13
- Filing Date
- 2026-05-13
- Publication Date
- 2026-11-19
AI Technical Summary
In ICL implantation surgery, current technology relies on the doctor's experience and manual adjustments based on OCT scans, which increases the workload, reduces surgical efficiency, and lowers safety.
By acquiring real-time images of the eye, identifying the information and location of the incision blade, automatically performing OCT scanning, determining the relative positional relationship between the incision blade and the eye tissue based on OCT image segmentation, and sending adjustment prompts when the parameters exceed the preset range.
It reduces unnecessary procedures during surgery, lowers surgical risks, and improves surgical safety and efficiency.
Smart Images

Figure CN2026096746_19112026_PF_FP_ABST
Abstract
Description
ICL Implantation Surgical Monitoring Methods and Surgical Microscope Systems
[0001] Cross-reference to related applications
[0002] This application claims priority to Chinese Patent Application No. 202510614719.2, filed on May 13, 2025, the entire contents of which are incorporated herein by reference. Technical Field
[0003] This application relates to the field of data processing technology, such as methods for monitoring ICL implantation surgery and surgical microscope systems. Background Technology
[0004] Currently, implantable collamer lens (ICL) surgery is considered the mainstream refractive and myopia correction surgery due to its high effectiveness, rapid procedure, and lack of side effects. The ICL implantation process involves creating a channel in the cornea for ICL insertion. During this process, the anterior segment of the eye needs to be observed, and the corneal condition assessed.
[0005] In related technologies, during ICL implantation surgery, doctors usually rely on experience and optical coherence tomography (OCT) to determine the corneal incision status. However, OCT scanning relies on manual adjustments, which increases the doctor's operational and cognitive burden, reduces surgical efficiency, and increases intraoperative risks and reduces surgical safety. Summary of the Invention
[0006] The first aspect of this application proposes a method for monitoring ICL implantation surgery, including:
[0007] Real-time acquisition of eye images of the operated eye;
[0008] Based on the acquired eye images, the cutting information and position information of the cutting knife are identified;
[0009] Perform an OCT scan at a specific location and acquire an OCT image based on at least one of the incision information and the incision blade position information;
[0010] The ocular tissue and the incision blade are segmented based on the OCT image, and the relative positional relationship information between the incision blade and the ocular tissue is determined based on the obtained segmentation results. The relative positional relationship information includes at least one of the following: a first relative distance between the incision blade and the lower boundary of the cornea, a second relative distance between the incision blade and the lens, and an angle between the incision blade and the horizontal line.
[0011] In response to the relative positional relationship information exceeding the corresponding preset parameter range, an adjustment prompt message is sent.
[0012] The second aspect of this application discloses a surgical microscope system for use in ICL implantation surgery, comprising:
[0013] The OCT scanning unit is configured to acquire OCT images;
[0014] The eye image acquisition unit is configured to acquire images of the surgical field of view from the surgical microscope;
[0015] At least one control computing unit is configured to perform any of the ICL implantation surgery monitoring methods described above.
[0016] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when executed, implements any of the ICL implantation surgery monitoring methods described above. Attached Figure Description
[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:
[0018] Figure 1 is a flowchart of an ICL implantation surgery monitoring method according to an embodiment of this application;
[0019] Figure 2 is a schematic diagram of a cut information provided according to an embodiment of this application;
[0020] Figure 3 is a schematic diagram of a segmentation result provided according to an embodiment of this application;
[0021] Figure 4 is a flowchart of an ICL implantation surgery monitoring method according to an embodiment of this application;
[0022] Figure 5 is a flowchart of an ICL implantation surgery monitoring method according to an embodiment of this application;
[0023] Figure 6 is a flowchart of an ICL implantation surgery monitoring method provided according to an embodiment of this application;
[0024] Figure 7 is a flowchart of an ICL implantation surgery monitoring method according to an embodiment of this application;
[0025] Figure 8 is a flowchart of an ICL implantation surgery monitoring method provided according to an embodiment of this application;
[0026] Figure 9 is a structural block diagram of an ICL implantation surgery monitoring system provided according to an embodiment of this application. Detailed Implementation
[0027] Where there is no conflict, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0029] The following description, with reference to the accompanying drawings, describes the ICL implantation surgical monitoring method and surgical microscope system proposed according to embodiments of this application.
[0030] Figure 1 is a flowchart of an ICL implantation surgery monitoring method provided according to an embodiment of this application. As shown in Figure 1, the method may include the following steps: S101-S105.
[0031] Step S101: Acquire real-time images of the operated eye.
[0032] In one embodiment of this application, the aforementioned eye image may be a frontal view of the eye obtained by electronic imaging of the surgical field of view of a surgical microscope.
[0033] Step S102: Based on the acquired eye image, identify the incision information and position information of the surgical incision knife (hereinafter referred to as the incision knife or scalpel).
[0034] In one embodiment of this application, identifying the cutting information and position information of a cutting knife based on an acquired eye image may include: identifying the cutting information and position information of the cutting knife using a target convolutional neural network based on the eye image. In one embodiment of this application, the aforementioned target convolutional neural network is obtained through training.
[0035] Furthermore, in one embodiment of this application, the cutting blade position information can describe the relative pose of the cutting blade in the field of view. Referring to Figure 2, the cutting blade position information (the pose of the cutting blade) can be represented as a rectangular frame RB1(θ, x1, y1, w1, h1) with an angle, where θ is the rotation angle of the cutting blade in the Cartesian coordinate system, (x1, y1) are the center coordinates of the rectangular frame where the cutting blade is located, and (w1, h1) are the width and height of the rectangular frame where the cutting blade is located. The cutting information can describe the relative position of the cutting blade edge in the field of view. Referring to Figure 2, the cutting information (the position of the cutting blade edge) can be represented as a rectangular frame RB2(x2, y2, w2, h2), where (x2, y2) are the center coordinates of the rectangular frame where the cutting blade edge is located, and (w2, h2) are the width and height of the rectangular frame where the cutting blade edge is located.
[0036] Step S103: Perform an OCT scan at a specific location and acquire an OCT image based on at least one of the incision information and the incision knife position information.
[0037] In one embodiment of this application, after obtaining the incision information and the incision knife position information through the above steps, an OCT scan can be automatically performed on a specific location based on at least one of the incision information and the incision knife position information to obtain an OCT image. As a result, the surgeon does not need to manually adjust the OCT scan during the operation, thus achieving higher accuracy and real-time performance.
[0038] In one embodiment of this application, OCT scanning uses a light source to emit low-coherence infrared light (invisible light) with a wavelength of 800-1300nm, which is split into two beams by a beam splitter. One beam is reflected back as a reference light, and the other beam is projected onto the object being measured (eye tissue) as a measurement light. The light is reflected by tissues at different depth levels. The reflected measurement light and the reflected reference light combine to form an interference signal. The interference signal is converted into depth information through Fourier transform. A one-dimensional depth scan (A scan) is obtained by measuring optical echoes at different depths (axial z-direction). A two-dimensional cross-section (B scan) is obtained by moving the scanning beam (lateral xy-direction) on the surface of the measured sample.
[0039] In one embodiment of this application, performing an OCT scan at a specific location and acquiring an OCT image based on at least one of the incision information and the incision blade position information may include: performing an OCT scan with the incision information as the center (with the blade position of the incision blade described by the incision information as the center) within a first preset imaging depth range and a preset scanning width range to obtain an OCT image corresponding to the cross-sectional B-scan data; or, performing an OCT scan with the first preset imaging depth range and a preset scanning width range along the direction corresponding to the rotation angle of the incision blade to obtain an OCT image corresponding to the cross-sectional B-scan data.
[0040] In one embodiment of this application, the first preset imaging depth range can be (2mm, 6mm), thereby enabling scanning imaging of the cornea, anterior chamber, and lens; the preset scanning width range can be (6mm, 18mm), thereby enabling scanning imaging of the cornea, anterior chamber angle, and the entire anterior segment.
[0041] In one embodiment of this application, when performing OCT scanning based on at least one of the incision information and the incision knife position information, the axial resolution (depth z direction) of the OCT imaging can be 5-10 μm, and the lateral resolution (xy direction) can be 10-30 μm.
[0042] Step S104: Segment the eye tissue and the incision knife based on the OCT image, and determine the relative positional relationship between the incision knife and the eye tissue based on the obtained segmentation results.
[0043] In one embodiment of this application, after obtaining the OCT image through the above steps, the eye tissue and the incision knife can be segmented based on the OCT image, and at least one relative positional relationship information between the incision knife and the eye tissue can be determined based on the obtained segmentation result. Thus, it can be determined whether to send adjustment prompt information based on at least one relative positional relationship information, so as to provide timely alarm prompts during the surgical operation.
[0044] In one embodiment of this application, segmenting eye tissue and an incision blade based on an OCT image may include: segmenting the eye tissue and incision blade in the OCT image using a first convolutional neural network to obtain a segmentation result including the tissue boundaries of the cornea and lens, as well as the incision blade. In one embodiment of this application, the aforementioned first convolutional neural network is obtained through training.
[0045] In one embodiment of this application, Figure 3 is a schematic diagram of a segmentation result proposed in this embodiment. As shown in Figure 3, the segmentation result includes the boundaries of the cornea, iris, incision blade, and lens, etc. The horizontal dashed line L1 under the tip of the incision blade is the horizontal line where the incision blade is located. Referring to Figures 2 and 3, the shape of the eye is described as an ellipse, and the horizontal line or horizontal direction is perpendicular to the direction of the eye axis or visual axis, while the vertical direction is parallel to the direction of the eye axis or visual axis.
[0046] Furthermore, in one embodiment of this application, the aforementioned relative positional relationship information may include at least one of the following: a first relative distance between the incision blade and the lower boundary of the cornea, a second relative distance between the incision blade and the lens, and the angle between the incision blade and the horizontal line.
[0047] Step S105: In response to the relative position relationship information exceeding the corresponding preset parameter range, an adjustment prompt message is sent.
[0048] In one embodiment of this application, after obtaining the relative positional relationship information through the above steps, in response to the relative positional relationship information exceeding the corresponding preset parameter range, an adjustment prompt message can be sent to provide timely alarm prompts during the surgical operation.
[0049] In one embodiment of this application, the above-mentioned preset parameter range includes at least one of the following:
[0050] The first preset parameter range corresponding to the first relative distance is 2.7mm to 3.5mm;
[0051] The second preset parameter range corresponding to the second relative distance is 1.0mm to 2.0mm;
[0052] The third preset parameter range corresponding to the angle between the cutting blade and the horizontal line is 45° to 60°.
[0053] If the first relative distance between the incision blade and the lower corneal boundary exceeds the range of the first preset parameters, it indicates a shallow anterior chamber depth and limited surgical space, potentially damaging ocular tissues. If the second relative distance between the incision blade and the lens exceeds the range of the second preset parameters but is less than 1.0 mm, it indicates a small safe distance between the incision blade and the lens, potentially damaging ocular tissues. If the angle between the incision blade and the horizontal line exceeds the range of the third preset parameters and is greater than 60°, it may damage the corneal endothelium or iris.
[0054] In one embodiment of this application, when the relative positional relationship information exceeds the corresponding preset parameter range, an audio warning can be used to indicate that the relative positional relationship information exceeds the corresponding preset parameter range. For example, a voice broadcast can be sent indicating that "the relative positional relationship information exceeds the corresponding preset parameter range and the specific value of the excess", or a specific prompt sound such as a beep can be emitted to indicate that the relative positional relationship information exceeds the corresponding preset parameter range. Thus, timely warnings can be given during the surgical procedure to avoid accidental damage to the eye tissue.
[0055] This application can perform OCT scanning based on automatically identified incision information and incision knife position information, and determine at least one relative positional relationship between the incision knife and eye tissue based on the obtained OCT image. If the relative positional relationship information exceeds the corresponding preset parameter range, it can send adjustment prompt information. Therefore, it does not require manual adjustment and can provide timely adjustment prompt information, thereby reducing unnecessary operations by doctors during surgery, reducing surgical risks, and improving surgical safety and efficiency.
[0056] In one embodiment of this application, as shown in FIG4, step 104 may include:
[0057] Step S201: The maximum vertical distance between the lower corneal boundary and the horizontal line where the incision blade is located is determined as the first relative distance between the incision blade and the lower corneal boundary.
[0058] For example, in one embodiment of this application, referring to FIG3, H1 represents the first relative distance between the incision blade and the lower corneal boundary.
[0059] Step S202: The maximum vertical distance between the horizontal line where the incision blade is located and the upper boundary of the lens is determined as the second relative distance between the incision blade and the lens.
[0060] For example, in one embodiment of this application, referring to FIG3, H2 represents the second relative distance between the incision blade and the lens.
[0061] Step S203: Determine the angle of inclination of the cutting blade relative to the horizontal direction as the angle between the cutting blade and the horizontal line.
[0062] In one embodiment of this application, the incision blade needs to be angled to enter the cornea to form a trapezoidal incision, which helps with postoperative sealing and healing. For example, in one embodiment of this application, referring to Figure 3, the included angle α represents the angle between the incision blade and the horizontal line.
[0063] In one embodiment of this application, after determining at least one relative positional relationship information through the above steps, it can be determined whether to send adjustment prompt information based on the at least one relative positional relationship information, so that adjustment prompt information can be provided in a timely manner to provide alarm prompts during the surgical operation.
[0064] In one embodiment of this application, as shown in FIG5, the method may further include:
[0065] Step S301: Identify the corresponding surgical stage based on the real-time acquired eye images.
[0066] In one embodiment of this application, step S301 may include: determining the probability value of the eye image belonging to each category through a second convolutional neural network, and determining the category with the highest confidence among the probability values of each category as the surgical stage corresponding to the eye image.
[0067] In one embodiment of this application, the second convolutional neural network can be obtained by training an initial convolutional neural network. In another embodiment of this application, the second convolutional neural network can be trained through the following steps:
[0068] Step 1: Obtain the first training dataset consisting of multiple surgical video clips;
[0069] Step 2: Annotate the first training dataset frame by frame based on a sampling rate with a preset threshold to obtain the corresponding second training dataset;
[0070] Step 3: Train the initial convolutional neural network based on the second training dataset to obtain the second convolutional neural network.
[0071] In one embodiment of this application, a first training dataset can be determined by acquiring multiple video segments (e.g., 200-400 segments) of preset duration (e.g., 15 minutes) using a large-scale video dataset (e.g., AVA Actions Dataset).
[0072] Furthermore, in one embodiment of this application, the aforementioned preset threshold can be set as needed; for example, the preset threshold is 1 FPS (frames per second). In one embodiment of this application, the actual operations and different stages of incision in the first training dataset can be labeled to obtain the corresponding second training dataset.
[0073] In one embodiment of this application, the cross-entropy loss function can be used during the training process to measure the gap between the predicted surgical stage of the initial convolutional neural network and the true label, thereby optimizing the initial convolutional neural network to obtain the second convolutional neural network.
[0074] Furthermore, in one embodiment of this application, after obtaining the second convolutional neural network through the above steps, the second convolutional neural network can be deployed and run on a GPU (Graphics Processing Unit) to ensure real-time operation.
[0075] In one embodiment of this application, the surgical stages may include pre-incision, intra-incision, and post-incision phases. In another embodiment, the intra-incision phase may be from the insertion of the scalpel into the corneal rim until the scalpel penetrates a specific area of the eye, or from the insertion of the scalpel into the corneal rim until the scalpel remains stationary for a preset time, or from the insertion of the scalpel into the corneal rim until the scalpel is withdrawn to the outer side of the cornea. The specific area and the preset time can be set as needed.
[0076] In one embodiment of this application, the incision stage begins with the incision of the incision into the cornea. However, the insertion or cutting process of the incision knife during the operation is very rapid. If the incision into the cornea is used as the judgment point, it may cause a delay in recognition, failing to obtain incision knife information in a timely manner, thus failing to provide timely warnings. Furthermore, it may fail to recognize some sensitive operations performed before the incision. Therefore, the aforementioned second convolutional neural network, combined with labeled data reflecting the actual operational needs of the surgeon, can identify effective information before the incision, thereby more rationally dividing the surgical stages and providing timely and reliable auxiliary warning information for different stages.
[0077] In one embodiment of this application, a second convolutional neural network can be used to determine the doctor's usual starting point for incision, thereby effectively locating and tracking surgical instruments or related tissues in advance. For example, it can identify the preparatory posture of surgical instruments in a time period close to the insertion of the incision scalpel into the eyeball.
[0078] Step S302: Based on the acquisition of incision information and incision knife position information during the surgical stage, OCT scans are performed on the corresponding specific locations.
[0079] In one embodiment of this application, step S302 may include: receiving surgical stage information, initiating the acquisition of incision information and incision knife position information, and performing OCT scanning on the corresponding specific location. In one embodiment of this application, when the surgical stage information indicates that an incision is in progress, the acquisition of incision information and incision knife position information may be initiated, and OCT scanning may be performed on the specific location.
[0080] In one embodiment of this application, if the surgical stage is after the incision, an OCT scan can be performed based on the incision information, the scanning range of the local corneal region, the second preset imaging depth range, and the preset number of sampling voxels to obtain the corresponding OCT image.
[0081] In one embodiment of this application, if the surgical stage is after incision, the OCT module can be guided to perform OCT volume scanning in the incision area after the incision is completed, and the corresponding OCT image can be obtained. This allows the doctor to observe the corneal incision based on the OCT image during the operation, so as to facilitate the doctor's intraoperative assessment and adjustment of the surgical operation.
[0082] In one embodiment of this application, the scanning range of the corneal local area can be (3×3mm, 6×6mm); the second preset imaging depth range can be (2mm, 3mm); and the preset sampling voxel count can be 256×256-512×512.
[0083] In this embodiment, by performing an OCT scan on the incision area in the post-incision stage to obtain an OCT image, the doctor can assess the incision status based on the OCT image, which is beneficial for the doctor to assess and adjust the surgical operation during the operation.
[0084] In one embodiment of this application, the corresponding surgical stage can be identified in a timely and accurate manner based on real-time acquired eye images. Based on the surgical stage, the collection of incision information and incision knife position information can be initiated, and OCT scanning can be performed on the corresponding specific location. This allows for the identification of effective information in the pre-incision stage, which helps doctors to more rationally divide the surgical stages and provides timely and reliable auxiliary early warning information for different stages.
[0085] In one embodiment of this application, as shown in FIG6, the above method may further include:
[0086] Step S401: Identify the corresponding surgical stage based on the real-time acquired eye images.
[0087] Step S402: Based on the acquisition of incision information and incision knife position information during the surgical stage, OCT scans are performed on the corresponding specific locations.
[0088] For a detailed description of steps 401 to 402 above, please refer to the above embodiments. The embodiments of this application will not be repeated here.
[0089] Step 403: Based on the surgical stage and relative positional relationship information, overlay and display relative positional setting information on the acquired eye image. The relative positional setting information is a numerical value or indication of the relative positional relationship information.
[0090] In one embodiment of this application, the information indicated by the relative position relationship information may include at least one of the following: displaying information in the relative position relationship information that is greater than or less than the corresponding standard value according to a standard value, so as to facilitate further adjustment; displaying the numerical value, line segment mark and area indicated by the relative position relationship information.
[0091] In one embodiment of this application, after overlaying relative position setting information onto the eye image through the above steps, changes in the overlayed relative position setting information can indicate that the relative position relationship information exceeds the corresponding preset parameter range. In another embodiment of this application, changes in the relative position setting information can be displayed through changes in the numerical value represented or indicated by the displayed relative position information, changes in the font size of the numerical value, changes in the color of the numerical value, changes in the color of the line segment marker, and synchronous display of corresponding symbol information.
[0092] In one embodiment of this application, relative position setting information is superimposed on the eye image based on the surgical stage and relative position relationship information, so that the doctor can intuitively observe the relative position relationship information during the operation, so that the doctor can evaluate and adjust the surgical operation during the operation.
[0093] Figure 7 is a flowchart of the ICL implantation surgery monitoring method in an embodiment of this application. The method includes: acquiring an eye image of the operated eye in real time; determining the surgical stage corresponding to the eye image through a second convolutional neural network; if the surgical stage is the pre-incision stage, not starting an OCT scan; if the surgical stage is the incision stage, starting an OCT scan and sending adjustment prompts for the ICL implantation surgery based on the obtained OCT image; if the surgical stage is the post-incision stage, starting an OCT scan and evaluating the incision status based on the obtained OCT image.
[0094] In one implementation, if the surgical stage is during the incision stage, an OCT scan is initiated, and adjustment prompts are sent to the ICL implantation surgery based on the obtained OCT images. The scanning depth of the OCT scan meets the first preset imaging depth range, and the scanning width of the OCT scan meets the pre-approval scanning width range. If the surgical stage is after the incision stage, an OCT scan is initiated, and the incision status is evaluated based on the obtained OCT images. The OCT module is guided to perform a volumetric OCT scan in the incision area by the incision location information to obtain the corresponding OCT images.
[0095] Figure 8 is a flowchart of the ICL implantation surgery monitoring method in an embodiment of this application. The method includes: acquiring an eye image of the operated eye in real time and determining the surgical stage corresponding to the image through a second convolutional neural network; if the surgical stage is the incision stage, determining incision information and incision knife position information through the eye image; performing an OCT scan based on at least one of the incision information and incision knife position information to obtain Bscan scan data; determining a segmentation result based on the Bscan scan data; determining at least one relative positional relationship information between the incision knife and the eye tissue based on the segmentation result; and sending an adjustment prompt message in response to the relative positional relationship information exceeding a preset parameter range.
[0096] Figure 9 is a schematic diagram of the structure of a surgical microscope system according to an embodiment of this application. As shown in Figure 9, the surgical microscope system 900 may include:
[0097] OCT scanning unit 901 is configured to acquire OCT images;
[0098] The eye image acquisition unit 902 is configured to acquire images of the surgical field of view from a surgical microscope;
[0099] At least one control computing unit 903 is configured to execute the ICL implantation surgery monitoring method described in any of the foregoing method embodiments, the method being able to achieve at least one of the following: processing of eye images, calculation of at least one relative positional relationship information, identification of eye tissue regions and boundaries, and determination of surgical stage based on eye images.
[0100] The explanations and descriptions of the aforementioned ICL implantation surgical monitoring method embodiments also apply to the surgical microscope system of this embodiment, and will not be repeated here.
[0101] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
Claims
1. A method for monitoring ICL implantation surgery, comprising: Real-time acquisition of eye images of the operated eye; Based on the acquired eye images, the cutting information and position information of the cutting knife are identified; Perform an OCT scan at a specific location and acquire an OCT image based on at least one of the incision information and the incision knife position information; The ocular tissue and the incision blade are segmented based on the OCT image, and the relative positional relationship information between the incision blade and the ocular tissue is determined based on the obtained segmentation results. The relative positional relationship information includes at least one of the following: a first relative distance between the incision blade and the lower boundary of the cornea, a second relative distance between the incision blade and the lens, and an angle between the incision blade and the horizontal line. In response to the relative positional relationship information exceeding the corresponding preset parameter range, an adjustment prompt message is sent.
2. The monitoring method according to claim 1, wherein The cutting blade position information includes the rotation angle of the cutting blade; Based on at least one of the incision information and the incision blade position information, perform an OCT scan at a specific location and acquire an OCT image, including: Using the incision information as the center, perform an OCT scan within a first preset imaging depth range and a preset scanning width range to obtain an OCT image corresponding to the cross-sectional B-scan data; or, OCT scanning is performed along the direction corresponding to the rotation angle of the cutting blade within a first preset imaging depth range and a preset scanning width range to obtain an OCT image corresponding to the cross-sectional B-scan data.
3. The monitoring method of claim 1, wherein, Segmenting eye tissue and incision blade based on the OCT image includes: segmenting eye tissue and incision blade in the OCT image using a first convolutional neural network to obtain segmentation results including the tissue boundaries of the cornea and lens and the incision blade.
4. The monitoring method of claim 3, wherein, Based on the obtained segmentation results, the relative positional relationship between the incision blade and the eye tissue is determined, including: The maximum vertical distance between the lower corneal boundary and the horizontal line where the incision blade is located is determined as the first relative distance between the incision blade and the lower corneal boundary; The maximum vertical distance between the horizontal line where the incision blade is located and the upper boundary of the lens is determined as the second relative distance between the incision blade and the lens; The angle of inclination of the cutting blade relative to the horizontal direction is determined as the angle between the cutting blade and the horizontal line.
5. The monitoring method of claim 1, wherein, The preset parameter range includes at least one of the following: The first preset parameter range corresponding to the first relative distance is 2.7mm to 3.5mm; The second preset parameter range corresponding to the second relative distance is 1.0mm to 2.0mm; The third preset parameter range corresponding to the angle between the cutting blade and the horizontal line is 45° to 60°.
6. The monitoring method according to claim 1 further includes: Based on real-time acquired eye images, the corresponding surgical stage is identified; Based on the surgical stage, the incision information and the incision knife position information are collected, and OCT scans are performed on the corresponding specific locations.
7. The monitoring method of claim 6, wherein, The surgical phases include pre-incision, during-incision, and post-incision stages; the acquisition of incision information and incision knife position information based on the surgical phases, and the performance of OCT scans on corresponding specific locations, includes: The system receives surgical stage information, initiates the acquisition of incision information and incision knife position information, and performs OCT scanning on the corresponding specific locations.
8. The monitoring method according to claim 6 further includes: Based on the surgical stage and the relative positional relationship information, relative positional setting information is superimposed and displayed on the acquired eye image. The relative positional setting information is a numerical value or an indication of the relative positional relationship information.
9. The method of claim 8, wherein, Send the adjustment notification message using at least one of the following methods: The change in the relative position setting information displayed in superimposed form indicates that the relative position relationship information exceeds the corresponding preset parameter range; An audible warning is used to indicate that the relative positional relationship information exceeds the corresponding preset parameter range.
10. A surgical microscope system for use in ICL implantation surgery, comprising: The OCT scanning unit is configured to acquire OCT images; The eye image acquisition unit is configured to acquire images of the surgical field of view from the surgical microscope; At least one control computing unit is configured to perform the ICL implantation surgery monitoring method according to any one of claims 1 to 9.
11. A computer-readable storage medium storing a computer program that, when executed, implements the monitoring method for ICL implantation surgery according to any one of claims 1 to 9.
