Statistical analysis method of DR image and DR imaging system

Abstract

The invention discloses a DR image statistical analysis method and a DR imaging system. The method comprises the following steps: acquiring multiple frames of DR images and related information of the multiple frames of DR images; extracting image features from the DR image, wherein the image features comprise at least one of a gray scale entropy feature, a texture feature, a noise feature, a gradient feature and a divergence feature; determining a DR feature index reflecting the basic feature information content of the DR image according to at least one image feature of the gray entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature; and determining a statistical result according to the DR feature indexes of the multiple frames of DR images and the related information of the multiple frames of DR images, and outputting the statistical result. Statistical analysis is carried out on the DR feature indexes of the multiple frames of DR images, the relevance between the DR feature indexes and related information of the DR images is presented through statistical results, and a DR image quality control tool can be provided for a user.

Description

Technical Field

[0001] The present invention relates to the field of medical image technology, and more specifically to a DR image statistical analysis method and a DR imaging system. Background Art

[0002] Digital Radiography (DR) images are a common type of medical digital images and are widely used in physical examinations and routine medical imaging diagnosis. With the development of digital X-ray detectors and digital image processing systems, DR images can often present diagnostic image effects within a wide range of exposure doses. This process often relies on the experience of the operator to grasp the final image effect. The accuracy of the judgment is easily affected by various factors such as experience differences, subjective differences, and post-processing. This leads to fluctuations in DR image quality for different patients or different operators due to various factors.

[0003] At present, hospitals usually rely on special quality control teams to regularly organize special personnel to conduct spot checks and reviews of DR images to find problems and ensure the overall image quality in the hospital. However, this operation cannot guarantee real-time performance and there is a certain delay in the discovery of problems. On the other hand, due to the subjectivity of manual review and the possibility of omissions in spot checks, it is impossible to objectively and comprehensively guarantee the image quality in the hospital. At the same time, due to the lack of objective guidance, even if there is a quality control team, it can only review the quality of DR images and cannot provide effective guidance for reducing the overall radiation dose in the hospital. Summary of the invention

[0004] A series of simplified concepts are introduced in the Summary of the Invention, which will be further described in detail in the Detailed Description of the Invention. The Summary of the Invention does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0005] An embodiment of the present invention provides a method for statistical analysis of DR images, the method comprising:

[0006] Acquire multiple frames of digital X-ray photography DR images and related information of the multiple frames of DR images;

[0007] Extracting image features from the DR image, the image features comprising at least one of grayscale entropy features, texture features, noise features, gradient features, and divergence features;

[0008] Determining a DR feature index reflecting the basic feature information content of the DR image according to at least one image feature of the grayscale entropy feature, the texture feature, the noise feature, the gradient feature, and the divergence feature;

[0009] A statistical result is determined according to the DR feature index of the multiple frames of DR images and the related information of the multiple frames of DR images, and the statistical result is output.

[0010] In one embodiment, the relevant information includes at least one of the following: time information of the DR image, operating technician, patient position, and patient personal information, and the statistical result includes a classified statistical result of the DR feature index under at least one of the relevant information.

[0011] In one embodiment, the method further includes: determining target related information from a plurality of related information based on the received operation instructions; the classified statistical results of the DR characteristic index under at least one of the related information include the classified statistical results of the DR characteristic index under the target related information.

[0012] In one embodiment, the statistical result includes a corresponding relationship diagram between the DR characteristic index and the relevant information.

[0013] In one embodiment, the relevant information includes time information, and the corresponding relationship diagram includes a trend diagram of the DR characteristic index changing with time.

[0014] In one embodiment, the relevant information includes an operating technician, a patient's body position or a patient's personal information, and the corresponding relationship diagram includes a distribution diagram of the DR characteristic index under different operating technicians, patient's body positions or patient's personal information.

[0015] In one embodiment, the method further includes: obtaining a reference level of a DR characteristic index; and displaying an identifier representing the reference level of the DR characteristic index in the correspondence diagram.

[0016] In one embodiment, outputting the statistical results includes: obtaining a DR feature index reference level; comparing the DR feature index of the multiple frames of DR images with the DR feature index reference level; determining a DR image whose DR feature index does not meet the DR feature index reference level as a target DR image, and displaying the statistical results of at least one of the related information of the target DR image.

[0017] In one embodiment, the DR characteristic index reference level is set according to a received operation instruction or a system default setting.

[0018] In one embodiment, the relevant information includes first relevant information and second relevant information, and the statistical results are determined based on the DR feature index of the multiple frames of DR images and the relevant information of the multiple frames of DR images, and the statistical results are output, including: obtaining a first reference level of the DR feature index corresponding to the first relevant information; extracting multiple frames of first DR images corresponding to the first relevant information from the multiple frames of DR images; comparing the DR feature index of the multiple frames of first DR images with the first reference level to determine a first DR image whose DR feature index does not meet the first reference level; determining and displaying the statistical results of the second relevant information of the first DR image.

[0019] In one embodiment, the grayscale entropy feature can be extracted from the DR image in the following manner: obtaining a first probability statistical distribution of each grayscale source in the DR image; determining a first probability statistical distribution of non-redundant grayscale sources from the first probability statistical distribution of the grayscale sources according to the size of the first probability statistical distribution; obtaining a second probability statistical distribution of each non-redundant grayscale source according to the ratio of the first probability statistical distribution of each non-redundant grayscale source to the sum of the first probability statistical distributions of all non-redundant grayscale sources; and obtaining the grayscale entropy feature by calculating the entropy of the second probability statistical distribution of the non-redundant grayscale sources.

[0020] In one embodiment, the texture feature can be extracted from the DR image in the following manner: obtaining a texture feature description matrix based on the grayscale value of each pixel in the DR image, the texture feature description matrix describing the distance between different pixel points in the DR image and the change in grayscale value in the direction between different pixel points; extracting at least one two-dimensional component of the texture feature description matrix as the texture feature.

[0021] In one embodiment, the noise feature can be extracted from the DR image in the following manner: filtering the DR image to obtain a high-frequency image; calculating the root mean square of the neighborhood of each pixel point in the high-frequency image to obtain a noise distribution image; and statistically analyzing the distribution of noise values ​​in the noise distribution image to obtain the noise feature.

[0022] In one embodiment, the gradient feature may be extracted from the DR image in the following manner: determining the regional distribution of different tissues in the DR image; and obtaining the clarity of the boundary of the regional distribution of different tissues as the gradient feature.

[0023] In one embodiment, the divergence feature can be extracted from the DR image in the following manner: determining the regional distribution of different tissues in the DR image; obtaining the transition strength and / or trend consistency of the boundaries of the regional distribution of different tissues as the divergence feature.

[0024] Another aspect of the present invention provides a method for statistical analysis of DR images, the method comprising:

[0025] Acquire multiple frames of digital X-ray photography DR images and related information of the multiple frames of DR images, wherein the related information includes at least one of time information of the DR images, an operating technician, a patient's body position, and patient personal information;

[0026] Determining a DR feature index reflecting basic feature information content of the multiple frames of DR images;

[0027] Perform statistical analysis on the DR feature indexes of the multiple frames of DR images according to at least one of the related information to obtain statistical analysis results, and display the statistical analysis results.

[0028] In one embodiment, the method further includes: performing a selection operation on a plurality of the related information; determining target related information from the plurality of related information based on the selection operation, and the statistical analysis result includes a classification statistical result of the DR characteristic index under the target related information.

[0029] In one embodiment, the statistical result includes a corresponding relationship diagram between the DR characteristic index and the relevant information.

[0030] In one embodiment, the method further includes: obtaining a reference level of a DR characteristic index; and displaying an identifier representing the reference level of the DR characteristic index in the correspondence diagram.

[0031] In one embodiment, displaying the statistical results includes: obtaining a DR characteristic index reference level; comparing the DR characteristic index of the multiple frames of DR images with the DR characteristic index reference level; determining a DR image whose DR characteristic index does not meet the DR characteristic index reference level as a target DR image, and displaying the statistical results of at least one of the related information of the target DR image.

[0032] In one embodiment, the relevant information includes first relevant information and second relevant information, and the DR feature index of the multiple frames of DR images is statistically analyzed based on at least one of the relevant information to obtain a statistical analysis result, and the statistical analysis result is displayed, including: obtaining a first reference level of the DR feature index corresponding to the first relevant information; extracting multiple frames of first DR images corresponding to the first relevant information from the multiple frames of DR images; comparing the DR feature index of the multiple frames of first DR images with the first reference level to determine a first DR image whose DR feature index does not meet the first reference level; determining and displaying the statistical result of the second relevant information of the first DR image.

[0033] Yet another aspect of an embodiment of the present invention provides a DR imaging system, comprising: an X-ray source, a flat-panel detector, a processor and an output device; the X-ray source is used to emit X-rays to a target part of a target object, so that the X-rays pass through the target part; the flat-panel detector is used to receive the X-rays after passing through the target part; the processor is used to process the X-rays after passing through the target part to obtain a DR image, and the processor is also used to execute the statistical analysis method of the DR image as described above; the output device is used to output the DR image.

[0034] The DR image statistical analysis method and DR imaging system of the embodiment of the present invention perform statistical analysis on the DR feature index of multiple frames of DR images, present the correlation between the DR feature index and the relevant information of the DR images through the statistical results, and can provide users with a quality control tool for DR images. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and other purposes, features and advantages of the present invention will become more apparent by describing the embodiments of the present invention in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0036] Figure 1 A schematic flow chart showing a statistical analysis method of DR images according to an embodiment of the present invention;

[0037] Figure 2 A schematic flow chart showing a statistical analysis method of DR images according to another embodiment of the present invention;

[0038] Figure 3 A schematic block diagram of a DR imaging system according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical scheme and advantages of the present invention more obvious, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present invention.

[0040] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0041] It should be understood that the present invention can be implemented in different forms and should not be interpreted as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make the disclosure thorough and complete and to fully convey the scope of the present invention to those skilled in the art.

[0042] The purpose of the terms used herein is only to describe specific embodiments and is not intended to be limiting of the present invention. When used herein, the singular forms "one", "an" and "said / the" are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "consisting of" and / or "comprising", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0043] In order to fully understand the present invention, a detailed structure will be presented in the following description to illustrate the technical solution proposed by the present invention. The optional embodiments of the present invention are described in detail as follows, but in addition to these detailed descriptions, the present invention may also have other implementations.

[0044] Next, first refer to Figure 1 A statistical analysis method 100 of a DR image according to an embodiment of the present invention is described. Figure 1 As shown, the DR image statistical analysis method 100 may include the following steps:

[0045] In step S110, a plurality of frames of digital X-ray photography DR images and related information of the plurality of frames of DR images are acquired;

[0046] In step S120, image features are extracted from the DR image, wherein the image features include at least one of grayscale entropy features, texture features, noise features, gradient features, and divergence features;

[0047] In step S130, a DR feature index reflecting the basic feature information content of the DR image is determined according to at least one image feature of the grayscale entropy feature, the texture feature, the noise feature, the gradient feature, and the divergence feature;

[0048] In step S140, a statistical result is determined according to the DR feature index of the multiple frames of DR images and the related information of the multiple frames of DR images, and the statistical result is output.

[0049] The statistical analysis method 100 of DR images in an embodiment of the present invention performs statistical analysis on the DR feature index of multiple frames of DR images, and presents the correlation between the DR feature index and the relevant information of the DR images through statistical results, thereby providing users with a quality control tool for DR images and enabling problems to be discovered and resolved in a timely manner.

[0050] Specifically, first, multiple frames of DR images and related information of each frame of DR images are acquired. The multiple frames of DR images can be multiple frames of DR images acquired within a preset time range, and the preset time range can be set by the user or can be a default time range. During DR imaging, the DR imaging system is controlled to emit X-rays to the target tissue part of the target object so that the X-rays pass through the target tissue part; the X-rays that pass through the target part are received, and a DR image is generated based on the X-rays that pass through the target part.

[0051] During the DR imaging process, the X-rays emitted by the X-ray source are attenuated to varying degrees after passing through the human body and are received by the flat-panel detector. Exemplarily, the upper layer of the flat-panel detector is an X-ray conversion medium, which has photoconductivity and can convert X-rays into electronic signals, generating positive and negative charges. These charges move along the electric field in the form of current under the action of the bias voltage and are collected by the detection unit array of the flat-panel detector. Each detection unit corresponds to a pixel of the DR image. A digital signal, i.e., a DR original image, can be obtained by amplifying and processing the electrical signal and performing analog-to-digital conversion. The DR original image can be a grayscale image that has not been post-processed by contrast adjustment, brightness adjustment, etc. The processed image of the DR original image can be an image of the DR original image after a certain transformation relationship, or an image of post-processing such as image contrast and image brightness adjustment. The DR image involved in the embodiment of the present invention can be a DR original image or a processed DR image, which is not specifically limited here.

[0052] The relevant information of the DR image includes information that may affect the imaging quality of the DR image. Exemplarily, the relevant information of the DR image includes at least one of the following: time information of the DR image, operating technician, patient position, and patient personal information. Among them, the patient personal information includes but is not limited to the patient's body shape, gender, age, etc.

[0053] Next, the DR feature index of the DR image is determined. Specifically, image features are extracted from the DR image, and the image features include at least one of grayscale entropy features, texture features, noise features, gradient features, and divergence features; the DR feature index is determined based on at least one image feature. The DR feature index can reflect the basic feature information content of the DR image, and can reflect the comprehensive level between the radiation dose of the X-ray and the image quality of the DR image. The DR feature index can also be called a DR feature index, a DR objectification index, or any other suitable name. Among them, the grayscale entropy feature, texture feature, noise feature, gradient feature, and divergence feature reflect the grayscale information, texture information, noise information, gradient information, and divergence information of the DR image, respectively. The multi-dimensional image features are conducive to obtaining a more accurate DR feature index, which can more comprehensively and accurately reflect the imaging effect of the DR image compared with conventional grayscale index and other evaluation indicators.

[0054] In one embodiment, the grayscale entropy feature is the information content obtained by statistically screening out redundant grayscale information sources in the DR image. According to the transmission characteristics of X-ray quanta converted into digital signals by the detector of the DR system, each independent grayscale in the DR image can be regarded as a source, and the DR imaging process can be regarded as a process of transmitting information through grayscale information sources. Among all the grayscales, there are some grayscales that do not have grayscale values, so they are regarded as redundant grayscale information sources. Since the extraction process of the grayscale entropy feature of the embodiment of the present invention screens out redundant grayscale information sources, more effective image information can be extracted.

[0055] For example, the grayscale entropy feature can be extracted from the DR image in the following manner:

[0056] First, the first probability statistical distribution pH(i) of each grayscale source in the DR image is obtained, where i is the image grayscale value of the DR image. Then, according to the size of the first probability statistical distribution, the first probability statistical distribution pNH(i) of the non-redundant grayscale source is determined from the first probability statistical distribution pH(i) of the grayscale source. Exemplarily, if the first probability statistical distribution pH(i) is greater than 0, it is determined to be the first probability statistical distribution pNH(i) of the non-redundant grayscale source. Conversely, if the first probability statistical distribution pH(i) is greater than 0, it is determined to be the first probability statistical distribution pNH(i) of the non-redundant grayscale source, that is:

[0057]

[0058] After obtaining the first probability statistical distribution pNH(i) of the non-redundant grayscale information source, the second probability statistical distribution pH'(i) of each non-redundant grayscale information source is obtained according to the ratio of the first probability statistical distribution pNH(i) of each non-redundant grayscale information source to the sum of the first probability statistical distributions ∑pNH(i) of all non-redundant grayscale information sources, that is:

[0059] pH'(i)=pNH(i) / ∑pNH(i) Formula (2)

[0060] Finally, entropy is calculated based on the second probability statistical distribution pH'(i) of the non-redundant grayscale information source to obtain the grayscale entropy feature H(Image). The method of calculating entropy includes but is not limited to taking the natural logarithm ln with e as the base or taking the logarithm with other values ​​as the base, which is expressed as follows:

[0061]

[0062] Thus, the grayscale entropy feature can be obtained after filtering out the redundant grayscale signal sources.

[0063] Texture features represent the spatial variation relationship of different grayscale values ​​on the DR image, which can reflect the abstract features of the law of changes in human tissue. For example, a statistical method can be used to extract the texture features of the DR image, which obtains the statistical characteristics of the texture area based on the grayscale attributes of the pixel and its neighborhood. The following mainly describes the specific details of the statistical method for extracting texture features, but the method for extracting texture features can also include geometric methods, model methods or other suitable texture feature extraction methods.

[0064] Exemplarily, when using statistical methods to extract texture features from a DR image, a texture feature description matrix is ​​first obtained based on the grayscale value of each pixel in the DR image; then, at least one two-dimensional component of the texture feature description matrix is ​​extracted as at least one texture feature.

[0065] In one embodiment, the texture feature description matrix describes the distance between different pixels and the change of grayscale values ​​in the direction between different pixels in the DR image. Assuming that the DR image Image = f(x, y), its texture feature description matrix P(i, j) is:

[0066] P(i,j)=#{(x1,y1),(x2,y2)∈M*N|f(x1,y1)=i,f(x2,y2)=j} Formula (4)

[0067] Among them, #(x) represents the number of elements in the set x. Assuming that the distance between two points (x1, y1) and (x2, y2) in the image is k, the texture feature description matrix in different directions l can be expanded to P(i, j, k, l). The texture feature description matrix can be expanded by counting the changes in grayscale values ​​at different distances and directions to obtain information in more dimensions. For example, in order to calculate the actual eigenvalues ​​at different angles, super-resolution interpolation can be performed on the DR image in each direction to obtain the sub-pixel grayscale values ​​corresponding to the new target position, and the texture feature description matrix in different directions can be obtained according to the sub-pixel grayscale values.

[0068] After obtaining the texture feature description matrix, extract at least one two-dimensional component of the texture feature description matrix to obtain a texture feature, where the texture feature reflects the key characteristics of the texture feature description matrix. Exemplarily, the texture feature includes at least one of the following:

[0069] The first texture feature P1 is used to count the value distribution of the texture feature description matrix and the overall distribution of texture changes in the DR image; the value of P1 can reflect the clarity of the DR image and the depth of the texture grooves. The deeper the texture grooves, the larger the P1 value, and vice versa, the shallower the grooves, the smaller the P1 value;

[0070] The second texture feature P2 is used to count the similarity between the value distribution in the texture feature description matrix and the parallel and normal directions in the DR image. The larger the P2 value, the greater the similarity of the grayscale of the image in different directions.

[0071] The third texture feature P3 is used to count the value distribution in the texture feature description matrix and the uniformity of the grayscale change distribution in the DR image. The size of the P3 value can reflect the uniformity of the image grayscale distribution and the coarseness of the texture. The larger the P3 value, the more stable the texture change of the DR image.

[0072] The fourth texture feature P4 is used to measure the distribution of values ​​in the texture feature description matrix and the local texture variation of the DR image. The larger the P4 value is, the stronger the regularity of the texture is.

[0073] The texture features extracted from the texture feature description matrix are not limited to the above four types. In other embodiments, other two-dimensional components of the texture feature description matrix may also be extracted as texture features.

[0074] Image noise mainly includes X-ray quantum noise, and the distribution of X-ray quanta obeys Poisson distribution, and its variance is proportional to the average number of quantum detections. Based on this characteristic of X-ray quantum noise, the fluctuation degree of X-ray quanta can be statistically analyzed from the DR image as the noise feature, that is, the noise feature reflects the fluctuation degree of X-ray quanta in the DR image.

[0075] In one embodiment, extracting noise features from a DR image includes the following steps: filtering the DR image to obtain a high-frequency image, wherein the high-frequency image obtained from the DR image mainly contains noise information; calculating the root mean square of the neighborhood of each pixel point in the high-frequency image to obtain a noise distribution image; and statistically analyzing the distribution of noise values ​​in the noise distribution image to obtain the noise features.

[0076] As an implementation, filtering the DR image to obtain a high-frequency image includes: performing low-frequency filtering on the DR image I to filter out the low-frequency components therein to obtain a low-frequency image I1; and obtaining the high-frequency image I2 according to the difference between the low-frequency image and the DR image. In other implementations, the DR image I may also be directly subjected to high-frequency filtering to obtain the high-frequency image I2.

[0077] Exemplarily, the DR image I can be subjected to Gaussian low-pass filtering to obtain a low-frequency image I1. Since the image is a two-dimensional signal, a two-dimensional Gaussian function is used for Gaussian low-pass filtering, and the two-dimensional Gaussian filter kernel is:

[0078]

[0079] The high-frequency image I2 can be obtained by calculating the difference between the low-frequency image I1 and the image I, that is, I2=I1-I. The noise distribution image I3 can be obtained by extracting the effective information in the high-frequency image I2. In one embodiment, the noise distribution image I3 is an image formed by calculating the root mean square of the neighborhood of each pixel point in the high-frequency image. The method for calculating the root mean square includes using the L1 norm or other approximate or equivalent measures, for example:

[0080]

[0081] Among them, I3(i,j) is the value of the noise distribution image I3 at the pixel point (i,j), and I2(l,k) is the value of the high frequency I2 at the pixel point (l,k).

[0082] After acquiring the noise distribution image I3, the noise value distribution thereof is statistically analyzed to obtain the acoustic feature. For example, the noise value interval with the highest noise value distribution probability in the noise distribution image can be determined, and the noise value of the noise value interval with the highest noise value distribution probability is used as the noise feature.

[0083] Specifically, first, the pixel values ​​of the noise distribution image I3 are divided into M intervals, the pixel value interval of each interval is d, the initialization histogram vector is h, the length is M, and each component h(i) of the initialization histogram represents the number of pixel values ​​in the i-th interval. For the pixel point (i, j) in the noise distribution image I3, the interval corresponding to the pixel value of this point is R[I3(i, j)]. After traversing each pixel point of the noise distribution image I3 and counting h(R(I3(i, j))), after obtaining h, the maximum value of its main peak is max(h), corresponding to the interval R0=arg max(h), then the noise distribution probability R0*d is calculated as the noise feature.

[0084] In some embodiments, the image features also include gradient features. Due to the different absorption coefficients of X-rays after penetrating different tissues of the human body, regional distributions of different tissues will be formed in the DR image, and there will be different degrees of boundaries between different tissue regions. The clarity of these boundaries can be quantified by extracting gradient features, that is, gradient features are used to characterize the clarity of boundaries between different tissues in the DR image. In one embodiment, extracting gradient features from a DR image includes: determining the regional distribution of different tissues in the DR image; obtaining the clarity of the boundaries of different tissue regional distributions as gradient features.

[0085] Exemplarily, the gradient feature can be calculated as follows:

[0086]

[0087] Among them, Grad(x,y) is used to represent the gradient size at the coordinates (x,y), and Image(x,y) is used to represent the pixel value at the coordinates (x,y).

[0088] In some embodiments, the image features also include divergence features. In DR images, the boundaries of different tissues are not strict boundaries, but there is a certain degree of transition. The strength and / or trend consistency of this transition can be quantified by extracting the divergence features, that is, the divergence features are used to characterize the strength and / or trend consistency of the transition of the boundaries of different tissues in the DR image. In one embodiment, extracting the divergence features from the DR image includes: determining the regional distribution of different tissues in the DR image; obtaining the strength and / or trend consistency of the transition of the boundaries of the regional distribution of different tissues as the divergence features.

[0089] For example, the divergence feature can be calculated as follows:

[0090]

[0091] Among them, Diver(x,y) is used to represent the divergence size at the coordinates (x,y), Image(x,y) is used to represent the pixel value at the coordinates (x,y), and actan represents the inverse tangent function.

[0092] In some embodiments, in addition to at least one of the above image features, other image features can also be extracted from the DR image for obtaining the DR feature index, such as grayscale gradient, grayscale mean, variance, pixel value information, signal-to-noise ratio, contrast-to-noise ratio, etc. The specific features can be determined according to actual conditions and are not specifically limited here.

[0093] After extracting the above-mentioned image features from the DR image, the image features can be input into a pre-trained target model, and the DR feature index output by the target model can be obtained. In the model training stage, first, a DR image set is obtained, and the DR image set includes multiple sample DR images, that is, DR images used as training samples. An image feature set can be obtained based on the DR image set, and the image feature set includes sample image features extracted from multiple sample DR images. Exemplarily, for each sample DR image in the DR image set, at least one sample image feature of grayscale entropy features, texture features, noise features, gradient features, and divergence features is extracted respectively, and multiple sample image features extracted from multiple sample DR images in the DR image set together constitute an image feature set, and each sample DR image in the DR image set corresponds to at least one sample image feature in the image feature set.

[0094] A scoring set can also be obtained according to the DR image set, and the scoring set includes the scores obtained by evaluating multiple sample DR images. Exemplarily, if the sample DR images in the DR image set are DR original images, the multiple sample DR images in the DR image set can be image processed separately to obtain multiple DR diagnostic images, that is, visual images used by doctors for diagnosis, and the multiple DR diagnostic images constitute a DR diagnostic image set, and the above-mentioned scoring set is obtained according to the DR diagnostic image set, and the scoring set includes the scores obtained by evaluating multiple DR diagnostic images. In some embodiments, clinical experts can evaluate the DR diagnostic images in the DR diagnostic image set according to the quality of the DR diagnostic images and give expert scores. The higher the score of the DR diagnostic image, the more basic feature information content is contained in the corresponding DR original image; conversely, the lower the score of the DR diagnostic image, the less basic feature information content is contained in the corresponding DR original image. The expert scores of the DR diagnostic images constitute the expert scoring set. Optionally, if the DR images in the DR image set are visual images used by doctors for diagnosis, the scoring set can be directly obtained according to the DR image set.

[0095] Afterwards, the initial model is trained using the acquired image feature set and score set as a training sample set to obtain a target model. The target model may be a traditional machine learning model or a deep learning model, including but not limited to a neural network, a support vector machine, a linear discriminant analysis, etc. The training method includes but is not limited to model training methods such as linear regression and gradient descent. Exemplarily, an optimal mapping function from image features to scores can be learned so that the error between the DR feature index obtained by the image feature mapping and the actual calibrated expert score is minimized.

[0096] In one embodiment, when the image feature set, the parameter feature set and the score set are used for classification and regression training, the classification and regression training formula used is:

[0097]

[0098] Among them, x is the feature vector, {x i} i＝1,…,m is the support vector, α i is the weighting coefficient, b is the bias, k is the kernel function, and each value of the eigenvector x needs to be obtained through the linear transfer function:

[0099]

[0100] in, is the input feature, w and s are the scaling and translation parameter vectors respectively, and the kernel function k can be or

[0101] It should be noted that the embodiments of the present invention do not limit the linear transfer function, kernel function or parameters used in the regression training method.

[0102] After obtaining the trained target model in the model training stage, in the actual application process, at least one image feature among the grayscale entropy feature, texture feature, noise feature, gradient feature and divergence feature extracted from the DR image is input into the trained network model to obtain the DR feature index. Optionally, the image features can also be comprehensively calculated according to a preset function to obtain the DR feature index. The DR feature index can characterize the basic feature information content of the DR image, and can also characterize the comprehensive level between the radiation dose of X-rays received by the target object and the image quality of the DR image. The comprehensive level refers to the quality of the image of the DR image, and the comprehensive level of the radiation dose of the X-rays received. If the user thinks that the image quality is good and meets the requirements, the DR feature index can be lowered to achieve the effect of reducing the radiation dose of the X-rays received; similarly, if the image quality is considered to be poor, the DR feature index can be increased to achieve the effect of improving the image quality.

[0103] After obtaining the DR characteristic index of multiple frames of DR images, the statistical results are determined based on the DR characteristic index of the multiple frames of DR images and the relevant information of the multiple frames of DR images, and the statistical results are output. Exemplarily, the statistical results include the classified statistical results of the DR characteristic index under at least one of the relevant information, and specifically may be the correspondence between the statistical value of the DR characteristic index and the relevant information. The statistical values ​​of the DR characteristic index include the mean, median, standard deviation, the number of images whose DR characteristic index meets the reference level of the DR characteristic index, or the number of images whose DR characteristic index does not meet the reference level of the DR characteristic index, etc. According to the statistical results, the changing trend of the DR characteristic index or the main factors affecting the DR characteristic index can be determined, and targeted measures can be taken.

[0104] For example, when the statistical results are determined based on the operating technician and the DR characteristic index, the average value, standard deviation and other statistical values ​​of the DR characteristic index of the DR images taken by different operating technicians can be counted, and the differences between different operating technicians can be intuitively known through comparison. When the statistical results are determined based on the patient's body position and the DR characteristic index, the DR characteristic index of the DR images corresponding to different body positions can be counted, so as to determine the influence of the patient's body position on the DR characteristic index, and the imaging parameters can be adjusted in a targeted manner when shooting in this position. Similarly, corresponding statistical results can be obtained for different relevant information, so as to conveniently form a management tool, conduct retrospective statistical analysis of historical DR images, and conveniently discover, locate and solve problems through the analysis results.

[0105] Exemplarily, the user can select relevant information of interest from a variety of relevant information and view the corresponding classified statistical results. Specifically, a selection operation is performed on a variety of relevant information, target relevant information is determined from a variety of relevant information based on the selection operation, and the classified statistical results of the DR feature index under the target relevant information are output. The target relevant information may include one or more, that is, at the same time, only the classified statistical results of the DR feature index under one target relevant information may be output, or the classified statistical results of the DR feature index under multiple target relevant information may be output simultaneously. The classified statistical results of the DR feature index under multiple target relevant information may be output separately or fused.

[0106] In order to present the statistical results intuitively, the statistical results can be output in a graphical form, that is, the output statistical results can include a corresponding relationship diagram between the DR feature index and related information. For example, the corresponding relationship diagram between time information and the DR feature index can include a trend diagram of the DR feature index changing over time, and the trend diagram can include a line graph, a curve graph, a histogram, etc. Specifically, the DR feature index statistical value of the DR image collected in each time period can be determined, and a trend diagram of the DR feature index changing over time can be drawn in chronological order.

[0107] The correspondence diagram between the operating technician, the patient's body position or the patient's personal information and the DR feature index includes a distribution diagram of the DR feature index under different operating technicians, patient's body positions or patient's personal information, and the specific form of the distribution diagram includes but is not limited to a histogram, a pie chart, a radar chart, etc. For example, the DR feature index statistical value of the DR image collected by each operating technician can be counted, and a histogram can be drawn with the operating technician as the first coordinate and the DR feature index statistical value as the second coordinate. Exemplarily, in addition to the correspondence diagram, the statistical results can also be output in a table.

[0108] In some embodiments, a DR characteristic index reference level can also be obtained, and an identifier representing the DR characteristic index reference level can be displayed in a corresponding relationship diagram, so that the user can quickly locate the DR characteristic index statistical value that does not meet the DR characteristic index reference level and view the corresponding related information. For example, a horizontal line representing the DR characteristic index reference level can be drawn in a line graph or a histogram. Alternatively, the DR characteristic index statistical values ​​that do not meet the DR characteristic index reference level can also be marked in the corresponding relationship diagram to attract the user's attention. For example, the corresponding time period can be marked in the line graph, and the corresponding rectangle can be displayed as a specific color in the histogram. Exemplarily, different related information can correspond to different DR characteristic index reference levels, and the DR characteristic index reference level is set according to the received operation instruction or the system default setting.

[0109] As clinical needs vary, the DR characteristic index reference level is not static. For example, if the hospital requires a reduction in the X-ray radiation dose, the DR characteristic index reference level will also be reduced. In order to make the DR characteristic index reference level meet clinical needs, the current DR characteristic index reference level can also be calibrated according to actual needs, and the current DR characteristic index reference level is calibrated in response to the calibration operation, and the calibrated DR characteristic index reference level is obtained. The calibration operation can be manually triggered by the user, and there are many ways to trigger the calibration operation, such as touch control, button control, remote control control, gesture control or voice control.

[0110] Alternatively, a calibration operation may be automatically triggered, such as regularly calibrating the DR characteristic index reference level. In addition, the frequency of the recent DR characteristic index not meeting the DR characteristic index reference level may be counted. If the frequency is too high, it indicates that the current DR characteristic index reference level no longer meets clinical needs, and calibration may be triggered at this time.

[0111] In one embodiment, multiple frames of reference DR images can be acquired, and the current DR characteristic index reference level can be calibrated based on the multiple frames of reference DR images. The multiple frames of reference DR images can be DR images that meet certain requirements, or they can be multiple frames of DR images acquired randomly. The DR characteristic index reference level can be calibrated based on the statistical results of the DR characteristic index of the multiple frames of reference DR images, and the statistical results include statistical values ​​such as mean, mean square error, and median. Calibrating the current DR characteristic index reference level based on the statistical results can be to directly use the statistical results such as the mean as the calibrated DR characteristic index reference level, or it can be to adjust the current DR characteristic index reference level based on the statistical results, such as weighted summing the statistical results and the current DR characteristic index reference level.

[0112] Exemplarily, the DR feature index of multiple frames of reference DR images can be calculated during the calibration process. Specifically, after acquiring multiple frames of reference DR images, the DR feature index of each frame of reference DR image is calculated, thereby eliminating the need to calculate the DR feature index for all DR images. Alternatively, while acquiring multiple frames of reference DR images, the DR feature index stored in association with each frame of reference DR image can also be acquired, that is, the DR feature index is calculated and stored when the reference DR image is acquired. Each time DR imaging is performed, its DR feature index is calculated and stored, so that during calibration, there is no need to calculate the DR feature index of a batch of DR images at one time, thereby improving the calibration speed.

[0113] Exemplarily, the multiple frames of reference DR images may be multiple frames of historical DR images acquired within a preset time range. The preset time range may be set based on user operation, for example, the user may select a time period during which the hospital reduces the dose as the preset time range; or, a default preset time range may be used. Furthermore, historical DR images may be automatically screened, and historical DR images that meet the preset requirements may be selected to calibrate the reference level of the DR characteristic index.

[0114] Exemplarily, the reference DR image can also be manually selected by the user. Specifically, multiple frames of historical DR images acquired within a preset time range are displayed, and the historical DR images are selected, and the selected historical DR images are determined as reference DR images. For example, multiple frames of historical DR images can be displayed frame by frame or tiled in batches in the calibration interface, and in-hospital experts can observe the image quality of historical DR images and select several frames of historical DR images that they agree on for calibrating the reference level of the DR characteristic index.

[0115] When outputting the statistical results, the DR characteristic index of multiple frames of DR images can also be compared with the DR characteristic index reference level, and the DR image whose DR characteristic index does not meet the DR characteristic index reference level is determined as the target DR image, and the statistical results of at least one relevant information of the target DR image are displayed. The DR characteristic index not meeting the DR characteristic index reference level can be that the difference between the DR characteristic index and the DR characteristic index reference level is greater than a preset threshold. By presenting the statistical results of the target DR image separately, it can help users quickly find problems. For example, the number of images whose DR characteristic index does not meet the DR characteristic index reference level in the DR images collected by each operating technician can be counted, and a histogram between the number of images and the operating technician can be drawn, so as to quickly determine which operating technicians have collected too many unqualified DR images, and make targeted improvements.

[0116] In one embodiment, the relevant information includes first relevant information and second relevant information. When outputting statistical results, first, from the multiple frames of DR images, multiple frames of first DR images corresponding to the first relevant information are extracted, and a first reference level of the DR feature index corresponding to the first relevant information is obtained; the DR feature index of the multiple frames of first DR images is compared with the first reference level to determine the first DR image whose DR feature index does not meet the first reference level; and the statistical results of the second relevant information of the first DR image are determined and displayed.

[0117] For example, taking the case where the first relevant information is a certain patient position and the second relevant information is an operating technician, firstly, the first DR image corresponding to the certain patient position is extracted from the multi-frame DR image total, and its DR characteristic index is compared with the first reference level to obtain an unqualified DR image in the first DR image corresponding to the certain patient position. When outputting the statistical results, this part of unqualified DR images is classified according to the operating technician, so as to locate the operating technician corresponding to the unqualified DR image, and provide a basis for further corrective measures.

[0118] Based on the above description, the statistical analysis method 100 of DR images according to an embodiment of the present invention performs statistical analysis on the DR feature index of multiple frames of DR images, and presents the correlation between the DR feature index and the relevant information of the DR images through statistical results, thereby providing users with a quality control tool for DR images.

[0119] Another embodiment of the present invention provides a method for statistical analysis of DR images. Figure 2 The DR image statistical analysis method 200 comprises the following steps:

[0120] In step S210, a plurality of frames of digital X-ray photography DR images and related information of the plurality of frames of DR images are acquired, wherein the related information includes at least one of time information of the DR images, an operating technician, a patient's body position, and patient personal information;

[0121] In step S220, a DR feature index reflecting the basic feature information content of the multiple DR images is determined;

[0122] In step S230, statistical analysis is performed on the DR feature indexes of the multiple frames of DR images according to at least one of the related information to obtain a statistical analysis result, and the statistical analysis result is displayed.

[0123] In some embodiments, the relevant information includes multiple types, and a selection operation can be performed on the multiple types of relevant information. Based on the selection operation, the target relevant information is determined from the multiple types of relevant information, and the classified statistical results of the DR feature index under the target relevant information are output.

[0124] In some embodiments, the statistical results include a corresponding relationship diagram between the DR characteristic index and related information, such as a line graph, a curve graph, a histogram, a pie chart, etc.

[0125] Furthermore, the DR characteristic index reference level can be obtained, and the symbol representing the DR characteristic index reference level can be displayed in the corresponding relationship diagram to help users determine whether the statistical results of the DR characteristic index corresponding to each relevant information meet the requirements.

[0126] An exemplary method of displaying the statistical results includes: comparing the DR characteristic index of multiple frames of DR images with the DR characteristic index reference level; determining the DR image whose DR characteristic index does not meet the DR characteristic index reference level as the target DR image, and displaying the statistical results of at least one related information of the target DR image. By displaying the statistical results of the target DR image that does not meet the requirements, it can help users quickly find problems and find out the specific causes of the problems.

[0127] In some embodiments, the relevant information includes first relevant information and second relevant information, and another exemplary method of displaying statistical results includes: obtaining a first reference level of a DR feature index corresponding to the first relevant information; extracting multiple frames of first DR images corresponding to the first relevant information from multiple frames of DR images; comparing the DR feature index of the multiple frames of first DR images with the first reference level, and determining a first DR image whose DR feature index does not meet the first reference level; and determining and displaying the statistical results of the second relevant information of the first DR image.

[0128] The statistical analysis method 200 of DR images in the embodiment of the present invention is similar to the statistical analysis method 100 of DR images, and also performs statistical analysis on the DR feature index of multiple frames of DR images, and presents the correlation between the DR feature index and the relevant information of the DR images through the statistical results, thereby providing the user with a quality control tool for DR images. The difference is that the statistical analysis method 200 of DR images in the embodiment of the present invention does not limit the way of obtaining the DR feature index, and the DR feature index can be determined based on at least one image feature of grayscale entropy feature, texture feature, noise feature, gradient feature and divergence feature, or can be determined by other methods. For more specific details, please refer to the relevant description above, which will not be repeated here.

[0129] Another embodiment of the present invention provides a DR imaging system, see Figure 3 The DR imaging system 300 includes: an X-ray source 310, a flat panel detector 320, a processor 330 and an output device 340, wherein the processor 330 is communicatively connected with the X-ray source 310, the flat panel detector 320 and the output device 340; the X-ray source 310 is used to generate X-rays, emit X-rays to a target tissue part of a target object, and control the X-rays to pass through the target tissue part; the flat panel detector 320 is used to receive the X-rays after passing through the target tissue part; the processor 330 is used to process the X-rays after passing through the target tissue part to obtain a digital X-ray photography DR image, and the output device 340 is used to output the DR image.

[0130] Exemplarily, the X-ray source 310 includes a tube for emitting X-rays; the flat panel detector 320 includes an X-ray conversion medium located in the upper layer and a detection unit array located in the lower layer. The X-ray conversion medium converts X-rays into electronic signals, generates positive and negative charges, and these charges move along the electric field in the form of current under the action of the bias voltage, are collected by the detection unit array, and converted into electrical signals. The flat panel detector 320 includes but is not limited to amorphous silicon, amorphous selenium, CCD, etc. When using the DR imaging system 300 for image acquisition, the position of the X-ray source 310 and the position of the flat panel detector 320 need to be fixed in a specified manner, so that the X-rays emitted by the X-ray source 310 can irradiate the flat panel detector 320 after passing through the target tissue, so that the flat panel detector 320 can collect the X-rays after passing through the target tissue site to obtain a DR image.

[0131] The processor 330 is used to process the X-rays after passing through the target tissue site to obtain a digital X-ray photography DR image. The processor 330 is also used to perform the steps of the above-mentioned DR image statistical analysis method 100 or DR image statistical analysis method 200; the output device 340 is used to output the DR image. The specific details of the DR image statistical analysis method can be referred to above.

[0132] The DR imaging system 300 of the embodiment of the present invention performs statistical analysis on the DR feature index of multiple frames of DR images, presents the correlation between the DR feature index and the relevant information of the DR images through the statistical results, and can provide users with a quality control tool for DR images.

[0133] In addition, according to an embodiment of the present invention, a computer storage medium is also provided, on which program instructions are stored, and when the program instructions are executed by a computer or a processor, the corresponding steps of the statistical analysis method of DR images of any embodiment of the present invention are executed. In some embodiments, the computer storage medium is a non-volatile computer-readable storage medium, which may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created during the execution of program instructions, etc. In addition, the non-volatile computer-readable storage medium may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the non-volatile computer-readable storage medium may optionally include a memory remotely arranged relative to the processor.

[0134] Exemplarily, the computer storage medium may include, for example, a hard disk of a personal computer, a storage component of a tablet computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory, a memory card of a smart phone, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0135] In addition, according to an embodiment of the present invention, a computer program is also provided, which can be stored in a cloud or local storage medium. When the computer program is executed by a computer or a processor, it is used to perform the corresponding steps of the statistical analysis method of DR images in the embodiment of the present invention.

[0136] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present invention thereto. Various changes and modifications may be made therein by one of ordinary skill in the art without departing from the scope and spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as required by the appended claims.

[0137] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0138] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0139] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0140] Similarly, it should be understood that in order to streamline the present invention and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present invention should not be interpreted as reflecting the following intention: the claimed invention requires more features than the features explicitly stated in each claim. More specifically, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present invention.

[0141] It will be understood by those skilled in the art that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0142] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0143] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some modules in the article analysis device according to an embodiment of the present invention. The present invention may also be implemented as a device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0144] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0145] The above is only a specific embodiment of the present invention or an explanation of a specific embodiment. The protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A statistical analysis method for DR images, characterized in that: The method comprises: Acquire multiple frames of digital X-ray photography DR images and related information of the multiple frames of DR images; Extracting image features from the DR image, the image features comprising at least one of grayscale entropy features, texture features, noise features, gradient features, and divergence features; Determining a DR feature index reflecting the basic feature information content of the DR image according to at least one image feature of the grayscale entropy feature, the texture feature, the noise feature, the gradient feature, and the divergence feature; A statistical result is determined according to the DR feature index of the multiple frames of DR images and the related information of the multiple frames of DR images, and the statistical result is output.

2. The method according to claim 1, characterized in that The relevant information includes at least one of the following: The time information of the DR image, the operating technician, the patient's body position, and the patient's personal information, and the statistical result includes the classified statistical result of the DR feature index under at least one of the relevant information.

3. The method according to claim 2, characterized in that Also includes: Determining target related information from the plurality of related information based on the received operation instruction; The classified statistical results of the DR characteristic index under at least one of the relevant information include the classified statistical results of the DR characteristic index under the target relevant information.

4. The method according to claim 2, characterized in that The statistical result includes a corresponding relationship diagram between the DR characteristic index and the relevant information.

5. The method according to claim 4, characterized in that The relevant information includes time information, and the corresponding relationship diagram includes a trend diagram of the DR characteristic index changing with time.

6. The method according to claim 4, characterized in that The relevant information includes an operating technician, a patient's body position or a patient's personal information, and the corresponding relationship diagram includes a distribution diagram of the DR characteristic index under different operating technicians, patient's body positions or patient's personal information.

7. The method according to claim 4, characterized in that Also includes: Obtaining the reference level of DR characteristic index; The corresponding relationship diagram shows an identifier representing the reference level of the DR characteristic index.

8. The method according to claim 1, characterized in that The outputting of the statistical results comprises: Obtaining the reference level of DR characteristic index; comparing the DR characteristic index of the multiple frames of DR images with the DR characteristic index reference level; A DR image whose DR characteristic index does not meet the DR characteristic index reference level is determined as a target DR image, and a statistical result of at least one of the related information of the target DR image is displayed.

9. The method according to claim 7 or 8, characterized in that The DR characteristic index reference level is set according to a received operation instruction or a system default setting.

10. The method according to claim 1, characterized in that The relevant information includes first relevant information and second relevant information, and the determining of statistical results according to the DR feature index of the multiple frames of DR images and the relevant information of the multiple frames of DR images, and outputting the statistical results, includes: Acquire a first reference level of a DR characteristic index corresponding to the first relevant information; Extracting, from the multiple frames of DR images, multiple frames of first DR images corresponding to the first relevant information; comparing the DR feature indexes of the plurality of frames of first DR images with the first reference level, and determining a first DR image whose DR feature index does not meet the first reference level; A statistical result of the second related information of the first DR image is determined and displayed.

11. The method according to claim 1, characterized in that The grayscale entropy feature can be extracted from the DR image in the following manner: Obtaining a first probability statistical distribution of each grayscale source in the DR image; Determining a first probability statistical distribution of a non-redundant grayscale information source from the first probability statistical distribution of the grayscale information source according to the size of the first probability statistical distribution; Obtaining a second probability statistical distribution of each non-redundant grayscale information source according to a ratio of the first probability statistical distribution of each non-redundant grayscale information source to the sum of the first probability statistical distributions of all non-redundant grayscale information sources; The entropy of the second probability statistical distribution of the non-redundant grayscale information source is calculated to obtain the grayscale entropy feature.

12. The method according to claim 1, characterized in that The texture features can be extracted from the DR image in the following manner: A texture feature description matrix is ​​obtained according to the gray value of each pixel in the DR image, wherein the texture feature description matrix describes the distance between different pixel points and the change of the gray value in the direction between different pixel points in the DR image; At least one two-dimensional component of the texture feature description matrix is ​​extracted as the texture feature.

13. The method according to claim 1, characterized in that The noise feature can be extracted from the DR image in the following manner: Performing filtering on the DR image to obtain a high-frequency image; Calculating the root mean square of the neighborhood of each pixel in the high-frequency image to obtain a noise distribution image; The noise value distribution in the noise distribution image is statistically analyzed to obtain the noise feature.

14. The method according to claim 1, characterized in that The gradient feature can be extracted from the DR image in the following manner: Determining the regional distribution of different tissues in the DR image; The clarity of the boundaries of different tissue region distributions is obtained as the gradient feature.

15. The method according to claim 1, characterized in that The divergence feature can be extracted from the DR image in the following manner: Determining the regional distribution of different tissues in the DR image; The transition strength and / or trend consistency of the boundaries of different tissue region distributions are obtained as the divergence feature.

16. A statistical analysis method for DR images, characterized in that: The method comprises: Acquire multiple frames of digital X-ray photography DR images and related information of the multiple frames of DR images, wherein the related information includes at least one of time information of the DR images, an operating technician, a patient's body position, and patient personal information; Determining a DR feature index reflecting basic feature information content of the multiple frames of DR images; Perform statistical analysis on the DR feature indexes of the multiple frames of DR images according to at least one of the related information to obtain statistical analysis results, and display the statistical analysis results.

17. The method according to claim 16, characterized in that Also includes: Performing a selection operation on a plurality of the related information; Based on the selection operation, target related information is determined from the multiple related information, and the statistical analysis result includes a classification statistical result of the DR feature index under the target related information.

18. The method according to claim 16, characterized in that The statistical result includes a corresponding relationship diagram between the DR characteristic index and the relevant information.

19. The method according to claim 18, characterized in that Also includes: Obtaining the reference level of DR characteristic index; The corresponding relationship diagram shows an identifier representing the reference level of the DR characteristic index.

20. The method of claim 16, wherein: The displaying of the statistical results comprises: Obtaining the reference level of DR characteristic index; comparing the DR characteristic index of the multiple frames of DR images with the DR characteristic index reference level; A DR image whose DR characteristic index does not meet the DR characteristic index reference level is determined as a target DR image, and a statistical result of at least one of the related information of the target DR image is displayed.

21. The method of claim 16, wherein: The relevant information includes first relevant information and second relevant information, and the statistical analysis of the DR feature indexes of the multiple DR images is performed according to at least one of the relevant information to obtain a statistical analysis result, and the statistical analysis result is displayed, including: Acquire a first reference level of a DR characteristic index corresponding to the first relevant information; Extracting, from the multiple frames of DR images, multiple frames of first DR images corresponding to the first relevant information; Comparing the DR characteristic indexes of the plurality of frames of first DR images with the first DR characteristic index reference level, and determining a first DR image whose DR characteristic index does not meet the first DR characteristic index reference level; A statistical result of the second related information of the first DR image is determined and displayed.

22. A DR imaging system, characterized in that: The DR imaging system includes: an X-ray source, a flat panel detector, a processor and an output device; The X-ray source is used to emit X-rays to a target part of a target object so that the X-rays pass through the target part; The flat panel detector is used to receive X-rays after passing through the target part; The processor is used to process the X-rays after passing through the target part to obtain a DR image, and the processor is also used to perform the statistical analysis method of the DR image according to any one of claims 1 to 21; The output device is used to output the DR image.

Images