CN116934839A - Automatic adjustment method and device for graph position of pheochromocytoma/paraganglioma - Google Patents
Automatic adjustment method and device for graph position of pheochromocytoma/paraganglioma Download PDFInfo
- Publication number
- CN116934839A CN116934839A CN202310834140.8A CN202310834140A CN116934839A CN 116934839 A CN116934839 A CN 116934839A CN 202310834140 A CN202310834140 A CN 202310834140A CN 116934839 A CN116934839 A CN 116934839A
- Authority
- CN
- China
- Prior art keywords
- image
- human body
- contour
- space
- center point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 206010061332 Paraganglion neoplasm Diseases 0.000 title claims description 20
- 208000007312 paraganglioma Diseases 0.000 title claims description 20
- 208000028591 pheochromocytoma Diseases 0.000 title claims description 20
- 239000013598 vector Substances 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims abstract description 25
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims abstract description 13
- 230000008676 import Effects 0.000 claims abstract description 6
- 210000004072 lung Anatomy 0.000 abstract description 3
- 210000000056 organ Anatomy 0.000 abstract description 3
- 238000002591 computed tomography Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012285 ultrasound imaging Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000009206 nuclear medicine Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
Abstract
The invention imports the image to be adjusted; the image is binarized, so that the calculation and the processing of the image are convenient; removing non-human body image pixels by a maximum connected threshold extraction method; performing inversion for removing organs such as lungs, and then using a maximum connected domain extraction method; to ensure that the image is a binarized image in a later process, the image is binarized; performing pixel edge expansion; subtracting the original image from the inflated image to obtain an image contour; extracting the outline of a human body; calculating a coplanar matrix, a central point and a variance, finding out a direction vector of a picture through a singular value decomposition method, calculating angles of three sides of a human body image axis and a space X, Y, Z, and calculating a distance from the central point of the human body image to the central point of the space, so that the axis vector of the human body image and the axial vector of the space are overlapped, and the central point of the human body and the central point of the space are overlapped; therefore, the medical image with incorrect position can be returned to the opposite position, so that the user can watch more comfortably, and the subsequent operation is prevented from being influenced.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to an automatic adjustment method for a pheochromocytoma/paraganglioma graph position and an automatic adjustment device for the pheochromocytoma/paraganglioma graph position.
Background
Medical images are images reflecting the internal structure of the human body, and are one of the main bases of modern medical diagnosis. The object of medical image processing is medical imaging of various imaging mechanisms, and the medical imaging categories widely used clinically mainly include: x-ray imaging (X-CT), computed Tomography (CT), positron emission computed tomography (PET-CT), magnetic Resonance Imaging (MRI), nuclear Medicine Imaging (NMI), ultrasound Imaging (UI), pathological images taken under a microscope, and the like.
However, when acquiring medical images, the placement position is often incorrect for various reasons, which may cause trouble to the reading of the user and affect the subsequent operation.
Disclosure of Invention
In order to overcome the defects of the prior art, the technical problem to be solved by the invention is to provide an automatic adjustment method for the graph position of pheochromocytoma/paraganglioma, which can enable an incorrect medical image to return to the opposite position, so that a user can watch more comfortably, and the subsequent operation is prevented from being influenced.
The technical scheme of the invention is as follows: the automatic adjustment method of the pattern position of the pheochromocytoma/paraganglioma comprises the following steps:
(1) Importing an image to be adjusted;
(2) Binarizing the image;
(3) Removing non-human body image pixels by a maximum connected threshold extraction method; the maximum connected threshold extraction method is that the upper image is binarized, more than 75% is set to be 1, the other images are set to be 0, then the whole image is traversed, the number of adjacent points and the number of adjacent areas are calculated according to the coordinates of each point, the sizes of the adjacent areas are ordered from big to small, and the largest area is taken;
(4) Reversing and then using a maximum connected domain extraction method;
(5) Binarizing the image;
(6) Performing pixel edge expansion;
(7) Subtracting the original image from the inflated image to obtain an image contour;
(8) Extracting the outline of a human body;
(9) Calculating a coplanar matrix, a center point and a variance;
(10) Finding out the direction vector of the picture by a singular value decomposition method;
(11) Calculating the angles of the human body image axis and three sides of the space X, Y, Z;
(12) Calculating the distance from the center point of the human body image to the space center point;
(13) The axial vector of the human body image is overlapped with the axial vector of the space, and the center point of the human body is overlapped with the center point of the space.
The invention imports the image to be adjusted; the image is binarized, so that the calculation and the processing of the image are convenient; removing non-human body image pixels by a maximum connected threshold extraction method; performing inversion for removing organs such as lungs, and then using a maximum connected domain extraction method; to ensure that the image is a binarized image in a later process, the image is binarized; performing pixel edge expansion; subtracting the original image from the inflated image to obtain an image contour; extracting the outline of a human body; calculating a coplanar matrix, a central point and a variance, finding out a direction vector of a picture through a singular value decomposition method, calculating angles of three sides of a human body image axis and a space X, Y, Z, and calculating a distance from the central point of the human body image to the central point of the space, so that the axis vector of the human body image and the axial vector of the space are overlapped, and the central point of the human body and the central point of the space are overlapped; therefore, the medical image with incorrect position can be returned to the opposite position, so that the user can watch more comfortably, and the subsequent operation is prevented from being influenced.
Also provided is an automatic adjustment device for the pattern position of pheochromocytoma/paraganglioma, comprising:
a data reading module configured to import an image to be adjusted;
a data processing module configured to binarize the image;
a removal module configured to remove non-human image pixels by a maximum connected threshold extraction method; the maximum connected threshold extraction method is that the upper image is binarized, more than 75% is set to be 1, the other images are set to be 0, then the whole image is traversed, the number of adjacent points and the number of adjacent areas are calculated according to the coordinates of each point, the sizes of the adjacent areas are ordered from big to small, and the largest area is taken;
an inversion module configured to invert;
an expansion module configured to perform pixel edge expansion;
the extraction module is configured to subtract the original image from the expanded image to obtain an image contour and extract a human body contour;
the computing module is configured to compute a coplanar matrix, a central point and a variance, find out a direction vector of the picture through a singular value decomposition method, compute angles of a human body image axis and three sides of a space X, Y, Z, and compute a distance from the central point of the human body image to the central point of the space;
and a coincidence module configured to coincide an axial vector of the human body image with an axial vector of the space, and a center point of the human body with a center point of the space.
Drawings
FIG. 1 is a flow chart of a method for automatically adjusting the position of a pheochromocytoma/paraganglioma pattern according to the present invention.
Detailed Description
As shown in fig. 1, the automatic adjustment method of the pattern position of the pheochromocytoma/paraganglioma comprises the following steps:
(1) Importing an image to be adjusted;
(2) Binarizing the image;
(3) Removing non-human body image pixels by a maximum connected threshold extraction method; the maximum connected threshold extraction method is that the upper image is binarized, more than 75% is set to be 1, the other images are set to be 0, then the whole image is traversed, the number of adjacent points and the number of adjacent areas are calculated according to the coordinates of each point, the sizes of the adjacent areas are ordered from big to small, and the largest area is taken;
(4) Reversing and then using a maximum connected domain extraction method;
(5) Binarizing the image;
(6) Performing pixel edge expansion;
(7) Subtracting the original image from the inflated image to obtain an image contour;
(8) Extracting the outline of a human body;
(9) Calculating a coplanar matrix, a center point and a variance;
(10) Finding out the direction vector of the picture by a singular value decomposition method;
(11) Calculating the angles of the human body image axis and three sides of the space X, Y, Z;
(12) Calculating the distance from the center point of the human body image to the space center point;
(13) The axial vector of the human body image is overlapped with the axial vector of the space, and the center point of the human body is overlapped with the center point of the space.
The invention imports the image to be adjusted; the image is binarized, so that the calculation and the processing of the image are convenient; removing non-human body image pixels by a maximum connected threshold extraction method; performing inversion for removing organs such as lungs, and then using a maximum connected domain extraction method; to ensure that the image is a binarized image in a later process, the image is binarized; performing pixel edge expansion; subtracting the original image from the inflated image to obtain an image contour; extracting the outline of a human body; calculating a coplanar matrix, a central point and a variance, finding out a direction vector of a picture through a singular value decomposition method, calculating angles of three sides of a human body image axis and a space X, Y, Z, and calculating a distance from the central point of the human body image to the central point of the space, so that the axis vector of the human body image and the axial vector of the space are overlapped, and the central point of the human body and the central point of the space are overlapped; therefore, the medical image with incorrect position can be returned to the opposite position, so that the user can watch more comfortably, and the subsequent operation is prevented from being influenced.
Preferably, in the step (6), a pixel value is expanded at the edge of the pixel of the inverted image, so that the contour of the target image of the human body is one layer less, and the contour is used for calculating the following contour.
Preferably, in the step (8), the pixel value is determined by determining that the obtained pixel value is a layer of pixels of the outermost contour of the human body, and the obtained pixel value is determined as the contour value of the human body.
Preferably, in the step (9), all the contour points are added to the center point of the contour obtained by averaging, the center point of the contour of each layer is obtained by averaging after adding the contour points of each layer, and then the variance of the center point of each layer is calculated.
Preferably, in the step (10), a 3x3 symmetric matrix is made with variance, the eigenvectors are calculated by singular value decomposition, and the eigenvectors of the first column of the calculated eigenvectors are obtained as eigenvectors of the human body axis.
Preferably, in the step (11), the angle between the axis of the image body and the space is calculated using a line-plane angle formula.
It will be understood by those skilled in the art that all or part of the steps in implementing the above embodiment method may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, where the program when executed includes the steps of the above embodiment method, and the storage medium may be: ROM/RAM, magnetic disks, optical disks, memory cards, etc. Thus, in accordance with the method of the present invention, the present invention also includes an automatic adjustment device for the position of the pheochromocytoma/paraganglioma pattern, which device is generally represented in the form of functional blocks corresponding to the steps of the method. The device comprises:
a data reading module configured to import an image to be adjusted;
a data processing module configured to binarize the image;
a removal module configured to remove non-human image pixels by a maximum connected threshold extraction method; the maximum connected threshold extraction method is that the upper image is binarized, more than 75% is set to be 1, the other images are set to be 0, then the whole image is traversed, the number of adjacent points and the number of adjacent areas are calculated according to the coordinates of each point, the sizes of the adjacent areas are ordered from big to small, and the largest area is taken;
an inversion module configured to invert;
an expansion module configured to perform pixel edge expansion;
the extraction module is configured to subtract the original image from the expanded image to obtain an image contour and extract a human body contour;
the computing module is configured to compute a coplanar matrix, a central point and a variance, find out a direction vector of the picture through a singular value decomposition method, compute angles of a human body image axis and three sides of a space X, Y, Z, and compute a distance from the central point of the human body image to the central point of the space;
and a coincidence module configured to coincide an axial vector of the human body image with an axial vector of the space, and a center point of the human body with a center point of the space.
Preferably, in the expanding module, a pixel value is expanded at the edge of the pixel of the inverted image, so that the contour of the target image of the human body is one layer less, and the contour is used for calculating the following contour.
Preferably, in the extracting module, the pixel value is determined to be a human body contour value, and the obtained pixel value is a layer of pixels of the human body outermost contour.
Preferably, in the calculation module, all the contour points are added at a center point of the contour obtained by taking an average value, the contour points of each layer are added and then the average value is taken to obtain the center point of the contour of each layer, and then the variance of the center point of each layer is calculated; using variance to make a 3x3 symmetric matrix, using singular value decomposition to calculate feature vector, and calculating first column feature vector of result to obtain feature vector of human body axis; and calculating the angle between the human body axis of the image and the space by using a linear-surface angle formula.
The present invention is not limited to the preferred embodiments, but can be modified in any way according to the technical principles of the present invention, and all such modifications, equivalent variations and modifications are included in the scope of the present invention.
Claims (10)
1. The automatic adjustment method for the pattern position of the pheochromocytoma/paraganglioma is characterized by comprising the following steps of: which comprises the following steps:
(1) Importing an image to be adjusted;
(2) Binarizing the image;
(3) Removing non-human body image pixels by a maximum connected threshold extraction method; the maximum connected threshold extraction method is that the upper image is binarized, more than 75% is set to be 1, the other images are set to be 0, then the whole image is traversed, the number of adjacent points and the number of adjacent areas are calculated according to the coordinates of each point, the sizes of the adjacent areas are ordered from big to small, and the largest area is taken;
(4) Reversing and then using a maximum connected domain extraction method;
(5) Binarizing the image;
(6) Performing pixel edge expansion;
(7) Subtracting the original image from the inflated image to obtain an image contour;
(8) Extracting the outline of a human body;
(9) Calculating a coplanar matrix, a center point and a variance;
(10) Finding out the direction vector of the picture by a singular value decomposition method;
(11) Calculating the angles of the human body image axis and three sides of the space X, Y, Z;
(12) Calculating the distance from the center point of the human body image to the space center point;
(13) The axial vector of the human body image is overlapped with the axial vector of the space, and the center point of the human body is overlapped with the center point of the space.
2. The method for automatically adjusting the pattern position of pheochromocytoma/paraganglioma according to claim 1, wherein: in the step (6), a pixel value is expanded at the edge of the pixel of the inverted image, so that the contour of the target image value of the human body is reduced by one layer, and the contour is used for calculating the following contour.
3. The method for automatically adjusting the pattern position of pheochromocytoma/paraganglioma according to claim 2, wherein: in the step (8), the pixel value is determined to be a human body contour value, wherein the obtained pixel value is a layer of pixels of the human body outermost contour.
4. The method for automatically adjusting the pattern position of pheochromocytoma/paraganglioma according to claim 3, wherein: in the step (9), all the contour points are added to the center point of the contour obtained by taking the average value, the center point of the contour of each layer is obtained by taking the average value after adding the contour points of each layer, and then the variance of the center point of each layer is calculated.
5. The method for automatically adjusting the pattern position of pheochromocytoma/paraganglioma according to claim 4, wherein: in the step (10), a 3x3 symmetric matrix is made by using variance, a feature vector is calculated by using singular value decomposition, and a feature vector of a human body axis is obtained by calculating a first column of feature vectors of the result.
6. The method for automatically adjusting the pattern position of pheochromocytoma/paraganglioma according to claim 5, wherein: in the step (11), the angle between the human body axis of the image and the space is calculated by using a linear-surface angle formula.
7. The device for the automatic adjustment method of the pattern position of pheochromocytoma/paraganglioma according to claim 1, wherein: it comprises the following steps:
a data reading module configured to import an image to be adjusted;
a data processing module configured to binarize the image;
a removal module configured to remove non-human image pixels by a maximum connected threshold extraction method; the maximum connected threshold extraction method is that the upper image is binarized, more than 75% is set to be 1, the other images are set to be 0, then the whole image is traversed, the number of adjacent points and the number of adjacent areas are calculated according to the coordinates of each point, the sizes of the adjacent areas are ordered from big to small, and the largest area is taken;
an inversion module configured to invert;
an expansion module configured to perform pixel edge expansion;
the extraction module is configured to subtract the original image from the expanded image to obtain an image contour and extract a human body contour;
the computing module is configured to compute a coplanar matrix, a central point and a variance, find out a direction vector of the picture through a singular value decomposition method, compute angles of a human body image axis and three sides of a space X, Y, Z, and compute a distance from the central point of the human body image to the central point of the space;
and a coincidence module configured to coincide an axial vector of the human body image with an axial vector of the space, and a center point of the human body with a center point of the space.
8. The apparatus for the automatic adjustment method of the pattern position of pheochromocytoma/paraganglioma according to claim 7, wherein: in the expansion module, a pixel value is expanded at the edge of the pixel of the inverted image, so that the contour of the target image value of the human body is one layer less and is used for calculating the following contour.
9. The apparatus for the automatic adjustment method of the pattern position of pheochromocytoma/paraganglioma according to claim 8, wherein: in the extraction module, the pixel value is judged by the pixel value, and the obtained pixel value is a layer of pixels of the outermost contour of the human body and is judged to be the contour value of the human body.
10. The apparatus for the automatic adjustment method of the pattern position of pheochromocytoma/paraganglioma according to claim 9, wherein: in the calculation module, all the contour points are added to the center point of the contour obtained by taking the average value, the center point of the contour of each layer is obtained by taking the average value after the contour points of each layer are added, and then the variance of the center point of each layer is calculated; using variance to make a 3x3 symmetric matrix, using singular value decomposition to calculate feature vector, and calculating first column feature vector of result to obtain feature vector of human body axis; and calculating the angle between the human body axis of the image and the space by using a linear-surface angle formula.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310834140.8A CN116934839A (en) | 2023-07-07 | 2023-07-07 | Automatic adjustment method and device for graph position of pheochromocytoma/paraganglioma |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310834140.8A CN116934839A (en) | 2023-07-07 | 2023-07-07 | Automatic adjustment method and device for graph position of pheochromocytoma/paraganglioma |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116934839A true CN116934839A (en) | 2023-10-24 |
Family
ID=88393445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310834140.8A Pending CN116934839A (en) | 2023-07-07 | 2023-07-07 | Automatic adjustment method and device for graph position of pheochromocytoma/paraganglioma |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116934839A (en) |
-
2023
- 2023-07-07 CN CN202310834140.8A patent/CN116934839A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Keraudren et al. | Automated fetal brain segmentation from 2D MRI slices for motion correction | |
| US8761475B2 (en) | System and method for automatic recognition and labeling of anatomical structures and vessels in medical imaging scans | |
| US20060188139A1 (en) | Tree structure based 2D to 3D registration | |
| US20060110071A1 (en) | Method and system of entropy-based image registration | |
| US7711167B2 (en) | Fissure detection methods for lung lobe segmentation | |
| Kainz et al. | Fast fully automatic brain detection in fetal MRI using dense rotation invariant image descriptors | |
| Keraudren et al. | Localisation of the brain in fetal MRI using bundled SIFT features | |
| Furukawa et al. | Automatic liver segmentation method based on maximum a posterior probability estimation and level set method | |
| US8244007B2 (en) | System and method for registration of medical images based on insufficiently similar image areas | |
| CN111932495B (en) | Medical image detection method, device and storage medium | |
| Prevost et al. | Kidney detection and real-time segmentation in 3D contrast-enhanced ultrasound images | |
| Moradi et al. | Deformable registration using scale space keypoints | |
| US11551371B2 (en) | Analyzing symmetry in image data | |
| CN116309647B (en) | Method for constructing craniocerebral lesion image segmentation model, image segmentation method and device | |
| Uchiyama et al. | Automated classification of cerebral arteries in MRA images and its application to maximum intensity projection | |
| CN112634280B (en) | MRI image brain tumor segmentation method based on energy functional | |
| CN116934839A (en) | Automatic adjustment method and device for graph position of pheochromocytoma/paraganglioma | |
| Oguz et al. | Minimally interactive placenta segmentation from three-dimensional ultrasound images | |
| Linguraru et al. | Multi-organ automatic segmentation in 4D contrast-enhanced abdominal CT | |
| Noble et al. | Myocardial delineation via registration in a polar coordinate system | |
| CN114373216A (en) | Eye movement tracking method, device, equipment and storage medium for anterior segment OCTA | |
| CN111080572A (en) | White matter high signal positioning method, device, equipment and storage medium | |
| Butman et al. | Assessment of ventricle volume from serial MRI scans in communicating hydrocephalus | |
| Dima et al. | A local level set method for liver segmentation in functional MR imaging | |
| Hopp et al. | Image registration of diffusion weighted and conventional breast MRI |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |