Puncture method based on image registration and related product

Abstract

The invention discloses a puncture method based on image registration and a related product. The method comprises the following steps: acquiring a CT image and an ultrasonic image; the CT image is an image obtained by performing CT scanning on a target object; the ultrasonic image is an image obtained by performing ultrasonic scanning on a target object, and the image size of the ultrasonic image is smaller than that of the CT image; determining an image of a target area with the same image size as the ultrasonic image in the CT image as a target area image; under the condition that the correlation between the target area image and the ultrasonic image is greater than a correlation threshold value, obtaining a first registration matrix according to the coordinate difference of the target area image and the ultrasonic image on the ultrasonic coordinate system; the first registration matrix is used for aligning the target area image and the ultrasonic image; and adjusting the CT image by using the first registration matrix to obtain a target image.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a puncture method based on image registration and related products. Background Art

[0002] With the advancement of computer technology, medicine has also ushered in a huge breakthrough. At present, before the puncture operation, it is necessary to align the computed tomography (CT) image and the ultrasound image so that the puncture path planned in the CT image can be aligned with the ultrasound image. However, in the current technology, the registration speed of CT images and ultrasound images is slow, and there is a risk of affecting the puncture time of the puncture operation. Therefore, how to quickly align CT images and ultrasound images is a very important issue. Summary of the invention

[0003] The present application provides a puncture method based on image registration and related products, wherein the related products include a puncture device based on image registration, an electronic device, a computer-readable storage medium and a computer program product.

[0004] In a first aspect, a puncture method based on image registration is provided, wherein before performing a puncture operation on a target object, the method is used to register a CT image of the target object with an ultrasound image to obtain a target image aligned with the ultrasound image, and the method comprises:

[0005] Acquire the CT image and the ultrasound image; the CT image is an image obtained by performing a CT scan on the target object; the ultrasound image is an image obtained by performing an ultrasound scan on the target object, and the image size of the ultrasound image is smaller than the image size of the CT image;

[0006] Determine, in the CT image, an image of a target area having the same image size as that of the ultrasound image as the target area image;

[0007] When the correlation between the target area image and the ultrasound image is greater than a correlation threshold, a first registration matrix is ​​obtained according to a coordinate difference between the target area image and the ultrasound image in an ultrasound coordinate system; the first registration matrix is ​​used to align the target area image with the ultrasound image;

[0008] The CT image is adjusted using the first registration matrix to obtain the target image.

[0009] In combination with any embodiment of the present application, when the correlation between the target area image and the ultrasound image is greater than a correlation threshold, before obtaining the first registration matrix according to the coordinate difference between the target area image and the ultrasound image in the ultrasound coordinate system, the method further includes:

[0010] Determine the correlation between pixels at the same position in the target area image and the ultrasound image to obtain a correlation matrix, wherein the number of parameters in the correlation matrix is ​​the same as the number of pixels in the target area image;

[0011] In a case where the modulus of the correlation matrix is ​​greater than a first threshold, the correlation between the target region image and the ultrasound image is determined to be greater than the correlation threshold.

[0012] In combination with any embodiment of the present application, the pixel at the first position in the target area image is the first pixel, and the pixel at the first position in the ultrasound image is the second pixel;

[0013] Determining the correlation between pixels at the same position in the target area image and the ultrasound image to obtain a correlation matrix includes:

[0014] Determine an average value of pixel information of pixels in the target area image to obtain a first average value;

[0015] Determine an average value of pixel information of pixels in the ultrasound image to obtain a second average value;

[0016] Determine pixel information of the first pixel to obtain a first pixel value;

[0017] Determine pixel information of the second pixel to obtain a second pixel value;

[0018] Determine a difference between the first pixel value and the first mean value to obtain a first difference value;

[0019] Determine a difference between the second pixel value and the second mean value to obtain a second difference value;

[0020] Determine, according to the product of the first difference and the second difference, a correlation between pixels at the first position in the target area image and the ultrasound image to obtain a first correlation;

[0021] The correlation matrix is ​​obtained according to the first correlation and the second correlation, wherein the second correlation is the correlation between pixels at the same position in the target area image and the ultrasound image except for the first position.

[0022] In combination with any embodiment of the present application, the acquiring of the CT image and the ultrasound image includes:

[0023] Acquire CT three-dimensional images and ultrasound three-dimensional images;

[0024] According to the target section, the CT image of the CT three-dimensional image on the target section is obtained, and the target section is a section from head to toe;

[0025] According to the target section, the ultrasonic image of the ultrasonic three-dimensional image on the target section is obtained.

[0026] In combination with any embodiment of the present application, the CT image includes a CT feature point, the ultrasound image includes an ultrasound feature point, the CT feature point is a pixel point in the CT image representing a second position of the target object, the ultrasound feature point is a pixel point in the ultrasound image representing the second position of the target object, the distance between the CT feature point and the ultrasound feature point is greater than a second threshold and less than a third threshold, and the second threshold is used to determine image registration;

[0027] Before determining in the CT image an image of the target area having the same image size as that of the ultrasound image as the target area image, the method further includes:

[0028] Acquire a first image, where the first image is an original image obtained by performing a CT scan on the target object, and the first image includes a first feature point, where the first feature point is a pixel point in the first image that represents the second position of the target object;

[0029] Obtaining a second registration matrix according to a positional relationship between the first feature point and the ultrasound feature point, wherein the second registration matrix is ​​used to adjust the first image to the CT image;

[0030] The first image is adjusted using the second registration matrix to obtain the CT image.

[0031] In combination with any embodiment of the present application, after adjusting the CT image using the first registration matrix to obtain a target image, the method further includes:

[0032] Determining a reference puncture path in the CT image, wherein the reference puncture path is a path used to guide puncture of a target object; the path in the target image used to guide puncture of a target object is a target puncture path;

[0033] When the target image is registered with the ultrasound image, the target object is punctured according to the target puncture path.

[0034] In a second aspect, a puncture device based on image registration is provided, and the puncture device based on image registration comprises:

[0035] An acquisition unit is used to acquire the CT image and the ultrasound image; the CT image is an image obtained by performing a CT scan on the target object; the ultrasound image is an image obtained by performing an ultrasound scan on the target object, and the image size of the ultrasound image is smaller than the image size of the CT image;

[0036] a determining unit, configured to determine, in the CT image, an image of a target area having the same image size as that of the ultrasound image, as the target area image;

[0037] a matrix calculation unit, configured to obtain a first registration matrix according to a coordinate difference between the target area image and the ultrasound image in an ultrasound coordinate system when the correlation between the target area image and the ultrasound image is greater than a correlation threshold; the first registration matrix is ​​used to align the target area image with the ultrasound image;

[0038] The first adjustment unit is used to adjust the CT image using the first registration matrix to obtain the target image.

[0039] In combination with any embodiment of the present application, the puncture device based on image registration further includes a correlation calculation unit, which is used to:

[0040] Determine the correlation between pixels at the same position in the target area image and the ultrasound image to obtain a correlation matrix, wherein the number of parameters in the correlation matrix is ​​the same as the number of pixels in the target area image;

[0041] In a case where the modulus of the correlation matrix is ​​greater than a first threshold, the correlation between the target region image and the ultrasound image is determined to be greater than the correlation threshold.

[0042] In combination with any embodiment of the present application, the pixel at the first position in the target area image is a first pixel, and the pixel at the first position in the ultrasound image is a second pixel;

[0043] The above correlation calculation unit is specifically used for:

[0044] Determine the average value of pixel information of pixels in the target area image to obtain a first average value;

[0045] Determine an average value of pixel information of pixels in the ultrasound image to obtain a second average value;

[0046] Determine pixel information of the first pixel to obtain a first pixel value;

[0047] Determine pixel information of the second pixel to obtain a second pixel value;

[0048] Determine a difference between the first pixel value and the first mean value to obtain a first difference value;

[0049] Determine a difference between the second pixel value and the second mean value to obtain a second difference value;

[0050] Determine, according to the product of the first difference and the second difference, the correlation between the pixel at the first position in the target area image and the ultrasonic image to obtain a first correlation;

[0051] The correlation matrix is ​​obtained according to the first correlation and the second correlation, wherein the second correlation is the correlation between pixels at the same position in the target area image and the ultrasound image except for the first position.

[0052] In conjunction with any embodiment of the present application, the acquisition unit is specifically used to:

[0053] Acquire CT three-dimensional images and ultrasound three-dimensional images;

[0054] According to the target section, the CT image of the CT three-dimensional image on the target section is obtained, and the target section is a section from head to toe;

[0055] According to the target section, the ultrasonic image of the ultrasonic three-dimensional image on the target section is obtained.

[0056] In combination with any embodiment of the present application, the CT image includes CT feature points, the ultrasound image includes ultrasound feature points, the CT feature points are pixel points in the CT image representing the second position of the target object, the ultrasound feature points are pixel points in the ultrasound image representing the second position of the target object, the distance between the CT feature points and the ultrasound feature points is greater than a second threshold and less than a third threshold, and the second threshold is used to determine image registration;

[0057] The puncture device based on image registration further includes a second adjustment unit, which is used to:

[0058] Acquire a first image, where the first image is an original image obtained by performing a CT scan on the target object, and the first image includes a first feature point, where the first feature point is a pixel point in the first image that represents the second position of the target object;

[0059] According to the positional relationship between the first feature point and the ultrasonic feature point, a second registration matrix is ​​obtained, wherein the second registration matrix is ​​used to adjust the first image to the CT image;

[0060] The first image is adjusted using the second registration matrix to obtain the CT image.

[0061] In conjunction with any embodiment of the present application, the puncture device based on image registration further includes a puncture unit, which is used to:

[0062] Determining a reference puncture path in the CT image, the reference puncture path being a path used to guide puncture of the target object; the path in the target image used to guide puncture of the target object is a target puncture path;

[0063] When the target image is registered with the ultrasound image, the target object is punctured according to the target puncture path.

[0064] According to a third aspect, an electronic device is provided, comprising: a processor and a memory, wherein the memory is used to store computer program code, wherein the computer program code comprises computer instructions, and when the processor executes the computer instructions, the electronic device executes the first aspect and any one of its embodiments described above.

[0065] In a fourth aspect, another electronic device is provided, comprising: a processor, a sending device, an input device, an output device and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes the first aspect and any one of its embodiments.

[0066] In a fifth aspect, a computer-readable storage medium is provided, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor, the processor is caused to execute the first aspect and any one of its embodiments.

[0067] In a sixth aspect, a computer program product is provided, wherein the computer program product comprises a computer program or instructions, and when the computer program or instructions are run on a computer, the computer is enabled to execute the above-mentioned first aspect and any embodiment thereof.

[0068] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application.

[0069] In an embodiment of the present application, after acquiring a CT image and an ultrasound image, the puncture device based on image registration determines a target area image having the same image size as the ultrasound image from the CT image. And when the correlation between the target area image and the ultrasound image is greater than the correlation threshold, a first registration matrix is ​​obtained according to the coordinate difference between the target area image and the ultrasound image in the ultrasound coordinate system. By determining the target area image having the same image size as the ultrasound image from the CT image and calculating the correlation with the ultrasound image, the number of times the puncture device based on image registration calculates the correlation can be reduced compared to calculating the correlation between any pixel in the CT image and all pixels in the ultrasound image, thereby improving the speed at which the puncture device based on image registration performs image registration. After determining the first registration matrix, the puncture device based on image registration adjusts the CT image using the first registration matrix to obtain a target image. Since the CT image includes the target area image, the target area image will also be transformed while the CT image is being transformed. The target image includes an image after the target area image is transformed using the first registration matrix. The image after the target area image is transformed using the first registration matrix is ​​aligned with the ultrasound image. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0071] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0072] Figure 1 A schematic diagram of a process flow of a puncture method based on image registration provided in an embodiment of the present application;

[0073] Figure 2 A schematic diagram of a precision inspection tool provided in an embodiment of the present application;

[0074] Figure 3 A physical picture of a precision inspection tool provided in an embodiment of the present application;

[0075] Figure 4 A schematic diagram of another precision inspection tool provided in an embodiment of the present application;

[0076] Figure 5 A schematic diagram of a calibrated finger provided in an embodiment of the present application;

[0077] Figure 6 A schematic diagram of the structure of a puncture device based on image registration provided in an embodiment of the present application;

[0078] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0079] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0080] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0081] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0082] The executor of the embodiment of the present application is a puncture device based on image registration, wherein the puncture device based on image registration can be any electronic device that can execute the technical solution disclosed in the method embodiment of the present application. Optionally, the puncture device based on image registration can be one of the following: a computer, a server.

[0083] It should be understood that the method embodiment of the present application can also be implemented by a processor executing a computer program code. The following describes the embodiment of the present application in conjunction with the drawings in the embodiment of the present application. Figure 1 , Figure 1 A flow chart of a puncture method based on image registration is provided in an embodiment of the present application. The puncture method based on image registration is applied to a puncture device based on image registration, hereinafter referred to as the puncture device. Before performing a puncture operation on a target object, the puncture device aligns a CT image of the target object with an ultrasound image to obtain a target image aligned with the ultrasound image.

[0084] In the embodiment of the present application, the CT image contains features of the target object in the ultrasound image, and the image registration represents an image transformation of the CT image so that the features of the target object in the ultrasound image contained in the CT image are aligned with the features of the target object in the ultrasound image.

[0085] 101. Obtain CT images and ultrasound images.

[0086] In the embodiment of the present application, the CT image is an image obtained by performing a CT scan on the target object, and the ultrasound image is an image obtained by performing an ultrasound scan on the target object.

[0087] In the process of performing CT scanning on the target object, the body parts of the target object are usually scanned to generate a CT image, which contains multiple organs of the above-mentioned body parts. For example, a CT scan is performed on the abdomen of the target object to obtain a CT image of the abdomen of the target object, and the CT image contains organs such as kidneys and liver in the abdomen of the target object. In the process of performing ultrasound scanning on the target object, the organs of the target object are usually scanned. For example, an ultrasound scan is performed on the kidneys of the target object to obtain an ultrasound image of the kidneys of the target object. Because the features of the target object contained in the CT image are more than the features of the target object contained in the ultrasound image, the image size of the ultrasound image is smaller than the image size of the CT image.

[0088] In an implementation of acquiring CT images and ultrasound images, the puncture device receives the CT images and ultrasound images input by an input component. The input component includes at least one of the following: a keyboard, a mouse, a touch screen, a touch pad, and an audio input device.

[0089] In another implementation of acquiring CT images and ultrasound images, the puncture device receives the CT images and ultrasound images sent by a terminal. The terminal includes at least one of the following: a mobile phone, a computer, a tablet computer, and a server.

[0090] It should be understood that in the embodiments of the present application, the steps of the puncture device acquiring the CT image and the ultrasound image can be performed separately or simultaneously, and the present application does not limit this.

[0091] 102. Determine, in the CT image, an image of a target region having the same image size as that of the ultrasound image as the target region image.

[0092] In the embodiment of the present application, the target area image is an image with the same image size as the ultrasound image. For example, the image size of the CT image is M×N, and the image size of the ultrasound image is m×n, where M is greater than m and N is greater than n. The m×n target area is determined from the CT image, and the image enclosed by the target area in the CT image is used as the target area image, and the image size of the target area image is m×n.

[0093] 103. When the correlation between the target region image and the ultrasound image is greater than a correlation threshold, a first registration matrix is ​​obtained according to a coordinate difference between the target region image and the ultrasound in an ultrasound coordinate system.

[0094] In the embodiment of the present application, the correlation threshold is a threshold used to determine whether the target area image and the ultrasound image represent the same part of the target object. When the correlation between the target area image and the ultrasound image is higher than the correlation threshold, it is determined that the target area image and the ultrasound image represent the same part of the target object. When the correlation between the target area image and the ultrasound image is lower than or equal to the correlation threshold, it is determined that the target area image and the ultrasound image represent different parts of the target object.

[0095] In a possible implementation, features in the target region image are extracted to obtain region features. Features of the ultrasound image are extracted to obtain ultrasound features, and the correlation between the target region image and the ultrasound image is determined by calculating the correlation between the vector of the region feature and the vector of the ultrasound feature.

[0096] In another possible implementation, the correlation matrix is ​​obtained by calculating the correlation of pixels at the same position in the target area image and the ultrasonic image, and then the correlation of the target area image and the ultrasonic image is obtained according to the modulus of the correlation matrix. For example, the target area image is [x1, x2], and the ultrasonic image is [x3, x4], where x1 and x2 are pixels in the target area image, and x3 and x4 are pixels in the ultrasonic image. The correlation of pixels at the same position in the target area image and the ultrasonic image is calculated, that is, the correlation of x1 and x3 is calculated to obtain the correlation y1, and the correlation of x2 and x4 is calculated to obtain the correlation y2. The correlation matrix [y1, y2] is obtained according to the correlation y1 and the correlation y2. The correlation between the target area image and the ultrasonic image is determined according to the modulus of the correlation matrix [y1, y2].

[0097] Generally speaking, the main method for image registration is to calculate the correlation between any pixel in the CT image and all pixels in the ultrasound image, and determine the two pixels with the maximum correlation as a data pair, and determine the matrix used to align the CT image and the ultrasound image based on the coordinate difference between the two pixels in the data pair. For example, the CT image is [x1, x2], the ultrasound image is [x3, x4], and the target area image with the same image size as the ultrasound image is determined from the CT image as [x1, x2]. Calculate the correlation between x1 and x3 to obtain correlation y1, and calculate the correlation between x1 and x4 to obtain correlation y3. When the correlation y1 is greater than the correlation y3, x1 and x3 are used as data pair z1. Calculate the correlation between x2 and x4 to obtain correlation y2, and calculate the correlation between x2 and x3 to obtain correlation y4. When the correlation y2 is greater than the correlation y4, x2 and x4 are used as data pair z2. In the case of determining the data pair z1 and the data pair z2, according to the coordinate difference between x1 and x3 in the data pair z1, and the coordinate difference between x2 and x4 in the data pair z2. Since the above main method needs to calculate the correlation between any pixel in the target area image and all pixels in the ultrasound image, when the number of pixels in the target area image and the ultrasound image is 2, the number of correlation calculations is 4, which is relatively high. In the puncture method based on image registration proposed in the embodiment of the present application, it is not necessary to calculate the correlation between any pixel in the target area image and all pixels in the ultrasound image, so the number of calculations of the puncture device can be reduced, thereby improving the speed of the puncture device in performing image registration.

[0098] In the embodiment of the present application, the first registration matrix is ​​a matrix used to align the target area image with the ultrasound image. The target area image is transformed using the first registration matrix to obtain an image aligned with the ultrasound image, wherein the image transformation includes one or more of translation, rotation, and scaling.

[0099] In the embodiment of the present application, when the correlation between the target area image and the ultrasound image is greater than the correlation threshold, the target area image and the ultrasound image are determined to represent information of the same part of the target object. In order to align the target area image and the ultrasound image, a first registration matrix is ​​determined based on the coordinate difference between the target area image and the ultrasound image in the ultrasound coordinate system. Using the first registration matrix, the image obtained by performing image transformation on the target area image is aligned with the ultrasound image.

[0100] In a possible implementation, the puncture device determines an image of a reference region in the CT image that has the same image size as the ultrasound image as the reference region image. When the correlation between the reference region image and the ultrasound image is less than or equal to the correlation threshold, the puncture device repeatedly performs steps 102 and 103 until a target region image is found that has a correlation with the ultrasound image that is greater than the correlation threshold.

[0101] 104. Use the first registration matrix to adjust the CT image to obtain the target image.

[0102] In the embodiment of the present application, the puncture device uses the first registration matrix to perform image transformation on the CT image to obtain a target image. Since the CT image includes the target area image, the target area image is also transformed while the CT image is being transformed. The target image includes an image after the image transformation of the target area image using the first registration matrix. The image after the image transformation of the target area image using the first registration matrix is ​​aligned with the ultrasound image.

[0103] In an embodiment of the present application, after acquiring a CT image and an ultrasound image, the puncture device determines a target area image having the same image size as the ultrasound image from the CT image. And when the correlation between the target area image and the ultrasound image is greater than a correlation threshold, a first registration matrix is ​​obtained according to the coordinate difference between the target area image and the ultrasound image in the ultrasound coordinate system. By determining a target area image having the same image size as the ultrasound image from the CT image and calculating the correlation with the ultrasound image, the number of times the puncture device calculates the correlation can be reduced compared to calculating the correlation between any pixel in the CT image and all pixels in the ultrasound image, thereby increasing the speed at which the puncture device performs image registration. After determining the first registration matrix, the puncture device adjusts the CT image using the first registration matrix to obtain a target image. Since the CT image includes the target area image, the target area image will also be transformed while the CT image is being transformed. The target image includes an image after the target area image is transformed using the first registration matrix. The image after the target area image is transformed using the first registration matrix is ​​aligned with the ultrasound image.

[0104] As an optional implementation, the puncture device performs the following steps before performing step 103:

[0105] 201. Determine the correlation between pixels at the same position in the target area image and the ultrasound image to obtain a correlation matrix.

[0106] In an embodiment of the present application, the target area image and the ultrasound image have the same number of pixels, and the number of data in the correlation matrix is ​​the same as the number of pixels in the target area image. The data at any position in the correlation matrix represents the correlation between the pixels at the same position in the target area image and the ultrasound image. The data at different positions in the correlation matrix correspond to different pixels in the target area image and the ultrasound image. For example. The correlation matrix is ​​[y1, y2], the target area image is [x1, x2], and the ultrasound image is [x3, x4]. The y1 in the correlation matrix represents the correlation between the pixel x1 in the target area image and the pixel x3 in the ultrasound image. The y2 in the correlation matrix represents the correlation between the pixel x2 in the target area image and the pixel x4 in the ultrasound image.

[0107] In a possible implementation, the Pearson correlation coefficient of pixels at any same position in the target area image and the ultrasound image is determined to determine the correlation between any two pixels at the same position, and the correlation between any two pixels at the same position is combined to obtain a correlation matrix.

[0108] In another possible implementation, the covariance between the target region image and the ultrasound image is calculated, and the covariance between the target region image and the ultrasound image is used as the correlation matrix between the target region image and the ultrasound image. The formula for determining the correlation matrix is ​​shown in formula (1):

[0109]

[0110] Among them, ρ(x,y) represents the correlation matrix between the target area image and the ultrasound image. x,y represents the target area image, and Us represents the ultrasound image. x,y ,Us) represents the covariance between the target area image and the ultrasound image. x,y represents the variance of the target area image, and D represents the variance of the ultrasound image.

[0111] 202. When the modulus of the correlation matrix is ​​greater than a first threshold, determine the correlation between the target area image and the ultrasound image to be greater than the correlation threshold.

[0112] In the embodiment of the present application, the larger the modulus of the correlation matrix, the greater the correlation between the target area image and the ultrasound image, and the smaller the modulus of the correlation matrix, the smaller the correlation between the target area image and the ultrasound image. Therefore, the modulus of the correlation matrix can be used as a basis for judging the correlation between the target area image and the ultrasound image.

[0113] In this embodiment, the puncture device calculates the correlation between the pixels at the same position in the target area image and the ultrasound image to obtain a correlation matrix. Since only the correlation between the pixels at the same position needs to be calculated, and the correlation between the pixels at different positions does not need to be calculated, compared with calculating the correlation between any pixel in the CT image and all pixels in the ultrasound image, the number of times the puncture device calculates the correlation can be reduced, thereby improving the speed at which the puncture device performs image registration. After determining the correlation matrix monkey, the puncture device determines the correlation between the target area image and the ultrasound image according to the modulus of the correlation matrix.

[0114] As an optional implementation, the pixel at the first position in the target area image is the first pixel, and the pixel at the first position in the ultrasound image is the second pixel. Optionally, the image sizes of the target area image and the ultrasound image are both m×n, and the first position represents the i-th row and j-th column, where i is a positive integer less than or equal to m, and j is a positive integer less than or equal to n. The first pixel represents the pixel at the i-th row and j-th column in the target area image, and the second pixel represents the pixel at the i-th row and j-th column in the ultrasound image.

[0115] The puncture device performs the following steps during the execution of step 201:

[0116] 301. Determine an average value of pixel information of pixels in the target area image to obtain a first average value.

[0117] In the embodiment of the present application, the pixel information is information used to characterize the pixel, and optionally, the pixel information includes one or more of a grayscale value, a brightness value, and a bit depth. The first mean is the average value of the pixel information used to characterize the pixels in the target area image. For example, the target area image includes a pixel x1 and a pixel x2, the pixel information of the pixel x1 is x11, and the pixel information of the pixel x2 is x21, and the average value of x11 and x21 is taken as the first mean value.

[0118] 302. Determine an average value of pixel information of pixels in the ultrasound image to obtain a second average value.

[0119] In the embodiment of the present application, the second mean is an average value of pixel information used to characterize pixels in the ultrasound image. For example, the ultrasound image includes pixel x3 and pixel x4, the pixel information of pixel x3 is x31, and the pixel information of pixel x4 is x41, and the average value of x31 and x41 is taken as the second mean value.

[0120] 303. Determine pixel information of the first pixel to obtain a first pixel value.

[0121] In the embodiment of the present application, the first pixel value represents the pixel information of the first pixel. When the pixel information includes a grayscale value, the first pixel value represents the grayscale value of the first pixel. When the pixel information includes a brightness value, the first pixel value represents the brightness value of the first pixel.

[0122] 304. Determine pixel information of the second pixel to obtain a second pixel value.

[0123] In the embodiment of the present application, the second pixel value represents the pixel information of the second pixel. When the pixel information includes a grayscale value, the second pixel value represents the grayscale value of the second pixel. When the pixel information includes a brightness value, the second pixel value represents the brightness value of the second pixel.

[0124] 305. Determine a difference between the first pixel value and the first mean value to obtain a first difference.

[0125] In the embodiment of the present application, the first difference is the difference between the first pixel value and the first mean value, and the first difference represents the difference between the pixel information of the first pixel and the first mean value.

[0126] 306. Determine a difference between the second pixel value and the second mean value to obtain a second difference.

[0127] In the embodiment of the present application, the second difference is the difference between the second pixel value and the second mean value, and the second difference represents the difference between the pixel information of the second pixel and the second mean value.

[0128] 307. Determine the correlation between the pixels at the first position in the target area image and the ultrasound image according to the product of the first difference and the second difference to obtain a first correlation.

[0129] In the embodiment of the present application, the first correlation is used to characterize the correlation between the first pixel and the second pixel, the first pixel is the pixel at the first position in the target area image, and the second pixel is the pixel at the first position in the ultrasound image. The first correlation is used to characterize the change trend of the pixel information of the first pixel compared to the first mean and the pixel information of the second pixel compared to the second mean. When the change trend of the pixel information of the first pixel compared to the first mean and the pixel information of the second pixel compared to the second mean is the same, the first correlation is greater than 0. When the change trend of the pixel information of the first pixel compared to the first mean and the pixel information of the second pixel compared to the second mean is different, the first correlation is less than 0. Specifically, when the first correlation is greater than 0, the first pixel value is greater than the first mean and the second pixel value is greater than the second mean, or the first pixel value is less than the first mean and the second pixel value is less than the second mean. When the first correlation is less than 0, the first pixel value is greater than the first mean and the second pixel value is less than the second mean, or the first pixel value is less than the first mean and the second pixel value is greater than the second mean.

[0130] 308. Obtain the above correlation matrix based on the above first correlation and the second correlation.

[0131] In the embodiment of the present application, the second correlation characterizes the correlation of pixels at the same position in the target area image and the ultrasound image except the first position. By combining the first correlation and the second correlation, a correlation matrix is ​​obtained, which includes the first correlation and the second correlation.

[0132] In a possible implementation, the first correlation is Y1, the second correlation is Y2, and a matrix [Y1, Y2] formed by combining the first correlation Y1 and the second correlation Y2 is used as a correlation matrix.

[0133] In another possible implementation, the formula for determining the correlation matrix is ​​shown in formula (2):

[0134]

[0135] Among them, ρ(x, y) represents the correlation matrix between the target area image with (x, y) as the upper left corner point and the same image size as the ultrasound image and the ultrasound image. x,y Represents the target area image with (x, y) as the upper left corner and the same image size as the ultrasound image, CT x,y (i,j) represents the data of the i-th row and j-th column in the target area image. The average value of the pixel information of the pixels in the target area image is represented, that is, the first mean value. Us represents the ultrasound image, and Us(i,j) represents the data of the i-th row and j-th column in the ultrasound image. The second mean value represents the average value of the pixel information of the pixels in the ultrasound image. The ultrasound image and the target area image are both m×n images, so the maximum value of i is m, and the maximum value of j is n.

[0136] In this embodiment, the puncture device obtains a first mean value according to the average value of the pixel information of the pixels in the target area image, and obtains a second mean value according to the average value of the pixel information of the pixels in the ultrasound image. When the first mean value and the second mean value are determined, the pixel information of the first pixel, that is, the difference between the first pixel value and the first mean value, is determined to obtain a first difference value, and the pixel information of the second pixel, that is, the difference between the second pixel value and the second mean value, is determined to obtain a second difference value, wherein the first pixel is an image of the first position in the target area image, and the second pixel is an image of the first position in the ultrasound image. The correlation between the first pixel and the second pixel is determined by the product of the first difference and the second difference to obtain a first correlation. When the first correlation is greater than 0, the first pixel value is greater than the first mean value and the second pixel value is greater than the second mean value, or the first pixel value is less than the first mean value and the second pixel value is less than the second mean value, indicating that the first pixel value has the same change trend compared to the first mean value and the second pixel value has the same change trend compared to the second mean value, thereby indicating that the correlation between the first pixel and the second pixel is high. In case of determining the first correlation, a correlation matrix is ​​determined according to the first correlation and a second correlation, wherein the second correlation characterizes the correlation of pixels at the same position in the target area image and the ultrasound image except for the first position.

[0137] As an optional implementation, the puncture device performs the following steps during the execution of step 101:

[0138] 401. Acquire a CT three-dimensional image and an ultrasound three-dimensional image.

[0139] In the embodiment of the present application, the CT three-dimensional image is a three-dimensional image obtained by CT scanning, and the ultrasonic three-dimensional image is a three-dimensional image obtained by ultrasonic scanning.

[0140] 402. According to the target section, obtain the CT image of the CT three-dimensional image on the target section.

[0141] In the embodiment of the present application, the target section is a section from head to toe. The CT three-dimensional image is sliced ​​from head to toe according to the target section to obtain a CT image containing multiple organs of the human body. For example, the CT image contains multiple human organs such as the brain, spine, heart, and kidneys.

[0142] 403. According to the target section, obtain the ultrasonic image of the ultrasonic three-dimensional image on the target section.

[0143] In the embodiment of the present application, the ultrasound three-dimensional image is cut from head to toe according to the target section. Since the ultrasound device usually performs a directional scan on the organ to be punctured when performing ultrasound scanning on the target object, the ultrasound three-dimensional image usually includes the organ to be punctured, and the ultrasound image obtained by slicing the ultrasound three-dimensional image includes the section of the organ to be punctured.

[0144] In a possible implementation, the puncture device slices the ultrasound 3D image and the CT 3D image every 5 mm after determining the target section, and obtains k CT images and k ultrasound images, and the CT images and the ultrasound images correspond to each other. Image registration is performed on any corresponding CT image and ultrasound image to obtain k target images. After merging the k target images in the order of slicing, a target 3D image aligned with the ultrasound 3D image can be obtained. The target 3D image represents the image obtained by CT scanning of the target object.

[0145] CT three-dimensional images are usually obtained by continuing to scan the target object over a large area. Therefore, the CT three-dimensional image is sliced ​​from head to toe, so that the CT image contains multiple organs of the human body. Ultrasound three-dimensional images are usually images obtained by scanning organs to be punctured. Therefore, the ultrasound three-dimensional image is sliced ​​from head to toe, and the ultrasound image obtained contains slices of the organs to be punctured. Through the above method, the puncture device can find the target area image with a high correlation with the image of the slice of the organ to be punctured in the CT image during the execution of step 103, avoiding the situation where the CT image does not contain the image of the slice of the organ to be punctured due to the wrong selection of the slice, which makes it impossible to perform image registration.

[0146] As an optional implementation, the CT image includes CT feature points, and the ultrasound image includes ultrasound feature points, the CT feature points are pixel points representing the second position of the target object in the CT image, and the ultrasound feature points are pixel points representing the second position of the target object in the ultrasound image, and the distance between the CT feature points and the ultrasound feature points is greater than a second threshold and less than a third threshold, and the second threshold is used to determine the image registration. In a possible implementation, when the distance between the feature points of the two images is greater than the second threshold, the two images are determined to be unregistered. When the distance between the feature points of the two images is less than the second threshold, the two images are determined to be registered.

[0147] The puncture device performs the following steps before performing step 101:

[0148] 501. Acquire a first image.

[0149] In the embodiment of the present application, the first image is an original image of a CT scan of a target object, wherein the original image is an image obtained from a CT scanning device without image transformation. The first image includes a first feature point, and the first feature point is a pixel point of a second position of the target object in the first image.

[0150] 502. Obtain a second registration matrix according to the positional relationship between the first feature point and the ultrasonic feature point.

[0151] In the embodiment of the present application, the second registration matrix is ​​a matrix used to perform image transformation on the first image to obtain a CT image.

[0152] 503. Use the second registration matrix to adjust the first image to obtain the CT image.

[0153] In an embodiment of the present application, the puncture device uses a second registration matrix to perform image transformation on the first image to obtain a CT image, wherein the distance between the CT feature point for characterizing the second position of the target object in the CT image and the ultrasonic feature point is greater than the second threshold and less than the third threshold.

[0154] In this embodiment, when the puncture device acquires the first image, the first image is the original image obtained by performing CT scanning on the target object. The feature points representing the second position of the target object are determined in the first image and the ultrasound image to obtain the first feature points and the ultrasound feature points, and the second registration matrix is ​​determined according to the positional relationship between the first feature points and the ultrasound feature points, wherein the second registration matrix is ​​used to perform a graphic transformation on the first image so that the distance between the first feature points and the ultrasound feature points after the graphic transformation is greater than the second threshold and less than the third threshold. After determining the second registration matrix, the first image is adjusted using the second registration matrix to obtain a CT image, and the distance between the feature points representing the second position of the target object in the CT image, that is, the CT feature points and the ultrasound feature points is greater than the second threshold and less than the third threshold. Since the distance between the CT feature points and the ultrasound feature points is greater than the second threshold and less than the third threshold, the puncture device can determine a target area image with a higher correlation within a smaller range near the ultrasound image during the execution of step 102, thereby reducing the probability of indiscriminately determining a target area image with a higher correlation with the ultrasound image in the CT image, reducing the amount of calculation of the puncture device, and thus speeding up the image registration.

[0155] As an optional implementation, after acquiring a CT image, a reference target point and a reference needle entry point are determined in the CT image, and the path formed by the reference target point and the reference needle entry point is the reference puncture path. After image registration, the target image includes a target target point and a target needle entry point, and the target target point and the reference target point represent the same position of the target object, and the reference needle entry point and the target needle entry point represent the same position of the target object. The path formed by the target eight points and the target needle entry point is the target puncture path. Since the target image and the ultrasound image are aligned images, the target puncture path can be determined in the ultrasound image, and the target object can be punctured according to the target puncture path.

[0156] As an optional implementation, the precision inspection tool is used as the target object, the reference target point and the reference needle point belong to the precision inspection tool, and the path passing through the reference target point and the reference needle point is the reference puncture path, which is the true value during the puncture operation. Figure 2 It is a schematic diagram of a precision inspection tool. Specifically, the centers of the cylinders a, b, and c can all be used as reference targets, and the centers of the cuboids d, e, and f can all be used as reference needle insertion points. When the precision inspection tool is subjected to CT scanning to obtain a CT image, the center of any cylinder among a, b, and c is determined as a reference target in the CT image, and the center of any cuboid among d, e, and f is determined as a reference needle insertion point. The reference target and the reference needle insertion point should be points in the target area image. After the puncture device is used for image registration, the CT image is adjusted to obtain a target image. While the CT image is registered, the target area image is registered to obtain a registered area image. The target image includes a registered area image. The target image includes a target target and a target needle insertion point for the puncture operation, wherein the target target and the target needle insertion point should be points in the registered area image. The puncture path passing through the target target and the target needle insertion point in the registered area image is determined to obtain a CT puncture path. According to the target difference between the CT puncture path and the reference puncture path, the registration accuracy of the puncture device can be determined. Optionally, the puncture guide is used to guide the puncture needle to coincide with the target puncture path, thereby achieving puncture.

[0157] As an optional implementation, Figure 3 for Figure 2 A physical picture of a precision inspection tool in FIG. Specifically, the precision inspection tool includes three cylinders and three rectangular protrusions, and the reference needle entry point of the precision inspection tool is the center of the upper surface of the three rectangular protrusions. The reference target point of the precision inspection tool is the center of the upper surface of the three cylinders. The puncture guide guides the puncture needle to pierce the reference needle entry point in the rectangular protrusion and finally reaches the reference target point on the cylinder.

[0158] As an optional implementation, Figure 4Schematic diagram of another precision inspection tool. Specifically, the precision inspection tool includes three cylinders and three rectangular protrusions. Any point on the cylinder can be used as a target point for puncture surgery, and any point on the rectangular protrusion can be used as a needle insertion point.

[0159] As an optional implementation, Figure 5 It is a schematic diagram of a calibration finger, the axis of which is used to indicate the puncture path. Specifically, the calibration finger is fixed in the puncture guide rail of the puncture guide, and the calibration finger is a cylinder.

[0160] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0161] The method of the embodiment of the present application is described in detail above, and the device of the embodiment of the present application is provided below.

[0162] See also Figure 6 , Figure 6 The schematic diagram of the structure of a puncture device based on image registration provided in an embodiment of the present application is as follows. The puncture device based on image registration 1 comprises: an acquisition unit 11, a determination unit 12, a matrix calculation unit 13, and a first adjustment unit 14. Among them:

[0163] An acquisition unit 11 is used to acquire the CT image and the ultrasound image; the CT image is an image obtained by performing a CT scan on the target object; the ultrasound image is an image obtained by performing an ultrasound scan on the target object, and the image size of the ultrasound image is smaller than the image size of the CT image;

[0164] A determination unit 12, configured to determine, in the CT image, an image of a target area having the same image size as that of the ultrasound image, as a target area image;

[0165] The matrix calculation unit 13 is used to obtain a first registration matrix according to the coordinate difference between the target area image and the ultrasound image in the ultrasound coordinate system when the correlation between the target area image and the ultrasound image is greater than a correlation threshold; the first registration matrix is ​​used to align the target area image with the ultrasound image;

[0166] The first adjustment unit 14 is used to adjust the CT image using the first registration matrix to obtain the target image.

[0167] In combination with any embodiment of the present application, the puncture device based on image registration further includes a correlation calculation unit 15, which is used to:

[0168] Determine the correlation between pixels at the same position in the target area image and the ultrasound image to obtain a correlation matrix, wherein the number of parameters in the correlation matrix is ​​the same as the number of pixels in the target area image;

[0169] In a case where the modulus of the correlation matrix is ​​greater than a first threshold, the correlation between the target region image and the ultrasound image is determined to be greater than the correlation threshold.

[0170] In combination with any embodiment of the present application, the pixel at the first position in the target area image is a first pixel, and the pixel at the first position in the ultrasound image is a second pixel;

[0171] The above correlation calculation unit 15 is specifically used for:

[0172] Determine the average value of pixel information of pixels in the target area image to obtain a first average value;

[0173] Determine an average value of pixel information of pixels in the ultrasound image to obtain a second average value;

[0174] Determine pixel information of the first pixel to obtain a first pixel value;

[0175] Determine pixel information of the second pixel to obtain a second pixel value;

[0176] Determine a difference between the first pixel value and the first mean value to obtain a first difference value;

[0177] Determine a difference between the second pixel value and the second mean value to obtain a second difference value;

[0178] Determine, according to the product of the first difference and the second difference, the correlation between the pixel at the first position in the target area image and the ultrasonic image to obtain a first correlation;

[0179] The correlation matrix is ​​obtained according to the first correlation and the second correlation, wherein the second correlation is the correlation between pixels at the same position in the target area image and the ultrasound image except for the first position.

[0180] In combination with any embodiment of the present application, the acquisition unit 11 is specifically used for:

[0181] Acquire CT three-dimensional images and ultrasound three-dimensional images;

[0182] According to the target section, the CT image of the CT three-dimensional image on the target section is obtained, and the target section is a section from head to toe;

[0183] According to the target section, the ultrasonic image of the ultrasonic three-dimensional image on the target section is obtained.

[0184] In combination with any embodiment of the present application, the CT image includes CT feature points, the ultrasound image includes ultrasound feature points, the CT feature points are pixel points in the CT image representing the second position of the target object, the ultrasound feature points are pixel points in the ultrasound image representing the second position of the target object, the distance between the CT feature points and the ultrasound feature points is greater than a second threshold and less than a third threshold, and the second threshold is used to determine image registration;

[0185] The puncture device based on image registration further includes a second adjustment unit 16, which is used to:

[0186] Acquire a first image, where the first image is an original image obtained by performing a CT scan on the target object, and the first image includes a first feature point, where the first feature point is a pixel point in the first image that represents the second position of the target object;

[0187] According to the positional relationship between the first feature point and the ultrasonic feature point, a second registration matrix is ​​obtained, wherein the second registration matrix is ​​used to adjust the first image to the CT image;

[0188] The first image is adjusted using the second registration matrix to obtain the CT image.

[0189] In combination with any embodiment of the present application, the puncture device based on image registration further includes a puncture unit 17, which is used to:

[0190] Determining a reference puncture path in the CT image, the reference puncture path being a path used to guide puncture of the target object; the path in the target image used to guide puncture of the target object is a target puncture path;

[0191] When the target image is registered with the ultrasound image, the target object is punctured according to the target puncture path.

[0192] In an embodiment of the present application, after acquiring a CT image and an ultrasound image, the puncture device based on image registration determines a target area image having the same image size as the ultrasound image from the CT image. And when the correlation between the target area image and the ultrasound image is greater than a correlation threshold, a first registration matrix is ​​obtained according to the coordinate difference between the target area image and the ultrasound image in the ultrasound coordinate system. By determining the target area image having the same image size as the ultrasound image from the CT image and calculating the correlation with the ultrasound image, the number of times the puncture device based on image registration calculates the correlation can be reduced compared to calculating the correlation between any pixel in the CT image and all pixels in the ultrasound image, thereby improving the speed at which the puncture device based on image registration performs image registration. After determining the first registration matrix, the puncture device based on image registration adjusts the CT image using the first registration matrix to obtain a target image. Since the CT image includes the target area image, the target area image will also be transformed while the CT image is being transformed. The target image includes an image after the target area image is transformed using the first registration matrix. The image after the target area image is transformed using the first registration matrix is ​​aligned with the ultrasound image.

[0193] In some embodiments, the functions or modules included in the device provided in the embodiments of the present application can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0194] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. The electronic device 2 includes a processor 21 and a memory 22. Optionally, the electronic device 2 also includes an input device 23 and an output device 24. The processor 21, the memory 22, the input device 23 and the output device 24 are coupled via a connector, and the connector includes various interfaces, transmission lines or buses, etc., which are not limited in the embodiments of the present application. It should be understood that in each embodiment of the present application, coupling refers to mutual connection in a specific manner, including direct connection or indirect connection through other devices, for example, it can be connected through various interfaces, transmission lines, buses, etc.

[0195] The processor 21 may include one or more processors, for example, one or more central processing units (CPUs). When the processor is a CPU, the CPU may be a single-core CPU or a multi-core CPU. Optionally, the processor 21 may be a processor group consisting of multiple CPUs, and the multiple processors are coupled to each other via one or more buses. Optionally, the processor may also be other types of processors, etc., which are not limited in the embodiments of the present application.

[0196] The memory 22 can be used to store computer program instructions and various computer program codes including the program code for executing the program code of the present application. Optionally, the memory includes but is not limited to random access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM), or portable read only memory (CD-ROM), which is used for related instructions and data.

[0197] The input device 23 is used to input data and / or signals, and the output device 24 is used to output data and / or signals. The input device 23 and the output device 24 can be independent devices or an integrated device.

[0198] It can be understood that in the embodiment of the present application, the memory 22 can be used not only to store relevant instructions, but also to store relevant data. For example, the memory 22 can be used to store CT images and ultrasound images obtained through the input device 23, or the memory 22 can also be used to store target images obtained through the processor 21, etc. The embodiment of the present application does not limit the specific data stored in the memory.

[0199] Understandably, Figure 7 Only a simplified design of an electronic device is shown. In practical applications, the electronic device may also include other necessary components, including but not limited to any number of input / output devices, processors, memories, etc., and all electronic devices that can implement the embodiments of the present application are within the protection scope of the present application.

[0200] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0201] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those skilled in the art can also clearly understand that the descriptions of the various embodiments of the present application have different focuses. For the convenience and brevity of description, the same or similar parts may not be repeated in different embodiments. Therefore, for parts not described or not described in detail in a certain embodiment, refer to the records of other embodiments.

[0202] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0203] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0204] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0205] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0206] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by a computer program to instruct the relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. The aforementioned storage medium includes: a read-only memory (ROM) or a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

Claims

1. A puncture method based on image registration, It is characterized in that The method is used to register a CT image of a target object with an ultrasound image before performing a puncture operation on the target object, so as to obtain a target image aligned with the ultrasound image, and the method comprises: Acquire the CT image and the ultrasound image; the CT image is an image obtained by performing a CT scan on the target object; the ultrasound image is an image obtained by performing an ultrasound scan on the target object, and the image size of the ultrasound image is smaller than the image size of the CT image; Determine, in the CT image, an image of a target area having the same image size as that of the ultrasound image as the target area image; When the correlation between the target area image and the ultrasound image is greater than a correlation threshold, a first registration matrix is ​​obtained according to a coordinate difference between the target area image and the ultrasound image in an ultrasound coordinate system; the first registration matrix is ​​used to align the target area image with the ultrasound image; The CT image is adjusted using the first registration matrix to obtain the target image.

2. The method according to claim 1, It is characterized in that When the correlation between the target area image and the ultrasound image is greater than a correlation threshold, before obtaining the first registration matrix according to the coordinate difference between the target area image and the ultrasound image in the ultrasound coordinate system, the method further includes: Determine the correlation between pixels at the same position in the target area image and the ultrasound image to obtain a correlation matrix, wherein the number of parameters in the correlation matrix is ​​the same as the number of pixels in the target area image; In a case where the modulus of the correlation matrix is ​​greater than a first threshold, the correlation between the target region image and the ultrasound image is determined to be greater than the correlation threshold.

3. The method according to claim 2, It is characterized in that The pixel at the first position in the target area image is a first pixel, and the pixel at the first position in the ultrasound image is a second pixel; Determining the correlation between pixels at the same position in the target area image and the ultrasound image to obtain a correlation matrix includes: Determine an average value of pixel information of pixels in the target area image to obtain a first average value; Determine an average value of pixel information of pixels in the ultrasound image to obtain a second average value; Determine pixel information of the first pixel to obtain a first pixel value; Determine pixel information of the second pixel to obtain a second pixel value; Determine a difference between the first pixel value and the first mean value to obtain a first difference value; Determine a difference between the second pixel value and the second mean value to obtain a second difference value; Determine, according to the product of the first difference and the second difference, a correlation between pixels at the first position in the target area image and the ultrasound image to obtain a first correlation; The correlation matrix is ​​obtained according to the first correlation and the second correlation, wherein the second correlation is the correlation between pixels at the same position in the target area image and the ultrasound image except for the first position.

4. The method according to any one of claims 1 to 3, It is characterized in that The acquiring of the CT image and the ultrasound image comprises: Acquire CT three-dimensional images and ultrasound three-dimensional images; According to the target section, the CT image of the CT three-dimensional image on the target section is obtained, and the target section is a section from head to toe; According to the target section, the ultrasonic image of the ultrasonic three-dimensional image on the target section is obtained.

5. The method according to any one of claims 1 to 3, It is characterized in that The CT image includes a CT feature point, and the ultrasound image includes an ultrasound feature point, the CT feature point is a pixel point in the CT image representing a second position of the target object, and the ultrasound feature point is a pixel point in the ultrasound image representing the second position of the target object, and a distance between the CT feature point and the ultrasound feature point is greater than a second threshold and less than a third threshold, and the second threshold is used to determine image registration; Before determining in the CT image an image of the target area having the same image size as that of the ultrasound image as the target area image, the method further includes: Acquire a first image, where the first image is an original image obtained by performing a CT scan on the target object, and the first image includes a first feature point, where the first feature point is a pixel point in the first image that represents the second position of the target object; obtaining a second registration matrix according to a positional relationship between the first feature point and the ultrasound feature point, wherein the second registration matrix is ​​used to adjust the first image to the CT image; The first image is adjusted using the second registration matrix to obtain the CT image.

6. The method according to any one of claims 1 to 3, It is characterized in that After adjusting the CT image using the first registration matrix to obtain a target image, the method further includes: Determining a reference puncture path in the CT image, wherein the reference puncture path is a path used to guide puncture of a target object; the path in the target image used to guide puncture of a target object is a target puncture path; When the target image is registered with the ultrasound image, the target object is punctured according to the target puncture path.

7. A puncture device based on image registration, which, before performing a puncture operation on a target object, aligns a CT image of the target object with an ultrasound image to obtain a target image aligned with the ultrasound image. include: an acquisition unit, configured to acquire the CT image and the ultrasound image; The CT image is an image obtained by performing a CT scan on the target object; The ultrasonic image is an image obtained by performing ultrasonic scanning on the target object, and the image size of the ultrasonic image is smaller than the image size of the CT image; A determining unit, configured to determine, in the CT image, an image of a target area having the same image size as that of the ultrasound image as the target area image; a matrix calculation unit, configured to obtain a first registration matrix according to a coordinate difference between the target area image and the ultrasound image in an ultrasound coordinate system when the correlation between the target area image and the ultrasound image is greater than a correlation threshold; the first registration matrix is ​​used to align the target area image with the ultrasound image; The first adjustment unit is used to adjust the CT image using the first registration matrix to obtain the target image.

8. An electronic device, It is characterized in that include: A processor and a memory, wherein the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and when the processor executes the computer instructions, the electronic device executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor is enabled to execute the method according to any one of claims 1 to 6.

10. A computer program product, It is characterized in that The computer program product comprises a computer program or instructions; when the computer program or instructions are run on a computer, the computer is enabled to execute the method according to any one of claims 1 to 6.

Images