Drilling path planning method of artificial cochlea implantation channel, storage medium and equipment

Abstract

The invention discloses a drilling path planning method for an artificial cochlea implantation channel, a storage medium and equipment, and belongs to the technical field of path planning in artificial cochlea implantation. The problems that an existing path planning method is low in efficiency and path deviation is likely to be introduced are solved. According to the method, a preoperative three-dimensional CT image is preprocessed, and an anatomical structure model is fused to extract three-dimensional space geometric information of key tissues including facial nerves and cochlea in a temporal bone. And then, by combining prior medical knowledge, a drilling path of an artificial cochlea electrode is automatically planned in a three-dimensional space, so that damage to key nerves is minimized, and the safety of an operation is ensured. The path planning method is suitable for the medical robot assisted artificial cochlea implantation operation, the dependence on subjective judgment of a doctor is remarkably reduced, the individualized adaptive capacity and efficiency of path design are improved, and path deviation caused by subjective judgment is effectively avoided. The method can be applied to path planning in an artificial cochlea implantation operation.

Description

Technical Field

[0001] The present invention belongs to the technical field of path planning in cochlear implantation, and in particular relates to a drilling path planning method, storage medium and equipment for a cochlear implantation channel. Background Art

[0002] During cochlear implant surgery, drilling path planning is directly related to surgical safety and implant effectiveness. To avoid damaging critical structures such as the facial nerve and auditory ossicles, doctors typically need to develop a safe and optimal drilling path based on preoperative CT imaging to ensure the implant reaches the cochlear opening.

[0003] Currently, path planning primarily relies on preoperative CT images. CT images provide clear information about bony anatomy, but they are presented in the form of two-dimensional slices, lacking spatial clarity. Doctors must possess extensive clinical experience, analyze slice by slice to identify key structures, and mentally construct their three-dimensional spatial relationships before manually planning the path. However, this approach has significant limitations: it is labor-intensive and inefficient, and it relies heavily on the physician's subjective judgment, which can easily introduce path deviations and even cause intraoperative complications. To overcome the limitations of two-dimensional images, 3D reconstruction technology is used to model CT images and visualize anatomical structures, thereby assisting the physician in observing the spatial distribution of target structures. This technology leverages prior medical knowledge to automatically plan the drilling path in three dimensions. This significantly reduces reliance on the physician's subjective judgment, improves the individualized adaptability of path design, and lays the technical foundation for intelligent ear surgery systems. Summary of the Invention

[0004] The purpose of the present invention is to solve the problems of low efficiency and easy introduction of path deviation in existing path planning methods, and to propose a drilling path planning method, storage medium and device for a cochlear implant channel.

[0005] The technical solution adopted by the present invention to solve the above technical problems is: a method for planning a drilling path for a cochlear implant channel, the method specifically comprising the following steps:

[0006] Step 1: Obtain a 3D CT image of the human cochlea, and then perform semantic segmentation on the acquired 3D CT image to obtain the spatial locations of the cochlea, vestibule, and facial nerve tissues;

[0007] According to the spatial locations of the cochlear, vestibular and facial nerve tissues, the cochlear point cloud, vestibular point cloud and facial nerve tissue point cloud data were extracted from the 3D CT images respectively;

[0008] Step two, determine the demarcation plane n between the cochlea and the vestibule based on the cochlea point cloud data and the vestibule point cloud data, and then translate the demarcation plane n to the cochlea direction to obtain a new plane n1;

[0009] Step three, perform drilling path planning according to the new plane n1 and the facial nerve tissue point cloud data to obtain a drilling path planning result.

[0010] Further, the 3D network model used for the semantic segmentation of the acquired three-dimensional CT image is a 3D Unet model.

[0011] Further, the soft support vector machine is used to determine the demarcation plane n between the cochlea and the vestibule based on the cochlea point cloud data and the vestibule point cloud data.

[0012] Further, the translation distance of the demarcation plane n to the new plane n1 in the cochlea direction is 0.5 millimeters.

[0013] Further, the specific process of step three is as follows:

[0014] Step three one, determine the points in the cochlea point cloud data that are located on the plane n1, and then select the cochlea point closest to the facial nerve tissue point cloud data from the determined points, and take the selected cochlea point as the target point P t ;

[0015] Step three two, perform slice processing on the three-dimensional CT image along the Z-axis direction to obtain a two-dimensional image slice where the target point P t is located, and draw a horizontal line L1 passing through the target point P t on the obtained two-dimensional image slice.

[0016] Calculate the distance from each facial nerve tissue point on the two-dimensional image slice where the target point P t is located to the horizontal line L1 respectively, and obtain the facial nerve tissue point P m corresponding to the minimum distance.

[0017] Step three three, take the point P m as the center, and draw a plane circle O with a radius D on the two-dimensional image slice where the target point P t is located.

[0018] Then draw a tangent line L2 of the target point P t to the plane circle O.

[0019] Step three four, calculate the distance from each facial nerve tissue point to L2 respectively.

[0020] If the distance from each facial nerve tissue point to L2 is greater than or equal to the distance D, then the tangent line L2 is extended to the outer surface of the CT skull, and the intersection of the tangent line L2 and the outer surface of the CT skull is used as the starting point P. s ; Then execute step 39;

[0021] Otherwise, obtain the facial nerve tissue point closest to L2 Then, proceed to steps three and five;

[0022] Step 35: Determine the point Mapping point on tangent line L2 Vector As a direction vector, from point Departure and extension and The straight line until it reaches the point

[0023] Step 36: Initialize the number of iterations l = 0;

[0024] Step 37: Connect target point P t and point Get a straight line Calculate the distance from each facial nerve tissue point to the straight line distance;

[0025] If each facial nerve tissue point to the straight line If the distances are greater than or equal to the distance D, then the straight line Extend to the outer surface of the CT skull and The intersection point with the outer surface of the CT skull is taken as the starting point P s ; Then execute step 39;

[0026] Otherwise, get the distance line The nearest facial nerve tissue point After that, confirm the point In a straight line Mapping point on Vector As a direction vector, from point Departure and extension and The straight line until it reaches the point Then execute step 38;

[0027] Step 38: Set l=l+1, and return to step 37;

[0028] Step 39: Connect the starting point P s and the target point P t The straight line is used as the final planned drilling path.

[0029] Furthermore, the radius D is:

[0030] D=d drill +d safe

[0031] Among them, d drill is the drilling radius, d safe For a safe distance.

[0032] Furthermore, the point Satisfaction: point with dot The straight-line distance is D.

[0033] A computer storage medium stores at least one instruction, which is loaded and executed by a processor to implement a drilling path planning method for a cochlear implant channel.

[0034] A drilling path planning device for a cochlear implant channel comprises a processor and a memory. The memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement a drilling path planning method for the cochlear implant channel.

[0035] The beneficial effects of the present invention are:

[0036] The present invention preprocesses preoperative three-dimensional CT images and integrates anatomical structural models to extract three-dimensional spatial geometric information of key tissues within the temporal bone, including the facial nerve and cochlea. Subsequently, combined with prior medical knowledge, the drilling path for the cochlear implant electrode is automatically planned in three-dimensional space to minimize damage to key nerves and ensure the safety of the operation. The path planning method of the present invention is suitable for medical robot-assisted cochlear implant surgery, significantly reducing reliance on the doctor's subjective judgment, improving the individualized adaptability and efficiency of path design, and effectively avoiding path deviations caused by human subjective judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the dividing plane between the cochlea and vestibule;

[0038] Figure 2 is a schematic diagram of the planning process within a 2D image slice;

[0039] Figure 3 It is a schematic diagram of extending the straight line where P2 and P3 are located to obtain a new straight line. DETAILED DESCRIPTION

[0040] Specific embodiment 1: A method for planning a drilling path for a cochlear implant channel according to this embodiment includes the following steps:

[0041] Step 1: Obtain a 3D CT image of the human cochlea, and then perform semantic segmentation on the acquired 3D CT image to obtain the spatial locations of the cochlea, vestibule, and facial nerve tissues;

[0042] According to the spatial locations of the cochlear, vestibular and facial nerve tissues, the cochlear point cloud, vestibular point cloud and facial nerve tissue point cloud data were extracted from the 3D CT images respectively;

[0043] Step 2: Figure 1 As shown, the boundary plane n between the cochlea and the vestibule is determined based on the cochlear point cloud data and the vestibular point cloud data, and then the boundary plane n is translated toward the cochlea to obtain a new plane n1;

[0044] Step 3: Perform drilling path planning based on the new plane n1 and the facial nerve tissue point cloud data to obtain the drilling path planning result.

[0045] Specific implementation method 2: This implementation method further limits the specific implementation method 1. The semantic segmentation of the acquired three-dimensional CT image adopts a 3D network model, and the 3D network model is a 3D Unet model.

[0046] Other steps and parameters are the same as those in the first embodiment.

[0047] Models that can be used in this embodiment include but are not limited to 3D Unet models.

[0048] Specific embodiment three: This embodiment further limits specific embodiment one, and the boundary plane n between the cochlea and the vestibule is determined based on the cochlear point cloud data and the vestibular point cloud data using a soft support vector machine (SoftSVM).

[0049] Other steps and parameters are the same as those in the first embodiment.

[0050] Specific embodiment 4: This embodiment is a further limitation of specific embodiment 1, wherein the boundary plane n is translated toward the cochlea to obtain a new plane n1, and the translation distance is 0.5 mm.

[0051] Other steps and parameters are the same as those in the first embodiment.

[0052] According to prior knowledge, the round window is approximately located about 0.5 mm below the junction of the cochlea and the vestibule. Therefore, the present invention sets the translation distance to 0.5 mm.

[0053] Specific implementation method 5: This implementation method further limits the specific implementation method 1. The specific process of step 3 is as follows:

[0054] Step 3. Identify the point on plane n1 in the cochlear point cloud data, and then select the cochlear point closest to the facial nerve tissue point cloud data from the determined points (i.e., for any determined point, calculate the distance between the point and each point of the facial nerve tissue, and then obtain the minimum distance corresponding to the determined point; then calculate the minimum distance corresponding to each determined point, and obtain the minimum value of each minimum distance by comparison to obtain the cochlear point corresponding to the minimum value), and use the selected cochlear point as the target point P t ;

[0055] Step 3.2: Slice the 3D CT image along the Z axis to obtain the target point P. t Draw a line through the target point P on the obtained two-dimensional image slice. t The horizontal line L1;

[0056] Calculate the target point P separately t The distance between each facial nerve tissue point on the two-dimensional image slice and the horizontal line L1 is obtained to obtain the facial nerve tissue point P corresponding to the minimum distance m ;

[0057] Step 3. Take point P m As the center of the circle, at the target point P t Draw a plane circle O with a radius D on the two-dimensional image slice where it is located;

[0058] Then draw the target point P t Tangent line L2 to plane circle O;

[0059] Steps 3 and 4: Calculate the distance from each facial nerve tissue point to L2;

[0060] If the distance from each facial nerve tissue point to L2 is greater than or equal to the distance D, then the tangent line L2 is extended to the outer surface of the CT skull, and the intersection of the tangent line L2 and the outer surface of the CT skull (or the intersection of the tangent line L2 and the outer surface of the CT skull) is used as the starting point P. s ,like Figure 2 As shown; then perform step thirty-nine;

[0061] Otherwise, obtain the facial nerve tissue point closest to L2 Then, proceed to steps three and five;

[0062] Step 35: Determine the point Mapping point on tangent line L2 (i.e. from point Draw a perpendicular line to the tangent line L2, and the foot of the perpendicular is ),like Figure 3 As shown, the vector As a direction vector, from point Departure and extension and The straight line until it reaches the point

[0063] Step 36: Initialize the number of iterations l = 0;

[0064] Step 37: Connect target point P t and point Get a straight line Calculate the distance from each facial nerve tissue point to the straight line distance;

[0065] If each facial nerve tissue point to the straight line If the distances are greater than or equal to the distance D, then the straight line Extend to the outer surface of the CT skull and The intersection point with the outer surface of the CT skull (which can also be located outside the outer surface of the CT skull and at the same time on the tangent line L2) is used as the starting point P s ; Then execute step 39;

[0066] Otherwise, get the distance line The nearest facial nerve tissue point After that, confirm the point In a straight line Mapping point on (i.e. from point Towards a straight line Draw a perpendicular line, and the foot of the perpendicular is ), with vector As a direction vector, from point Departure and extension and The straight line until it reaches the point Then execute step 38;

[0067] Step 38: Set l=l+1, and return to step 37;

[0068] Step 39: Connect the starting point P s and the target point P t The straight line is used as the final planned drilling path.

[0069] The overall planning algorithm is shown in Table 1:

[0070] Table 1

[0071]

[0072]

[0073] Other steps and parameters are the same as those in the first embodiment.

[0074] Specific embodiment 6: This embodiment is a further limitation of specific embodiment 5, and the radius D is:

[0075] D=d drill +d safe

[0076] Among them, d drill is the drilling radius (taken as 0.9 mm), d safe For safety distance (the drilling channel should maintain a safety distance of at least 0.5 mm from the facial nerve to prevent damage to the facial nerve during surgery, the present invention will safe set to 2.4 mm).

[0077] Other steps and parameters are the same as those in the fifth embodiment.

[0078] Specific implementation method seven: This implementation method is a further limitation of the specific implementation method five. Satisfaction: point with dot The straight-line distance is D.

[0079] Other steps and parameters are the same as those in the fifth embodiment. Specific implementation method eight:

[0081] This embodiment is a computer storage medium, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement the drilling path planning method for a cochlear implant channel.

[0082] It should be understood that the instructions include computer program products, software, or computerized methods corresponding to any method described in the present invention; the instructions can be used to program a computer system or other electronic device. Computer storage media may include readable media on which instructions are stored, and may include but are not limited to magnetic storage media, optical storage media; magneto-optical storage media include read-only memory ROM, random access memory RAM, erasable programmable memory (e.g., EPROM and EEPROM) and flash memory layers, or other types of media suitable for storing electronic instructions. Specific implementation method nine:

[0084] This embodiment is a device for planning a drilling path for a cochlear implant channel. The device includes a processor and a memory. It should be understood that the device includes any device including a processor and a memory described in the present invention, and may also include other units or modules that perform display, interaction, processing, control, and other functions through signals or instructions.

[0085] At least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to implement the drilling path planning method for a cochlear implant channel.

[0086] Those skilled in the art will appreciate that at least one instruction stored is a computer program product corresponding to the method or system. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and interpreted scripting language JavaScript, etc.

[0087] The present application is described with reference to the flowcharts and / or block diagrams of the methods, systems, and computer program products according to the embodiments of the present application, and can also be used for corresponding devices. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0090] The above examples are merely illustrative of the calculation model and process of the present invention and are not intended to limit the embodiments of the present invention. Persons skilled in the art will readily appreciate that other variations or modifications based on the above description are possible. This list of embodiments is not exhaustive; however, any obvious variations or modifications derived from the technical solution of the present invention remain within the scope of protection of the present invention.

Claims

1. A method for planning a drilling path for a cochlear implant channel, characterized in that: The method specifically comprises the following steps: Step 1: Obtain a 3D CT image of the human cochlea, and then perform semantic segmentation on the acquired 3D CT image to obtain the spatial locations of the cochlea, vestibule, and facial nerve tissues; According to the spatial locations of the cochlear, vestibular and facial nerve tissues, the cochlear point cloud, vestibular point cloud and facial nerve tissue point cloud data were extracted from the 3D CT images respectively; Step 2: Determine the boundary plane n between the cochlea and the vestibule based on the cochlear point cloud data and the vestibular point cloud data, and then translate the boundary plane n toward the cochlea to obtain a new plane n1; Step 3: Perform drilling path planning based on the new plane n1 and the facial nerve tissue point cloud data to obtain the drilling path planning result.

2. A method for planning a drilling path for a cochlear implant channel according to claim 1, characterized in that: The semantic segmentation of the acquired three-dimensional CT image adopts a 3D network model, and the 3D network model is a 3DUnet model.

3. The method for planning a drilling path for a cochlear implant channel according to claim 1, wherein: The method for determining the boundary plane n between the cochlea and the vestibule based on the cochlear point cloud data and the vestibular point cloud data adopts a soft support vector machine.

4. The method for planning a drilling path for a cochlear implant channel according to claim 1, wherein: The boundary plane n is translated toward the cochlea to obtain a new plane n1, and the translation distance is 0.5 mm.

5. The method for planning a drilling path for a cochlear implant channel according to claim 1, wherein: The specific process of step three is: Step 3: Identify the point on plane n1 in the cochlear point cloud data, and then select the cochlear point closest to the facial nerve tissue point cloud data from the determined points, and use the selected cochlear point as the target point P. t ; Step 3.2: Slice the 3D CT image along the Z axis to obtain the target point P. t Draw a line through the target point P on the obtained two-dimensional image slice. t The horizontal line L1; Calculate the target point P separately t The distance between each facial nerve tissue point on the two-dimensional image slice and the horizontal line L1 is obtained to obtain the facial nerve tissue point P corresponding to the minimum distance m ; Step 3. Take point P m As the center of the circle, at the target point P t Draw a plane circle O with a radius D on the two-dimensional image slice where it is located; Then draw the target point P t Tangent line L2 to plane circle O; Steps 3 and 4: Calculate the distance from each facial nerve tissue point to L2; If the distance from each facial nerve tissue point to L2 is greater than or equal to the distance D, then the tangent line L2 is extended to the outer surface of the CT skull, and the intersection of the tangent line L2 and the outer surface of the CT skull is used as the starting point P. s ; Then execute step 39; Otherwise, obtain the facial nerve tissue point closest to L2 Then, proceed to steps three and five; Step 35: Determine the point Mapping point on tangent line L2 Vector As a direction vector, from point Departure and extension and The straight line until it reaches the point Step 36: Initialize the number of iterations l = 0; Step 37: Connect target point P t and point Get a straight line Calculate the distance from each facial nerve tissue point to the straight line distance; If each facial nerve tissue point to the straight line If the distances are greater than or equal to the distance D, then the straight line Extend to the outer surface of the CT skull and The intersection point with the outer surface of the CT skull is taken as the starting point P s ; Then execute step 39; Otherwise, get the distance line The nearest facial nerve tissue point After that, determine the point In a straight line Mapping point on Vector As a direction vector, from point Departure and extension and The straight line until it reaches the point Then execute step 38; Step 38: Set l=l+1, and return to step 37; Step 39: Connect the starting point P s and the target point P t The straight line is used as the final planned drilling path.

6. The method for planning a drilling path for a cochlear implant channel according to claim 5, wherein: The radius D is: D=d drill +d safe Among them, d drill is the drilling radius, d safe For a safe distance.

7. The method for planning a drilling path for a cochlear implant channel according to claim 5, wherein: Said point Satisfaction: point with dot The straight-line distance is D.

8. A computer storage medium, characterized in that The storage medium stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the drilling path planning method for a cochlear implant channel according to any one of claims 1 to 7.

9. A drilling path planning device for a cochlear implant channel, characterized in that: The device includes a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the drilling path planning method for a cochlear implant channel according to any one of claims 1 to 7.

Images