CN115880326A

CN115880326A - Contour acquisition method of medical image, terminal and storage medium

Info

Publication number: CN115880326A
Application number: CN202111130458.5A
Authority: CN
Inventors: 杨伟群; 闫浩; 罗春
Original assignee: Our United Corp
Current assignee: Our United Corp
Priority date: 2021-09-26
Filing date: 2021-09-26
Publication date: 2023-03-31

Abstract

The application discloses a contour acquisition method of a medical image, a terminal and a storage medium, and belongs to the technical field of medical images. The method comprises the following steps: acquiring a first contour matrix corresponding to a first tangent plane contour of a target part in Y first medical tangent plane images; acquiring data points of a target row in Y first contour matrixes; and determining a second section contour of the target part based on the data point with the median of the data points of the Y target rows as a first preset value. The two section profiles are the profiles of the target part on the section perpendicular to the cross section. Thus, when the section perpendicular to the cross section is a coronal plane, the determined second section profile is the profile of the target site on the coronal plane; when the section perpendicular to the transverse plane is a sagittal plane, the contour of the second section is determined to be the contour of the target part on the sagittal plane. The types of the obtained outlines of the target parts are effectively enriched.

Description

Contour acquisition method of medical image, terminal and storage medium

Technical Field

The present application relates to the field of medical imaging technologies, and in particular, to a method and an apparatus for obtaining a contour of a medical image, and a storage medium.

Background

Currently, medical Imaging devices using Computed Tomography (CT), spectral CT, cone Beam CT (CBCT), magnetic Resonance Imaging (MRI), and other technologies are widely used in clinical medical image diagnosis.

After a medical imaging device acquires a medical sectional image (for example, a CT image) of a patient, the medical sectional image is processed by an Artificial Intelligence (AI) model, so that the contour of a target part (for example, a lesion and an organ at risk around the lesion) in the medical sectional image can be obtained. Subsequently, the contour of the target part is added on the medical sectional image, so that the medical sectional image with the contour can be obtained.

To evaluate the delineation of the target site contour in three-dimensional space, the physician typically needs to view the contour of the target site in the transverse, sagittal, or coronal planes. However, the medical sectional image acquired by the medical imaging apparatus is generally an image of a patient in a cross section, and therefore, only the contour of the target portion in the cross section can be acquired, and how to acquire the contour of the target portion in other planes (for example, a sagittal plane or a coronal plane) is a technical problem to be solved by the present application.

Disclosure of Invention

The embodiment of the application provides a contour acquisition method of a medical image, a terminal and a storage medium. The method can solve the problem that the type of the contour of the target part obtained at present is single, and the technical scheme is as follows:

in one aspect, a method for contour acquisition of a medical image is provided, the method comprising:

acquiring a first contour matrix corresponding to a first tangent plane contour of a target part in Y first medical tangent plane images, wherein the first contour matrix comprises X rows and Z columns of data points, values of data points corresponding to the first tangent plane contour in the first contour matrix are first preset values, and values of at least part of other data points are different from the first preset values;

acquiring Y data points of a target row in the first contour matrix;

determining a second tangent plane profile of the target part based on the data point with the median of the data points of the Y target rows as the first preset value;

wherein X, Y and Z are both integers greater than 1.

Optionally, obtaining each of the Y first contour matrices includes:

acquiring each first contour point coordinate of a first tangent plane contour of a target part in each first medical tangent plane image;

and constructing the first contour matrix based on the coordinates of the first contour points and the data points in the first medical sectional image.

Optionally, constructing the first contour matrix based on the coordinates of the first contour points and the data points in the first medical sectional image includes:

constructing an initial matrix based on data points in the first medical sectional image, wherein the initial matrix comprises X rows and Z columns of data points, and the value of each data point in the initial matrix is a second preset value;

and setting the values of the data points corresponding to the coordinates of the first contour points in the initial matrix as the first preset values and setting the values of the data points in the area surrounded by the first contour points as the first preset values based on the coordinates of the first contour points to obtain the first contour matrix, wherein the first preset values are different from the second preset values.

Optionally, before the acquiring Y data points of the target row in the first contour matrix, the method further includes:

receiving indication information triggered by a user and used for acquiring a second section contour of the target part on the target section;

and determining a target row corresponding to the target tangent plane in the first contour matrix based on the indication information.

Optionally, the determining a second tangent profile of the target portion based on the data point whose median of the data points in the Y target rows is the first preset value includes:

splicing the data points of the Y target rows to obtain a second contour matrix, wherein the second contour comprises Y rows of data points;

determining coordinates of each second contour point corresponding to the data point with the value of the first preset value based on the data point with the median of the second contour matrix as the first preset value;

and determining a second tangent plane contour of the target part based on the coordinates of the second contour points.

Optionally, the data points of the Y target rows are spliced to obtain a second contour matrix, including:

and splicing the data points of the Y target rows according to a target sequence to obtain a second contour matrix, wherein the target sequence is the sequential ordering of the target parts in the Y first medical sectional images according to different sectional positions.

Optionally, the method further includes:

superposing the first medical section image and the first section contour to obtain a first target medical image;

after the second tangent plane contour of the target part is determined, a second medical tangent plane image corresponding to the second tangent plane contour is obtained, and the second medical tangent plane image and the second tangent plane contour are superposed to obtain a second target medical image.

Optionally, the method further includes:

after a contour modification instruction is received, adjusting a first tangent contour in the first target medical image to obtain an updated first target medical image;

and adjusting a second tangent plane contour in the second target medical image based on the updated first target medical image.

In another aspect, a terminal is provided, which includes: a processor and a memory for storing executable instructions of the processor, wherein the processor is configured to execute the contour acquisition method of medical images described above.

In yet another aspect, a computer-readable storage medium is provided, having instructions stored therein, which when run on a processing assembly, causes the processing assembly to perform the above-mentioned contour acquisition method for medical images.

The beneficial effects that technical scheme that this application embodiment brought include at least:

by obtaining first contour matrixes corresponding to first section contours of Y target parts on the cross section and obtaining target row data points from each first contour matrix, a second section contour of the target part can be determined based on Y target row pixel points, and the second section contour is the contour of the target part on a section perpendicular to the cross section. Thus, when the section perpendicular to the cross section is a coronal plane, the determined second section contour is the contour of the target part on the coronal plane; when the section perpendicular to the transverse plane is a sagittal plane, the contour of the second section is determined to be the contour of the target part on the sagittal plane. The types of the obtained outlines of the target parts are effectively enriched, and the diagnosis effect of a doctor on a patient is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a medical system according to a contour acquisition method for medical images provided in an embodiment of the present application;

FIG. 2 is a schematic illustration of a transverse, sagittal and coronal plane in the medical field;

fig. 3 is a flowchart of a contour acquiring method for medical images according to an embodiment of the present application;

fig. 4 is a flowchart of another contour acquisition method for medical images according to an embodiment of the present application;

FIG. 5 is a diagram illustrating an effect of obtaining a second contour matrix according to an embodiment of the present application;

fig. 6 is a block diagram illustrating a configuration of a medical image contour acquiring apparatus according to an embodiment of the present application;

fig. 7 is a block diagram of a first obtaining module according to an embodiment of the present disclosure;

fig. 8 is a block diagram of a first determining module according to an embodiment of the present disclosure.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

Referring to fig. 1, fig. 1 is a schematic structural diagram of a medical system according to a method for obtaining a contour of a medical image according to an embodiment of the present application. The medical system 100 may include: a medical imaging device 101 and a terminal 102.

The medical imaging device 101 may be: a CT device, a spectral CT device, a cone beam CT device or an MRI device. The medical imaging device 101 is capable of acquiring medical sectional images (e.g., CT images indicating a cross-section) of a patient.

The terminal 102 may be a computer device such as a cell phone, a tablet, a laptop, or a desktop.

Wherein the medical imaging device 101 and the terminal 102 are communicatively connected. The medical imaging device 101 can send the medical sectional image acquired by the medical imaging device to the terminal 102.

Referring to fig. 2, fig. 2 is a schematic diagram of a transverse, sagittal, and coronal plane of a medical field. The cross section is as follows: dividing the human body into an upper section and a lower section; the sagittal plane refers to: dividing the human body into a left section and a right section; the coronal plane refers to: cutting the front and back parts of human body. Wherein any two different planes in the transverse plane, the sagittal plane and the coronal plane are two planes perpendicular to each other.

In the embodiment of the present application, the medical sectional image acquired by the medical imaging apparatus 101 is generally the first medical sectional image of the patient in the transverse plane. After the medical imaging device 101 sends the acquired first medical sectional image to the terminal 102, the terminal 102 can process the first medical sectional image in the web end, so that the target portion of the patient can be presented in the web page in the transverse plane, the sagittal plane, and the transverse plane.

Optionally, as shown in fig. 1, the medical system 100 may further include: a server 103. The server 103 may be communicatively connected to the medical imaging apparatus 101 and the terminal 102, respectively. The medical imaging device 101 sends the acquired first medical sectional image to the server 103, the server 103 processes the first medical sectional image to obtain a first sectional profile of the target portion in the first medical sectional image, and then sends the first medical sectional image and the first sectional profile of the target portion to the terminal 102.

In the present embodiment, the communication connection may be a communication connection established through a wired network or a wireless network.

Referring to fig. 3, fig. 3 is a flowchart of a contour acquiring method for medical images according to an embodiment of the present application. The contour acquisition method for medical images is applied to the terminal 102 in the medical system shown in fig. 1. The contour acquisition method for medical images can comprise the following steps:

step 201, a first contour matrix corresponding to a first tangent plane contour of a target part in Y first medical tangent plane images is obtained.

The first profile matrix comprises X rows and Z columns of data points, the value of a data point corresponding to the first tangent plane profile in the first profile matrix is a first preset value, and the value of at least part (or all) of other data points except the data point corresponding to the first tangent plane profile is different from the first preset value. In an embodiment of the present application, the first medical sectional image may be a sectional image of the patient in a cross section, and the first sectional profile of the target region in the first medical sectional image is a profile of the target region in the cross section.

Step 202, acquiring data points of a target row in Y first contour matrixes.

For example, the data point of the target row may be a row of data points in the first contour matrix, or may be a column of data points in the first contour matrix.

And step 203, determining a second section contour of the target part based on the data point of which the median of the data points of the Y target rows is the first preset value. Wherein X, Y and Z are both integers greater than 1.

In the embodiment of the present application, the second sectional profile is a profile of the target portion on a sectional plane perpendicular to the transverse plane. For example, when the data points in the target row are data points in one row in the first contour matrix, based on the data points of which the median value of the data points in the Y target rows is the first preset value, the determined second tangent plane contour is the contour of the target part on the coronal plane; and when the data points of the target row are a row of data points in the first contour matrix, determining the contour of the second tangent plane as the contour of the target part on the sagittal plane based on the data points of which the median of the data points of the Y target rows is the first preset value.

In summary, according to the contour acquiring method for a medical image provided in the embodiment of the present application, by acquiring first contour matrices corresponding to first tangent plane contours of Y target portions on a cross section and acquiring target row data points from each first contour matrix, a second tangent plane contour of a target portion can be determined based on Y target row pixel points, where the second tangent plane contour is a contour of the target portion on a tangent plane perpendicular to the cross section. Thus, when the section perpendicular to the cross section is a coronal plane, the determined second section contour is the contour of the target part on the coronal plane; when the section perpendicular to the transverse plane is a sagittal plane, the contour of the second section is determined to be the contour of the target part on the sagittal plane. The types of the obtained outlines of the target parts are effectively enriched, and the diagnosis effect of a doctor on a patient is improved.

Referring to fig. 4, fig. 4 is a flowchart of another medical image contour acquiring method according to an embodiment of the present application. The contour acquisition method for medical images is applied to the terminal 102 in the medical system shown in fig. 1. The contour acquisition method of the medical image can comprise the following steps:

step 301, obtaining Y first medical sectional images and a first sectional profile of a target portion in each first medical sectional image.

In this embodiment, the terminal may acquire Y first medical sectional images and a first sectional profile of the target portion in each first medical sectional image. The first medical sectional images are images of a section of the patient on the cross section, and the positions of the sections of the patient in the first medical sectional images are different. By way of example, after the medical imaging device shoots a patient, the medical imaging device can acquire Y first medical sectional images of the patient at different positions on the cross section, and the medical imaging device can send the acquired Y first medical sectional images to the terminal.

It should be noted that the first medical sectional image may include cross-sectional images of a plurality of different organs of the patient and lesions near the organs. The first medical sectional image may be processed using an AI model to obtain a first sectional profile of a target site (e.g., a lesion of a patient and an organ at risk around the lesion) in the first medical sectional image. The first cross-sectional profile is the cross-sectional profile of the target site. It should be noted that, the first tangent plane profile of the target portion in the first medical tangent plane image may be represented in a coordinate manner, and the first tangent plane profile of the target portion is: and coordinates of each pixel in a circle of pixels at the outermost side of the region where the target part is located in the first medical sectional image.

For example, after the medical imaging device acquires Y first medical sectional images, the medical imaging device may send the acquired Y first medical sectional images to the server. The server may input the first medical sectional image to the AI model to obtain a first sectional profile of the target portion in the first medical sectional image output by the AI model. The AI model may be a model obtained by learning and training using a deep neural network or a convolutional neural network. In this way, the server may obtain the first tangent profile of the target region in each first medical tangent image by processing the Y first medical tangent images. Subsequently, the server may send the Y first medical sectional images and the first sectional profile of the target portion in each first medical sectional image to the terminal. Therefore, the terminal can acquire Y first medical sections and first section outlines of the target part in each first medical section image.

Step 302, based on the Y first medical sectional images and the first sectional profile of the target portion in each first medical sectional image, generating Y first profile matrices corresponding to the Y first medical sectional images one to one.

In this embodiment, the terminal may generate Y first contour matrices corresponding to the Y first medical sectional images one to one based on the Y first medical sectional images and the first sectional contour of the target portion in each first medical sectional image. For example, the terminal may generate a first contour matrix corresponding to the first medical sectional image based on each first medical sectional image and the first sectional contour of the target site in the first sectional image.

Each first contour matrix comprises X rows and Z columns of data points, the values of the data points corresponding to the first tangent plane contour in the first contour matrix are first preset values, and the values of at least some other data points are different from the first preset values. For example, each data point in the first contour matrix may be a preset value, and each first contour matrix generated by the terminal is a grayscale image.

It should be noted that the other data points in the embodiment of the present application refer to data points in the first profile matrix other than the data points corresponding to the first tangent plane profile.

In one case, the values of a portion of other data points in the first profile matrix may be the same as the first predetermined value, and at least a portion of other data points in the first profile matrix may be the same as the first predetermined value. For example, the values of the other data points in the area surrounded by the data points corresponding to the first tangent plane profile in the first profile matrix are all the first preset values, and the values of the remaining data points in the first profile matrix are all different from the first preset values.

In another case, all other data points in the first contour matrix have different values from the first predetermined value, but it is necessary to ensure that the values of some other data points in the first contour matrix are different from the values of some other data points in the second contour matrix. For example, the values of the other data points in the area surrounded by the data points corresponding to the first tangent plane profile in the first profile matrix need to be different from the values of the remaining data points.

It should be further noted that, for convenience of subsequent processing, the subsequent embodiments are schematically illustrated by taking an example that the values of a part of other data points in the first profile matrix are the same as the first preset value. In this case, the shape of the area formed by the data points of which the median value in the first contour matrix is the first preset value can represent: the shape of a cross-sectional cut of the target site.

In this embodiment of the present application, obtaining each of the Y first contour matrices may include the following steps:

step 3021, obtaining coordinates of each first contour point of the first tangent plane contour of the target portion in each first medical tangent plane image.

In the embodiment of the present application, the first tangent profile acquired by the terminal can be represented in a coordinate manner. Therefore, the terminal can directly acquire the coordinates of each first contour point of the first tangent plane contour of the target part in each first medical tangent plane image. Each first contour point coordinate may be a coordinate of a corresponding data point in the first medical sectional image.

And step 3022, constructing a first contour matrix based on the coordinates of the first contour points and the data points in the first medical sectional image.

In the embodiment of the application, after the terminal acquires the coordinates of each first contour point of the first tangent plane image, the terminal can construct the first contour matrix based on the coordinates of each first contour point and the data points in the first medical tangent plane image.

By way of example, constructing each first contour matrix may include the following steps:

and step 3022a, constructing an initial matrix based on the data points in the first medical sectional image.

In this embodiment, the terminal may construct an initial matrix based on data points in the first medical sectional image. The initial matrix comprises X rows and Z columns of data points, the value of each data point in the initial matrix is a second preset value, and the second preset value is different from the first preset value.

For example, the number of data points included in the initial matrix may be the same as the number of data points included in the first medical sectional image. That is, the resolution of the initial matrix is the same as the resolution of the first medical sectional image. It should be noted that, since the resolutions of the Y first medical sectional images are generally the same, the initial matrix constructed based on each first medical sectional image is the same. For this reason, in the process of building Y first contour matrices, the step 3022a is only required to be performed once to build the initial matrix.

Step 3022b, based on the coordinates of the first contour points, setting values of data points corresponding to the coordinates of the first contour points in the initial matrix as first preset values, and setting values of data points in an area surrounded by the first contour points as the first preset values to obtain the first contour matrix.

In this embodiment, after the terminal acquires the coordinates of each first contour point of the first tangent plane image, the terminal may set, based on the coordinates of each first contour point, a value of a data point corresponding to each first contour point coordinate in the initial matrix as a first preset value, and set a value of a data point in an area surrounded by each first contour point as the first preset value, so as to obtain the first contour matrix. Thus, the values of the data points in the first profile matrix corresponding to the first tangent plane profile and the data points corresponding to the area enclosed by the first tangent plane profile are: a first predetermined value, and the values of the other data points in the first profile matrix are: a second preset value.

In this case, the coordinates of the first profile points of the first tangent profile acquired by the terminal are the coordinates of the corresponding data points in the first medical tangent image, and the resolution of the first tangent profile is the same as the resolution of the initial matrix. Thus, the terminal can determine the coordinates of a circle of data points corresponding to the first tangent profile in the initial template based on the respective first profile point coordinates. Then, the terminal may process the circle of data points and the values of the data points in the area surrounded by the circle of data points from the second preset value to the first preset value, so as to obtain a first contour matrix.

It should be noted that, in the above embodiments, the resolution of the initial matrix is the same as the resolution of the first medical sectional image. In other possible implementations, the resolution of the initial matrix may also be different from the resolution of the first medical sectional image. In this case, it is necessary to ensure that each data point in the initial matrix can be mapped with each data point in the first medical sectional image. In this way, after the terminal performs mapping conversion on the coordinates of each first contour point of the first tangent plane contour of the target portion in the first medical tangent plane image, the coordinates of a circle of data points corresponding to the first tangent plane contour can be determined in the initial matrix.

For example, when the value of each data point in the initial matrix is a preset value, the value of each data point in the initial matrix may be 0, that is, the initial matrix is a gray image with a black color. The data points corresponding to the first tangent plane profile in the first profile matrix obtained by processing the initial matrix by the terminal and the data points corresponding to the area enclosed by the first tangent plane profile may both have a value of 255. Thus, the first profile matrix is: the middle is a gray image with white and black surroundings.

Step 303, obtaining target row data points in the Y first contour matrixes.

In this embodiment of the application, after the Y first contour matrices are obtained in step 302, the terminal may obtain target row data points in the Y first contour matrices.

For example, the target row of data points in each first contour matrix may be a row of data points in the first contour matrix, or may be a column of data points in the first contour matrix. For example, when the target row of data points is a row of data points in the first contour matrix, the number of the target row of data points is X, and thus Y × X data points may be obtained; when the target row of data points is a column of data points in the first contour matrix, the number of the target row of data points is Z, so that Y × Z data points can be obtained.

Optionally, before the terminal acquires the target row data points in the Y first contour matrices, the contour acquiring method for the medical image may further include: and receiving indication information which is triggered by a user and used for acquiring the second section contour of the target part on the target section, and determining a target row corresponding to the target section in the first contour matrix based on the indication information. In this way, the terminal can obtain the corresponding target row data point in each first contour matrix. The target section may be perpendicular to the transverse plane, and may be a sagittal plane, a coronal plane, or other inclined planes (the included angle between the inclined plane and the sagittal plane or the coronal plane is an acute angle), etc.

In the embodiment of the application, when a user needs to check the contour of the target part on the target tangent plane, the user may trigger the indication information, so that the terminal can obtain the target row data points in the Y first contour matrixes after receiving the indication information, and the terminal can subsequently obtain the contour of the target part on the target tangent plane based on the Y target row data points.

For example, when the user needs to view the contour of the target portion on the coronal plane, the user may trigger the corresponding indication information, so that the terminal can acquire a row of data points in Y first contour matrices, and the position of the row of data points in each first contour matrix in the first contour matrix is the same, so that the terminal can subsequently acquire the contour of the target portion on the coronal plane based on the row of data points; when a user needs to view the contour of the target part on the sagittal plane, the user can trigger corresponding indication information, so that the terminal can acquire a column of data points in Y first contour matrixes, and the position of the column of data points in each first contour matrix in the first contour matrix is the same, so that the terminal can acquire the contour of the target part on the sagittal plane based on the Y column of data points.

And step 304, splicing the data points of the Y target rows to obtain a second contour matrix.

In this embodiment, after the terminal acquires the data points of the Y target rows, the terminal may splice the data points of the Y target rows to obtain a second contour matrix. Wherein the second contour matrix includes Y rows of data points.

Illustratively, the first profile matrix includes X rows and Z columns of data points. Therefore, when the data points of the target row in the first contour matrix are a row of data points, the second contour matrix obtained by splicing the data points of the Y target rows comprises Y rows and X columns of data points; and when the data points of the target row in the first contour matrix are a column of data points, splicing the data points of the Y target rows to obtain a second contour matrix comprising Y rows and Z columns of data points. In this case, the shape of the area formed by the data points of which the median value in the second contour matrix is the first preset value can represent: the shape of the section of the target site on the target section.

It should be noted that, when the target row pixel point obtained in step 303 is a row of data points in the first contour matrix, the subsequent terminal can obtain the contour of the target portion on the coronal plane based on the second contour matrix; when the target data point acquired in step 303 is a column of data points in the first contour matrix, the subsequent terminal may acquire the contour of the target portion on the sagittal plane based on the second contour matrix.

In this embodiment, in order to obtain the contour of the target portion at the position of the different tangent planes on the coronal plane, the terminal needs to take each row of data points in the Y first contour matrices as the target row of data points in step 303. Thus, in step 304, after the obtained Y target row data points are sequentially stitched, the obtained second contour matrix can be used to obtain the contour of the target portion at the corresponding tangent plane on the coronal plane.

Similarly, in order to obtain the contour of the target portion at the position of a different section on the sagittal plane, the terminal needs to take each row of data points in the Y first contour matrices as the target row of data points in step 303. Thus, in step 304, after the acquired Y target row data points are sequentially spliced, the obtained second contour matrix can be used to acquire the contour of the target portion at the corresponding section on the sagittal plane.

In this embodiment of the application, the Y first medical sectional images acquired in step 301 need to be sorted according to a target sequence, where the target sequence is a sequence of target sites in the Y first medical sectional images sorted according to different sectional positions. For example, the positions of the cross-sections of the Y first medical sectional images are arranged in order from the head to the foot of the patient. In this way, the Y first contour matrices obtained in step 302 may also be arranged in the target order.

In this case, the splicing, by the terminal, data points of Y target rows to obtain a second contour matrix may include: and splicing the data points of the Y target rows according to the target sequence to obtain a second contour matrix.

For example, as shown in fig. 5, fig. 5 is a diagram of an effect of obtaining the second contour matrix according to an embodiment of the present application. It is assumed that the Y first contour matrices are arranged in the order from left to right as shown in fig. 5, and the target row of data points in each first contour matrix is the second row of pixels in the first contour matrix. And splicing the Y target row data points according to the arrangement sequence of the Y first contour matrixes to obtain a second contour matrix.

And 305, determining coordinates of each second contour point corresponding to the data point with the value of the first preset value based on the data point with the value of the first preset value in the second contour matrix.

In this embodiment, after the terminal acquires the second contour matrix, the terminal may determine, based on the data points whose median values are the first preset values in the second contour matrix, coordinates of the second contour points corresponding to the data points whose values are the first preset values.

For example, the second contour matrix is obtained by stitching Y target row data points, and the Y first contour matrices are each composed of a first preset value and a second preset value. The second contour matrix is therefore also formed from the first and second preset values. For this, the terminal determines coordinates of each second contour point corresponding to the data point with the value of the first preset value based on the data point with the value of the first preset value in the second contour matrix, and may include the following steps:

step 3051, obtaining a target area of which the median of the second contour matrix is the first preset value.

In this embodiment, the terminal may obtain a target area whose median of the second contour matrix is a first preset value. Wherein, the target area with the value as the first preset value is: the area of the target site. The values of the data points in the region where the target portion is located in the second contour matrix are all first preset values, and the values of the data points in the region except the target portion in the second contour matrix are all second preset values. Therefore, the terminal can extract data points of which the preset values are the first preset values in the second contour matrix to obtain the target area.

And step 3052, determining coordinates of each data point in the circle of data points at the outermost side of the target area in the second contour matrix as coordinates of each second contour point.

In this embodiment of the application, after the terminal acquires the target area, the coordinates of each data point in the circle of data points at the outermost side of the target area in the second contour matrix may be determined as the coordinates of each second contour point.

And step 306, determining a second tangent plane contour of the target part based on the coordinates of the second contour points.

In this embodiment of the application, after the terminal acquires the coordinates of each second contour point, the terminal may determine the second tangent plane contour of the target portion. The second tangent plane outline is the outline of the target part on the target tangent plane.

It should be noted that, it is assumed that the second medical sectional image is an image of a sectional plane of the patient on the target sectional plane, and the second medical sectional image corresponds to the second contour matrix, that is, the position of the sectional plane of the patient on the target sectional plane in the second medical sectional image is the same as the position of the sectional plane of the target portion on the target sectional plane in the corresponding second contour matrix. Then, the second tangent plane profile determined by the terminal based on the second profile matrix is: and coordinates of each data point in a circle of data points at the outermost side of the region where the target position is located in the second medical sectional image.

It is further assumed that the resolution of the region where the target site is located in the second contour matrix is the same as the resolution of the target site in the corresponding second medical sectional image. Then, each pixel point of the second contour matrix can be mapped to a corresponding data point in the second medical sectional image. Therefore, the terminal performs coordinate conversion on the coordinates of each second contour point to obtain a second tangent plane contour.

However, the resolution of the region where the target portion is located in the second contour matrix obtained in step 304 may be affected by the number of Y first contour matrices. That is, if the number of the Y first contour matrices is larger, the resolution of the region where the target portion is located in the second contour matrix is higher; if the number of the Y first contour matrices is smaller, the resolution of the region where the target portion is located in the second contour matrix is lower. Therefore, the resolution of the region where the target site is located in the second contour matrix may be different from the resolution of the target site in the corresponding second medical sectional image, and the resolution of the region where the target site is located in the second contour matrix is usually smaller than the resolution of the target site in the corresponding second medical sectional image.

Therefore, in the embodiment of the present application, after the terminal performs coordinate conversion on the coordinates of each second contour point, the terminal further needs to process the coordinates of each converted data point, so as to determine the second tangent plane contour.

For example, it is assumed that the number of data points in a row in the second contour matrix is the same as the number of data points in the target row in the first contour matrix, and the number of data points in a column in the second contour matrix is the same as the number in the Y first contour matrices. Then, the number of data points of the target portion in the second contour matrix in the row direction is the same as the number of data points of the target portion in the corresponding second medical sectional image in the row direction. And when the number of the Y first contour matrixes is less, the number of data points of the target part in the second contour matrix in the column direction is less than the number of data points of the target part in the corresponding second medical sectional image in the column direction and is the same.

Further assume that the abscissa of the coordinates of each data point in the second profile matrix is determined based on the number of data points in a row of the second profile matrix and the ordinate is determined based on the number of data points in a column of the second profile matrix. Then, after the terminal converts the coordinates of each data point based on the coordinates of each data point in the circle of data points at the outermost side of the target region in the second contour matrix, the terminal needs to multiply the vertical coordinate in the coordinates of each data point by a specified coefficient, that is, the coordinates of each data point in the circle of data points at the outermost side of the region where the target portion is located in the second medical sectional image, that is, the second sectional contour.

Wherein the assigned coefficient is determined based on the distance between any two adjacent sections of the patient in the Y first medical sectional images in the transverse section and the distance between any two adjacent data points in the column direction in the second contour matrix. It is assumed that the distance between any two adjacent cross-sectional planes of the patient in the Y first medical sectional images is d1, and the distance between any two adjacent data points in the column direction in the second contour matrix is d2. Then, the specified coefficient a = d1/d2. It should be noted that, a data point in the present application may be a pixel, and thus, a distance between any two adjacent data points is a distance between any two pixels.

And 307, acquiring a second medical sectional image corresponding to the second contour matrix.

In this embodiment, the terminal may acquire a second medical sectional image corresponding to the second sectional profile. The second medical tangent plane image is a tangent plane image of the patient on the target tangent plane, and the contour of the target part in the second medical tangent plane image is the second tangent plane contour obtained based on the second contour matrix.

For example, the second medical sectional image may be generated based on a plurality of pieces of medical data corresponding to the plurality of pieces of first medical sectional images. If the first medical sectional image is a CT image, the medical data corresponding to the first medical sectional image is CT data. The CT data is a two-dimensional array of HU (Hounsfield Unit) values arranged in an array. Each CT data may be CT data of a slice of the target region in a cross-section. Therefore, different CT data at different tangent plane positions on the cross section are spliced, and a three-dimensional array consisting of HU values can be obtained. Therefore, the CT data of the three-dimensional array on the target section is converted, and a second medical section image corresponding to the second contour matrix can be obtained.

And 308, overlapping the first medical section image and the first section contour to obtain a first target medical image, and overlapping the second medical section image and the second section contour to obtain a second target medical image.

In this embodiment, the terminal may superimpose the first medical sectional image and the first sectional profile to obtain a first target medical image, and superimpose the second medical sectional image and the second sectional profile to obtain a second target medical image. The first target medical image is a first medical sectional image with a contour, and the second target medical image is a second medical sectional image with a contour.

It should be noted that, in step 308, the terminal may add a corresponding first cross-sectional profile to each first medical cross-sectional image, so as to obtain a plurality of first target medical images in the cross-sectional plane. Through steps 302 to 308, the terminal may obtain a plurality of second medical sectional images on the target sectional plane and a second sectional profile of the target portion in each second medical sectional image, and therefore, the terminal may add a corresponding second sectional profile to each first medical sectional image to obtain a plurality of second target medical images.

In the embodiment of the application, after the terminal obtains the first target medical image and the second target medical image, the first target medical image and the second target medical image can be displayed on a display interface of the terminal.

And 309, after receiving the contour modification instruction, adjusting the first tangent plane contour in the first target medical image to obtain an updated first target medical tangent plane image.

In this embodiment, after the first target medical image and the second target medical image are displayed on the display interface of the terminal, if the terminal receives the contour modification instruction, the terminal needs to adjust the contour of the first tangent plane in the first target medical image based on the contour modification instruction to obtain the updated first target medical image.

For example, it is assumed that, after the doctor views the first target medical image displayed on the display interface of the terminal, if the doctor does not overlap the outline of the target portion in the first target medical sectional image with the outer boundary of the target portion. Then, the doctor may trigger a contour modification instruction on the terminal, so that after receiving the contour modification instruction, the terminal adjusts the contour in the first target medical sectional image to obtain a further first target medical image.

For example, an expansion button and a contraction button may be displayed on the display interface of the terminal. If the doctor clicks the expansion button and performs sliding operation on the periphery of the first tangent plane outline in the first target medical image, and the area covered by the sliding operation is the area to be expanded, the terminal can expand the first tangent plane outline in the first target medical image according to the area to be expanded to obtain an updated first target medical image; if the doctor clicks the contraction button and performs sliding operation in the first tangent plane profile in the first target tangent plane image, and the area covered by the sliding operation is the area needing to be contracted, the terminal can reduce the first tangent plane profile in the first target medical image according to the area needing to be contracted to obtain the updated first target medical tangent plane image.

And 310, adjusting a second tangent plane contour in the second target medical image based on the updated first target medical tangent plane image to obtain an updated second target medical image.

In this embodiment, the terminal may adjust the second target medical image based on the updated first target medical image to obtain the updated second target medical image. The process of adjusting the second target medical image by the terminal to obtain the updated second target medical image may be the same as the above steps 302 to 308, that is, after the terminal adjusts the first tangent plane profile in the first target medical image, the terminal needs to re-execute the above steps 302 to 306 according to the updated profile of the target portion on the cross section.

It should be noted that, the sequence of the steps of the method for obtaining a contour of a medical image provided in the embodiment of the present application may be appropriately adjusted, and the steps may also be increased or decreased according to the circumstances, and any method that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application shall be included in the protection scope of the present application, and therefore, no further description is given.

Referring to fig. 6, fig. 6 is a block diagram of a medical image contour acquiring apparatus according to an embodiment of the present application. The contour acquiring apparatus 400 for medical images may be integrated in the terminal 102 of the medical system shown in fig. 1. The contour acquiring apparatus 400 for medical images may include:

the first obtaining module 401 is configured to obtain a first contour matrix corresponding to a first tangent plane contour of a target portion in Y first medical tangent plane images, where the first contour matrix includes X rows and Z columns of data points, values of data points in the first contour matrix corresponding to the first tangent plane contour are a first preset value, and values of at least some other data points are different from the first preset value.

A second obtaining module 402, configured to obtain Y data points of the target row in the first contour matrix.

The first determining module 403 is configured to determine a second tangent profile of the target portion based on the data point whose median value of the data points in the Y target rows is the first preset value. Wherein X, Y and Z are both integers greater than 1.

In summary, the contour acquiring device for a medical image according to the embodiment of the present application acquires the first contour matrixes corresponding to the first tangent plane contours of the Y target portions on the cross section, and acquires the target row data points from each first contour matrix, so that the second tangent plane contour of the target portion can be determined based on the Y target row pixel points, where the second tangent plane contour is the contour of the target portion on the tangent plane perpendicular to the cross section. Thus, when the section perpendicular to the cross section is a coronal plane, the determined second section contour is the contour of the target part on the coronal plane; when the section perpendicular to the transverse plane is a sagittal plane, the contour of the second section is determined to be the contour of the target part on the sagittal plane. The types of the obtained outlines of the target parts are effectively enriched, and the diagnosis effect of a doctor on a patient is improved.

Optionally, as shown in fig. 7, fig. 7 is a block diagram of a first obtaining module according to an embodiment of the present disclosure. The first obtaining module 401 may include:

the obtaining unit 4011 is configured to obtain respective first contour point coordinates of a first tangent plane contour of the target portion in each first medical tangent plane image.

The constructing unit 4012 is configured to construct a first contour matrix based on the coordinates of the first contour points and the data points in the first medical sectional image.

Optionally, the constructing unit 4012 is configured to construct an initial matrix based on the data points in the first medical sectional image, where the initial matrix includes X rows and Z columns of data points, and values of each data point in the initial matrix are second preset values; and setting the values of the data points corresponding to the coordinates of the first contour points in the initial matrix as first preset values based on the coordinates of the first contour points, and setting the values of the data points in the area surrounded by the first contour points as the first preset values to obtain the first contour matrix, wherein the first preset values are different from the second preset values.

Optionally, the contour acquiring apparatus for medical images further includes: the receiving module is used for receiving indication information which is triggered by a user and used for acquiring a second section outline of the target part on the target section; and the second determining module is used for determining the target row corresponding to the target tangent plane in the first contour matrix based on the indication information.

Optionally, as shown in fig. 8, fig. 8 is a block diagram of a first determining module provided in an embodiment of the present application. The first determining module 403 may include:

the stitching unit 4031 is configured to stitch the data points in the Y target rows to obtain second contour matrices, where the second contours each include Y rows of data points.

A first determining unit 4032, configured to determine, based on the data points whose median values in the second contour matrix are the first preset values, coordinates of the respective second contour points corresponding to the data points whose values are the first preset values.

A second determining unit 4033, configured to determine a second tangent plane contour of the target portion based on the coordinates of the respective second contour points.

Optionally, the splicing unit 4031 is configured to: and splicing the data points of the Y target rows according to a target sequence to obtain a second contour matrix, wherein the target sequence is that the target parts in the Y first medical sectional images are sequentially sequenced according to different sectional positions.

Optionally, the contour acquiring apparatus for medical images may further include:

and the first superposition module is used for superposing the first medical section image and the first section outline to obtain a first target medical image.

And the second superposition module is used for acquiring a second medical sectional image corresponding to the second sectional contour after the second sectional contour of the target part is determined, and superposing the second medical sectional image and the second sectional contour to obtain a second target medical image.

and the first adjusting module is used for adjusting the first tangent plane contour in the first target medical image to obtain an updated first target medical image after receiving the contour modification instruction.

And the second adjusting module is used for adjusting a second tangent plane profile in the second target medical image based on the updated first target medical image.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, modules and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In practical applications, each module and each unit under the module in this embodiment can be implemented by devices such as a Central Processing Unit (CPU), a microprocessor unit (MPU), a Digital Signal Processor (DSP), or a Field Programmable Gate Array (FPGA), a modem, and the like on the medical image contour acquisition device.

The embodiment of the present application also provides a terminal, which may be the terminal 102 in the medical system 000 shown in fig. 1. The contour acquisition device for medical images shown in fig. 6 may be integrated in the terminal 102.

The terminal may include: a processor, and a memory for storing executable instructions for the processor. Wherein the processor is configured to perform the contour acquisition method of medical images shown in fig. 3 or 4.

The embodiment of the application also provides a computer readable storage medium. The computer readable storage medium has stored therein instructions which, when run on the processing assembly, cause the processing assembly to perform the contour acquisition method of medical images shown in fig. 3 or fig. 4.

In this application, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The term "plurality" means two or more unless expressly limited otherwise.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is intended only to illustrate the alternative embodiments of the present application, and should not be construed as limiting the present application, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for contour acquisition of medical images, the method comprising:

acquiring Y data points of a target row in the first contour matrix;

determining a second tangent profile of the target part based on the data point with the median of the data points of the Y target rows as the first preset value;

wherein X, Y and Z are both integers greater than 1.

2. The method of claim 1, wherein obtaining each of the Y first contour matrices comprises:

3. The method of claim 2, wherein constructing the first contour matrix based on the respective first contour point coordinates and data points in the first medical sectional image comprises:

4. The method of claim 1, wherein prior to said acquiring Y data points of a target row in said first contour matrix, said method further comprises:

5. The method of claim 1, wherein determining a second tangent profile of the target site based on the data point having the first preset value as the median of the data points of the Y target rows comprises:

splicing the data points of the Y target rows to obtain a second contour matrix, wherein the second contours comprise Y rows of data points;

6. The method of claim 5, wherein stitching the data points of the Y target rows to obtain a second contour matrix comprises:

7. The method of claim 1, further comprising:

8. The method of claim 7, further comprising:

after receiving a contour modification instruction, adjusting a first tangent plane contour in the first target medical image to obtain an updated first target medical image;

9. A terminal, comprising: a processor and a memory for storing executable instructions of the processor, wherein the processor is configured to execute the contour acquisition method of medical images according to any one of claims 1 to 8.

10. A computer-readable storage medium, having stored therein instructions, which, when run on a processing component, cause the processing component to execute a method of contour acquisition of medical images as claimed in any one of claims 1 to 8.