DR image analysis method and electronic equipment

Abstract

The invention discloses a DR image analysis method and electronic equipment, and the method comprises the steps: obtaining a DR image which comprises at least one of a DR original image and a processed image of the DR original image; 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; and inputting at least one image feature of the gray entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature into a target model, and outputting a DR image index reflecting the basic feature information content of the DR image. The DR image index capable of objectively reflecting the basic feature information content of the DR image is obtained from the image features extracted from the DR image, so that an objective image judgment basis is provided for an operator.

Description

[0001] This application is a divisional application of the patent application No. 202111193213.7 filed on October 13, 2021. TECHNICAL FIELD

[0002] The present application relates to the technical field of medical image, more particularly to a DR image analysis method and an electronic device. BACKGROUND

[0003] As a common type of medical digital image, digital radiography (DR) image is widely used in physical examination and routine medical image diagnosis field. With the development of digital X-ray detector and digital image processing system, DR image can often present an image effect that can be used for diagnosis within a wide exposure dose range. However, in the image acquisition process, the final image effect is often grasped by the experience of the operator technician, and the accuracy of the judgment is easily affected by experience difference, subjective difference and post-processing and other factors.

[0004] In order to reflect the effect of DR image, one way is to use exposure index (EI) to indicate the size of single exposure amount, but exposure index usually has energy dependence for specific line quality, and exposure index usually only uses the gray scale information of the image. Due to the complexity and diversity of clinical images and human body structure, exposure index cannot well reflect the image information actually used for diagnosis in DR image. SUMMARY

[0005] A series of simplified concepts are introduced in the summary section, which will be further described in detail in the specific embodiment section. The summary section of the present application does not mean to try to limit the key features and necessary technical features of the claimed technical solution, nor to try to determine the protection scope of the claimed technical solution.

[0006] In one aspect, the present application provides a DR image analysis method, the method comprising:

[0007] emitting X-rays to a target tissue site and controlling the X-rays to pass through the target tissue site;

[0008] receiving the X-rays after passing through the target tissue site;

[0009] processing the X-rays after passing through the target tissue site to obtain a digital radiography (DR) image, wherein the DR image comprises at least one of a DR original image and an image after the DR original image is processed;

[0010] extracting image features from the DR image, the image features comprising at least one of a gray level entropy feature, a texture feature, a noise feature, a gradient feature and a divergence feature;

[0011] inputting the at least one of the gray level entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature into a target model, and outputting, by the target model, a DR image index reflecting a basic feature information content of the DR image.

[0012] Another aspect of the present application provides a method for analyzing a DR image, the method comprising:

[0013] obtaining a digital radiography DR image, wherein the DR image comprises at least one of a DR original image and an image processed from the DR original image;

[0014] extracting image features from the at least one of the DR original image and the image processed from the DR original image, the image features comprising at least one of a gray level entropy feature, a texture feature, a noise feature, a gradient feature and a divergence feature;

[0015] determining, according to the at least one of the gray level entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature, a DR image index reflecting a basic feature information content of the DR image;

[0016] outputting the DR image index reflecting the basic feature information content of the DR image.

[0017] Another aspect of the present application provides a method for analyzing a DR image, the method comprising:

[0018] obtaining a digital radiography DR image, wherein the DR image comprises at least one of a DR original image and an image processed from the DR original image;

[0019] determining, according to the at least one of the DR original image and the image processed from the DR original image, a DR image index reflecting a basic feature information content of the DR image;

[0020] outputting the DR image index reflecting the basic feature information content of the DR image.

[0021] Another aspect of the present application provides a method for analyzing a DR image, the method comprising:

[0022] acquire a digital radiography (DR) image and image features corresponding to the DR image, wherein the DR image comprises at least one of a DR original image and a processed image of the DR original image, and the image features comprise at least one of a gray entropy feature, a texture feature, a noise feature, a gradient feature and a divergence feature;

[0023] determine a DR image index reflecting a basic feature information content of the DR image according to the DR image and the image features corresponding to the DR image;

[0024] output the DR image index reflecting the basic feature information content of the DR image.

[0025] Another aspect of the present application provides a DR imaging device, which comprises:

[0026] an X-ray generator, a detector, a processor and a display;

[0027] the X-ray generator is configured to generate X-rays, emit the X-rays to a target tissue site, and control the X-rays to pass through the target tissue site;

[0028] the detector is configured to receive the X-rays after passing through the target tissue site, and process the X-rays after passing through the target tissue site to acquire a digital radiography (DR) image, wherein the DR image comprises at least one of a DR original image and a processed image of the DR original image;

[0029] the processor is configured to input at least one of the gray entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature into a target model, and output a DR image index reflecting a basic feature information content of the DR image through the target model;

[0030] the display is configured to display the DR image index reflecting the basic feature information content of the DR image.

[0031] Another aspect of the present application provides an electronic device, which comprises a memory and a processor, wherein the memory stores a computer program running by the processor, and the computer program performs the steps of the DR image analysis method provided by the present application when running by the processor.

[0032] In the present application, a DR image index reflecting a basic feature information content of a DR image is obtained according to image features extracted from the DR image, so as to provide an objective image judgment basis for an operator. BRIEF DESCRIPTION OF DRAWINGS

[0033] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0034] Figure 1 A schematic flow chart showing a method for analyzing a DR image according to an embodiment of the present invention;

[0035] Figure 2 A schematic diagram illustrating model training and DR image analysis using the trained network model according to one embodiment of the present invention is shown;

[0036] Figure 3 A schematic flow chart showing a method for analyzing a DR image according to another embodiment of the present invention;

[0037] Figure 4 A structural block diagram of an electronic device according to an embodiment of the present invention is shown;

[0038] Figure 5 A schematic flow chart showing a method for analyzing a DR image according to another embodiment of the present invention;

[0039] Figure 6 A schematic flow chart showing a method for analyzing a DR image according to another embodiment of the present invention;

[0040] Figure 7 A structural block diagram of a DR imaging device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the present application more apparent, the following is a detailed description of example embodiments of the present application with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in this application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of this application.

[0042] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present application. However, it will be apparent to those skilled in the art that the present application can be implemented without one or more of these details. In other examples, some technical features well known in the art are not described in order to avoid confusion with the present application.

[0043] It is to be understood that the application can assume various alternative embodiments, and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

[0044] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising", when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0045] For a thorough understanding of the application, reference will be made to the following detailed description, in which reference will be made to the drawings. Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein.

[0046] Below, first reference Figure 1 The analysis method 100 of the DR image according to an embodiment of the application is described. The analysis method can be applied to a DR imaging device, and can also be applied to other electronic devices, such as a computer, a smart terminal, etc. As shown in Figure 1 The analysis method 100 of the DR image can include the following steps:

[0047] In step S110, a digital X-ray radiography DR image is acquired;

[0048] In the embodiment of the application, the device acquiring the DR image can be acquired locally, or acquired from other external devices, which is not limited here. Wherein, the local acquisition can be real-time acquisition of the DR image by the device, or non-real-time acquisition and local storage.

[0049] In one possible implementation, the specific process of the device acquiring the DR image from the local is as follows:

[0050] X-rays are emitted to a target tissue site, and the X-rays are controlled to pass through the target tissue site; the X-rays after passing through the target tissue site are received; and the X-rays after passing through the target tissue site are processed to acquire a digital X-ray radiography DR image. Wherein, the target tissue site can be a tissue site to be examined of a human body or other animal body. For example, head, abdomen, etc.

[0051] In the present application, the DR image includes at least one of a DR original image and an image after the DR original image is processed. The DR original image is a gray-scale image without post-processing such as contrast adjustment and brightness adjustment. For example, the DR original image can be digital image information obtained by converting X-rays into visible light and converting the visible light into an electrical signal. The image after the DR original image is processed includes an image after post-processing such as image contrast, image brightness adjustment, and the like, i.e., the image after the DR original image is processed can be regarded as an image after arbitrary post-processing of the DR original image, which is not limited here.

[0052] In step S120, image features are extracted from the DR image, the image features including at least one of a gray entropy feature, a texture feature, a noise feature, a gradient feature, and a divergence feature.

[0053] In step S130, at least one of the gray entropy feature, the texture feature, the noise feature, the gradient feature, and the divergence feature is input into a target model, and a DR image index reflecting the basic feature information content of the DR image is output.

[0054] In the DR image analysis method 100 of the embodiments of the present application, at least one of a gray entropy feature, a texture feature, a noise feature, a gradient feature, and a divergence feature is extracted from a DR image, and a DR image index reflecting the basic feature information content of the DR image, or an image feature index (IFI), which can be objectively obtained according to the extracted at least one image feature, is obtained. The DR image index can provide an objective basis for the operator to make a judgment, and can guide the direction of in-hospital quality control and dose reduction imaging.

[0055] Specifically, the DR image can be an original image collected by a DR imaging system. In the present application, the original image can be an image displayed on a display, or original image data or original data, which is not limited here. The DR system mainly includes an X-ray generator, a detector (for example, a flat panel detector), a workstation, a mechanical device, and the like. The working process mainly includes: X-rays generated by the X-ray generator pass through the target part of the measured object and are attenuated, the attenuated X-rays are projected onto the detector, the flat panel detector converts the X-rays into visible light, and then converts the visible light into an electrical signal, thereby obtaining digital image information, and the digital image information is transmitted to the workstation. In addition, the DR image can also be an image after the DR original image is processed, for example, image post-processing is performed by the workstation, and finally an image after the DR original image is processed is obtained.

[0056] In step S120, image features are extracted from the DR image, the image features including at least one of a gray entropy feature, a texture feature, a noise feature, a gradient feature, and a divergence feature. That is, the image features extracted in step S120 can be the gray entropy feature, the texture feature, and the noise feature, the gradient feature, and the divergence feature, or any one or any two of the image features. The gray entropy feature, the texture feature, and the noise feature, and the gradient feature and the divergence feature respectively reflect the gray, texture, and noise information of the DR image, gradient information, and divergence information, and the multi-dimensional image features are conducive to obtaining more accurate DR image indexes.

[0057] In one embodiment, the gray entropy feature is the information content obtained by statistically screening out redundant gray level sources in the DR image. According to the transfer characteristics of X-ray quanta converted into digital signals by the detector of the DR system, each independent gray level 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 the gray level source. Among all the gray levels, there are some gray levels on which there is no gray value, and thus they are regarded as redundant gray level sources. Since the extraction process of the gray entropy feature of the present application screens out the redundant gray level sources, more effective image information can be extracted.

[0058] Exemplarily, when the gray entropy feature is the information content obtained by statistically screening out redundant gray level sources in the DR image, the gray entropy feature can be extracted from the DR image in the following manner:

[0059] First, a first probability statistical distribution pH(i) of each gray level source in the DR image is obtained, where i is the image gray value of the DR image; the first probability statistical distribution of the redundant gray level sources in each gray level source is screened to obtain the first probability statistical distribution pNH(i) of the non-redundant gray level sources, that is:

[0060]

[0061] According to the ratio of the first probability statistical distribution pNH(i) of each non-redundant gray level source to the sum ∑pNH(i) of the first probability statistical distributions of all non-redundant gray level sources, a second probability statistical distribution pH'(i) of each non-redundant gray level source is obtained:

[0062] pH'(i) = pNH(i) / ∑pNH(i) Formula (2)

[0063] Finally, the second probability statistical distribution pH'(i) of the non-redundant gray level source is used to calculate the entropy to obtain the gray entropy feature H(Image). The way of calculating the entropy includes but is not limited to taking the natural logarithm ln with e as the base or taking the logarithm with other numerical values as the base, and is expressed in the formula as:

[0064]

[0065] Thus, the image gray entropy feature after the redundant gray level sources are screened out can be obtained.

[0066] The texture feature represents the spatial variation of different gray values on the DR image, and can reflect the abstract feature of the variation law of human tissues. For example, the texture feature of the DR image can be extracted by using a statistical method, which obtains the statistical characteristics of the texture region based on the gray attributes of the pixels and their neighborhoods. Hereinafter, the specific details of extracting the texture feature by using the statistical method will be described, but the method of extracting the texture feature can also include a geometric method, a model method or other suitable texture feature extraction methods.

[0067] For example, when the texture feature is extracted from the DR image by using the statistical method, first, a texture feature description matrix is obtained according to the gray values of the pixels 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.

[0068] In one embodiment, the texture feature description matrix describes the variation of the gray values in different distances and different directions of the DR image. Assuming that the DR image is Image=f(x,y), the texture feature description matrix P(i,j) of the DR image is:

[0069] P(i,j) = #{(x1,y1),(x2,y2) ∈ M*N | f(x1,y1)=i,f(x2,y2)=j} Formula (4)

[0070] wherein # (x) represents the number of elements in the set x, and 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 extended to P(i,j,k,l). The extension of the texture feature description matrix to obtain the information in more dimensions can be performed by counting the variation of the gray values in different distances and different directions to obtain the texture feature description matrix. For example, in order to calculate the actual feature values in different angles, the DR image can be super-resolution interpolated in each direction to obtain the sub-pixel gray value corresponding to the new target position, and the texture feature description matrix in different directions can be obtained according to the sub-pixel gray value.

[0071] After the texture feature description matrix is obtained, at least one two-dimensional component of the texture feature description matrix is extracted to obtain the texture feature, which reflects the key characteristics of the texture feature description matrix. For example, the texture feature includes at least one of the following:

[0072] The first texture feature P1 is used to statistically analyze the value distribution of the texture feature description matrix and the overall distribution of the texture change in the DR image. The value of P1 can reflect the definition and the depth of the texture groove of the DR image. The deeper the texture groove, the larger the value of P1. Conversely, the shallower the texture groove, the smaller the value of P1.

[0073] The second texture feature P2 is used to statistically analyze the value distribution of the texture feature description matrix and the similarity in the parallel and normal directions of the DR image. The larger the value of P2, the greater the similarity of the gray level of the image in different directions.

[0074] The third texture feature P3 is used to statistically analyze the value distribution of the texture feature description matrix and the uniformity of the gray scale change distribution in the DR image. The value of P3 can reflect the uniformity of the gray scale distribution and the fineness of the texture of the DR image. The larger the value of P3, the more stable the texture change of the DR image.

[0075] The fourth texture feature P4 is used to statistically analyze the value distribution of the texture feature description matrix and the measure of the local texture change of the DR image. The larger the value of P4, the stronger the regularity of the texture.

[0076] The texture features extracted from the texture feature description matrix are not limited to the above four kinds. In other embodiments, other two-dimensional components of the texture feature description matrix can also be extracted as texture features.

[0077] The image noise mainly includes X-ray quantum noise, and the distribution of X-ray quantum obeys Poisson distribution. The variance is proportional to the average number of quantum detections. According to this characteristic of X-ray quantum noise, the fluctuation degree of X-ray quantum can be statistically analyzed from the DR image as the image noise feature, that is, the image noise feature reflects the fluctuation degree of X-ray quantum in the DR image.

[0078] In one embodiment, the image noise feature is extracted from the DR image, including the following steps: obtaining a high-frequency image from the DR image, the high-frequency image obtained from the DR image mainly contains noise information; extracting the effective information in the high-frequency image to obtain a noise distribution image; and statistically analyzing the noise value distribution in the noise distribution image to obtain the image noise feature.

[0079] As an implementation manner, the high-frequency image is obtained from the DR image, including: performing low-frequency filtering on the DR image I to filter out the low-frequency components in the DR image I 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 implementation manners, the DR image I can also be directly high-frequency filtered to obtain the high-frequency image I2.

[0080] Exemplarily, the DR image I can be Gaussian low-pass filtered 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:

[0081]

[0082] A high-frequency image I2 can be obtained by calculating the difference between the low-frequency image I1 and the DR image I, i.e., 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 composed of the local root mean square of each pixel point in the high-frequency image. The method for calculating the local root mean square includes using the L1 norm or other approximate or equivalent measures, for example:

[0083]

[0084] where 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).

[0085] After obtaining the noise distribution image I3, the noise value distribution is counted to obtain the image noise feature. Exemplarily, 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 taken as the image noise feature.

[0086] Specifically, first, the pixel values of the noise distribution image I3 are divided into M intervals, and the pixel value interval of each interval is d. The histogram vector h is initialized to have a length of M, and each component h(i) of the histogram represents the number of pixel values in the ith interval. For the pixel point (i,j) in the noise distribution image I3, the interval corresponding to the pixel value of the point is R[I3(i,j)]. Each pixel point of the noise distribution image I3 is traversed, and h(R(I3(i,j))) is counted. After obtaining h, the maximum value of the main peak is max(h), and the corresponding interval R0 = arg max(h). Then, the noise distribution probability R0*d is calculated as the noise feature.

[0087] In one embodiment, the gradient feature is used to represent the sharpness of the boundaries of different tissues in the DR image. The gradient feature is extracted from the DR image, including: determining the region distribution of different tissues in the DR image; and obtaining the sharpness of the boundaries of the different tissue region distribution as the gradient feature.

[0088] Exemplarily, according to the different absorption coefficients of X-rays after penetrating different tissues of a human body, different tissue region distributions are formed in the DR image, and there are boundaries of different degrees between different tissue regions. The clarity of these boundaries can be quantified by extracting gradient features. Specifically, the clarity of the boundaries can be calculated according to the following formula:

[0089]

[0090] where Grad(x, y) is used to represent the gradient size at the coordinate (x, y), and Image(x, y) is used to represent the pixel value at the coordinate (x, y).

[0091] In one embodiment, a divergence feature is used to represent the transition strength and / or trend consistency of the boundaries of different tissues in the DR image. The divergence feature is extracted from the DR image, including: determining the region distribution of different tissues in the DR image; and obtaining the transition strength and / or trend consistency of the boundaries of the region distribution of different tissues as the divergence feature.

[0092] Exemplarily, in the DR image, the boundaries of different tissues are not strict boundaries, but there is a certain degree of transition. The transition strength and / or trend consistency of the transition can be quantified by extracting the divergence feature. Specifically, the transition strength and / or trend consistency of the transition can be calculated according to the following formula:

[0093]

[0094] where Diver(x, y) is used to represent the divergence size at the coordinate (x, y), Image(x, y) is used to represent the pixel value at the coordinate (x, y), and actan represents the inverse tangent function.

[0095] In some embodiments, in addition to at least one of the above several image features, other image features can be extracted from the DR image for obtaining the DR image index, such as a gray gradient, a gray mean value, a variance, pixel value information, a signal-to-noise ratio, a contrast-to-noise ratio, etc. The specific image features can be determined according to actual conditions, and are not limited herein.

[0096] In step S130, as Figure 2As shown, at least one of the image features of the gray entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature is input into a target model, and a DR image index reflecting the basic feature information content of the DR image is output. The target model can be a trained model or an untrained model. The target model can output the DR image index reflecting the basic feature information content of the DR image. In a possible implementation, the target model includes a pre-trained network model, wherein the network model can be trained in an offline manner, and the training method mainly includes:

[0097] First, a DR image set is obtained, and the DR image set includes a plurality of DR images. According to the DR image set, an image feature set can be obtained, and the image feature set includes a plurality of image features extracted from the plurality of DR images. Specifically, for each DR image in the DR image set, at least one of the gray entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature is extracted, respectively. The plurality of image features extracted from the plurality of DR images in the DR image set collectively constitute the image feature set, and each DR image in the DR image set corresponds to at least one image feature in the image feature set.

[0098] According to the DR image set, a DR diagnosis image set is obtained, and the DR diagnosis image set includes a plurality of DR diagnosis images obtained by image processing on the plurality of DR images. Specifically, the plurality of DR images in the DR image set can be respectively processed by a DR image processing system to obtain a plurality of DR diagnosis images, that is, visualized images used for diagnosis by doctors.

[0099] According to the DR diagnosis image set, a score set is obtained, and the score set includes scores obtained by evaluating the plurality of DR diagnosis images. In some embodiments, a clinical expert can evaluate the DR diagnosis images in the DR diagnosis image set according to the quality of the DR diagnosis images and give expert scores. The higher the score of the DR diagnosis image, the more basic feature information content contained in the corresponding DR image; on the contrary, the lower the score of the DR diagnosis image, the less basic feature information content contained in the corresponding DR image. The expert scores of the DR diagnosis images constitute an expert score set.

[0100] Afterwards, the network model is trained with the acquired image feature set and score set as a training sample set to obtain a trained network model. The network model can be a traditional machine learning model or a deep learning model, including but not limited to neural networks, support vector machines, linear discriminant analysis, etc.; the training method includes but is not limited to linear regression, gradient descent, etc. model training method. Exemplarily, an optimal mapping function from image features to scores can be learned, so that the error between the DR image index obtained by mapping the image features and the actual expert score is minimized. For the image features acquired in step S120, performing this optimal mapping function can obtain the prediction result of the DR image index closest to the expert score.

[0101] In one embodiment, when the DR image feature set and the expert score set are used for classification regression training, the classification regression training formula used is:

[0102]

[0103] wherein x is a feature vector, {x i} i＝1,…,m is a support vector, a i is a weighting coefficient, b is a bias, k is a kernel function, and each value of the feature vector x needs to pass through a linear transfer function to obtain:

[0104]

[0105] wherein, is an input feature, w and s are scaling and translation parameter vectors respectively, and the kernel function k adopts or

[0106] It should be noted that the linear transfer function, kernel function or parameters used in the regression training method are not limited in the present application.

[0107] After obtaining the trained network model in the model training stage, in the actual application process, at least one of the gray entropy features, texture features, noise features, gradient features and divergence features extracted in step S120 is input into the trained network model, so as to obtain the DR image index reflecting the basic feature information content of the DR image, and the DR image index can be displayed by a display device or output in other ways.

[0108] Based on the above description, the DR image analysis method according to the embodiment of the present application extracts at least one of the gray entropy feature, the texture feature and the noise feature from the DR image, and obtains a DR image index reflecting the basic feature information content of the DR image according to the extracted at least one image feature, which can provide an objective judgment basis for the operator and can guide the in-hospital quality control and the dose reduction imaging, etc.

[0109] In the following, the DR image analysis method according to another embodiment of the present application is described. Figure 3 The DR image analysis method according to another embodiment of the present application is described. Figure 3 is a schematic flow chart of the DR image analysis method 300 according to the embodiment of the present application.

[0110] As shown in Figure 3 , the DR image analysis method 300 includes the following steps:

[0111] In step S310, a digital X-ray radiography DR image is acquired, wherein the DR image includes at least one of a DR original image and an image processed from the DR original image;

[0112] In step S320, an image feature is extracted from the DR image, wherein the image feature includes at least one of a gray entropy feature, a texture feature, a noise feature, a gradient feature and a divergence feature;

[0113] In step S330, a DR image index reflecting the basic feature information content of the DR image is determined according to at least one of the gray entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature;

[0114] It should be noted that in step S330, there are many ways to determine the DR image index reflecting the basic feature information content of the DR image according to at least one of the gray entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature, which can be determined by inputting a target model as shown in Figure 1 and Figure 2 , can be processed by other processors on the device, or can be processed by other processors outside the device, which is not limited here.

[0115] In step S340, the DR image index reflecting the basic feature information content of the DR image is outputted.

[0116] The DR image analysis method 300 is similar to the DR image analysis method 100 described above, but the DR image analysis method 300 does not limit the specific method of determining the DR image index based on the image features. After extracting at least one image feature among the grayscale entropy feature, texture feature, noise feature, gradient feature, and divergence feature, the DR image index can be directly processed and calculated, or the DR image index can be obtained through the trained network model as described above, or any other suitable method can be used to obtain the DR image index. In addition, in step S340, the method of outputting the DR image index can be to display the DR image index through a display device, or to output the DR image index through a speaker, printer, or other output device, which is not specifically limited here.

[0117] The steps of the DR image analysis method 300 and the DR image analysis method 100 have many identical or similar contents. For details, please refer to the relevant description above and will not be repeated here.

[0118] Based on the above description, the DR image analysis method 300 according to the embodiment of the present application extracts at least one of grayscale entropy features, texture features, noise features, gradient features and divergence features from the DR image, and obtains a DR image index that can objectively reflect the basic feature information content of the DR image based on the at least one extracted image feature. The DR image index can provide the operator with an objective judgment basis, and can guide the direction of in-hospital quality control and dose reduction imaging.

[0119] like Figure 5 As shown, the DR image analysis method 500 includes the following steps:

[0120] In step S510, a digital X-ray photography DR image is acquired, wherein the DR image includes at least one of an original DR image and an image obtained by processing the original DR image;

[0121] In step S520, a DR image index reflecting basic feature information content of the DR image is determined based on at least one of the DR original image and the image after the DR original image is processed;

[0122] It should be noted that in the DR image analysis method 500, there is no need to extract image features from the DR image. Instead, the DR image index reflecting the basic feature information content of the DR image is directly determined based on the image. This processing method is efficient and has a simple operation process.

[0123] In some possible implementation manners, determining the DR image index reflecting the basic characteristic information content of the DR image according to at least one of the DR original image and the image processed from the DR original image includes: inputting at least one of the DR original image and the image processed from the DR original image into a target model, and outputting the DR image index reflecting the basic characteristic information content of the DR image by the target model. Of course, in addition to inputting the target model to determine the DR image index, other processors on the device can also be used for processing, and other processors outside the device can also be used for processing, which is not limited here.

[0124] In step S530, the DR image index reflecting the basic characteristic information content of the DR image is output.

[0125] As shown in FIG. 6, the DR image analysis method 600 includes the following steps: Figure 6

[0126] In step S610, a digital X-ray photography DR image and image features corresponding to the DR image are acquired, wherein the DR image includes at least one of a DR original image and an image processed from the DR original image, and the image features include at least one of a gray entropy feature, a texture feature, a noise feature, a gradient feature, and a divergence feature.

[0127] In step S620, a DR image index reflecting the basic characteristic information content of the DR image is determined according to the DR image and the image features corresponding to the DR image.

[0128] It should be noted that in the DR image analysis method 600, the DR image and the image features corresponding to the DR image are needed to determine the DR image index, and the DR image index obtained by this processing manner is more accurate. Instead of determining the DR image index only by the DR image or the image features corresponding to the DR image.

[0129] In a possible implementation manner, determining the DR image index reflecting the basic characteristic information content of the DR image according to the DR image and the image features corresponding to the DR image includes:

[0130] inputting the DR image and the image features corresponding to the DR image into a target model, and outputting the DR image index reflecting the basic characteristic information content of the DR image. Of course, in addition to inputting the target model to determine the DR image index, other processors on the device can also be used for processing, and other processors outside the device can also be used for processing, which is not limited here.

[0131] ​At step S630, outputting the DR image index reflecting the basic feature information content of the DR image.

[0132] It should be noted that each step of the DR image analysis method 500 and 600 has many same or similar contents with the DR image analysis method 100, and the specific contents can be referred to the related description above, which will not be repeated here.

[0133] With reference to Figure 4 The embodiments of the present application further provide an electronic device 400, which can be used to implement the DR image analysis method 100, the DR image analysis method 300, the DR image analysis method 500 or the DR image analysis method 600 described above. The electronic device 400 can be a DR device for DR imaging, such as a flat panel detector or an automatic exposure controller or a mobile DR device or a fixed DR device, etc., or other computers or terminal devices, such as a mobile phone, a computer, a palm computer, etc., which will not be limited here. The electronic device 400 comprises a memory 410 and a processor 420, and the memory 410 stores a computer program which is run by the processor 420. The computer program, when being run by the processor, executes the steps of the DR image analysis method 100 or the DR image analysis method 300. When used to implement the DR image analysis method 100, the computer program stored in the memory 410, when being run by the processor 420, executes the following steps: acquiring a digital X-ray DR image; extracting image features from the DR image, the image features comprising at least one of a gray entropy feature, a texture feature, a noise feature, a gradient feature and a divergence feature; inputting the at least one of the gray entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature into a pre-trained network model, and outputting a DR image index reflecting the basic feature information content of the DR image. Of course, in actual application, the DR image index can also be displayed by a display device. When used to implement the DR image analysis method 300, the computer program stored in the memory 410, when being run by the processor 420, executes the following steps: acquiring a digital X-ray DR image; extracting image features from the DR image, the image features comprising at least one of a gray entropy feature, a texture feature, a noise feature, a gradient feature and a divergence feature; determining a DR image index reflecting the basic feature information content of the DR image according to the at least one of the gray entropy feature, the texture feature, the noise feature, the gradient feature and the divergence feature; and outputting the DR image index reflecting the basic feature information content of the DR image. The other specific details of the DR image analysis method 100 and the DR image analysis method 300 can be referred to the above, which will not be repeated here.

[0134] The processor 420 can be implemented by hardware, software, firmware or any combination thereof, and can use circuits, single or multi-processor, single or multi-core, programmable logic devices, or any combination thereof, or other suitable devices, and can control other components in the electronic device 400 to execute desired functions.

[0135] The memory 410 can include one or more computer program products, which can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read-only memory (ROM), hard disk drive, flash memory, and / or the like. One or more computer program instructions can be stored on the computer-readable storage media, and the processor 420 can execute the program instructions to implement the DR image analysis method and / or other various desired functions in the present application. Various application programs and various data, such as various data used and / or generated by the application programs, and the like, can also be stored in the computer-readable storage media.

[0136] In addition, according to the embodiments of the present application, a computer storage medium is also provided, on which program instructions are stored, and the program instructions are used to execute the corresponding steps of the DR image analysis method of any of the embodiments of the present application when executed by a computer or a processor. In some embodiments, the computer storage medium is a non-volatile computer-readable storage medium, which can include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required by a function; the data storage area can store data created during execution of the program instructions, and the like. In addition, the non-volatile computer-readable storage medium can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some embodiments, the non-volatile computer-readable storage medium can optionally include a memory remotely arranged with respect to the processor.

[0137] Exemplarily, the computer storage medium can 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 compact disc 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 can be any combination of one or more computer-readable storage media.

[0138] In a possible implementation, seeFigure 7 The electronic device can be a DR imaging device 700, which includes an X-ray generator 710, a detector 720, and a processor 730 and a display 740, wherein the processor 730 and the X-ray generator 710, the detector 720, and the display 740 are communicatively connected; the X-ray generator 710 is configured to generate X-rays, emit X-rays to a target tissue site, and control the X-rays to pass through the target tissue site;

[0139] The detector 720 is configured to receive the X-rays after passing through the target tissue site, and process the X-rays after passing through the target tissue site to obtain a digital radiography (DR) image, wherein the DR image includes at least one of a DR original image and an image processed from the DR original image;

[0140] The processor 730 is configured to input at least one of the image features of the gray entropy feature, the texture feature, the noise feature, the gradient feature, and the divergence feature into a target model, and output a DR image index reflecting a basic feature information content of the DR image;

[0141] The display 740 is configured to display the DR image index reflecting the basic feature information content of the DR image.

[0142] In addition, according to the embodiments of the present application, a computer program is also provided, which can be stored on a cloud or a local storage medium. When the computer program is run by a computer or a processor, it is used to execute the corresponding steps of the DR image analysis method of the embodiments of the present application.

[0143] To sum up, according to the DR image analysis method and device of the present application, the DR image index reflecting the basic feature information content of the DR image can be obtained objectively according to the image features extracted from the DR image, thereby providing an objective basis for the operator to make a judgment.

[0144] Although the example embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the above-described example embodiments are merely exemplary and are not intended to limit the scope of the present application thereto. Various changes and modifications can be made thereto by those of ordinary skill in the art without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as claimed in the appended claims.

[0145] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0146] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0147] In the specification provided herein, a large number of specific details are described. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some examples, well-known methods, structures and techniques are not described in detail in order not to obscure the understanding of the specification.

[0148] Similarly, it should be understood that, in order to simplify the present application and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, various features of the present application are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of the present application should not be interpreted as reflecting an intention that the claimed present application requires more features than those explicitly recited in each claim. Rather, as reflected by the corresponding claims, the inventive point is that the corresponding technical problem can be solved with fewer features than all the features of a certain disclosed single embodiment. Therefore, the claims following the specific embodiments are hereby expressly incorporated into the specific embodiments, wherein each claim itself is a separate embodiment of the present application.

[0149] Those skilled in the art can understand that, except for the mutual exclusion between features, all the features disclosed in the specification (including the accompanying claims, abstract and drawings) and all the processes or units of any method or device disclosed in this way can be combined in any combination. Unless explicitly stated otherwise, each feature disclosed in the specification (including the accompanying claims, abstract and drawings) can be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0150] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of this application and to form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

[0151] The various component embodiments of the present application can 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) can be used in practice to implement some or all of the functions of some modules in the article analysis device according to the embodiment of the present application. The application can also be implemented as a device program (e.g., computer program and computer program product) for executing a part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0152] It should be noted that the above embodiments illustrate rather than limit the present application, and that a person skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbols placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0153] The above description is merely a specific embodiment or illustration of a specific embodiment of the present application, and the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. The scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A DR image analysis method, characterized in that: The method comprises: Acquiring a digital X-ray photography (DR) image, wherein the DR image includes at least one of an original DR image and an image obtained by processing the original DR image; Determining a DR image index reflecting basic feature information content of the DR image based on at least one of the DR original image and the image after the DR original image is processed, wherein the DR image index is determined based on at least one image feature of grayscale entropy, texture, noise, gradient, and divergence; Among them, the grayscale entropy feature is the information content obtained after statistically screening out redundant grayscale sources in the DR image; the texture feature is used to characterize the spatial variation relationship of different grayscale values ​​on the DR image; the noise feature includes X-ray quantum noise, and the noise feature is used to characterize the degree of fluctuation of X-ray quanta in the DR image; the gradient feature is used to characterize the clarity of different tissue boundaries in the DR image; the divergence feature is used to characterize the transition strength and / or trend consistency of different tissue boundaries in the DR image.

2. The method according to claim 1, wherein The step of obtaining a digital X-ray photography DR image comprises: emitting X-rays toward a target tissue site, and controlling the X-rays to pass through the target tissue site; receiving X-rays after passing through the target tissue site; The DR image is acquired according to the X-rays that pass through the target tissue site.

3. The method according to claim 1 or 2, wherein: The determining of a DR image index reflecting the basic characteristic information content of the DR image based on at least one of the DR original image and the image obtained by processing the DR original image includes: Extracting at least one image feature among a grayscale entropy feature, a texture feature, a noise feature, a gradient feature, and a divergence feature from at least one of the DR original image and the image after the DR original image is processed; At least one image feature among the grayscale entropy feature, texture feature, noise feature, gradient feature and divergence feature is input into a target model to determine a DR image index of the basic feature information content of the DR image.

4. The method according to claim 1 or 2, wherein: The determining of a DR image index reflecting the basic characteristic information content of the DR image based on at least one of the DR original image and the image obtained by processing the DR original image includes: Extracting at least one image feature among a grayscale entropy feature, a texture feature, a noise feature, a gradient feature, and a divergence feature from at least one of the DR original image and the image after the DR original image is processed; The DR image index of the basic feature information content of the DR image is determined directly according to at least one image feature among the grayscale entropy feature, texture feature, noise feature, gradient feature and divergence feature.

5. The method according to claim 3 or 4, wherein: Extracting a grayscale entropy feature from at least one of the DR original image and the image after the DR original image is processed includes: Obtaining a first probability statistical distribution of each grayscale signal source in at least one of the DR original image and the image after the DR original image is processed; screening the first probability statistical distribution of redundant grayscale information sources in the grayscale information sources to obtain the first probability statistical distribution of non-redundant grayscale information sources; Obtaining a second probability statistical distribution of each non-redundant grayscale signal source according to a ratio of the first probability statistical distribution of each non-redundant grayscale signal source to the sum of the first probability statistical distributions of all non-redundant grayscale signal sources; The entropy is calculated according to the second probability statistical distribution of the non-redundant grayscale information source to obtain the grayscale entropy feature.

6. The method according to claim 3 or 4, wherein: Extracting texture features from at least one of the DR original image and the image obtained by processing the DR original image comprises: Obtaining a texture feature description matrix according to the grayscale value of each pixel in at least one of the DR original image and the image after the DR original image is processed; At least one two-dimensional component of the texture feature description matrix is ​​extracted as at least one texture feature.

7. The method according to claim 6, wherein The texture feature includes at least one of the following: A first texture feature 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 second texture feature 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; A third texture feature is used to calculate the uniformity of the value distribution in the texture feature description matrix and the grayscale change distribution in the DR image; The fourth texture feature is used to measure the distribution of values ​​in the texture feature description matrix and the local variation of the texture of the DR image.

8. The method according to claim 3 or 4, wherein: Extracting a noise feature from at least one of the DR original image and the image obtained by processing the DR original image comprises: Obtaining a high-frequency image from at least one of the DR original image and the image obtained by processing the DR original image; Extracting effective information from the high-frequency image to obtain a noise distribution image, wherein the noise distribution image is an image formed by the local root mean square of each pixel in the high-frequency image; Statistics are performed on the noise value distribution in the noise distribution image to obtain the noise feature.

9. The method according to claim 8, wherein The performing statistics on the noise value distribution in the noise value distribution image to obtain the noise feature includes: Determining a noise value interval having a highest probability of noise value distribution in the noise distribution image; The noise value in the noise value interval with the highest noise value distribution probability is used as the noise feature.

10. The method according to claim 8, wherein The obtaining of a high-frequency image from at least one of the DR original image and the image obtained by processing the DR original image comprises: performing low-frequency filtering on at least one of the DR original image and the image after the DR original image is processed to obtain a low-frequency image, and obtaining the high-frequency image according to a difference between the low-frequency image and the DR image; or High-frequency filtering is performed on at least one of the DR original image and the image obtained by processing the DR original image to obtain the high-frequency image.

11. The method according to claim 3 or 4, characterized in that The extracting gradient features from at least one of the DR original image and the image obtained by processing the DR original image comprises: determining regional distributions of different tissues in at least one of the DR original image and the image after processing the DR original image; The clarity of the boundaries between different tissue regions is obtained as the gradient feature.

12. The method according to claim 3 or 4, characterized in that The extracting of the divergence feature from at least one of the DR original image and the image obtained by processing the DR original image comprises: determining the regional distribution of different tissues in the DR image; The transition strength and / or trend consistency of the boundaries of the distribution of different tissue regions are obtained as the divergence feature.

13. The method according to any one of claims 1 to 12, characterized in that The method further includes: controlling the output of the DR image index.

14. A DR image analysis method, characterized in that: The method comprises: Acquiring a digital X-ray photography (DR) image, wherein the DR image includes at least one of an original DR image and an image obtained by processing the original DR image; A DR image index reflecting the basic characteristic information content of the DR image is determined according to at least one of the DR original image and the image obtained by processing the DR original image.

15. The method according to claim 14, wherein The determining of a DR image index reflecting the basic characteristic information content of the DR image based on at least one of the DR original image and the image obtained by processing the DR original image includes: Inputting at least one of the DR original image and the image obtained by processing the DR original image into a target model, and outputting the DR image index through the target model; And / or, the DR image index is obtained by processing at least one of the DR original image and the image after the DR original image is processed by a processor.

16. The method according to claim 14 or 15, characterized in that At least one of the DR original image and the image after the DR original image is processed has at least one image feature among grayscale entropy feature, texture feature, noise feature, gradient feature and divergence feature; Among them, the grayscale entropy feature is the information content obtained after statistically screening out redundant grayscale sources in the DR image; the texture feature is used to characterize the spatial variation relationship of different grayscale values ​​on the DR image; the noise feature includes X-ray quantum noise, and the noise feature is used to characterize the degree of fluctuation of X-ray quanta in the DR image; the gradient feature is used to characterize the clarity of different tissue boundaries in the DR image; the divergence feature is used to characterize the transition strength and / or trend consistency of different tissue boundaries in the DR image.

17. A DR imaging device, characterized in that: The DR imaging device includes: an X-ray generator, a detector, a processor and a display; The X-ray generator is used to generate X-rays, emit X-rays toward a target tissue site, and control the X-rays to pass through the target tissue site; The detector is used to receive the X-rays after passing through the target tissue site, and process the X-rays after passing through the target tissue site to obtain a DR image, wherein the DR image includes at least one of a DR original image and an image obtained by processing the DR original image; The processor is configured to execute the method according to any one of claims 1 to 16.

18. An electronic device, characterized in that: The electronic device includes a memory and a processor, wherein a computer program executed by the processor is stored in the memory, and when the computer program is executed by the processor, the steps of the DR image analysis method according to any one of claims 1 to 16 are executed.

Images