CN116350347A - Method, device, electronic equipment and storage medium for determining a surgical path - Google Patents

Abstract

The invention discloses a method and a device for determining a surgical path, electronic equipment and a storage medium. Acquiring a focus image and an angiographic image of a focus part; determining a plurality of to-be-processed starting points on the edge contour line of the focus image, and determining a plurality of to-be-processed paths based on the to-be-processed starting points and the corresponding operation end points of the focus part; determining first path characteristic information corresponding to each path to be operated based on the focus image, and determining second path characteristic information corresponding to each path to be operated based on the angiography image; based on a target neural network model obtained through pre-training, first path characteristic information and second path characteristic information corresponding to the surgical paths to be selected, determining target surgical paths corresponding to focus positions from a plurality of surgical paths to be selected, solving the problems of low surgical path determination efficiency and low accuracy and improving the efficiency and accuracy of determining the surgical paths.

Description

A method, device, electronic equipment and storage medium for determining a surgical path

technical field

The present invention relates to the technical field of data processing, in particular to a method, device, electronic equipment and storage medium for determining an operation path.

Background technique

On the premise that the lesion site in the body is known, the line segment from the starting point of the body surface operation to the end point of the lesion site operation is the surgical path. If the surgical path passes through a dangerous area that cannot be touched by the human body, it will cause greater harm to the medical staff and is not conducive to the operation, so the surgical path needs to be determined in advance.

At present, the usual way to determine the surgical path is to design the surgical path in the surgical planning software by comprehensively analyzing the imaging data and clinical data of the patient based on their own experience. However, the problem with this method is that it is highly dependent on manual work, and the surgical path needs to be determined based on the past experience of the receiving staff, which is somewhat subjective, and there are technical problems such as low efficiency and low accuracy in determining the surgical path.

Contents of the invention

Embodiments of the present invention provide a method, device, electronic device, and storage medium for determining a surgical path, so as to improve the efficiency and accuracy of determining the surgical path.

In a first aspect, the present invention provides a method for determining a surgical path, the method comprising:

Acquiring a lesion image containing the same lesion site and an angiographic image corresponding to the lesion image;

Determining multiple candidate surgical starting points on the edge contour line of the lesion image, and determining multiple candidate surgical paths based on the multiple candidate surgical starting points and the surgical end points corresponding to the lesion site;

determining first path characteristic information corresponding to each surgical path to be selected based on the lesion image, and determining second path characteristic information corresponding to each surgical path to be selected based on the angiography image;

Based on the target neural network model obtained through pre-training, the first path characteristic information and the second path characteristic information corresponding to the candidate surgical path, the target surgical path corresponding to the lesion site is determined from the plurality of candidate surgical paths.

In a second aspect, the present invention provides a device for determining a surgical path, the device comprising:

An image data acquisition module, configured to acquire a lesion image containing the same lesion site and an angiographic image corresponding to the lesion image;

A candidate path determination module, configured to determine multiple candidate surgical starting points on the edge contour of the lesion image, and determine multiple candidate surgical paths based on the multiple candidate surgical starting points and the surgical end points corresponding to the lesion site;

A characteristic information determination module, configured to determine first path characteristic information corresponding to each surgical path to be selected based on the lesion image, and determine second path characteristic information corresponding to each surgical path to be selected based on an angiographic image;

A target path determination module, configured to determine the lesion site from multiple candidate surgical paths based on the pre-trained target neural network model, the first path feature information and the second path feature information corresponding to the candidate surgical path Corresponding target surgical path.

In a third aspect, the present invention provides an electronic device, comprising:

at least one processor; and

memory communicatively coupled to at least one processor; wherein,

The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor, so that at least one processor can execute the method for determining an operation path in any embodiment of the present invention.

In a fourth aspect, the present invention provides a computer-readable storage medium, where computer instructions are stored in the computer-readable storage medium, and the computer instructions are used to enable a processor to implement the method for determining the surgical path in any embodiment of the present invention when executed.

In the technical solution provided by the embodiment of the present invention, by acquiring the lesion image and angiographic image of the lesion, multiple candidate surgical starting points are determined on the edge contour line of the lesion image, and based on the correspondence between the multiple candidate surgical starting points and the lesion site Surgical end point, determine multiple candidate surgical paths. Determine the first path feature information corresponding to each surgical path to be selected based on the lesion image, and determine the second path feature information corresponding to each surgical path to be selected based on the angiographic image, so that based on the target neural network model obtained in advance, the target neural network model to be selected Select the first path characteristic information and the second path characteristic information corresponding to the surgical path, and determine the target surgical path corresponding to the lesion from multiple surgical paths to be selected, thereby realizing the automatic determination of the surgical path without human participation, and the lesion The first path feature information and the second path feature information are obtained by parametric evaluation of the candidate surgical path in the image and angiography image, and path prediction is performed on the first path feature information and the second path feature information through the target neural network model, which can be The appropriate surgical path is accurately determined, and the efficiency and accuracy of the surgical path are improved.

It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will be easily understood from the following description.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained based on these drawings without creative effort.

FIG. 1 is a flowchart of a method for determining a surgical path provided in Embodiment 1 of the present invention;

FIG. 2 is a schematic diagram of a lesion image involved in Embodiment 1 of the present invention;

FIG. 3 is a schematic diagram of a candidate surgical path in an angiographic image according to Embodiment 1 of the present invention;

FIG. 4 is a flow chart of a method for determining a surgical path provided in Embodiment 2 of the present invention;

Fig. 5 is a schematic diagram of the functional organization area involved in Embodiment 2 of the present invention;

6 is a schematic structural diagram of a device for determining a surgical path provided by Embodiment 3 of the present invention;

FIG. 7 is a schematic structural diagram of an electronic device provided by Embodiment 4 of the present invention.

Detailed ways

In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is an embodiment of a part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

It should be noted that the terms "first preset condition" and "second preset condition" in the description and claims of the present invention and the above drawings are used to distinguish similar objects, but not necessarily to describe specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or electronic device comprising a series of steps or elements need not be limited to the expressly listed Instead, other steps or elements not explicitly listed or inherent to the process, method, product or electronic device may be included.

Embodiment one

FIG. 1 is a flow chart of a method for determining a surgical path provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation where the surgical path is determined on the premise of knowing the lesion site of the patient. The method can be executed by the device for determining the surgical path. The device can be implemented in the form of hardware and/or software. The device can be configured on a computer device, which can be a notebook, a desktop computer, a smart tablet, and the like. As shown in Figure 1, the method includes:

S110. Acquire a lesion image and an angiographic image of the lesion.

Wherein, the lesion image is an examination image taken by the medical personnel during physical examination, and the lesion image includes the position of the lesion target. For example, the lesion image may be a magnetic resonance image (Magnetic Resonance Imaging, MRI). Angiographic images are inspection images showing the structure of blood vessels. In this embodiment, the angiographic image contains a focal target consistent with the focal image. For example, the angiography image may be CT angiography (CT angiography, CTA).

In the actual production process, the visiting personnel need to do a series of preoperative inspections before the operation, and the preoperative inspection items include taking lesion images and angiographic images. The existing medical software can be used to calibrate and fuse the lesion image and angiography image, so that the lesion image and angiography image can truly reflect the actual physiological structure of the lesion and its surrounding tissues and organs.

Exemplarily, for patients with cerebral hemorrhage, a series of preoperative examinations are required before the operation to determine whether the visiting personnel can perform the operation and determine the location of the lesion target for the operation. The results of these preoperative examinations include lesion images and angiographic images. Wherein, the lesion image and the angiography image are three-dimensional images, and after determining the position of the lesion target, a two-dimensional image with the most obvious lesion target can be further determined from the three-dimensional lesion images as the lesion image. And determine the two-dimensional angiographic image corresponding to the two-dimensional lesion image.

S120. Determine multiple candidate surgical starting points on the edge contour of the lesion image, and determine multiple candidate surgical paths based on the multiple candidate surgical starting points and the surgical end points corresponding to the lesion.

Wherein, the edge contour line is a line formed by edge contour pixel points in the lesion image. The edge outline represents the body surface in a physiological sense. During the operation, the target of the lesion is the end point of the operation. The problem is how to determine the starting point of the operation. Therefore, the starting point of the operation to be selected is a set of hypothetical starting points of the operation. In this embodiment, the surgical path to be selected is a straight line segment determined by the surgical end point corresponding to the lesion site and the surgical start point to be selected.

Specifically, on the basis of the acquired lesion image, the edge contour line of the lesion image can be detected and marked through the edge detection model, so as to determine multiple candidate operation starting points on the edge contour line. A straight-line connection is made between each determined starting point of the operation to be selected and the end point of the operation corresponding to the lesion site, so as to determine the path of the operation to be selected corresponding to each starting point of the operation to be selected.

For example, see Fig. 2 for a schematic diagram of lesion images. As shown in Figure 2, the peripheral curve is the edge contour line, and the four candidate surgical starting points are determined on the edge contour line as A1, A2, A3, and A4, and O is the surgical end point corresponding to the lesion site. L1 is the candidate surgical path determined by the candidate surgical starting point A1 and the surgical end point O corresponding to the lesion site. Correspondingly, L2 is the candidate surgical path determined by the candidate surgical starting point A2 and the surgical end point O; L3 is the candidate surgical path determined by the candidate surgical starting point A3 and the surgical end point O; L4 is the candidate surgical starting point A4 and the surgical path The candidate surgical path determined by the end point O.

S130. Determine first path characteristic information corresponding to each candidate surgical path based on the lesion image, and determine second path characteristic information corresponding to each candidate surgical path based on the angiography image.

Wherein, the first path feature information is used to characterize the data feature of the candidate surgical path on the lesion image; the second path feature information is used to characterize the data feature of the candidate surgical path on the angiographic image. Optionally, the first path feature information and the second path feature information may be in the form of feature vectors. For each candidate surgical path, corresponding first path characteristic information and second path characteristic information are determined.

Specifically, each candidate surgical path in the lesion image can be mapped to the angiography image. For each surgical path to be selected, the first path characteristic parameter corresponding to the surgical path to be selected is determined based on the pixel points of the surgical path to be selected through the lesion image; pixels, and determine the second path characteristic parameter corresponding to the candidate surgical path.

S140. Based on the target neural network model obtained through pre-training, the first path characteristic information and the second path characteristic information corresponding to the candidate surgical paths, determine the target surgical path corresponding to the lesion site from the plurality of candidate surgical paths.

Among them, the target neural network model is obtained through pre-training. The training sample set used in the training process of the target neural network model includes at least one sample data, and each sample data includes a lesion image of the same lesion site, an angiographic image corresponding to the lesion image, and a pre-marked operation path. Since the training sample set is historical diagnosis and treatment data, the pre-marked surgical path is determined according to the actual surgical path determined by the reception staff.

Wherein, the target surgical path is a surgical path finally determined from multiple candidate surgical paths. The target surgical path is used to characterize the relatively ideal surgical path among the candidate surgical paths.

Specifically, the first path feature information and the second path feature information corresponding to each surgical path to be selected are used as a set of feature vectors and input to the target neural network model obtained in advance, and the target neural network model can output each candidate surgical path The predicted probability value corresponding to the surgical path. Furthermore, according to the predicted probability value corresponding to each candidate surgical path, the target surgical path corresponding to the lesion site is determined from the plurality of candidate surgical paths.

On the basis of the above example, the first path feature information M1 and the second path feature information N1 of L1 may be used as a set of feature vectors (M1, N1). Correspondingly, the eigenvector corresponding to L2 can be expressed as (M2, N2); the eigenvector corresponding to L3 can be expressed as (M3, N3); the eigenvector corresponding to L4 can be expressed as (M4, N4) . Then, (M1, N1), (M2, N2), (M2, N2) and (M2, N2) are input to the target neural network model, and the target neural network model outputs the predicted probability value X1 corresponding to L1, which is corresponding to L2. The corresponding predicted probability value X2, the predicted probability value X3 corresponding to L3, and the predicted probability value X4 corresponding to L4. Finally, according to the relationship between the numerical values of X1, X2, X3 and X4, the target surgical path corresponding to the lesion site is determined from L1, L2, L3 and L4.

It should be noted that multiple target neural network models corresponding to different lesion sites can be pre-trained. For example, a target neural network model corresponding to a head lesion, a target neural network model corresponding to an abdominal lesion, etc. may be pre-trained. In the specific application process, according to the corresponding lesion of the lesion, the target neural network model corresponding to the lesion is determined, and further, the first path feature information and the second path feature information corresponding to the lesion are input into the path corresponding to the lesion The target neural network model corresponding to the site, so as to obtain the target surgical path corresponding to the lesion site.

In the technical solution provided by the embodiment of the present invention, by acquiring the lesion image and angiographic image of the lesion, multiple candidate surgical starting points are determined on the edge contour line of the lesion image, and based on the correspondence between the multiple candidate surgical starting points and the lesion site Surgical end point, determine multiple candidate surgical paths. Determine the first path feature information corresponding to each surgical path to be selected based on the lesion image, and determine the second path feature information corresponding to each surgical path to be selected based on the angiographic image, so that based on the target neural network model obtained in advance, the target neural network model to be selected Select the first path characteristic information and the second path characteristic information corresponding to the surgical path, and determine the target surgical path corresponding to the lesion from multiple surgical paths to be selected, thereby realizing the automatic determination of the surgical path without human participation, and the lesion The first path feature information and the second path feature information are obtained by parametric evaluation of the candidate surgical path in the image and angiography image, and path prediction is performed on the first path feature information and the second path feature information through the target neural network model, which can be The appropriate surgical path is accurately determined, and the efficiency and accuracy of the surgical path are improved.

On the basis of the above-mentioned embodiments, determining a plurality of candidate surgical start points on the edge contour line of the lesion image specifically includes: determining a candidate surgical start point every preset number of pixels on the edge contour line of the lesion image; Or, based on the length and the preset number of edge contour lines, determine the distance information between two adjacent candidate surgical start points, and determine multiple candidate surgical start points on the edge contour lines of the lesion image based on the distance information.

In this embodiment, determining a plurality of candidate operation starting points on the edge contour line of the lesion image may include at least two manners. One way is to determine a starting point of a candidate operation every preset number of pixels on the edge contour line of the lesion image, for example, a starting point of a candidate operation can be determined every 20 pixels; A specified number of candidate surgical starting points are identified online. Exemplarily, it is preset to determine 100 candidate surgical starting points on the edge contour line, then the preset number is 100, the length of the edge contour line can be directly determined according to the pixel points corresponding to the edge contour line, and then the edge contour line Dividing the length by the preset number can determine the distance information between two adjacent start points of the operation to be selected, so that multiple start points of the operation to be selected can be determined on the edge outline of the lesion image according to the distance information.

Embodiment two

Fig. 4 is a flow chart of a method for determining a surgical path provided by Embodiment 2 of the present invention. On the basis of the above-mentioned embodiments, the embodiment of the present invention further refines S130 of the embodiment of the present invention. The embodiment of the present invention can be compared with the above-mentioned Various optional solutions in one or more embodiments are combined. As shown in Figure 4, the method includes:

S210. Acquire a lesion image and an angiographic image of the lesion.

S220. Determine multiple candidate surgical starting points on the edge contour of the lesion image, and determine multiple candidate surgical paths based on the multiple candidate surgical starting points and the surgical end points corresponding to the lesion.

S231. For each surgical path to be selected, based on the multiple functional tissue areas and lesion images corresponding to the target site, determine the target functional tissue area that the surgical path to be selected passes through the lesion image and the first functional tissue area corresponding to each target functional tissue area. Number of passing pixels.

Wherein, the target site is the body part where the lesion is located, for example, the target site may be the head or the abdomen. The functional organization area is a pre-set different functional division corresponding to the target site. The target functional tissue area is the functional tissue area that the surgical path to be selected passes through in the lesion image.

Optionally, if the lesion is a head lesion, the functional tissue area corresponding to the head lesion includes: epidermal skull area and brain function classification area; if the lesion is an abdominal lesion, the functional tissue area corresponding to the abdominal lesion The divisions include: skin, connective tissue and organs classification division.

Wherein, the brain function division includes at least one sub-function division. The organ classification area includes at least one sub-organ division. For an exemplary schematic diagram of the functional organization area, refer to FIG. 5 . As shown in Figure 5, the image of the lesion corresponding to the head, the target part is the head, and the functional tissue area corresponding to the head includes the skull area S1, the sub-function area S2, the sub-function area S3, the sub-function area S4, the sub-function area Functional partition S5 and sub-functional partition S6.

Optionally, the weight value corresponding to the epidermal skull area is smaller than the weight value corresponding to the brain function classification area; the weight value corresponding to the skin is smaller than the weight value corresponding to the connective tissue, and the weight value corresponding to the connective tissue is smaller than the weight value corresponding to the organ classification area.

In this embodiment, different weight values are preset for different functional organization areas. During the operation, if the surgical path passes through the epidermis and skull area, it will have little impact on the patient, but if the surgical path passes through the brain function classification area corresponding to the important brain tissue, the surgical effect will be affected. Based on this, the weight value corresponding to the epidermal skull area is smaller than the weight value corresponding to the brain function classification area. Different weight values are set for the sub-function divisions included in the brain function classification area according to their importance. For example, the weight value of the more important sub-function partition setting is larger.

If the lesion is an abdominal lesion, the functional organization area includes: skin, connective tissue, and organ classification area. Different weight values can be set for skin, connective tissue, and organ classification areas respectively. During the operation, if the surgical path passes through the skin, it will not affect the operation, but if it passes through the connective tissue, it may affect the operation, and if the surgical path passes through important organs and tissues, it will have a serious negative impact on the operation. Based on this, the weight value corresponding to the skin is smaller than the weight value corresponding to the connective tissue, and the weight value corresponding to the connective tissue is smaller than the weight value corresponding to the organ classification area. The sub-organ divisions included in the organ classification area have different weight values set according to their importance.

It should be noted that the method for determining the first path characteristic information of each candidate surgical path is the same, and one of the candidate surgical paths is taken as an example to illustrate.

In this embodiment, multiple functional tissue regions corresponding to the target site may be pre-marked. According to the target site where the lesion is located, multiple functional tissue regions corresponding to the target site can be retrieved. Further, for a candidate surgical path, it is firstly determined that in the lesion image, the candidate surgical path passes through at least one target functional tissue area of the lesion image. Further, the number of first passing pixel points of the candidate surgical path passing through each target functional tissue area is determined.

Exemplarily, as shown in FIG. 5 , the target functional tissue areas passed by the surgical path L1 to be selected include S1, S2, S5, and S6, and the number of the first passing pixels passing through the target functional tissue area S1 is 100 , the number of first passing pixels passing through the target functional organization area S2 is 500, the number of first passing pixels passing through the target functional organization area S5 is 150, and the first passing pixel points passing through the target functional organization area S6 The number of passing pixels is 130.

S232. Based on the target functional organization area and the corresponding relationship between the functional organization area and the weight value, determine a target weight value corresponding to each target functional organization area.

Wherein, the target weight value is the weight value corresponding to the target functional organization area.

In practical applications, the corresponding relationship between different functional organization areas and weight values can be set in advance, and on the basis of determining each target functional organization area, according to the corresponding relationship, determine the target function corresponding to each target functional organization area. Weights.

On the basis of the above example, the target weight value q1 corresponding to the target functional organization area S1, the target weight value q2 corresponding to the target functional organization area S2, the target weight value q3 corresponding to the target functional organization area S5, and the target functional organization area S6 corresponding to The target weight value of q4.

S233. Based on the number of first passing pixels and the target weight value, determine the feature value of the functional area corresponding to each target functional organization area.

In this embodiment, the feature value of the functional area corresponding to each target functional organization area is the product of the number of first passing pixels and the target weight value.

On the basis of the above example, the characteristic value of the functional area corresponding to the target functional organization area S1 can be expressed as 100×q1, the characteristic value of the functional area corresponding to the functional organization area 2 can be expressed as 500×q2, and the characteristic value of the functional area corresponding to the functional organization area S5 can be expressed as The characteristic value of the functional area can be expressed as 150×q3, and the characteristic value of the functional area corresponding to the functional organization area S6 can be expressed as 130×q4.

S234. Based on the feature values of the functional areas corresponding to the target functional tissue areas, determine the first path feature information corresponding to each surgical path to be selected.

In this embodiment, the first path feature information corresponding to a candidate surgical path is a vector composed of feature values of functional areas corresponding to target functional tissue areas. Based on the above example, the first path characteristic information corresponding to the surgical path L1 to be selected may be expressed as {100×q1, 500×q2, 150×q3, 130×q4}.

S241. Determine that the surgical path to be selected passes through each second passing pixel point of the angiographic image, and determine a target blood vessel pixel point closest to each second passing pixel point.

Wherein, the second passing pixel point is a pixel point corresponding to the surgical path to be selected on the angiography image. Exemplarily, as shown in FIG. 3 , each pixel point corresponding to the surgical path L1 to be selected on the angiography image is the second passing pixel point.

In this embodiment, on the basis of determining each second passing pixel point, the target blood vessel pixel point closest to each second passing pixel point is further determined.

S242. For each second passing pixel point, determine blood vessel distance information corresponding to each second passing pixel point based on the second passing pixel point and the target blood vessel pixel point closest to the second passing pixel point.

Wherein, the blood vessel distance information is actual physical length information between the second crossing pixel point and the target blood vessel pixel point.

In this embodiment, the method for determining the blood vessel distance information corresponding to each second crossing pixel point is the same. For one of the second passing pixel points, after determining the corresponding target blood vessel pixel point, the distance between the second passing pixel point and the target blood vessel pixel point on the angiographic image and the imaging of the angiographic image ratio, and determine the blood vessel distance information corresponding to the second crossing pixel point.

S243. Based on the distance information of each blood vessel, determine the second path characteristic information corresponding to each surgical path to be selected.

In this embodiment, the second path characteristic information corresponding to a surgical path to be selected is a vector composed of distance information of various blood vessels.

On the basis of the above example, if the surgical path L1 to be selected contains 10 second passing pixel points, the blood vessel distance information to each second passing pixel point is: d1, d2, d3, d4, d5, d6, d7, d8, d9, and d10, the second path feature information corresponding to the candidate surgical path L1 can be expressed as {d1, d2, d3, d4, d5, d6, d7, d8, d9, d10}.

S250. Input the first path characteristic information and the second path characteristic information corresponding to each candidate surgical path into the pre-trained target neural network model for path prediction, and obtain the predicted probability value corresponding to each candidate surgical path.

In practical applications, the first path characteristic information and the second path characteristic information corresponding to each surgical path to be selected are used as input quantities, and the input quantities are input into the target neural network model obtained through pre-training. The output of the target neural network model is the predicted probability value corresponding to each surgical path to be selected.

S260. Based on the predicted probability value, determine a target surgical path corresponding to the lesion site from multiple surgical paths to be selected.

In this embodiment, after the predicted probability values corresponding to each candidate surgical path are determined, the candidate surgical path with the largest predicted probability value is further determined as the target surgical path.

In the technical solution provided by the embodiment of the present invention, when determining the first path characteristic information corresponding to the surgical path to be selected, the target of the surgical path to be selected passing through the lesion image is determined based on the multiple functional tissue areas and lesion images corresponding to the target site The number of pixels corresponding to the functional organization area and each target functional organization area, based on the corresponding relationship between the target functional organization area and the functional organization area and the weight value, determine the corresponding to each target functional organization area The target weight value, based on the number of first passing pixels and the target weight value, determine the corresponding functional area feature value of each target functional organization area, and then determine each candidate function area based on the functional area feature value corresponding to each target functional organization area The first path feature information corresponding to the surgical path. When determining the second path characteristic information corresponding to the surgical path to be selected, firstly determine that the surgical path to be selected passes through each second passing pixel point of the angiography image, and determine the target blood vessel closest to each second passing pixel point Pixel points, and then for each second passing pixel point, based on the second passing pixel point and the target blood vessel pixel point closest to the second passing pixel point, determine the blood vessel distance corresponding to each second passing pixel point information, so as to determine the second path characteristic information corresponding to each surgical path to be selected based on the distance information of each blood vessel. In the embodiment of the present invention, in the process of determining the surgical path, the first path characteristic information of the surgical path to be selected in the lesion image is firstly determined, and the second path characteristic information of the surgical path to be selected in the angiographic image is determined, so as to realize image The parametric evaluation of the content uses the target neural network model to perform path prediction on the first path feature information and the second path feature information, thereby determining the target surgical path, and further improving the efficiency and accuracy of determining the surgical path.

Embodiment Three

FIG. 6 is a schematic structural diagram of an apparatus for determining a surgical path provided by Embodiment 3 of the present invention, and the apparatus can implement the method for determining an operating path provided by the embodiment of the present invention. The device includes: an image data acquisition module 310 , a candidate path determination module 320 , a feature information determination module 330 and a target path determination module 340 .

An image data acquisition module 310, configured to acquire lesion images and angiographic images of lesion sites;

The candidate path determination module 320 is configured to determine multiple candidate surgical starting points on the edge contour of the lesion image, and determine multiple candidate surgical paths based on the multiple candidate surgical starting points and the surgical end points corresponding to the lesion site;

A characteristic information determining module 330, configured to determine first path characteristic information corresponding to each surgical path to be selected based on the lesion image, and determine second path characteristic information corresponding to each surgical path to be selected based on the angiography image;

The target path determination module 340 is configured to determine the target corresponding to the lesion from multiple surgical paths to be selected based on the target neural network model obtained in advance, the first path characteristic information and the second path characteristic information corresponding to the surgical path to be selected surgical path.

On the basis of the above-mentioned technical solutions, the candidate path determination module 320 includes a candidate surgery start point determination unit, which is used to determine a candidate surgery start point every preset number of pixels on the edge contour line of the lesion image; or, Based on the length and the preset number of the edge contour lines, the distance information between two adjacent candidate operation start points is determined, and multiple candidate operation start points are determined on the edge contour lines of the lesion image based on the distance information.

On the basis of the above technical solutions, the feature information determining module 330 includes: a first feature determining unit and a second feature determining unit. The first feature determination unit includes:

The pass quantity determination subunit is used to determine, for each surgical path to be selected, the target functional tissue area and each target functional tissue area of the lesion image that the surgical path to be selected passes through based on the multiple functional tissue areas and lesion images corresponding to the target site. The number of first passing pixels corresponding to the functional tissue area;

A target weight value determining subunit, configured to determine a target weight value corresponding to each target functional organization area based on the target functional organization area and the correspondence between the functional organization area and the weight value;

The feature value determination subunit is used to determine the feature value of each functional area corresponding to each target functional organization area based on the number of pixels passed through first and the target weight value;

The first feature determining subunit is configured to determine first path feature information corresponding to each candidate surgical path based on the feature values of the functional areas corresponding to each target functional tissue area.

The second feature determination unit includes:

A pixel point determining subunit, configured to determine the second passing pixel points of the angiography image through which the surgical path to be selected passes, and determine the nearest target blood vessel pixel point to each second passing pixel point;

The distance information determination subunit is used to determine, for each second passing pixel point, based on the second passing pixel point and the target blood vessel pixel point closest to the second passing pixel point, Corresponding blood vessel distance information;

The second feature determination subunit is configured to determine the second path feature information corresponding to each surgical path to be selected based on the distance information of each blood vessel.

On the basis of the above-mentioned technical solutions, the target path determination module 340 includes:

The prediction probability value determination subunit is used to input the first path feature information and the second path feature information corresponding to each candidate surgical path into the target neural network model obtained in pre-training for path prediction, and obtain each candidate surgical path The predicted probability value corresponding to the path;

The target path determining subunit is configured to determine a target surgical path corresponding to the lesion site from multiple candidate surgical paths based on the predicted probability value.

In the technical solution provided by the embodiment of the present invention, by acquiring the lesion image and angiographic image of the lesion, multiple candidate surgical starting points are determined on the edge contour line of the lesion image, and based on the correspondence between the multiple candidate surgical starting points and the lesion site Surgical end point, determine multiple candidate surgical paths. Determine the first path feature information corresponding to each surgical path to be selected based on the lesion image, and determine the second path feature information corresponding to each surgical path to be selected based on the angiographic image, so that based on the target neural network model obtained in advance, the target neural network model to be selected Select the first path characteristic information and the second path characteristic information corresponding to the surgical path, and determine the target surgical path corresponding to the lesion from multiple surgical paths to be selected, thereby realizing the automatic determination of the surgical path without human participation, and the lesion The first path feature information and the second path feature information are obtained by parametric evaluation of the candidate surgical path in the image and angiography image, and path prediction is performed on the first path feature information and the second path feature information through the target neural network model, which can be The appropriate surgical path is accurately determined, and the efficiency and accuracy of the surgical path are improved.

The device for determining a surgical path provided by an embodiment of the present disclosure can execute the method for determining a surgical path provided by any embodiment of the present disclosure, and has corresponding functional modules and beneficial effects for executing the method.

It is worth noting that the units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only In order to facilitate mutual distinction, it is not intended to limit the protection scope of the embodiments of the present disclosure.

Embodiment Four

FIG. 7 is a schematic structural diagram of an electronic device provided by Embodiment 4 of the present invention. Electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable electronic devices (eg, helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the inventions described and/or claimed herein.

As shown in FIG. 7 , the electronic device 10 includes at least one processor 11, and a memory connected in communication with the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores There is a computer program executable by at least one processor, and the processor 11 can operate according to a computer program stored in a read-only memory (ROM) 12 or loaded from a storage unit 18 into a random access memory (RAM) 13. Various appropriate actions and processes are performed. In the RAM 13, various programs and data necessary for the operation of the electronic device 10 are also stored. The processor 11 , the ROM 12 and the RAM 13 are connected to each other through the bus 13 . An input/output (I/O) interface 15 is also connected to the bus 13 .

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

Processor 11 may be various general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes various methods and processes described above, such as a method for determining a surgical path.

In some embodiments, the method for determining the surgical path can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18 . In some embodiments, part or all of the computer program may be loaded and/or installed on the electronic device 10 via the ROM 12 and/or the communication unit 19 . When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the surgical path described above can be executed. Alternatively, in other embodiments, the processor 11 may be configured in any other suitable manner (for example, by means of firmware) to execute the method for determining the surgical path.

Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic devices (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.

Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable surgical path determination devices, so that when the computer program is executed by the processor, the functions/operations specified in the flowcharts and/or block diagrams are implemented. A computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

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

In order to provide interaction with the user, the systems and techniques described herein can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display)) for displaying information to the user. monitor); and a keyboard and pointing device (eg, a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.

The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

A computing system can include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or a cloud host. It is a host product in the cloud computing service system to solve the problems of difficult management and weak business expansion in traditional physical hosts and VPS services. defect. It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, each step described in the present invention may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution of the present invention can be achieved, there is no limitation herein. The above specific implementation methods do not constitute a limitation to the protection scope of the present invention. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. A method of determining a surgical path, comprising:

acquiring a focus image and an angiography image corresponding to a focus position;

determining a plurality of to-be-processed starting points on the edge contour line of the focus image, and determining a plurality of to-be-processed paths based on the to-be-processed starting points and the corresponding operation end points of the focus part;

determining first path characteristic information corresponding to each path to be operated based on the focus image, and determining second path characteristic information corresponding to each path to be operated based on the angiographic image;

and determining the target operation path corresponding to the focus part from a plurality of to-be-operated paths based on the target neural network model obtained through pre-training, the first path characteristic information and the second path characteristic information corresponding to the to-be-operated paths.

2. The method of claim 1, wherein the determining a plurality of waiting surgical origins on the edge contour of the lesion image comprises:

determining a starting point to be selected at intervals of the number of preset pixel points on the edge contour line of the focus image; or alternatively, the first and second heat exchangers may be,

and determining interval information between two adjacent waiting operation starting points based on the length of the edge contour lines and the preset number, and determining a plurality of waiting operation starting points on the edge contour lines of the focus image based on the interval information.

3. The method of claim 1, wherein the determining first path feature information corresponding to each path to be treated based on the lesion images comprises:

for each path to be operated, determining the number of target functional tissue areas of the path to be operated passing through the focus image and first passing pixel points corresponding to each target functional tissue area based on a plurality of functional tissue areas corresponding to the target part and the focus image;

determining a target weight value corresponding to each target functional organization area based on the target functional organization area and the corresponding relation between the functional organization area and the weight value;

determining a feature value of a functional area corresponding to each target functional organization area based on the first passing pixel point number and the target weight value;

and determining first path characteristic information corresponding to each path to be operated based on the function area characteristic values corresponding to the target function organization areas.

4. The method of claim 3, wherein if the focal site is a head lesion, the functional tissue area corresponding to the head lesion comprises: a epidermal skull region and a brain function classification region; if the lesion site is an abdominal lesion site, the functional tissue region corresponding to the abdominal lesion site includes: skin, connective tissue and organ classification.

5. The method of claim 4, wherein the weight value corresponding to the epidermal skull region is less than the weight value corresponding to the brain function classification region; the weight value corresponding to the skin is smaller than the weight value corresponding to the connective tissue, and the weight value corresponding to the connective tissue is smaller than the weight value corresponding to the organ classification area.

6. The method of claim 1, wherein determining second path feature information corresponding to each path to be planned based on the angiographic image comprises:

determining each second passing pixel point of the angiography image through which the path to be operated passes, and determining a target vascular pixel point nearest to each second passing pixel point;

for each second passing pixel point, determining blood vessel distance information corresponding to each second passing pixel point based on the second passing pixel point and a target blood vessel pixel point nearest to the second passing pixel point;

and determining second path characteristic information corresponding to each path to be operated based on the blood vessel distance information.

7. The method according to claim 1, wherein determining the target surgical path corresponding to the focal site from the plurality of surgical paths to be selected based on the target neural network model obtained by training in advance, the first path feature information and the second path feature information corresponding to the surgical path to be selected, comprises:

Inputting the first path characteristic information and the second path characteristic information corresponding to each path to be operated into a target neural network model obtained through training in advance to conduct path prediction, and obtaining a prediction probability value corresponding to each path to be operated;

and determining a target operation path corresponding to the focus part from a plurality of operation paths to be selected based on the predicted probability value.

8. A surgical path determination apparatus, comprising:

an image data acquisition module for acquiring a focus image containing the same focus part and an angiography image corresponding to the focus image;

the candidate route determining module is used for determining a plurality of candidate surgical starting points on the edge contour line of the focus image and determining a plurality of candidate surgical routes based on the plurality of candidate surgical starting points and surgical end points corresponding to focus positions;

the feature information determining module is used for determining first path feature information corresponding to each path to be operated based on the focus image and determining second path feature information corresponding to each path to be operated based on the angiography image;

the target path determining module is used for determining a target operation path corresponding to the focus part from a plurality of to-be-operated paths based on a target neural network model obtained through pre-training, the first path characteristic information and the second path characteristic information corresponding to the to-be-operated paths.

9. An electronic device, the electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of determining a surgical path according to any one of claims 1 to 7.

10. A computer readable storage medium storing computer instructions for causing a processor to perform the method of determining a surgical path according to any one of claims 1 to 7.

Images