Intelligent planning method and device for nail channel in hand fracture treatment

Abstract

The present disclosure relates to an intelligent planning method and device for nail channels for hand bone fracture treatment, the method comprising: obtaining a target image of a fractured hand bone; receiving a fractured bone region specified by a user in the target image; performing expansion and corrosion processing on the fractured bone region to separate the fractured bone region into two isolated island-like regions; determining a to-be-fixed nail channel through a preset channel determination strategy based on the two isolated island-like regions; and determining a target nail channel from the to-be-fixed nail channel. In this way, by obtaining a target image of a fractured hand bone, determining the to-be-fixed nail channel through a preset channel strategy, and determining the target nail channel from the to-be-fixed nail channel, the nail channel can be accurately determined based on image data, and intelligent planning of the nail channel can be achieved, the reliability of nail channel planning can be improved, the risk factor of manually determining the nail channel can be reduced, and excessive reliance on doctor's experience can be avoided.

Description

Technical Field

[0001] The present disclosure relates to medical technology, and in particular, to an intelligent planning method and device for nail channels for treating hand bone fractures. Background Art

[0002] Fixing fracture fragments with steel nails after fracture is a common treatment method in modern medicine. Fixing fracture fragments with steel nails can prevent the fracture fragments from being displaced due to the traction of other muscle tissues or ligaments, and ensure that the broken bones are in the correct position and heal in the proper posture. However, if the position of the nail channel is determined incorrectly, the broken bones cannot be completely fixed, or the position is inaccurate, it will have a certain impact on the fracture patient, such as the broken bones healing in an inappropriate position, causing the patient to have difficulty in moving after healing, endure longer or more severe pain, lose consciousness in some areas of nerve damage, and damage blood vessels. However, at present, doctors usually plan the location of the nail channel based on clinical experience, and manually specify the nail channel according to the specific bone fracture situation. The accuracy of the nail channel determined in this way depends entirely on the doctor's experience, lacks reliable data basis, and has low reliability. In addition, the risk factor of the nail channel location determined by doctors who are not particularly experienced in clinical practice will be higher. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent planning method and device for nail channels for hand fracture treatment, which is used to solve the technical problems that the nail channel is currently manually determined, completely relies on experience, lacks data basis, has low reliability, and is high risk.

[0004] In order to achieve the above-mentioned object, the first aspect of the present disclosure provides an intelligent planning method for nail channels for hand fracture treatment, the method comprising:

[0005] Acquire a target image of a fractured hand bone;

[0006] receiving a fractured bone region specified by a user in the target image;

[0007] Performing expansion and corrosion processing on the fractured bone region to separate the fractured bone region into two isolated island-shaped regions;

[0008] Determine the channel for the pins to be placed according to the two island-shaped areas by using a preset channel determination strategy;

[0009] A target nail placement channel is determined from the nail placement channels to be placed.

[0010] Optionally, the preset channel determination strategy includes one or more of the following strategies:

[0011] Obtaining a centroid line connecting the two isolated island-shaped regions, obtaining a target line connecting the center position of the fractured hand bone and the bone surface, and determining a first target angle between the centroid line and the target line, and taking an area in the fractured bone region where the first target angle is less than or equal to a first preset angle threshold as the channel for the pin to be placed;

[0012] Generate a fracture line according to the centroids of the two isolated island-shaped areas by using a preset fracture line generation algorithm, obtain a target line between the center position of the fractured hand bone and the bone surface, determine a second target angle between the fracture line and the target line, and use an area in the fractured bone area where the second target angle is less than or equal to a second preset angle threshold as the channel for the pin to be placed;

[0013] The area of ​​the broken bone region except the bone blood vessels is used as the channel for the nail to be fixed.

[0014] Optionally, in a case where the channel determination strategy includes one strategy, determining the target nail placement channel from the nail placement channels to be placed includes: using the nail placement channel to be placed as the target nail placement channel.

[0015] Optionally, when the channel determination strategy includes a plurality of strategies, determining a target nail placement channel from the nail placement channels to be placed includes:

[0016] Marking the target channel to be determined and the area outside the nail channel to be determined obtained under each strategy with colors to obtain a fractured bone image with color marks;

[0017] Obtaining a Mohr-Weide projection image corresponding to each of the fractured bone images;

[0018] Obtain the weight coefficient corresponding to each channel to be fixed;

[0019] The Moorweide projection images corresponding to the multiple strategies are fused according to the weight coefficient to obtain a fused projection image, and the target nail placement channel is determined from the fused projection image.

[0020] Optionally, obtaining a weight coefficient corresponding to each nail channel to be fixed includes:

[0021] The Moorvida projection graphs under multiple strategies are used as inputs of a pre-trained target neural network model to calculate the weight coefficients.

[0022] Optionally, fusing the Moorweide projection images corresponding to the multiple strategies according to the weight coefficient to obtain a fused projection image, and determining the target nail placement channel from the fused projection image includes:

[0023] Obtain the color value corresponding to each pixel in the Moorweide projection image under each strategy;

[0024] Performing weighted processing on the color values ​​at the same position in a plurality of different Moorweide projection images according to the weight coefficient to obtain a target color value at each position;

[0025] Obtaining the fused projection image according to the target color value at each position;

[0026] The area in the fused projection image where the target color value is within a preset range is determined as the target pin placement channel.

[0027] In a second aspect of the present disclosure, there is provided an intelligent planning device for nail channels for treating hand bone fractures, the device comprising:

[0028] An acquisition module, used for acquiring a target image of a fractured hand bone;

[0029] A receiving module, used for receiving a fractured bone region specified by a user in the target image;

[0030] A processing module, used for performing expansion and corrosion processing on the fractured bone region to separate the fractured bone region into two isolated island regions;

[0031] A first determination module is used to determine a nail channel to be fixed according to the two island-shaped areas by using a preset channel determination strategy;

[0032] The second determining module is used to determine the target nail placement channel from the nail placement channels to be placed.

[0033] Optionally, the preset channel determination strategy includes one or more of the following strategies:

[0034] Obtaining a centroid line connecting the two isolated island-shaped regions, obtaining a target line connecting the center position of the fractured hand bone and the bone surface, and determining a first target angle between the centroid line and the target line, and taking an area in the fractured bone region where the first target angle is less than or equal to a first preset angle threshold as the channel for the pin to be placed;

[0035] Generate a fracture line according to the centroids of the two isolated island-shaped areas by using a preset fracture line generation algorithm, obtain a target line between the center position of the fractured hand bone and the bone surface, determine a second target angle between the fracture line and the target line, and use an area in the fractured bone area where the second target angle is less than or equal to a second preset angle threshold as the channel for the pin to be placed;

[0036] The area of ​​the broken bone region except the bone blood vessels is used as the channel for the nail to be fixed.

[0037] Optionally, when the channel determination strategy includes one strategy, the second determination module is used to:

[0038] The nail placement channel to be fixed is used as the target nail placement channel.

[0039] Optionally, when the channel determination strategy includes multiple strategies, the second determination module includes:

[0040] A coloring submodule, used for coloring the area outside the target channel to be determined and the nail channel to be determined obtained under each strategy, so as to obtain a fractured bone image with color markings;

[0041] A first acquisition submodule is used to acquire a Mohr-Weide projection image corresponding to each of the fractured bone images;

[0042] The second acquisition submodule is used to obtain the weight coefficient corresponding to each nail channel to be fixed;

[0043] The determination submodule is used to fuse the Moorweide projection images corresponding to multiple strategies according to the weight coefficient to obtain a fused projection image, and determine the target nail placement channel from the fused projection image.

[0044] Optionally, the second acquisition submodule is used to:

[0045] The Moorvida projection graphs under multiple strategies are used as inputs of a pre-trained target neural network model to calculate the weight coefficients.

[0046] Optionally, the determining submodule is used to:

[0047] Obtain the color value corresponding to each pixel in the Moorweide projection image under each strategy;

[0048] Performing weighted processing on the color values ​​at the same position in a plurality of different Moorweide projection images according to the weight coefficient to obtain a target color value at each position;

[0049] Obtaining the fused projection image according to the target color value at each position;

[0050] The area in the fused projection image where the target color value is within a preset range is determined as the target pin placement channel.

[0051] The above technical solution obtains a target image of a fractured hand bone; receives a fractured bone region specified by a user in the target image; performs expansion and corrosion processing on the fractured bone region to separate the fractured bone region into two isolated island regions; determines the channel to be fixed by a preset channel determination strategy based on the two isolated island regions; and determines the target nail placement channel from the channels to be fixed. In this way, by obtaining a target image of a fractured hand bone, determining the channel to be fixed by a preset channel strategy, and determining the target nail placement channel from the channels to be fixed, the nail placement channel can be accurately determined based on the image data, and the intelligent planning of the nail placement channel can be realized, which can improve the reliability of the nail placement channel planning and reduce the risk factor of manually determining the nail placement channel.

[0052] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0054] Figure 1 It is a flow chart of an intelligent planning method for nail channels for treating hand bone fractures, shown in an exemplary embodiment of the present disclosure;

[0055] Figure 2 is a schematic diagram of a fracture line on a fracture analysis surface shown in an exemplary embodiment of the present disclosure;

[0056] Figure 3 is based on Figure 1 The illustrated embodiment shows a flow chart of an intelligent planning method for nail channels in the treatment of hand bone fractures;

[0057] Figure 4 It is a block diagram of an intelligent planning device for nail channels for treating hand bone fractures, shown in an exemplary embodiment of the present disclosure;

[0058] Figure 5 is based on Figure 4 The illustrated embodiment shows a block diagram of an intelligent planning device for nail channels in the treatment of hand bone fractures. DETAILED DESCRIPTION

[0059] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0060] Before introducing the specific embodiments of the present invention, the specific application scenarios of the present invention are briefly described. The present invention can be applied to the process of placing steel nails in the fractured bones of patients with fractures in clinical medicine. Fixing the fractured bones with steel nails can avoid the displacement of the fractured bones due to the traction of other muscle tissues or ligaments, and ensure that the fractured bones are in the correct position and healed in an appropriate posture. Among them, the position determination of the nail placement channel is particularly critical. Accurately placing the nail placement channel position will be very beneficial to the patient's bone recovery. If the position of the nail placement channel is determined incorrectly or the position is inaccurate, it will have a certain impact on the fractured patient, such as the fractured bone healing at an inappropriate position, causing the patient to be inconvenient to move after healing, endure longer or more severe pain, lose consciousness in some areas of nerve damage, and damage blood vessels. In the prior art, doctors usually plan the position of the nail placement channel based on clinical experience, and manually specify the nail placement channel according to the specific bone fracture condition. The accuracy of the nail placement channel determined in this way depends entirely on the doctor's experience, lacks reliable data basis, and has low reliability. In addition, the risk factor of the nail placement channel position determined by doctors who are not particularly experienced in clinical practice will be higher.

[0061] In order to solve the above technical problems, the present disclosure provides an intelligent planning method and device for nail channels for hand bone fracture treatment, the method comprises the following steps: obtaining a target image of a fractured hand bone; receiving a fractured bone region specified by a user in the target image; performing expansion and corrosion processing on the fractured bone region to separate the fractured bone region into two isolated island-like regions; determining a to-be-fixed nail channel through a preset channel determination strategy based on the two isolated island-like regions; and determining a target nail channel from the to-be-fixed nail channel. In this way, by obtaining a target image of a fractured hand bone, determining the to-be-fixed nail channel through a preset channel strategy, and determining the target nail channel from the to-be-fixed nail channel, the nail channel can be accurately determined based on image data, and intelligent planning of the nail channel can be achieved, the reliability of nail channel planning can be improved, the risk factor of manually determining the nail channel can be reduced, and excessive reliance on doctor's experience can be avoided.

[0062] Figure 1 is a flow chart of an intelligent planning method for nail channels for hand bone fracture treatment shown in an exemplary embodiment of the present disclosure; Figure 1 , the method may include the following steps:

[0063] Step 101, obtaining a target image of a fractured hand bone.

[0064] The target image may be an X-ray film, a CT (Computed Tomography) film or a MRI film.

[0065] For example, if a patient has a hand fracture, a CT image of the patient's hand bones can be obtained, and the specific broken bones can be determined through the CT image of the hand bones.

[0066] Step 102: receiving a fractured bone region specified by a user in the target image.

[0067] A possible implementation of this step is: based on the GraphCut-3D algorithm, each independent bone can be separated by manual / automatic segmentation.

[0068] For example, based on the GraphCut-3D algorithm, each coherent bone region in the target image is identified, and the target image is divided into multiple coherent bone regions. For a broken bone, if the connection area is greater than a preset area threshold, the two fractured bones in the broken bone can be divided into a coherent bone region. In this case, the user can select the coherent bone region as the broken bone region; for a fractured region, if the coherent area is less than or equal to the preset area, the two fractured bones of the broken bone can be respectively divided into a coherent bone region. In this case, the user can select the two coherent bone regions to be determined as the broken bone regions.

[0069] Step 103, dilating and corroding the broken bone region to separate the broken bone region into two isolated island regions.

[0070] The expansion process is used to fill the edges and internal pits of each fractured bone fragment in the fractured bone region. The corrosion process is used to remove the edge burrs of each fractured bone fragment in the fractured bone region. Multiple corrosion and expansion processes can be used to make the surface corresponding to each fractured bone fragment in the fractured bone region smoother.

[0071] In this step, the image of the broken bone area is expanded and corroded to completely separate the two fracture blocks that were originally connected by flesh and blood, so that the image corresponding to each fracture block forms an island-like area, and finally two island-like areas are obtained.

[0072] Step 104: Determine the nail channel to be placed according to the two isolated island-shaped areas by using a preset channel determination strategy.

[0073] The preset channel determination strategy may include one or more of the following strategies:

[0074] Strategy one, obtain the center of mass connection line of the two isolated island-shaped areas, obtain the target connection line between the center position of the fractured hand bone and the bone surface, and determine the first target angle between the center of mass connection line and the target connection line, and use the area in the broken bone area where the first target angle is less than or equal to the first preset angle threshold as the channel for the pin to be placed.

[0075] It should be noted that the centroid line is the line between the centroid positions of the two isolated island-shaped areas. When the coordinates of each point in the isolated island-shaped area in the target image are determined, the centroid position coordinates (X c ,Y c ,Z c ):

[0076]

[0077] Among them, G represents the mass corresponding to each particle in the material system; X, Y, and Z represent the coordinates of each particle respectively.

[0078] In addition, it should be noted that the first preset angle can be set to 5 degrees, and the area in the fractured bone region where the first target angle is greater than the first preset angle threshold is used as a non-pending nail channel; the non-pending area can be further divided into a prohibited area and an unknown area. A third preset angle threshold can be set, and the area where the first target angle is greater than the first preset angle threshold and less than the second preset angle threshold is determined as an unknown area; the area where the first target angle is greater than the second preset angle threshold is determined as a prohibited area, and the third preset angle threshold is greater than the first preset angle threshold.

[0079] Strategy 2: Generate a fracture line based on the centroids of the two isolated island-like areas through a preset fracture line generation algorithm, obtain the target line between the center position of the fractured hand bone and the bone surface, and determine the second target angle between the fracture line and the target line, and use the area in the broken bone area where the second target angle is less than or equal to the second preset angle threshold as the channel for the pin to be placed.

[0080] The fracture line is the projection of the fracture section between the two isolated island-shaped regions on the fracture analysis surface. The fracture analysis surface is the image presented after the fractured bone region is cut along the long axis direction (longitudinal direction). When determining the fracture line, the fracture analysis surface can be obtained first (see Figure 2 , Figure 2 It is a schematic diagram of a fracture line on a fracture analysis surface shown in an exemplary embodiment of the present disclosure, which includes a first section 201 of an island area on the fracture analysis surface, a second section 202 of another island area on the fracture analysis surface, and a fracture line 203), and then the positions of the centroids of the two island-shaped areas on the fracture analysis surface are determined, and the fracture line is automatically calculated by a 2D graph-cut algorithm based on the positions of the two centroids.

[0081] It should be noted that the second preset angle threshold may be the same as or different from the first preset angle threshold. The area in the fractured bone region where the second target angle is greater than the second preset angle threshold is used as a non-pending nail channel; the non-pending area can be further divided into a prohibited area and an unknown area. A fourth preset angle threshold can be set, and the area where the second target angle is greater than the second preset angle threshold and less than the fourth preset angle threshold is determined as an unknown area; the area where the second target angle is greater than the fourth preset angle threshold is determined as a prohibited area, and the fourth preset angle threshold is greater than the second preset angle threshold.

[0082] Strategy three, the area in the broken bone area except the bone blood vessels is used as the channel for the nail to be fixed.

[0083] It should be noted that the image grayscales of the bone vessels and other regions except the bone vessels on the CT image are different, so the channel for the pin to be fixed can be determined according to the difference in image grayscales.

[0084] Step 105, determining a target nail placement channel from the nail placement channels to be determined.

[0085] Wherein, when the channel determination strategy includes one strategy, the channel to be fixed can be used as the target fixing channel. When the channel determination strategy includes multiple strategies, the target fixing channel can be determined from the channel to be fixed by the following method:

[0086] The target channel to be determined and the area outside the nail placement channel to be determined obtained under each strategy are colored and marked to obtain a broken bone image with a color mark; the Moorverde projection image corresponding to each broken bone image is obtained; the weight coefficient corresponding to each nail placement channel to be determined is obtained; the Moorverde projection images corresponding to multiple strategies are fused according to the weight coefficient to obtain a fused projection image, and the target nail placement channel is determined from the fused projection image.

[0087] It should be noted that the pinning channel to be determined by each strategy can be used as the target pinning channel, but in order to ensure the optimal target pinning channel, the pinning channels obtained under each strategy can be integrated to determine the target pinning channel with the lowest risk. Among them, the weight coefficient can be preset, or it can be calculated by using the Moorweide projection map under multiple strategies as the input of the pre-trained target neural network model. The target neural network model can be trained in the following way:

[0088] The first Mollverde projection map, the second Mollverde projection map, and the third Mollverde projection map corresponding to the target hand bone of multiple completed hand fracture nail placement channel planning in the historical time are obtained to establish a hand fracture nail placement channel planning data set; the target neural network model is obtained by performing machine learning on the hand fracture nail placement channel planning data set, wherein the target neural network model can be the first Mollverde projection map, the second Mollverde projection map, and the third Mollverde projection map as inputs and the weight coefficient as output, and the target neural network model is used to determine the proportion of the color value at each position in the Mollverde projection map determined under each strategy in the final color value corresponding to the corresponding position in the finally determined fusion projection map.

[0089] In the above training method, the first Moorverde projection image can be a CT image of a target hand bone for hand fracture nail placement channel planning that has been completed within the historical time, after the to-be-determined nail placement channel is determined by the above strategy one, the to-be-determined target channel obtained by the strategy one and the area outside the to-be-determined nail placement channel are colored and marked to obtain a first fractured bone image with color markings, and the first fractured bone image is subjected to Moorverde projection equal-area projection to obtain the Moorverde projection image. The second Moorverde projection image can be a CT image of a target hand bone for hand fracture nail placement channel planning that has been completed within the historical time, after the to-be-determined nail placement channel is determined by the above strategy two, the to-be-determined target channel obtained by the strategy two and the area outside the to-be-determined nail placement channel are colored and marked to obtain a second fractured bone image with color markings, and the first fractured bone image is subjected to Moorverde projection equal-area projection to obtain the Moorverde projection image. The third Moorverde projection image can be a CT image of a target hand bone for the hand bone fracture nail placement channel planning that has been completed within the historical time, after the to-be-determined nail placement channel is determined by the above-mentioned strategy three, and the to-be-determined target channel and the area outside the to-be-determined nail placement channel obtained under the strategy three are colored and marked to obtain a third fractured bone image with color markings, and the Moorverde projection image is obtained by performing Moorver projection equal-area projection on the third fractured bone image.

[0090] The above technical scheme, by acquiring the target image of the fractured hand bone, determining the channel to be fixed by a preset channel strategy, and determining the target nail placement channel from the channel to be fixed, can accurately determine the nail placement channel based on the image data, realize the intelligent planning of the nail placement channel, improve the reliability of the nail placement channel planning, and reduce the risk factor of manually determining the nail placement channel.

[0091] Figure 3 is based on Figure 1The embodiment shown is a flow chart of an intelligent planning method for nail channels for hand fracture treatment; in the case where the channel determination strategy includes multiple strategies, step 105 can be performed as follows Figure 3 The method shown is implemented in Figure 3 , the step 105 may include the following steps:

[0092] Step 1051, color-marking the target channel to be determined and the area outside the nail channel to be determined obtained under each strategy to obtain a fractured bone image with color markings.

[0093] The nail channel to be fixed and the area other than the nail channel to be fixed can be dyed with different colors respectively, so that the nail channel to be fixed can be clearly distinguished from other areas.

[0094] For example, if the area of ​​the to-be-fixed nail channel obtained under each strategy is dyed green, the prohibited area is dyed red, and the area of ​​uncertainty is dyed yellow, three broken bone images with red, yellow and green markings are obtained.

[0095] Step 1052, obtaining the Moorweide projection image corresponding to each broken bone image.

[0096] For example, after the to-be-fixed nail channel determined by the strategy one is dyed green, the unknown area is dyed yellow, and the forbidden area is dyed red, the first target fractured bone image is obtained, and the first target fractured bone image is subjected to Mohrdahl equal-area projection to obtain a first target Mohrdahl projection map, and the green area on the first target Mohrdahl projection map is the to-be-fixed nail channel. Similarly, the first target Mohrdahl projection map corresponding to the strategy two and the first target Mohrdahl projection map corresponding to the strategy two can be obtained.

[0097] Step 1053, obtaining the weight coefficient corresponding to each nail channel to be fixed.

[0098] Among them, the weight coefficient is used to characterize the weight of the color in the Moorvida projection image obtained under each strategy in the color of the final fused projection image. The weight coefficient can be a pre-set parameter, or it can be calculated by taking the Moorvida projection images under multiple strategies as the input of the pre-trained target neural network model.

[0099] Step 1054, obtaining the color value corresponding to each pixel in the Moorweide projection image under each strategy.

[0100] For example, the color value at pixel A in the first Moorverde projection image obtained by the above strategy one is hexadecimal data CD0000, the color value at pixel A in the second Moorverde projection image obtained by the above strategy two is hexadecimal data 9ACD32, and the color value at pixel A in the third Moorverde projection image obtained by the above strategy three is hexadecimal data EEE00.

[0101] Step 1055, weighting the color values ​​at the same position in a plurality of different Moorweide projection images according to the weight coefficient to obtain a target color value at each position.

[0102] For example, the weight coefficient of the color value in the first Moorverde projection image in the target color value corresponding to the fused projection image is 0.4, the weight coefficient of the color value in the second Moorverde projection image in the target color value corresponding to the fused projection image is 0.4, and the weight coefficient of the color value in the third Moorverde projection image in the target color value corresponding to the fused projection image is 0.2. Still taking the above pixel A as an example, the target color value is:

[0103] CD0000×0.4+9ACD32×0.4+EEE00×0.2.

[0104] Step 1056, obtaining the fused projection image according to the target color value at each position.

[0105] A possible implementation of this step is: displaying the corresponding target color value at each position, so as to obtain the fused projection image.

[0106] Step 1057, determining the area in the fused projection image where the target color value is within a preset range as the target pin placement channel.

[0107] Among them, the preset range can be determined according to the diameter of the steel nail to be used. The steel nail to be used is a device to be placed in the nail placement channel for fixing the bone fragment. The larger the diameter of the steel nail to be used, the larger the preset range.

[0108] The above technical scheme performs weighted processing on the color values ​​at the same position in multiple different Moorvida projection images according to the weight coefficient to obtain the target color value at each position, obtains the fused projection image according to the target color value at each position, and determines the area in the fused projection image where the target color value is within a preset range as the target pin placement channel. It can accurately determine the pin placement channel based on image data, realize intelligent planning of the pin placement channel, improve the reliability of pin placement channel planning, and reduce the risk factor of manually determining the pin placement channel.

[0109] Figure 4 is a block diagram of an intelligent planning device for nail channels for hand bone fracture treatment, shown in an exemplary embodiment of the present disclosure; see Figure 4 , the device comprises:

[0110] An acquisition module 401 is used to acquire a target image of a fractured hand bone;

[0111] A receiving module 402 is used to receive a fractured bone region specified by a user in the target image;

[0112] The processing module 403 is used to perform expansion and corrosion processing on the broken bone region to separate the broken bone region into two isolated island regions;

[0113] A first determination module 404 is used to determine a nail channel to be fixed according to the two isolated island-shaped areas by using a preset channel determination strategy;

[0114] The second determining module 405 is used to determine a target nail placement channel from the nail placement channels to be placed.

[0115] The above technical scheme acquires the target image of the fractured hand bone through the acquisition module 401, determines the channel to be fixed according to the preset channel strategy through the first determination module 404, and determines the target nail placement channel from the channel to be fixed through the second determination module 405. It can accurately determine the nail placement channel based on the image data, realize the intelligent planning of the nail placement channel, improve the reliability of the nail placement channel planning, and reduce the risk factor of manually determining the nail placement channel.

[0116] Optionally, the preset channel determination strategy includes one or more of the following strategies:

[0117] Obtaining a centroid line connecting the two isolated island-shaped regions, obtaining a target line connecting the center position of the fractured hand bone and the bone surface, and determining a first target angle between the centroid line and the target line, and taking an area in the fractured bone region where the first target angle is less than or equal to a first preset angle threshold as the channel for the pin to be placed;

[0118] Generate a fracture line according to the centroids of the two isolated island-shaped regions by using a preset fracture line generation algorithm, obtain a target line between the center position of the fractured hand bone and the bone surface, determine a second target angle between the fracture line and the target line, and use an area in the fractured bone region where the second target angle is less than or equal to a second preset angle threshold as the channel for the pin to be placed;

[0119] The area of ​​the broken bone region except the bone blood vessels is used as the channel for the nail to be fixed.

[0120] Optionally, when the channel determination strategy includes one strategy, the second determination module 405 is used to:

[0121] The channel to be fixed for nail placement is used as the target nail placement channel.

[0122] Figure 5 is based on Figure 4 The embodiment shown is a block diagram of an intelligent planning device for nail channels in the treatment of hand bone fractures; see Figure 5 In the case where the channel determination strategy includes multiple strategies, the second determination module 405 includes:

[0123] The coloring submodule 4051 is used to color the area outside the target channel to be determined and the nail channel to be determined obtained under each strategy to obtain a fractured bone image with color markings;

[0124] The first acquisition submodule 4052 is used to acquire a Mohr-Weide projection image corresponding to each fractured bone image;

[0125] The second acquisition submodule 4053 is used to obtain the weight coefficient corresponding to each nail channel to be fixed;

[0126] The determination submodule 4054 is used to fuse the Moorweide projection images corresponding to multiple strategies according to the weight coefficient to obtain a fused projection image, and determine the target nail placement channel from the fused projection image.

[0127] Optionally, the second acquisition submodule 4053 is used to:

[0128] The Moorvida projection graphs under multiple strategies are used as inputs of a pre-trained target neural network model to calculate the weight coefficients.

[0129] Optionally, the determination submodule 4054 is used to:

[0130] Obtain the color value corresponding to each pixel in the Mohrweider projection image under each strategy;

[0131] Performing weighted processing on the color values ​​at the same position in a plurality of different Moorweide projection images according to the weight coefficient to obtain a target color value at each position;

[0132] Obtain the fused projection image according to the target color value at each position;

[0133] The area in the fused projection image where the target color value is within a preset range is determined as the target pinning channel.

[0134] The above technical scheme, by determining the submodule, performs weighted processing on the color values ​​at the same position in multiple different Moorvida projection images according to the weight coefficient to obtain the target color value at each position, obtains the fused projection image according to the target color value at each position, and determines the area in the fused projection image where the target color value is within a preset range as the target pin placement channel. It can accurately determine the pin placement channel based on image data, realize intelligent planning of the pin placement channel, improve the reliability of pin placement channel planning, and reduce the risk factor of manually determining the pin placement channel.

[0135] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0136] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0137] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0138] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. An intelligent planning method for nail channels in hand fracture treatment, characterized in that: The method comprises: Acquire a target image of a fractured hand bone; receiving a fractured bone region specified by a user in the target image; Performing expansion and corrosion processing on the fractured bone region to separate the fractured bone region into two isolated island-shaped regions; Determine the channel for the pins to be placed according to the two island-shaped areas by using a preset channel determination strategy; Determine a target nail placement channel from the nail placement channels to be placed; The preset channel determination strategy includes: Obtain a centroid line connecting the two isolated island-shaped areas, obtain a target line connecting the center position of the fractured hand bone and the bone surface, and determine a first target angle between the centroid line and the target line, and use the area in the fractured bone area where the first target angle is less than or equal to a first preset angle threshold as the channel for the pin to be placed.

2. The method according to claim 1, characterized in that The preset channel determination strategy also includes: Generate a fracture line according to the centroids of the two isolated island-shaped areas by using a preset fracture line generation algorithm, obtain a target line between the center position of the fractured hand bone and the bone surface, determine a second target angle between the fracture line and the target line, and use an area in the fractured bone area where the second target angle is less than or equal to a second preset angle threshold as the channel for the pin to be placed; or The area of ​​the broken bone region except the bone blood vessels is used as the channel for the nail to be fixed.

3. The method according to claim 2, characterized in that In the case that the channel determination strategy includes one strategy, determining the target nail placement channel from the nail placement channels to be placed includes: using the nail placement channel to be placed as the target nail placement channel.

4. The method according to claim 2, characterized in that: In the case where the channel determination strategy includes a plurality of strategies, determining a target nail placement channel from the nail placement channels to be placed includes: Marking the to-be-fixed nail channel and the area outside the to-be-fixed nail channel obtained under each strategy with colors to obtain a fractured bone image with color markings; Obtaining a Mohr-Weide projection image corresponding to each of the fractured bone images; Obtain the weight coefficient corresponding to each channel to be fixed; The Moorweide projection images corresponding to the multiple strategies are fused according to the weight coefficient to obtain a fused projection image, and the target nail placement channel is determined from the fused projection image.

5. The method according to claim 4, characterized in that The step of obtaining the weight coefficient corresponding to each nail channel to be fixed includes: The Moorvida projection graphs under multiple strategies are used as inputs of a pre-trained target neural network model to calculate the weight coefficients.

6. The method according to claim 4, characterized in that The step of fusing the Moorweide projection images corresponding to the multiple strategies according to the weight coefficient to obtain a fused projection image, and determining the target nail placement channel from the fused projection image comprises: Obtain the color value corresponding to each pixel in the Moorweide projection image under each strategy; Performing weighted processing on the color values ​​at the same position in a plurality of different Moorweide projection images according to the weight coefficient to obtain a target color value at each position; Obtaining the fused projection image according to the target color value at each position; The area in the fused projection image where the target color value is within a preset range is determined as the target pin placement channel.

7. An intelligent planning device for nail channels in hand fracture treatment, characterized in that: The device comprises: An acquisition module, used for acquiring a target image of a fractured hand bone; A receiving module, used for receiving a fractured bone region specified by a user in the target image; A processing module, used for performing expansion and corrosion processing on the fractured bone region to separate the fractured bone region into two isolated island regions; A first determination module is used to determine a nail channel to be fixed according to the two island-shaped areas by using a preset channel determination strategy; A second determination module is used to determine a target nail placement channel from the nail placement channels to be placed; The preset channel determination strategy includes: Obtain a centroid line connecting the two isolated island-shaped areas, obtain a target line connecting the center position of the fractured hand bone and the bone surface, and determine a first target angle between the centroid line and the target line, and use the area in the fractured bone area where the first target angle is less than or equal to a first preset angle threshold as the channel for the pin to be placed.

8. The device according to claim 7, characterized in that The preset channel determination strategy also includes: Generate a fracture line according to the centroids of the two isolated island-shaped areas by using a preset fracture line generation algorithm, obtain a target line between the center position of the fractured hand bone and the bone surface, determine a second target angle between the fracture line and the target line, and use an area in the fractured bone area where the second target angle is less than or equal to a second preset angle threshold as the channel for the pin to be placed; or The area of ​​the broken bone region except the bone blood vessels is used as the channel for the nail to be fixed.

9. The device according to claim 8, characterized in that In the case where the channel determination strategy includes one strategy, the second determination module is used to: The nail placement channel to be fixed is used as the target nail placement channel.

10. The device according to claim 8, characterized in that In the case where the channel determination strategy includes a plurality of strategies, the second determination module includes: A coloring submodule, used for coloring the to-be-fixed nail channel and the area outside the to-be-fixed nail channel obtained under each strategy, so as to obtain a fractured bone image with color markings; A first acquisition submodule is used to acquire a Mohr-Weide projection image corresponding to each of the fractured bone images; The second acquisition submodule is used to obtain the weight coefficient corresponding to each nail channel to be fixed; The determination submodule is used to fuse the Moorweide projection images corresponding to multiple strategies according to the weight coefficient to obtain a fused projection image, and determine the target nail placement channel from the fused projection image.

Images