CN116485846A

CN116485846A - Needle insertion position determining method and device, electronic equipment and readable storage medium

Info

Publication number: CN116485846A
Application number: CN202310226343.9A
Authority: CN
Inventors: 王欣; 王战; 阳光
Original assignee: Shukun Shanghai Medical Technology Co ltd
Current assignee: Shukun Shanghai Medical Technology Co ltd
Priority date: 2022-09-21
Filing date: 2023-03-09
Publication date: 2023-07-25
Anticipated expiration: 2043-03-09
Also published as: CN116485846B; CN115474992A

Abstract

The application discloses a needle insertion position determining method, a device, electronic equipment and a readable storage medium, wherein the method comprises the following steps: acquiring a medical image and a target point in the medical image; classifying the targets according to the position change information of the targets to obtain registration targets and correction targets; registering focus image positions of focuses in the medical image according to target image positions of the registration targets to obtain target focus positions and reference needle inserting positions corresponding to the target focus positions; and correcting the reference needle inserting position according to the target position change information of the correction target point to obtain a corrected target needle inserting position. According to the method, on one hand, the accuracy of registration is improved, the accurate reference needle-inserting position is obtained, and on the other hand, after the reference needle-inserting position is obtained, the reference needle-inserting position is further corrected, so that the accuracy of the needle-inserting position is guaranteed.

Description

Needle insertion position determining method and device, electronic equipment and readable storage medium

Technical Field

The application relates to the technical field of medical treatment, in particular to a needle insertion position determining method, a needle insertion position determining device, electronic equipment and a readable storage medium.

Background

In recent years, minimally invasive surgery is widely applied to the medical field due to the advantages of small wound surface, high surgical cleanliness and the like. The puncture operation belongs to a minimally invasive operation, can directly reach the focus, and can treat and treat the focus in a targeted way.

In the conventional puncture operation process, an automatic or semi-automatic mode is generally adopted to position a puncture point, so that the accuracy of the puncture position is ensured, and excessive damage to a non-target area is avoided. In general, when positioning, a target spot needs to be preset on the skin of a patient, and the position of a focus in an image is converted into an actual position through the position of the target spot so as to determine the needle inserting position during puncture. However, the current method for determining the needle insertion position is inaccurate in the needle insertion position, which easily causes that the puncture device cannot puncture the focus.

Disclosure of Invention

The application provides a needle insertion position determining method, a needle insertion position determining device, electronic equipment and a readable storage medium, and aims to solve the technical problem that an existing needle insertion position determining method is inaccurate.

In a first aspect, the present application provides a method for determining a needle insertion position, including:

acquiring a medical image and a target point in the medical image;

Classifying the targets according to the position change information of the targets to obtain registration targets and correction targets;

registering focus image positions of focuses in the medical image according to target image positions of the registration targets to obtain target focus positions and reference needle inserting positions corresponding to the target focus positions;

and correcting the reference needle inserting position according to the target position change information of the correction target point to obtain a corrected target needle inserting position.

In one possible implementation manner of the present application, the classifying the target according to the position change information of the target to obtain a registration target and a correction target includes:

inputting the position change information into a preset target point classification model to obtain a registration target point in the target points and a correction target point in the target points, wherein the preset target point classification model comprises at least one of a machine learning model and a statistical model.

In one possible implementation manner of the present application, the preset target point classification model includes a statistical model, and the preset target point classification model is used for counting a target displacement characteristic value corresponding to the position change information, comparing the target displacement characteristic value with a preset characteristic threshold value, and obtaining a corrected target point where the target displacement characteristic value is greater than or equal to the characteristic threshold value, and a registration target point where the target displacement characteristic value is less than the characteristic threshold value.

In one possible implementation manner of the present application, the target displacement feature value is a target range corresponding to the position change information.

In one possible implementation manner of the present application, the preset target point classification model is further configured to calculate a similarity between the position change information and preset skin motion information, obtain target skin motion information with a similarity greater than a preset similarity threshold, and a preset motion pattern corresponding to the target skin motion information, and adjust an initial displacement feature value corresponding to the position change information according to the preset motion pattern, so as to obtain a target displacement feature value corresponding to the position change information.

In one possible implementation manner of the present application, the preset target classification model further includes a region selection model, and the preset target classification model is configured to use, as the correction target, a target located in the predetermined target physiological region from targets with a target displacement characteristic value greater than or equal to the characteristic threshold.

In one possible implementation manner of the present application, the correcting the reference needle insertion position according to the target position change information of the correction target point to obtain a corrected target needle insertion position includes:

Obtaining change deviation information between the target position change information of the correction target point and preset reference position change information;

and correcting the reference needle inserting position according to the change deviation information to obtain a corrected target needle inserting position.

In a possible implementation manner of the present application, the registering, according to the target image position of the registration target, the focus image position of the focus in the medical image to obtain a target focus position, and the reference needle insertion position corresponding to the target focus position includes:

calculating to obtain a target focus position of the focus according to the target spot image position of the registration target spot, the target spot actual position of the registration target spot and the focus image position of the focus in the medical image;

correcting the preset needle inserting position according to the position deviation information between the preset focus position and the target focus position to obtain a reference needle inserting position corresponding to the target focus position,

or, based on a preset needle insertion position calculation strategy, calculating to obtain a reference needle insertion position corresponding to the target focus position according to the target focus position.

In one possible implementation manner of the present application, the acquiring a medical image, and a target point in the medical image, includes:

acquiring a medical image and presetting a target point searching area corresponding to a needle inserting position in the medical image;

and identifying the target spot searching area to obtain the target spot in the medical image.

In a possible implementation manner of the present application, the identifying the target searching area to obtain the target in the medical image includes:

taking the target point in the target point searching area as a candidate target point, and performing spatial interpolation processing on the preset needle inserting position according to the target point image position of the candidate target point to obtain a needle inserting position displacement characteristic value corresponding to each candidate target point;

combining the candidate targets to obtain target combinations;

counting needle insertion position displacement characteristic values corresponding to the target point combinations to obtain a displacement characteristic value range corresponding to the target point combinations and a target point combination with the minimum displacement characteristic value range;

and setting the candidate targets in the target combination as targets in the medical image.

In one possible implementation manner of the present application, the needle insertion position displacement characteristic value corresponding to each target point combination is that the needle insertion position displacement corresponding to each target point combination is extremely poor.

In a second aspect, the present application provides a needle insertion position determining device comprising:

the acquisition unit is used for acquiring the medical image and a target point in the medical image;

the classification unit is used for classifying the targets according to the position change information of the targets to obtain registration targets and correction targets;

the registration unit is used for registering the focus image position of the focus in the medical image according to the target image position of the registration target point to obtain a target focus position and a reference needle inserting position corresponding to the target focus position;

and the correction unit is used for correcting the reference needle inserting position according to the target position change information of the correction target point to obtain a corrected target needle inserting position.

In one possible implementation of the present application, the classification unit is further configured to:

inputting the position change information into a preset target point classification model to obtain a registration target point in the target points and a correction target point in the target points, wherein the preset target point classification model is one of a machine learning model and a statistical model.

In one possible implementation manner of the present application, the preset target point classification model is a statistical model, and the preset target point classification model is used for counting a target displacement characteristic value corresponding to the position change information, comparing the target displacement characteristic value with a preset characteristic threshold value, and obtaining a corrected target point where the target displacement characteristic value is greater than or equal to the characteristic threshold value, and a registration target point where the target displacement characteristic value is less than the characteristic threshold value.

In a possible implementation of the present application, the correction unit is further configured to:

In a possible implementation of the present application, the registration unit is further configured to:

In a possible implementation manner of the present application, the obtaining unit is further configured to:

combining the candidate targets to obtain target combinations;

In a third aspect, the present application also provides an electronic device comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor executing the steps of any of the needle insertion position determining methods provided herein when the processor invokes the computer program in the memory.

In a fourth aspect, the present application further provides a readable storage medium having stored thereon a computer program which, when executed by a processor, performs steps in any of the needle insertion position determining methods provided herein.

In summary, the method for determining the needle insertion position provided in the embodiment of the present application includes: acquiring a medical image and a target point in the medical image; classifying the targets according to the position change information of the targets to obtain registration targets and correction targets; registering focus image positions of focuses in the medical image according to target image positions of the registration targets to obtain target focus positions and reference needle inserting positions corresponding to the target focus positions; and correcting the reference needle inserting position according to the target position change information of the correction target point to obtain a corrected target needle inserting position.

Therefore, the needle inserting position determining method provided by the embodiment of the application can divide the target points in the medical image according to the position change information to obtain the registration target points suitable for registering the focus image positions and the correction target points suitable for correcting the reference needle inserting positions, so that on one hand, the accuracy of registration is improved, the accurate reference needle inserting positions are obtained, and on the other hand, after the reference needle inserting positions are obtained, the reference needle inserting positions are further corrected, and the accuracy of the needle inserting positions is guaranteed.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is an application scenario schematic diagram of a needle insertion position determining method provided in an embodiment of the present application;

FIG. 2 is a schematic flow chart of a method for determining a needle insertion position according to an embodiment of the present application;

FIG. 3 is a schematic flow chart of obtaining a target needle insertion position according to an embodiment of the present disclosure;

FIG. 4 is a flow chart of acquiring a target point in a medical image provided in an embodiment of the present application;

FIG. 5 is another flow chart of acquiring a target point in a medical image provided in an embodiment of the present application;

FIG. 6 is a schematic view of an embodiment of a needle insertion position determining apparatus provided in an embodiment of the present application;

fig. 7 is a schematic structural diagram of an embodiment of an electronic device provided in an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

In the description of the embodiments of the present application, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or an implicit indication of the number of features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the embodiments of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known processes have not been described in detail in order to avoid unnecessarily obscuring descriptions of the embodiments of the present application. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in the embodiments of the present application.

The embodiment of the application provides a needle insertion position determining method, a needle insertion position determining device, electronic equipment and a readable storage medium. The needle insertion position determining device can be integrated in an electronic device, and the electronic device can be a server or a terminal.

The execution body of the needle insertion position determining method in the embodiment of the present application may be a needle insertion position determining device provided in the embodiment of the present application, or different types of electronic devices such as a server device, a physical host, or a User Equipment (UE) integrated with the needle insertion position determining device, where the needle insertion position determining device may be implemented in a hardware or software manner, and the UE may specifically be a terminal device such as a smart phone, a tablet computer, a notebook computer, a palm computer, a desktop computer, or a personal digital assistant (Personal Digital Assistant, PDA).

The electronic device may be operated in a single operation mode, or may also be operated in a device cluster mode.

Referring to fig. 1, fig. 1 is a schematic view of a needle insertion position determining system according to an embodiment of the present application. The needle insertion position determining system may include an electronic device 100, and a needle insertion position determining device is integrated in the electronic device 100.

In addition, as shown in fig. 1, the needle insertion position determining system may further comprise a memory 200 for storing data, such as text data.

It should be noted that, the schematic view of the scenario of the needle insertion position determining system shown in fig. 1 is only an example, and the needle insertion position determining system and scenario described in the embodiments of the present application are for more clearly describing the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application, and those skilled in the art can know that, with the evolution of the needle insertion position determining system and the appearance of a new service scenario, the technical solutions provided by the embodiments of the present invention are equally applicable to similar technical problems.

Next, an embodiment of the present application, in which an electronic device is used as an execution body, will be described beginning with an introduction position determining method, and in order to simplify and facilitate the description, the execution body will be omitted in the following method embodiments. The key idea of the needle insertion position determining method is that a plurality of targets arranged on a patient are screened by utilizing the movement degree of the targets, and the targets for registration and the targets for needle insertion correction are distinguished. Then, determining the actual position of the focus by using the image position of the registration target point and the image position of the focus; and the needle insertion point is adjusted and corrected by utilizing the correction target point, so that the displacement of the skin of the patient caused by breathing is eliminated, and the image of the actual needle insertion point caused by the displacement is avoided. In addition, in the process of screening the corrected target points, the corrected target points can be further accurately screened according to the areas where the target points are located, so that the corrected target points after carefully selection have a better correction effect on the needle insertion points.

Specifically, the needle insertion position determining method includes: acquiring a medical image and a target point in the medical image; classifying the targets according to the position change information of the targets to obtain registration targets and correction targets; registering focus image positions of focuses in the medical image according to target image positions of the registration targets to obtain target focus positions and reference needle inserting positions corresponding to the target focus positions; and correcting the reference needle inserting position according to the target position change information of the correction target point to obtain a corrected target needle inserting position.

Referring to fig. 2, fig. 2 is a schematic flow chart of a method for determining a needle insertion position according to an embodiment of the present application. It should be noted that although a logical order is depicted in the flowchart, in some cases the steps depicted or described may be performed in a different order than presented herein. The needle insertion position determining method specifically may include the following steps 201 to 204, in which:

201. acquiring a medical image, and a target point in the medical image.

Medical images may refer to images taken of a patient during surgery or prior to surgery, in which the patient's lesion information should be included. By way of example, a medical image may refer to a CT image taken of a lesion of a patient during a procedure by means of an electronic computed tomography (Computed Tomography, CT) technique. For example, when the lesion of the patient is a stomach, the stomach of the patient may be photographed by CT technique to obtain a medical image.

In a medical image, a target point should be contained, i.e. the medical image should also be an image containing a target point. The target point can be understood as a reference position for calibrating a focus of a patient in a surgical procedure, and a doctor can determine the actual position of the focus through the position of the target point in a medical image, the actual position of the target point and the position compiled in the medical image in the surgical procedure, so that the doctor can determine the needle insertion position in the puncture operation. The doctor can attach the optical mark capable of reflecting light on the skin surface of the patient, and the electronic equipment takes the optical mark as a target point. For example, a doctor may attach optical markers such as spherical reflectors, sheet reflectors, etc. to the skin surface of a patient, targeting these optical markers.

It should be noted that in the embodiment of the present application, there should be a plurality of medical images. For example, images of the lesion location of a patient may be continuously acquired during a surgical procedure by CT techniques, and all images including the target point acquired during the surgical procedure may be used as medical images.

In some embodiments, in order to avoid information that the medical image does not include a focus, the shot image may be detected through a trained focus detection model, if the image includes a focus, the shot image may be used as a medical image, if the image does not include a focus, alarm information may be sent to prompt a doctor to re-arrange a target point on the skin surface of the patient, and then the image of the focus position of the patient is collected again. For example, the electronic device may determine whether the image includes a lesion through the trained lesion detection model. For example, an initial focus detection model may be trained by using an open-source target detection model such as AlexNet as an initial focus detection model, through a preset sample focus image, and label information of the sample focus image, so as to obtain a trained focus detection model.

When executing step 201, the electronic device may acquire a target point in the medical image through the trained target point detection model. For example, an initial target detection model may be trained by using an open-source target detection model such as AlexNet as an initial target detection model, through a preset sample target image and label information of the sample target image, so as to obtain a trained target detection model.

202. Classifying the targets according to the position change information of the targets to obtain registration targets and correction targets.

The registration target point is a target point for calculating the actual position of the focus according to the image position of the registration target point and the image position of the focus. For example, a target point of the plurality of medical images, which is less affected by the respiration of the patient, may be used as a registration target point. For example, a target point with small position change in a plurality of medical images can be used as a registration target point. The position change of the registration target point is smaller, so that the influence of skin fluctuation caused by respiration of a patient on the registration target point is smaller, the accuracy is higher when the conversion between the image position and the actual position is carried out, the actual position of the focus obtained through calculation of the registration target point is more accurate, and the accuracy of the conversion relation between the image position and the actual position is not influenced by the skin fluctuation caused by respiration.

The correction target point is used for correcting the needle insertion position corresponding to the actual focus position, and the adopted target point is equivalent to the focus position obtained when the influence of the respiration of the patient is not calculated when the actual focus position is determined through the registration target point, so that the change of the respiration of the patient on the focus position is eliminated, but in the operation process, the focus position can be changed due to the respiration of the patient, and if the needle insertion position corresponding to the actual focus position is not corrected, the puncture equipment can not accurately puncture the focus. Therefore, the needle insertion position needs to be further corrected by correcting the target point according to the change degree of the patient breathing to the focus position. For example, a target point of the plurality of medical images, which is greatly affected by the respiration of the patient, may be used as a registration target point. For example, a target point with a large position change in a plurality of medical images can be used as a registration target point. From the above, it can be seen that the patient breathing affects the accuracy of determining the needle insertion position, so in order to correct the deviation caused by the patient breathing, the target point with the larger position change, that is, the target point with the greatest influence of the patient breathing, can be screened from the target points, and the needle insertion position corresponding to the theoretical actual position is corrected through the target points.

The position change information of the target point refers to the change information of the position of the target point image in a plurality of medical images. The electronic device may acquire the target image positions in each medical image, and then generate a position change curve of the target according to each target image position and the image time stamp corresponding to each target image position, and use the position change curve as position change information of the target.

When executing step 202, the position change information of the target point can be input into a preset target point classification model to output the type of the target point, so as to obtain a registration target point and a correction target point in the target point.

In some embodiments, the preset target classification model may be one of a machine learning model and a statistical model, that is, the step of classifying the target according to the position change information of the target to obtain a registration target and a correction target includes:

When the preset target classification model is a machine learning model, the model can learn the position change information of the skin surface when the patient breathes through training, or learn the position change information of the sample correction target, and match the position change information of the target with the learned information according to the step 202, so as to obtain the target with the maximum similarity between the position change information and the learned information, namely, the target with the movement mode closest to the skin surface when the patient breathes, and the target with the larger influence of the patient breathes is taken as the correction target, and other targets are taken as registration targets.

In some embodiments, an open-source logistic regression (Logistic Regression) model may be used as an initial target classification model, and the initial target classification model may be trained by using preset first sample data to obtain the preset target classification model, where the first sample data may refer to the above information about the change in position of the skin surface when the patient breathes, or the information about the change in position of the sample correction target.

When the preset target point classification model comprises a statistical model, the model can obtain a characteristic value for representing the position change of the target point according to the position change information, the characteristic value is compared with a preset threshold value, if the characteristic value is larger than or equal to the preset threshold value, the target point is indicated to have larger position change, the target point is taken as a correction target point, if the characteristic value is smaller than the preset threshold value, the target point is indicated to have smaller position change, the target point is taken as a registration target point, namely the preset target point classification model is taken as the statistical model, the preset target point classification model is used for counting a target displacement characteristic value corresponding to the position change information, the target displacement characteristic value is compared with the preset characteristic threshold value, and the correction target point with the target displacement characteristic value larger than or equal to the characteristic threshold value and the target point with the target displacement characteristic value smaller than the characteristic threshold value are obtained "

The method for acquiring the target displacement characteristic value is not limited, and the target displacement characteristic value can reflect the position change of the target point. For example, when the position change information refers to a position change curve, an average value of target image positions in the position change curve may be calculated, a maximum value in the target image positions may be obtained by screening, a difference between the maximum value and the average value may be calculated, and the difference may be used as a target displacement characteristic value, where a larger target displacement characteristic value indicates a larger target position change, and a smaller target displacement characteristic value indicates a smaller target position change. For example, the target position change may be calculated by selecting a next-maximum value and a next-minimum value from target image positions of the position change curve, and calculating a difference between the next-maximum value and the next-minimum value, wherein the larger the target displacement characteristic value is, the larger the target position change is, the smaller the target displacement characteristic value is, and the smaller the target position change is.

In some embodiments, in order to more accurately represent the magnitude of the change of the target position, the maximum value and the minimum value may be obtained by screening from the target image positions of the position change curve, and the difference between the maximum value and the minimum value is calculated and used as the target displacement characteristic value, that is, the extreme difference corresponding to the position change curve is used as the target displacement characteristic value.

Or when the preset target classification model comprises a statistical model, the preset target classification model can also match the characteristic value with a preset characteristic value range so as to classify the target. Or, the targets may be sorted according to the magnitudes of the feature values, the targets with the magnitudes of the feature values ranked N before are used as correction targets, and the targets with the magnitudes of the feature values ranked N after are used as registration targets. In short, it is only necessary to classify the target according to the size of the change in position or the similarity with the skin's movement pattern.

In this embodiment, in order to make the accuracy of correcting the target point higher, the preset target point classification model may further include a region selection model, where after the target point where the target displacement characteristic value is greater than or equal to the characteristic threshold value is primarily screened out, the target physiological region where the primarily screened target point is located may be detected, and then, the target point located in the target physiological region is used as a carefully selected correction target point. Thereby further improving the correction accuracy and correction effect of the correction target point.

For example, an ablation procedure of the right lung nodule is required. A plurality of targets are arranged in the right lung area of a human body. Then, the target point for registration and the target point for correcting the displacement of the skin caused by respiration can be primarily screened out according to the target displacement characteristic value (namely, the movement range) of the target point. And then screening out the target points for correcting the displacement of the skin caused by respiration, wherein the target points in the middle lobe area of the right lung are used as the correction target points for finally correcting the needle insertion position.

In other embodiments, considering the movement patterns of the skin at different positions, the movement patterns corresponding to the target point are different, so that the calculation methods of the characteristic values of the degree of the change of the target point position can be accurately reflected, therefore, the movement patterns corresponding to the target point can be determined first, and then the displacement characteristic values obtained through statistics by the method can be adjusted according to the movement patterns, so as to obtain the target displacement characteristic values. The target point classification model is further used for calculating the similarity between the position change information and preset skin movement information, obtaining target skin movement information with the similarity being larger than a preset similarity threshold value, a preset movement mode corresponding to the target skin movement information, and adjusting an initial displacement characteristic value corresponding to the position change information according to the preset movement mode to obtain a target displacement characteristic value corresponding to the position change information. The movement pattern may include, among other things, lateral movement, longitudinal movement, expansive movement, and the like, to which embodiments of the present application are not limited. In this embodiment, on the basis of considering the movement mode, the location of the target point may be further considered, so that the accuracy of correcting the target point is higher, the preset target point classification model may further include a region selection model, and after the target point with the target displacement characteristic value greater than or equal to the characteristic threshold value is primarily screened out, the target physiological region where the primarily screened target point is located may be detected, and then the target point located in the target physiological region is used as a carefully selected correction target point. Thereby further improving the correction accuracy and correction effect of the correction target point.

For example, an ablative procedure of a thyroid nodule is required. A plurality of targets are arranged in the front side area of the neck of a human body. Then, the target point for registration and the target point for correcting the displacement of the skin caused by respiration can be primarily screened out according to the target displacement characteristic value of the target point (namely, the movement degree determined according to the movement mode). And then screening out the target points for correcting the displacement of the skin caused by respiration, wherein the target points positioned on the right side of the thyroid structure are used as correction target points for finally correcting the needle insertion position.

The method for calculating the initial displacement feature value may refer to the above, for example, the range corresponding to the position change information may be used as the initial displacement feature value corresponding to the position change information, which is not described in detail.

The preset skin movement information may refer to a skin movement curve constructed by the positions of the skin corresponding to different times. For example, the image of each part of the patient may be acquired in advance by a method of capturing a CT image, and a skin motion curve corresponding to each part may be constructed according to positions corresponding to different times of the skin in the image of each part, and the obtained skin motion curve may be used as preset skin motion information.

When comparing the position change information of the target point with the skin movement information, the electronic device can learn the initial movement pattern recognition model to obtain the corresponding relation between different skin movement information and movement patterns through training the initial movement pattern recognition model to obtain a trained movement pattern recognition model, then input the position change information of the target point into the trained movement pattern recognition model, calculate the similarity between the position change information and the skin movement information through the trained movement pattern recognition model to obtain target skin movement information with the similarity larger than a preset similarity threshold, and output a movement pattern corresponding to the target skin movement information. The trained movement pattern recognition model can compare the characteristic information such as gradient change information, range, average value and the like between the position change information and the skin movement information so as to determine the similarity between the position change information and the skin movement information.

Alternatively, the characteristic information such as gradient change information, the difference, the average value and the like of the position change information and the skin movement information can be counted and compared instead of the model, so that the similarity between the position change information and the skin movement information is determined, and the target skin movement information with the similarity greater than a preset similarity threshold value and the movement mode corresponding to the target skin movement information are obtained.

After the motion mode corresponding to the target skin motion information is obtained, the initial displacement characteristic value can be correspondingly adjusted according to the motion mode. For example, when the movement pattern is longitudinal movement, the change in the position of the target spot in the lateral direction of the skin can be determined as an error, which is zeroed. When the movement mode is transverse movement, the position change of the target point in the skin longitudinal direction can be judged as an error, and the error is zeroed. It should be noted that the foregoing examples are provided merely for convenience of understanding and are not to be construed as limiting the embodiments of the present application.

203. And registering the focus image position of the focus in the medical image according to the target image position of the registration target to obtain a target focus position and a reference needle-inserting position corresponding to the target focus position.

It should be noted first that registration in the embodiment of the present application refers to converting an image position in a medical image into an actual position. For example, the image position in the medical image may be converted into the actual position by a preset image position-actual position conversion relationship.

It will be appreciated that the target lesion location is the actual lesion location obtained after registration. For example, the image position deviation between the registration target point and the focus can be calculated according to the target point image position of the registration target point and the focus image position of the focus in the medical image, then the image position deviation is converted into the actual position deviation through a preset image position-actual position conversion relation, and the target focus position is calculated according to the actual position deviation and the target point actual position of the registration target point.

The reference needle insertion position corresponding to the target focus position may be a position calculated in real time or a position calculated in advance.

When the reference needle insertion position is a position calculated in real time, the electronic device can generate the reference needle insertion position according to the target focus position through a preset needle insertion position determining algorithm.

When the reference needle insertion position is a pre-calculated position, the doctor may preset corresponding candidate needle insertion positions for different body areas of the patient, and when step 203 is executed, the electronic device matches the target focus position with the body area to obtain a target body area to which the target focus position belongs, and uses the candidate needle insertion position corresponding to the target body area as the reference needle insertion position corresponding to the target focus position. Or when a doctor estimates the focus in advance to obtain a preset focus position, and determines a preset needle inserting position according to the preset focus position, the preset needle inserting position can be adjusted according to the target focus position and the preset focus position to obtain a reference needle inserting position. The step of registering the focus image position of the focus in the medical image according to the target image position of the registration target point to obtain a target focus position and a reference needle-inserting position corresponding to the target focus position comprises the following steps:

(1.1) calculating a target focus position of a focus according to the target spot image position of the registration target spot, the target spot actual position of the registration target spot and the focus image position of the focus in the medical image;

the calculation of the target lesion position may be described above without further description.

(1.2) correcting the preset needle inserting position according to the position deviation information between the preset position of the focus and the target focus position to obtain a reference needle inserting position corresponding to the target focus position,

The preset position of the focus refers to the preset focus position, and the preset needle inserting position refers to the preset needle inserting position determined by the doctor according to the preset focus position.

When the step (1.2) is executed, the electronic device may calculate a difference between the preset position and the target focus position to obtain position offset information, and calculate a reference needle insertion position according to the position offset information and the preset needle insertion position.

In addition, the reference needle insertion position may be a manually set position. For example, the reference needle insertion position may be a position input by the doctor into the electronic device according to the target lesion position after the electronic device outputs the target lesion position to the target terminal. The target terminal may refer to a computer, a CT device, etc.

It should be noted that, if there are multiple registration targets, the actual focus position may be determined sequentially according to each registration target, and the average value of each actual focus position may be used as the target focus position, or the average value of the image positions of each registration target may be calculated, and the average value of the actual positions of each registration target may be further determined, or one target focus position may be obtained uniformly by other methods.

204. And correcting the reference needle inserting position according to the target position change information of the correction target point to obtain a corrected target needle inserting position.

The target position change information refers to position change information of the corrected target point. In the embodiment of the application, the change of the focus position in the operation is represented by the target position change information so as to improve the accuracy of the puncture operation in the puncture operation.

The target needle insertion position is the actual needle insertion position in the operation obtained after the respiration of the patient is calculated and the reference needle insertion position is corrected, namely the actual needle insertion position obtained after the influence of the respiration of the patient on the focus position is calculated.

For example, the electronic device may input the target position change information, and the reference needle insertion position into a trained position correction model, and output a corrected target needle insertion position. The electronic equipment can train the initial position correction model by taking the open-source logistic regression model as the initial position correction model through preset second sample data to obtain a trained position correction model. The second sample data may include target position change information as a sample, a reference needle insertion position as a sample, and a target needle insertion position as a sample.

If there are multiple correction targets, the processing method when there are multiple registration targets can be referred to, and detailed description is omitted.

Therefore, by the method from step 201 to step 204, on one hand, when the focus image position is aligned, the registration target point with smaller influence on the respiration of the patient can be selected, the accuracy of the conversion between the image position and the actual position is improved, and further, the more accurate target focus position and the reference needle insertion position are obtained. On the other hand, the reference needle insertion position can be corrected through the correction target point with larger influence on the respiration of the patient, and the change of the respiration of the patient on the focus position is eliminated. Therefore, the method can effectively improve the accuracy of the needle insertion position, and in the traditional method, on one hand, a target point with larger influence of patient respiration is easily used as a target point for registration, and on the other hand, even if the target point with smaller influence of patient respiration is adopted in registration, the influence of patient respiration on the needle insertion position is not considered.

In some embodiments, the target position change information may be compared with preset reference information to obtain a deviation between the target position change information and the preset reference information, and the reference needle insertion position may be corrected according to the deviation to obtain the target needle insertion position. Referring to fig. 3, at this time, the step of "correcting the reference needle insertion position according to the target position change information of the correction target point to obtain a corrected target needle insertion position" includes:

301. and acquiring change deviation information between the target position change information of the correction target point and preset reference position change information.

In some embodiments, the preset reference position change information may refer to a position change curve of the skin surface in a non-breathing state of the patient.

In other embodiments, considering that the change of the focal position is small when the patient breathes steadily, the focal position will change greatly only when the patient breathes abnormally due to injury and physiological reaction, and the like after entering an operation, so that the change curve of the position of the skin surface can be used as preset reference position change information when the patient breathes steadily.

The preset reference position change information may be manually set by the doctor and then stored in a background database of the hospital, and when step 301 is executed, the electronic device may directly read the preset reference position change information from the background database.

The change deviation information can be obtained by comparing the target position change information with the reference position change information. For example, when the target position change information refers to a position change curve of the correction target point, and the reference position change information refers to a position change curve of the skin surface in a non-breathing state of the patient, the electronic device may respectively calculate a first average value of each image position in the target position change information and a second average value of each image position in the reference position change information, and a difference between the first average value and the second average value is used as change deviation information.

302. And correcting the reference needle inserting position according to the change deviation information to obtain a corrected target needle inserting position.

And calculating the target needle inserting position according to the variation deviation information and the reference needle inserting position.

It can be understood that, according to the embodiment of the application, the deviation information of the focus position in the operation process is represented by correcting the deviation information of the target point in different states of the patient, so that the reference needle insertion position can be corrected according to the deviation information of the focus position in the operation process, and the accuracy of the puncture operation in the puncture operation is improved.

In some embodiments, the physician may preset the needle insertion point, particularly with reference to the description in step 203. In order to make the motion pattern of the target point more matched with the motion pattern of the needle insertion point, further improve the accuracy in determining the reference needle insertion position and determining the target needle insertion position, the target point around the preset needle insertion point may be used as the target point in the medical image in step 201. Referring to fig. 4, at this time, the step of "acquiring a medical image, and a target point in the medical image", includes:

401. acquiring a medical image, and presetting a target point searching area corresponding to a needle inserting position in the medical image.

The preset needle insertion position refers to the position of the preset needle insertion point. For example, any medical image may be selected, and the image position of the preset needle insertion point in the any medical image is taken as the preset needle insertion position.

For example, the electronic device may calculate a target search area in the medical image according to the preset search distance and the preset needle insertion position. The specific value of the search distance can be set according to actual scene requirements.

402. And identifying the target spot searching area to obtain the target spot in the medical image.

The electronic device may obtain the basic target in the medical image through the target detection model trained above, and take the basic target in the target search area as the target in the medical image.

Through steps 401-402, the target points around the preset needle insertion position can be used as the target points in the medical image in step 201, so that the accuracy in determining the reference needle insertion position and determining the target needle insertion position is improved.

In some embodiments, in addition to selecting a target point by limiting the position, to improve accuracy in determining the reference needle insertion position and determining the target needle insertion position, a displacement characteristic value of the preset needle insertion position may be estimated according to the base target point, a base target point combination with a minimum range of variation of the displacement characteristic value may be selected, and the target point in the base target point combination may be used as the target point in the medical image in step 201. Referring to fig. 5, at this time, the step of identifying the target searching area to obtain a target in the medical image includes:

501. And taking the target point in the target point searching area as a candidate target point, and performing spatial interpolation processing on the preset needle inserting position according to the target point image position of the candidate target point to obtain a needle inserting position displacement characteristic value corresponding to each candidate target point.

Through spatial interpolation processing, the position of the preset needle inlet point at the corresponding time point of each target point image position can be calculated according to the known target point image position. After the spatial interpolation processing, the needle insertion position characteristic value can be obtained according to the position of the preset needle insertion point at each time point by the method for obtaining the target displacement characteristic value. It will be appreciated that for each candidate target point, a needle insertion displacement characteristic value may be calculated.

The description of the needle insertion position characteristic value may refer to the target displacement characteristic value, and detailed description is omitted. In some embodiments, the needle insertion position displacement characteristic value may refer to a very poor needle insertion position displacement.

502. And combining the candidate targets to obtain target combinations.

503. And counting needle insertion position displacement characteristic values corresponding to the target point combinations to obtain a displacement characteristic value range corresponding to the target point combinations and a target point combination with the minimum displacement characteristic value range.

Because the needle insertion position characteristic value can be calculated for each candidate target point, the displacement characteristic value range corresponding to each target point combination can be obtained after the candidate target points are combined. And selecting the target point combination with the smallest displacement characteristic value range from the target point combinations.

504. And setting the candidate targets in the target combination as targets in the medical image.

The method can reduce the error when correcting the preset needle inserting position, and improve the accuracy when determining the reference needle inserting position and the target needle inserting position, because the method can obtain a plurality of targets with similar motion modes to be set as targets in medical images, and further when registering and correcting by sequentially adopting different targets or adopting the average image position of the targets, the accuracy of the needle inserting position is reduced when registering and correcting due to the fact that the motion modes of the targets differ too far.

In order to better implement the method for determining a needle insertion position in the embodiment of the present application, based on the method for determining a needle insertion position, the embodiment of the present application further provides a device for determining a needle insertion position, as shown in fig. 6, which is a schematic structural diagram of an embodiment of the device for determining a needle insertion position in the embodiment of the present application, where the device 600 for determining a needle insertion position includes:

An acquisition unit 601, configured to acquire a medical image, and a target point in the medical image;

the classification unit 602 is configured to classify the target according to the position change information of the target, so as to obtain a registration target and a correction target;

a registration unit 603, configured to register a focus image position of a focus in the medical image according to the target image position of the registration target, to obtain a target focus position and a reference needle insertion position corresponding to the target focus position;

and the correcting unit 604 is configured to correct the reference needle insertion position according to the target position change information of the correction target point, so as to obtain a corrected target needle insertion position.

In one possible implementation of the present application, the classification unit 602 is further configured to:

On the basis of the method steps of screening the corrected target points, the preset target point classification model can further comprise a region selection model, and the preset target point classification model is used for taking the target point which is positioned in the preset target physiological region in the target points with the target displacement characteristic values larger than or equal to the characteristic threshold value as the corrected target point, so that the corrected target point after the selection has a better correction effect on the needle insertion point.

In a possible implementation of the present application, the correction unit 604 is further configured to:

In a possible implementation of the present application, the registration unit 603 is further configured to:

In a possible implementation manner of the present application, the obtaining unit 601 is further configured to:

combining the candidate targets to obtain target combinations;

In the implementation, each module may be implemented as an independent entity, or may be combined arbitrarily, and implemented as the same entity or several entities, and the implementation of each module may be referred to the foregoing method embodiment, which is not described herein again.

Since the needle insertion position determining device can execute the steps in the needle insertion position determining method in any embodiment, the beneficial effects that can be achieved by the needle insertion position determining method in any embodiment of the present application can be achieved, and detailed descriptions are omitted herein.

In addition, in order to better implement the method for determining a needle insertion position in the embodiment of the present application, based on the method for determining a needle insertion position, the embodiment of the present application further provides an electronic device, referring to fig. 7, fig. 7 shows a schematic structural diagram of the electronic device in the embodiment of the present application, and specifically, the electronic device provided in the embodiment of the present application includes a processor 701, where the processor 701 is configured to implement each step of the method for determining a needle insertion position in any embodiment when executing a computer program stored in a memory 702; alternatively, the processor 701 is configured to implement the functions of the respective modules in the corresponding embodiment of fig. 6 when executing the computer program stored in the memory 702.

By way of example, a computer program may be partitioned into one or more modules/units that are stored in the memory 702 and executed by the processor 701 to accomplish the embodiments of the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing particular functions to describe the execution of the computer program in a computer device.

Electronic devices may include, but are not limited to, processor 701, memory 702. It will be appreciated by those skilled in the art that the illustrations are merely examples of electronic devices and are not limiting of electronic devices, and may include more or fewer components than illustrated, or may combine certain components, or different components.

The processor 701 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center for an electronic device, with various interfaces and lines connecting various parts of the overall electronic device.

The memory 702 may be used to store computer programs and/or modules, and the processor 701 implements the various functions of the computer device by running or executing the computer programs and/or modules stored in the memory 702, and invoking data stored in the memory 702. The memory 702 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, video data, etc.) created according to the use of the electronic device, and the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the needle insertion position determining device, the electronic device and the corresponding modules described above may refer to the description of the needle insertion position determining method in any embodiment, and will not be described herein in detail.

Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions or by controlling associated hardware, which may be stored on a readable storage medium and loaded and executed by a processor.

For this reason, the embodiment of the present application provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps in the needle insertion position determining method in any embodiment of the present application, and specific operations may refer to the description of the needle insertion position determining method in any embodiment, which is not repeated herein.

Wherein the readable storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.

Because the instructions stored in the readable storage medium may perform the steps in the needle insertion position determining method in any embodiment of the present application, the beneficial effects that can be achieved by the needle insertion position determining method in any embodiment of the present application may be achieved, which is described in detail in the foregoing description and will not be repeated here.

The above describes in detail a method, an apparatus, a storage medium, and an electronic device for determining a needle insertion position provided in the embodiments of the present application, and specific examples are applied to describe principles and implementations of the present application, where the description of the above embodiments is only for helping to understand the method and core ideas of the present application; meanwhile, those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, and the present description should not be construed as limiting the present application in view of the above.

Claims

1. A method of determining a needle insertion position, comprising:

acquiring a medical image and a target point in the medical image;

2. The method for determining a needle insertion position according to claim 1, wherein classifying the target according to the position change information of the target to obtain a registration target and a correction target comprises:

3. The needle insertion position determining method according to claim 2, wherein the preset target point classification model comprises a statistical model, the preset target point classification model is used for counting target displacement characteristic values corresponding to the position change information, and comparing the target displacement characteristic values with preset characteristic thresholds to obtain a corrected target point with the target displacement characteristic values being greater than or equal to the characteristic thresholds and a registration target point with the target displacement characteristic values being smaller than the characteristic thresholds.

4. The needle insertion position determining method according to claim 3, wherein the target displacement characteristic value is a target range corresponding to the position change information.

5. The method for determining a needle insertion position according to claim 3, wherein the preset target point classification model is further used for calculating similarity between the position change information and preset skin movement information, obtaining target skin movement information with similarity greater than a preset similarity threshold, and a preset movement pattern corresponding to the target skin movement information, and adjusting an initial displacement characteristic value corresponding to the position change information according to the preset movement pattern, so as to obtain a target displacement characteristic value corresponding to the position change information.

6. The needle insertion position determining method according to claim 4 or 5, wherein the preset target point classification model further comprises a region selection model, and the preset target point classification model is used for taking a target point located in a preset target physiological region as a correction target point from target points with target displacement characteristic values greater than or equal to the characteristic threshold.

7. The method for determining a needle insertion position according to claim 1, wherein the correcting the reference needle insertion position according to the target position change information of the corrected target spot to obtain a corrected target needle insertion position includes:

8. The method of determining a needle insertion position according to claim 1, wherein registering a focus image position of a focus in the medical image according to the target image position of the registration target to obtain a target focus position, and a reference needle insertion position corresponding to the target focus position, includes:

9. The needle penetration location determination method of any one of claims 1-8 wherein the acquiring a medical image, and a target point in the medical image, comprises:

10. The needle penetration location determination method of claim 9, wherein the identifying the target point search area results in a target point in the medical image comprising:

combining the candidate targets to obtain target combinations;

11. The needle penetration location determination method of claim 10, wherein the needle penetration location characteristic value for each of the target combinations is a minimum needle penetration location for each of the target combinations.

12. A needle insertion position determining apparatus, comprising:

13. An electronic device comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the steps in the needle insertion position determination method according to any one of claims 1 to 11 when the computer program is executed by the processor.

14. A readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the needle penetration position determination method of any of claims 1 to 11.