A CT image processing and medical navigation method, device and storage medium

Abstract

Embodiments of the present application provide a CT image processing and medical navigation method, device and storage medium. In the method, a CT image of a chest part of a user can be acquired, the chest part containing a plurality of blood vessels and a trachea; threshold segmentation is performed on the CT image to obtain a trachea stem structure; when the number of trachea branches contained in the trachea stem structure is less than a threshold value, a direction feature and a position feature of the plurality of blood vessels in the CT image are extracted; according to the direction feature and the position feature of the plurality of blood vessels, region growing is performed on terminal branches in the plurality of trachea branches to obtain new trachea branches, and when the number of trachea branches of the trachea stem structure is not less than the threshold value, the growing is stopped to obtain a trachea global structure. In this way, when the quality of the CT image is poor and a relatively complete trachea structure cannot be obtained, region growing is performed on the basis of the trachea stem structure according to the blood vessel feature information to obtain a relatively complete trachea global structure more accurately.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical devices, and in particular to a CT image processing and medical navigation method, device and storage medium. BACKGROUND

[0002] At present, in clinical practice, each bronchus region contained in an image can be segmented based on a CT image of a lung region of a patient. A navigation path to a lesion in the patient's body can be further planned through the segmentation result. The related prior art of bronchus segmentation is often limited by the quality of the CT image. When the CT image quality is poor (for example, the image has heavy artifacts), the accuracy of bronchus region segmentation is low.

[0003] Therefore, a solution is urgently needed. SUMMARY

[0004] Aspects of the present application provide a CT image processing and medical navigation method, device and storage medium to improve the accuracy of bronchus region segmentation.

[0005] The CT image processing method provided by the embodiments of the present application comprises: acquiring a CT image of a target chest part, the target chest part containing a plurality of bronchi and a plurality of blood vessels, and the plurality of bronchi having a branching relationship; performing threshold segmentation processing on the CT image according to a pixel threshold corresponding to a bronchus to obtain a bronchus trunk structure containing a plurality of bronchus branches; when the number of bronchus branches of the bronchus trunk structure is less than a preset threshold, extracting blood vessel feature information in the CT image; the blood vessel feature information at least includes respective direction features and position features of the plurality of blood vessels; and performing region growing on end branches in the plurality of bronchus branches respectively according to the respective direction features and position features of the plurality of blood vessels contained in the blood vessel feature information to generate new bronchus branches, and stopping growing when the number of bronchus branches of the bronchus trunk structure is not less than the preset threshold to obtain a global bronchus structure.

[0006] Further optionally, performing threshold segmentation processing on the CT image according to a pixel threshold corresponding to a bronchus to obtain a bronchus trunk structure comprises: determining at least one seed point for region growing from the CT image, the at least one seed point being determined according to a preset selection rule or in response to a seed point selection operation for the CT image; screening pixel points in a neighborhood of each of the at least one seed point according to the pixel threshold corresponding to the bronchus to obtain at least one pixel point set with a pixel value less than the pixel threshold; generating a bronchus branch according to the at least one pixel point set, and stopping region growing when the generated bronchus branch does not meet a preset shape condition to obtain the bronchus trunk structure.

[0007] Further optionally, according to the respective direction features and position features of the plurality of blood vessels, a terminal branch in the plurality of airway branches is respectively subjected to region growing to generate a new airway branch, comprising: extracting a center line of the airway trunk structure through each branch; the center line comprises a plurality of center points; determining a center point meeting a preset terminal branch condition from the plurality of center points, and determining a terminal branch at the end of the airway trunk structure according to the center point; according to the respective direction features and position features of the plurality of blood vessels, determining a target blood vessel from the plurality of blood vessels, which has a feature similarity with the terminal branch meeting a preset condition; and according to the direction feature of the target blood vessel, subjecting the terminal branch to region growing to generate the new airway branch.

[0008] Further optionally, according to the respective direction features and position features of the plurality of blood vessels, a terminal branch in the plurality of airway branches is respectively subjected to region growing to generate a new airway branch, comprising: extracting a center line of the airway trunk structure through each branch; the center line comprises a plurality of center points; determining a center point meeting a preset terminal branch condition from the plurality of center points, and determining a terminal branch at the end of the airway trunk structure according to the center point; according to the respective direction features and position features of the plurality of blood vessels, determining a target blood vessel from the plurality of blood vessels, which has a feature similarity with the terminal branch meeting a preset condition; and according to the direction feature of the target blood vessel, subjecting the terminal branch to region growing to generate the new airway branch.

[0009] Further optionally, according to the respective direction features and position features of the plurality of blood vessels, a terminal branch in the plurality of airway branches is respectively subjected to region growing to generate a new airway branch, comprising: extracting a center line of the airway trunk structure through each branch; the center line comprises a plurality of center points; determining a center point meeting a preset terminal branch condition from the plurality of center points, and determining a terminal branch at the end of the airway trunk structure according to the center point; according to the respective direction features and position features of the plurality of blood vessels, determining a target blood vessel from the plurality of blood vessels, which has a feature similarity with the terminal branch meeting a preset condition; and according to the direction feature of the target blood vessel, subjecting the terminal branch to region growing to generate the new airway branch.

[0010] Further optionally, judging whether the target branch satisfies the condition of being a trachea branch by using a preset judging rule and a radius of the target branch, comprises: using the preset judging rule, when the radius of the target branch is not less than a preset radius threshold, if there is a trachea wall or a blood vessel wall in a preset range of the target branch, the target branch is a trachea branch; when the radius of the target branch is less than the preset radius threshold, obtaining other trachea branches in a growth direction of the target branch, if the target branch and the other trachea branches have connectivity, the target branch is a trachea branch.

[0011] The embodiment of the present application further provides a medical navigation method, comprising: acquiring a CT image of a target chest part, the target chest part containing a plurality of trachea and a plurality of blood vessels, and the plurality of trachea having a branching relationship; performing threshold segmentation processing on the CT image according to a pixel threshold corresponding to the trachea to obtain a trachea stem structure containing a plurality of trachea branches; when the number of trachea branches of the trachea stem structure is less than a preset threshold, extracting blood vessel feature information in the CT image; the blood vessel feature information at least includes respective running direction features and position features of the plurality of blood vessels; according to the respective running direction features and position features of the plurality of blood vessels contained in the blood vessel feature information, performing region growing on terminal branches in the plurality of trachea branches respectively to generate new trachea branches, and stopping growing when the number of trachea branches of the trachea stem structure is not less than the preset threshold to obtain a trachea global structure; and navigating the medical probe to a lesion in the target chest part according to the trachea global structure.

[0012] Further optionally, the method is suitable for a magnetic navigation robot.

[0013] The embodiment of the present application further provides an electronic device, comprising: a memory and a processor; wherein the memory is used for storing one or more computer instructions; and the processor is used for executing the one or more computer instructions to perform steps in any one of the CT image processing method or the medical navigation method.

[0014] The embodiment of the present application further provides a computer readable storage medium, when the computer program is executed by a processor, the processor can implement steps in any one of the CT image processing method or the medical navigation method.

[0015] In the embodiment, a CT image of a chest part of a user can be acquired, the chest part containing a plurality of blood vessels and a trachea; threshold segmentation is performed on the CT image to obtain a trachea stem structure; when the number of trachea branches contained in the trachea stem structure is less than a threshold, a direction feature and a position feature of the plurality of blood vessels in the CT image are extracted; according to the direction feature and the position feature of the plurality of blood vessels, a terminal branch in the plurality of trachea branches is respectively grown to obtain a new trachea branch, and when the number of trachea branches of the trachea stem structure is not less than the threshold, the growth is stopped to obtain a trachea global structure. In this way, when the quality of the CT image is poor and a relatively complete trachea structure cannot be obtained, the trachea global structure can be obtained more accurately based on the trachea stem structure and the blood vessel feature information. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and serve to explain the principles of the application, and do not limit the application. In the drawings:

[0017] Figure 1 A flowchart of a CT image processing method according to an example embodiment of the application is shown in FIG. 1;

[0018] Figure 2 A schematic diagram of a terminal branch according to an example embodiment of the application is shown in FIG. 2;

[0019] Figure 3 A schematic diagram of the terminal branch extension line according to an example embodiment of the application is shown in FIG. 3;

[0020] Figure 4 A flowchart of a medical navigation method according to an example embodiment of the application is shown in FIG. 4;

[0021] Figure 5 A schematic diagram of a navigation path according to an example embodiment of the application is shown in FIG. 5;

[0022] Figure 6 A schematic diagram of an electronic device according to an example embodiment of the application is shown in FIG. 6. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions and advantages of the application clearer, the technical solutions of the application will be described below in detail with reference to the embodiments of the application and the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the application, but not all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the application.

[0024] Currently, in clinical practice, each airway region contained in an image can be segmented based on a CT image of a lung region of a patient. A navigation path to a lesion in the patient can be further planned through the segmentation result. The related prior art of airway segmentation is often limited by the quality of the CT image, and when the CT image quality is poor (for example, the image has heavy artifacts), the accuracy of the airway region segmentation is low.

[0025] To solve the above technical problems, in some embodiments of the present application, a solution is provided, which will be described in detail below in combination with the drawings.

[0026] Figure 1 is a flowchart of a CT image processing method provided by an exemplary embodiment of the present application, as shown in Figure 1 the method comprises:

[0027] Step 11, obtaining a CT image of a target chest site, the target chest site containing a plurality of airways and a plurality of blood vessels, and the plurality of airways having a branching relationship.

[0028] Step 12, performing threshold segmentation processing on the CT image according to a pixel threshold corresponding to the airway to obtain an airway trunk structure containing a plurality of airway branches.

[0029] Step 13, when the number of airway branches of the airway trunk structure is less than a preset threshold, extracting blood vessel feature information in the CT image; the blood vessel feature information at least includes respective direction features and position features of the plurality of blood vessels.

[0030] Step 14, according to the respective direction features and position features of the plurality of blood vessels contained in the blood vessel feature information, respectively performing region growing on terminal branches of the plurality of airway branches to generate new airway branches, and stopping growing when the number of airway branches of the airway trunk structure is not less than the preset threshold to obtain an airway global structure.

[0031] The present embodiment can be executed by an electronic device, which can include a mobile phone, a tablet computer, a computer, a magnetic navigation robot, a medical control terminal, and the like, and the present embodiment is not limited thereto.

[0032] In the present embodiment, the electronic device can obtain a CT image (i.e. a chest CT) of a target chest site. The target chest site can be a lung, and the target chest site can contain a plurality of airways and a plurality of blood vessels, and the plurality of airways have a branching relationship. It should be noted that in the lung CT, the lung parenchyma region contains airways, blood vessels and lung nodules, wherein the airway wall and the blood vessel wall have similar characteristics, and there are many blood vessels near the airways (i.e. within a certain range) in the lung, the airways and the blood vessels in the lung are interdependent, and there is a correlation between the direction of the airways and the direction of the blood vessels near the airways.

[0033] The electronic device can perform threshold segmentation processing on the CT image according to the pixel threshold corresponding to the trachea to obtain a trachea stem structure containing a plurality of tracheal branches. Wherein, the electronic device can obtain the preset pixel threshold corresponding to the trachea from the memory, or obtain the pixel threshold corresponding to the trachea in response to the setting operation of the tracheal pixel threshold, or determine the pixel threshold corresponding to the trachea based on the CT image by using the preset tracheal pixel threshold setting rule, which is not limited in the embodiment. Specifically, the electronic device can use the pixel threshold corresponding to the trachea to start region growing from at least one seed point of region growing, and perform region growing by merging adjacent pixel points with similar characteristics of each seed point, thereby obtaining a trachea stem structure containing a plurality of tracheal branches.

[0034] It should be noted that in the case of poor CT image quality, such as the presence of artifacts, the electronic device cannot identify the complete tracheal structure based on the CT image. Therefore, the electronic device can conditionally judge the number of tracheal branches of the trachea stem structure to determine whether the CT image quality is poor and whether the generated trachea stem structure is complete.

[0035] Wherein, when the number of tracheal branches of the trachea stem structure is not less than the preset threshold, it means that the possibility of poor CT image quality is low, and the completeness of the trachea stem structure is high. Wherein, the preset threshold can be preset according to actual design requirements, such as 50, 45 or 55, etc., which is not limited in the embodiment.

[0036] When the number of tracheal branches of the trachea stem structure is less than the preset threshold, it means that the CT image quality is poor, the number of tracheal branches of the trachea stem structure is insufficient, and the completeness of the trachea stem structure is low. In this case, the electronic device can extract the blood vessel feature information in the CT image, wherein the blood vessel feature information at least includes the characteristics of a plurality of blood vessels, and the characteristics of any blood vessel can include a direction feature and a position feature. Wherein, the direction feature is used to represent the extension direction of the blood vessel. The position feature is used to represent the relative position of the blood vessel in the CT image.

[0037] Wherein, when extracting the blood vessel feature information in the CT image, the CT image can be first filtered by Frangi filtering (a kind of blood vessel enhancement method) to highlight the blood vessel region in the CT image, so that the blood vessel region can be extracted, and the characteristics of each blood vessel are determined based on image recognition technology. In addition, the electronic device can also use a pre-trained blood vessel recognition model to perform image recognition on the CT image to obtain the blood vessel feature information in the CT image. The blood vessel recognition model is trained based on CT image samples and blood vessel feature information samples corresponding to the CT image samples.

[0038] After the CT blood vessel feature information is extracted, the electronic device can perform region growing on the terminal branches in the plurality of bronchial branches respectively according to the respective direction features and position features of the plurality of blood vessels contained in the blood vessel feature information to generate new bronchial branches. The terminal branch refers to a branch at the terminal position on the plurality of bronchial branches. The terminal branch can be one or more, which is not limited in the embodiment. As shown in FIG. 8, there are five terminal branches in the two solid boxes. Figure 2

[0039] The electronic device can determine, for any terminal branch, a target blood vessel with the highest feature similarity to the terminal branch from the blood vessels within a certain range of the terminal branch according to the respective direction features and position features of the plurality of blood vessels contained in the blood vessel feature information, and perform region growing on the terminal branch according to the features of the target blood vessel to generate a new bronchial branch.

[0040] In the process of generating new bronchial branches, the electronic device can count the number of bronchial branches of the bronchial trunk structure. When the number of bronchial branches of the bronchial trunk structure is not less than a preset threshold, it means that the number of bronchial branches has reached the requirement, at which time the growing can be stopped to obtain the global bronchial structure.

[0041] In the embodiment, a CT image of a user's chest part can be obtained, which contains a plurality of blood vessels and bronchial tubes. The CT image is subjected to threshold segmentation to obtain a bronchial trunk structure. When the number of bronchial branches contained in the bronchial trunk structure is less than a threshold, the direction features and position features of the plurality of blood vessels in the CT image are extracted. According to the direction features and position features of the plurality of blood vessels, region growing is performed on the terminal branches in the plurality of bronchial branches to obtain new bronchial branches, and the growing is stopped when the number of bronchial branches of the bronchial trunk structure is not less than the threshold to obtain a global bronchial structure. In this way, when the quality of the CT image is poor and a relatively complete bronchial structure cannot be obtained, region growing can be performed on the basis of the bronchial trunk structure according to the blood vessel feature information to obtain a relatively complete global bronchial structure more accurately.

[0042] In some optional embodiments, step 12 "threshold segmentation of the CT image according to the pixel threshold corresponding to the bronchial tube to obtain a bronchial trunk structure" in the foregoing embodiment can be implemented based on the following steps:

[0043] Step 121: determining at least one seed point for region growing from the CT image. The seed point can be regarded as the starting point of region growing. The at least one seed point can be determined according to a preset selection rule or in response to a seed point selection operation on the CT image.

[0044] ​Step 122, according to the pixel threshold corresponding to the trachea, the pixel points in the respective neighborhood of the at least one seed point are screened to obtain at least one pixel point set with a pixel value less than the pixel threshold. The size of the neighborhood can be customized according to design requirements. The pixel value can be the intensity value of the pixel. For any seed point, the electronic device can traverse all pixel points in the neighborhood of the seed point to screen the pixel point set, and the pixel value of the pixel in the pixel point set is less than the pixel threshold.

[0045] Step 123, generating a tracheal branch according to the at least one pixel point set, and stopping region growing when the generated tracheal branch does not meet the preset shape condition to obtain a tracheal stem structure.

[0046] Each pixel point in each pixel point set can form a tracheal branch. The preset shape condition can be that the shape is a long strip, that is, the shape of the trachea. During the region growing process, the electronic device can perform leakage detection on the generated tracheal branch, and if the generated tracheal branch meets the shape condition, the electronic device can determine a new seed point on the generated tracheal branch, and continue to grow from the new seed point by using the above region growing method to obtain a new tracheal branch. If the generated tracheal branch does not meet the shape condition of "long strip shape", the electronic device can stop region growing to obtain a tracheal stem structure.

[0047] In this way, the electronic device can perform threshold segmentation processing on the CT image based on the region growing method to obtain a relatively accurate tracheal stem structure.

[0048] In some optional embodiments, the step 13 in the foregoing embodiments "region growing is performed on the end branches in the plurality of tracheal branches respectively based on the respective direction features and position features of the plurality of blood vessels in the blood vessel feature information to generate new tracheal branches" can be implemented based on the following steps:

[0049] Step 131, extracting a center line of the tracheal stem structure penetrating through each branch. The center line can include a plurality of center points. The electronic device can use a thinning algorithm to extract the center line of the tracheal stem structure penetrating through each branch. Some pixel points not at the center position of the branch can be screened out from the tracheal stem structure by using the thinning algorithm, and the original structure characteristics of the tracheal stem structure are still maintained, and the remaining pixel points are the center points, which can form the center line of the tracheal stem structure penetrating through each branch.

[0050] In step 132, a center point meeting a preset end branch condition is determined from the plurality of center points, and an end branch at the end of the trachea trunk structure is determined according to the center point. The end branch condition can be a position condition that needs to be met by the center point on the end branch. For example, the plurality of trachea branches on the trachea trunk structure can have levels (for example, from a main trachea branch to an end trachea branch, the levels decrease in turn), and the end branch condition can be that the center point is located on a branch at the last level. The electronic device can filter the center point located on the branch at the last level from the plurality of center points. When the center point meeting the preset end branch condition is determined to determine the end branch at the end of the trachea trunk structure, the center point meeting the preset end branch condition can be connected to obtain the end branch, or the center point meeting the preset end branch condition can be fitted to obtain the end branch. The present embodiment is not limited.

[0051] In step 133, a target blood vessel meeting a preset condition in similarity of a feature of the end branch is determined from the plurality of blood vessels according to the respective running feature and position feature of the plurality of blood vessels.

[0052] For any end branch, the electronic device can determine the running feature and position feature of the end branch according to the center point included in the end branch. The electronic device can calculate the relative position of the center point included in the end branch in the CT image to obtain the position feature of the end branch, and determine the extension direction of the end branch as the running feature according to at least two center points in the center point included in the end branch and the relative position of the at least two center points in the CT image. For example, the electronic device can randomly select two center points from the center point included in the end branch, calculate the extension direction of the end branch according to the relative position of the two center points in the CT image, that is, connect the two center points, and the connection direction is the extension direction of the end branch. For another example, the electronic device can randomly select more than two center points (for example, three center points, in turn, point D1, point D2 and point D3) from the center point included in the end branch, calculate the first extension direction of the end branch according to the relative position of point D1 and point D2 in the CT image, calculate the second extension direction of the end branch according to the relative position of point D2 and point D3 in the CT image, and perform weighted average on the first extension direction and the second extension direction to obtain the extension direction of the end branch as the running feature.

[0053] Afterwards, the electronic device can determine a candidate vessel within a certain range of the end branch from the plurality of vessels. Wherein, the size of the certain range of the end branch can be customized according to design requirements in advance, and the embodiment is not limited. Wherein, the number of candidate vessels can be one or more. For any candidate vessel, the electronic device can calculate a first feature difference value of the orientation feature between the candidate vessel and the end branch, and a second feature difference value of the position feature between the candidate vessel and the end branch, and use the preset weight information to weight and sum the first feature difference value and the second feature difference value to obtain the feature similarity of the candidate vessel and the end branch. Wherein, the weight information is used to describe the respective weights of the first feature difference value and the second feature difference value.

[0054] For example, the position feature and the orientation feature of the end branch are N1 and M1 respectively, and the position feature and the orientation feature of the candidate vessel are N2 and M2 respectively. The electronic device can calculate N2-N1 to obtain the second feature difference value, and calculate M2-M1 to obtain the first feature difference value. Assuming that the weight information is that the weights of the first feature difference value and the second feature difference value are a1 and a2 respectively. The electronic device can use the weight information to weight and sum the first feature difference value and the second feature difference value to obtain a1 x (M2-M1) + a2 x (N2-N1), which is the feature similarity of the candidate vessel and the end branch.

[0055] After the electronic device determines the target vessel with similar position and orientation to the end branch from the plurality of vessels by the above method, the electronic device can continue to perform the following step 134:

[0056] Step 134, region growing the end branch according to the orientation feature of the target vessel to generate a new bronchial branch.

[0057] Wherein, the electronic device can take the extension direction represented by the orientation feature of the target vessel as the growth direction of the end branch. Afterwards, the electronic device can take the center point of the end branch as the starting point, and generate center points along the growth direction of the end branch pixel by pixel, wherein the generated center points can be connected to form an end branch extension line. For example, the electronic device can take the center point f1 of the end branch as the starting point, generate the center point f2 at the next pixel point after f1 along the growth direction of the end branch, and generate the center point f3 at the next pixel point after f2, wherein f1, f2 and f3 can be connected to form an end branch extension line. Since the end branch extension line is a line connected by a plurality of center points, and the actual trachea is a long strip shape with a radius. Based on this, the electronic device can use the preset inflation rule to inflate the end branch extension line connected to obtain a target branch connected to the end branch. As shown in the following figure: Figure 3 ​

[0058] After obtaining the target branch, the electronic device can determine whether the target branch meets the condition of being a bronchial branch by using a preset determination rule and a radius of the target branch; if yes, the region growing is continued; if no, the region growing is stopped, and the generated target branch meeting the condition of being a bronchial branch is output.

[0059] The electronic device can determine whether the radius of the target branch is less than a preset radius threshold by using a preset determination rule. The preset radius threshold can be set according to actual design requirements, and can be 1 mm, or 0.9 mm, or the like, which is not limited in the embodiment. If the radius of the target branch is not less than the preset radius threshold, the electronic device can search for a bronchial wall or a blood vessel wall in a preset range of the target branch. If the bronchial wall or the blood vessel wall exists in the preset range of the target branch, the target branch is a bronchial branch. The preset range can be set by the user according to actual design requirements, which is not limited in the embodiment.

[0060] If the radius of the target branch is less than the preset radius threshold, the electronic device can obtain other bronchial branches in the growth direction of the target branch. If the target branch is communicable with the other bronchial branches, the target branch is a bronchial branch. In other words, in the case that the radius of the target branch is less than the preset radius threshold, the electronic device can determine whether the target branch is communicable with other bronchial branches in the growth direction. If the target branch is communicable, the target branch can be regarded as a bronchial branch.

[0061] In this way, even if the quality of the CT image is poor and some bronchial branches cannot be identified, the electronic device can still generate these bronchial branches more accurately with the assistance of the blood vessel feature information, so that a more complete global structure of the bronchus is obtained.

[0062] Correspondingly, the embodiment of the present application also provides a medical navigation method, as shown in Figure 4 The medical navigation method can include the following steps:

[0063] Step 41, obtaining a CT image of a target chest part, the target chest part containing a plurality of bronchi and a plurality of blood vessels, and the plurality of bronchi having a branching relationship.

[0064] Step 42, performing threshold segmentation processing on the CT image according to a pixel threshold corresponding to the bronchus, to obtain a bronchus trunk structure containing a plurality of bronchial branches.

[0065] Step 43, when the number of bronchial branches of the bronchus trunk structure is less than a preset threshold, extracting blood vessel feature information in the CT image; the blood vessel feature information at least includes respective direction features and position features of the plurality of blood vessels.

[0066] Step 44, according to the respective direction features and position features of the plurality of blood vessels contained in the blood vessel feature information, region growing is performed on the terminal branches in the plurality of bronchial branches respectively to generate new bronchial branches, and the growing is stopped when the number of bronchial branches of the bronchial trunk structure is not less than a preset threshold, to obtain the bronchial global structure.

[0067] Step 45, according to the bronchial global structure, navigation of the medical probe to the lesion in the target chest site is performed.

[0068] Optionally, the above method can be performed by a magnetic navigation robot. The magnetic navigation robot can include a processor, a memory, an extracorporeal magnetic field positioning assembly, and a medical probe. As shown in the figure, after obtaining the bronchial global structure, when the magnetic navigation robot performs navigation of the medical probe to the lesion in the target chest site according to the bronchial global structure, the magnetic navigation robot can first plan a navigation path according to the bronchial global structure, and generate corresponding control instructions according to the planned navigation path and send the control instructions to the extracorporeal magnetic field positioning assembly, so that the extracorporeal magnetic field positioning assembly generates corresponding magnetism according to the control instructions to control the medical probe to move under the influence of the magnetic force to the lesion in the target chest site. Figure 5

[0069] Further optionally, according to the pixel threshold corresponding to the bronchus, threshold segmentation processing is performed on the CT image to obtain the bronchial trunk structure, including: determining at least one seed point for region growing from the CT image, the at least one seed point being determined according to a preset selection rule or in response to a seed point selection operation on the CT image; according to the pixel threshold corresponding to the bronchus, screening the pixel points in the neighborhood of each of the at least one seed point to obtain at least one pixel point set with a pixel value less than the pixel threshold; generating a bronchial branch according to the at least one pixel point set, and stopping region growing when the generated bronchial branch does not meet a preset shape condition, to obtain the bronchial trunk structure.

[0070] Further optionally, according to the respective direction features and position features of the plurality of blood vessels contained in the blood vessel feature information, region growing is performed on the terminal branches in the plurality of bronchial branches respectively to generate new bronchial branches, including: extracting a center line of the bronchial trunk structure through each branch; the center line includes a plurality of center points; determining a center point that meets a preset terminal branch condition from the plurality of center points, and determining a terminal branch at the end of the bronchial trunk structure according to the center point; according to the respective direction features and position features of the plurality of blood vessels, determining a target blood vessel from the plurality of blood vessels that has a feature similarity to the terminal branch meeting a preset condition; according to the direction feature of the target blood vessel, region growing is performed on the terminal branch to generate a new bronchial branch.

[0071] ​Further optionally, the target blood vessel is determined from the plurality of blood vessels according to the respective direction feature and position feature of each of the plurality of blood vessels, including: determining the direction feature and position feature of the terminal branch according to the center point included in the terminal branch for any terminal branch; determining candidate blood vessels within a certain range of the terminal branch from the plurality of blood vessels; calculating a first feature difference value of the direction feature between the candidate blood vessel and the terminal branch and a second feature difference value of the position feature between the candidate blood vessel and the terminal branch for any candidate blood vessel; weighting and summing the first feature difference value and the second feature difference value using preset weight information to obtain a feature similarity of the candidate blood vessel and the terminal branch; and determining the blood vessel with the largest feature similarity with the terminal branch from the plurality of candidate blood vessels as the target blood vessel.

[0072] Further optionally, the terminal branch is regionally grown according to the direction feature of the target blood vessel to generate a new bronchial branch, including: taking the extension direction represented by the direction feature of the target blood vessel as the growth direction of the terminal branch; generating the center point of the terminal branch pixel by pixel along the growth direction of the terminal branch from the center point of the terminal branch as the starting point; connecting the generated center points as the extension line of the terminal branch; inflating the extension line of the terminal branch using a preset inflation rule to obtain the target branch connected to the terminal branch; determining whether the target branch meets the condition of being a bronchial branch using a preset determination rule and the radius of the target branch; if yes, continuing the regional growth; if no, stopping the regional growth and outputting the generated target branch meeting the condition of being a bronchial branch.

[0073] Further optionally, the target branch is determined whether it meets the condition of being a bronchial branch using a preset determination rule and the radius of the target branch, including: using the preset determination rule to determine that the target branch is a bronchial branch if there is a bronchial wall or a blood vessel wall within a preset range of the target branch when the radius of the target branch is not less than a preset radius threshold; and determining the other bronchial branches in the growth direction of the target branch when the radius of the target branch is less than the preset radius threshold, and determining that the target branch is a bronchial branch if the target branch has connectivity with the other bronchial branches.

[0074] In this embodiment, a CT image of a target chest part of a user can be acquired, the target chest part of the user containing a plurality of blood vessels and a trachea; threshold segmentation is performed on the CT image to obtain a trachea stem structure; when the number of trachea branches contained in the trachea stem structure is less than a threshold, the direction features and position features of the plurality of blood vessels in the CT image are extracted; according to the direction features and position features of the plurality of blood vessels, region growing is performed on terminal branches in the plurality of trachea branches to obtain new trachea branches, and when the number of trachea branches of the trachea stem structure is not less than the threshold, the growing is stopped to obtain a trachea global structure, and the medical probe is navigated to a lesion in the target chest part according to the trachea global structure. In this way, when the quality of the CT image is poor and a relatively complete trachea structure cannot be obtained, region growing is performed on the basis of the trachea stem structure according to the blood vessel feature information to obtain a relatively complete trachea global structure, so that the medical probe is navigated to the lesion in the target chest part more accurately.

[0075] It should be noted that the execution subject of each step of the method provided in the above embodiments can be the same device, or the method can also be executed by different devices as the execution subject. For example, the execution subject of steps 11 to 14 can be device A; for another example, the execution subject of steps 11 to 12 can be device A, and the execution subject of steps 13 to 14 can be device B; and the like.

[0076] In addition, in some of the processes described in the above embodiments and the accompanying drawings, a plurality of operations appearing in a specific order are included, but it should be clearly understood that these operations can be executed or executed in parallel without the order in which they appear in this text. The serial numbers of the operations, such as 11, 12, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes can include more or fewer operations, and the operations can be executed in sequence or in parallel.

[0077] It should be noted that the "first", "second", and the like in this text are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence. "First" and "second" are not of different types.

[0078] Figure 6 is a structural schematic diagram of an electronic device provided by an exemplary embodiment of the present application, which is suitable for the CT image processing method or medical navigation method provided by the foregoing embodiments. As shown in FIG. 1, the electronic device includes a memory 601, a processor 602, and a display component 603. The electronic device is realized as a mobile phone, a tablet computer, a computer, a magnetic navigation robot, a medical control terminal, and the like, and the present embodiment is not limited thereto. Figure 6

[0079] ​The memory 601 is configured to store computer programs and can be configured to store other various data to support operations on the terminal device. Examples of the data include instructions of any application program or method for operating on the terminal device, contact data, phonebook data, messages, pictures, videos, and the like.

[0080] In some embodiments, the processor 602, coupled with the memory 601, is configured to execute the computer programs in the memory 601, to acquire a CT image of a target chest site, the target chest site containing a plurality of tracheas and a plurality of blood vessels, and the plurality of tracheas having a branching relationship therebetween; perform threshold segmentation processing on the CT image according to a pixel threshold corresponding to the trachea, to obtain a trachea stem structure containing a plurality of trachea branches; when the number of trachea branches of the trachea stem structure is less than a preset threshold, extract blood vessel feature information in the CT image; the blood vessel feature information at least includes respective direction features and position features of the plurality of blood vessels; perform region growing on end branches in the plurality of trachea branches respectively according to the respective direction features and position features of the plurality of blood vessels contained in the blood vessel feature information to generate new trachea branches, and stop growing when the number of trachea branches of the trachea stem structure is not less than the preset threshold, to obtain a trachea global structure.

[0081] Further optionally, when the processor 602 performs threshold segmentation processing on the CT image according to a pixel threshold corresponding to the trachea to obtain a trachea stem structure, it is specifically configured to: determine at least one seed point for region growing from the CT image, the at least one seed point being determined according to a preset selection rule or in response to a seed point selection operation for the CT image; screen pixel points in respective neighborhoods of the at least one seed point according to the pixel threshold corresponding to the trachea, to obtain at least one pixel point set with a pixel value less than the pixel threshold; generate a trachea branch according to the at least one pixel point set, and stop region growing when the generated trachea branch does not conform to a preset shape condition, to obtain the trachea stem structure.

[0082] Further optionally, when the processor 602 generates the new bronchial branch by region growing for the terminal branch according to the respective direction features and position features of the plurality of blood vessels, the processor 602 is specifically configured to: extract a center line of the bronchial trunk structure extending through each branch; the center line includes a plurality of center points; determine a center point that meets a preset terminal branch condition from the plurality of center points, and determine a terminal branch at the end of the bronchial trunk structure according to the center point; determine a target blood vessel from the plurality of blood vessels according to the respective direction features and position features of the plurality of blood vessels, the target blood vessel having a feature similarity to the terminal branch meeting a preset condition; and generate the new bronchial branch by region growing for the terminal branch according to the direction feature of the target blood vessel.

[0083] Further optionally, when the processor 602 determines a target blood vessel from the plurality of blood vessels according to the respective direction features and position features of the plurality of blood vessels, the processor 602 is specifically configured to: for any terminal branch, determine the direction feature and the position feature of the terminal branch according to the center point included in the terminal branch; and determine a candidate blood vessel within a certain range of the terminal branch from the plurality of blood vessels; for any candidate blood vessel, calculate a first feature difference value of the direction feature between the candidate blood vessel and the terminal branch, and a second feature difference value of the position feature between the candidate blood vessel and the terminal branch; weight and sum the first feature difference value and the second feature difference value using preset weight information to obtain a feature similarity of the candidate blood vessel to the terminal branch; and determine a blood vessel having the largest feature similarity to the terminal branch from the plurality of candidate blood vessels as the target blood vessel.

[0084] Further optionally, when the processor 602 generates the new bronchial branch by region growing for the terminal branch according to the direction feature of the target blood vessel, the processor 602 is specifically configured to: take an extension direction represented by the direction feature of the target blood vessel as a growth direction of the terminal branch; generate center points pixel by pixel along the growth direction of the terminal branch from a center point of the terminal branch as a starting point; connect the generated center points to form a terminal branch extension line; dilate the terminal branch extension line using a preset dilation rule to obtain a target branch connected to the terminal branch; determine whether the target branch meets a condition of being a bronchial branch using a preset judgment rule and a radius of the target branch; if yes, continue region growing; and if no, stop region growing and output the generated target branch meeting the condition of being a bronchial branch.

[0085] Further optionally, the processor 602 is configured to determine whether the target branch satisfies the condition of being a tracheal branch by using a preset determination rule and a radius of the target branch, specifically configured to: when the radius of the target branch is not less than a preset radius threshold, if there is a tracheal wall or a blood vessel wall in a preset range of the target branch, the target branch is a tracheal branch; when the radius of the target branch is less than the preset radius threshold, obtain other tracheal branches in a growth direction of the target branch, and if the target branch and the other tracheal branches have connectivity, the target branch is a tracheal branch.

[0086] In some other embodiments, the processor 602, coupled to the memory 601, is configured to execute a computer program in the memory 601 to: obtain a CT image of a target chest site, the target chest site containing a plurality of tracheas and a plurality of blood vessels, and the plurality of tracheas having a branching relationship; perform threshold segmentation processing on the CT image according to a pixel threshold corresponding to a trachea to obtain a tracheal stem structure containing a plurality of tracheal branches; when the number of tracheal branches of the tracheal stem structure is less than a preset threshold, extract blood vessel feature information in the CT image; the blood vessel feature information at least includes respective running direction features and position features of the plurality of blood vessels; according to the respective running direction features and position features of the plurality of blood vessels contained in the blood vessel feature information, respectively perform region growing on terminal branches in the plurality of tracheal branches to generate new tracheal branches, and stop growing when the number of tracheal branches of the tracheal stem structure is not less than the preset threshold to obtain a global tracheal structure; and navigate the medical probe to a lesion in the target chest site according to the global tracheal structure.

[0087] Further optionally, the method is applicable to a magnetic navigation robot.

[0088] Further, Figure 6 The electronic device is only schematically shown with some components, and does not mean that the electronic device only includes Figure 6 The components shown.

[0089] The above Figure 6 The memory 601 in the above embodiments can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0090] Correspondingly, the embodiments of the present application also provide a computer readable storage medium, when a computer program is executed by a processor, the processor can implement the steps in the CT image processing method or the medical navigation method.

[0091] In the embodiment, the electronic device can acquire a CT image of a target chest part of a user, the target chest part of the user containing a plurality of blood vessels and a trachea; perform threshold segmentation on the CT image to obtain a trachea stem structure; extract a running direction feature and a position feature of the plurality of blood vessels in the CT image when a number of trachea branches contained in the trachea stem structure is less than a threshold; and perform region growing on terminal branches in the plurality of trachea branches respectively according to the running direction feature and the position feature of the plurality of blood vessels to obtain new trachea branches, and stop growing to obtain a trachea global structure when the number of trachea branches of the trachea stem structure is not less than the threshold. In this way, when the quality of the CT image is poor and a relatively complete trachea structure cannot be obtained, region growing is performed according to the blood vessel feature information on the basis of the trachea stem structure to obtain a relatively complete trachea global structure more accurately.

[0092] Those skilled in the art should understand that embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0093] The present application is described in reference to the flowcharts and / or block diagrams of the method, device (system), and computer program product according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0094] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction devices that implement the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0095] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 Figure 1

[0096] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0097] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, non-volatile memory, such as read-only memory (ROM), EPROM, and / or flash memory, etc. The memory is an example of computer readable media.

[0098] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic disks storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to computing devices. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "comprising," "including," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0100] ​​The above merely provides an example of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the scope of claims of the present application.

Claims

1. A CT image processing method, characterized in that: include: Acquiring a CT image of a target chest region, wherein the target chest region includes a plurality of tracheas and a plurality of blood vessels, and the plurality of tracheas have a branching relationship between them; performing threshold segmentation processing on the CT image according to a pixel threshold corresponding to the trachea to obtain a tracheal trunk structure including a plurality of tracheal branches; When the number of tracheal branches in the tracheal trunk structure is less than a preset threshold, extracting vascular feature information from the CT image; The blood vessel characteristic information includes at least: the direction characteristics and position characteristics of each of the plurality of blood vessels; Extracting a center line of the tracheal trunk structure passing through each branch; the center line includes multiple center points; Determining a center point that meets a preset terminal branch condition from the multiple center points, and determining a terminal branch at the end of the tracheal trunk structure based on the center point; determining, from the plurality of blood vessels, a target blood vessel whose characteristic similarity to the terminal branch meets a preset condition, based on the direction characteristics and position characteristics of the plurality of blood vessels; According to the direction characteristics of the target blood vessel, the terminal branches are regionally grown to generate new tracheal branches, and the growth is stopped when the number of tracheal branches in the tracheal trunk structure is not less than a preset threshold, thereby obtaining the global tracheal structure.

2. The method according to claim 1, characterized in that Performing threshold segmentation processing on the CT image according to the pixel threshold corresponding to the trachea to obtain the tracheal trunk structure, including: Determining at least one seed point for region growth from the CT image, wherein the at least one seed point is determined according to a preset selection rule or in response to a seed point selection operation on the CT image; Filtering pixel points within a neighborhood of each of the at least one seed point according to the pixel threshold corresponding to the trachea to obtain at least one set of pixel points having pixel values ​​less than the pixel threshold; A tracheal branch is generated according to the at least one pixel point set, and region growing is stopped when the generated tracheal branch does not meet a preset shape condition, thereby obtaining the tracheal trunk structure.

3. The method according to claim 1, characterized in that Determining, from the plurality of blood vessels, a target blood vessel whose characteristic similarity to the terminal branch meets a preset condition, according to the respective direction characteristics and position characteristics of the plurality of blood vessels, includes: For any terminal branch, determining the direction characteristics and position characteristics of the terminal branch according to the center point of the terminal branch; and determining a candidate blood vessel located within a certain range of the terminal branch from multiple blood vessels; For any candidate blood vessel, calculating a first feature difference value of a direction feature between the candidate blood vessel and the terminal branch, and a second feature difference value of a position feature between the candidate blood vessel and the terminal branch; Using preset weight information, performing a weighted summation on the first feature difference and the second feature difference to obtain a feature similarity between the candidate blood vessel and the terminal branch; From the plurality of candidate blood vessels, a blood vessel having the greatest feature similarity to the terminal branch is determined as the target blood vessel.

4. The method according to claim 1, wherein According to the direction characteristics of the target blood vessel, performing regional growth on the terminal branch to generate the new tracheal branch includes: using the extension direction represented by the trend feature of the target blood vessel as the growth direction of the terminal branch; Taking the center point of the terminal branch as a starting point, a center point is generated pixel by pixel along the growth direction of the terminal branch; the generated center points are connected to form an extension line of the terminal branch; Using a preset expansion rule, the extension line of the terminal branch is expanded to obtain a target branch connected to the terminal branch; Using the preset discrimination rules and the radius of the target branch, determine whether the target branch meets the conditions of being a tracheal branch; if so, continue region growing; if not, stop region growing and output the generated target branch that meets the conditions of being a tracheal branch.

5. The method according to claim 4, characterized in that Using a preset discrimination rule and the radius of the target branch, determining whether the target branch meets the conditions for being a tracheal branch includes: Using the preset discrimination rule, when the radius of the target branch is not less than a preset radius threshold, if there is a tracheal wall or a blood vessel wall within a preset range of the target branch, the target branch is a tracheal branch; When the radius of the target branch is smaller than a preset radius threshold, other tracheal branches in the growth direction of the target branch are acquired. If the target branch is connected to the other tracheal branches, the target branch is a tracheal branch.

6. A medical navigation method, characterized in that: include: Acquiring a CT image of a target chest region, wherein the target chest region includes a plurality of tracheas and a plurality of blood vessels, and the plurality of tracheas have a branching relationship between them; performing threshold segmentation processing on the CT image according to a pixel threshold corresponding to the trachea to obtain a tracheal trunk structure including a plurality of tracheal branches; When the number of tracheal branches in the tracheal trunk structure is less than a preset threshold, extracting vascular feature information from the CT image; The blood vessel characteristic information includes at least: the direction characteristics and position characteristics of each of the plurality of blood vessels; Extracting a center line of the tracheal trunk structure passing through each branch; the center line includes multiple center points; Determining a center point that meets a preset terminal branch condition from the multiple center points, and determining a terminal branch at the end of the tracheal trunk structure based on the center point; determining, from the plurality of blood vessels, a target blood vessel whose characteristic similarity to the terminal branch meets a preset condition, based on the direction characteristics and position characteristics of the plurality of blood vessels; According to the direction characteristics of the target blood vessel, regional growth is performed on the terminal branches to generate new tracheal branches, and the growth is stopped when the number of tracheal branches in the tracheal trunk structure is not less than a preset threshold, thereby obtaining a global tracheal structure; The medical probe is navigated to the lesion in the target chest area according to the global tracheal structure.

7. The method according to claim 6, characterized in that The method is applicable to magnetic navigation robots.

8. An electronic device, characterized in that: include: A memory and a processor; wherein the memory is used to: store one or more computer instructions; the processor is used to execute the one or more computer instructions to: perform the steps in the method according to any one of claims 1-5 or claims 6-7.

9. A computer-readable storage medium, characterized in that When the computer program is executed by a processor, the processor is enabled to implement the steps of the method according to any one of claims 1 to 5 or claims 6 to 7.

Images