Methods, systems, electronic devices, and storage media for determining the theoretical shape of a cone.

Abstract

This disclosure provides a method, system, electronic device, and storage medium for determining the theoretical shape of a vertebra. The method includes: acquiring a vertebral image; using preset edge processing rules to identify and process each edge of the vertebral body in the image to obtain the true edge line of each edge; forming a closed shape based on each true edge line, which serves as the true edge shape of the vertebral body; and generating a bounding rectangle of the true edge shape based on the true leading edge line, the true trailing edge line, and the true edge shape, which serves as the theoretical shape of the vertebral body. By applying corresponding preset edge processing rules to different edges of the vertebral body, each actual edge line of the vertebral body is automatically, quickly, and accurately extracted. Then, a closed quadrilateral is obtained from the actual edge lines, forming the corresponding bounding rectangle, which serves as the theoretical shape of the vertebral body in the image. This ensures the accuracy, efficiency, and rationality of determining the theoretical shape of the vertebral body.

Description

Technical Field

[0001] This disclosure relates to the field of medical imaging technology, and in particular to a method, system, electronic device, and storage medium for determining the theoretical shape of a vertebral body. Background Technology

[0002] Currently, the theoretical shape recognition of vertebrae in vertebral images is generally achieved by constructing a large amount of model training data to train the corresponding shape preset model; however, this method has problems such as complex data processing and low prediction accuracy; or it is based on manual annotation to extract the theoretical shape of the vertebrae, but this method obviously has problems such as low recognition efficiency, very high manual input cost, and easy error, thus failing to meet the recognition needs of theoretical scenarios. Summary of the Invention

[0003] The technical problem to be solved by this disclosure is to overcome the above-mentioned defects in the prior art and to provide a method, system, electronic device and storage medium for determining the theoretical shape of a cone.

[0004] This disclosure solves the above-mentioned technical problems through the following technical solution:

[0005] This disclosure provides a method for determining the theoretical shape of a cone body, the method comprising:

[0006] Acquire vertebral body images;

[0007] Using preset edge processing rules, each edge of the vertebra in the vertebral body image is identified and processed to obtain the true edge line corresponding to each edge;

[0008] The real edge lines include the real leading edge line, the real trailing edge line, the real upper edge line, and the real lower edge line;

[0009] Based on each of the real edge lines, a closed shape is formed and used as the real edge shape corresponding to the cone body;

[0010] Based on the true leading edge line, the true trailing edge line, and the true edge pattern, a bounding rectangle of the true edge pattern is generated, and the bounding rectangle is used as the theoretical shape of the cone.

[0011] Preferably, the step of generating the bounding rectangle of the true edge pattern based on the true leading edge line, the true trailing edge line, and the true edge pattern, and using the bounding rectangle as the theoretical shape of the cone, includes:

[0012] The longer line segment between the true leading edge line and the true trailing edge line is selected as the width of the circumscribed rectangle.

[0013] Wherein, the true leading edge line and the true trailing edge line are parallel to each other;

[0014] The distance between the real leading edge line and the real trailing edge line is taken as the length of the circumscribed rectangle.

[0015] Based on the width and length sides, the bounding rectangle of the real edge graphic is generated, and the bounding rectangle is used as the theoretical shape of the cone.

[0016] Preferably, the step of using preset edge processing rules to identify and process each edge of the vertebral body in the vertebral body image to obtain the true edge line corresponding to each edge includes:

[0017] Obtain the edge association information of each edge of the vertebral body in the vertebral body image;

[0018] Determine whether the edge association information meets the corresponding preset conditions. If it does, then use the matching preset edge processing rules to process the edge association information to generate the real edge line corresponding to each edge.

[0019] Different edges correspond to different preset conditions and preset edge processing rules.

[0020] Preferably, for the posterior edge of the vertebral body, the edge association information is posterior edge information;

[0021] The step of determining whether the edge association information meets the corresponding preset conditions, and if so, processing the edge association information using the matching preset edge processing rules to generate the real edge line corresponding to each edge, includes:

[0022] Based on the trailing edge information, determine whether there is a ghosting region in the vertebral body image; if so, obtain multiple initial trailing edge curves.

[0023] Identify the pedicle region in the vertebral body image;

[0024] Obtain the initial posterior edge curve that is furthest from the pedicle region, and use it as the target posterior edge curve;

[0025] Obtain the first upper endpoint and the first lower endpoint corresponding to the trailing edge curve of the target;

[0026] The first line segment formed by connecting the first upper endpoint and the first lower endpoint;

[0027] Based on the first line segment, the true posterior edge line of the vertebral body is obtained.

[0028] Preferably, for the upper edge of the vertebral body, the edge association information is the upper edge information;

[0029] The step of determining whether the edge association information meets the corresponding preset conditions, and if so, processing the edge association information using the matching preset edge processing rules to generate the real edge line corresponding to each edge, includes:

[0030] Based on the upper edge information, determine whether there are multiple initial upper edge curves. If so, obtain a first target curve within a first preset position range between the two initial upper edge curves located at the outermost and innermost edges, and obtain the actual upper edge line based on the obtained first target curve.

[0031] If there is only one initial upper edge curve, then the actual upper edge line is obtained based on the initial upper edge curve;

[0032] And / or,

[0033] For the lower edge of the vertebral body, the edge association information is the lower edge information;

[0034] The step of determining whether the edge association information meets the corresponding preset conditions, and if so, processing the edge association information using a matching preset edge processing rule to generate the real edge line corresponding to each edge, includes:

[0035] Based on the lower edge information, determine whether there are multiple initial lower edge curves. If so, obtain a second target curve within a second preset position range between the two innermost and outermost initial lower edge curves, and obtain the real lower edge line based on the obtained second target curve.

[0036] If there is only one initial lower edge curve, then the actual lower edge line is obtained based on the initial lower edge curve.

[0037] Preferably, if the vertebral body image contains two initial upper edge curves, the step of obtaining a first target curve within a first preset position range between the two initial upper edge curves located at the outermost and innermost edges, and obtaining the true upper edge line based on the obtained first target curve, includes:

[0038] A first target curve is formed in the region between one-third and two-thirds of the position between the two initial upper edge curves, and the actual upper edge line is obtained based on the formed first target curve;

[0039] The trend of the first target curve lies between the trends of the two initial upper edge curves.

[0040] And / or,

[0041] When the vertebral image contains two initial lower edge curves, the step of obtaining a second target curve within a second preset position range between the two innermost and outermost initial lower edge curves, and obtaining the true lower edge line based on the obtained second target curve, includes:

[0042] A second target curve is formed in the region between one-third and two-thirds of the position between the two initial lower edge curves, and the true lower edge line is obtained based on the formed second target curve;

[0043] The trend of the second target curve lies between the trends of the two initial lower edge curves.

[0044] Preferably, the first target curve is the midline between the two initial upper edge curves;

[0045] And / or,

[0046] The second target curve is the midline between the two initial lower edge curves.

[0047] Preferably, the step of obtaining the true posterior edge line of the vertebral body based on the first line segment includes:

[0048] Obtain the first intersection point of the straight line containing the first line segment with the first target curve, and the second intersection point with the second target curve;

[0049] The second line segment between the first intersection point and the second intersection point is taken as the true posterior edge line of the vertebral body;

[0050] Wherein, the first intersection point is the first left endpoint of the actual upper edge line, and the second intersection point is the second left endpoint of the actual lower edge line.

[0051] Preferably, for the anterior edge of the vertebral body, the edge association information is the anterior edge information;

[0052] The step of determining whether the edge association information meets the corresponding preset conditions, and if so, processing the edge association information using the matching preset edge processing rules to generate the real edge line corresponding to each edge, includes:

[0053] The initial anterior curve of the vertebral body is obtained based on the anterior edge information;

[0054] Determine whether there is a concave curvature greater than a first set threshold on the initial anterior edge curve. If so, determine that there is osteophyte formation at the anterior edge of the vertebral body.

[0055] Based on the vertex of the bend, a tangent is formed using a preset slope to obtain an initial straight line;

[0056] Wherein, the preset slope is equal to the first slope of the first line segment;

[0057] Obtain the third intersection point of the initial straight line with the first target curve and the fourth intersection point with the second target curve;

[0058] The third line segment between the third intersection point and the fourth intersection point is taken as the true anterior edge line of the vertebral body;

[0059] The third intersection point is the first right endpoint of the actual upper edge line, and the fourth intersection point is the second right endpoint of the actual lower edge line.

[0060] Preferably, the method for determining the theoretical shape of the cone further includes:

[0061] When it is determined that there is no concave curvature greater than a first set threshold on the initial anterior edge curve, it is determined that there is no osteophyte formation on the anterior edge of the vertebral body, and the initial anterior edge curve is taken as the target anterior edge curve;

[0062] Obtain the fifth intersection point of the target leading edge curve with the actual upper edge line and the sixth intersection point with the actual lower edge line;

[0063] The connecting curve between the fifth intersection point and the sixth intersection point is taken as the true anterior edge line of the vertebral body;

[0064] Wherein, the fifth intersection point is the first right endpoint of the actual upper edge line, and the sixth intersection point is the second right endpoint of the actual lower edge line;

[0065] or,

[0066] Obtain the second upper endpoint and the second lower endpoint corresponding to the leading edge curve of the target;

[0067] The third line segment formed by connecting the second upper endpoint and the second lower endpoint;

[0068] Adjust the slope of the second line segment to the first slope to obtain the fourth line segment;

[0069] Obtain the seventh intersection point of the straight line containing the third line segment with the actual upper edge line and the eighth intersection point with the actual lower edge line;

[0070] The fifth line segment between the seventh intersection point and the eighth intersection point is taken as the true anterior edge line of the vertebral body;

[0071] The seventh intersection point is the first right endpoint of the actual upper edge line, and the eighth intersection point is the second right endpoint of the actual lower edge line.

[0072] Preferably, the step of obtaining the true upper edge line based on the acquired first target curve includes:

[0073] The curve between the first left endpoint and the first right endpoint is taken as the true upper edge line;

[0074] And / or,

[0075] The step of obtaining the true lower edge line based on the acquired second target curve includes:

[0076] The curve between the second left endpoint and the second right endpoint is taken as the true lower edge line.

[0077] Preferably, the step of acquiring vertebral body images includes:

[0078] Acquire lateral radiographs of the thoracic and lumbar spine based on X-ray images generated by an X-ray machine (the device that produces X-ray films);

[0079] The lateral radiograph image is segmented to obtain the vertebral body image.

[0080] This disclosure also provides a system for determining the theoretical shape of a cone, the system comprising:

[0081] Vertebral body image acquisition module, used to acquire vertebral body images;

[0082] The real edge line acquisition module is used to identify and process each edge of the vertebra in the vertebral body image using preset edge processing rules, so as to obtain the real edge line corresponding to each edge.

[0083] The real edge lines include the real leading edge line, the real trailing edge line, the real upper edge line, and the real lower edge line;

[0084] The real edge graphic acquisition module is used to form a closed graphic based on each of the real edge lines, and use it as the real edge graphic corresponding to the cone.

[0085] The theoretical shape acquisition module is used to generate the bounding rectangle of the real edge pattern based on the real leading edge line, the real trailing edge line and the real edge pattern, and use the bounding rectangle as the theoretical shape of the cone.

[0086] This disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for determining the theoretical shape of the cone.

[0087] This disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for determining the theoretical shape of a cone.

[0088] Based on common knowledge in the field, the preferred conditions described can be combined arbitrarily to obtain the preferred embodiments of this disclosure.

[0089] The positive and progressive effects of this disclosure are as follows:

[0090] In this disclosure, different edges of the vertebral body are processed using corresponding preset edge processing rules to automatically, quickly and accurately extract each actual edge line of the vertebral body, ensuring the accuracy and efficiency of segmenting the actual shape of the vertebral body from the vertebral body image; then, the corresponding circumscribed rectangle is formed by the real anterior edge line, the real posterior edge line, and the quadrilateral closed by the four real edge lines, which serves as the theoretical shape of the vertebral body in the vertebral body image, thereby ensuring the accuracy and rationality of determining the theoretical shape of the vertebral body. Attached Figure Description

[0091] Figure 1 This is a flowchart of the method for determining the theoretical shape of the cone body according to Embodiment 1 of this disclosure.

[0092] Figure 2 This is a schematic diagram of the original vertebral body image in Embodiment 1 of this disclosure.

[0093] Figure 3 This is a schematic diagram of the actual graphic of the vertebral body image in Embodiment 1 of this disclosure.

[0094] Figure 4 This is a first flowchart of the method for determining the theoretical shape of the cone body according to Embodiment 2 of this disclosure.

[0095] Figure 5 This is a second flowchart of the method for determining the theoretical shape of the cone body according to Embodiment 2 of this disclosure.

[0096] Figure 6 This is a schematic diagram of the posterior edge of the vertebral body image in Embodiment 1 of this disclosure.

[0097] Figure 7 This is the third flowchart of the method for determining the theoretical shape of the cone body in Embodiment 2 of this disclosure.

[0098] Figure 8 This is the fourth flowchart of the method for determining the theoretical shape of the cone body in Embodiment 2 of this disclosure.

[0099] Figure 9 This is a schematic diagram showing that the upper and lower edges of the vertebral body exist on both sides in the vertebral body image of Embodiment 2 of this disclosure.

[0100] Figure 10 This is a schematic diagram of the midline at the upper and lower edges of the vertebral body in Embodiment 2 of this disclosure.

[0101] Figure 11This is the fifth flowchart of the method for determining the theoretical shape of the cone body in Embodiment 2 of this disclosure.

[0102] Figure 12 This is a schematic diagram of the leading edge of a vertebral body image according to Embodiment 2 of this disclosure.

[0103] Figure 13 This is a schematic diagram of the module of the method for determining the theoretical shape of the cone body according to Embodiment 3 of this disclosure.

[0104] Figure 14 This is a schematic diagram of the structure of an electronic device that implements the method for determining the theoretical shape of a cone in Embodiment 5 of this disclosure. Detailed Implementation

[0105] The present disclosure is further illustrated below by way of embodiments, but the present disclosure is not limited to the scope of the embodiments described herein.

[0106] Example 1

[0107] like Figure 1 As shown, the method for determining the theoretical shape of the vertebral body in this embodiment includes:

[0108] S101. Obtain vertebral body images;

[0109] The vertebral body image is a segmented image obtained from the initial image acquired from the X-ray machine. The vertebral body image includes the vertebral body and the pedicles connected to the vertebral body.

[0110] S102. Using preset edge processing rules, each edge of the vertebra in the vertebral body image is identified and processed to obtain the real edge line corresponding to each edge.

[0111] Among them, such as Figure 2 The image of the vertebral body shown includes the anterior, posterior, superior, and inferior margins of the vertebral body.

[0112] The true edge line includes the true leading edge line, the true trailing edge line, the true upper edge line, and the true lower edge line;

[0113] Furthermore, this processing method does not rely on complex processes such as model training, reducing the initial data preparation and processing operations, and greatly optimizing the process of recognizing the actual shape of the vertebrae in vertebral images.

[0114] S103. Based on each real edge line, form a closed shape and use it as the real edge shape corresponding to the cone.

[0115] Based on the four actual edge lines—the front edge, rear edge, upper edge, and lower edge—a closed quadrilateral is automatically formed to obtain the actual edge pattern corresponding to the cone body. For example... Figure 2 The image shown is an unprocessed image of the vertebral body; as shown... Figure 3As shown, the quadrilateral (black frame) is the actual edge shape of the cone.

[0116] S104. Based on the true leading edge line, the true trailing edge line, and the true edge shape, generate the bounding rectangle of the true edge shape, and use the bounding rectangle as the theoretical shape of the cone.

[0117] In this embodiment, different edges of the vertebral body are processed using corresponding preset edge processing rules to automatically, quickly, and accurately extract each actual edge line of the vertebral body, ensuring the accuracy and efficiency of segmenting the actual shape of the vertebral body from the vertebral body image. Then, the corresponding circumscribed rectangle is formed by the real leading edge line, the real trailing edge line, and the quadrilateral closed by the four real edge lines, which serves as the theoretical shape of the vertebral body in the vertebral body image, thereby ensuring the accuracy and rationality of determining the theoretical shape of the vertebral body.

[0118] Example 2

[0119] The method for determining the theoretical shape of the vertebral body in this embodiment is a further improvement on Embodiment 1, specifically:

[0120] In a feasible solution, such as Figure 4 As shown, step S104 includes:

[0121] S1041. Select the longer line segment between the real leading edge and the real trailing edge as the width of the circumscribed rectangle.

[0122] Among them, the true leading edge line and the true trailing edge line are parallel to each other;

[0123] S1042. Use the distance between the real leading edge and the real trailing edge as the length of the circumscribed rectangle.

[0124] S1043. Generate the bounding rectangle of the real edge graphic based on the width and length sides, and use the bounding rectangle as the theoretical shape of the cone.

[0125] In this scheme, the theoretical shape of the cone is predefined as a rectangle, the width of which is the larger of the front and rear edges. Based on this width, the generated actual closure shape (or real edge shape) is circumscribed by a rectangle. This circumscribed rectangle serves as the theoretical shape of the cone, ensuring the accuracy of the determination of the theoretical shape of the cone.

[0126] In one feasible embodiment, step S102 includes:

[0127] S1021. Obtain the edge association information of each edge of the vertebral body in the vertebral body image;

[0128] Edge association information includes all information that can characterize and describe each corresponding edge, including but not limited to whether there are multiple curves and curve position information.

[0129] S1022. Determine whether the edge association information meets the corresponding preset conditions. If it does, proceed to step S1023.

[0130] S1023. The edge association information is processed using a matching preset edge processing rule to generate the real edge line corresponding to each edge.

[0131] Different edges correspond to different preset conditions and preset edge processing rules.

[0132] That is, for the leading edge, trailing edge, upper edge, and lower edge, each has its own characteristics due to its different presentation state. Pre-built matching preset conditions are used to automatically identify the actual situation of the corresponding edge, and then the matching preset edge processing rules are used for targeted processing to extract the real edge line corresponding to each edge.

[0133] In one feasible approach, for the posterior edge of the vertebral body, the edge association information is the posterior edge information; where the posterior edge is the edge of the vertebral body at the junction with the pedicle.

[0134] like Figure 5 As shown, step S1022 includes:

[0135] S10221. Determine whether there is a ghosting region in the vertebral body image based on the posterior edge information. If so, proceed to step S1023.

[0136] The presence of a ghosting region is determined by the presence of multiple initial trailing edge curves. If there are ≥2 initial trailing edge curves, a ghosting region will be formed, meaning the actual position of the trailing edge cannot be directly determined.

[0137] Step S1023 includes:

[0138] S102311. Obtain multiple initial trailing edge curves;

[0139] S102312. Identify the pedicle region in the vertebral body image;

[0140] S102313. Obtain the initial posterior edge curve that is furthest from the pedicle region, and use it as the target posterior edge curve;

[0141] Specifically, each irregular initial trailing edge curve can be unified into a line segment shape, such as... Figure 6 As shown, the distances between different line segments and the pedicle region are calculated to obtain the initial posterior edge curve that is furthest from the pedicle region.

[0142] S102314. Obtain the first upper endpoint and the first lower endpoint corresponding to the trailing edge curve of the target;

[0143] The first upper endpoint is the intersection of the target trailing edge curve and the innermost curve at the upper edge of the vertebral body; the first lower endpoint is the intersection of the target trailing edge curve and the innermost curve at the lower edge of the vertebral body. That is, the target trailing edge curve intersects with other curves only at the endpoints, and there are no other intersections with other curves elsewhere.

[0144] S102315, The first line segment formed by connecting the first upper endpoint and the first lower endpoint;

[0145] S102316. Based on the first line segment, obtain the true posterior edge line of the vertebral body.

[0146] In this scheme, it is determined whether there is more than one initial posterior edge curve within the area where the posterior edge is located. If so, it is determined that there is a ghosting. At this time, it is necessary to call the preset edge processing rules for posterior edge recognition for matching processing. That is, select the initial posterior edge curve that is farthest from the pedicle region, and then obtain the line segment formed by connecting the two endpoints of the initial posterior edge curve. Use this line segment as a reference to finally determine the true posterior edge line of the vertebral body. This effectively ensures the recognition accuracy of the true posterior edge line, and thus also ensures the recognition accuracy of other remaining edge lines.

[0147] In addition, when there is no ghosting region, an initial trailing edge curve in the region where the trailing edge is located is directly taken as the target trailing edge curve. Then, the upper and lower endpoints of the target trailing edge curve are obtained to form a line segment, and finally the true trailing edge line of the vertebral body is obtained. The specific implementation process is similar to that described above, so it will not be repeated here.

[0148] In a feasible solution, for the upper edge of the vertebral body, the edge association information is the upper edge information;

[0149] like Figure 7 As shown, step S1022 includes:

[0150] S10222. Determine whether there are multiple initial upper edge curves based on the upper edge information. If so, proceed to step S1023.

[0151] Step S1023 includes:

[0152] S102321. Obtain a first target curve within a first preset position range between the two initial upper edge curves located on the outermost and innermost sides, and obtain the real upper edge line based on the obtained first target curve.

[0153] The first target curve can be obtained through direct selection or automatic generation.

[0154] In this scheme, when there are multiple initial upper edge curves, one curve located in the middle range is selected as the first target curve, and the true upper edge line of the vertebra is finally determined based on the first target curve. This avoids the situation where the true upper edge line cannot be identified based on a curve located on the outer or inner side, thus effectively ensuring the accuracy of the acquisition of the true upper edge line.

[0155] In a feasible solution, if there is only one initial upper edge curve, the actual upper edge line is obtained based on the initial upper edge curve.

[0156] In this scheme, if there is only one initial upper edge curve, it means that there is no interference at the upper edge of the vertebral body. The true upper edge line of the vertebral body is determined directly based on the first target curve, so as to achieve timely and accurate identification of the situation and thus ensure the accuracy of the acquisition of the true upper edge line.

[0157] In a feasible solution, for the lower edge of the vertebral body, the edge association information is the lower edge information;

[0158] like Figure 8 As shown, step S1022 includes:

[0159] S10223. Determine whether there are multiple initial lower edge curves based on the lower edge information. If so, proceed to step S1023.

[0160] Step S1023 includes:

[0161] S102331. Obtain a second target curve within a second preset position range between the two initial lower edge curves located at the innermost and outermost edges, and obtain the actual lower edge line based on the obtained second target curve;

[0162] The second target curve can be obtained through direct selection or automatic generation.

[0163] In this scheme, when there are multiple initial lower edge curves, one curve located in the middle range is obtained as the second target curve, and the true lower edge line of the vertebra is finally determined based on the second target curve. This avoids the situation where the true lower edge line cannot be identified based on the curve located on the outer side or the inner side, thus effectively ensuring the accuracy of the acquisition of the true lower edge line.

[0164] In a feasible solution, if there is only one initial lower edge curve, the actual lower edge line is obtained based on the initial lower edge curve.

[0165] In this scheme, if there is only one initial lower edge curve, it means that there is no interference at the lower edge of the vertebral body. The true lower edge line of the vertebral body is determined directly based on the first target curve, so as to realize timely and accurate identification of the situation and thus ensure the accuracy of obtaining the true lower edge line.

[0166] In one feasible embodiment, step S102321 includes:

[0167] A first target curve is formed within a region of one-third to two-thirds of the area between the two initial upper edge curves, and the true upper edge line is obtained based on the formed first target curve.

[0168] The trend of the first target curve lies between the trends of the two initial upper edge curves;

[0169] In this plan, such as Figure 9 As shown, to determine whether the upper edge has two sides, when there are two initial upper edge curves (curves 1 and 2 marked in the figure), an arbitrary curve is generated between 1 / 3 and 2 / 3 of the distance between the two initial lower edge curves. This curve serves as the first target curve, and the true upper edge line of the vertebra is ultimately determined based on this first target curve. This avoids determining the true upper edge line based on a curve located on the outermost or innermost side, which could compromise the accuracy of the true upper edge line recognition. This effectively ensures the accuracy of obtaining the true upper edge line. Of course, the area where the first target curve is located can be further narrowed or expanded according to the actual needs of the scenario.

[0170] In one feasible embodiment, step S102331 includes:

[0171] A second target curve is formed within a region of one-third to two-thirds of the area between the two initial lower edge curves, and the true lower edge line is obtained based on the formed second target curve;

[0172] The trend of the second target curve lies between the trends of the two initial lower edge curves.

[0173] In this plan, such as Figure 9 As shown, to determine whether the lower edge has two sides, when two initial lower edge curves exist (curves 3 and 4 marked in the figure), an arbitrary curve is generated between 1 / 3 and 2 / 3 of the distance between the two initial lower edge curves to serve as the second target curve. This second target curve is then used as a reference to ultimately determine the true lower edge line of the vertebral body. This avoids determining the true lower edge line based on a curve located on the outermost or innermost side, which could compromise the accuracy of the true lower edge line recognition. This effectively ensures the accuracy of obtaining the true lower edge line. Of course, the area where the second target curve is located can be further narrowed or expanded according to the actual needs of the scenario.

[0174] In a feasible approach, the first target curve is the midline between the two initial upper edge curves;

[0175] like Figure 10 As shown, the midline between the two initial upper edge curves (the curve between curves 1 and 2 marked in the figure) is taken as the first target curve, and the overall undulation of the first target curve lies between the two initial upper edge curves.

[0176] In this scheme, based on the midline between the two initial upper edge curves, the accuracy of determining the true upper edge line can be further improved, thereby ensuring the accuracy of obtaining other edge lines.

[0177] In one feasible approach, the second target curve is the midline between the two initial lower edge curves.

[0178] like Figure 10 As shown, the midline between the two initial lower edge curves (the curve between curves 3 and 4 marked in the figure) is taken as the second target curve, and the overall undulation of the second target curve lies between the two initial lower edge curves.

[0179] In this scheme, based on the midline between the two initial lower edge curves, the accuracy of determining the true lower edge line can be further improved, thereby ensuring the accuracy of obtaining other edge lines.

[0180] Preferably, the upper and lower edges are processed using the same edge processing rules to ensure that the final identified real upper and lower edges better meet the actual processing requirements.

[0181] In one feasible embodiment, step S102316 includes:

[0182] Obtain the first intersection point of the straight line containing the first line segment with the first target curve, and the second intersection point with the second target curve;

[0183] The second line segment between the first and second intersection points is taken as the true posterior edge line of the vertebral body;

[0184] The first intersection point is the first left endpoint of the actual upper edge line, and the second intersection point is the second left endpoint of the actual lower edge line.

[0185] In this scheme, based on the first line segment, the curve where the real upper edge line is located, and the curve where the real lower edge line is located, the intersection points between the straight line where the first line segment is located and the first target curve and the second target district are automatically obtained, so as to finally determine the two endpoints of the real trailing edge line, thereby ensuring the rationality and accuracy of the acquisition of the real trailing edge line.

[0186] In a feasible solution, for the anterior edge of the vertebral body, the edge association information is the anterior edge information;

[0187] like Figure 11 As shown, step S1022 includes:

[0188] S10224. Obtain the initial anterior curve of the vertebral body based on the anterior edge information;

[0189] S10225. Determine whether there is a concave curvature greater than the first set threshold on the initial leading edge curve. If so, proceed to step S1023.

[0190] For example, if there is a concave curvature greater than 15° on the curve, then it is determined that there is bone hyperplasia at that curvature.

[0191] Step S1023 includes:

[0192] S102341. It was determined that there was osteophyte formation at the anterior margin of the vertebral body;

[0193] S102342. Based on the vertex of the bend, perform tangent processing using a preset slope to obtain an initial straight line;

[0194] Among them, such as Figure 12 As shown, the preset slope is equal to the first slope of the first line segment;

[0195] S102343, Obtain the third intersection point of the initial straight line with the first target curve and the fourth intersection point with the second target curve;

[0196] S102344. Take the third line segment between the third and fourth intersection points as the true anterior edge line of the vertebral body;

[0197] The third intersection point is the first right endpoint of the actual upper edge line, and the fourth intersection point is the second right endpoint of the actual lower edge line.

[0198] In this scheme, the presence of osteophytes is automatically identified by analyzing the initial leading edge curve. If osteophytes are present, the influence of osteophytes on the determination of the actual shape of the vertebral body needs to be eliminated. Targeted matching processing is performed on cases with osteophytes to ensure the accuracy of the identification of the true leading edge line.

[0199] In one feasible approach, the method for determining the theoretical shape of the cone also includes:

[0200] When it is determined that there is no concave curvature greater than the first set threshold on the initial anterior edge curve, it is determined that there is no osteophyte formation at the anterior edge of the vertebral body, and the initial anterior edge curve is taken as the target anterior edge curve.

[0201] Obtain the fifth intersection point of the target leading edge curve with the true upper edge line and the sixth intersection point with the true lower edge line;

[0202] The connecting curve between the fifth and sixth intersection points is taken as the true anterior edge line of the vertebral body;

[0203] Among them, the fifth intersection point is the first right endpoint of the actual upper edge line, and the sixth intersection point is the second right endpoint of the actual lower edge line;

[0204] In one feasible approach, the method for determining the theoretical shape of the cone also includes:

[0205] When it is determined that there is no concave curvature greater than the first set threshold on the initial anterior edge curve, it is determined that there is no osteophyte formation at the anterior edge of the vertebral body, and the initial anterior edge curve is taken as the target anterior edge curve.

[0206] Obtain the second upper endpoint and the second lower endpoint corresponding to the target leading edge curve;

[0207] The third line segment is formed by connecting the second upper endpoint and the second lower endpoint;

[0208] Adjust the slope of the second line segment to the first slope to obtain the fourth line segment;

[0209] Find the seventh intersection point of the line containing the third line segment with the actual upper edge line and the eighth intersection point with the actual lower edge line;

[0210] The fifth line segment between the seventh and eighth intersection points is taken as the true anterior edge line of the vertebral body;

[0211] The seventh intersection point is the first right endpoint of the actual upper edge line, and the eighth intersection point is the second right endpoint of the actual lower edge line.

[0212] In this scheme, when it is determined that there is no osteophyte formation at the anterior edge, the anterior edge is obtained based on the actual imaging results. That is, the initial anterior edge curve is used as the target anterior edge curve, and then the two endpoints of the target anterior edge curve are obtained. Based on the intersection of the straight line containing the line segment between the two endpoints with the real upper edge line and the real lower edge line, the final connecting curve is obtained as the real anterior edge line of the vertebral body, thereby automatically, efficiently and accurately obtaining the real anterior edge line.

[0213] In one feasible approach, the step of obtaining the true upper edge line based on the acquired first target curve includes:

[0214] The curve between the first left endpoint and the first right endpoint is taken as the true upper edge line;

[0215] And / or,

[0216] The steps for obtaining the true lower edge line based on the acquired second target curve include:

[0217] The curve between the second left endpoint and the second right endpoint is taken as the true lower edge line.

[0218] In this scheme, the two endpoints of the curves corresponding to the true upper edge line and the true lower edge line are the intersection points connected to the true front edge line and the true rear edge line, respectively. This ensures that the positions of the two ends of the true upper edge line and the true lower edge line are determined accurately and in a timely manner, and also ensures the efficiency of recognizing the actual shape of the entire vertebral body in the vertebral body image.

[0219] In one feasible embodiment, step S101 includes:

[0220] Obtain lateral radiographs of the thoracic and lumbar vertebrae generated by an X-ray machine; of course, X-ray images of other vertebrae can also be obtained.

[0221] Image segmentation was performed on the lateral radiographs to obtain vertebral body images.

[0222] In this scheme, the lateral radiographs of the thoracic and lumbar vertebrae taken by an X-ray machine are segmented to obtain vertebral images that meet the processing requirements of set size and resolution, so as to ensure the efficiency and reliability of the actual shape extraction and processing of each vertebra in each vertebral image.

[0223] Example 3

[0224] like Figure 13 As shown, the system for determining the theoretical shape of the cone body in this embodiment includes:

[0225] Vertebral body image acquisition module 1 is used to acquire vertebral body images;

[0226] The vertebral body image is a segmented image obtained from the initial image acquired from the X-ray machine. The vertebral body image includes the vertebral body and the pedicles connected to the vertebral body.

[0227] The real edge line acquisition module 2 is used to identify and process each edge of the vertebra in the vertebral body image using preset edge processing rules, so as to obtain the real edge line corresponding to each edge.

[0228] Among them, such as Figure 2 The image of the vertebral body shown includes the anterior, posterior, superior, and inferior margins of the vertebral body.

[0229] The true edge line includes the true leading edge line, the true trailing edge line, the true upper edge line, and the true lower edge line;

[0230] The real edge graphic acquisition module 3 is used to form a closed graphic based on each real edge line, and use it as the real edge graphic corresponding to the cone.

[0231] Based on the four actual edge lines—the front edge, rear edge, upper edge, and lower edge—a closed quadrilateral is automatically formed to obtain the actual edge pattern corresponding to the cone body. For example... Figure 2The image shown is an unprocessed image of the vertebral body; as shown... Figure 3 As shown, the quadrilateral (black frame) is the actual edge shape of the cone.

[0232] The theoretical shape acquisition module 4 is used to generate the bounding rectangle of the real edge shape based on the real leading edge line, the real trailing edge line and the real edge shape, and use the bounding rectangle as the theoretical shape of the cone.

[0233] In this embodiment, different edges of the vertebral body are processed using corresponding preset edge processing rules to automatically, quickly, and accurately extract each actual edge line of the vertebral body, ensuring the accuracy and efficiency of segmenting the actual shape of the vertebral body from the vertebral body image. Then, the corresponding circumscribed rectangle is formed by the real leading edge line, the real trailing edge line, and the quadrilateral closed by the four real edge lines, which serves as the theoretical shape of the vertebral body in the vertebral body image, thereby ensuring the accuracy and rationality of determining the theoretical shape of the vertebral body.

[0234] Example 4

[0235] The system for determining the theoretical shape of the cone body in this embodiment is a further improvement on Embodiment 3, specifically:

[0236] In one feasible solution, the theoretical shape acquisition module 4 includes:

[0237] The width determination module is used to select the longer line segment between the real leading edge line and the real trailing edge line as the width of the circumscribed rectangle.

[0238] Among them, the true leading edge line and the true trailing edge line are parallel to each other;

[0239] The long side determination unit is used to determine the length of the circumscribed rectangle by the distance between the real leading edge and the real trailing edge.

[0240] The theoretical shape acquisition unit is used to generate the bounding rectangle of the real edge graphic based on the width and length side lengths, and use the bounding rectangle as the theoretical shape of the cone.

[0241] In this scheme, the theoretical shape of the cone is predefined as a rectangle, the width of which is the larger of the front and rear edges. Based on this width, the generated actual closure shape (or real edge shape) is circumscribed by a rectangle. This circumscribed rectangle serves as the theoretical shape of the cone, ensuring the accuracy of the determination of the theoretical shape of the cone.

[0242] In one feasible solution, the real edge line acquisition module 2 includes:

[0243] The edge information acquisition unit is used to acquire the edge association information of each edge of the vertebral body in the vertebral body image;

[0244] Edge association information includes all information that can characterize and describe each corresponding edge, including but not limited to whether there are multiple curves and curve position information.

[0245] The judgment unit is used to determine whether the edge association information meets the corresponding preset conditions. If it does, the real edge line acquisition unit is called.

[0246] The real edge line acquisition unit is used to process the edge association information using a matching preset edge processing rule to generate the real edge line corresponding to each edge;

[0247] Different edges correspond to different preset conditions and preset edge processing rules.

[0248] That is, for the leading edge, trailing edge, upper edge, and lower edge, each has its own characteristics due to its different presentation state. Pre-built matching preset conditions are used to automatically identify the actual situation of the corresponding edge, and then the matching preset edge processing rules are used for targeted processing to extract the real edge line corresponding to each edge.

[0249] In one feasible approach, for the posterior edge of the vertebral body, the edge association information is the posterior edge information; where the posterior edge is the edge of the vertebral body at the junction with the pedicle.

[0250] The judgment unit is used to determine whether there is a ghosting region in the vertebral body image based on the posterior edge information. If it exists, the unit that obtains the true edge line is called.

[0251] The presence of a ghosting region is determined by the presence of multiple initial trailing edge curves. If there are ≥2 initial trailing edge curves, a ghosting region will be formed, meaning the actual position of the trailing edge cannot be directly determined.

[0252] The real edge line acquisition unit includes:

[0253] The initial trailing edge curve acquisition sub-unit is used to acquire multiple initial trailing edge curves;

[0254] The region recognition subunit is used to identify the pedicle region in the vertebral body image;

[0255] The target trailing edge curve acquisition sub-unit is used to acquire the initial trailing edge curve that is furthest from the pedicle region, as the target trailing edge curve;

[0256] Specifically, each irregular initial trailing edge curve can be unified into a line segment shape, such as... Figure 6 As shown, the distances between different line segments and the pedicle region are calculated to obtain the initial posterior edge curve that is furthest from the pedicle region.

[0257] The first endpoint acquisition sub-unit is used to acquire the first upper endpoint and the first lower endpoint corresponding to the target trailing edge curve;

[0258] The first upper endpoint is the intersection of the target trailing edge curve and the innermost curve at the upper edge of the vertebral body; the first lower endpoint is the intersection of the target trailing edge curve and the innermost curve at the lower edge of the vertebral body. That is, the target trailing edge curve intersects with other curves only at the endpoints, and there are no other intersections with other curves elsewhere.

[0259] The first line segment acquisition sub-unit is used to form the first line segment by connecting the first upper endpoint and the first lower endpoint;

[0260] The True Trailing Edge Acquisition Sub-unit is used to acquire the true trailing edge of the vertebral body based on the first line segment.

[0261] In this scheme, it is determined whether there is more than one initial posterior edge curve within the area where the posterior edge is located. If so, it is determined that there is a ghosting. At this time, it is necessary to call the preset edge processing rules for posterior edge recognition for matching processing. That is, select the initial posterior edge curve that is farthest from the pedicle region, and then obtain the line segment formed by connecting the two endpoints of the initial posterior edge curve. Use this line segment as a reference to finally determine the true posterior edge line of the vertebral body. This effectively ensures the recognition accuracy of the true posterior edge line, and thus also ensures the recognition accuracy of other remaining edge lines.

[0262] In addition, when there is no ghosting region, an initial trailing edge curve in the region where the trailing edge is located is directly taken as the target trailing edge curve. Then, the upper and lower endpoints of the target trailing edge curve are obtained to form a line segment, and finally the true trailing edge line of the vertebral body is obtained. The specific implementation process is similar to that described above, so it will not be repeated here.

[0263] In a feasible solution, for the upper edge of the vertebral body, the edge association information is the upper edge information;

[0264] The judgment unit is used to determine whether there are multiple initial upper edge curves based on the upper edge information. If they exist, the unit for obtaining the actual edge line is called.

[0265] The real edge line acquisition unit is used to acquire a first target curve within a first preset position range between the two initial upper edge curves located at the outermost and innermost edges, and to obtain the real upper edge line based on the acquired first target curve.

[0266] The first target curve can be obtained through direct selection or automatic generation.

[0267] In this scheme, when there are multiple initial upper edge curves, one curve located in the middle range is selected as the first target curve, and the true upper edge line of the vertebra is finally determined based on the first target curve. This avoids the situation where the true upper edge line cannot be identified based on a curve located on the outer or inner side, thus effectively ensuring the accuracy of the acquisition of the true upper edge line.

[0268] The real edge line acquisition unit is also used to obtain the real upper edge line based on the initial upper edge curve if only one initial upper edge curve exists.

[0269] In this scheme, if there is only one initial upper edge curve, it means that there is no interference at the upper edge of the vertebral body. The true upper edge line of the vertebral body is determined directly based on the first target curve, so as to achieve timely and accurate identification of the situation and thus ensure the accuracy of the acquisition of the true upper edge line.

[0270] In a feasible solution, for the lower edge of the vertebral body, the edge association information is the lower edge information;

[0271] The judgment unit is used to determine whether there are multiple initial lower edge curves based on the lower edge information. If they exist, the unit for obtaining the actual edge line is called.

[0272] The real edge line acquisition unit is used to acquire a second target curve within a second preset position range between the two initial lower edge curves located at the innermost and outermost edges, and to obtain the real lower edge line based on the acquired second target curve.

[0273] The second target curve can be obtained through direct selection or automatic generation.

[0274] In this scheme, when there are multiple initial lower edge curves, one curve located in the middle range is obtained as the second target curve, and the true lower edge line of the vertebra is finally determined based on the second target curve. This avoids the situation where the true lower edge line cannot be identified based on the curve located on the outer side or the inner side, thus effectively ensuring the accuracy of the acquisition of the true lower edge line.

[0275] The real edge line acquisition unit is also used to obtain the real lower edge line based on the initial lower edge curve if only one initial lower edge curve exists.

[0276] In this scheme, if there is only one initial lower edge curve, it means that there is no interference at the lower edge of the vertebral body. The true lower edge line of the vertebral body is determined directly based on the first target curve, so as to realize timely and accurate identification of the situation and thus ensure the accuracy of obtaining the true lower edge line.

[0277] In one feasible solution, the real edge line acquisition unit is used to form a first target curve within a positional region of one-third to two-thirds between two initial upper edge curves, and to obtain the real upper edge line based on the formed first target curve.

[0278] The trend of the first target curve lies between the trends of the two initial upper edge curves;

[0279] In this plan, such as Figure 9 As shown, to determine whether the upper edge has two sides, when there are two initial upper edge curves (curves 1 and 2 marked in the figure), an arbitrary curve is generated between 1 / 3 and 2 / 3 of the distance between the two initial lower edge curves. This curve serves as the first target curve, and the true upper edge line of the vertebra is ultimately determined based on this first target curve. This avoids determining the true upper edge line based on a curve located on the outermost or innermost side, which could compromise the accuracy of the true upper edge line recognition. This effectively ensures the accuracy of obtaining the true upper edge line. Of course, the area where the first target curve is located can be further narrowed or expanded according to the actual needs of the scenario.

[0280] In one feasible scheme, the real edge line acquisition unit is also used to form a second target curve in a position region of one-third to two-thirds between the two initial lower edge curves, and to obtain the real lower edge line based on the formed second target curve;

[0281] The trend of the second target curve lies between the trends of the two initial lower edge curves.

[0282] In this plan, such as Figure 9 As shown, to determine whether the lower edge has two sides, when two initial lower edge curves exist (curves 3 and 4 marked in the figure), an arbitrary curve is generated between 1 / 3 and 2 / 3 of the distance between the two initial lower edge curves to serve as the second target curve. This second target curve is then used as a reference to ultimately determine the true lower edge line of the vertebral body. This avoids determining the true lower edge line based on a curve located on the outermost or innermost side, which could compromise the accuracy of the true lower edge line recognition. This effectively ensures the accuracy of obtaining the true lower edge line. Of course, the area where the second target curve is located can be further narrowed or expanded according to the actual needs of the scenario.

[0283] In a feasible approach, the first target curve is the midline between the two initial upper edge curves;

[0284] like Figure 10 As shown, the midline between the two initial upper edge curves (the curve between curves 1 and 2 marked in the figure) is taken as the first target curve, and the overall undulation of the first target curve lies between the two initial upper edge curves.

[0285] In this scheme, based on the midline between the two initial upper edge curves, the accuracy of determining the true upper edge line can be further improved, thereby ensuring the accuracy of obtaining other edge lines.

[0286] The second target curve is the midline between the two initial lower edge curves.

[0287] like Figure 10 As shown, the midline between the two initial lower edge curves (the curve between curves 3 and 4 marked in the figure) is taken as the second target curve, and the overall undulation of the second target curve lies between the two initial lower edge curves.

[0288] In this scheme, based on the midline between the two initial lower edge curves, the accuracy of determining the true lower edge line can be further improved, thereby ensuring the accuracy of obtaining other edge lines.

[0289] Preferably, the upper and lower edges are processed using the same edge processing rules to ensure that the final identified real upper and lower edges better meet the actual processing requirements.

[0290] In one feasible solution, the true trailing edge acquisition subunit is used to acquire the first intersection point of the straight line containing the first line segment with the first target curve and the second intersection point with the second target curve; the second line segment between the first intersection point and the second intersection point is taken as the true trailing edge line of the vertebral body;

[0291] The first intersection point is the first left endpoint of the actual upper edge line, and the second intersection point is the second left endpoint of the actual lower edge line.

[0292] In this scheme, based on the first line segment, the curve where the real upper edge line is located, and the curve where the real lower edge line is located, the intersection points between the straight line where the first line segment is located and the first target curve and the second target district are automatically obtained, so as to finally determine the two endpoints of the real trailing edge line, thereby ensuring the rationality and accuracy of the acquisition of the real trailing edge line.

[0293] In a feasible solution, for the anterior edge of the vertebral body, the edge association information is the anterior edge information;

[0294] The judgment unit is used to obtain the initial anterior edge curve of the vertebral body based on the anterior edge information; to determine whether there is a concave curvature greater than the first set threshold on the initial anterior edge curve; if so, it is determined that there is osteophyte formation at the anterior edge of the vertebral body, and the real edge line acquisition unit is called.

[0295] For example, if there is a concave curvature greater than 15° on the curve, then it is determined that there is bone hyperplasia at that curvature.

[0296] The real edge line acquisition unit includes:

[0297] The initial straight line acquisition unit is used to obtain an initial straight line by performing tangent processing with a preset slope based on the vertex of the curve.

[0298] Among them, such as Figure 12 As shown, the preset slope is equal to the first slope of the first line segment;

[0299] The first intersection point acquisition unit is used to acquire the third intersection point of the initial straight line with the first target curve and the fourth intersection point with the second target curve;

[0300] The true leading edge acquisition unit is used to take the third line segment between the third intersection point and the fourth intersection point as the true leading edge line of the vertebral body;

[0301] The third intersection point is the first right endpoint of the actual upper edge line, and the fourth intersection point is the second right endpoint of the actual lower edge line.

[0302] In this scheme, the presence of osteophytes is automatically identified by analyzing the initial leading edge curve. If osteophytes are present, the influence of osteophytes on the determination of the actual shape of the vertebral body needs to be eliminated. Targeted matching processing is performed on cases with osteophytes to ensure the accuracy of the identification of the true leading edge line.

[0303] In a feasible approach, the method for determining the theoretical shape of the cone body also includes:

[0304] When it is determined that there is no concave curvature greater than the first set threshold on the initial anterior edge curve, it is determined that there is no osteophyte formation at the anterior edge of the vertebral body, and the initial anterior edge curve is taken as the target anterior edge curve.

[0305] Obtain the fifth intersection point of the target leading edge curve with the true upper edge line and the sixth intersection point with the true lower edge line;

[0306] The connecting curve between the fifth and sixth intersection points is taken as the true anterior edge line of the vertebral body;

[0307] The fifth intersection point is the first right endpoint of the actual upper edge line, and the sixth intersection point is the second right endpoint of the actual lower edge line.

[0308] In a feasible approach, the method for determining the theoretical shape of the cone body also includes:

[0309] When it is determined that there is no concave curvature greater than the first set threshold on the initial anterior edge curve, it is determined that there is no osteophyte formation at the anterior edge of the vertebral body, and the initial anterior edge curve is taken as the target anterior edge curve.

[0310] Obtain the second upper endpoint and the second lower endpoint corresponding to the target leading edge curve;

[0311] The third line segment is formed by connecting the second upper endpoint and the second lower endpoint;

[0312] Adjust the slope of the second line segment to the first slope to obtain the fourth line segment;

[0313] Find the seventh intersection point of the line containing the fourth line segment with the actual upper edge line and the eighth intersection point with the actual lower edge line;

[0314] The fifth line segment between the seventh and eighth intersection points is taken as the true anterior edge line of the vertebral body;

[0315] The seventh intersection point is the first right endpoint of the actual upper edge line, and the eighth intersection point is the second right endpoint of the actual lower edge line.

[0316] In this scheme, when it is determined that there is no osteophyte formation at the anterior edge, the anterior edge is obtained based on the actual imaging results. That is, the initial anterior edge curve is used as the target anterior edge curve, and then the two endpoints of the target anterior edge curve are obtained. Based on the intersection of the straight line containing the line segment between the two endpoints with the real upper edge line and the real lower edge line, the final connecting curve is obtained as the real anterior edge line of the vertebral body, thereby automatically, efficiently and accurately obtaining the real anterior edge line.

[0317] In one feasible approach, the step of obtaining the true upper edge line based on the acquired first target curve includes:

[0318] The curve between the first left endpoint and the first right endpoint is taken as the true upper edge line;

[0319] And / or,

[0320] The steps for obtaining the true lower edge line based on the acquired second target curve include:

[0321] The curve between the second left endpoint and the second right endpoint is taken as the true lower edge line.

[0322] In this scheme, the two endpoints of the curves corresponding to the true upper edge line and the true lower edge line are the intersection points connected to the true front edge line and the true rear edge line, respectively. This ensures that the positions of the two ends of the true upper edge line and the true lower edge line are determined accurately and in a timely manner, and also ensures the efficiency of recognizing the actual shape of the entire vertebral body in the vertebral body image.

[0323] In one feasible embodiment, the vertebral body image acquisition module 1 is used to acquire lateral radiographs of the thoracic and lumbar vertebrae generated by an X-ray machine; the lateral radiographs are then processed for image segmentation to obtain vertebral body images. Of course, X-ray images of other vertebrae can also be used.

[0324] In this scheme, the lateral radiographs of the thoracic and lumbar vertebrae taken by an X-ray machine are segmented to obtain vertebral images that meet the processing requirements of set size and resolution, so as to ensure the efficiency and reliability of the actual shape extraction and processing of each vertebra in each vertebral image.

[0325] Example 5

[0326] Figure 14 This is a schematic diagram of the structure of an electronic device according to Embodiment 5 of this disclosure. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the methods described in the above embodiments. Figure 14 The electronic device 30 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0327] like Figure 14 As shown, the electronic device 30 can be represented in the form of a general computing device, such as a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including memory 32 and processor 31).

[0328] Bus 33 includes a data bus, an address bus, and a control bus.

[0329] The memory 32 may include volatile memory, such as random access memory (RAM) 321 and / or cache memory 322, and may further include read-only memory (ROM) 323.

[0330] The memory 32 may also include a program / utility 325 having a set (at least one) of program modules 324, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0331] The processor 31 performs various functional applications and data processing, such as the methods described in the above embodiments of this disclosure, by running computer programs stored in the memory 32.

[0332] Electronic device 30 can also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). This communication can be performed via input / output (I / O) interface 35. Furthermore, the model-generating device 30 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 36. Figure 14As shown, network adapter 36 communicates with other modules of the model-generated device 30 via bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0333] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0334] Example 6

[0335] This embodiment provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps in the method described above.

[0336] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0337] In possible implementations, this disclosure can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the methods described above.

[0338] The program code for executing this disclosure can be written using any combination of one or more programming languages. The program code can be executed entirely on a user device, partially on a user device, as a standalone software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0339] While specific embodiments of this disclosure have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of this disclosure is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of this disclosure, but all such changes and modifications fall within the scope of protection of this disclosure.

Claims

1. A method for determining the theoretical shape of a cone, characterized in that, The determination method includes: Acquire vertebral images; Using preset edge processing rules, each edge of the vertebra in the vertebral body image is identified and processed to obtain the true edge line corresponding to each edge; The real edge lines include the real leading edge line, the real trailing edge line, the real upper edge line, and the real lower edge line; Based on each of the real edge lines, a closed shape is formed and used as the real edge shape corresponding to the cone body; Based on the true leading edge line, the true trailing edge line, and the true edge pattern, a bounding rectangle of the true edge pattern is generated, and the bounding rectangle is used as the theoretical shape of the cone. The step of using preset edge processing rules to identify and process each edge of the vertebral body in the vertebral body image to obtain the true edge line corresponding to each edge includes: Obtain the edge association information of each edge of the vertebral body in the vertebral body image; Determine whether the edge association information meets the corresponding preset conditions. If it does, then use the matching preset edge processing rules to process the edge association information to generate the real edge line corresponding to each edge. For the posterior edge of the vertebral body, the edge association information is the posterior edge information; The step of determining whether the edge association information meets the corresponding preset conditions, and if so, processing the edge association information using the matching preset edge processing rules to generate the real edge line corresponding to each edge, includes: Based on the trailing edge information, determine whether there is a ghosting region in the vertebral body image; if so, obtain multiple initial trailing edge curves. Identify the pedicle region in the vertebral body image; Obtain the initial posterior edge curve that is furthest from the pedicle region, and use it as the target posterior edge curve; Obtain the first upper endpoint and the first lower endpoint corresponding to the trailing edge curve of the target; A first line segment is formed by connecting the first upper endpoint and the first lower endpoint; Based on the first line segment, obtain the true posterior edge line of the vertebral body; And / or, For the upper edge of the vertebral body, the edge association information is the upper edge information; The step of determining whether the edge association information meets the corresponding preset conditions, and if so, processing the edge association information using the matching preset edge processing rules to generate the real edge line corresponding to each edge, includes: Based on the upper edge information, determine whether there are multiple initial upper edge curves. If so, obtain a first target curve within a first preset position range between the two initial upper edge curves located at the outermost and innermost edges, and obtain the actual upper edge line based on the obtained first target curve. If there is only one initial upper edge curve, then the actual upper edge line is obtained based on the initial upper edge curve; And / or, For the lower edge of the vertebral body, the edge association information is the lower edge information; The step of determining whether the edge association information meets the corresponding preset conditions, and if so, processing the edge association information using a matching preset edge processing rule to generate the real edge line corresponding to each edge, includes: Based on the lower edge information, determine whether there are multiple initial lower edge curves. If so, obtain a second target curve within a second preset position range between the two innermost and outermost initial lower edge curves, and obtain the real lower edge line based on the obtained second target curve. If there is only one initial lower edge curve, then the actual lower edge line is obtained based on the initial lower edge curve; And / or, For the anterior edge of the vertebral body, the edge association information is the anterior edge information; for the superior edge of the vertebral body, the edge association information is the superior edge information; and for the inferior edge of the vertebral body, the edge association information is the inferior edge information. The step of determining whether the edge association information meets the corresponding preset conditions, and if so, processing the edge association information using the matching preset edge processing rules to generate the real edge line corresponding to each edge, includes: The initial anterior curve of the vertebral body is obtained based on the anterior edge information; Determine whether there is a concave curvature greater than a first set threshold on the initial anterior edge curve. If so, determine that there is osteophyte formation at the anterior edge of the vertebral body. Based on the vertex of the bend, a tangent is formed using a preset slope to obtain an initial straight line; Wherein, the preset slope is equal to the first slope of the first line segment; Based on the upper edge information, determine whether there are multiple initial upper edge curves. If so, obtain a first target curve within a first preset position range between the two outermost and innermost initial upper edge curves. Based on the lower edge information, determine whether there are multiple initial lower edge curves. If so, obtain a second target curve within a second preset position range between the two innermost and outermost initial lower edge curves. Obtain the third intersection point of the initial straight line with the first target curve and the fourth intersection point with the second target curve; The third line segment between the third intersection point and the fourth intersection point is taken as the true anterior edge line of the vertebral body; The third intersection point is the first right endpoint of the actual upper edge line, and the fourth intersection point is the second right endpoint of the actual lower edge line.

2. The method for determining the theoretical shape of a vertebra as described in claim 1, characterized in that, The step of generating the bounding rectangle of the true edge pattern based on the true leading edge line, the true trailing edge line, and the true edge pattern, and using the bounding rectangle as the theoretical shape of the vertebral body, includes: The longer line segment between the true leading edge line and the true trailing edge line is selected as the width of the circumscribed rectangle. Wherein, the true leading edge line and the true trailing edge line are parallel to each other; The distance between the real leading edge line and the real trailing edge line is taken as the length of the circumscribed rectangle. Based on the width and length sides, the bounding rectangle of the real edge graphic is generated, and the bounding rectangle is used as the theoretical shape of the cone.

3. The method for determining the theoretical shape of a cone as described in claim 1, characterized in that, Different edges correspond to different preset conditions and preset edge processing rules.

4. The method for determining the theoretical shape of the vertebral body as described in claim 1, characterized in that, If the vertebral image contains two initial upper edge curves, the step of obtaining a first target curve within a first preset position range between the two initial upper edge curves located at the outermost and innermost edges, and obtaining the true upper edge line based on the obtained first target curve, includes: A first target curve is formed in the region between one-third and two-thirds of the position between the two initial upper edge curves, and the actual upper edge line is obtained based on the formed first target curve; The trend of the first target curve lies between the trends of the two initial upper edge curves. And / or, When the vertebral image contains two initial lower edge curves, the step of obtaining a second target curve within a second preset position range between the two innermost and outermost initial lower edge curves, and obtaining the true lower edge line based on the obtained second target curve, includes: A second target curve is formed in the region between one-third and two-thirds of the position between the two initial lower edge curves, and the true lower edge line is obtained based on the formed second target curve; The trend of the second target curve lies between the trends of the two initial lower edge curves.

5. The method for determining the theoretical shape of the vertebral body as described in claim 4, characterized in that, The first target curve is the midline between the two initial upper edge curves; And / or, The second target curve is the midline between the two initial lower edge curves.

6. The method for determining the theoretical shape of a vertebral body as described in claim 1, characterized in that, The step of obtaining the true posterior edge line of the vertebral body based on the first line segment includes: Obtain the first intersection point of the straight line containing the first line segment with the first target curve, and the second intersection point with the second target curve; The second line segment between the first intersection point and the second intersection point is taken as the true posterior edge line of the vertebral body; Wherein, the first intersection point is the first left endpoint of the actual upper edge line, and the second intersection point is the second left endpoint of the actual lower edge line.

7. The method for determining the theoretical shape of a vertebral body as described in claim 6, characterized in that, The method for determining the theoretical shape of the cone also includes: When it is determined that there is no concave curvature greater than a first set threshold on the initial anterior edge curve, it is determined that there is no osteophyte formation on the anterior edge of the vertebral body, and the initial anterior edge curve is taken as the target anterior edge curve; Obtain the fifth intersection point of the target leading edge curve with the actual upper edge line and the sixth intersection point with the actual lower edge line; The connecting curve between the fifth intersection point and the sixth intersection point is taken as the true anterior edge line of the vertebral body; Wherein, the fifth intersection point is the first right endpoint of the actual upper edge line, and the sixth intersection point is the second right endpoint of the actual lower edge line; or, Obtain the second upper endpoint and the second lower endpoint corresponding to the leading edge curve of the target; Connect the second upper endpoint and the second lower endpoint to form a third line segment; Adjust the slope of the second line segment to the first slope to obtain the fourth line segment; Obtain the seventh intersection point of the line containing the fourth line segment with the actual upper edge line and the eighth intersection point with the actual lower edge line; The fifth line segment between the seventh intersection point and the eighth intersection point is taken as the true anterior edge line of the vertebral body; The seventh intersection point is the first right endpoint of the actual upper edge line, and the eighth intersection point is the second right endpoint of the actual lower edge line.

8. The method for determining the theoretical shape of a cone as described in claim 7, characterized in that, The step of obtaining the true upper edge line based on the acquired first target curve includes: The curve between the first left endpoint and the first right endpoint is taken as the true upper edge line; And / or, The step of obtaining the true lower edge line based on the acquired second target curve includes: The curve between the second left endpoint and the second right endpoint is taken as the true lower edge line.

9. The method for determining the theoretical shape of a cone body as described in any one of claims 1-8, characterized in that, The step of acquiring vertebral body images includes: Obtain lateral radiographs of the thoracic and lumbar spine generated by an X-ray machine; The lateral radiograph image is segmented to obtain the vertebral body image.

10. A system for determining the theoretical shape of a cone, characterized in that, The determining system includes: Vertebral body image acquisition module, used to acquire vertebral body images; The real edge line acquisition module is used to identify and process each edge of the vertebra in the vertebral body image using preset edge processing rules, so as to obtain the real edge line corresponding to each edge. The real edge lines include the real leading edge line, the real trailing edge line, the real upper edge line, and the real lower edge line; The real edge graphic acquisition module is used to form a closed graphic based on each of the real edge lines, and use it as the real edge graphic corresponding to the cone. The theoretical shape acquisition module is used to generate the bounding rectangle of the real edge pattern based on the real leading edge line, the real trailing edge line and the real edge pattern, and use the bounding rectangle as the theoretical shape of the cone. The real edge line acquisition module includes: An edge information acquisition unit is used to acquire edge association information of each edge of the vertebral body in the vertebral body image; The judgment unit is used to determine whether the edge association information meets the corresponding preset conditions. If it does, the real edge line acquisition unit is called. The real edge line acquisition unit is used to process the edge association information using the matching preset edge processing rules to generate the real edge line corresponding to each edge; For the posterior edge of the vertebral body, the edge association information is the posterior edge information; The judgment unit is used to determine whether there is a ghosting region in the vertebral body image based on the trailing edge information. If it exists, the real edge line acquisition unit is invoked. The real edge line acquisition unit includes: The initial trailing edge curve acquisition sub-unit is used to acquire multiple initial trailing edge curves; A region recognition subunit is used to identify the pedicle region in the vertebral body image; The target trailing edge curve acquisition subunit is used to acquire the initial trailing edge curve that is furthest from the pedicle region, as the target trailing edge curve; The first endpoint acquisition subunit is used to acquire the first upper endpoint and the first lower endpoint corresponding to the target trailing edge curve; The first line segment acquisition sub-unit is used to connect the first upper endpoint and the first lower endpoint to form a first line segment; The true posterior edge line acquisition subunit is used to acquire the true posterior edge line of the vertebral body based on the first line segment; And / or, For the upper edge of the vertebral body, the edge association information is the upper edge information; The judgment unit is used to determine whether there are multiple initial upper edge curves based on the upper edge information. If so, the real edge line acquisition unit is invoked. The real edge line acquisition unit is used to acquire a first target curve within a first preset position range between the two initial upper edge curves located at the outermost and innermost sides, and to obtain the real upper edge line based on the acquired first target curve. And / or, For the lower edge of the vertebral body, the edge association information is the lower edge information; The judgment unit is used to determine whether there are multiple initial lower edge curves based on the lower edge information. If so, the real edge line acquisition unit is invoked. The real edge line acquisition unit is used to acquire a second target curve within a second preset position range between the two initial lower edge curves located at the innermost and outermost sides, and to obtain the real lower edge line based on the acquired second target curve. And / or, For the anterior edge of the vertebral body, the edge association information is the anterior edge information; for the superior edge of the vertebral body, the edge association information is the superior edge information; and for the inferior edge of the vertebral body, the edge association information is the inferior edge information. The judgment unit is used to obtain the initial anterior edge curve of the vertebral body based on the anterior edge information; to determine whether there is a curvature on the initial anterior edge curve with an inward curvature greater than a first set threshold; if so, it is determined that there is osteophyte formation at the anterior edge of the vertebral body, and the real edge line acquisition unit is called. The real edge line acquisition unit includes: The initial straight line acquisition unit is used to obtain an initial straight line by performing tangent processing with a preset slope based on the vertex of the bend. Wherein, the preset slope is equal to the first slope of the first line segment; The judgment unit is used to determine whether there are multiple initial upper edge curves based on the upper edge information. If so, the real edge line acquisition unit is invoked. The real edge line acquisition unit is used to acquire a first target curve within a first preset position range between the two initial upper edge curves located at the outermost and innermost edges; The judgment unit is used to determine whether there are multiple initial lower edge curves based on the lower edge information. If so, the real edge line acquisition unit is invoked. The real edge line acquisition unit is used to acquire a second target curve within a second preset position range between the two initial lower edge curves located at the innermost and outermost edges; The first intersection point acquisition unit is used to acquire the third intersection point of the initial straight line with the first target curve and the fourth intersection point with the second target curve; The true leading edge line acquisition unit is used to take the third line segment between the third intersection point and the fourth intersection point as the true leading edge line of the vertebral body; The third intersection point is the first right endpoint of the actual upper edge line, and the fourth intersection point is the second right endpoint of the actual lower edge line.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for determining the theoretical shape of the cone as described in any one of claims 1-9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for determining the theoretical shape of the cone as described in any one of claims 1-9.

Images