Ellipse positioning data processing method, device, equipment and computer readable medium

Abstract

The embodiments of the present disclosure disclose an ellipse positioning data processing method, device, equipment and computer-readable medium. A specific implementation of the method includes: obtaining ellipse positioning data; determining a target energy functional; converting the target energy functional to obtain an unconstrained function to be processed; initializing the number of iterations; executing the following generation steps: updating the number of iterations; generating ellipse parameter update data; generating ellipse positioning update data; determining the ellipse parameter update data as an ellipse parameter; determining the ellipse positioning update data as an ellipse positioning data; executing the generation steps again; in response to the number of iterations being greater than or equal to the preset number of iterations and / or the ellipse parameter and the ellipse positioning data not satisfying the preset ellipse numerical condition, determining the ellipse parameter as the target ellipse parameter; controlling the associated display device to display the ellipse media information. This implementation improves data accuracy, adaptability to different types of noise interference and the accuracy of displayed lymph nodes.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to an ellipse positioning data processing method, apparatus, device, and computer-readable medium. Background Art

[0002] Circular target detection has a wide range of applications in security monitoring, industrial automation measurement, robot navigation and other fields. Circular target detection can be used to detect lymph nodes in images. The projection shape of a circle in three-dimensional space is an ellipse, so it is usually detected based on the ellipse positioning data of the lymph nodes. At present, the existing method for processing the ellipse positioning data of the lymph nodes is to process the ellipse positioning data by minimizing the L2 norm of the observed data.

[0003] However, when the above method is used to process the ellipse positioning data of the lymph nodes, the following technical problems often occur:

[0004] The accuracy of the ellipse-related data obtained after processing is low. In addition, when processing the ellipse positioning data including different types of noise interference, the accuracy of the obtained ellipse-related data varies greatly. The above method has poor adaptability to different types of noise interference, resulting in low accuracy of the lymph nodes marked for display in the lymph node marking image when the ellipse positioning data is lymph node edge point data. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose ellipse positioning data processing methods, devices, electronic devices and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide an ellipse positioning data processing method, the method comprising: acquiring ellipse positioning data, wherein the ellipse positioning data comprises noisy ellipse positioning data and non-noise ellipse positioning data, and the ellipse positioning data is determined by the lymph node edge point data in the lymph node edge point data set after a lymph node edge point data set is generated based on an original lymph node image; determining a target energy functional according to an L0 norm, the noisy ellipse positioning data and the non-noise ellipse positioning data included in the ellipse positioning data; converting the target energy functional to obtain an unconstrained function to be processed; initializing the number of iterations; performing the following generation steps according to the ellipse positioning data, the ellipse parameters, the unconstrained function to be processed and the number of iterations: updating the number of iterations according to a preset value; and according to the unconstrained function to be processed and the ellipse positioning data, Generate ellipse parameter update data; generate ellipse positioning update data according to the above-mentioned unconstrained function to be processed and the above-mentioned ellipse parameters; determine the above-mentioned ellipse parameter update data as ellipse parameters to update the ellipse parameters; determine the above-mentioned ellipse positioning update data as ellipse positioning data to update the ellipse positioning data; in response to the above-mentioned number of iterations being less than the preset number of iterations, and the updated ellipse parameters and the updated ellipse positioning data satisfying the preset ellipse numerical conditions, execute the above-mentioned generation step again; in response to the above-mentioned number of iterations being greater than or equal to the above-mentioned preset number of iterations and / or the updated ellipse parameters and the updated ellipse positioning data not satisfying the above-mentioned preset ellipse numerical conditions, determine the updated ellipse parameters as target ellipse parameters; according to the above-mentioned target ellipse parameters, control the associated display device to display ellipse media information, wherein the above-mentioned ellipse media information is a lymph node marking image.

[0008] In a second aspect, some embodiments of the present disclosure provide an ellipse positioning data processing device, the device comprising: an acquisition unit, configured to acquire ellipse positioning data, wherein the ellipse positioning data comprises noise ellipse positioning data and non-noise ellipse positioning data, and the ellipse positioning data is generated based on an original lymph node image, and then the lymph node edge point data in the lymph node edge point data set is determined; a first determination unit, configured to determine a target energy functional according to an L0 norm, the noise ellipse positioning data and the non-noise ellipse positioning data included in the ellipse positioning data; a conversion unit, configured to convert the target energy functional to obtain an unconstrained function to be processed; an initialization unit, configured to initialize the number of iterations; an execution unit, configured to perform the following generation steps according to the ellipse positioning data, the ellipse parameters, the unconstrained function to be processed and the number of iterations: updating the number of iterations according to a preset value; updating the number of iterations according to the unconstrained function to be processed Processing function and the above-mentioned ellipse positioning data to generate ellipse parameter update data; generating ellipse positioning update data according to the above-mentioned unconstrained function to be processed and the above-mentioned ellipse parameters; determining the above-mentioned ellipse parameter update data as ellipse parameters to update the ellipse parameters; determining the above-mentioned ellipse positioning update data as ellipse positioning data to update the ellipse positioning data; in response to the above-mentioned number of iterations being less than the preset number of iterations, and the updated ellipse parameters and the updated ellipse positioning data satisfying the preset ellipse numerical conditions, executing the above-mentioned generation step again; a second determination unit is configured to determine the updated ellipse parameters as target ellipse parameters in response to the above-mentioned number of iterations being greater than or equal to the preset number of iterations and / or the updated ellipse parameters and the updated ellipse positioning data not satisfying the preset ellipse numerical conditions; a control unit is configured to control the associated display device to display ellipse media information according to the above-mentioned target ellipse parameters, wherein the above-mentioned ellipse media information is a lymph node marking image.

[0009] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0010] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0011] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the ellipse positioning data processing method of some embodiments of the present disclosure, the accuracy of the ellipse related data obtained after data processing can be improved, the adaptability to different types of noise interference can be improved, and the accuracy of the lymph nodes marked in the lymph node marking image for display can be improved. Specifically, the reason for the low data accuracy and adaptability is that the accuracy of the ellipse related data obtained after processing is low. In addition, when processing the ellipse positioning data including different types of noise interference, the accuracy of the obtained ellipse related data is relatively different. The above-mentioned method has poor adaptability to different types of noise interference, resulting in the low accuracy of the lymph nodes marked in the lymph node marking image for display when the ellipse positioning data is lymph node edge point data. Based on this, the ellipse positioning data processing method of some embodiments of the present disclosure first obtains ellipse positioning data. Among them, the above-mentioned ellipse positioning data includes noise ellipse positioning data and non-noise ellipse positioning data. The above-mentioned ellipse positioning data is determined by the lymph node edge point data in the above-mentioned lymph node edge point data set after the lymph node edge point data set is generated based on the original lymph node image. Then, the target energy functional is determined according to the L0 norm, the noise ellipse positioning data and the non-noise ellipse positioning data included in the ellipse positioning data. Thus, a constrained problem for the ellipse positioning data can be established according to the L0 norm, and a target energy functional constraining the ellipse positioning data can be obtained. Secondly, the target energy functional is transformed to obtain an unconstrained function to be processed. Thus, an unconstrained function to be processed that needs to be minimized can be obtained. Then, the number of iterations is initialized. Thus, the number of iterations that characterize the initial value can be obtained. Afterwards, according to the ellipse positioning data, the ellipse parameters, the above-mentioned unconstrained function to be processed and the number of iterations, the following generation steps are performed: according to the preset value, the number of iterations is updated; according to the above-mentioned unconstrained function to be processed and the above-mentioned ellipse positioning data, the ellipse parameter update data is generated; according to the above-mentioned unconstrained function to be processed and the above-mentioned ellipse parameters, the ellipse positioning update data is generated; the above-mentioned ellipse parameter update data is determined as the ellipse parameter to update the ellipse parameter; the above-mentioned ellipse positioning update data is determined as the ellipse positioning data to update the ellipse positioning data; in response to the above-mentioned number of iterations being less than the preset number of iterations, and the updated ellipse parameters and the updated ellipse positioning data satisfying the preset ellipse numerical conditions, the above-mentioned generation steps are performed again. In this way, the ellipse parameters can be continuously updated. Then, in response to the number of iterations being greater than or equal to the preset number of iterations and / or the updated ellipse parameters and the updated ellipse positioning data not satisfying the preset ellipse numerical conditions, the updated ellipse parameters are determined as the target ellipse parameters. In this way, the target ellipse parameters for displaying the ellipse media information can be obtained. Finally, according to the target ellipse parameters, the associated display device is controlled to display the ellipse media information. Wherein, the above-mentioned ellipse media information is a lymph node marking image. Thus, the elliptical media information can be displayed.Because the ellipse positioning data is continuously refined by using the ellipse parameters through the continuous execution of the generation steps, the accuracy of the ellipse parameters generated according to the ellipse positioning data is improved. Also, because the L0 norm is used to determine the target energy functional, when the noise corresponding to the noise ellipse positioning data included in the ellipse positioning data is unstructured sparse noise, such as Gaussian noise, Laplace noise, and when the noise ellipse positioning data included in the ellipse positioning data is empty, the noise ellipse positioning data can be constrained, thereby reducing the influence of the noise ellipse positioning data included in the ellipse positioning data on the accuracy of the generated ellipse parameters, and improving the adaptability of the ellipse positioning data processing method to different types of noise interference. Therefore, when the ellipse positioning data is lymph node edge point data, the displayed lymph nodes can be more accurately marked in the lymph node marking image. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0013] Figure 1 is a flow chart of some embodiments of the ellipse positioning data processing method according to the present disclosure;

[0014] Figure 2 It is a schematic diagram of ellipse positioning data including noise ellipse positioning data being empty in the ellipse positioning data processing method disclosed in the present invention;

[0015] Figure 3 It is a schematic diagram of the corresponding ellipse media information when the noise ellipse positioning data included in the simulated ellipse positioning data is empty and the number of iterations is 2 in the ellipse positioning data processing method disclosed in the present invention;

[0016] Figure 4 It is a schematic diagram of the ellipse positioning data including the noise ellipse positioning data corresponding to the Gaussian noise ellipse positioning data in the ellipse positioning data processing method disclosed in the present invention;

[0017] Figure 5 It is a schematic diagram of the ellipse media information corresponding to Gaussian noise, in which the noise ellipse positioning data included in the simulated ellipse positioning data corresponds to Gaussian noise, and the number of iterations is 200 in the ellipse positioning data processing method disclosed in the present invention;

[0018] Figure 6 It is a schematic diagram of the ellipse positioning data including the noise ellipse positioning data corresponding to the ellipse positioning data of Laplace noise in the ellipse positioning data processing method disclosed in the present invention;

[0019] Figure 7It is a schematic diagram of the ellipse media information corresponding to the Laplace noise included in the simulated ellipse positioning data in the ellipse positioning data processing method of the present disclosure, and the number of iterations is 200;

[0020] Figure 8 is a schematic diagram of the structure of some embodiments of the ellipse positioning data processing device according to the present disclosure;

[0021] Fig. 9 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0022] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0023] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0024] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0025] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0026] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0027] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0028] Figure 1 The process 100 of some embodiments of the ellipse positioning data processing method according to the present disclosure is shown. The ellipse positioning data processing method comprises the following steps:

[0029] Step 101, obtaining ellipse positioning data.

[0030] In some embodiments, the execution subject (e.g., a computing device) of the ellipse positioning data processing method may obtain the ellipse positioning data through a wired connection or a wireless connection. The ellipse positioning data may include noise ellipse positioning data and non-noise ellipse positioning data. The ellipse positioning data is determined by the lymph node edge point data in the lymph node edge point data set after the lymph node edge point data set is generated based on the original lymph node image. The original lymph node image may be an original image showing at least one lymph node. The lymph node edge point data set may be the image coordinates of each point generated by the original lymph node image. The ellipse positioning data may be a set of coordinates of each point constituting the outline of the ellipse in a preset coordinate system. The coordinates of each point correspond to the same ellipse. The noise ellipse positioning data may be the coordinate data of each point that is a noise point. The non-noise ellipse positioning data may be the coordinate data of each point that is not a noise point. The initial value of the noise ellipse positioning data may be set to null. The initial value of the non-noise ellipse positioning data may be set to the ellipse positioning data. The ellipse may be a quadratic curve whose curve parameters satisfy the preset ellipse parameter conditions. The above quadratic curve can be expressed as in, δ=(a,b,c,d,e,f) T . Where x represents the horizontal coordinate of the point on the quadratic curve and y represents the vertical coordinate of the point on the quadratic curve. is a row vector expressed in terms of x and y. δ represents the curve parameter in the form of a column vector. The curve parameter δ includes parameter a, parameter b, parameter c, parameter d, parameter e, and parameter f. Parameter a is x 2 Parameter b is the parameter corresponding to xy. Parameter c is the parameter corresponding to y. 2 The corresponding parameter. The parameter d is the corresponding row vector The parameter e is the corresponding row vector The parameter f is the parameter used for normalization. The preset ellipse parameter condition can be b 2 -4ac<0. Therefore, when the quadratic curve satisfies the preset ellipse parameter condition, the quadratic curve can represent an ellipse, and (x, y) can represent the abscissa and ordinate of each point constituting the outline of the ellipse. The coordinates corresponding to each point in the ellipse positioning data can be represented. δ can be an ellipse parameter. It should be noted that the above wireless connection method can include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0031] It should be noted that the above-mentioned computing device can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here. It should be understood that any number of computing devices can be provided according to implementation needs.

[0032] In some optional implementations of some embodiments, the ellipse positioning data may be generated according to the following steps:

[0033] The first step is to obtain an original lymph node image. The original lymph node image shows at least one lymph node. The original lymph node image can be an original image showing at least one lymph node. In practice, the original lymph node image can be obtained by wired connection or wireless connection.

[0034] The second step is to crop the original lymph node image to obtain a cropped sub-image set. In practice, a preset cropping method can be used to crop the original lymph node image to obtain a cropped sub-image set, so that the cropped sub-images in the cropped sub-image set display a lymph node or do not display a lymph node. The preset cropping method can be a pre-set cropping method. For example, the preset cropping method can be a method of cropping according to a preset size.

[0035] The third step is to perform edge detection processing on each cropped sub-image in the above cropped sub-image set to generate lymph node edge point data and obtain a lymph node edge point data set. The above lymph node edge point data can be the coordinates of each point obtained after edge detection processing in the corresponding cropped sub-image. The above lymph node edge point data can be in the form of a matrix. The number of rows in the above matrix is ​​the same as the number of points obtained after edge detection. The form of each row vector included in the above matrix is: (x 2 ,xy,y 2 , x, y, 1).

[0036] In the fourth step, the empty lymph node edge point data in the lymph node edge point data set are deleted from the lymph node edge point data set, wherein the empty lymph node edge point data may be a zero matrix of the lymph node edge point data.

[0037] In the fifth step, for each lymph node edge point data in the lymph node edge point data set after the deletion process, the above lymph node edge point data is determined as ellipse positioning data, thereby obtaining ellipse positioning data representing the lymph node.

[0038] Step 102, determining a target energy functional according to the L0 norm, the noise ellipse positioning data and the non-noise ellipse positioning data included in the ellipse positioning data.

[0039] In some embodiments, the execution subject may determine the target energy functional according to the L0 norm, the noise ellipse positioning data and the non-noise ellipse positioning data included in the ellipse positioning data. Wherein, Φ=U+V. Φ represents the ellipse positioning data. U represents the non-noise ellipse positioning data. V represents the noise ellipse positioning data. Φ, U, and V are matrices of the same size. The number of rows of the matrix is ​​the number of points that constitute the outline of the ellipse. Each row vector included in Φ, U, and V is in the form of (x 2 ,xy,y 2 , x, y, l). Among them, x 2 ,xy,y 2 , x, y, 1 are the elements included in the vector. The row vectors whose elements in the matrix U are all 0 do not all have 0 elements in the row vectors of the corresponding rows in the matrix V. The row vectors whose elements in the matrix V are all 0 do not all have 0 elements in the row vectors of the corresponding rows in the matrix U.

[0040] As an example, Φ may be:

[0041]

[0042] Wherein, x1 represents the horizontal coordinate of the first point included in the ellipse positioning data. y1 represents the vertical coordinate of the first point included in the ellipse positioning data. x2 represents the horizontal coordinate of the second point included in the ellipse positioning data. y2 represents the vertical coordinate of the second point included in the ellipse positioning data. x3 represents the horizontal coordinate of the third point included in the ellipse positioning data. y3 represents the vertical coordinate of the third point included in the ellipse positioning data. x4 represents the horizontal coordinate of the fourth point included in the ellipse positioning data. y4 represents the vertical coordinate of the fourth point included in the ellipse positioning data. x5 represents the horizontal coordinate of the fifth point included in the ellipse positioning data. y5 represents the vertical coordinate of the fifth point included in the ellipse positioning data.

[0043] U can be:

[0044]

[0045] V can be:

[0046]

[0047] Wherein, V in the above example includes only one row vector whose elements are not all 0. When V includes only one row vector whose elements are not all 0, V may also be a row vector whose elements are not all 0. V in the above example may also be:

[0048]

[0049] In practice, the following formula can be determined as the target energy functional:

[0050]

[0051] Among them, Φ represents the ellipse positioning data. U represents the non-noise ellipse positioning data. V represents the noisy ellipse positioning data. δ represents the ellipse parameter. ||Uδ|| 2 Represents the square of the norm of the product of matrix U and matrix δ. λ is a regularization parameter, where λ is greater than 0. For example, λ can be 1. ||V||0 represents the L0 norm of matrix V. The value of ||V||0 represents the number of non-zero elements in matrix V. ||Uδ|| 2 +λ||V||0 represents the target energy functional. It means that when the target energy functional ||Uδ|| 2 When the value of +λ||V||0 is the smallest, the corresponding δ, U, and V are the solutions of the target energy functional. Therefore, according to the L0 norm, a constrained problem for the ellipse positioning data can be established to obtain the target energy functional constraining the ellipse positioning data.

[0052] Step 103, transform the target energy functional to obtain an unconstrained function to be processed.

[0053] In some embodiments, the execution subject may convert the target energy functional to obtain an unconstrained function to be processed. In practice, the Lagrangian factor method may be used to convert the solution of the target energy functional to the solution of the unconstrained function to be processed, and the obtained unconstrained function to be processed may be shown as follows:

[0054]

[0055] Among them, α and β are constants greater than 0. For example, α and β can both be set to 1. T Cδ can be 4ac-b 2 Indicates. T represents the transpose of δ. Since b 2 When -4ac=-1, the above preset ellipse parameter condition b is satisfied 2 -4ac<0,b 2 The equivalent form of -4ac=-1 is 4ac-b 2 =1.4ac-b 2 =1 is in the form of δ T Cδ=1. Therefore, δ T Cδ represents 4ac-b 2 . The value of matrix C is as follows:

[0056]

[0057] Thus, the unconstrained function to be processed that needs to be minimized can be obtained.

[0058] Step 104, initializing the number of iterations.

[0059] In some embodiments, the execution entity may initialize the number of iterations k.

[0060] The iteration number k may represent the number of times step 105 is performed. In practice, the value of the iteration number k may be set to 0. Thus, the iteration number representing the initial value may be obtained.

[0061] Step 105, according to the ellipse positioning data, the ellipse parameters, the unconstrained function to be processed and the number of iterations, the following generation steps are performed:

[0062] Step 1051, update the number of iterations according to a preset value. The preset value may be a pre-set value. For example, the preset value may be 1. In practice, the execution subject may redefine the sum of the preset value and the number of iterations as the number of iterations to update the number of iterations. As an example, the number of iterations may be updated using the following formula:

[0063] k=k+1.

[0064] The k on the left side of the equation represents the number of iterations after the update, and the k on the right side of the equation represents the number of iterations before the update.

[0065] Step 1052, generating ellipse parameter update data according to the unconstrained function to be processed and the ellipse positioning data.

[0066] In practice, first, the noise ellipse positioning data and the non-noise ellipse positioning data included in the above ellipse positioning data can be brought into the above unconstrained function to be processed. When the above step 1052 is performed for the first time, the initial value of the noise ellipse positioning data and the initial value of the non-noise ellipse positioning data can be substituted into the above unconstrained function to be processed. When the above step 1052 is not performed for the first time, the noise ellipse positioning data and the non-noise ellipse positioning data obtained by the last execution of step 105 can be substituted into the above unconstrained function to be processed.

[0067] Secondly, the alternating direction minimum method can be used to solve the unconstrained function to be processed after substitution. The unconstrained function to be processed after substitution is shown as follows:

[0068]

[0069] Wherein, J(δ′) represents the unconstrained function to be processed after substitution. δ′ represents the ellipse parameter update data. δ′ is the only variable included in the unconstrained function to be processed after substitution. express The value of δ′ corresponding to the minimum value.

[0070] When solving the unconstrained function to be processed after the above substitution, the first step is to find the partial derivative of δ′ at both ends of the unconstrained function to be processed after the above substitution, and obtain In the second step, we can make the above partial derivative Solving for (UU T +βC)δ′=0. Step 3, since (UU T +βC)δ′=0, the right side is 0, (UU T +βC)δ′=0 has no exact analytical solution. Therefore, the approximate solution of δ′ is:

[0071]

[0072] Here, ε is a constant close to 0. For example, ε = 10 -9 .

[0073] Step 1053, generating ellipse positioning update data according to the unconstrained function to be processed and the ellipse parameters.

[0074] In some embodiments, the execution subject may generate ellipse positioning update data according to the unconstrained function to be processed and the ellipse parameters. In practice, various methods may be used to generate ellipse positioning update data Φ′ according to the unconstrained function to be processed and the ellipse parameters.

[0075] In some optional implementations of some embodiments, first, the execution subject may generate non-noise ellipse positioning update data according to the ellipse parameters and the noise ellipse positioning data. In practice, in the first step, the ellipse parameters and the noise ellipse positioning data may be substituted into the unconstrained function to be processed to obtain the following formula:

[0076]

[0077] Wherein, J(U′) represents the unconstrained function to be processed after substitution, and U′ represents the non-noise ellipse positioning update data. U′ is the only variable included in the unconstrained function to be processed after substitution.

[0078] In the second step, the above equation can be solved to obtain the non-noise ellipse positioning update data. For example, the non-noise ellipse positioning update data can be

[0079] Then, the noisy ellipse positioning update data can be generated according to the ellipse parameters and the non-noise ellipse positioning data. In practice, the first step is to substitute the ellipse parameters and the non-noise ellipse positioning data into the unconstrained processing function to obtain the following formula:

[0080]

[0081] Wherein, J(V′) represents the unconstrained function to be processed after substitution, V′ represents the noise ellipse positioning update data, and V′ is the only variable included in the unconstrained function to be processed after substitution.

[0082] In the second step, the above equation can be solved to obtain the noise ellipse positioning update data. For example, the noise ellipse positioning update data can be

[0083] Finally, the non-noise ellipse positioning update data and the noisy ellipse positioning update data can be combined into the ellipse positioning update data. In practice, the row vectors whose elements in the noisy ellipse positioning update data are not all 0 can be used to replace the row vectors with the same row number in the non-noise ellipse positioning update data, thereby obtaining the ellipse positioning update data. In this way, the non-noise ellipse positioning update data and the noisy ellipse positioning update data can be updated in sequence.

[0084] Step 1054, determining the ellipse parameter update data as the ellipse parameters to update the ellipse parameters.

[0085] In some embodiments, the execution subject may determine the ellipse parameter update data as the ellipse parameter to update the ellipse parameter. In practice, the ellipse parameter update data δ′ may be determined as the ellipse parameter δ to update the ellipse parameter δ.

[0086] Step 1055: determine the ellipse positioning update data as the ellipse positioning data to update the ellipse positioning data. In practice, the ellipse positioning update data Φ′ may be determined as the ellipse positioning data Φ to update the ellipse positioning data Φ.

[0087] Step 1056, in response to the number of iterations being less than the preset number of iterations, and the updated ellipse parameters and the updated ellipse positioning data satisfying the preset ellipse numerical conditions, the generation step is performed again. The preset number of iterations may be a pre-set number of iterations. For example, the preset number of iterations may be 200. The preset ellipse numerical conditions may be: Where k is greater than or equal to 2. k Indicates the ellipse parameter corresponding to the number of iterations k. k-1It represents the ellipse parameter corresponding to the iteration number k-1. Thus, the ellipse parameter can be continuously updated.

[0088] Optionally, before executing step 105, the execution subject may determine the noise ratio of the noise ellipse positioning data according to the ellipse positioning data. In practice, the ratio of the value of ||V||0 to the number of row vectors included in the ellipse positioning data may be determined as the noise ratio.

[0089] In some optional implementations of some embodiments, in response to the noise ratio satisfying a preset noise ratio condition, the execution subject may perform the following generation steps according to the ellipse positioning data, the ellipse parameters, the unconstrained function to be processed and the number of iterations. The preset noise ratio condition may be less than a preset noise ratio threshold. The preset noise ratio threshold may be a preset noise ratio threshold. For example, the preset noise ratio threshold may be 10%. Thus, under the premise of certain requirements for accuracy, the accuracy may be improved by controlling the noise ratio.

[0090] Step 106 , in response to the number of iterations being greater than or equal to a preset number of iterations and / or the updated ellipse parameters and the updated ellipse positioning data not satisfying a preset ellipse value condition, determining the updated ellipse parameters as target ellipse parameters.

[0091] In some embodiments, the execution subject may determine the updated ellipse parameters as target ellipse parameters in response to the number of iterations being greater than or equal to the preset number of iterations and / or the updated ellipse parameters and the updated ellipse positioning data not satisfying the preset ellipse numerical conditions. Thus, the target ellipse parameters for displaying ellipse media information may be obtained.

[0092] Step 107: Control the associated display device to display the ellipse media information according to the target ellipse parameters.

[0093] In some embodiments, the above-mentioned execution subject can control the associated display device to display the ellipse media information according to the above-mentioned target ellipse parameters. The above-mentioned ellipse media information is a lymph node marking image. The above-mentioned lymph node marking image can be an image of the lymph nodes being marked. The above-mentioned ellipse media information can be information representing the ellipse corresponding to the above-mentioned target ellipse parameters. For example, the above-mentioned ellipse media information can be a picture showing the ellipse. The above-mentioned ellipse media information can also be a video or animated picture of drawing the ellipse. The above-mentioned associated display device can be a smart terminal connected for communication, such as a smart phone or a laptop. In practice, the above-mentioned execution subject can control the associated display device to display the ellipse media information in various ways according to the above-mentioned target ellipse parameters. In this way, the ellipse media information can be displayed.

[0094] In some optional implementations of some embodiments, first, the execution subject may normalize the target ellipse parameters to obtain normalized target ellipse parameters. In practice, each element a, b, c, d, e, f in the ellipse parameter δ may be divided by f to obtain Where η represents the normalized target ellipse parameter. A represents B stands for C stands for D stands for E stands for F is 1. Then, the ellipse fitting parameters can be determined according to the normalized target ellipse parameters. The ellipse fitting parameters include the ellipse center (Cx, Cy), the length of the major semi-axis of the ellipse R x , the length of the minor semi-axis of the ellipse is R y And the ellipse rotation angle θ. In practice, the ellipse fitting parameters can be determined by the following formula based on the above normalized target ellipse parameters:

[0095]

[0096] Finally, the associated display device can be controlled to display the ellipse media information according to the ellipse fitting parameters. In practice, the execution subject can control the ellipse center (C x , C y ), the major semi-axis of the ellipse R x , the minor semi-axis of the ellipse R y The ellipse is rotated by an angle θ, the ellipse is automatically drawn, the ellipse media information is obtained, and the associated display device is controlled to display the ellipse media information. Thus, the display of the ellipse media information can be realized.

[0097] In some optional implementations of some embodiments, first, the execution subject may mark lymph nodes in each cropped sub-image in the cropped sub-image set according to the target ellipse parameters to obtain a lymph node marked sub-image. In practice, for each cropped sub-image in the cropped sub-image set, a quadratic curve as an ellipse may be marked in the cropped sub-image according to the target ellipse parameters. For example, the ellipse center (C x , C y ), the major semi-axis of the ellipse R x , the minor semi-axis of the ellipse R yAnd the ellipse rotation angle θ is automatically drawn as a quadratic curve of the ellipse in the above cropped sub-image, so that the drawn ellipse coincides with the outline of the lymph node displayed in the above cropped sub-image, thereby marking the lymph node displayed in the cropped sub-image. Then, the obtained lymph node marking sub-images can be spliced ​​to obtain a lymph node marking image. Finally, the associated display device can be controlled to display the above lymph node marking image. In this way, a lymph node marking image with marked lymph nodes can be obtained, so that relevant personnel can find the lymph nodes on the above lymph node marking image through marking.

[0098] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the ellipse positioning data processing method of some embodiments of the present disclosure, the accuracy of the ellipse related data obtained after data processing can be improved, the adaptability to different types of noise interference can be improved, and the accuracy of the lymph nodes marked in the lymph node marking image for display can be improved. Specifically, the reason for the low data accuracy and adaptability is that the accuracy of the ellipse related data obtained after processing is low. In addition, when processing the ellipse positioning data including different types of noise interference, the accuracy of the obtained ellipse related data is relatively different. The above-mentioned method has poor adaptability to different types of noise interference, resulting in the low accuracy of the lymph nodes marked in the lymph node marking image for display when the ellipse positioning data is lymph node edge point data. Based on this, the ellipse positioning data processing method of some embodiments of the present disclosure first obtains ellipse positioning data. Among them, the above-mentioned ellipse positioning data includes noise ellipse positioning data and non-noise ellipse positioning data. The above-mentioned ellipse positioning data is determined by the lymph node edge point data in the above-mentioned lymph node edge point data set after the lymph node edge point data set is generated based on the original lymph node image. Then, the target energy functional is determined according to the L0 norm, the noise ellipse positioning data and the non-noise ellipse positioning data included in the ellipse positioning data. Thus, a constrained problem for the ellipse positioning data can be established according to the L0 norm, and a target energy functional constraining the ellipse positioning data can be obtained. Secondly, the target energy functional is transformed to obtain an unconstrained function to be processed. Thus, an unconstrained function to be processed that needs to be minimized can be obtained. Then, the number of iterations is initialized. Thus, the number of iterations that characterize the initial value can be obtained. Afterwards, according to the ellipse positioning data, the ellipse parameters, the above-mentioned unconstrained function to be processed and the number of iterations, the following generation steps are performed: according to the preset value, the number of iterations is updated; according to the above-mentioned unconstrained function to be processed and the above-mentioned ellipse positioning data, the ellipse parameter update data is generated; according to the above-mentioned unconstrained function to be processed and the above-mentioned ellipse parameters, the ellipse positioning update data is generated; the above-mentioned ellipse parameter update data is determined as the ellipse parameter to update the ellipse parameter; the above-mentioned ellipse positioning update data is determined as the ellipse positioning data to update the ellipse positioning data; in response to the above-mentioned number of iterations being less than the preset number of iterations, and the updated ellipse parameters and the updated ellipse positioning data satisfying the preset ellipse numerical conditions, the above-mentioned generation steps are performed again. In this way, the ellipse parameters can be continuously updated. Then, in response to the number of iterations being greater than or equal to the preset number of iterations and / or the updated ellipse parameters and the updated ellipse positioning data not satisfying the preset ellipse numerical conditions, the updated ellipse parameters are determined as the target ellipse parameters. In this way, the target ellipse parameters for displaying the ellipse media information can be obtained. Finally, according to the target ellipse parameters, the associated display device is controlled to display the ellipse media information. Wherein, the above-mentioned ellipse media information is a lymph node marking image. Thus, the elliptical media information can be displayed.Because the ellipse positioning data is continuously refined by using the ellipse parameters through the continuous execution of the generation steps, the accuracy of the ellipse parameters generated according to the ellipse positioning data is improved. Also, because the L0 norm is used to determine the target energy functional, when the noise corresponding to the noise ellipse positioning data included in the ellipse positioning data is unstructured sparse noise, such as Gaussian noise, Laplace noise, and when the noise ellipse positioning data included in the ellipse positioning data is empty, the noise ellipse positioning data can be constrained, thereby reducing the influence of the noise ellipse positioning data included in the ellipse positioning data on the accuracy of the generated ellipse parameters, and improving the adaptability of the ellipse positioning data processing method to different types of noise interference. Therefore, when the ellipse positioning data is lymph node edge point data, the displayed lymph nodes can be more accurately marked in the lymph node marking image.

[0099] Reference below Figure 2 , Figure 2 is a schematic diagram of an ellipse positioning data processing method disclosed in the present invention, wherein the noise ellipse positioning data included in the simulation is an empty ellipse positioning data. Figure 2 The coordinates of each point of the ellipse shown. The center of the ellipse shown in Figure 2 is (C x , C y )=(60,50), the length of the major semi-axis is R x =30, the length of the minor semi-axis is R y =25, the rotation angle is θ=1.0472 radians.

[0100] Reference below Figure 3 , Figure 3 is a schematic diagram of the corresponding ellipse media information when the noise ellipse positioning data included in the simulated ellipse positioning data is empty and the number of iterations is 2 in the ellipse positioning data processing method disclosed in the present invention. The ellipse included in the ellipse media information can be Figure 3 The ellipse is shown. Figure 3 The center of the displayed ellipse is (C x , C y )=(60.000,50.000), the length of the major semi-axis is R x =30.000, the length of the minor semi-axis is R y =25.000, and the rotation angle is θ=1.0472 radians.

[0101] Reference below Figure 4 , Figure 4 is a schematic diagram of the noise ellipse positioning data included in the simulation corresponding to the ellipse positioning data of Gaussian noise in the ellipse positioning data processing method disclosed in the present invention. The above-mentioned ellipse positioning data includes Figure 4The coordinates of each point of the ellipse shown. The center of the ellipse shown in FIG4 is (C x , C y )=(60,50), the length of the major semi-axis is R x =30, the length of the minor semi-axis is R y =25, the rotation angle is θ=1.0472 radians.

[0102] Reference below Figure 5 , Figure 5 : is a schematic diagram of the ellipse media information corresponding to the noise ellipse positioning data included in the ellipse positioning data processing method of the present disclosure, and the number of iterations is 200. The ellipse included in the ellipse media information can be Figure 5 The ellipse is shown. Figure 5 The center of the displayed ellipse is (C x , C y )=(60.282,50.0699), the length of the major semi-axis is R x =29.2345, the length of the minor semi-axis is R y =25.8437, and the rotation angle is θ=1.1365 radians.

[0103] Reference below Figure 6 , Figure 6 is a schematic diagram of the noise ellipse positioning data included in the simulation corresponding to the ellipse positioning data of Laplace noise in the ellipse positioning data processing method disclosed in the present invention. The above-mentioned ellipse positioning data includes Figure 6 The coordinates of the points of the displayed ellipse. Figure 6 The center of the displayed ellipse is (C x , C y )=(60,50), the length of the major semi-axis is R x =30, the length of the minor semi-axis is R y =25, the rotation angle is θ=1.0472 radians.

[0104] Reference below Figure 7 , Figure 7 : is a schematic diagram of the ellipse media information corresponding to the Laplace noise included in the simulated ellipse positioning data in the ellipse positioning data processing method of the present disclosure, and the number of iterations is 200. The ellipse included in the ellipse media information can be Figure 7 The ellipse is shown. Figure 7 The center of the displayed ellipse is (C x , C y )=(60.1455,50.0826), the length of the major semi-axis is R x=30.3557, the length of the minor semi-axis is R y =24.8952, and the rotation angle is θ=1.0177 radians.

[0105] Continue to refer Figure 8 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an ellipse positioning data processing device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0106] like Figure 8 As shown, the ellipse positioning data processing device 800 of some embodiments includes: an acquisition unit 801, a first determination unit 802, a conversion unit 803, an initialization unit 804, an execution unit 805, a second determination unit 806 and a control unit 807. Wherein, the acquisition unit 801 is configured to acquire ellipse positioning data, wherein the ellipse positioning data includes noise ellipse positioning data and non-noise ellipse positioning data, and the ellipse positioning data is generated based on the original lymph node image. The lymph node edge point data set is determined by the lymph node edge point data in the above lymph node edge point data set; the first determination unit 802 is configured to determine the target energy functional according to the L0 norm, the noise ellipse positioning data and the non-noise ellipse positioning data included in the above ellipse positioning data; the conversion unit 803 is configured to convert the above target energy functional to obtain an unconstrained function to be processed; the initialization unit 804 is configured to initialize the number of iterations; the execution unit 805 is configured to perform the following generation steps according to the ellipse positioning data, the ellipse parameters, the above unconstrained function to be processed and the number of iterations: according to a preset value, update the number of iterations; according to the above unconstrained function to be processed and the above ellipse positioning data , generate ellipse parameter update data; generate ellipse positioning update data according to the above-mentioned unconstrained function to be processed and the above-mentioned ellipse parameters; determine the above-mentioned ellipse parameter update data as ellipse parameters to update the ellipse parameters; determine the above-mentioned ellipse positioning update data as ellipse positioning data to update the ellipse positioning data; in response to the above-mentioned number of iterations being less than the preset number of iterations, and the updated ellipse parameters and the updated ellipse positioning data satisfying the preset ellipse numerical conditions, execute the above-mentioned generation step again; the second determination unit 806 is configured to determine the updated ellipse parameters as target ellipse parameters in response to the above-mentioned number of iterations being greater than or equal to the preset number of iterations and / or the updated ellipse parameters and the updated ellipse positioning data not satisfying the preset ellipse numerical conditions; the control unit 807 is configured to control the associated display device to display ellipse media information according to the above-mentioned target ellipse parameters, wherein the above-mentioned ellipse media information is a lymph node marking image.

[0107] It is understood that the units described in the device 800 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 800 and the units included therein, and will not be described in detail here.

[0108] Reference below Fig. 9 , which shows a structural schematic diagram of an electronic device (eg, a computing device) 900 suitable for implementing some embodiments of the present disclosure. Fig. 9 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0109] like Fig. 9 As shown, the electronic device 900 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 are also stored. The processing device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0110] Typically, the following devices may be connected to the I / O interface 905: an input device 906 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 908 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Although Fig. 9 The electronic device 900 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Fig. 9 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0111] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the processing device 901, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0112] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0113] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0114] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains ellipse positioning data, wherein the above-mentioned ellipse positioning data includes noise ellipse positioning data and non-noise ellipse positioning data, and the above-mentioned ellipse positioning data is determined by the lymph node edge point data in the above-mentioned lymph node edge point data set after the lymph node edge point data set is generated based on the original lymph node image; determines the target energy functional according to the L0 norm, the noise ellipse positioning data and the non-noise ellipse positioning data included in the above-mentioned ellipse positioning data; transforms the above-mentioned target energy functional to obtain an unconstrained function to be processed; initializes the number of iterations; and performs the following generation steps according to the ellipse positioning data, the ellipse parameters, the above-mentioned unconstrained function to be processed and the number of iterations: updates the number of iterations according to a preset value; updates the number of iterations according to the above-mentioned unconstrained function to be processed and the above-mentioned Ellipse positioning data, generating ellipse parameter update data; generating ellipse positioning update data according to the above-mentioned unconstrained to-be-processed function and the above-mentioned ellipse parameters; determining the above-mentioned ellipse parameter update data as the ellipse parameters to update the ellipse parameters; determining the above-mentioned ellipse positioning update data as the ellipse positioning data to update the ellipse positioning data; in response to the above-mentioned number of iterations being less than the preset number of iterations, and the updated ellipse parameters and the updated ellipse positioning data satisfying the preset ellipse numerical conditions, executing the above-mentioned generation step again; in response to the above-mentioned number of iterations being greater than or equal to the above-mentioned preset number of iterations and / or the updated ellipse parameters and the updated ellipse positioning data not satisfying the above-mentioned preset ellipse numerical conditions, determining the updated ellipse parameters as the target ellipse parameters; according to the above-mentioned target ellipse parameters, controlling the associated display device to display ellipse media information, wherein the above-mentioned ellipse media information is a lymph node marking image.

[0115] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0116] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0117] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a first determination unit, a conversion unit, an initialization unit, an execution unit, a second determination unit and a control unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the acquisition unit may also be described as a "unit for acquiring ellipse positioning data".

[0118] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0119] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A method for processing ellipse positioning data, comprising: Acquiring ellipse positioning data, wherein the ellipse positioning data includes noise ellipse positioning data and non-noise ellipse positioning data, and the ellipse positioning data is determined by the lymph node edge point data in the lymph node edge point data set after the lymph node edge point data set is generated based on the original lymph node image; Determining a target energy functional according to the L0 norm, the noise ellipse positioning data and the non-noise ellipse positioning data included in the ellipse positioning data; Transforming the target energy functional to obtain an unconstrained function to be processed; Initialize the number of iterations; Determining the noise ratio of the noise ellipse positioning data according to the ellipse positioning data; In response to the noise ratio satisfying a preset noise ratio condition, the following generating steps are performed according to the ellipse positioning data, the ellipse parameters, the unconstrained function to be processed and the number of iterations: According to the preset value, the number of iterations is updated, where the number of iterations is updated using the following formula: , where the left side of the equation is represents the number of iterations after the update, and the right side of the equation Indicates the number of iterations before updating; Generate ellipse parameter update data according to the unconstrained function to be processed and the ellipse positioning data; Generate ellipse positioning update data according to the unconstrained function to be processed and the ellipse parameters; Determining the ellipse parameter update data as the ellipse parameter to update the ellipse parameter; Determining the ellipse positioning update data as the ellipse positioning data to update the ellipse positioning data; In response to the number of iterations being less than a preset number of iterations, and the updated ellipse parameters and the updated ellipse positioning data satisfying a preset ellipse numerical condition, the generating step is performed again, and the preset ellipse numerical condition is: ,in, Greater than or equal to 2, It means the number of iterations is The corresponding ellipse parameters are It means the number of iterations is The corresponding ellipse parameters when ; In response to the number of iterations being greater than or equal to the preset number of iterations and / or the updated ellipse parameters and the updated ellipse positioning data not satisfying the preset ellipse value condition, determining the updated ellipse parameters as target ellipse parameters; According to the target ellipse parameter, controlling an associated display device to display ellipse media information, wherein the ellipse media information is a lymph node marking image; The ellipse positioning data is a set of coordinates of each point constituting the outline of the ellipse in a preset coordinate system. The ellipse is a quadratic curve whose curve parameters satisfy the preset ellipse parameter conditions. The quadratic curve is expressed as ,in, , ,in, represents the horizontal coordinate of a point on the quadratic curve, represents the ordinate of a point on a quadratic curve, Based on and Represents the row vector, The curve parameters are expressed as a column vector, where the curve parameters Include Parameters ,parameter ,parameter ,parameter ,parameter ,parameter ,parameter for Corresponding parameters, parameters for Corresponding parameters, parameters for Corresponding parameters, parameters is the corresponding row vector In Parameters, parameters is the corresponding row vector In Parameters, parameters is the parameter used for normalization processing, and the preset ellipse parameter condition is , when the quadratic curve meets the preset ellipse parameter conditions, the quadratic curve represents an ellipse, represents the horizontal and vertical coordinates of the points that make up the outline of the ellipse. Represents the coordinates corresponding to each point in the ellipse positioning data, is the ellipse parameter; Wherein, the ellipse positioning data is generated according to the following steps: Acquiring an original lymph node image, wherein the original lymph node image displays at least one lymph node; Cropping the original lymph node image to obtain a set of cropped sub-images; Perform edge detection processing on each cropped sub-image in the cropped sub-image set to generate lymph node edge point data to obtain a lymph node edge point data set, wherein the lymph node edge point data is in the form of a matrix, the number of rows of the matrix is ​​the same as the number of points obtained after edge detection, and each row vector included in the matrix is ​​in the form of: ; Deleting empty lymph node edge point data in the lymph node edge point data set from the lymph node edge point data set; For each lymph node edge point data in the lymph node edge point data set after the deletion process, determining the lymph node edge point data as ellipse positioning data; in, , Represents ellipse positioning data, represents the non-noise ellipse positioning data, represents the noise ellipse positioning data, , , is a matrix of the same size, the number of rows of the matrix is ​​the number of points that make up the outline of the ellipse, , , Each row vector included is of the form ,in, is the element included in the vector, the matrix The row vectors whose elements are all 0 in the matrix The elements of the row vectors corresponding to the rows in the matrix are not all 0. The row vectors whose elements are all 0 in the matrix The elements included in the row vectors of the corresponding rows in are not all 0; in, for: , in, Indicates the horizontal coordinate of the first point included in the ellipse positioning data. Indicates the ordinate of the first point included in the ellipse positioning data. Indicates the horizontal coordinate of the second point included in the ellipse positioning data. Indicates the ordinate of the second point included in the ellipse positioning data. Indicates the horizontal coordinate of the third point included in the ellipse positioning data. Indicates the ordinate of the third point included in the ellipse positioning data. Indicates the horizontal coordinate of the fourth point included in the ellipse positioning data, Indicates the ordinate of the fourth point included in the ellipse positioning data. Indicates the horizontal coordinate of the fifth point included in the ellipse positioning data, Indicates the ordinate of the fifth point included in the ellipse positioning data; for: , for: , Among them, the Only one row vector whose elements are not all 0 is included. When it contains only one row vector whose elements are not all 0, is also a row vector whose elements are not all 0, Also for: ， The following formula is determined as the target energy functional: , in, Represents ellipse positioning data, represents the non-noise ellipse positioning data, represents the noise ellipse positioning data, represents the ellipse parameters, Representation Matrix and matrix The square of the norm of the product of is the regularization parameter, greater than 0, is 1, Representation Matrix The L0 norm of The value of represents the matrix The number of non-zero elements in , represents the target energy functional, It means that when the target energy functional When the value of is the smallest, the corresponding , , is the solution of the target energy functional; Among them, the Lagrangian factor method is used to convert the solution of the target energy functional into the solution of the unconstrained function to be processed, and the obtained unconstrained function to be processed is shown in the following formula: ， in, is a constant greater than 0, are all set to 1. by express, express The transpose of When the preset ellipse parameter condition is met , The equivalent form of , The matrix form is ,therefore, express , where the value of matrix C is as follows: ， Wherein, generating ellipse parameter update data according to the unconstrained function to be processed and the ellipse positioning data includes: bringing the noise ellipse positioning data and the non-noise ellipse positioning data included in the ellipse positioning data into the unconstrained function to be processed; using the alternating direction minimum method to solve the unconstrained function to be processed after the substitution process, and the unconstrained function to be processed after the substitution process is shown in the following formula: ， in, represents the unconstrained function to be processed after substitution, Indicates the ellipse parameter update data. is the only variable included in the unconstrained function to be processed after substitution, express The corresponding minimum value The value of When solving the unconstrained function to be processed after the substitution process, the two ends of the unconstrained function to be processed after the substitution process are respectively Taking partial derivative, we get , let the partial derivative , and the solution is ,because The right end of is 0, There is no exact analytical solution, so The approximate solution is: , in, is a constant close to 0; The step of generating ellipse positioning update data according to the unconstrained function to be processed and the ellipse parameters includes: Generating non-noise ellipse positioning update data according to the ellipse parameters and the noise ellipse positioning data, including: substituting the ellipse parameters and the noise ellipse positioning data into the unconstrained to-be-processed function to obtain the following formula: ， in, represents the unconstrained function to be processed after substitution, represents the non-noise ellipse positioning update data, is the only variable included in the unconstrained function to be processed after substitution; Solving the above equation, we can obtain the non-noise ellipse positioning update data, which is: ; Generating noisy ellipse positioning update data according to the ellipse parameters and the non-noise ellipse positioning data, including: substituting the ellipse parameters and the non-noise ellipse positioning data into the unconstrained to-be-processed function to obtain the following formula: , in, represents the unconstrained function to be processed after substitution, Represents the noise ellipse positioning update data, is the only variable included in the unconstrained function to be processed after substitution; Solve the above equation to get the noise ellipse positioning update data, which is: ; combining the non-noise ellipse positioning update data and the noise ellipse positioning update data into ellipse positioning update data; The step of controlling the associated display device to display the ellipse media information according to the target ellipse parameter includes: The target ellipse parameters are normalized to obtain normalized target ellipse parameters, wherein the ellipse parameters are Each element in Divide by ,get ,in, represents the normalized target ellipse parameters, express , express , express , express , express , is 1; According to the normalized target ellipse parameters, the ellipse fitting parameters are determined, wherein the ellipse fitting parameters include the ellipse center , the length of the major semi-axis of the ellipse , the length of the minor semi-axis of the ellipse And the ellipse rotation angle , wherein, according to the normalized target ellipse parameters, the ellipse fitting parameters are determined by the following formula: ； According to the ellipse fitting parameters, the associated display device is controlled to display the ellipse media information, wherein the ellipse center included in the ellipse fitting parameters , the major semi-axis of the ellipse , the minor semi-axis of the ellipse And the ellipse rotation angle , automatically draw an ellipse, obtain ellipse media information, and control an associated display device to display the ellipse media information; The step of controlling the associated display device to display the ellipse media information according to the target ellipse parameter includes: For each cropped sub-image in the cropped sub-image set, lymph nodes are marked in the cropped sub-image according to the target ellipse parameters to obtain a lymph node marked sub-image, wherein the ellipse center is , the major semi-axis of the ellipse , the minor semi-axis of the ellipse And the ellipse rotation angle , automatically drawing a quadratic curve as an ellipse in the cropped sub-image, so that the drawn ellipse coincides with the outline of the lymph node displayed in the cropped sub-image; splicing the obtained lymph node marker sub-images to obtain a lymph node marker image; The associated display device is controlled to display the lymph node marking image.

2. An ellipse positioning data processing device, comprising: an acquisition unit, configured to acquire ellipse positioning data, wherein the ellipse positioning data includes noise ellipse positioning data and non-noise ellipse positioning data, and the ellipse positioning data is determined by the lymph node edge point data in the lymph node edge point data set after the lymph node edge point data set is generated based on the original lymph node image; A first determining unit is configured to determine a target energy functional according to an L0 norm, noise ellipse positioning data included in the ellipse positioning data, and non-noise ellipse positioning data; A conversion unit is configured to convert the target energy functional to obtain an unconstrained function to be processed; An initialization unit, configured to initialize the number of iterations; a noise ratio determination unit, configured to determine the noise ratio of the noise ellipse positioning data according to the ellipse positioning data; The execution unit is configured to, in response to the noise ratio satisfying a preset noise ratio condition, perform the following generation steps according to the ellipse positioning data, the ellipse parameters, the unconstrained function to be processed and the number of iterations: update the number of iterations according to a preset value, wherein the number of iterations is updated using the following formula: , where the left side of the equation is represents the number of iterations after the update, and the right side of the equation Indicates the number of iterations before updating; generates ellipse parameter update data according to the unconstrained function to be processed and the ellipse positioning data; generates ellipse positioning update data according to the unconstrained function to be processed and the ellipse parameters; determines the ellipse parameter update data as the ellipse parameters to update the ellipse parameters; determines the ellipse positioning update data as the ellipse positioning data to update the ellipse positioning data; in response to the number of iterations being less than the preset number of iterations, and the updated ellipse parameters and the updated ellipse positioning data satisfying the preset ellipse numerical conditions, executes the generating step again; A second determining unit is configured to determine the updated ellipse parameters as target ellipse parameters in response to the number of iterations being greater than or equal to the preset number of iterations and / or the updated ellipse parameters and the updated ellipse positioning data not satisfying the preset ellipse numerical condition; A control unit, configured to control an associated display device to display ellipse media information according to the target ellipse parameter, wherein the ellipse media information is a lymph node marking image; The ellipse positioning data is a set of coordinates of each point constituting the outline of the ellipse in a preset coordinate system. The ellipse is a quadratic curve whose curve parameters satisfy the preset ellipse parameter conditions. The quadratic curve is expressed as ,in, , ,in, represents the horizontal coordinate of a point on the quadratic curve, represents the ordinate of a point on a quadratic curve, Based on and Represents the row vector, The curve parameters are expressed as a column vector, where the curve parameters Include Parameters ,parameter ,parameter ,parameter ,parameter ,parameter ,parameter for Corresponding parameters, parameters for Corresponding parameters, parameters for Corresponding parameters, parameters is the corresponding row vector In Parameters, parameters is the corresponding row vector In Parameters, parameters is the parameter used for normalization processing, and the preset ellipse parameter condition is , when the quadratic curve meets the preset ellipse parameter conditions, the quadratic curve represents an ellipse, represents the horizontal and vertical coordinates of the points that make up the outline of the ellipse. Represents the coordinates corresponding to each point in the ellipse positioning data, is the ellipse parameter; Wherein, the ellipse positioning data is generated according to the following steps: Acquiring an original lymph node image, wherein the original lymph node image displays at least one lymph node; Cropping the original lymph node image to obtain a set of cropped sub-images; Perform edge detection processing on each cropped sub-image in the cropped sub-image set to generate lymph node edge point data to obtain a lymph node edge point data set, wherein the lymph node edge point data is in the form of a matrix, the number of rows of the matrix is ​​the same as the number of points obtained after edge detection, and each row vector included in the matrix is ​​in the form of: ; Deleting empty lymph node edge point data in the lymph node edge point data set from the lymph node edge point data set; For each lymph node edge point data in the lymph node edge point data set after the deletion process, determining the lymph node edge point data as ellipse positioning data; in, , Represents ellipse positioning data, represents the non-noise ellipse positioning data, represents the noise ellipse positioning data, , , is a matrix of the same size, the number of rows of the matrix is ​​the number of points that make up the outline of the ellipse, , , Each row vector included is of the form ,in, is the element included in the vector, the matrix The row vectors whose elements are all 0 in the matrix The elements of the row vectors corresponding to the rows in the matrix are not all 0. The row vectors whose elements are all 0 in the matrix The elements included in the row vectors of the corresponding rows in are not all 0; in, for: ， in, Indicates the horizontal coordinate of the first point included in the ellipse positioning data. Indicates the ordinate of the first point included in the ellipse positioning data. Indicates the horizontal coordinate of the second point included in the ellipse positioning data. Indicates the ordinate of the second point included in the ellipse positioning data. Indicates the horizontal coordinate of the third point included in the ellipse positioning data. Indicates the ordinate of the third point included in the ellipse positioning data. Indicates the horizontal coordinate of the fourth point included in the ellipse positioning data, Indicates the ordinate of the fourth point included in the ellipse positioning data. Indicates the horizontal coordinate of the fifth point included in the ellipse positioning data, Indicates the ordinate of the fifth point included in the ellipse positioning data; for: , for: , Among them, the Only one row vector whose elements are not all 0 is included. When it contains only one row vector whose elements are not all 0, is also a row vector whose elements are not all 0, Also for: ， The following formula is determined as the target energy functional: , in, Represents ellipse positioning data, represents the non-noise ellipse positioning data, represents the noise ellipse positioning data, represents the ellipse parameters, Representation Matrix and matrix The square of the norm of the product of is the regularization parameter, greater than 0, is 1, Representation Matrix The L0 norm of The value of represents the matrix The number of non-zero elements in , represents the target energy functional, It means that when the target energy functional When the value of is the smallest, the corresponding , , is the solution of the target energy functional; Among them, the Lagrangian factor method is used to convert the solution of the target energy functional into the solution of the unconstrained function to be processed, and the obtained unconstrained function to be processed is shown in the following formula: ， in, is a constant greater than 0, are all set to 1. by express, express The transpose of When the preset ellipse parameter condition is met , The equivalent form of , The matrix form is ,therefore, express , where the value of matrix C is as follows: ， Wherein, generating ellipse parameter update data according to the unconstrained function to be processed and the ellipse positioning data includes: bringing the noise ellipse positioning data and the non-noise ellipse positioning data included in the ellipse positioning data into the unconstrained function to be processed; using the alternating direction minimum method to solve the unconstrained function to be processed after the substitution process, and the unconstrained function to be processed after the substitution process is shown in the following formula: ， in, represents the unconstrained function to be processed after substitution, Indicates the ellipse parameter update data. is the only variable included in the unconstrained function to be processed after substitution, express The corresponding minimum value When solving the unconstrained function to be processed after the substitution, the two ends of the unconstrained function to be processed after the substitution are respectively Taking partial derivative, we get , let the partial derivative , and the solution is ,because The right end of is 0, There is no exact analytical solution, so The approximate solution is: ， in, is a constant close to 0; The step of generating ellipse positioning update data according to the unconstrained function to be processed and the ellipse parameters includes: Generating non-noise ellipse positioning update data according to the ellipse parameters and the noise ellipse positioning data, including: substituting the ellipse parameters and the noise ellipse positioning data into the unconstrained to-be-processed function to obtain the following formula: ， in, represents the unconstrained function to be processed after substitution, represents the non-noise ellipse positioning update data, is the only variable included in the unconstrained function to be processed after substitution; Solving the above equation, we can obtain the non-noise ellipse positioning update data, which is: ; Generating noisy ellipse positioning update data according to the ellipse parameters and the non-noise ellipse positioning data, including: substituting the ellipse parameters and the non-noise ellipse positioning data into the unconstrained to-be-processed function to obtain the following formula: ， in, represents the unconstrained function to be processed after substitution, Represents the noise ellipse positioning update data, is the only variable included in the unconstrained function to be processed after substitution; Solve the above equation to get the noise ellipse positioning update data, which is: ; combining the non-noise ellipse positioning update data and the noise ellipse positioning update data into ellipse positioning update data; Wherein, the control unit is further configured to: The target ellipse parameters are normalized to obtain normalized target ellipse parameters, wherein the ellipse parameters are Each element in Divide by ,get ,in, represents the normalized target ellipse parameters, express , express , express , express , express , is 1; According to the normalized target ellipse parameters, the ellipse fitting parameters are determined, wherein the ellipse fitting parameters include the ellipse center , the length of the major semi-axis of the ellipse , the length of the minor semi-axis of the ellipse And the ellipse rotation angle , wherein, according to the normalized target ellipse parameters, the ellipse fitting parameters are determined by the following formula: ； According to the ellipse fitting parameters, the associated display device is controlled to display the ellipse media information, wherein the ellipse center included in the ellipse fitting parameters , the major semi-axis of the ellipse , the minor semi-axis of the ellipse And the ellipse rotation angle , automatically draw an ellipse, obtain ellipse media information, and control an associated display device to display the ellipse media information; Wherein, the control unit is further configured to: For each cropped sub-image in the cropped sub-image set, lymph nodes are marked in the cropped sub-image according to the target ellipse parameters to obtain a lymph node marked sub-image, wherein the ellipse center is , the major semi-axis of the ellipse , the minor semi-axis of the ellipse And the ellipse rotation angle , automatically drawing a quadratic curve as an ellipse in the cropped sub-image, so that the drawn ellipse coincides with the outline of the lymph node displayed in the cropped sub-image; splicing the obtained lymph node marker sub-images to obtain a lymph node marker image; The associated display device is controlled to display the lymph node marking image.

3. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in claim 1.

4. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to claim 1 is implemented.

Images