Method and apparatus for automatic adjustment of chromaffinoma / paraganglioma graphic position

Abstract

The application introduces the image needing to be adjusted; the image is binarized, which is convenient for the calculation and processing of the image; the non-human body image pixels are removed through the maximum connected threshold extraction method; in order to remove organs such as lungs, inversion is performed, and then the maximum connected domain extraction method is used; in order to ensure that the image is a binarized image in the subsequent processing, the image is binarized; pixel edge inflation is performed; the inflated image is subtracted from the original image to obtain an image contour; the human body contour is extracted; the coplanar matrix, the center point and the variance are calculated, the direction vector of the picture is found out through the singular value decomposition method, the angle between the human body image axis and the space X, Y and Z three surfaces is calculated, the distance between the center point of the human body image and the space center point is calculated, the human body image axis vector and the space axis vector are coincided, and the human body center point and the space center point are coincided; therefore, the medical image in the incorrect position can be returned to the correct position, the user can watch more comfortably, and the subsequent operation is avoided to be affected.

Description

Technical Field

[0001] This invention relates to the field of medical image processing technology, and more particularly to an automatic adjustment method for the position of pheochromocytoma / paraganglioma images, as well as an automatic adjustment device for the position of pheochromocytoma / paraganglioma images. Background Technology

[0002] Medical images are images that reflect the internal structure of the human body and are one of the main bases for modern medical diagnosis. Medical image processing deals with medical images using various imaging mechanisms. The types of medical imaging widely used in clinical practice include: X-ray imaging (X-CT), computed tomography (CT), positron emission tomography-computed tomography (PET-CT), magnetic resonance imaging (MRI), nuclear medicine imaging (NMI), ultrasound imaging (UI), and pathological images taken under a microscope.

[0003] However, when acquiring medical images, various reasons often lead to incorrect placement, which can cause problems for users in reading the images and affect their subsequent operations. Summary of the Invention

[0004] To overcome the shortcomings of the prior art, the technical problem to be solved by the present invention is to provide an automatic adjustment method for the position of pheochromocytoma / paraganglioma images, which can bring incorrectly positioned medical images back to the correct position, making the viewing more comfortable for users and avoiding affecting their subsequent operations.

[0005] The technical solution of this invention is: an automatic adjustment method for the position of pheochromocytoma / paraganglioma graphics, which includes the following steps:

[0006] (1) Import the image that needs to be adjusted;

[0007] (2) Binarize the image;

[0008] (3) Remove non-human image pixels by using the maximum connectivity threshold extraction method. The maximum connectivity threshold extraction method is to binarize the above image, set 75% or more to 1 and the rest to 0, then traverse the entire image, calculate the number of adjacent points and the number of adjacent regions according to the coordinates of each point, sort these adjacent regions from largest to smallest, and take the largest region.

[0009] (4) Reverse the order, and then use the maximum connected component extraction method;

[0010] (5) Binarize the image;

[0011] (6) Perform pixel edge dilation;

[0012] (7) Subtract the original image from the dilated image to obtain the image outline;

[0013] (8) Extract the human body contour;

[0014] (9) Calculate the coplanar matrix, center point, and variance;

[0015] (10) Find the direction vector of the image using singular value decomposition;

[0016] (11) Calculate the angles between the human body image axis and the X, Y, and Z planes in space;

[0017] (12) Calculate the distance from the center point of the human body image to the center point of the space;

[0018] (13) Make the axis vector of the human body image coincide with the axis vector of space, and make the center point of the human body coincide with the center point of space.

[0019] This invention imports the image to be adjusted; binarizes the image to facilitate subsequent image calculations and processing; removes non-human image pixels using the maximum connected component extraction method; performs inversion to remove organs such as lungs, and then uses the maximum connected component extraction method; binarizes the image to ensure it is a binarized image in subsequent processing; performs pixel edge dilation; subtracts the original image from the dilated image to obtain the image contour; extracts the human contour; calculates the coplanar matrix, center point, and variance; finds the image's direction vector using singular value decomposition; calculates the angles between the human image axis and the X, Y, and Z planes of space; calculates the distance from the center point of the human image to the center point of space, ensuring that the axis vector of the human image coincides with the axis vector of space, and that the center point of the human body coincides with the center point of space; thus, it can correct incorrectly positioned medical images, making viewing more comfortable for users and avoiding interference with subsequent operations.

[0020] An automatic adjustment device for the graphic position of pheochromocytoma / paraganglioma is also provided, which includes:

[0021] The data reading module is configured to import images that need to be adjusted.

[0022] The data processing module is configured to binarize the image;

[0023] The removal module is configured to remove non-human image pixels using the maximum connectivity threshold extraction method. The maximum connectivity threshold extraction method involves binarizing the image above, setting 75% or more to 1 and the rest to 0, then traversing the entire image, calculating the number of neighboring points and the number of adjacent regions according to the coordinates of each point, sorting these adjacent regions from largest to smallest, and taking the largest region.

[0024] The inversion module is configured to perform inversion.

[0025] The dilation module is configured to perform pixel edge dilation.

[0026] The extraction module is configured to subtract the original image from the dilated image to obtain the image contour and extract the human body contour.

[0027] The calculation module is configured to calculate the coplanar matrix, center point and variance, find the direction vector of the image through the singular value decomposition method, calculate the angle between the human image axis and the X, Y and Z planes of space, and calculate the distance from the center point of the human image to the center point of space.

[0028] The overlap module is configured to make the axis vector of the human body image coincide with the axis vector of space, and the center point of the human body coincide with the center point of space. Attached Figure Description

[0029] Figure 1 This is a flowchart illustrating the automatic adjustment method for the graphic position of pheochromocytoma / paraganglioma according to the present invention. Detailed Implementation

[0030] like Figure 1 As shown, this method for automatically adjusting the position of a pheochromocytoma / paraganglioma graphic includes the following steps:

[0031] (1) Import the image that needs to be adjusted;

[0032] (2) Binarize the image;

[0033] (3) Remove non-human image pixels by using the maximum connectivity threshold extraction method. The maximum connectivity threshold extraction method is to binarize the above image, set 75% or more to 1 and the rest to 0, then traverse the entire image, calculate the number of adjacent points and the number of adjacent regions according to the coordinates of each point, sort these adjacent regions from largest to smallest, and take the largest region.

[0034] (4) Reverse the order, and then use the maximum connected component extraction method;

[0035] (5) Binarize the image;

[0036] (6) Perform pixel edge dilation;

[0037] (7) Subtract the original image from the dilated image to obtain the image outline;

[0038] (8) Extract the human body contour;

[0039] (9) Calculate the coplanar matrix, center point, and variance;

[0040] (10) Find the direction vector of the image using singular value decomposition;

[0041] (11) Calculate the angles between the human body image axis and the X, Y, and Z planes in space;

[0042] (12) Calculate the distance from the center point of the human body image to the center point of the space;

[0043] (13) Make the axis vector of the human body image coincide with the axis vector of space, and make the center point of the human body coincide with the center point of space.

[0044] This invention imports the image to be adjusted; binarizes the image to facilitate subsequent image calculations and processing; removes non-human image pixels using the maximum connected component extraction method; performs inversion to remove organs such as lungs, and then uses the maximum connected component extraction method; binarizes the image to ensure it is a binarized image in subsequent processing; performs pixel edge dilation; subtracts the original image from the dilated image to obtain the image contour; extracts the human contour; calculates the coplanar matrix, center point, and variance; finds the image's direction vector using singular value decomposition; calculates the angles between the human image axis and the X, Y, and Z planes of space; calculates the distance from the center point of the human image to the center point of space, ensuring that the axis vector of the human image coincides with the axis vector of space, and that the center point of the human body coincides with the center point of space; thus, it can correct incorrectly positioned medical images, making viewing more comfortable for users and avoiding interference with subsequent operations.

[0045] Preferably, in step (6), the edge of the inverted image pixel is expanded by one pixel value, so that the image target value contour of the human body is reduced by one layer, which is used to calculate the contour of the following image.

[0046] Preferably, in step (8), the pixel value is determined by the pixel value, which is the pixel of the outermost contour of the human body, and is determined as the human body contour value.

[0047] Preferably, in step (9), the center point of the contour is obtained by adding up all the contour points and taking the average value. The center point of each layer is obtained by adding up the contour points of each layer and taking the average value. Then the variance of the center point of each layer is calculated.

[0048] Preferably, in step (10), a 3x3 symmetric matrix is ​​constructed using variance, and the eigenvectors are calculated using singular value decomposition. The eigenvectors of the human body axis are obtained from the first column of the calculated eigenvectors.

[0049] Preferably, in step (11), the angle between the human body axis in the image and space is calculated using the line-plane angle formula.

[0050] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium. When executed, the program includes the steps of the methods of the above embodiments. The storage medium can be ROM / RAM, magnetic disk, optical disk, memory card, etc. Therefore, corresponding to the method of the present invention, the present invention also includes an automatic adjustment device for the graphic position of pheochromocytoma / paraganglioma. This device is typically represented in the form of functional modules corresponding to the steps of the method. The device includes:

[0051] The data reading module is configured to import images that need to be adjusted.

[0052] The data processing module is configured to binarize the image;

[0053] The removal module is configured to remove non-human image pixels using the maximum connectivity threshold extraction method. The maximum connectivity threshold extraction method involves binarizing the image above, setting 75% or more to 1 and the rest to 0, then traversing the entire image, calculating the number of neighboring points and the number of adjacent regions according to the coordinates of each point, sorting these adjacent regions from largest to smallest, and taking the largest region.

[0054] The inversion module is configured to perform inversion.

[0055] The dilation module is configured to perform pixel edge dilation.

[0056] The extraction module is configured to subtract the original image from the dilated image to obtain the image contour and extract the human body contour.

[0057] The calculation module is configured to calculate the coplanar matrix, center point and variance, find the direction vector of the image through the singular value decomposition method, calculate the angle between the human image axis and the X, Y and Z planes of space, and calculate the distance from the center point of the human image to the center point of space.

[0058] The overlap module is configured to make the axis vector of the human body image coincide with the axis vector of space, and the center point of the human body coincide with the center point of space.

[0059] Preferably, in the dilation module, the edge of the inverted image pixel is dilated by one pixel value, so that the contour of the human image target value is reduced by one layer, which is used to calculate the contour of the following image.

[0060] Preferably, in the extraction module, the pixel value is determined by judging the pixel value as the outermost layer of the human body contour.

[0061] Preferably, in the calculation module, the center point of the contour is obtained by summing all the contour points and taking the average. The center point of each layer is obtained by summing the contour points of each layer and taking the average. Then, the variance of the center point of each layer is calculated. A 3x3 symmetric matrix is ​​constructed using the variance. The eigenvector is calculated using singular value decomposition. The eigenvector of the human body axis is obtained from the first column of the calculated eigenvector. The angle between the human body axis and space is calculated using the line-plane angle formula.

[0062] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention shall still fall within the protection scope of the present invention.

Claims

1. An automatic adjustment method for the graphic position of pheochromocytoma / paraganglioma, characterized in that: It includes the following steps: (1) Import the image that needs to be adjusted; (2) Binarize the image; (3) Remove non-human image pixels by the maximum connectivity threshold extraction method; the maximum connectivity threshold extraction method is to binarize the above image, set 75% or more to 1 and the rest to 0, then traverse the entire image, calculate the number of adjacent points and the number of adjacent regions according to the coordinates of each point, sort these adjacent regions from largest to smallest, and take the largest region. (4) Reverse the process, and then use the maximum connected component extraction method; (5) Binarize the image; (6) Perform pixel edge dilation; (7) Subtract the original image from the dilated image to obtain the image outline; (8) Extract human body contours; (9) Calculate the coplanar matrix, center point, and variance; (10) Find the eigenvectors of the human body axis using the singular value decomposition method; (11) Calculate the angles between the human body image axis and the X, Y, and Z planes in space; (12) Calculate the distance from the center point of the human body image to the center point of the space; (13) Make the axis vector of the human body image coincide with the axis vector of space, and make the center point of the human body coincide with the center point of space; In step (9), the center point of the contour is obtained by adding up all the contour points and taking the average value. The center point of each layer is obtained by adding up the contour points of each layer and taking the average value. Then the variance of the center point of each layer is calculated. In step (10), a 3×3 symmetric matrix is ​​constructed using variance, and the eigenvectors are calculated using singular value decomposition. The first column of the calculated eigenvectors is used to obtain the eigenvectors of the human body axis.

2. The automatic adjustment method for the graphic position of pheochromocytoma / paraganglioma according to claim 1, characterized in that: In step (6), the edge of the reversed image pixel is expanded by one pixel value, so that the human image target value contour is reduced by one layer, which is used to calculate the contour of the following image.

3. The automatic adjustment method for the graphic position of pheochromocytoma / paraganglioma according to claim 2, characterized in that: In step (8), the pixel value is used to make a judgment. The obtained pixel value is the pixel of the outermost contour of the human body and is determined to be the human body contour value.

4. The automatic adjustment method for the graphic position of pheochromocytoma / paraganglioma according to claim 3, characterized in that: In step (11), the angle between the human body axis in the image and space is calculated using the line-plane angle formula.

5. The apparatus for automatically adjusting the position of pheochromocytoma / paraganglioma patterns according to claim 1, characterized in that: It includes: The data reading module is configured to import images that need to be adjusted. The data processing module is configured to binarize the image; The removal module is configured to remove non-human image pixels using the maximum connectivity threshold extraction method. The maximum connectivity threshold extraction method involves binarizing the image above, setting 75% or more to 1 and the rest to 0, then traversing the entire image, calculating the number of neighboring points and the number of adjacent regions according to the coordinates of each point, sorting these adjacent regions from largest to smallest, and taking the largest region. The inversion module is configured to perform inversion. The dilation module is configured to perform pixel edge dilation. The extraction module is configured to subtract the original image from the dilated image to obtain the image contour and extract the human body contour. The calculation module is configured to calculate the coplanar matrix, center point and variance, find the feature vector of the human body axis through the singular value decomposition method, calculate the angle between the human body image axis and the X, Y and Z planes of space, and calculate the distance from the center point of the human body image to the center point of space. The overlap module is configured to make the axis vector of the human body image coincide with the axis vector of space, and the center point of the human body coincide with the center point of space.

6. The apparatus for automatically adjusting the position of pheochromocytoma / paraganglioma patterns according to claim 5, characterized in that: In the dilation module, the edge of the inverted image pixel is dilated by one pixel value, so that the contour of the human image target value is reduced by one layer, which is used to calculate the contour of the following image.

7. The apparatus for automatically adjusting the position of pheochromocytoma / paraganglioma patterns according to claim 6, characterized in that: In the extraction module, the pixel value is used for judgment. The obtained pixel value is the pixel of the outermost contour of the human body and is determined to be the human body contour value.

Images