CN107221009B - Method and device for positioning abdominal aorta bifurcation, medical imaging system and storage medium - Google Patents
Method and device for positioning abdominal aorta bifurcation, medical imaging system and storage medium Download PDFInfo
- Publication number
- CN107221009B CN107221009B CN201710400073.3A CN201710400073A CN107221009B CN 107221009 B CN107221009 B CN 107221009B CN 201710400073 A CN201710400073 A CN 201710400073A CN 107221009 B CN107221009 B CN 107221009B
- Authority
- CN
- China
- Prior art keywords
- image
- abdominal aorta
- bifurcation
- determining
- pixel 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/77—Determining position or orientation of objects or cameras using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The embodiment of the invention provides a method and a device for positioning an abdominal aorta bifurcation, a medical imaging system and a storage medium, wherein the method comprises the following steps: determining a position area containing an abdominal aorta bifurcation in an image to be detected; calculating the probability value of each pixel point contained in the position area as a pixel point at the bifurcation of the abdominal aorta; and determining the position of the abdominal aorta bifurcation according to the probability value of each pixel point at the abdominal aorta bifurcation. By adopting the technical scheme, the embodiment of the invention can ensure the positioning accuracy, and has high positioning speed and high positioning efficiency.
Description
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to a method and a device for positioning an abdominal aorta bifurcation, a medical imaging system and a storage medium.
Background
The medical imaging technology refers to a technology of scanning a scanned object through related equipment to obtain related scanning data, and then obtaining object shape information through digital processing, and in medical research and clinical medicine, doctors or technicians can perform better disease diagnosis and treatment on patients through medical images.
Vascular calcification (vascular calcification) is the pathological manifestation of atherosclerosis, hypertension, vascular injury and other diseases, the rupture of calcified plaques is one of the important factors of high morbidity and high mortality of cardiovascular and cerebrovascular diseases, and the abdominal aorta bifurcation is a high incidence point of plaque calcification. In the situations of Transcatheter Aortic Valve Implantation (TAVI), aortic aneurysm stent planning, and the like, the positioning of the abdominal aortic bifurcation has a very important role, and based on the positioning of the abdominal aortic bifurcation, the subsequent calculation of the diameter and the cross-sectional area of the blood vessel at the position can be performed, and the calcification of plaque at the position can be analyzed, so that the feasibility of stent Implantation in surgery can be judged, for example, whether the blood vessel at the abdominal aortic bifurcation is too narrow or not, and the stent may not normally pass through; or calcification of the plaque, there may be a risk of causing plaque to shed when the stent is placed. At present, when the position of the abdominal aorta bifurcation is determined, a doctor or a technician usually judges and determines the position of the abdominal aorta bifurcation by human eyes according to a medical image, the influence of subjective judgment of the doctor or the technician is easily caused, the positioning speed is slow, the operation of the doctor or the technician is inconvenient, and the practicability is poor.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for positioning an abdominal aorta bifurcation, a medical imaging system and a storage medium, so as to solve the technical defects of slow positioning speed, inconvenience for a doctor or a technician to operate, and poor practicability of the existing positioning technology for the abdominal aorta bifurcation.
In a first aspect, an embodiment of the present invention provides a method for positioning an abdominal aorta bifurcation, including:
determining a position area containing an abdominal aorta bifurcation in an image to be detected;
calculating the probability value of each pixel point contained in the position area as a pixel point at the bifurcation of the abdominal aorta;
and determining the position of the abdominal aorta bifurcation according to the probability value of each pixel point at the abdominal aorta bifurcation.
In a second aspect, an embodiment of the present invention further provides a positioning device for an abdominal aorta bifurcation, including:
the position area determining module is used for determining a position area containing an abdominal aorta bifurcation in the image to be detected;
the probability calculation module is used for calculating the probability value that each pixel point contained in the position area is a pixel point at the abdominal aorta bifurcation;
and the positioning module is used for determining the position of the abdominal aorta bifurcation according to the probability value of each pixel point being the pixel point at the abdominal aorta bifurcation.
In a third aspect, an embodiment of the present invention further provides a medical imaging system, including:
and the acquisition device is used for acquiring images of the patient.
And the display device is used for displaying the image and the editing interface.
An image processing device for executing a computer program, the computer program executing the method for positioning an abdominal aorta bifurcation according to any one of the embodiments of the present invention.
In a fourth aspect, embodiments of the present invention further provide a computer-readable storage medium configured to store an executable program for performing the method for positioning an abdominal aortic bifurcation described in any one of the embodiments of the present invention.
According to the technical scheme provided by the embodiment of the invention, the position area containing the abdominal aorta bifurcation is determined in the image to be detected, coarse positioning is realized, then probability calculation is carried out on all pixel points contained in the position area, the position of the abdominal aorta bifurcation is determined according to the calculation result, and fine positioning is realized.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the contents of the embodiments of the present invention and the drawings without creative efforts.
Fig. 1a is a schematic flow chart of a method for positioning an abdominal aorta bifurcation according to an embodiment of the present invention;
fig. 1b is a schematic diagram of a three-dimensional image to be detected according to the first embodiment;
fig. 2a is a schematic flow chart of a method for positioning an abdominal aorta bifurcation according to a second embodiment of the present invention;
FIG. 2b is a schematic diagram of a first projection image according to a second embodiment of the present invention;
FIG. 2c is a schematic diagram of a second projection image according to the second embodiment of the present invention;
fig. 3 is a schematic flowchart of a method for positioning an abdominal aorta bifurcation according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a positioning device for an abdominal aorta bifurcation provided in the fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the steps as a sequential process, many of the steps can be performed in parallel, concurrently or simultaneously. In addition, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1a is a schematic flow chart of a method for positioning an abdominal aorta bifurcation according to an embodiment of the present invention. The method may be performed by a positioning device at the abdominal aortic bifurcation, which may be implemented by software and/or hardware, and may generally be integrated in a medical imaging apparatus. As shown in fig. 1a, the method may comprise the steps of:
step 110, determining a position area containing the abdominal aorta bifurcation in the image to be detected.
For example, the image to be detected may be a reconstructed CT image or an MRI image, and specifically, the image to be detected may be a three-dimensional image reconstructed from a plurality of image sequences. As shown in fig. 1b, a schematic diagram of a three-dimensional image to be detected provided in this embodiment is specifically a three-dimensional reconstructed image of a thoracic abdomen of a human body, and a position indicated by an arrow in fig. 1b is an approximate position of a bifurcation of an abdominal aorta. In the image to be detected, an image of a position region including the bifurcation of the abdominal aorta may be cut out from the image based on an empirical value, for example, an image in the range of 1/3 to 2/3 of the horizontal direction length of the image to be detected is cut out as the position region.
And 120, calculating the probability value of each pixel point contained in the position area as a pixel point at the abdominal aorta bifurcation.
Illustratively, according to the CT values of the pixels and the corresponding structural position information, etc., the probability value of each pixel included in the position area being a pixel at the bifurcation of the abdominal aorta is calculated.
And step 130, determining the position of the abdominal aorta bifurcation according to the probability value of each pixel point being the pixel point at the abdominal aorta bifurcation.
For example, the calculated probability values of the pixel points at the abdominal aorta bifurcation are compared, and according to the comparison result, the position of the abdominal aorta bifurcation is determined, for example, the position of the pixel point with the maximum calculated probability value is determined as the position of the abdominal aorta bifurcation.
According to the technical scheme provided by the embodiment, the position area containing the abdominal aorta bifurcation is determined in the image to be detected, the rough positioning of the abdominal aorta bifurcation is realized, then the specific position of the abdominal aorta bifurcation is determined according to the probability value of each pixel point in the calculated position area as the pixel point of the abdominal aorta bifurcation, the fine positioning of the abdominal aorta bifurcation is realized, the positioning accuracy can be ensured, the positioning speed is high, the positioning efficiency is high, the operation of a doctor or a technician is greatly simplified, and the practicability is good.
Example two
Fig. 2a is a schematic flow chart of a method for positioning an abdominal aorta bifurcation according to a second embodiment of the present invention. The present embodiment is based on the first embodiment, and optimizes "determining the location area including the abdominal aorta bifurcation" in the image to be detected, as shown in fig. 2a, the method may include the following steps:
Typically, when a medical imaging system is used to scan a patient, a corresponding scanning coordinate system may be established, generally, the head and foot direction of the human body is set as a Z axis, the front and back direction of the human body is set as a Y axis, and the left and right direction of the human body is set as an X axis, and the coronal plane may be understood as a cross section obtained by longitudinally cutting the human body into two parts, i.e., an XZ in-plane image, along the left and right direction of the human body.
Illustratively, as shown in fig. 1b, a coronal view of a three-dimensional image of a human thorax and abdomen is projected on a coronal plane, that is, the three-dimensional image in fig. 1b is projected inward or outward along the paper surface, and a corresponding projection image is obtained.
Specifically, taking a CT image as an example, a pixel point in the image to be detected shown in fig. 1b is projected along a pixel line where a CT value reaches a preset threshold, and if at least one pixel point with a CT value reaching the preset threshold exists in the pixel line, a gray value of a projection pixel point corresponding to the pixel point is set to 1; if there is no pixel point with a CT value reaching a preset threshold in the pixel row, the gray value of the projection pixel point corresponding to the pixel point is set to 0, the preset threshold may be set to be a CT value of 400, and the projection calculation is performed on all the pixel points included in fig. 1b to obtain a projection image of the image to be detected on the coronal plane, as shown in fig. 2b, which is a first projection image schematic diagram provided in the second embodiment of the present invention.
And step 220, performing traversal statistics on the first projection image, and determining the position information of the upper edge of the ilium in the image to be detected according to the statistical result.
Illustratively, the traversal statistics is performed on the pixel points included in the first projection image, taking the projection image shown in fig. 2b as an example, the number of the pixel points with the gray value of 1 in the pixel points included in each pixel row in the horizontal direction is counted, a preset number threshold may be set, and if the total number of the pixel points with the gray value of 1 in a certain pixel row obtained through the traversal statistics satisfies the preset number threshold, the pixel row is determined as the pixel row position on the upper edge of the ilium, where the preset number threshold may be determined according to the sample statistics. As shown in fig. 2b, the position indicated by the arrow is the approximate position of the upper iliac edge, and the position information of the upper iliac edge in the image to be detected, such as the Z-coordinate position of the upper iliac edge, is determined by determining the position information of the upper iliac edge in the second projection image.
In addition, before performing traversal statistics on the first projection image, the first projection image may be cut according to a preset range, for example, an image in a range from 1/3 to 2/3 in the vertical direction of the image shown in fig. 2b is cut to obtain an image sub-region including the upper iliac edge, and then, traversal statistics is performed on the image sub-region to further improve the positioning speed for determining the upper iliac edge.
In an optional implementation manner of this embodiment, performing traversal statistics on the first projection image, and determining the position information of the upper iliac edge in the image to be detected according to the statistical result may further include:
and A, removing the spine region image contained in the first projection image to obtain a second projection image.
Illustratively, the area of spinal concentration may be determined empirically, for example, by determining the area 3 cm to the left and right of the horizontal center position of fig. 2b as the spinal area, or by determining the range 1/3 to 2/3 of the horizontal length of the image shown in fig. 2b as the spinal area, and cutting out the determined spinal area in the image shown in fig. 2b to obtain a second projection image, which is schematically shown in fig. 2c and provided for the second embodiment of the present invention.
And B, counting the number of pixels of each pixel line in the second projection image according to a preset rule.
For example, for the image shown in fig. 2c, the number of pixels having a gray value of 1 in each pixel row is counted sequentially from bottom to top in units of pixel rows in the horizontal direction.
And step C, determining the position information of the upper edge of the ilium in the image to be detected according to the statistical result and a preset threshold value.
Illustratively, the position information of the upper iliac edge in the second projection image is determined according to the comparison between the statistical result and the preset number threshold, and further the position information of the upper iliac edge in the image to be detected is correspondingly obtained.
Specifically, the preset threshold may be set to a specific numerical value or a range value, taking fig. 2c as an example, the preset threshold may be set to 20, the number of pixels with a gray value of 1 in each pixel row is counted from bottom to top line by line, each time a pixel row is counted, the counted result of the pixel row is compared with the preset threshold, when the number of pixels counted for a certain pixel row is less than 20, the pixel row is determined as the position of the superior iliac edge, and counting for subsequent pixel rows is stopped.
In the image shown in fig. 2b, since the number of pixel points in the spine region is relatively small, interference may be caused to the determination of the position of the upper iliac edge, the accuracy of the determined position of the upper iliac edge can be improved by removing the spine region, the data volume is reduced in the statistical process, and the positioning speed of the upper iliac edge is increased.
And step 230, determining a region with a preset distance range from the upper iliac edge upwards and/or downwards as the position region according to the position information of the upper iliac edge and the preset distance range.
For example, the preset distance range may be determined according to an empirical value, and in the example of fig. 1b, the preset distance range may include a first preset distance range and a second preset distance range, for example, the first preset distance range may be 10 centimeters, the second preset distance range may be 5 centimeters, and a three-dimensional image area within a range of 10 centimeters upwards and 5 centimeters downwards from the iliac bone in the Z direction in fig. 1b is determined as the position area based on the Z coordinate of the iliac bone upper edge.
If the information on the iliac upper edge included in the thoracic-abdominal image is small or absent, a region of 10 cm in the positive Z-axis direction (foot-head direction) is set as the position region, and the set distance range is related to the relative positions of the iliac region and the abdominal aorta bifurcation included in the three-dimensional image. Based on the clinical experience of a doctor or a technician, the three-dimensional image of the chest and the abdomen can be divided according to the more common image information of the iliac bones and the abdominal aorta bifurcation, and the preset distance range corresponding to each category is set.
And 240, calculating the probability value of each pixel point contained in the position area as a pixel point at the abdominal aorta bifurcation.
And step 250, determining the position of the abdominal aorta bifurcation according to the probability value of each pixel point being the pixel point at the abdominal aorta bifurcation.
According to the technical scheme provided by the embodiment, the three-dimensional image to be detected is projected, the position information of the upper edge of the ilium in the image to be detected is determined according to the obtained projection image, the position of the upper edge of the ilium is used as a reference, the preset distance range is set, the rough positioning of the abdominal aorta bifurcation is realized, the effectiveness of the determined position area is ensured, the accuracy of the subsequently determined abdominal aorta bifurcation is improved, the relative fixity of the abdominal aorta bifurcation relative to the position of the upper edge of the ilium can be utilized, the position area image range with the abdominal aorta bifurcation image and the proper range is determined, the data volume of subsequent processing is reduced, and the positioning speed is improved.
Further, after the second projection image is obtained, connected component calculation may be performed. Connected components are visually understood to be one region formed by points that are connected to one another, while unconnected points form a different region, e.g., pixels A, B and C are spatially adjacent to one another to form connected component M, pixels E and F are spatially adjacent to one another but not to either of pixels A, B and C, and E and F form another connected component N.
Illustratively, small connected component calculation is performed in the second projection image, a plurality of connected components in the second projection image and the number of pixel points included in each connected component can be obtained, the obtained connected components are screened by setting a threshold, if the threshold is set to be 20, the small connected components with the number of the pixel points less than 20 in the obtained connected components are removed from the second projection image, a third projection image is obtained, subsequent traversal statistics is performed on the third image, and then the position of the upper iliac edge is determined, the influence of the small connected components on the subsequent traversal statistics can be eliminated, the accuracy of the determined position of the upper iliac edge is ensured, and the accuracy of the positioning of the abdominal aorta bifurcation is further ensured.
EXAMPLE III
Fig. 3 is a flowchart illustrating a method for positioning an abdominal aorta bifurcation according to a third embodiment of the present invention. Based on the above embodiments, the present embodiment optimizes "calculating probability values of the pixel points included in the location area as the pixel points at the bifurcation of the abdominal aorta", as shown in fig. 3, the method may include the following steps:
For example, a positive sample may be understood as a sample belonging to a certain category, and a negative sample may be understood as a sample not belonging to the category. The bifurcation of the abdominal aorta can be understood as the intersection position of the abdominal aorta and the left and right iliac arteries, usually the intersection connection of the three arteries is a line, for example, called a cross line, and the determined bifurcation of the abdominal aorta is a certain point with the highest possibility among the pixel points included in the cross line. In this embodiment, the positive samples may be pixel points belonging to an abdominal aorta intersection, and the negative samples may be pixel points not belonging to an abdominal aorta intersection, and it can be understood that any pixel point which easily affects identification of an abdominal aorta bifurcation in a three-dimensional image of a thoracic region and an abdominal region may be selected as a negative sample, for example, a pixel point at a renal artery bifurcation position.
Illustratively, a plurality of thoracic and abdominal three-dimensional images are collected as sample images, and a plurality of positive sample pixel points and negative sample pixel points are selected from each sample image, for example, in each sample image, about 10 positive sample pixel points can be selected in a small range of an abdominal aorta cross line, and about 60 negative sample pixel points can be selected in a range not belonging to the abdominal aorta cross line, wherein the positive sample pixel points and the negative sample pixel points can be extracted from the thoracic and abdominal three-dimensional images in a manual, semi-automatic or automatic manner.
And 330, training a classifier according to the training samples to obtain a target classifier.
For example, the determined positive samples and the determined negative samples are input into a classifier for sample training, and the trained classifier is determined as a target classifier, wherein the classifier can be trained by using an Adaboost algorithm, a Probabilistic Boosting Tree (PBT) algorithm, or a random forest algorithm.
In an optional implementation manner of this embodiment, the performing classifier training according to the training samples to obtain a target classifier may include:
according to the training sample, carrying out Adaboost classifier training to obtain a plurality of weak classifiers;
and combining the weak classifiers according to a preset rule to obtain the target classifier.
Illustratively, in the three-dimensional image of the chest and abdomen, 3D-like Haar-like features including the positive sample and the negative sample are selected, the Haar features are feature descriptors commonly used for identifying objects, the Haar features are suitable for tracking objects with stable structures, and the training speed by using the features is faster than that by simply using pixel points. And calculating the Haar characteristic value of each selected Haar-like characteristic, and selecting effective Haar characteristics based on an Adaboost algorithm, wherein each effective Haar characteristic corresponds to one weak classifier.
Specifically, the step of obtaining a single weak classifier by training samples may be: assuming that k 3D-like Haar-like features are counted for a sample x, and then the features are abbreviated as Haar features, one Haar feature t is selected, m positive sample points and n negative sample points are selected from the sample image, wherein m and n can be equal or unequal, and the feature value f of all training sample points in the sample x relative to the feature t is calculatedt(x) And selecting a threshold value theta related to the characteristic ttAnd an offset character PtWherein the offset character PtFor controlling the sign direction, P, in the following weak classifier calculation formula (1)tThe value can be 1 or-1, when ft(x)>θtSeason PtIs 1 when ft(x)<θtSeason PtTo-1, the calculation formula of the weak classifier is shown in formula (1):
by calculating the characteristic value f of each sample point with respect to the characteristic tt(x) The obtained characteristic values are arranged according to ascending order and are respectively marked as ft(1)，ft(2)……ft(m + n) and selecting the optimal threshold value thetatAs the watershed of classification, the classification error of positive and negative sample classification of all training samples by using the characteristic t is minimized, wherein the threshold value thetatIs selected in relation to a minimum misclassification rate etIs shown in formula (2):
where min represents the minimum value of the function, Tt+Represents the sum of the weights of all positive samples, Tt-Representing the sum of the weights of all negative examples, St+Is at thetatAll characteristic values below the threshold are less than thetatPositive sample weight of, St-Is at thetatAll characteristic values below the threshold value are less thanθtNegative sample weight sum.
In the initial state, all samples are given equal weight values according to the minimum misclassification rate etDetermining an optimum threshold value thetat，θtThe corresponding characteristic t is an effective Haar characteristic, and the effective Haar characteristic corresponds to a weak classifier h (x), namely the weak classifier obtained through training.
It should be noted that, along with the training process, the weak classifier obtained by training can be used to determine whether the positive and negative samples are accurately classified, and if a certain pixel is accurately classified, the weight of the pixel will be reduced in the next training; if a certain pixel is wrongly classified, the weight of the pixel is increased in the next training, so as to obtain a new sample distribution. That is, in each iteration, normalization processing needs to be performed on the weights of all the positive samples and the negative samples according to the training result of the previous iteration, and the weights of all the pixel points are normalized according to the following formula (3).
Wherein q isT(j) Represents the new weight of the jth sample in the Tth iteration, n represents the number of samples, T represents the number of iterations, ωT(j) Representing the weight of the jth sample in the T iteration.
Traversing all the characteristics and utilizing the optimal weak classifier h (x, f) containing one Haar characteristic selected in the processt,Pt,θt) Calculating the weighted error classification rate of the weak classifier to m + n samples according to the formula (4), and finding out the error rate epsilon corresponding to each weak classifier group with effective Haar characteristicstMinimum weak classifier hjAnd selecting the corresponding characteristic t.
The weights of the next round of training samples are then updated
Wherein
If the sample is correctly classified ejIf the text is misclassified as 0, ej1. According to the AdaBoost iterative algorithm, R Haar features are obtained through R-round iteration, wherein R selection can be 60 in the embodiment.
Further, combining R weak classifiers obtained after R training passes and weights thereof together to form a strong classifier, for example, cascading a plurality of strong classifiers to form an Adaboost cascade classifier h (x), where the expression of the strong classifier h (x) is shown in formula (5).
Wherein the content of the first and second substances,
if h (x) is 1, the sample point is classified as a positive sample, i.e., a point on the abdominal aorta bifurcation, and if h (x) is 0, the sample point is classified as a negative sample, i.e., a point on the abdominal aorta bifurcation, αtThe weight assigned to the weak classifier corresponding to the effective Haar feature t represents the performance of the weak classifier, and a smaller weight represents a smaller role of the weak classifier in the final strong classifier, and a larger weight represents a larger role of the weak classifier in the final strong classifier. For a single weak classifier, the classification accuracy is relatively low, but the accuracy of the obtained strong classifier can be effectively improved by giving different weights to each weak classifier and combining the weak classifiers into the strong classifier.
Illustratively, after the target classifier is determined, all pixel points in the position area are input into the target classifier, and the probability value that each pixel point is a pixel point at the bifurcation of the abdominal aorta is calculated, wherein a specific calculation formula is shown in formula (6).
Wherein h ist(x) A weak classifier for a sample x in the location area image corresponding to the valid Haar feature t, αtRepresenting the corresponding weight of each weak classifier, and vessel (x) representing the probability that the sample x is the pixel point at the bifurcation of the abdominal aorta, wherein the sample x is selected as the pixel point x of the sample.
And 350, determining the position of the abdominal aorta bifurcation according to the probability value of each pixel point being the pixel point at the abdominal aorta bifurcation.
For example, the position of the abdominal aorta bifurcation can be determined by comparing the probability value of each pixel point being the pixel point at the abdominal aorta bifurcation with a preset threshold, for example, the preset threshold can be determined by
Calculating, namely comparing the probability value of each pixel point in the position region, which is the pixel point at the abdominal aorta bifurcation, with the threshold value, determining the pixel point with the maximum probability value in all the pixel points with the probability value reaching the threshold value in the position region as the pixel point at the abdominal aorta bifurcation, and determining the position of the abdominal aorta bifurcation according to the position of the pixel point; if the probability values of all the pixel points contained in the position area, namely the pixel points at the abdominal aorta bifurcation, do not reach the threshold value, the fact that the abdominal aorta bifurcation does not exist in the position area is indicated.
According to the technical scheme, the sample image is used for extracting the positive samples and the negative samples and carrying out classifier training, the probability value that the pixel points in the position area are the abdominal aorta bifurcation is calculated according to the target classifier obtained by training, the position of the abdominal aorta bifurcation is further determined, the accuracy of positioning the abdominal aorta bifurcation can be further improved, the positioning speed is high, and the positioning efficiency is high.
Example four
Fig. 4 is a schematic structural diagram of a positioning device for an abdominal aorta bifurcation provided in the fourth embodiment of the present invention. The apparatus may be implemented in software and/or hardware, typically integrated in a medical imaging device, and may construct a protocol suite by performing a localization method at the abdominal aortic bifurcation. As shown in fig. 4, the apparatus may include: a location area determination module 410, a probability calculation module 420, and a location module 430.
The position area determining module 410 is configured to determine a position area including an abdominal aorta bifurcation in an image to be detected;
a probability calculation module 420, configured to calculate a probability value that each pixel included in the location area is a pixel at an abdominal aorta bifurcation;
and the positioning module 430 is configured to determine the location of the bifurcation of the abdominal aorta according to the probability value that each pixel is a pixel at the bifurcation of the abdominal aorta.
According to the technical scheme provided by the embodiment, the position area containing the abdominal aorta bifurcation is determined in the image to be detected, so that the coarse positioning of the abdominal aorta bifurcation is realized, then the specific position of the abdominal aorta bifurcation is determined according to the probability value of each pixel point in the calculated position area as the pixel point of the abdominal aorta bifurcation, the fine positioning of the abdominal aorta bifurcation is realized, the positioning accuracy can be guaranteed, the positioning speed is high, and the positioning efficiency is high.
On the basis of the above embodiment, the location area determining module 410 may include:
the projection unit is used for projecting the image to be detected on a coronal plane to obtain a first projection image;
the coarse positioning unit is used for performing traversal statistics on the first projection image and determining the position information of the upper edge of the ilium in the image to be detected according to a statistical result;
and the position area determining unit is used for determining an area of the upper iliac edge within the preset distance range upwards and/or downwards as the position area according to the position information of the upper iliac edge and the preset distance range.
On the basis of the foregoing embodiments, the coarse positioning unit may include:
the projection subunit is used for removing the spine region image contained in the first projection image to obtain a second projection image;
the calculating subunit is used for counting the number of pixels of each pixel row in the second projection image according to a preset rule;
and the coarse positioning subunit is used for determining the position information of the upper edge of the ilium in the image to be detected according to the statistical result and a preset threshold value.
On the basis of the foregoing embodiments, the probability calculation module 420 may include:
a sample determining unit, configured to determine a training sample according to a sample image including an abdominal aorta bifurcation, where the training sample includes a number of positive samples and negative samples;
the training unit is used for carrying out classifier training according to the training samples to obtain a target classifier;
and the probability calculation unit is used for calculating the probability value of each pixel point contained in the position area as a pixel point at the abdominal aorta bifurcation based on the target classifier.
On the basis of the foregoing embodiments, the training unit may include:
the first training subunit is used for carrying out Adaboost classifier training according to the training samples to obtain a plurality of weak classifiers;
and the second training subunit is used for combining the weak classifiers according to a preset rule to obtain the target classifier.
EXAMPLE five
This embodiment provides a medical imaging system, and the system may include: collection system, display device and image processing device.
Wherein, the collection system is used for collecting images of patients.
And the display device is used for displaying an editing interface for adjusting the reconstruction range parameters, and the editing interface is used for displaying the generated preview image.
The image processing device may integrate the positioning device for an abdominal aorta bifurcation provided in the embodiments of the present invention, and is used to run a computer program, and when the computer program runs, the positioning method for an abdominal aorta bifurcation provided in all embodiments of the present invention is implemented.
Illustratively, the medical imaging system in this embodiment may be a CT imaging system, such as CT angiography (CTA).
When a user uses the medical imaging system in the embodiment to position the abdominal aorta bifurcation, the imaging system can determine a position area containing the abdominal aorta bifurcation in an image to be detected, realize coarse positioning, calculate the probability value that each pixel point contained in the position area is the pixel point of the abdominal aorta bifurcation, determine the position of the abdominal aorta bifurcation according to the calculated probability value that each pixel point is the pixel point of the abdominal aorta bifurcation, realize fine positioning, ensure the accuracy of positioning the abdominal aorta bifurcation, greatly improve the positioning speed and strive for precious time for subsequent treatment.
The positioning device and the medical imaging system for the abdominal aorta bifurcation provided in the above embodiments can perform the positioning method for the abdominal aorta bifurcation provided in any embodiment of the present invention, and have corresponding functional modules and beneficial effects for performing the method. The technical details not described in detail in the above embodiments can be referred to the method for positioning the abdominal aortic bifurcation provided by any embodiment of the present invention.
EXAMPLE six
The sixth embodiment provides a computer-readable storage medium configured to store an executable program, which when executed by a processor, implements the method for positioning an abdominal aorta bifurcation provided by all embodiments of the present invention:
namely: the program when executed by a processor implements: determining a position area containing an abdominal aorta bifurcation in an image to be detected; calculating the probability value of each pixel point contained in the position area as a pixel point at the bifurcation of the abdominal aorta; and determining the position of the abdominal aorta bifurcation according to the probability value of each pixel point at the abdominal aorta bifurcation.
Any combination of one or more computer-readable media may be employed. The computer readable storage medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable storage medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. The computer readable storage medium can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (5)
1. A method of locating an abdominal aortic bifurcation, comprising:
determining a position area containing an abdominal aorta bifurcation in an image to be detected;
calculating the probability value of each pixel point contained in the position area as a pixel point at the bifurcation of the abdominal aorta;
determining the position of the abdominal aorta bifurcation according to the probability value of each pixel point being the pixel point at the abdominal aorta bifurcation;
the step of determining the position area containing the abdominal aorta bifurcation in the image to be detected comprises the following steps:
projecting the image to be detected on a coronal plane to obtain a first projection image;
removing a spine region image contained in the first projection image to obtain a second projection image;
counting the number of pixels of each pixel line in the second projection image according to a preset rule;
determining the position information of the upper edge of the ilium in the image to be detected according to the statistical result and a preset threshold value;
determining a region with a preset distance range upwards and/or downwards from the upper iliac edge as the position region according to the position information of the upper iliac edge and the preset distance range;
the calculating the probability value that each pixel point contained in the position area is a pixel point at the bifurcation of the abdominal aorta comprises the following steps:
determining a training sample according to a sample image containing an abdominal aorta bifurcation, wherein the training sample comprises a plurality of positive samples and negative samples;
performing classifier training according to the training samples to obtain a target classifier;
calculating the probability value of each pixel point contained in the position area as a pixel point at the abdominal aorta bifurcation based on the target classifier;
after obtaining the second projection image, the method further includes:
performing connected domain calculation on the second projection image to obtain at least one connected domain in the second projection image and the number of pixel points contained in each connected domain;
and screening the connected domains based on a set threshold value to obtain a third projection image so as to traverse the third projection image and determine the position area.
2. The method of claim 1, wherein performing classifier training based on the training samples to obtain a target classifier comprises:
according to the training sample, carrying out Adaboost classifier training to obtain a plurality of weak classifiers;
and combining the weak classifiers according to a preset rule to obtain the target classifier.
3. A positioning device for an abdominal aortic bifurcation, comprising:
the position area determining module is used for determining a position area containing an abdominal aorta bifurcation in the image to be detected;
the probability calculation module is used for calculating the probability value that each pixel point contained in the position area is a pixel point at the abdominal aorta bifurcation;
the positioning module is used for determining the position of the abdominal aorta bifurcation according to the probability value of each pixel point being the pixel point at the abdominal aorta bifurcation;
the location area determination module comprises:
the projection unit is used for projecting the image to be detected on a coronal plane to obtain a first projection image;
the coarse positioning unit is used for performing traversal statistics on the first projection image and determining the position information of the upper edge of the ilium in the image to be detected according to a statistical result;
the position region determining unit is used for determining a region with a preset distance range from the upper iliac edge upwards and/or downwards as the position region according to the position information of the upper iliac edge and the preset distance range;
the coarse positioning unit is further used for removing a spine region image contained in the first projection image to obtain a second projection image;
counting the number of pixels of each pixel line in the second projection image according to a preset rule;
determining the position information of the upper edge of the ilium in the image to be detected according to the statistical result and a preset threshold value;
the probability calculation module comprises:
a sample determining unit, configured to determine a training sample according to a sample image including an abdominal aorta bifurcation, where the training sample includes a number of positive samples and negative samples;
the training unit is used for carrying out classifier training according to the training samples to obtain a target classifier;
a probability calculation unit, configured to calculate, based on the target classifier, a probability value that each pixel included in the location region is a pixel at an abdominal aorta bifurcation;
the location area determination unit is further configured to:
performing connected domain calculation on the second projection image to obtain at least one connected domain in the second projection image and the number of pixel points contained in each connected domain;
and screening the connected domains based on a set threshold value to obtain a third projection image so as to traverse the third projection image and determine the position area.
4. A medical imaging system, comprising:
the acquisition device is used for acquiring images of a patient;
the display device is used for displaying the image and the editing interface;
image processing means for running a computer program which when running performs the method of positioning an abdominal aortic bifurcation according to any one of claims 1 to 2.
5. A computer-readable storage medium configured to store an executable program to perform the method of locating an abdominal aortic bifurcation of any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710400073.3A CN107221009B (en) | 2017-05-31 | 2017-05-31 | Method and device for positioning abdominal aorta bifurcation, medical imaging system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710400073.3A CN107221009B (en) | 2017-05-31 | 2017-05-31 | Method and device for positioning abdominal aorta bifurcation, medical imaging system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107221009A CN107221009A (en) | 2017-09-29 |
| CN107221009B true CN107221009B (en) | 2020-06-16 |
Family
ID=59947229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710400073.3A Active CN107221009B (en) | 2017-05-31 | 2017-05-31 | Method and device for positioning abdominal aorta bifurcation, medical imaging system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107221009B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11127138B2 (en) * | 2018-11-20 | 2021-09-21 | Siemens Healthcare Gmbh | Automatic detection and quantification of the aorta from medical images |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1983333A (en) * | 2005-11-17 | 2007-06-20 | 通用电气公司 | Methods and apparatus for selecting and/or labeling vessel branches |
| CN102968783A (en) * | 2012-10-15 | 2013-03-13 | 深圳市旭东数字医学影像技术有限公司 | Method and system for automatically segmenting bones from abdomen image data |
| CN104574413A (en) * | 2015-01-22 | 2015-04-29 | 深圳大学 | Blood vessel bifurcation extracting method and system of lung CT picture |
| CN104825177A (en) * | 2014-02-11 | 2015-08-12 | 西门子（中国）有限公司 | Cerebral blood volume correction method and apparatus, and angiography equipment |
| CN105809696A (en) * | 2016-03-11 | 2016-07-27 | 中国矿业大学(北京) | Automatic positioning and segmentation method for adrenal gland in sequence CT image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070106375A1 (en) * | 2005-11-07 | 2007-05-10 | Carlos Vonderwalde | Bifurcated stent assembly |
-
2017
- 2017-05-31 CN CN201710400073.3A patent/CN107221009B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1983333A (en) * | 2005-11-17 | 2007-06-20 | 通用电气公司 | Methods and apparatus for selecting and/or labeling vessel branches |
| CN102968783A (en) * | 2012-10-15 | 2013-03-13 | 深圳市旭东数字医学影像技术有限公司 | Method and system for automatically segmenting bones from abdomen image data |
| CN104825177A (en) * | 2014-02-11 | 2015-08-12 | 西门子（中国）有限公司 | Cerebral blood volume correction method and apparatus, and angiography equipment |
| CN104574413A (en) * | 2015-01-22 | 2015-04-29 | 深圳大学 | Blood vessel bifurcation extracting method and system of lung CT picture |
| CN105809696A (en) * | 2016-03-11 | 2016-07-27 | 中国矿业大学(北京) | Automatic positioning and segmentation method for adrenal gland in sequence CT image |
Non-Patent Citations (5)
| Title |
|---|
| Probabilistic Branching Node Detection Using Adaboost and Hybrid Local Features;Tatyana Nuzhnaya et al.;《2010 IEEE International Symposium on Biomedical Imaging: Form Nano to Macro》;20100417;第3-4节 * |
| Tatyana Nuzhnaya et al..Probabilistic Branching Node Detection Using Adaboost and Hybrid Local Features.《2010 IEEE International Symposium on Biomedical Imaging: Form Nano to Macro》.2010, * |
| 基于MRI图像的儿童发育性髋关节发育不良的髋关节三维模型建立;杜一;《中国学位论文全文数据库》;20150817;第2.2节 * |
| 脐、髂嵴顶点与腹主动脉分叉位置关系的对比影像解剖学研究;菅洪健 等;《实用医学杂志》;20170516;第1.2节，表1 * |
| 血管内超声灰阶图像的自动组织标定;孙正 等;《生物医学工程学杂志》;20160430;第33卷(第2期);第1.3-2节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107221009A (en) | 2017-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11344273B2 (en) | Methods and systems for extracting blood vessel | |
| CN106340021B (en) | Blood vessel extraction method | |
| CN107545584B (en) | Method, device and system for positioning region of interest in medical image | |
| US20210106299A1 (en) | Method and system for extracting lower limb vasculature | |
| US8761475B2 (en) | System and method for automatic recognition and labeling of anatomical structures and vessels in medical imaging scans | |
| JP5643304B2 (en) | Computer-aided lung nodule detection system and method and chest image segmentation system and method in chest tomosynthesis imaging | |
| JP6564018B2 (en) | Radiation image lung segmentation technology and bone attenuation technology | |
| US8934693B2 (en) | Method and system for intervention planning for transcatheter aortic valve implantation from 3D computed tomography data | |
| US20100239148A1 (en) | Method and System for Automatic Aorta Segmentation | |
| US20120238866A1 (en) | Method and System for Catheter Tracking in Fluoroscopic Images Using Adaptive Discriminant Learning and Measurement Fusion | |
| US10268915B2 (en) | Real-time collimation and ROI-filter positioning in X-ray imaging via automatic detection of the landmarks of interest | |
| JPH11276462A (en) | Automatically setting method for collimator of x-ray imaging system in image collection and x-ray imaging system | |
| US20110052026A1 (en) | Method and Apparatus for Determining Angulation of C-Arm Image Acquisition System for Aortic Valve Implantation | |
| US9269165B2 (en) | Rib enhancement in radiographic images | |
| US9424648B2 (en) | Method and system for device detection in 2D medical images | |
| Yang et al. | An automated method for accurate vessel segmentation | |
| JP5364009B2 (en) | Image generating apparatus, image generating method, and program thereof | |
| CN107221009B (en) | Method and device for positioning abdominal aorta bifurcation, medical imaging system and storage medium | |
| WO2015052919A1 (en) | Medical image processing device and operation method therefore, and medical image processing program | |
| CN112184664A (en) | Vertebra detection method and computer equipment | |
| CN112308821B (en) | Vertebra detection method and computer equipment | |
| US20220375081A1 (en) | Workload reducer for quality auditors in radiology | |
| Grigorieva et al. | The Construction of an Individualized Spinal 3D Model Based on the X-ray Recognition | |
| CN117765081A (en) | Preoperative target plane positioning method and device and medical scanning imaging equipment | |
| CN113177945A (en) | System and method for linking segmentation graph to volume data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Patentee after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Patentee before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |