Image segmentation method and device suitable for skeleton image data, medium and product

Abstract

The invention discloses an image segmentation method and device suitable for skeleton image data, a medium and a product. The method comprises the following steps: determining an initial point set corresponding to an initial active contour arranged in a skeleton CT image, wherein all skeletons in the skeleton CT image are in the initial active contour; a weight matrix of the skeleton CT image is determined based on a weight function, the weight matrix comprises the weighted sum of the gray scale weight and the gradient weight of each pixel in the skeleton CT image, and the weight function comprises a gray scale item and a gradient item which are both monotonically decreasing functions; an iteration equation is solved based on the initial point set, the weight matrix and a preset iteration step length, a target active contour coinciding with the skeleton boundary is obtained, the iteration equation is a gradient flow equation of a minimized energy functional, and the energy functional optimizes the active contour based on the weighted sum of the weighted perimeter and the weighted area of the active contour; and in the skeleton CT image, determining a skeleton segmentation result corresponding to the target movable contour. According to the embodiment of the invention, the accuracy of a skeleton segmentation result can be improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image segmentation method, device, medium and product suitable for bone image data. Background Art

[0002] Existing technologies usually perform bone segmentation on bone CT images based on boundary detection methods, region detection methods, and bone segmentation models. However, the accuracy of bone segmentation results determined based on these methods is low. For example, non-bone with high grayscale values ​​is easily regarded as bone, or the accuracy of determined bone boundaries is low due to the inability to accurately identify cortical bone and cancellous bone.

[0003] Therefore, it is necessary to provide an image segmentation method suitable for bone image data to improve the accuracy of bone segmentation results. Summary of the invention

[0004] The present invention provides an image segmentation method, device, medium and product applicable to bone image data, so as to solve the technical problem that the existing bone segmentation method has low accuracy of bone segmentation results.

[0005] According to one aspect of the present invention, there is provided an image segmentation method applicable to bone image data, comprising:

[0006] Determine an initial point set corresponding to an initial active contour set in the bone CT image, wherein all bones in the bone CT image are in the initial active contour;

[0007] Determining a weight matrix of the bone CT image based on a weight function, the weight matrix comprising a weighted sum of a grayscale weight and a gradient weight of each pixel in the bone CT image, the weight function comprising a grayscale term and a gradient term both being monotonically decreasing functions, the grayscale term being used to determine a grayscale weight of a pixel that does not meet a soft tissue grayscale condition, and the gradient term being used to determine a gradient weight of a pixel that does not meet a soft tissue gradient condition;

[0008] An iterative equation is solved based on the initial point set, the weight matrix and a predetermined iteration step size to obtain a target active contour that coincides with the bone boundary. The iterative equation is a gradient flow equation that minimizes an energy functional. The energy functional optimizes the active contour based on a weighted sum of a weighted perimeter and a weighted area of ​​the active contour. The weights used in determining the weighted perimeter and the weighted area come from the weight matrix.

[0009] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0010] at least one processor; and

[0011] a memory communicatively connected to the at least one processor; wherein,

[0012] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the image segmentation method applicable to bone image data described in any embodiment of the present invention.

[0013] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the image segmentation method applicable to bone image data described in any embodiment of the present invention when executed.

[0014] According to another aspect of the present invention, a computer program product is provided, characterized in that the computer program product comprises a computer program, and when the computer program is executed by a processor, the image segmentation method applicable to bone image data described in any embodiment is implemented.

[0015] In the bone CT image, the pixel grayscale value of the bone area is higher than the pixel grayscale value of the surrounding soft tissue area, and the pixel gradient change value at the bone boundary is higher than the gradient change value of the pixel in other areas. The technical solution provided by the embodiment of the present invention, the weight function includes a grayscale term and a gradient term, both of which are monotonically decreasing functions, the grayscale term is used to determine the grayscale weight of pixels that do not meet the soft tissue grayscale condition, and the gradient term is used to determine the gradient weight of pixels that do not meet the soft tissue gradient condition; based on this feature, the weights of soft tissue pixels and bone pixels can be differentiated, and the contribution of soft tissue to the weighted area and weighted perimeter determined by the energy functional can be weakened, thereby reducing the influence of soft tissue on the accuracy of the weighted area and weighted perimeter of the active contour, and in the process of minimizing the energy functional, the active contour can be controlled to accurately approach the bone boundary according to the characteristics of the weighted sum determined by the weight function, and an accurate target active contour can be obtained, thereby determining a bone segmentation result with high accuracy based on the target active contour.

[0016] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 is a flow chart of an image segmentation method applicable to bone image data provided by an embodiment of the present invention;

[0019] Figure 2 is a schematic diagram of an initial activity profile provided according to an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of a weight matrix provided according to an embodiment of the present invention;

[0021] Figure 4 is a schematic diagram of a target activity profile provided according to an embodiment of the present invention;

[0022] Figure 5 is another flow chart of an image segmentation method applicable to bone image data provided according to an embodiment of the present invention;

[0023] Figure 6 is a schematic diagram of an image segmentation method applicable to bone image data provided according to an embodiment of the present invention;

[0024] Figure 7 is a comparison diagram of skeleton segmentation results provided according to an embodiment of the present invention;

[0025] Figure 8 is a schematic diagram of active contours of different algorithms under the same number of iteration steps provided by an embodiment of the present invention;

[0026] Fig. 9 is a schematic diagram of bone segmentation results of bone CT images of different parts determined based on different algorithms provided by an embodiment of the present invention;

[0027] Fig.10 is a schematic diagram of the structure of an image segmentation device applicable to bone image data provided by an embodiment of the present invention;

[0028] Fig.11 is another structural schematic diagram of an image segmentation device applicable to bone image data provided by an embodiment of the present invention;

[0029] Fig.12 is another structural schematic diagram of an image segmentation device applicable to bone image data provided by an embodiment of the present invention;

[0030] Fig.13 is another structural schematic diagram of an image segmentation device applicable to bone image data provided by an embodiment of the present invention;

[0031] Fig.14 It is a structural schematic diagram of an electronic device for implementing the image segmentation method applicable to bone image data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only an embodiment of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] Figure 1 The flowchart of the image segmentation method applicable to bone image data provided by the embodiment of the present invention is applicable to the case where the bone segmentation result of the bone CT image is determined based on the active contour. The method can be executed by an image segmentation device applicable to bone image data. The image segmentation device applicable to bone image data can be implemented in the form of hardware and / or software. The image segmentation device applicable to bone image data can be configured in the processor of the electronic device. Figure 1 As shown, the method includes:

[0035] S110, determining an initial point set corresponding to an initial active contour set in the bone CT image, wherein all bones in the bone CT image are in the initial active contour.

[0036] Among them, the bone CT image is a CT image including bones, such as a foot CT image, a leg CT image, a hip CT image, etc.

[0037] The initial active contour can be a closed curve of any shape, such as a circle, rectangle (see Figure 2 The red rectangular box in the figure), etc., as long as all the bones in the bone CT image are within the initial active contour.

[0038] In one embodiment, in response to the contour drawing operation in the bone CT image in the contour drawing mode, a corresponding initial active contour is generated. Since this embodiment is mainly for doctors, and doctors have good image reading ability, they can add accurate initial active contours on the bone CT image, so this embodiment can quickly determine the accurate initial active contour.

[0039] In one embodiment, the bone distribution range in the bone CT image is identified based on the pre-trained bone recognition model, and then the bone distribution range is expanded to set a size to obtain an initial active contour; or a closed curve including the bone distribution range is used as the initial active contour. Since the pre-trained bone recognition model may not be able to accurately identify the bone boundary, but it can identify the bone distribution range, the initial active contour determined based on the bone distribution range has a higher accuracy, achieving the technical effect of automatically adding an accurate initial active contour to the bone CT image.

[0040] After the initial active contour is determined, all pixels included in the initial active contour are used as the initial point set. In this embodiment, the skeleton image is represented as I, where I:Ω→R, Ω is the image domain of the skeleton image I, and R is the real number space. The active contour is represented as φ, which is the level set function on the image domain Ω. Its zero level set is {x∈Ω|φ(x)=0}, which represents the active contour under consideration, and it is agreed that the area less than zero {x∈Ω|φ(x)<0} is the interior of the active contour, which is the target area; the area greater than zero {x∈Ω|φ(x)>0} is the exterior of the active contour, which is the background area.

[0041] S120. Determine a weight matrix of the bone CT image based on a weight function, wherein the weight matrix includes a weighted sum of the grayscale weight and the gradient weight of each pixel in the bone CT image, and the weight function includes a grayscale term and a gradient term, both of which are monotonically decreasing functions. The grayscale term is used to determine the grayscale weight of pixels that do not meet the soft tissue grayscale condition, and the gradient term is used to determine the gradient weight of pixels that do not meet the soft tissue gradient condition.

[0042] The weight matrix includes the weights of each pixel in the bone image (see Figure 3 ), and the weight of each pixel is the weighted sum of the grayscale weight and gradient weight of each pixel. Figure 3 In the image, the weights of most soft tissue pixels are relatively large, and the weights of pixels at the bone boundary are much smaller than those of the surrounding pixels.

[0043] In bone CT images, the grayscale value of bone pixels is higher than that of the surrounding soft tissue pixels, and the pixels distributed on the bone boundary have a higher gradient. Therefore, the weighted sum of grayscale weight and gradient weight is used as the weight of each pixel to improve the accuracy of determining the weight of each pixel.

[0044] A monotonically decreasing function is a function whose output data decreases as the independent variable increases.

[0045] The soft tissue grayscale condition is used to remove some or all soft tissue pixels in the bone CT image, and the grayscale term is used to determine the grayscale weight of each remaining pixel in the bone CT image after removing the part or all of the soft tissue; the soft tissue gradient condition is also used to remove some or all of the soft tissue pixels in the bone CT image, and the gradient term is used to determine the gradient weight of each remaining pixel in the bone CT image after removing the part or all of the soft tissue. It can be understood that the pixel combination corresponding to the soft tissue grayscale condition may be the same as or different from the pixel combination corresponding to the soft tissue gradient condition. The grayscale weight of the soft tissue pixel corresponding to the soft tissue grayscale condition is 1, and the gradient weight of the soft tissue pixel corresponding to the soft tissue gradient condition is also 1, which realizes the elimination of the contribution of the grayscale weight of the corresponding pixel to the weighted sum through the soft tissue grayscale condition, and the elimination of the contribution of the gradient weight of the corresponding pixel to the weighted sum through the soft tissue gradient condition.

[0046] In one embodiment, the soft tissue grayscale condition is a grayscale threshold; the soft tissue gradient condition is a gradient threshold; the grayscale threshold is greater than or equal to a first grayscale value and less than or equal to a second grayscale value; the first grayscale value is the maximum value of the soft tissue pixel grayscale values ​​used in the bone CT image browsing; the second grayscale value is the minimum value of the bone pixel grayscale values ​​used in the bone CT image browsing; the gradient threshold is greater than or equal to zero and less than or equal to a third grayscale value, and the third grayscale value is equal to the difference between the second grayscale value and the first grayscale value.

[0047] Based on this, the grayscale term is used to target pixels with grayscale values ​​higher than the grayscale threshold, and the higher the grayscale value, the lower the grayscale weight of the pixel; the gradient term is used to target pixels with gradient values ​​higher than the gradient threshold, and the higher the gradient value, the lower the gradient weight of the pixel. Since the grayscale value and gradient value of the pixels at the bone boundary are much larger than the grayscale value and gradient value of the surrounding pixels, the weight of the pixels on the bone boundary is significantly smaller than the weight of the pixels in other areas, so that in the process of minimizing the energy functional, the active contour can be accurately controlled to approach the bone boundary.

[0048] Specifically, in clinical orthopedic diagnosis, doctors usually need to browse the patient's bone CT images within the bone window range. In the field of mathematics, browsing within the bone window range refers to the process of truncating and mapping the CT value to the image grayscale range according to the window width and window position of the bone window, which can be expressed as follows:

[0049]

[0050] Since there is a significant difference in density between bones and surrounding soft tissues, there is also a significant difference in their CT values. When the window width and window position are given, the grayscale value difference between bone pixels and soft tissue pixels can be calculated through the above grayscale mapping.

[0051] Generally speaking, when browsing CT images of specific parts, different doctors will not adjust the window width and window position to a fixed value, but can adjust it to a certain range empirically. This embodiment uses the range of the bone window width and window position, combined with the CT value range of bones and soft tissues, to calculate the upper limit of the soft tissue pixel grayscale range and the lower limit of the bone pixel grayscale value range, and determines the grayscale threshold and gradient threshold corresponding to the weight function based on the upper and lower limits, so that the weight function can accurately differentiate the weight of each pixel and reduce the influence of other tissues and organs on the contraction of the active contour.

[0052] Set the window width and window position range to: W ω ∈[ω 1 ,ω 2 ],W t ∈[l 1 ,l 2 ], and assuming that the CT value of soft tissue is less than or equal to S, and the CT value of bone is greater than or equal to B, the upper bound θ of the corresponding gray value is calculated by solving the following two optimization problems 1 and the lower bound θ 2 , and called θ 1 is the first gray value, called θ 2 For the second gray value:

[0053] θ 1 =maxm(z;W ω ,W l )stz≤S,ω 1 ≤W ω ≤ω 2 ,l 1 ≤W l ≤l 2 ,

[0054] θ 2 =minm(z;W ω ,W l )stz≥B,ω 1 ≤W ω ≤ω 2 ,l 1 ≤W l ≤l 2 It can be seen that θ 1 ≤θ 2 , and called θ 2 -θ 1 is the third gray value.

[0055] Considering that the bone boundary has the characteristics of high grayscale value and high gradient value, the grayscale information and gradient information are embedded in the weight function at the same time. The weight function can be selected as:

[0056]

[0057] Among them, γ>0 is used to adjust the ratio of grayscale term to gradient term, that is, the weighting coefficient between the two. 1 is the function corresponding to the soft tissue grayscale condition, f 2 is a function corresponding to the soft tissue gradient condition. The weight function contained in the formula is abbreviated as

[0058] In one embodiment, Here + =max{z,0},δ 1 ,δ 2 >0, and select ε 1 ∈[θ 1 ,θ 2 ],ε 2 ∈[0,θ 2 -θ 1 ]. It should be noted that f 1 With f 2 The selection includes but is not limited to this form. In another embodiment, the selection method is f 1 (z) = exp((z - ε 1 ) + ), f 2 (z) = exp((z - ε 2 ) + ), exp(·) represents the natural exponential operation, which can be realized by any function that is monotonically increasing within the range of positive real numbers.

[0059] In the process of determining the weighted sum of grayscale weights and gradient weights, the above-mentioned weight function filters out the influence of some soft tissue information on the weighted sum, thereby realizing the weight differentiation of soft tissue pixels and bone pixels; at the same time, the grayscale information and gradient information of the pixels are considered, and since both the grayscale weight and the gradient term are monotonically decreasing functions, the weight of the pixels at the bone boundary in the bone CT image is significantly smaller than the weight of the pixels at other positions. Therefore, the weight matrix of the bone CT image determined based on the weight function can better guide the active contour to evolve toward the bone boundary in the process of minimizing the energy functional, thereby avoiding the influence of other tissues and organs on the accuracy of the evolution results.

[0060] S130. Solve the iterative equation based on the initial point set, the weight matrix and the predetermined iteration step size to obtain the target active contour that coincides with the bone boundary. The iterative equation is a gradient flow equation that minimizes the energy functional. The energy functional optimizes the active contour based on the weighted sum of the weighted perimeter and weighted area of ​​the active contour. The weights used in determining the weighted perimeter and weighted area come from the weight matrix.

[0061] In one embodiment, the energy functional is:

[0062]

[0063] Among them, H(φ(x)) is zero when φ(x) is less than or equal to zero, and is 1 when φ(x) is greater than zero. In other words, for pixels outside the active contour, H(φ(x)) is 1, and H(φ(x)) is 0 in other cases; is a weight function used to determine the weight matrix of the bone CT image. α is the ratio between the weighted perimeter term and the weighted area term. This value is an empirical value and its value range can be (0,2). is the weighted perimeter term, which is used to determine the weighted perimeter of the active contour; is the weighted area term, which is used to determine the weighted area inside the active contour.

[0064] It should be noted that the weighted perimeter term and the weighted area term in the energy functional may also be implemented in other ways, as long as the perimeter and the area of ​​the active contour can be accurately determined, which will not be elaborated in this embodiment.

[0065] After the energy functional is determined, the gradient flow equation used to minimize the energy functional is determined, and then the gradient flow equation is discretized to obtain an iterative equation; then the iterative equation is iteratively calculated based on the initial point set, the initial weight matrix and the predetermined iteration step until the set stop condition is met to obtain the target active contour. Figure 4 As shown, the red closed curve is the target active contour, which coincides with the bone boundary in the bone CT image.

[0066] The gradient flow equation used to minimize this energy functional is:

[0067]

[0068] The gradient flow equation is discretized to obtain the iterative equation, which is:

[0069]

[0070] Where h is the time step, φ n is the active contour in the previous iteration, φ n+1is the active contour in the current iteration round, is the gradient operator, is the divergence operator.

[0071] S140: Determine the bone segmentation result corresponding to the target active contour in the bone CT image.

[0072] Since the target active contour coincides with the bone boundary in the bone CT image, the bone CT image can be segmented based on the target active contour to obtain a bone segmentation result.

[0073] Specifically, the target active contour is taken as the bone boundary, the inner area of ​​the target active contour is taken as the bone, and the outer area of ​​the target active contour is taken as the background area. Therefore, based on the target active contour, the target active contour and the inner area of ​​the target active contour can be segmented from the bone CT image as the bone.

[0074] Since the grayscale information and gradient information of each pixel are fully considered in the process of determining the target active contour, the target active contour has a high degree of overlap with the bone boundary. Therefore, the bone area can be completely segmented from the bone CT image based on the target active contour, and it has a high generalization ability for different bone parts.

[0075] Due to the physiological structure of different bone parts, some bones in the bone segmentation result may include non-bone holes or slits. In view of this, in one embodiment, a hole removal operation and / or a slit removal operation are performed on the bone part in the bone segmentation result to obtain an updated bone segmentation result; the updated bone segmentation result is binarized to obtain a mask for the target bone. Among them, holes can be obtained by internal active contour expansion, and slits can be obtained by a region generation algorithm; of course, other methods can also be used to detect whether holes and / or slits exist, and when holes and / or slits exist, holes and / or slits in the bone segmentation result are removed by operations such as hole and / or slit filling and expansion to obtain an updated bone segmentation result; then the updated bone segmentation result is binarized, such as assigning pixels of the target bone area in the updated bone segmentation result to 1, and assigning pixels of the non-bone area to 0, etc., to obtain a mask for the target bone.

[0076] It can be understood that since the target bone in the target bone segmentation result or the mask for the target bone includes the three-dimensional information of the target bone in the bone image, the three-dimensional spatial structure of the target bone can be determined based on the bone segmentation result or the mask.

[0077] The embodiment of the present invention can be used for the segmentation of real bones, and can also be used for the segmentation of implant objects similar to bones.

[0078] In a bone CT image, the grayscale value of a bone pixel is higher than the grayscale value of a surrounding soft tissue pixel, and the gradient change value of a pixel at a bone boundary is higher than the gradient change value of a pixel in other areas; in the technical solution provided by an embodiment of the present invention, a weight function includes a grayscale term and a gradient term, both of which are monotonically decreasing functions, the grayscale term is used to determine the grayscale weight of a pixel that does not meet the soft tissue grayscale condition, and the gradient term is used to determine the gradient weight of a pixel that does not meet the soft tissue gradient condition; this feature makes the weight of a soft tissue pixel significantly different from the weight of a bone pixel, weakens the contribution of soft tissue to the weighted area and weighted perimeter determined by an energy functional, thereby reducing the influence of soft tissue on the accuracy of the weighted area and weighted perimeter of an active contour, and in the process of minimizing the energy functional, controls the active contour to accurately approach the bone boundary, obtains an accurate target active contour, and thereby determines a bone segmentation result with high accuracy based on the target active contour.

[0079] Figure 5 This is a flow chart of an image segmentation method for bone image data provided by an embodiment of the present invention. This embodiment refines the predetermined iteration step size based on the above-mentioned embodiment. Figure 5 As shown, the method includes:

[0080] S220, determining an initial point set corresponding to an initial active contour set in the bone CT image, wherein all bones in the bone CT image are in the initial active contour.

[0081] S220. Determine a weight matrix of the bone CT image based on a weight function, wherein the weight matrix includes a weighted sum of the grayscale weight and the gradient weight of each pixel in the bone CT image, and the weight function includes a grayscale term and a gradient term, both of which are monotonically decreasing functions. The grayscale term is used to determine the grayscale weight of pixels that do not meet the soft tissue grayscale condition, and the gradient term is used to determine the gradient weight of pixels that do not meet the soft tissue gradient condition.

[0082] S230. Solve the iterative equation based on the initial point set, the weight matrix and the predetermined iterative step size to obtain a target active contour that coincides with the bone boundary. The iterative equation is a gradient flow equation that minimizes the energy functional. The energy functional optimizes the active contour based on the weighted sum of the weighted perimeter and the weighted area of ​​the active contour. The weights used in the process of determining the weighted perimeter and the weighted area come from the weight matrix. The predetermined iterative step size includes a time step and an adaptive step size based on the boundary distance. The adaptive step size is determined based on the distance between each pixel in the active contour and the bone boundary. The distance between each pixel in the active contour and the bone boundary is extracted from a first boundary distance set; the first boundary distance set includes the normalized distance between each pixel in the bone CT image and the bone boundary.

[0083] The time step is greater than 0 and less than 0.5. In this embodiment, the time step is preferably greater than 0 and less than 0.2.

[0084] Adaptive step size can be understood as spatial step size. Specifically, based on the distance between each pixel in the previous active contour and the bone boundary, the spatial step size in the current iteration round is adaptively determined, and the active contour in the current iteration round is determined according to the previous active contour (the active contour in the previous iteration round) and the spatial step size. As the distance between the active contour and the bone boundary shortens, the spatial step size also shortens, and the iterative evolution speed decreases.

[0085] Since the first boundary distance set includes the normalized distance between each pixel in the bone CT image and the bone boundary, the distance between each pixel in the current active contour and the bone boundary can be determined based on the first boundary distance set. In this way, when it is detected that the distance between each pixel of the current active contour and the bone boundary is less than or equal to the set threshold, the iterative evolution operation is triggered to stop, and the current active contour is used as the target active contour.

[0086] In one embodiment, the first boundary distance set may be implemented by the following steps:

[0087] Step a1: determine the bone boundary set corresponding to the bone CT image.

[0088] To determine the distance between each pixel and the bone boundary in the bone CT image, it is necessary to first determine the bone boundary in the bone CT image. In one embodiment, the bone CT image is analyzed by a bone boundary extraction algorithm (such as a Canny operator, etc.) to obtain all pixels distributed on the bone boundary in the bone CT image, and the set of all pixels distributed on the bone boundary is used as the bone boundary set (E bone ). Specifically:

[0089] The grayscale value near the bone boundary is usually higher, while the grayscale value of the non-bone position is lower, so this feature can be used to filter out the non-bone boundary and obtain the bone boundary. When the algorithm is implemented, its characteristic function can be expressed as:

[0090]

[0091] Among them, {φ 0 ≤0} is the set of internal elements of the initial active contour, K is the convolution kernel used to filter out non-bone boundaries, η is a threshold, It is the set of pixels on all boundaries of the bone CT image.

[0092] In yet another embodiment, the bone CT image is input into a pre-trained bone boundary extraction model to obtain a bone boundary set corresponding to the bone CT image.

[0093] It is understandable that, for a fracture scenario, the fracture boundary corresponding to the fracture gap can also be regarded as a bone boundary. For this reason, the bone boundary set in this embodiment also includes a fracture boundary set.

[0094] When there is a fracture in the bone CT image, but the boundary of the fracture is not obvious or even does not exist, the active contour will not be able to stay at the fracture. The present invention integrates the artificial interaction information of the fracture into the boundary distance so that the active contour can stay at the fracture, so that the bone segmentation result can be used in the fracture recovery scenario.

[0095] Specifically, in the fracture edge drawing mode, the doctor uses a drawing tool to outline the fracture in the bone CT image, and the processor responds to the confirmation operation of the fracture edge outlining result in the fracture edge drawing mode, determines all pixels in the bone CT image corresponding to the fracture edge outlining result; and takes all pixels in the bone CT image corresponding to the fracture edge outlining result as the fracture boundary set. Figure 6 The red rectangle in the bone CT image on the left is the initialized active contour (ie, the initial active contour), the yellow curve in the bone CT image is the fracture hint, and the pixel set corresponding to the fracture hint is the fracture boundary set.

[0096] Since doctors have good fracture recognition ability, the fracture boundary set (E prompt ) has a higher accuracy. Moreover, the bone boundary set as a fracture hint allows the active contour to stop at the fracture, which improves the accuracy of iteration stop, as well as the interactivity and flexibility of target active contour determination.

[0097] After the fracture boundary set is determined, the union of the fracture boundary set and the bone boundary set is used as the updated bone boundary set.

[0098] Step a2: determine the distance between each pixel in the bone CT image and the bone boundary corresponding to the bone boundary set, and obtain the distance between each pixel in the bone CT image and the bone boundary.

[0099] Step a3: The summary result of the distances between all pixels and the bone boundary is taken as the second boundary distance set, and each distance in the second boundary distance set is normalized to obtain the first boundary distance set.

[0100] Specifically, the second boundary distance set can be expressed as: d(x,E bone ), where x∈Ω.

[0101] After the second boundary distance set is determined, the normalization of each distance in the second boundary distance set is completed by the following formula to obtain the first boundary distance set:

[0102]

[0103] For the bone boundary set including the fracture boundary set, the second boundary distance set corresponding to the bone boundary set is: Where x∈Ω. The first boundary distance set corresponding to the second boundary distance set is determined by the following formula:

[0104]

[0105] when

[0106] If this function is used as the adaptive step size, when the active contour is far away from the bone boundary, the active contour evolves faster. As the distance decreases, the evolution speed gradually slows down until the active contour reaches the bone boundary, the evolution speed is zero, and the evolution stops, thereby achieving the purpose of stabilizing the algorithm. Figure 6 The adaptive step length integrated into the boundary distance is shown, that is, the adaptive step length determined based on the first bone boundary distance set, and the width of each color distribution area corresponds to an adaptive step length.

[0107] The gradient flow function including the adaptive step size can be expressed as:

[0108]

[0109] After discretization, the iterative equation is obtained:

[0110]

[0111] Here, h is the time step.

[0112] S240: Determine the bone segmentation result corresponding to the target active contour in the bone CT image.

[0113] In this embodiment, the bone boundary set used to determine the second bone boundary distance set corresponds to the bone boundary in the bone CT image, and the target active contour also corresponds to the bone boundary in the bone CT image; however, the former has low accuracy and cannot distinguish between the inside and outside of the bone, while the latter is the opposite. In other words, this embodiment determines a target active contour with high accuracy based on the combination of energy functional and the bone boundary set with low accuracy.

[0114] In order to improve the accuracy of bone segmentation results, Figure 6 As shown, after the skeleton segmentation result is determined, the skeleton segmentation result is post-processed, such as a hole removal operation and / or a slit removal operation, etc., to update the skeleton segmentation result.

[0115] The technical solution provided by the embodiment of the present invention has a spatial step size in which the adaptive step size is adjusted according to the distance between the active contour and the bone boundary during the energy functional evolution process, thereby achieving the purpose of controlling the evolution speed. Moreover, it can be foreseen that when the distance between the active contour and the bone boundary is less than a set threshold or is zero, the iterative evolution can be stopped directly, thereby improving the accuracy of the timing of stopping the iterative evolution and the accuracy of the target active contour.

[0116] Figure 7 A comparison diagram of the skeleton segmentation results provided in an embodiment of the present invention, specifically a comparison result between the skeleton segmentation result provided in an embodiment of the present invention and the skeleton segmentation result determined based on the Chan-Vese algorithm.

[0117] The bone CT image in the embodiment of the present invention can be a pelvic CT image or a foot and ankle CT image. The window width range and window position range based on which the grayscale value of each pixel in the bone CT image is determined are [1000HU, 1500HU] and [250HU, 350HU] respectively; and it is considered that the CT value of soft tissue does not exceed 100HU, and the CT value of bone is not less than 300HU. Solving the optimization problem, it is obtained that the pixel grayscale value of soft tissue does not exceed 102, and the pixel grayscale value of bone is not less than 115, and the appropriate parameter ε is selected. 1 ∈[102,115] and ε 2 ∈[0,13]. Fixed selection of δ 1 =1,δ 2 = 2 and γ = 1. When constructing the adaptive step size, the Canny operator is selected for boundary extraction, and the convolution kernel for filtering non-bone boundaries uses a 3×3 uniformly distributed convolution kernel with a threshold of η = 70.

[0118] like Figure 7 As shown, since the Chan-Vese algorithm uses two constants to approximate the image foreground and background, it cannot adapt well to the characteristics of the large difference in density and texture between the cortical bone and the cancellous bone in the bone structure, and thus cannot segment the complete bone area. The embodiment of the present invention accurately segments the cortical bone and the cancellous bone at the same time.

[0119] In CT images of the pelvis and ankle, numerical experiments and comparisons were also conducted with the method described in the embodiment of the present invention and the original geodesic active contour method. The results are as follows: Figure 8 shown. Figure 8The initial active contours of the two methods and the iterative results at 1000, 2000, 3000, 6000 and 7000 steps are shown. It can be seen that in the original geodesic active contour method, the active contour is easily affected by the boundaries of other tissues and organs, and the active contour is unstable at 7000 iterations. In the embodiment of the present invention, the active contour is not affected by the boundaries of other tissues and organs, and the shape of the active contour is stably maintained during the iteration process, and the active contour also stays well at these positions.

[0120] Fig. 9 A schematic diagram of the bone segmentation results of bone CT images of different parts determined based on different algorithms is provided, specifically the comparison results of the method described in the embodiment of the present invention, the SAM method, the continuous maximum flow algorithm, the Chan-Vese algorithm, the U-Net method and the real label. The continuous maximum flow algorithm is the same as the Chan-Vese algorithm and cannot segment the complete bone area. SAM is a large model algorithm, and its results come from the official website. The white box is the prompt outline, and the blue outline is the bone outline found by the algorithm. It can be seen that SAM can only give the approximate outline of the segmentation target, and still cannot give accurate results in the segmentation details, especially the fracture. The U-Net used in the experiment was trained on the pelvic CT image data of 90 patients for 20 rounds. The test results showed slightly better performance on the pelvic image, but could not be generalized to the ankle. Generalization ability has always been a key issue of deep learning algorithms. In comparison, the algorithm proposed in the present invention belongs to the traditional mathematical model algorithm, which has an advantage in generalization ability and obtains better results for both the pelvis and the ankle.

[0121] The present invention considers the following four numerical indicators to measure the quality of the segmentation results. It is agreed that G represents the true value label and S represents the segmentation result. represents the boundary of the set, and |·| represents the measure. This embodiment uses the Dice coefficient and the Jaccard coefficient to evaluate the prediction accuracy of the segmentation result at the pixel level. The results obtained by the two coefficients are in the range of [0%, 100%]. The larger the value, the better the segmentation result.

[0122] in,

[0123] This embodiment uses Hausdorff distance (HD) and average symmetric surface difference (ASSD) to evaluate the closeness between the bone boundary in the bone segmentation result and the bone boundary in the true label. The smaller the value, the better the bone segmentation.

[0124]

[0125] Based on the Dice coefficient, Jaccard coefficient, Hausdorff distance and average symmetric surface distance, the comparison results of the skeleton segmentation results determined by the embodiment of the present invention and the true label, as well as the comparison results of the skeleton segmentation results determined by other algorithms and the true label are determined, as shown in Table 1. It can be seen from Table 1 that the index data of the skeleton segmentation results determined by the embodiment of the present invention are generally optimal.

[0126] Table 1 Index data display table of bone segmentation results corresponding to different methods

[0127]

[0128] In summary, the accuracy of the skeleton segmentation result determined by the embodiment of the present invention is significantly higher than the accuracy of the skeleton segmentation result determined by other existing skeleton segmentation methods.

[0129] Fig.10 The schematic diagram of the structure of the image segmentation device for bone image data provided by the embodiment of the present invention. Fig.10 As shown, the device comprises:

[0130] An initial point set module 310 is used to determine an initial point set corresponding to an initial active contour set in the bone CT image, where all bones in the bone CT image are in the initial active contour;

[0131] A weight matrix module 320 is used to determine a weight matrix of the bone CT image based on a weight function, wherein the weight matrix includes a weighted sum of a grayscale weight and a gradient weight of each pixel in the bone CT image, wherein the weight function includes a grayscale term and a gradient term both of which are monotonically decreasing functions, wherein the grayscale term is used to determine a grayscale weight of a pixel that does not meet a soft tissue grayscale condition, and wherein the gradient term is used to determine a gradient weight of a pixel that does not meet a soft tissue gradient condition;

[0132] An iterative solution module 330, configured to solve an iterative equation based on the initial point set, the weight matrix and a predetermined iterative step size to obtain a target active contour that coincides with the bone boundary, wherein the iterative equation is a gradient flow equation that minimizes an energy functional, wherein the energy functional optimizes the active contour based on a weighted sum of a weighted perimeter and a weighted area of ​​the active contour, wherein the weights used in determining the weighted perimeter and the weighted area come from the weight matrix;

[0133] The segmentation module 340 is used to determine the bone segmentation result corresponding to the target active contour in the bone CT image.

[0134] In one embodiment, the soft tissue grayscale condition is a grayscale threshold;

[0135] The soft tissue gradient condition is a gradient threshold;

[0136] The grayscale threshold is greater than or equal to the first grayscale value and less than or equal to the second grayscale value;

[0137] The first grayscale value is the maximum value of the soft tissue pixel grayscale values ​​used in browsing the bone CT image;

[0138] The second grayscale value is the minimum value of the bone pixel grayscale values ​​used in browsing the bone CT image;

[0139] The gradient threshold is greater than or equal to zero and less than or equal to a third grayscale value, and the third grayscale value is equal to the difference between the second grayscale value and the first grayscale value.

[0140] In one embodiment, the predetermined iteration step size includes a time step size and an adaptive step size based on a boundary distance, the adaptive step size is determined based on the distance between each pixel in the active contour and a bone boundary, and the distance between each pixel in the active contour and a bone boundary is extracted from a first boundary distance set;

[0141] The first boundary distance set includes the normalized distance between each pixel in the bone CT image and the bone boundary.

[0142] In one embodiment, the boundary distance module 350 (see Fig.11 ) determines a first boundary distance set, the boundary distance module comprising:

[0143] A bone boundary unit, used to determine a bone boundary set corresponding to the bone CT image;

[0144] A distance unit, used to determine the distance between each pixel in the bone CT image and the bone boundary corresponding to the bone boundary set, so as to obtain the distance between each pixel in the bone CT image and the bone boundary;

[0145] The normalization unit is used to summarize the distances between all the pixels and the bone boundaries as a second boundary distance set, and normalize each distance in the second boundary distance set to obtain a first boundary distance set.

[0146] In one embodiment, the boundary distance module further includes a fracture boundary unit, the fracture boundary unit including:

[0147] A fracture boundary subunit, used for acquiring a pixel set at a fracture location in the bone CT image, and using the pixel set at the fracture location as a fracture boundary set;

[0148] An updating subunit is used to add the fracture boundary set to the bone boundary set to update the bone boundary set.

[0149] In one embodiment, the fracture boundary subunit is specifically used to:

[0150] In response to a confirmation operation on a fracture edge delineation result in a fracture edge drawing mode, determining all pixels in the bone CT image corresponding to the fracture edge delineation result;

[0151] All pixels in the bone CT image corresponding to the fracture edge delineation result are taken as the fracture boundary set.

[0152] In one embodiment, Fig.12 As shown, the device further includes a post-processing module 360, which is used to:

[0153] Performing a hole removal operation and / or a slit removal operation on the bone part in the bone segmentation result to obtain an updated bone segmentation result;

[0154] The updated bone segmentation result is binarized to obtain a mask for the target bone.

[0155] In one embodiment, Fig.13 As shown, the device further includes an application module 370, and the application module 370 is used to:

[0156] Tool parameters are determined based on the bone segmentation result, where the tool parameters are parameters of the bone fixation tool for the fracture.

[0157] In a bone CT image, the grayscale value of a bone pixel is higher than the grayscale value of a surrounding soft tissue pixel, and the gradient change value of a pixel at a bone boundary is higher than the gradient change value of a pixel in other areas; in the technical solution provided by an embodiment of the present invention, a weight function includes a grayscale term and a gradient term, both of which are monotonically decreasing functions, the grayscale term is used to determine the grayscale weight of a pixel that does not meet the soft tissue grayscale condition, and the gradient term is used to determine the gradient weight of a pixel that does not meet the soft tissue gradient condition; this feature makes the weight of a soft tissue pixel significantly different from the weight of a bone pixel, weakens the contribution of soft tissue to the weighted area and weighted perimeter determined by an energy functional, thereby reducing the influence of soft tissue on the accuracy of the weighted area and weighted perimeter of an active contour, and in the process of minimizing the energy functional, controls the active contour to accurately approach the bone boundary, obtains an accurate target active contour, and thereby determines a bone segmentation result with high accuracy based on the target active contour.

[0158] The image segmentation device applicable to bone image data provided by the embodiment of the present invention can execute the image segmentation method applicable to bone image data provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0159] Fig.14 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0160] like Fig.14 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0161] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0162] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 performs the various methods and processes described above, such as an image segmentation method applicable to bone image data.

[0163] In some embodiments, the image segmentation method applicable to bone image data can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the image segmentation method applicable to bone image data described above can be executed. Alternatively, in other embodiments, processor 11 can be configured to execute the image segmentation method applicable to bone image data by any other appropriate means (e.g., by means of firmware).

[0164] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0165] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0166] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0167] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0168] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0169] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0170] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements an image segmentation method applicable to bone image data as provided in any embodiment of the present application.

[0171] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0172] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0173] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An image segmentation method suitable for bone image data, characterized in that: include: Determine an initial point set corresponding to an initial active contour set in the bone CT image, wherein all bones in the bone CT image are in the initial active contour; Determining a weight matrix of the bone CT image based on a weight function, the weight matrix comprising a weighted sum of a grayscale weight and a gradient weight of each pixel in the bone CT image, the weight function comprising a grayscale term and a gradient term both being monotonically decreasing functions, the grayscale term being used to determine a grayscale weight of a pixel that does not meet a soft tissue grayscale condition, and the gradient term being used to determine a gradient weight of a pixel that does not meet a soft tissue gradient condition; Solving an iterative equation based on the initial point set, the weight matrix and a predetermined iteration step size to obtain a target active contour that coincides with the bone boundary, wherein the iterative equation is a gradient flow equation that minimizes an energy functional, wherein the energy functional optimizes the active contour based on a weighted sum of a weighted perimeter and a weighted area of ​​the active contour, and the weights used in determining the weighted perimeter and the weighted area come from the weight matrix; In the bone CT image, a bone segmentation result corresponding to the target active contour is determined.

2. The method according to claim 1, characterized in that The soft tissue grayscale condition is a grayscale threshold; The soft tissue gradient condition is a gradient threshold; The grayscale threshold is greater than or equal to the first grayscale value and less than or equal to the second grayscale value; The first grayscale value is the maximum value of the soft tissue pixel grayscale values ​​used in browsing the bone CT image; The second grayscale value is the minimum value of the bone pixel grayscale values ​​used in browsing the bone CT image; The gradient threshold is greater than or equal to zero and less than or equal to a third grayscale value, and the third grayscale value is equal to the difference between the second grayscale value and the first grayscale value.

3. The method according to claim 1, characterized in that The predetermined iteration step size includes a time step size and an adaptive step size based on a boundary distance, wherein the adaptive step size is determined based on a distance between each pixel in the active contour and a bone boundary, and the distance between each pixel in the active contour and a bone boundary is extracted from a first boundary distance set; The first boundary distance set includes the normalized distance between each pixel in the bone CT image and the bone boundary.

4. The method according to claim 3, characterized in that The first boundary distance set is determined by the following steps: Determine a bone boundary set corresponding to the bone CT image; Determine the distance between each pixel in the bone CT image and the bone boundary corresponding to the bone boundary set to obtain the distance between each pixel in the bone CT image and the bone boundary; The summary result of the distances between all the pixels and the bone boundary is taken as a second boundary distance set, and each distance in the second boundary distance set is normalized to obtain a first boundary distance set.

5. The method according to claim 4, characterized in that Before determining the distance between each pixel in the bone CT image and the bone boundary corresponding to the bone boundary set, the method further includes: Acquire a pixel set at a fracture location in the bone CT image, and use the pixel set at the fracture location as a fracture boundary set; The fracture boundary set is added to the bone boundary set to update the bone boundary set.

6. The method according to claim 5, characterized in that The step of acquiring a pixel set at a fracture location in the bone CT image and using the pixel set at the fracture location as a fracture boundary set includes: In response to a confirmation operation on a fracture edge delineation result in a fracture edge drawing mode, determining all pixels in the bone CT image corresponding to the fracture edge delineation result; All pixels in the bone CT image corresponding to the fracture edge delineation result are taken as the fracture boundary set.

7. The method according to claim 1, characterized in that After determining the bone segmentation result corresponding to the target active contour in the bone CT image, the method further includes: Performing a hole removal operation and / or a slit removal operation on the bone part in the bone segmentation result to obtain an updated bone segmentation result; The updated bone segmentation result is binarized to obtain a mask for the target bone.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the image segmentation method applicable to bone image data described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the image segmentation method applicable to bone image data as described in any one of claims 1-7 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the image segmentation method applicable to bone image data according to any one of claims 1 to 7.

Images