Preprocessing method for foot hallux valgus surgical planning and related products

Abstract

The invention discloses a preprocessing method for foot hallux valgus surgical planning and a related product. The preprocessing method comprises the following steps: acquiring a foot CT image of a detected person; performing three-dimensional reconstruction on the foot of the detected person based on the foot CT image to obtain a three-dimensional reconstruction surface body of the foot of the detected person; performing hallux valgus affected side identification based on the three-dimensional reconstruction surface body to obtain the hallux valgus affected side of the detected person; and converting the hallux valgus affected side from the CT coordinate system to a hallux valgus coordinate system so as to realize preprocessing of foot hallux valgus surgical planning. By means of the scheme, the foot CT image can be processed into the data facilitating follow-up calculation of the operation planning parameters, and the operation planning efficiency and accuracy are improved.

Description

Technical Field

[0001] The present application generally relates to the technical field of minimally invasive hallux valgus. More specifically, the present application relates to a pretreatment method, a pretreatment device and a computer-readable storage medium for planning a hallux valgus surgery. Background Art

[0002] Hallux valgus refers to the deformity of the first metatarsophalangeal joint, that is, the big toe deviates outward relative to the first metatarsal bone, causing the angle between the two (hallux valgus angle) to exceed 15°, which is generally manifested as a bunion or pain on the medial side of the first metatarsal head. Hallux valgus is a common forefoot deformity in clinical practice. Surgical treatment is the mainstream treatment method at home and abroad. However, there are hundreds of surgical treatments for hallux valgus, and there is still controversy about the best surgical technique. In recent years, with the improvement of people's requirements for quality of life, minimally invasive surgery for hallux valgus has been accepted by more and more patients due to its advantages such as less trauma, less postoperative pain, early weight-bearing walking and aesthetics, and has also attracted the attention of clinicians again. At present, the minimally invasive surgery technology for hallux valgus has developed to the third generation, and its core is to obtain good surgical results through minimally invasive osteotomy, reduction and internal fixation.

[0003] At present, the existing method is to collect CT images of the subject's foot, and calculate the parameters such as osteotomy, reduction, internal fixation, etc. required for minimally invasive hallux valgus based on the CT images of the foot, so as to facilitate subsequent surgical planning. However, the original foot CT images are usually point cloud data, and contain both the affected side and the non-affected side of the subject's foot, which facilitates the subsequent surgical planning calculation for the affected side of hallux valgus. In addition, the point cloud data in the collected foot CT images are in CT coordinates, which can only record the position of each point, but cannot identify the specific part to which each point belongs, so that it is impossible to accurately calculate the surgical planning parameters such as osteotomy, reduction, and internal fixation. Therefore, processing the foot CT images into data that is convenient for the subsequent calculation of surgical planning parameters has become a technical problem that needs to be solved urgently.

[0004] In view of this, there is an urgent need to provide a preprocessing solution for hallux valgus surgery planning, so as to process the foot CT images into data that are convenient for subsequent calculation of surgical planning parameters, thereby improving the efficiency and accuracy of surgical planning. Summary of the invention

[0005] In order to at least solve one or more of the above-mentioned technical problems, the present application proposes a pretreatment scheme for hallux valgus surgery planning in multiple aspects.

[0006] In a first aspect, the present application provides a preprocessing method for planning surgery for hallux valgus of the foot, comprising: acquiring a CT image of a subject's foot; performing three-dimensional reconstruction of the subject's foot based on the CT image of the foot to obtain a three-dimensional reconstructed surface volume of the subject's foot; identifying the hallux valgus affected side based on the three-dimensional reconstructed surface volume to obtain the hallux valgus affected side of the subject; and converting the hallux valgus affected side from the CT coordinate system to the hallux valgus coordinate system to achieve preprocessing of surgery planning for hallux valgus of the foot.

[0007] In one embodiment, the foot CT image includes three-dimensional point cloud data, and the subject's foot is three-dimensionally reconstructed based on the foot CT image to obtain the three-dimensional reconstructed surface volume of the subject's foot, which includes: converting the three-dimensional point cloud data in the foot CT image into a three-dimensional Boolean matrix; extracting the surface point set of the three-dimensional point cloud data from the three-dimensional Boolean matrix; and performing three-dimensional reconstruction of the subject's foot based on the surface point set to obtain the three-dimensional reconstructed surface volume of the subject's foot.

[0008] In another embodiment, converting the three-dimensional point cloud data in the foot CT image into a three-dimensional Boolean matrix includes: determining a preset grayscale value of a target area in the three-dimensional point cloud data in the foot CT image; setting a transformation function according to the preset grayscale value; and converting the three-dimensional point cloud data in the foot CT image into the three-dimensional Boolean matrix based on the transformation function.

[0009] In another embodiment, extracting the surface point set of the three-dimensional point cloud data from the three-dimensional Boolean matrix includes: setting a surface point set filter based on a contour algorithm; and filtering the three-dimensional Boolean matrix using the surface point set filter to extract the surface point set of the three-dimensional point cloud data.

[0010] In another embodiment, performing three-dimensional reconstruction on the subject's foot based on the surface point set to obtain the three-dimensional reconstructed surface volume of the subject's foot includes: using a triangulation function to mesh the surface point set to perform three-dimensional reconstruction on the subject's foot to obtain the three-dimensional reconstructed surface volume of the subject's foot.

[0011] In yet another embodiment, the preprocessing method further comprises: performing a scaling operation and / or a smoothing operation on the three-dimensional reconstructed surface volume.

[0012] In yet another embodiment, the three-dimensional reconstructed surface volume is represented by the following formula:

[0013]

[0014] Among them, I 3drepresents the three-dimensional reconstructed surface volume, represents the three-dimensional point cloud data, H + (·) represents the transformation function, filter(·) represents the surface point set filter, represents the spatial scaling matrix, Denotes the triangulation function.

[0015] In another embodiment, identifying the hallux valgus affected side based on the three-dimensional reconstructed surface body to obtain the hallux valgus affected side of the subject includes: identifying a minimum three-dimensional rectangular bounding box of the hallux valgus affected side based on the three-dimensional reconstructed surface body; and cutting the three-dimensional reconstructed surface body along the minimum three-dimensional rectangular bounding box to obtain the hallux valgus affected side of the subject.

[0016] In yet another embodiment, identifying the minimum three-dimensional rectangular bounding box of the hallux valgus affected side based on the three-dimensional reconstructed surface volume comprises: identifying the minimum three-dimensional rectangular bounding box of the hallux valgus affected side by the following formula:

[0017]

[0018] in, represents the minimum three-dimensional rectangular bounding box, I 3d represents the three-dimensional reconstructed surface volume, Δx + ,Δy + ,Δz + ,Δx - ,Δy - ,Δz - Indicates the positive and negative directions along x, y, and z. Represents the distance from seed point a0 to The bounding faces on the bounding box on , Φ represents the empty set.

[0019] In another embodiment, converting the hallux valgus affected side from the CT coordinate system to the hallux valgus coordinate system includes: setting the hallux valgus coordinate system based on multiple detection points on the hallux valgus affected side; and establishing a conversion relationship according to the coordinate position of the coordinate vector of the target point on the CT coordinate system on the hallux valgus coordinate system; and converting the hallux valgus affected side from the CT coordinate system to the hallux valgus coordinate system based on the conversion relationship.

[0020] In a second aspect, the present application provides a preprocessing device for hallux valgus surgery planning, comprising: a processor; and a memory, in which program instructions for preprocessing for hallux valgus surgery planning are stored, and when the program instructions are executed by the processor, the preprocessing device implements multiple embodiments of the aforementioned first aspect.

[0021] In a third aspect, the present application provides a computer-readable storage medium having stored thereon computer-readable instructions for preprocessing for hallux valgus surgery planning, wherein when the computer-readable instructions are executed by one or more processors, multiple embodiments of the aforementioned first aspect are implemented.

[0022] Through the preprocessing scheme for hallux valgus surgery planning provided above, the embodiment of the present application performs preprocessing operations such as three-dimensional reconstruction, hallux valgus affected side identification, and coordinate system conversion on the foot CT image to extract the hallux valgus affected side and convert the hallux valgus affected side from the CT coordinate system to the hallux valgus coordinate system, thereby processing the foot CT image into data that is convenient for subsequent calculation of surgical planning parameters. The surgical planning parameters can be calculated directly based on the preprocessed data, thereby improving the efficiency and accuracy of surgical planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easy to understand. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0024] Figure 1 is an exemplary schematic diagram showing hallux valgus;

[0025] Figure 2 is an exemplary flowchart showing a preprocessing method for hallux valgus surgery planning according to an embodiment of the present application;

[0026] Figure 3 is an exemplary schematic diagram showing a three-dimensional reconstructed surface volume and an identified minimum three-dimensional rectangular bounding box of the hallux valgus affected side according to an embodiment of the present application;

[0027] Figure 4 is an exemplary schematic diagram showing a hallux valgus coordinate system set according to an embodiment of the present application;

[0028] Figure 5 is an exemplary intention showing a CT coordinate system of the hallux valgus affected side and a converted hallux valgus coordinate system according to an embodiment of the present application;

[0029] Figure 6 is an exemplary structural block diagram showing a preprocessing device for hallux valgus surgery planning according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0031] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present application indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0032] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this application specification and claims, unless the context clearly indicates otherwise, the singular forms of "a", "an" and "the" are intended to include plural forms. It should also be further understood that the term "and / or" used in this application specification and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0033] As used in this specification and claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0034] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0035] Figure 1 is an exemplary diagram illustrating hallux valgus of the foot.

[0036] like Figure 1 The CT image of the subject's foot with hallux valgus is shown in FIG. In actual application scenarios, it can be determined whether the subject has hallux valgus deformity based on three target angles. Figure 1As shown in Figures (a) and (b), the three target angles are respectively the angle α1 between the axis l1 of the subject's big toe 101 and the axis l2 of the first metatarsal 102 (also known as the hallux valgus angle), the angle α2 between the axis l2 of the first metatarsal 102 and the axis l3 of the second metatarsal 103 (also known as the first and second metatarsal angle), and the angle α3 between the distal articular surface e of the first metatarsal 102 and the axis l2 of the first metatarsal 102 (also known as the first metatarsal distal articular surface angle). It should be understood that in the embodiments of the present application, the distal ends of the first and second metatarsal bones refer to the ends connected to the thumb, and the ends not connected to the thumb are the proximal ends of the first and second metatarsal bones. For example Figure 1 In Figure (b), the ellipse is the distal end of the second metatarsal bone, and the rectangular frame is the proximal end of the second metatarsal bone.

[0037] For the above three target angles, when the hallux valgus angle α1 is greater than 15°, the angle between the first and second metatarsals α2 is greater than 9°, or the angle α3 of the distal articular surface of the first metatarsal is not 90°, it is determined that the subject's foot has hallux valgus deformity. Furthermore, according to the hallux valgus angle and the angle between the first and second metatarsals, the degree of hallux valgus deformity can also be determined. For example, according to the grading of the hallux valgus angle, mild: 15°<hallus valgus angle<30°, moderate: 30°<hallus valgus angle<40°, severe: hallux valgus angle>40°; according to the grading of the angle between the first and second metatarsals, mild: the angle between the first and second metatarsals <10°, moderate: 10°<the angle between the first and second metatarsals <15°, severe: the angle between the first and second metatarsals>15°. In actual application scenarios, the correction of the deformity of hallux valgus of the foot is also the correction of the above three target angles.

[0038] As described in the background technology, surgical treatment is the mainstream treatment method for hallux valgus deformity correction at home and abroad. At present, the minimally invasive surgery technology for hallux valgus has developed to the third generation, and its core is to obtain good surgical results through minimally invasive osteotomy, reduction, and internal fixation. Before calculating the surgical planning parameters such as osteotomy, reduction, and internal fixation, it is necessary to process the foot CT images into data that is convenient for the subsequent calculation of surgical planning parameters.

[0039] Based on this, an embodiment of the present application provides a preprocessing method for hallux valgus surgery planning. By performing preprocessing operations such as three-dimensional reconstruction of the foot CT images, identification of the hallux valgus affected side, and coordinate system conversion, the foot CT images are processed into data that is convenient for subsequent calculation of surgical planning parameters, thereby improving the efficiency and accuracy of surgical planning.

[0040] Figure 2 FIG. 2 is an exemplary flowchart showing a preprocessing method 200 for planning a hallux valgus surgery according to an embodiment of the present application. Figure 2As shown in , at step S201, a CT image of the foot of the subject is acquired. In an implementation scenario, the foot CT image can be acquired by, for example, a CT scanning device. Based on the acquired foot CT image, at step S202, a three-dimensional reconstruction of the subject's foot is performed based on the foot CT image to obtain a three-dimensional reconstructed surface volume of the subject's foot. In one embodiment, the three-dimensional point cloud data in the foot CT image can be converted into a three-dimensional Boolean matrix, and then the surface point set of the three-dimensional point cloud data can be extracted from the three-dimensional Boolean matrix to perform three-dimensional reconstruction of the subject's foot based on the surface point set to obtain a three-dimensional reconstructed surface volume of the subject's foot. Wherein, the aforementioned foot CT image includes three-dimensional point cloud data.

[0041] In one implementation scenario, the preset grayscale value of the target area in the three-dimensional point cloud data in the foot CT image can be determined, and a transformation function can be set according to the preset grayscale value, and then the three-dimensional point cloud data in the foot CT image can be converted into a three-dimensional Boolean matrix based on the transformation function. It should be understood that the preset grayscale values ​​for the bone tissue and skin tissue in the target area will be different. As an example, for the bone tissue in the first metatarsal region, the corresponding preset grayscale value can be set to 100-160; for the skin tissue in the first metatarsal region, the corresponding preset grayscale value can be set to -100 to 0. In some embodiments, a transformation function can be constructed by setting points above the preset grayscale value to 1 and points below the preset grayscale value to 0, so as to convert the three-dimensional point cloud data in the foot CT image into a three-dimensional Boolean matrix based on the transformation function.

[0042] After obtaining the aforementioned three-dimensional Boolean matrix, in an implementation scenario, a surface point set filter can be set based on a contour algorithm, and the three-dimensional Boolean matrix can be filtered using the surface point set filter to extract the surface point set of the three-dimensional point cloud data. In some embodiments, in addition to the aforementioned contour algorithm, the aforementioned surface point set filter can also be set by, for example, an alpha type method to extract the surface point set of the three-dimensional point cloud data from the aforementioned three-dimensional Boolean matrix. Further, the aforementioned surface point set is meshed using a triangulation function to perform three-dimensional reconstruction of the subject's foot, and a three-dimensional reconstructed surface volume of the subject's foot is obtained.

[0043] In one embodiment, the embodiments of the present application also involve performing scaling operations and / or smoothing operations on the aforementioned three-dimensional reconstructed surface volume. For example, the aforementioned three-dimensional reconstructed surface volume is scaled by using the spacing information in the foot CT image, and the scaled three-dimensional reconstructed surface volume is subjected to, for example, a surface smoothing operation to obtain two three-dimensional reconstructed surface volumes. In some embodiments, the aforementioned surface smoothing operation may be, for example, a smoothing operation using a linear or high-order polynomial or a neighborhood domain moving root mean square or a local optimal surface regression. In an implementation scenario, one of the aforementioned two three-dimensional reconstructed surface volumes is a three-dimensional reconstructed surface volume of bone tissue (for example Figure 3 As shown in (a) in the figure), it can be used for subsequent calculations of surgical planning in the embodiment of the present application, and the other is a three-dimensional reconstructed surface body including skin and bone tissue, which can be used for subsequent modeling of percutaneous surgical guides.

[0044] In an implementation scenario, the three-dimensional reconstructed surface volume of the subject's foot can be expressed by the following formula:

[0045]

[0046] in, represents the 3D point cloud data in the foot CT image, H + (·) represents the transformation function that converts the three-dimensional point cloud data in the foot CT image into a three-dimensional Boolean matrix. Filter (·) represents the surface point set filter, such as the contour method or alpha type method to extract the surface point set in the three-dimensional point data. represents the spatial scaling matrix, Denotes the triangulation function. Based on the above formula (1), the three-dimensional reconstructed surface volume can be obtained: This includes surface point set information and triangulation triangle surface information.

[0047] According to the three-dimensional reconstructed surface body obtained as described above, at step S203, the hallux valgus affected side is identified based on the three-dimensional reconstructed surface body to obtain the hallux valgus affected side of the subject. In an implementation scenario, the minimum three-dimensional rectangular bounding box of the hallux valgus affected side can be identified based on the three-dimensional reconstructed surface body, and the three-dimensional reconstructed surface body is cut along the minimum three-dimensional rectangular bounding box to obtain the hallux valgus affected side of the subject. It can be understood that in minimally invasive hallux valgus surgery, the hallux valgus affected side of the subject is the left foot or the right foot. In some embodiments, after determining that the affected side of the subject is the left foot or the right foot, based on the three-dimensional reconstructed surface body of the skin and bone tissue obtained in the above steps, the minimum three-dimensional rectangular bounding box of the affected side is identified by adopting, for example, a manual selection method or an adaptive minimum boundary extraction method. Then, the three-dimensional reconstructed surface body is cut along the minimum three-dimensional rectangular bounding box to obtain the hallux valgus affected side of the subject. That is, the hallux valgus affected side of the subject is the three-dimensional reconstructed surface body (for example, the minimum three-dimensional rectangular bounding box) retained within the minimum three-dimensional rectangular bounding box. Figure 3 Similarly, the 3D reconstructed surface volume of the bone tissue can also be cut according to the minimum 3D rectangular bounding box of the 3D reconstructed surface volume of the skin and bone tissue, and the cut 3D reconstructed surface volume is retained.

[0048] In an implementation scenario, the aforementioned adaptive minimum boundary extraction method can be implemented by the following formula:

[0049]

[0050] in, represents the minimum three-dimensional rectangular bounding box, I 3d represents the 3D reconstructed surface volume, Δx + ,Δy + ,Δz + ,Δx - ,Δy - ,Δz - Indicates the positive and negative directions along x, y, and z. Represents the distance from seed point a0 to That is, starting from the seed point a0, find the minimum distance along the positive (+) and negative (-) directions of x, y, and z to reach the minimum three-dimensional rectangular bounding box. The boundary surface on the bounding box and the 3D reconstructed surface volume I 3d The intersection of is the empty set.

[0051] Further, at step S204, the hallux valgus affected side is converted from the CT coordinate system to the hallux valgus coordinate system to achieve preprocessing of the hallux valgus surgery planning. In one embodiment, the hallux valgus coordinate system can be set based on multiple detection points on the hallux valgus affected side, and then a conversion relationship is established according to the coordinate position of the coordinate vector of the target point on the CT coordinate system on the hallux valgus coordinate system, and then the hallux valgus affected side is converted from the CT coordinate system to the hallux valgus coordinate system based on the conversion relationship.

[0052] In some embodiments, the aforementioned multiple detection points may include, for example, the lowest point of the first sesamoid bone, the lowest point of the fifth sesamoid bone, and the lowest point of the basal bone. Next, the geometric center of the triangle formed by the lowest point of the first sesamoid bone, the lowest point of the fifth sesamoid bone, and the lowest point of the basal bone among the aforementioned multiple detection points is used as the origin, and the unit vector of the perpendicular line from the lowest point of the basal bone to the line connecting the lowest point of the first sesamoid bone and the lowest point of the fifth sesamoid bone is used as the positive direction of the x1 axis, the unit vector of the direction of the line connecting the lowest point of the fifth sesamoid bone to the lowest point of the first sesamoid bone is used as the positive direction of the y1 axis, and the normal vector of the plane where the lowest point of the first sesamoid bone, the lowest point of the fifth sesamoid bone, and the lowest point of the basal bone are located is used as the positive direction of the z1 axis, so as to form a hallux valgus coordinate system (for example Figure 4 shown).

[0053] Based on the hallux valgus coordinate system defined above, the hallux valgus affected side can be converted from the CT coordinate system to the hallux valgus coordinate system. Specifically, first assume that the world coordinate system (i.e., the CT coordinate system) is OXYZ, the local coordinate system (i.e., the hallux valgus coordinate system) is OXYZi, and set the coordinate vector of a point in the world coordinate system The coordinate position in a local coordinate system is Then we get the conversion relationship: Among them W1 -1Represents the multi-coordinate system inverse operation coordinate system conversion matrix. Among them, W1 represents the multi-coordinate system forward operation coordinate system conversion matrix, Represents the unit vector of each coordinate system starting from the origin in the local coordinate system Four-dimensional homogeneous coordinate vector in the world coordinate system. According to the aforementioned conversion relationship, the hallux valgus affected side can be converted from the CT coordinate system to the hallux valgus coordinate system. According to the aforementioned conversion relationship, the hallux valgus affected side can be converted from the CT coordinate system to the hallux valgus coordinate system. Subsequently, by extracting the key bone points in the hallux valgus affected side in the hallux valgus coordinate system, the surgical planning parameters such as osteotomy, reduction, and internal fixation can be calculated, which greatly improves the efficiency and accuracy of surgical planning.

[0054] In combination with the above description, it can be seen that the embodiment of the present application performs pre-processing operations such as three-dimensional reconstruction, hallux valgus affected side identification, and coordinate system conversion on the foot CT image to extract the hallux valgus affected side and convert the hallux valgus affected side from the CT coordinate system to the hallux valgus coordinate system, thereby processing the foot CT image into data that is convenient for subsequent calculation of surgical planning parameters. The surgical planning parameters can be calculated directly based on the pre-processed data, thereby improving the efficiency and accuracy of surgical planning.

[0055] Figure 3 3 is an exemplary schematic diagram showing a 3D reconstructed surface volume and a minimum 3D rectangular bounding box of the hallux valgus affected side identified according to an embodiment of the present application. Figure 3 The three-dimensional reconstructed surface volume is shown in Figure (a). In an implementation scenario, the three-dimensional point cloud data in the foot CT image can be converted into a three-dimensional Boolean matrix, and the surface point set of the three-dimensional point cloud data can be extracted from the three-dimensional Boolean matrix to perform three-dimensional reconstruction of the subject's foot based on the surface point set to obtain the three-dimensional reconstructed surface volume. Specifically, the three-dimensional reconstructed surface volume can be obtained based on the above (1). Then, based on the three-dimensional reconstructed surface volume, for example, a manual selection method or an adaptive minimum boundary extraction method can be used to identify the minimum three-dimensional rectangular bounding box of the affected side, for example Figure 3 As shown in FIG. (b) in FIG. 1 , the adaptive minimum boundary extraction method can be implemented based on the above formula (2). Further, the three-dimensional reconstructed surface volume is cut along the minimum three-dimensional rectangular bounding box to obtain the hallux valgus affected side (eg, left foot) of the subject.

[0056] Figure 4 : is an exemplary schematic diagram showing a hallux valgus coordinate system set according to an embodiment of the present application. Figure 4As shown in , first, multiple detection points can be defined, such as the lowest point a of the first sesamoid bone, the lowest point b of the fifth sesamoid bone, and the lowest point c of the radicular bone. Then, the geometric center of the triangle formed by the lowest point a of the first sesamoid bone, the lowest point b of the fifth sesamoid bone, and the lowest point c of the radicular bone is taken as the origin O1, the unit vector of the perpendicular line from the lowest point c of the radicular bone to the line ab between the lowest point a of the first sesamoid bone and the lowest point b of the fifth sesamoid bone is taken as the positive direction of the x1 axis, the unit vector of the direction of the line from the lowest point b of the fifth sesamoid bone to the lowest point a of the first sesamoid bone is taken as the positive direction of the y1 axis, and the normal vector of the plane where the lowest point a of the first sesamoid bone, the lowest point b of the fifth sesamoid bone, and the lowest point c of the radicular bone are located is taken as the positive direction of the z1 axis, so as to form the hallux valgus coordinate system O1x1y1z1. Further, a conversion relationship is established according to the coordinate position of the coordinate vector of the target point on the CT coordinate system on the hallux valgus coordinate system, and then the affected side of the hallux valgus is converted from the CT coordinate system to the hallux valgus coordinate system based on the conversion relationship.

[0057] Figure 5 2 is an exemplary diagram showing the CT coordinate system of the hallux valgus affected side and the converted hallux valgus coordinate system according to an embodiment of the present application. Figure 5 The middle left picture shows the CT coordinate system of the hallux valgus affected side. Figure 5 The middle right figure shows the hallux valgus coordinate system of the hallux valgus affected side. In an implementation scenario, the hallux valgus affected side can be converted from the CT coordinate system to the hallux valgus coordinate system through the conversion relationship constructed by the coordinate position of the coordinate vector of a point in the world coordinate system in a local coordinate system. Based on the converted hallux valgus coordinate system, the subsequent surgical planning parameters such as osteotomy, reduction and internal fixation can be calculated in the hallux valgus coordinate system.

[0058] As an example, by extracting the bone key points in the hallux valgus affected side in the above-mentioned hallux valgus coordinate system, such as the boundary point of the distal articular surface of the first metatarsal, the boundary point of the distal section of the first metatarsal shaft, the boundary point of the proximal section of the first metatarsal shaft, the boundary point of the distal section of the second metatarsal shaft, and the boundary point of the proximal section of the second metatarsal shaft. Further, the aforementioned bone key points can be used to calculate the parameters such as osteotomy, reduction, and internal fixation related to the hallux valgus deformity correction operation at the hallux valgus affected side. In some embodiments, the aforementioned reduction parameters may at least include the reduction translation distance, the reduction rotation angle, the internal fixation path, and the internal fixation placement position. In addition, the aforementioned reduction parameters may also include, for example, the placement position and placement vector direction of the first metatarsal distal reduction needle and the first metatarsal proximal reduction needle, and the position and vector direction of the fixed guide hole and the alignment groove at the target tissue in the hallux valgus affected side.

[0059] Taking the calculation of the osteotomy position as an example, the upper surface point and the lower surface point of the distal end of the first metatarsal shaft are calculated based on the bone key points on the hallux valgus affected side, and then the line between the upper surface point and the lower surface point of the distal end of the first metatarsal shaft is used as the osteotomy position related to performing the hallux valgus deformity correction operation.

[0060] Figure 6 6 is an exemplary structural block diagram of a preprocessing device 600 for hallux valgus surgery planning according to an embodiment of the present application. It is understood that the preprocessing device implementing the solution of the present application can be a single device (such as a computing device) or a multifunctional device including various peripheral devices.

[0061] like Figure 6 As shown in , the preprocessing device of the present application may include a central processing unit or central processing unit ("CPU") 611, which may be a general-purpose CPU, a dedicated CPU, or other information processing and program execution unit. Further, the preprocessing device 600 may also include a large-capacity memory 612 and a read-only memory ("ROM") 613, wherein the large-capacity memory 612 may be configured to store various types of data, including various data related to foot CT images, three-dimensional reconstructed surface bodies, hallux valgus affected side, hallux valgus coordinate system, algorithm data, intermediate results, and various programs required to run the preprocessing device 600. ROM 613 may be configured to store data and instructions required for power-on self-test of the preprocessing device 600, initialization of various functional modules in the system, basic input / output drivers of the system, and booting the operating system.

[0062] Optionally, the preprocessing device 600 may also include other hardware platforms or components, such as the tensor processing unit ("TPU") 614, graphics processing unit ("GPU") 615, field programmable gate array ("FPGA") 616, and machine learning unit ("MLU") 617 shown. It is understood that although a variety of hardware platforms or components are shown in the preprocessing device 600, they are merely exemplary and not restrictive, and those skilled in the art may add or remove corresponding hardware according to actual needs. For example, the preprocessing device 600 may only include a CPU, related storage devices, and interface devices to implement the preprocessing method for hallux valgus surgery planning of the present application.

[0063] In some embodiments, in order to facilitate the transmission and interaction of data with an external network, the pre-processing device 600 of the present application further includes a communication interface 618, so that it can be connected to a local area network / wireless local area network ("LAN / WLAN") 605 through the communication interface 618, and then connected to a local server 606 or to the Internet ("Internet") 607 through the LAN / WLAN. Alternatively or additionally, the pre-processing device 600 of the present application can also be directly connected to the Internet or a cellular network through the communication interface 618 based on wireless communication technology, such as wireless communication technology based on the third generation ("3G"), the fourth generation ("4G") or the fifth generation ("5G") of the 3rd generation ("3G"), the fourth generation ("4G") or the fifth generation ("5G") of the 5th ...

[0064] The peripheral devices of the pre-processing device 600 may include a display device 602, an input device 603 and a data transmission interface 604. In one embodiment, the display device 602 may include, for example, one or more speakers and / or one or more visual displays, which are configured to perform voice prompts and / or image video display on the pre-processing for the hallux valgus surgery planning of the present application. The input device 603 may include other input buttons or controls such as a keyboard, a mouse, a microphone, a gesture capture camera, etc., which are configured to receive input and / or user instructions of audio data. The data transmission interface 604 may include, for example, a serial interface, a parallel interface or a universal serial bus interface ("USB"), a small computer system interface ("SCSI"), a serial ATA, a FireWire ("FireWire"), a PCI Express and a high-definition multimedia interface ("HDMI"), etc., which are configured to transmit and interact with other devices or systems. According to the scheme of the present application, the data transmission interface 604 can receive the foot CT image of the subject collected from the CT acquisition device, and transmit the foot CT image of the subject or various other types of data or results to the pre-processing device 600.

[0065] The CPU 611, the mass storage 612, the ROM 613, the TPU 614, the GPU 615, the FPGA 616, the MLU 617 and the communication interface 618 of the pre-processing device 600 of the present application can be connected to each other through a bus 619, and data interaction with peripheral devices can be achieved through the bus. In one embodiment, through the bus 619, the CPU 611 can control other hardware components and peripheral devices in the pre-processing device 600.

[0066] Combination of the above Figure 6 The present invention describes a pre-treatment device for hallux valgus surgery planning that can be used to perform the present invention. It should be understood that the device structure or architecture here is only exemplary, and the implementation method and implementation entity of the present invention are not limited thereto, but can be changed without departing from the spirit of the present invention.

[0067] According to the above description in combination with the accompanying drawings, those skilled in the art can also understand that the embodiments of the present application can also be implemented by software programs. Therefore, the present application also provides a computer-readable storage medium, which stores computer-readable instructions for preprocessing of hallux valgus surgery planning. When the computer-readable instructions are executed by one or more processors, they can be used to implement the present application in combination with the accompanying drawings. Figure 2 The pretreatment approach described for surgical planning of hallux valgus foot.

[0068] It should be noted that although the operations of the method of the present application are described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0069] It should be understood that when the terms "first", "second", "third" and "fourth" are used in the claims, the specification and the drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0070] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this application specification and claims, unless the context clearly indicates otherwise, the singular forms of "a", "an" and "the" are intended to include plural forms. It should also be further understood that the term "and / or" used in this application specification and claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0071] Although the implementation methods of the present application are as above, the contents described are only examples adopted to facilitate the understanding of the present application, and are not intended to limit the scope and application scenarios of the present application. Any technician in the technical field described in the present application can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present application, but the scope of patent protection of the present application shall still be subject to the scope defined in the attached claims.

Claims

1. A pretreatment method for hallux valgus surgery planning, comprising: Obtain CT images of the subject's foot; Performing three-dimensional reconstruction of the subject's foot based on the foot CT image to obtain a three-dimensional reconstructed surface volume of the subject's foot; Identify the hallux valgus affected side based on the three-dimensional reconstructed surface volume to obtain the hallux valgus affected side of the subject; as well as The hallux valgus affected side is converted from the CT coordinate system to the hallux valgus coordinate system to achieve preprocessing of the hallux valgus surgery planning.

2. The preprocessing method according to claim 1, wherein the foot CT image comprises three-dimensional point cloud data, and performing three-dimensional reconstruction on the subject's foot based on the foot CT image to obtain a three-dimensional reconstructed surface volume of the subject's foot comprises: Converting the three-dimensional point cloud data in the foot CT image into a three-dimensional Boolean matrix; Extracting a surface point set of the three-dimensional point cloud data from the three-dimensional Boolean matrix; as well as The foot of the subject is three-dimensionally reconstructed based on the surface point set to obtain a three-dimensional reconstructed surface volume of the foot of the subject.

3. The preprocessing method according to claim 2, wherein converting the three-dimensional point cloud data in the foot CT image into a three-dimensional Boolean matrix comprises: Determining a preset grayscale value of a target area in the three-dimensional point cloud data in the foot CT image; Setting a transformation function according to the preset grayscale value; as well as The three-dimensional point cloud data in the foot CT image is converted into the three-dimensional Boolean matrix based on the transformation function.

4. The preprocessing method according to claim 3, wherein extracting the surface point set of the three-dimensional point cloud data from the three-dimensional Boolean matrix comprises: Set surface point set filter based on contour algorithm; as well as The three-dimensional Boolean matrix is ​​filtered using the surface point set filter to extract the surface point set of the three-dimensional point cloud data.

5. The preprocessing method according to claim 4, wherein performing three-dimensional reconstruction on the subject's foot based on the surface point set to obtain a three-dimensional reconstructed surface volume of the subject's foot comprises: The surface point set is meshed using a triangulation function to perform three-dimensional reconstruction on the subject's foot, thereby obtaining a three-dimensional reconstructed surface volume of the subject's foot.

6. The pretreatment method according to any one of claims 1 to 5, further comprising: A scaling operation and / or a smoothing operation is performed on the three-dimensional reconstructed surface volume.

7. The preprocessing method according to claim 6, wherein the three-dimensional reconstructed surface volume is represented by the following formula: in, I 3d represents the three-dimensional reconstructed surface volume, represents the three-dimensional point cloud data, H + (·) represents the transformation function, filter(·) represents the surface point set filter, represents the spatial scaling matrix, Denotes the triangulation function.

8. The preprocessing method according to claim 1, wherein identifying the hallux valgus affected side based on the three-dimensional reconstructed surface volume to obtain the hallux valgus affected side of the subject comprises: Identify a minimum three-dimensional rectangular bounding box of the hallux valgus affected side based on the three-dimensional reconstructed surface volume; as well as The three-dimensional reconstructed surface volume is cut along the minimum three-dimensional rectangular boundary box to obtain the hallux valgus affected side of the subject.

9. The preprocessing method according to claim 8, wherein identifying the minimum three-dimensional rectangular bounding box of the hallux valgus affected side based on the three-dimensional reconstructed surface volume comprises: The minimum three-dimensional rectangular bounding box of the hallux valgus affected side is identified by the following formula: in, represents the minimum three-dimensional rectangular bounding box, I 3d represents the three-dimensional reconstructed surface volume, Δx + ,Δy + ,Δz + ,Δx - ,Δy - ,Δz - Indicates the positive and negative directions along x, y, and z. Represents the distance from seed point a0 to The bounding faces on the bounding box on , Φ represents the empty set.

10. The preprocessing method according to claim 1, wherein converting the hallux valgus affected side from a CT coordinate system to a hallux valgus coordinate system comprises: Setting a hallux valgus coordinate system based on a plurality of detection points on the hallux valgus affected side; Establishing a conversion relationship according to the coordinate position of the coordinate vector of the target point on the CT coordinate system on the hallux valgus coordinate system; as well as The hallux valgus affected side is transformed from the CT coordinate system to the hallux valgus coordinate system based on the transformation relationship.

11. A pretreatment device for hallux valgus surgery planning, comprising: processor; as well as A memory storing program instructions for preprocessing of hallux valgus surgery planning. When the program instructions are executed by the processor, the preprocessing device implements the method according to any one of claims 1 to 10.

12. A computer-readable storage medium having stored thereon computer-readable instructions for pre-processing of hallux valgus surgery planning, wherein when the computer-readable instructions are executed by one or more processors, the method according to any one of claims 1 to 10 is implemented.

Images