CN107885835B - Similar layer image searching method and device of tomography image - Google Patents
Similar layer image searching method and device of tomography image Download PDFInfo
- Publication number
- CN107885835B CN107885835B CN201711098324.3A CN201711098324A CN107885835B CN 107885835 B CN107885835 B CN 107885835B CN 201711098324 A CN201711098324 A CN 201711098324A CN 107885835 B CN107885835 B CN 107885835B
- Authority
- CN
- China
- Prior art keywords
- image
- images
- feature points
- target
- layer
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Abstract
The invention provides a method and a device for searching similar layer images of a tomography image, wherein the method comprises the following steps: the method comprises the steps of obtaining a first image and a plurality of second images of the same object, carrying out feature extraction on the first image and each second image to obtain feature points, determining target feature points matched with the feature points of the first image from the feature points of the second images aiming at each second image, and determining a target image similar to the layer where the first image is located from the plurality of second images according to the number of the target feature points in each second image. The method has the advantages that the obtained first image and the plurality of second images are subjected to feature extraction, and the target image similar to the layer where the first image is located is determined by comparing the extracted feature points and the number of the feature points, so that the manual screening of a user is avoided, and the technical problems that in the prior art, when the user needs to search the target image similar to the layer where the images are located from the plurality of images, the user needs to manually search and screen the target image, and the efficiency is low are solved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for searching similar layer images of a tomography image.
Background
With the advent of tomographic apparatuses, Computed Tomography (CT) technology has provided assistance in the diagnosis of diseases. At present, when a plurality of patients visit a hospital, doctors need to make corresponding diagnosis according to medical image images shot by the doctors. When the patient is periodically reexamined after rehabilitation, the doctor needs to observe whether the treatment is effective or not and whether the patient is improved or not according to the medical image after the treatment.
In the prior art, aiming at a multilayer CT image, when a doctor selects an image required by the doctor, the doctor needs to manually search and compare the latest image of a patient after a period of time to find a layer close to the image, observe whether the image changes in two periods, whether the state of an illness is improved, whether treatment is effective and the like, and the doctor searches similar layers of the image in a large number of images, so that a large amount of time is consumed, and the efficiency is low.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, the invention provides a method for searching similar layer images of a tomography image, which is used for realizing the characteristic extraction of the acquired first image and a plurality of second images and determining a target image similar to the layer where the first image is located by comparing the extracted characteristic points with the number of the characteristic points, thereby avoiding the manual screening of a user and solving the technical problems that in the prior art, when the user needs to search the target image similar to the layer where the image is located from a plurality of images, the user needs to manually search and screen the target image, and the efficiency is low.
The invention provides a similar layer image searching device for a tomography image.
The invention provides a computer device.
The invention provides a computer readable storage medium.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides a method for searching similar layer images of a tomographic image, including:
acquiring a first image and a plurality of second images of the same object; the first image is a layer image in a multilayer image obtained by carrying out tomography at a first moment; the second image is a multilayer image obtained by carrying out tomography at a second moment;
extracting the features of the first image and each second image to obtain feature points;
for each second image, determining a target feature point matched with the feature point of the first image from the feature points of the second image;
and determining a target image similar to the layer where the first image is located from the plurality of second images according to the number of the target feature points in each second image.
In the method for searching similar layer images of a tomography image, a first image and a plurality of second images of the same object are obtained, feature extraction is carried out on the first image and each second image to obtain feature points, for each second image, target feature points matched with the feature points of the first image are determined from the feature points of the second images, and according to the number of the target feature points in each second image, a target image similar to the layer where the first image is located is determined from the plurality of second images. The method has the advantages that the obtained first image and the plurality of second images are subjected to feature extraction, and the target image similar to the layer where the first image is located is determined by comparing the extracted feature points and the number of the feature points, so that the manual screening of a user is avoided, and the technical problems that in the prior art, when the user needs to search the target image similar to the layer where the images are located from the plurality of images, the user needs to manually search and screen the target image, and the efficiency is low are solved.
In order to achieve the above object, a second embodiment of the present invention provides a similar layer image searching apparatus for a tomographic image, including:
the device comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a first image and a plurality of second images of the same object; the first image is a layer image in a multilayer image obtained by carrying out tomography at a first moment; the second image is a multilayer image obtained by carrying out tomography at a second moment;
the extraction module is used for extracting the features of the first image and each second image to obtain feature points;
the matching module is used for determining a target feature point matched with the feature point of the first image from the feature points of the second images aiming at each second image;
and the determining module is used for determining a target image similar to the layer where the first image is located from the plurality of second images according to the number of the target feature points in each second image.
In the similar layer image searching device of the tomographic image, an obtaining module is used for obtaining a first image and a plurality of second images of the same object, an extracting module is used for performing feature extraction on the first image and each second image to obtain feature points, a matching module is used for determining target feature points matched with the feature points of the first image from the feature points of the second images aiming at each second image, and a determining module is used for determining a target image similar to the layer where the first image is located from the plurality of second images according to the number of the target feature points in each second image. The method has the advantages that the obtained first image and the plurality of second images are subjected to feature extraction, and the target image similar to the layer where the first image is located is determined by comparing the extracted feature points and the number of the feature points, so that the manual screening of a user is avoided, and the technical problems that in the prior art, when the user needs to search the target image similar to the layer where the images are located from the plurality of images, the user needs to manually search and screen the target image, and the efficiency is low are solved.
To achieve the above object, a third embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the similar layer image searching method for a tomographic image according to the first embodiment.
In order to achieve the above object, a fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements a similar layer image search method for a tomographic image as described in the first aspect.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a method for searching a similar layer image of a tomographic image according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of another method for searching similar slice images of a tomographic image according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a similar layer image searching apparatus for a tomographic image according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of another similar layer image searching apparatus for a tomographic image according to an embodiment of the present invention; and
FIG. 5 illustrates a block diagram of an exemplary computer device suitable for use in implementing embodiments of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
A similar layer image search method and apparatus for a tomographic image according to an embodiment of the present invention will be described below with reference to the drawings.
Fig. 1 is a schematic flowchart of a method for searching a similar layer image of a tomographic image according to an embodiment of the present invention.
As shown in fig. 1, the method includes:
step S101, a first image and a plurality of second images of the same object are acquired.
Specifically, according to the electronic computed tomography CT apparatus, a plurality of slice images can be obtained by performing slice scanning on the same object, and different slice images can be obtained at different times.
And S102, extracting the characteristics of the first image and each second image to obtain characteristic points.
Specifically, as a possible implementation manner, a Speeded-Up robust features (SURF) algorithm is adopted to perform feature extraction on the first image and each second image to obtain feature points, where the feature points may be described by using Haar wavelet features.
Step S103, for each second image, determines a target feature point matching the feature point of the first image from the feature points of the second image.
Specifically, as a possible implementation manner, for each feature point in each second image, a euclidean distance between each feature point and each feature point of the second image is calculated, and according to the euclidean distance, a matched target feature point is determined from each second image.
And step S104, determining a target image similar to the layer where the first image is located from the plurality of second images according to the number of the target feature points in each second image.
And inquiring the images to be selected with the maximum number of the target characteristic points from the plurality of second images, and adopting a corresponding strategy to determine the target images according to the number of the images to be selected. Specifically, if one image to be selected is selected, determining the image to be selected as a target image; and if the number of the images to be selected is at least two, inquiring a Z-axis value used for indicating the position information of the layer in the DICOM information of each image to be selected, and determining the target image from the at least two images to be selected according to a difference absolute value between the Z-axis value in the DICOM information of each image to be selected and the Z-axis value in the DICOM information of the first image.
In the method for searching similar layer images of a tomography image, a first image and a plurality of second images of the same object are obtained, feature extraction is carried out on the first image and each second image to obtain feature points, for each second image, target feature points matched with the feature points of the first image are determined from the feature points of the second images, and according to the number of the target feature points in each second image, a target image similar to the layer where the first image is located is determined from the plurality of second images. The method has the advantages that the obtained first image and the plurality of second images are subjected to feature extraction, and the target image similar to the layer where the first image is located is determined by comparing the extracted feature points and the number of the feature points, so that the manual screening of a user is avoided, and the technical problems that in the prior art, when the user needs to search the target image similar to the layer where the images are located from the plurality of images, the user needs to manually search and screen the target image, and the efficiency is low are solved.
Based on the foregoing embodiment, an embodiment of the present invention further provides another method for searching for a similar layer image of a tomographic image, and fig. 2 is a schematic flow chart of the method for searching for a similar layer image of a tomographic image according to the embodiment of the present invention, which further clearly explains a process of determining a target image similar to a layer where a first image is located, and as shown in fig. 2, the method includes the following steps:
in step S201, a first image and a plurality of second images of the same object are acquired.
Specifically, tomographic scanning of the same object to obtain a multi-slice image, for example, 300 images can be acquired by performing tomographic scanning, and the 300 image interval is fixed, about 5mm or so. The method includes the steps that tomography scanning is carried out on the same object at different moments to obtain different multilayer images, wherein one layer of the multilayer images obtained through tomography scanning at the first moment is called a first image, and the multilayer images obtained through tomography scanning at the second moment are called a second image.
Step S202, feature extraction is carried out on the first image and each second image to obtain feature points.
As a possible implementation manner, the first image and each second image may be subjected to feature extraction by using a SURF algorithm to obtain feature points, the SURF algorithm is an accelerated version of the SIFT algorithm, and the SURF algorithm may complete matching of objects in the two images under a moderate condition, so that real-time processing is basically realized.
The SURF algorithm steps are as follows:
first, a Hessian matrix is constructed.
Firstly, a Hessian matrix of a pixel point (x, y) in an image is obtained through calculation:
wherein L isxx、LxyAnd LyyThe second derivatives for each direction are determined for the gaussian filtered image based on the x and y axes.
Next, in order to find out the feature points in the image, it is necessary to perform the process on the original imageAnd transforming to obtain a transformation diagram, wherein the transformation diagram is formed by the approximate values of the Hessian matrix determinant of each pixel of the original image, and the approximate value forming formula of the Hessian matrix determinant of each pixel of the original image is as follows: det (H)approx)＝LxxLyy-(0.9Lxy)2Wherein 0.9 is an empirical value given in this embodiment, and those skilled in the art may set other empirical values according to the circumstances, which is not limited herein.
And secondly, constructing a Gaussian pyramid.
Specifically, in order to ensure that the image matching has scale invariance, the images need to be layered, a scale space of the images is established, that is, a gaussian pyramid is constructed, and then feature points are searched for on the images with different scales. The SURF algorithm does not have a down-sampling process, and thus the processing speed is improved.
And thirdly, preliminarily determining the characteristic points.
Specifically, an extreme value is preset, all values smaller than the preset extreme value are discarded, the number of the detected feature points is reduced by increasing the extreme value, and only a few feature strongest points can be detected finally. In the detection process, a filter with the size corresponding to the resolution of the image of the scale layer is used for detection, 26 feature points in total are respectively compared with the other 8 feature points in the scale layer and the 9 feature points in the two scale layers above and below the feature points in the image of the scale layer, and if the feature value of the pixel point is greater than the feature values of the surrounding pixel points, the pixel point can be preliminarily determined to be the feature point of the region.
And fourthly, positioning the main direction of the characteristic points.
Specifically, in SURF, in order to ensure rotation invariance, its gradient histogram is not counted, but the Harr wavelet feature in the feature point domain is counted. Taking a feature point as a center, calculating the sum of Haar wavelet responses of all points in a 60-degree fan in the horizontal (x) and vertical (y) directions (the side length of the Haar wavelet is 4s) in a neighborhood with the radius of 6s (s is the scale value of the feature point), giving Gaussian weight coefficients to the response values to make the response contribution close to the feature point large and the response contribution far away from the feature point small, then adding the responses in the 60-degree range to form a new vector, traversing the whole circular region, and selecting the direction of the longest vector as the main direction of the feature point. In this way, the main direction of each feature point is obtained by calculating the feature points one by one.
And fifthly, constructing a feature description subregion.
Specifically, a square frame is taken around the feature point, the side length of the frame is 20s (s is the dimension of the detected feature point), and the frame strip direction, i.e., the direction, is the main direction detected in the fourth step. Then the frame is divided into 16 subregions, each subregion counts haar wavelet characteristics of 25 pixels in the horizontal direction and the vertical direction, wherein the horizontal direction and the vertical direction are relative to the main direction, the haar wavelet characteristics are the sum of values in the horizontal direction, the sum of absolute values in the vertical direction and the sum of absolute values in the vertical direction, so that each subregion has 4 values, and each characteristic point is a vector with 16 x 4-64 dimensions.
By the algorithm, the characteristic points of the image and the vector description thereof can be determined.
In step S203, for each second image, a target feature point matching the feature point of the first image is determined from the feature points of the second image.
As a possible implementation manner, for each feature point in each second image, the euclidean distance between each feature point in each second image and each feature point in the second image is calculated, specifically, a certain feature point in the first image and each feature point in one image in the second image are taken to calculate the euclidean distance, a set of distances is obtained, the set of distances is compared and operated, the minimum euclidean distance and the next minimum euclidean distance are obtained, a threshold is set, and when the ratio of the minimum euclidean distance to the next minimum euclidean distance is smaller than the threshold, the feature point is considered to be matched with the feature point corresponding to the minimum euclidean distance, that is, the certain feature point in the first image is matched with the feature point. And then, according to the Euclidean distance, determining matched target feature points from each second image.
And step S204, eliminating the mismatching target feature points by adopting a GTM algorithm aiming at each second image.
After the feature point Matching is performed on the first image and the plurality of second images, a feature point pair which is mismatched exists, the target feature point which is mismatched needs to be deleted to ensure the Matching accuracy, and as a possible implementation manner, the target feature point which is mismatched can be eliminated by adopting a Graph Transformation Matching (GTM) algorithm.
To represent the associations between vertices in a graph, the structure of the graph can be represented by an adjacency matrix, which is a two-dimensional matrix representing the association between edges, the adjacency matrix being a matrix of N × N, where N is the vertex of the graph, and G (V, E) is a graph with 5 vertices, and the adjacency matrix being a matrix of 5 x 5, e.g., A (A) is a matrix of 5 x 51：
In step S203, after the target feature point matching the feature point of the first image is determined for one second image, two corresponding point sets with the size of N are obtained, where the corresponding point set of the first image is P ═ PiA second image corresponding point set is P' ═ Pi', where i takes the value 1 … N. The points in the set of points are in a one-to-one correspondence, that is, the matching point pairs (p, p ') located in different images have mapping relationships { p → p ' } and { p ' → p }.
The GTM algorithm is a method for eliminating the corresponding point of the damaged domain relation in an iteration mode. For a set of points P ═ PiP ═ Pi' } respectivelyGenerating a k-nearest neighbor (k-NN) graph G with undirected medianp＝(Vp,Ep) And Gp'＝(Vp',Ep') Corresponding to the adjacent matrix is ApAnd Ap'Defining a vertex viRepresents a set of corresponding points (p)i,p'i)，Vp＝{v1,…,vN}. Corresponding point set P ═ PiFor vertex piWill judge pjIs piWill satisfy | p simultaneously as the first judgment conditioni-pjIf | ≦ η, there is an edge (i, j) as the second determination condition, where η is the median of the distances between all vertices, defined as:
the first condition indicates that a vertex can only identify the structure between it and its neighbors, and the second condition limits the proximity of the structure if point piUnder the limitation of the two conditions, if the number of the adjacent points does not reach the preset threshold value K, p isiMay be considered unconnected.
EpIs the set of all edges, for the adjacency matrix ApWhen (i, j) ∈ EpWhen, Ap(i, j) ═ 1; otherwise Ap(i, j) ═ 0. Likewise, for a set of points P' { Pi' } giving rise to FIG. Gp'＝(Vp',Ep',Ap')。
The GTM algorithm is based on the assumption that there is a smooth transition between the two images, in this case the point p in the first imageiAnd a second image point pi' the neighboring points are in one-to-one correspondence, and if all correspondences are correct, then GpAnd Gp'Are of the same structure and a false match results in GpAnd Gp'Different structures, by using similar structure criteria, the mismatching results can be eliminated during the iteration process, thereby eliminating mismatching target feature points in a second image.
Furthermore, the target feature points which are mismatched in each image in the second image can be removed.
Step S205, according to the number of target feature points in each second image, querying the candidate image with the largest number of target feature points from the plurality of second images.
Specifically, the number of the target feature points in each second image is counted, and the image to be selected with the largest number of the target feature points in the plurality of second images is determined.
Step S206, determining whether the number of the images to be selected is one, if yes, performing step S207, and if not, performing step S208.
Specifically, if the number of the images to be selected with the largest number of the target feature points is one, step S207 is executed, that is, the image to be selected with the largest number of the target feature points is determined to be the target image; if the number of the images to be selected with the largest number of the target feature points is at least two, step S208 is executed, and the target image is further determined from the at least two images to be selected.
And step S207, determining the image to be selected as the target image.
And S208, inquiring the Z-axis value in the DICOM information of each image to be selected.
Specifically, if the number of the images to be selected with the largest number of the determined target feature points is at least two, a Z-axis value in Digital Imaging and Communications in medicine (DICOM) information of each image to be selected is queried, DICOM is an international standard for medical images and related information (ISO 12052) and defines a medical image format which can meet clinical requirements in quality and can be used for data exchange, wherein the Z-axis value in the DICOM information is used for indicating position information of a layer where the image to be selected is located, and further, the image to be selected is determined by querying the position information of the layer where the image to be selected is located.
Step S209, according to the absolute value of the difference between the Z-axis value in the DICOM information of each image to be selected and the Z-axis value in the DICOM information of the first image, determining a target image from at least two images to be selected.
In particular, DICOM communication of the first imageZ-axis value in information is recorded as Z1And the Z-axis value in DICOM information of the image to be selected is recorded as ZiWherein i represents the number of the images to be selected. Respectively calculating Z for at least two images to be selected1And ZiAbsolute value of difference between | Z1-ZiAnd taking the image to be selected with the minimum absolute value of the difference value as a target image.
In the method for searching similar layer images of a tomography image, a first image and a plurality of second images of the same object are obtained, feature extraction is carried out on the first image and each second image to obtain feature points, for each second image, target feature points matched with the feature points of the first image are determined from the feature points of the second images, and according to the number of the target feature points in each second image, a target image similar to the layer where the first image is located is determined from the plurality of second images. The method has the advantages that the obtained first image and the plurality of second images are subjected to feature extraction, and the target image similar to the layer where the first image is located is determined by comparing the extracted feature points and the number of the feature points, so that the manual screening of a user is avoided, and the technical problems that in the prior art, when the user needs to search the target image similar to the layer where the images are located from the plurality of images, the user needs to manually search and screen the target image, and the efficiency is low are solved.
In order to implement the above embodiment, the present invention further provides a similar layer image searching device for a tomography image, and fig. 3 is a schematic structural diagram of the similar layer image searching device for a tomography image according to the embodiment of the present invention.
As shown in fig. 3, the apparatus includes: an acquisition module 31, an extraction module 32, a matching module 33 and a determination module 34.
The acquiring module 31 is configured to acquire a first image and a plurality of second images of the same object, where the first image is a layer image in a multi-layer image obtained by performing tomography at a first time, and the second image is a multi-layer image obtained by performing tomography at a second time.
And an extracting module 32, configured to perform feature extraction on the first image and each second image to obtain feature points.
And a matching module 33, configured to determine, for each second image, a target feature point that matches the feature point of the first image from the feature points of the second image.
And the determining module 34 is configured to determine, from the plurality of second images, a target image similar to the layer where the first image is located according to the number of the target feature points in each second image.
It should be noted that the foregoing explanation of the method embodiment is also applicable to the apparatus of this embodiment, and is not repeated herein.
In the similar layer image searching device of the tomographic image, an obtaining module is used for obtaining a first image and a plurality of second images of the same object, an extracting module is used for performing feature extraction on the first image and each second image to obtain feature points, a matching module is used for determining target feature points matched with the feature points of the first image from the feature points of the second images aiming at each second image, and a determining module is used for determining a target image similar to the layer where the first image is located from the plurality of second images according to the number of the target feature points in each second image. The method has the advantages that the obtained first image and the plurality of second images are subjected to feature extraction, and the target image similar to the layer where the first image is located is determined by comparing the extracted feature points and the number of the feature points, so that the manual screening of a user is avoided, and the technical problems that in the prior art, when the user needs to search the target image similar to the layer where the images are located from the plurality of images, the user needs to manually search and screen the target image, and the efficiency is low are solved.
Based on the foregoing embodiment, an embodiment of the present invention further provides a possible implementation manner of a similar layer image searching apparatus for a tomographic image, and fig. 4 is a schematic structural diagram of another similar layer image searching apparatus for a tomographic image according to an embodiment of the present invention, as shown in fig. 4, on the basis of the foregoing embodiment, the apparatus further includes: and a culling module 35.
And a removing module 35, configured to remove the target feature points that are mismatched by using a GTM algorithm for each second image.
As a possible implementation manner, the determining module 34 may further include:
the querying unit 341 is configured to query the candidate image with the largest number of target feature points from the plurality of second images.
The first determining unit 342 is configured to determine that the image to be selected is the target image if the image to be selected is one.
The second determining unit 343 is configured to query, if the number of the images to be selected is at least two, a Z-axis value in DICOM information of each image to be selected, where the Z-axis value in the DICOM information is used to indicate location information of a layer where the image is located. And determining a target image from at least two images to be selected according to the absolute value of the difference between the Z-axis value in the DICOM information of each image to be selected and the Z-axis value in the DICOM information of the first image.
As a possible implementation manner, the extraction module 32 is specifically configured to:
and performing feature extraction on the first image and each second image by adopting an SURF algorithm to obtain feature points, wherein the feature points are described by adopting Haar wavelet features.
As a possible implementation manner, the matching module 33 is specifically configured to:
and calculating Euclidean distances between each feature point in each second image and each feature point of the second image, and determining a matched target feature point from each second image according to the Euclidean distances.
It should be noted that the foregoing explanation of the method embodiment is also applicable to the apparatus of this embodiment, and is not repeated herein.
In the similar layer image searching device of the tomographic image, an obtaining module is used for obtaining a first image and a plurality of second images of the same object, an extracting module is used for performing feature extraction on the first image and each second image to obtain feature points, a matching module is used for determining target feature points matched with the feature points of the first image from the feature points of the second images aiming at each second image, and a determining module is used for determining a target image similar to the layer where the first image is located from the plurality of second images according to the number of the target feature points in each second image. The method has the advantages that the obtained first image and the plurality of second images are subjected to feature extraction, and the target image similar to the layer where the first image is located is determined by comparing the extracted feature points and the number of the feature points, so that the manual screening of a user is avoided, and the technical problems that in the prior art, when the user needs to search the target image similar to the layer where the images are located from the plurality of images, the user needs to manually search and screen the target image, and the efficiency is low are solved.
In order to implement the above embodiments, the present invention further provides a computer device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the similar layer image searching method for tomographic images according to the foregoing method embodiments.
In order to achieve the above embodiments, the present invention also proposes a computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements a similar layer image search method for a tomographic image as described in the embodiment of the first aspect.
FIG. 5 illustrates a block diagram of an exemplary computer device suitable for use in implementing embodiments of the present application. The computer device 12 shown in fig. 5 is only an example and should not bring any limitation to the function and scope of use of the embodiments of the present application.
As shown in FIG. 5, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described herein.
The processing unit 16 executes various functional applications and data processing, for example, implementing the methods mentioned in the foregoing embodiments, by executing programs stored in the system memory 28.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (9)
1. A method for searching similar layer images of a tomography image is characterized by comprising the following steps:
acquiring a first image and a plurality of second images of the same object; the first image is a layer image in a multilayer image obtained by carrying out tomography at a first moment; the second image is a multilayer image obtained by carrying out tomography at a second moment;
extracting the features of the first image and each second image to obtain feature points;
for each second image, determining a target feature point matched with the feature point of the first image from the feature points of the second image;
inquiring the images to be selected with the largest number of target characteristic points from the plurality of second images according to the number of the target characteristic points in each second image, and inquiring Z-axis values in DICOM information of each image to be selected if the number of the images to be selected is at least two; the Z-axis value in the DICOM information is used for indicating the position information of the layer where the image is located, and the target image is determined from at least two images to be selected according to the absolute value of the difference value between the Z-axis value in the DICOM information of each image to be selected and the Z-axis value in the DICOM information of the first image;
and determining a target image similar to the layer where the first image is located from the images to be selected.
2. The method for searching similar layer images according to claim 1, wherein after the query of the candidate image with the largest number of the target feature points, the method further comprises:
and if the number of the images to be selected is one, determining that the images to be selected are the target images.
3. The method for finding a similar layer image according to any one of claims 1-2, wherein after determining, for each of the second images, a target feature point matching the feature point of the first image from the feature points of the second image, the method further comprises:
and eliminating the mismatching target feature points by adopting a GTM algorithm aiming at each second image.
4. The method for searching similar layer images according to any one of claims 1-2, wherein the extracting features of the first image and each of the second images to obtain feature points comprises:
performing feature extraction on the first image and each second image by using a SURF algorithm to obtain feature points; wherein, the characteristic points are described by using Haar wavelet characteristics.
5. The method for finding similar layer images according to any one of claims 1-2, wherein for each of the second images, determining a target feature point matching the feature point of the first image from the feature points of the second image comprises:
calculating Euclidean distances between each feature point in each second image and each feature point of the second image;
and determining matched target feature points from each second image according to the Euclidean distance.
6. A similar layer image search device for a tomographic image, comprising:
the device comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a first image and a plurality of second images of the same object; the first image is a layer image in a multilayer image obtained by carrying out tomography at a first moment; the second image is a multilayer image obtained by carrying out tomography at a second moment;
the extraction module is used for extracting the features of the first image and each second image to obtain feature points;
the matching module is used for determining a target feature point matched with the feature point of the first image from the feature points of the second images aiming at each second image;
the determining module is used for inquiring the images to be selected with the largest number of target feature points from the plurality of second images according to the number of the target feature points in each second image, and inquiring the Z-axis value in the DICOM information of each image to be selected if the number of the images to be selected is at least two; the Z-axis value in the DICOM information is used for indicating the position information of the layer where the DICOM information is located; and determining the target image from at least two images to be selected according to the absolute value of the difference between the Z-axis value in the DICOM information of each image to be selected and the Z-axis value in the DICOM information of the first image.
7. The similar layer image searching device as claimed in claim 6, wherein the determining module is further configured to:
and if the number of the images to be selected is one, determining that the images to be selected are the target images.
8. A computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a similar layer image finding method for a tomographic image as claimed in any one of claims 1 to 5 when executing the program.
9. A computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the similar layer image finding method for a tomographic image as recited in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711098324.3A CN107885835B (en) | 2017-11-09 | 2017-11-09 | Similar layer image searching method and device of tomography image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711098324.3A CN107885835B (en) | 2017-11-09 | 2017-11-09 | Similar layer image searching method and device of tomography image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107885835A CN107885835A (en) | 2018-04-06 |
| CN107885835B true CN107885835B (en) | 2020-08-28 |
Family
ID=61779804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711098324.3A Active CN107885835B (en) | 2017-11-09 | 2017-11-09 | Similar layer image searching method and device of tomography image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107885835B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782459B (en) * | 2019-01-08 | 2021-02-19 | 北京嘀嘀无限科技发展有限公司 | Image processing method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760874A (en) * | 2016-03-08 | 2016-07-13 | 中国科学院苏州生物医学工程技术研究所 | CT image processing system and method for pneumoconiosis |
| CN106778785A (en) * | 2016-12-23 | 2017-05-31 | 东软集团股份有限公司 | Build the method for image characteristics extraction model and method, the device of image recognition |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100423695C (en) * | 2006-11-08 | 2008-10-08 | 沈阳东软医疗系统有限公司 | Device and method for determining interesting zone |
| NO329839B1 (en) * | 2010-04-06 | 2011-01-10 | Svein Fimreite | Transmission of explicit commands and functions using DICOM Query Retrieve |
| KR101029160B1 (en) * | 2011-02-07 | 2011-04-13 | (주)올라웍스 | Method, system and computer-readable recording medium for writing new image and its information onto image database |
| CN105045886B (en) * | 2015-07-23 | 2020-03-13 | 青岛海信医疗设备股份有限公司 | DICOM image importing method |
| CN105678778B (en) * | 2016-01-13 | 2019-02-26 | 北京大学深圳研究生院 | A kind of image matching method and device |
-
2017
- 2017-11-09 CN CN201711098324.3A patent/CN107885835B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105760874A (en) * | 2016-03-08 | 2016-07-13 | 中国科学院苏州生物医学工程技术研究所 | CT image processing system and method for pneumoconiosis |
| CN106778785A (en) * | 2016-12-23 | 2017-05-31 | 东软集团股份有限公司 | Build the method for image characteristics extraction model and method, the device of image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107885835A (en) | 2018-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111325739B (en) | Method and device for detecting lung focus and training method of image detection model | |
| EP3246871A1 (en) | Image splicing | |
| CN107886508B (en) | Differential subtraction method and medical image processing method and system | |
| JP5851160B2 (en) | Image processing apparatus, operation method of image processing apparatus, and image processing program | |
| CN111091536B (en) | Medical image processing method, apparatus, device, medium, and endoscope | |
| WO2008151113A1 (en) | Methods and apparatus for computer automated diagnosis of mammogram images | |
| CN110782489B (en) | Image data matching method, device and equipment and computer readable storage medium | |
| JP2018175217A (en) | Image processing apparatus, method and program | |
| WO2020050721A1 (en) | Determination of a growth rate of an object in 3d data sets using deep learning | |
| JP2005065728A (en) | Similar image retrieval system | |
| CN115861656A (en) | Method, apparatus and system for automatically processing medical images to output an alert | |
| Almakady et al. | Rotation invariant features based on three dimensional Gaussian Markov random fields for volumetric texture classification | |
| CN107885835B (en) | Similar layer image searching method and device of tomography image | |
| Mamalakis et al. | MA-SOCRATIS: An automatic pipeline for robust segmentation of the left ventricle and scar | |
| CN114511558B (en) | Method and device for detecting cleanliness of intestinal tract | |
| Doğanay et al. | A hybrid lung segmentation algorithm based on histogram-based fuzzy C-means clustering | |
| Bathina et al. | Robust matching of multi-modal retinal images using radon transform based local descriptor | |
| Mansoor et al. | Near-optimal keypoint sampling for fast pathological lung segmentation | |
| Yu et al. | A three-object model for the similarity searches of chest CT images | |
| WO2009077938A1 (en) | Successive landmark-based image registration | |
| Shaziya et al. | Comprehensive review of automatic lung segmentation techniques on pulmonary CT images | |
| Han et al. | Detection of colonic polyp candidates with level set-based thickness mapping over the colon wall | |
| Wang et al. | A novel colon wall flattening model for computed tomographic colonography: method and validation | |
| Hsieh et al. | Fast and fully automatic phalanx segmentation using a grayscale-histogram morphology algorithm | |
| US20240005503A1 (en) | Method for processing medical images |
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 |