Image processing device, radiographic image capturing system, and program

Abstract

To provide an image processing device, a radiographic image capturing system, and a program capable of detecting a calcification lesion in a state that an influence of noise is reduced from a radiation image of the breast as compared with a conventional technology.SOLUTION: An image processing device 4 includes: an image acquisition unit 30 for acquiring a radiation image obtained by imaging the breast with X-rays; a leveling unit 32 for leveling the rate of change in a luminance gradient using a degree of variations indicating a degree of variations for each local area in the rate of change in a luminance gradient in the acquired radiation image; and a calcification detection unit 33 for detecting the position of a calcification lesion in the radiation image by performing threshold processing using a threshold determined beforehand for the leveled rate of change in the luminance gradient.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to an image processing device, a radiographic image capturing system, and a program. [Background technology]

[0002] In recent years, imaging diagnosis using radiological imaging devices (called mammography) for capturing images of the breast has been attracting attention in order to promote early detection of breast cancer. Tomosynthesis imaging has also been proposed for mammography, in which a moving radiation source irradiates the breast from multiple radiation source positions to capture images, and then the resulting multiple projection images are reconstructed to generate a tomographic image that emphasizes the desired tomographic plane. In tomosynthesis imaging, depending on the characteristics of the imaging device and the required tomographic image, the radiation source is moved parallel to the radiation detector or in a circular or elliptical arc to capture multiple projection images of the breast. These projection images are then reconstructed to generate a tomographic image using a backprojection method, such as simple backprojection or filtered backprojection, or an iterative reconstruction method.

[0003] By generating such tomographic images on multiple sections of the breast, it is possible to separate structures that overlap in the depth direction of the breast where the sections are aligned. This makes it possible to discover abnormalities such as lesions that are difficult to detect in 2D images obtained by conventional simple radiography, in which radiation is irradiated onto the subject from a predetermined direction (hereinafter referred to as simple 2D images).

[0004] As a technology using such tomographic images, Patent Document 1 discloses a technology for generating a pseudo two-dimensional image (hereinafter referred to as a composite two-dimensional image) equivalent to a simple two-dimensional image by combining multiple tomographic images acquired by tomosynthesis imaging, which are at different distances (height positions) from the detection surface of a radiation detector toward the radiation source, using an addition method, an averaging method, a maximum intensity projection method, a minimum intensity projection method, or the like.

[0005] In breast radiographic images such as the above-described composite two-dimensional images, it is easy to detect large calcified lesions (hereinafter also referred to as "calcified lesions"), but it is extremely difficult to detect relatively small calcified lesions due to the large influence of noise.

[0006] As a technique that can be applied to solve this problem, Patent Document 2 discloses a method for displaying abnormal shadow candidates, which aims to prevent doctors from overlooking them and improve the efficiency of image interpretation by providing only detection information for abnormal shadow candidates that are questionable as to whether they are true positive abnormal shadows and / or abnormal shadow candidates with low visibility.

[0007] This display method is characterized by comprising a detection step of detecting abnormal shadow candidates by performing image analysis on a medical image, an extraction step of extracting abnormal shadow candidates to be displayed from the detected abnormal shadow candidates, and a display step of displaying detection information of the extracted abnormal shadow candidates.

[0008] Furthermore, Patent Document 3 discloses an image display device that aims to stably provide similar cases.

[0009] This image display device comprises a display means, a storage means for storing breast images in association with features of lesion candidates detected in designated areas of the breast images designated by a doctor, a candidate detection means for detecting lesion candidates in designated areas of the breast image to be diagnosed designated by a user and calculating the features of the lesion candidates, and a control means for retrieving breast images corresponding to features similar to the calculated features from the storage means and displaying them on the display means as similar cases. [Prior art documents] [Patent documents]

[0010] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-128716 [Patent Document 2] Japanese Patent Application Laid-Open No. 2006-325640 [Patent Document 3] Japanese Patent Application Laid-Open No. 2010-000130 Summary of the Invention [Problem to be solved by the invention]

[0011] However, the techniques disclosed in Patent Documents 2 and 3 analyze calcification by analyzing density gradients in radiological images of the breast. As a result, although images of minute calcified lesions can be obtained, the effects of differences with the background image due to differences in mammary gland distribution, breast thickness, etc. cannot be eliminated, and noise other than calcified lesions still has a significant effect.

[0012] The present disclosure has been made in consideration of the above circumstances, and aims to provide an image processing device, a radiographic imaging system, and a program that are capable of detecting calcified lesions from breast radiographic images with reduced influence of noise compared to conventional techniques. [Means for solving the problem]

[0013] In order to achieve the above object, an image processing device of a first aspect of the present disclosure includes at least one processor, which acquires a radiological image obtained by imaging a breast with radiation, smooths the rate of change of the brightness gradient using a variability indicating the degree of variation for each local region in the rate of change of the brightness gradient in the acquired radiological image, and performs threshold processing using a predetermined threshold on the smoothed rate of change of the brightness gradient, thereby detecting the position of a calcified lesion in the radiological image.

[0014] An image processing device according to a second aspect of the present disclosure is the image processing device according to the first aspect, wherein the processor creates a composite two-dimensional image of the breast using the detection result of the position of the calcified lesion.

[0015] An image processing device according to a third aspect of the present disclosure is the image processing device according to the first or second aspect, wherein the degree of variation is a standard deviation or variance for each local region in the rate of change of the brightness gradient.

[0016] An image processing device of a fourth aspect of the present disclosure is an image processing device of the first or second aspect, in which the processor performs smoothing by multiplying the reciprocal of the degree of variation by the rate of change of the brightness gradient.

[0017] An image processing device according to a fifth aspect of the present disclosure is the image processing device according to the first or second aspect, wherein the processor derives the rate of change of the brightness gradient by filtering using a gradient convergence filter.

[0018] An image processing device of a sixth aspect of the present disclosure is an image processing device of the fifth aspect, in which the processor applies either a gradient concentration filter with isotropic weighting or a gradient concentration filter with anisotropic weighting.

[0019] In order to achieve the above object, a radiographic imaging system according to a seventh aspect of the present disclosure includes an image processing device according to the present disclosure, and a radiographic imaging device that captures a radiographic image used by the image processing device.

[0020] Furthermore, in order to achieve the above object, the program of the eighth aspect of the present disclosure causes a computer to execute a process of acquiring a radiographic image obtained by imaging a breast with radiation, smoothing the rate of change of the brightness gradient using a degree of variation indicating the degree of variation for each local region in the rate of change of the brightness gradient in the acquired radiographic image, and detecting the position of a calcified lesion in the radiographic image by performing threshold processing using a predetermined threshold on the smoothed rate of change of the brightness gradient. [Effects of the Invention]

[0021] According to the present disclosure, calcified lesions can be detected from radiographic images of the breast with reduced influence of noise compared to conventional techniques. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a schematic configuration diagram of a radiation image capturing system to which an image processing apparatus according to an embodiment is applied; [Figure 2] 2 is a view of the mammography apparatus according to the embodiment as seen from the direction of arrow A in FIG. 1. [Figure 3] FIG. 2 is a block diagram showing an example of an electrical configuration of the image processing apparatus according to the embodiment. [Figure 4] FIG. 1 is a functional block diagram showing a functional configuration of an image processing apparatus according to an embodiment. [Figure 5] FIG. 2 is a diagram for explaining acquisition of a projection image according to the embodiment. [Figure 6] 3A and 3B are diagrams for explaining generation of a tomographic image according to the embodiment. [Figure 7] 10A to 10C are diagrams illustrating an example of a gradient convergence filter according to an embodiment, and a method for deriving a rate of change in brightness gradient for a radiological image using the gradient convergence filter; [Figure 8] 10A and 10B are diagrams illustrating the effect of filtering by a gradient convergence filter according to an embodiment. [Figure 9] 10A and 10B are diagrams illustrating problems that arise when no leveling is performed by the leveling unit according to the embodiment. [Figure 10A] 10A and 10B are diagrams illustrating the effect of leveling by the leveling unit according to the embodiment. [Figure 10B] 10A and 10B are diagrams illustrating the effect of leveling by the leveling unit according to the embodiment. [Figure 10C] 10A and 10B are diagrams illustrating the effect of leveling by the leveling unit according to the embodiment. [Figure 11] FIG. 2 is a diagram showing an example of a composite two-dimensional image generated from a group of tomographic images according to the embodiment. [Figure 12] 10 is a flowchart illustrating an example of image processing according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0023] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Fig. 1 is a schematic diagram of a radiographic imaging system 90 to which an image processing device 4 according to an embodiment of the present disclosure is applied, and Fig. 2 is a view of a mammography apparatus 1 in the radiographic imaging system 90 as viewed from the direction of arrow A in Fig. 1.

[0024] As shown in Fig. 1, a radiation imaging system 90 according to this embodiment is configured to capture a plurality of radiation images, i.e., a plurality of projection images, by imaging a subject, a breast M, from a plurality of radiation source positions in order to perform tomosynthesis imaging of the breast and generate a tomographic image. The radiation imaging system 90 according to this embodiment includes a mammography apparatus 1, a console 2, an image storage system 3, and an image processing device 4. The mammography apparatus 1 corresponds to the radiation imaging apparatus of the technology of the present disclosure.

[0025] The mammography device 1 has an arm 12 connected to a base (not shown) by a rotation shaft 11. An imaging table 13 is attached to one end of the arm 12, and a radiation irradiator 14 is attached to the other end so as to face the imaging table 13. The arm 12 is configured so that only the end to which the radiation irradiator 14 is attached can rotate, making it possible to rotate only the radiation irradiator 14 while fixing the imaging table 13.

[0026] A radiation detector 15, such as a flat panel detector, is provided inside the imaging table 13. The radiation detector 15 has a radiation detection surface 15A. Also installed inside the imaging table 13 are a circuit board and the like on which are provided a charge amplifier that converts charge signals read out from the radiation detector 15 into voltage signals, a correlated double sampling circuit that samples the voltage signals output from the charge amplifier, and an AD (Analog-Digital) conversion unit that converts the voltage signals into digital signals.

[0027] A radiation source 16 is housed inside the radiation irradiation unit 14. The radiation source 16 emits X-rays as radiation, and the timing at which radiation is emitted from the radiation source 16 and the radiation generation conditions in the radiation source 16, i.e., the selection of target and filter materials, tube voltage, irradiation time, etc., are controlled by the console 2.

[0028] The arm 12 is also provided with a compression plate 17 that is disposed above the imaging table 13 and presses down on the breast M, a support portion 18 that supports the compression plate 17, and a movement mechanism 19 that moves the support portion 18 in the vertical direction in Figures 1 and 2. The distance between the compression plate 17 and the imaging table 13, i.e., the compression thickness, is input to the console 2.

[0029] The console 2 has a function of controlling the mammography apparatus 1 using imaging orders and various information acquired from a radiology information system (RIS) (not shown) or the like via a network such as a wireless LAN (Local Area Network) and instructions given directly by a technician or the like. Specifically, the console 2 causes the mammography apparatus 1 to perform tomosynthesis imaging of the breast M, thereby acquiring multiple projection images as described below. As an example, in this embodiment, a server computer is used as the console 2.

[0030] The image storage system 3 is a system that stores image data such as projected images captured by the mammography device 1. The image storage system 3 extracts images from the stored images in response to requests from the console 2, image processing device 4, etc., and transmits them to the device that issued the request. A specific example of the image storage system 3 is a PACS (Picture Archiving and Communication Systems).

[0031] Next, an image processing device 4 according to this embodiment will be described. First, a hardware configuration of the image processing device 4 according to this embodiment will be described with reference to FIG. 3. As shown in FIG. 3, the image processing device 4 is a computer such as a workstation, a server computer, or a personal computer, and includes a CPU (Central Processing Unit) 21, non-volatile storage 23, and memory 26 as a temporary storage area. The image processing device 4 also includes a display 24 such as a liquid crystal display, an input device 25 such as a keyboard and a mouse, and a network I / F (Interface) 27 connected to a network (not shown). The CPU 21, the storage 23, the display 24, the input device 25, the memory 26, and the network I / F 27 are connected to a bus 28. The CPU 21 is an example of a processor in the present disclosure.

[0032] The storage 23 is realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, etc. The storage 23 as a storage medium stores the image processing program 22 installed in the image processing device 4. The CPU 21 reads the image processing program 22 from the storage 23, loads it into the memory 26, and executes the loaded image processing program 22.

[0033] The image processing program 22 is stored in a state where it can be accessed from outside, in a storage device of a server computer connected to the network, or in a network storage, and is downloaded and installed in response to a request into a computer constituting the image processing device 4. Alternatively, the program is recorded on a recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) and distributed, and is installed from the recording medium into a computer constituting the image processing device 4.

[0034] Next, the functional configuration of the image processing device 4 according to this embodiment will be described. Fig. 4 is a diagram showing the functional configuration of the image processing device 4 according to this embodiment.

[0035] 4, the image processing device 4 according to this embodiment includes an image acquisition unit 30, a tomographic image reconstruction unit 31, a leveling unit 32, a calcification detection unit 33, an image creation unit 34, and a display control unit 35. The CPU 21 executes the image processing program 22 to function as the image acquisition unit 30, the tomographic image reconstruction unit 31, the leveling unit 32, the calcification detection unit 33, the image creation unit 34, and the display control unit 35.

[0036] The image acquisition unit 30 acquires a plurality of projection images acquired by the console 2 causing the mammography apparatus 1 to perform tomosynthesis imaging of the breast M. The image acquisition unit 30 acquires the projection images from the console 2 or the image storage system 3 via the network I / F 27. In addition, the tomographic image reconstruction unit 31 reconstructs a plurality of tomographic images from the projection images acquired by the image acquisition unit 30.

[0037] Here, tomosynthesis imaging and generation of tomographic images will be described. When performing tomosynthesis imaging to generate tomographic images, the console 2 moves the radiation source 16 by rotating the arm 12 about the rotation axis 11, irradiates the breast M, which is the subject, with radiation at multiple radiation source positions achieved by the movement of the radiation source 16 under predetermined imaging conditions for tomosynthesis imaging, detects the radiation that has passed through the breast M with the radiation detector 15, and acquires multiple projection images Gi (i = 1 to n, n is the number of radiation source positions, for example, n = 15) at the multiple radiation source positions.

[0038] Fig. 5 is a diagram for explaining how projection images Gi are acquired. As shown in Fig. 5, radiation source 16 is moved to each of radiation source positions S1, S2, ..., Sn, and is driven at each radiation source position to irradiate breast M with radiation. X-rays that have passed through breast M are detected by radiation detector 15, thereby acquiring projection images G1, G2, ..., Gn corresponding to each radiation source position S1 to Sn. Note that the same dose of radiation is irradiated onto breast M at each of radiation source positions S1 to Sn.

[0039] 5, the radiation source position Sc is the radiation source position where the optical axis X0 of the radiation emitted from the radiation source 16 is perpendicular to the detection surface 15A of the radiation detector 15. The radiation source position Sc is referred to as the reference radiation source position Sc.

[0040] Then, the tomographic image reconstruction unit 31 reconstructs the multiple projection images Gi to generate a tomographic image in which a desired cross-sectional plane of the breast M is emphasized. Specifically, the image processing device 4 reconstructs the multiple projection images Gi using a well-known back projection method such as simple back projection or filtered back projection, and generates multiple tomographic images Dj (j=1 to m) for each of the multiple cross-sectional planes of the breast M, as shown in Fig. 6. At this time, a three-dimensional coordinate position in a three-dimensional space including the breast M is set, and pixel values ​​of corresponding pixels in the multiple projection images Gi are reconstructed with respect to the set three-dimensional coordinate position, and the pixel value of the coordinate position is calculated.

[0041] In the following, a case where the multiple tomographic images obtained by the above processing are applied as "radiation images" of the technology of the present disclosure will be described. Therefore, for convenience, "tomographic images" may also be referred to as "radiation images" hereinafter.

[0042] The smoothing unit 32 smooths the rate of change of the luminance gradient using the degree of variation that indicates the degree of variation for each local region in the rate of change of the luminance gradient in the radiographic image obtained by the above processing.

[0043] The leveling unit 32 according to the present embodiment applies the standard deviation of the rate of change of the luminance gradient for each local region as the degree of variation, but this is not limited to this. For example, the variance of the rate of change of the luminance gradient for each local region may be applied as the degree of variation. In short, any value that indicates the degree of variation in the rate of change of the luminance gradient for each local region can be applied as the degree of variation according to the present embodiment.

[0044] Furthermore, the leveling unit 32 according to this embodiment performs the leveling by multiplying the reciprocal of the degree of variation by the rate of change of the luminance gradient. However, this is not limited to this, and any process can be applied as long as it can level the rate of change of the luminance gradient using the degree of variation, such as a process of dividing the rate of change of the luminance gradient by the degree of variation.

[0045] Furthermore, the smoothing unit 32 according to this embodiment derives the rate of change of the luminance gradient by filtering using a gradient convergence filter. However, the present invention is not limited to this, and any method that can derive the rate of change of the luminance gradient of a radiological image, such as a method of deriving the rate of change by filtering using a filter other than a gradient convergence filter, or a method that does not use a filter, can also be applied.

[0046] Furthermore, the leveling unit 32 according to this embodiment selectively applies either an isotropically weighted or anisotropically weighted gradient converged filter to derive the rate of change in the brightness gradient of the radiographic image. When an isotropically weighted gradient converged filter is applied, it is highly effective in detecting minute calcifications that are nearly circular. On the other hand, when an anisotropically weighted gradient converged filter is applied, it is highly effective in separating calcifications whose directional components are elongated (such as oblong shapes). Therefore, the leveling unit 32 according to this embodiment selectively uses either an isotropically weighted gradient converged filter or an anisotropic weighted gradient converged filter depending on the shape of the calcified lesion to be detected. The processing performed by the leveling unit 32 according to this embodiment will be described in detail below.

[0047] Meanwhile, the calcification detection unit 33 detects the location of calcified lesions in the radiographic image by performing threshold processing using a predetermined threshold on the smoothed rate of change of the brightness gradient. In this embodiment, the threshold is a value statistically obtained in advance from existing radiographic images, and is used as a value at which pixels with a rate of change of brightness gradient equal to or greater than the threshold can be considered to be pixels indicating calcified lesions. However, the present invention is not limited to this. For example, the threshold may be preset by having a technician or the like input the value in advance depending on the purpose of detecting calcified lesions, the patient's condition, etc.

[0048] The image creation unit 34 uses the positions of the calcified lesions detected by the calcification detection unit 33 to create a composite two-dimensional image of the subject (in this embodiment, the breast M).

[0049] The image creation unit 34 according to this embodiment creates a composite two-dimensional image by taking a weighted average for each pixel, where the weight value (e.g., 0.9) of a tomographic image including the position of a calcified lesion detected by the calcification detection unit 33 is set to a value greater than the weight value (e.g., 0.1) of a tomographic image other than the detected tomographic image. However, the method for creating a composite two-dimensional image is not limited to this averaging method, and other methods such as addition, maximum intensity projection, and minimum intensity projection may also be used.

[0050] For example, when minimum intensity projection is applied as a method for creating a composite two-dimensional image, an example of a form in which only the tomographic images that include the location of the calcified lesion are targeted among the tomographic images to be projected can be used.

[0051] In this embodiment, a composite two-dimensional image is used as the image created by the image creation unit 34, but the present invention is not limited to this. For example, a slab image, which is an image having thickness information, may be used as the image created by the image creation unit 34. In this case, an example of the form is a form in which a slab image is created using only the tomographic images including the position of the calcified lesion.

[0052] The display control unit 35 displays the composite 2D image generated by the image generation unit 34 on the display 24. This composite 2D image is generated by weighting the tomographic image containing the location of the calcified lesion with a higher weight than the other tomographic images. Therefore, the composite 2D image displayed here is an extremely high-quality image in which the calcified lesion is emphasized.

[0053] The images created by the image creation unit 34 are not limited to the above-mentioned composite two-dimensional image and slab image, but may also be images for displaying a composite two-dimensional image created from multiple tomographic images Dj in conjunction with the corresponding tomographic images Dj.

[0054] That is, generally, the number of tomographic images may reach 100 or more depending on the application, which poses a problem that a relatively long time is required to interpret all the tomographic images.

[0055] Therefore, in this embodiment, the CPU 21 first creates and displays a composite 2D image as described above. In response to this, the operator refers to the displayed composite 2D image and specifies a structure of interest if the structure of interest displayed in the composite 2D image is suspected to be a calcified lesion. In response to this specification, the CPU 21 displays a tomographic image including the specified structure of interest. This significantly reduces the time required to interpret the tomographic image.

[0056] Next, the processing by the leveling unit 32 according to this embodiment will be described in detail with reference to Figs. 7 to 10. Fig. 7 is a diagram illustrating an example of the gradient convergence filter 60 according to this embodiment and a method for deriving the rate of change of the luminance gradient for a radiological image 70 by the gradient convergence filter 60. Fig. 8 is a diagram illustrating the effect of filtering by the gradient convergence filter 60 according to this embodiment. Fig. 9 is a diagram illustrating problems that arise when leveling by the leveling unit 32 according to this embodiment is not performed, and Figs. 10A to 10C are diagrams illustrating the effect of leveling by the leveling unit 32 according to this embodiment.

[0057] The smoothing unit 32 according to this embodiment derives the rate of change in the luminance gradient of a radiographic image by filtering using a gradient convergence filter 60 with a size of 3×3, as shown in the left diagram of Fig. 7. With this gradient convergence filter 60, the center position of the gradient convergence filter 60 is set to a pixel of interest X, and when the weighting is anisotropic, the rate of change Xc in the luminance gradient of the pixel of interest X is derived, for example, by the following equation (1).

[0058] Xc=(Xa) / 1.4+(Xb)+(Xc) / 1.4+(Xd) +(Xe) / 1.4+(Xf)+(Xg) / 1.4+(Xh) (1)

[0059] When a gradient convergence filter 60 having isotropic weighting is used, all "1.4" on the right side of equation (1) should be set to "1.0".

[0060] 7, the leveling unit 32 according to this embodiment moves the gradient convergence filter 60 from the upper left corner of the target radiographic image 70 toward the right, repeatedly moving row by row toward the bottom edge of the radiographic image 70. This allows filtering by the gradient convergence filter 60 to be performed on all pixels of the radiographic image 70.

[0061] In this way, in this embodiment, a gradient concentrated filter 60 having a size of 3×3 is used, but this is not limited to this. For example, a gradient concentrated filter having a size other than 3×3, such as a size of 5×5 or 7×7, may be used as the gradient concentrated filter 60.

[0062] The left diagram in Figure 8 shows an example of the distribution of brightness values ​​when minute calcified lesions are reflected in a tomographic image generated from a phantom, and as shown in the figure, there is a lot of noise per dot in the distribution of brightness values ​​in this case.In contrast, as shown in the right diagram in Figure 8, in the distribution of brightness values ​​filtered using the gradient concentration filter 60, the random unevenness (noise) per dot is attenuated, and the areas where the brightness gradient is concentrated are relatively emphasized.

[0063] However, simply relatively emphasizing the areas where the brightness gradient is concentrated by filtering using the gradient concentration filter 60 results in variations in SNR (Signal-Noise Ratio) due to differences in the distribution of mammary glands in tissue and differences in breast thickness among subjects, as shown in Fig. 9 for example, making it difficult to display calcified lesions in an emphasized manner in a composite 2D image. Note that the graph in the upper right of Fig. 9 is an example of the score for calcified lesions in an area with a relatively large number of mammary glands, and the graph in the lower right of Fig. 9 is an example of the score for calcified lesions in an area with a relatively small number of mammary glands. Note that the "score" shown in Figs. 8 and 9 represents the rate of change in the brightness gradient and essentially represents the intensity of calcification.

[0064] Generally, calcified lesions range in size from relatively large to minute. However, the image processing device 4 according to this embodiment primarily detects minute calcified lesions, for example, with a diameter of approximately 100 μm, and the impact of noise due to the SNR variation described above is severe.

[0065] Therefore, the leveling unit 32 according to the present embodiment uses a local moving kernel to derive a degree of variation (in the present embodiment, a standard deviation) indicating the degree of variation in the rate of change of the luminance gradient for each local region in the radiographic image.The leveling unit 32 according to the present embodiment then uses the degree of variation to level the rate of change of the luminance gradient.

[0066] The "moving kernel" referred to here indicates an area to be calculated that is defined on the radiographic image by the algorithm. In this embodiment, for example, a window size of 31 pixels is defined in both the vertical and horizontal directions, and the standard deviation is calculated within that area. As with the gradient convergence filter 60 shown on the right side of FIG. 7, this 31 x 31 window for calculating the standard deviation is moved one pixel at a time from the upper left to the lower right of the radiographic image, and the standard deviation within the area is calculated. The standard deviation value obtained as a result of this calculation is retained as the value at the center of the 31 x 31 window (position (15, 15) within the window). By this process, the standard deviation for each pixel of the radiographic image can be obtained.

[0067] Then, the smoothing unit 32 according to this embodiment smooths the rate of change of the derived luminance gradient for each corresponding pixel by multiplying the rate of change of the luminance gradient by the reciprocal of the derived standard deviation.

[0068] For example, if a 31x31 window is located at one position in the luminance gradient derivation result and the standard deviation there is 2.8 and at another position the standard deviation is 1.3, the smoothing according to this embodiment represents dividing the luminance gradient value by 2.8 and 1.3, respectively, which brings the standard deviation closer to 1.0 for the entire luminance gradient derivation result.

[0069] Figures 10A to 10C each show the distribution of the rate of change of the brightness gradient from an area with a relatively large number of mammary glands to an area with a relatively small number of mammary glands, with Figure 10A being before the smoothing according to this embodiment, Figure 10B being after the smoothing, and Figure 10C being the result of applying a threshold to the image shown in Figure 10B.

[0070] As shown in these figures, the normalization according to this embodiment can reduce the influence of noise, and as a result, minute calcified lesions can be detected with high accuracy by threshold processing.

[0071] Furthermore, as shown in Fig. 11, for example, a composite 2D image in which minute calcified lesions are emphasized can be obtained by generating a composite 2D image by emphasizing the positions of calcified lesions in the group of tomographic images as described above using the positions of calcified lesions detected by threshold processing. Fig. 11 is a diagram showing an example of a composite 2D image generated from the group of tomographic images according to this embodiment.

[0072] Next, the processing performed in this embodiment will be described. Fig. 12 is a flowchart showing the image processing performed in this embodiment. It is assumed here that a plurality of projection images Gi are acquired in advance and stored in the storage 23. To avoid confusion, the following description will be given of a case in which either one of an isotropic weighting filter and an anisotropic weighting filter is selected in advance as the gradient convergence filter 60 to be applied in this image processing.

[0073] When the input device 25 receives an instruction from the operator to start processing, the image processing program 22 starts to be executed, and the image processing shown in FIG. 12 starts.

[0074] First, the image acquisition unit 30 acquires projection images Gi obtained by imaging a subject (in this embodiment, a breast M) from multiple angles using radiation emitted from the radiation source 16 by reading them from the storage 23 (step 100). Next, the tomographic image reconstruction unit 31 reconstructs multiple tomographic images Dj from the acquired projection images Gi (step 102).

[0075] Next, the smoothing unit 32 performs the smoothing process described above on the reconstructed multiple tomographic images Dj (step 104). Next, the calcification detection unit 33 detects the position of the calcified lesion described above using the smoothed tomographic images Dj (step 106).

[0076] Then, the image creation unit 34 creates a composite two-dimensional image from the multiple tomographic images Dj as described above using the detected positions of the calcified lesions (step 108). Subsequently, the display control unit 35 displays the composite two-dimensional image on the display 24 (step 110), and the processing ends. As a result of the processing in step 110, the composite two-dimensional image shown in the right diagram of FIG. 11 is displayed on the display 24 as an example.

[0077] As described above, the image processing device according to this embodiment acquires radiographic images obtained by radiographing a breast, smooths the rate of change of the brightness gradient using a degree of variation indicating the degree of variation for each local region in the rate of change of the brightness gradient in the acquired radiographic image, and performs threshold processing using a predetermined threshold on the smoothed rate of change of the brightness gradient to detect the location of calcified lesions in the radiographic image. Therefore, compared to conventional techniques, it is possible to detect calcified lesions from breast radiographic images with reduced influence of noise.

[0078] Furthermore, the image processing device according to this embodiment creates a composite 2D image of the breast using the results of detecting the positions of calcified lesions, thereby enabling the creation of a composite 2D image in which calcified lesions are emphasized with reduced noise compared to conventional techniques.

[0079] Furthermore, according to the image processing device of this embodiment, the degree of variation is determined as the standard deviation or variance of the rate of change of the brightness gradient for each local region. Therefore, the degree of variation can be derived by the standard deviation or variance, which is a statistical method.

[0080] Furthermore, according to the image processing device of this embodiment, smoothing is performed by multiplying the reciprocal of the degree of variation by the rate of change of the brightness gradient. Therefore, smoothing can be performed using the derived degree of variation, and as a result, the calculation load can be reduced compared to when smoothing is performed using information other than the degree of variation.

[0081] Furthermore, according to the image processing device of this embodiment, the rate of change of the brightness gradient is derived by filtering using a gradient convergence filter, so that the rate of change of the brightness gradient can be easily derived by filtering.

[0082] Furthermore, the image processing device according to this embodiment selectively applies either an isotropic weighted or an anisotropic weighted gradient converged filter. Therefore, applying an isotropic weighted gradient converged filter can improve the detection effect for minute, nearly circular calcifications. Applying an anisotropic weighted gradient converged filter can improve the separation performance for calcifications with elongated (e.g., oblong) shapes in the directional component. This can ultimately contribute to the detection of linear structures in mammary glands and adipose tissue, as well as lesions such as elliptical calcifications that tend to be embedded within them.

[0083] In the above embodiment, the CPU 21 provided in the image processing device 4 is used as the processor of the technology of the present disclosure, but the present disclosure is not limited to this. For example, a CPU provided in any of the mammography device 1, the console 2, and the image storage system 3 may be used as the processor of the technology of the present disclosure.

[0084] In the above embodiment, the leveling of the technology of the present disclosure is applied to a tomographic image, but the present disclosure is not limited to this. For example, the leveling of the technology of the present disclosure may be applied to a composite two-dimensional image.

[0085] In the above embodiment, the gradient concentrated filter 60 to be applied is either one with isotropic weighting or one with anisotropic weighting. However, the present invention is not limited to this. For example, one of the gradient concentrated filters 60 may be applied first, and then another gradient concentrated filter 60 may be applied when it is desired to observe calcified lesions from a different perspective. In this way, the gradient concentrated filters 60 may be used in multiple stages.

[0086] In the above embodiment, the following various processors can be used as the hardware structure of processing units that perform various processes, such as the image acquisition unit 30, the tomographic image reconstruction unit 31, the leveling unit 32, the calcification detection unit 33, the image creation unit 34, and the display control unit 35. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as dedicated electrical circuits, such as programmable logic devices (PLDs) whose circuit configuration can be changed after manufacture, such as field programmable gate arrays (FPGAs), and application specific integrated circuits (ASICs), which are processors with a circuit configuration designed specifically for performing specific processes.

[0087] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.

[0088] Examples of configuring multiple processing units with a single processor include, first, a form in which one processor is configured with a combination of one or more CPUs and software, and this processor functions as multiple processing units, as typified by computers such as client and server. Second, a form in which a processor is used to realize the functions of the entire system including multiple processing units with a single IC (Integrated Circuit) chip, as typified by systems on chips (SoCs). In this way, various processing units are configured using one or more of the above-mentioned various processors as a hardware structure.

[0089] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0090] In the above embodiment, the image processing program 22 is pre-stored (installed) in the storage 23 of the image processing device 4, but the present invention is not limited to this. The image processing program 22 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The image processing program 22 may also be downloaded from an external device via a network.

[0091] From the above description, the invention described in the following appendix can be understood.

[0092] [Appendix 1] at least one processor; The processor: A radiological image is obtained by imaging the breast with radiation, smoothing the rate of change of the luminance gradient using a degree of variation indicating the degree of variation for each local region in the rate of change of the luminance gradient in the acquired radiographic image; and detecting the position of the calcified lesion in the radiological image by performing threshold processing using a predetermined threshold on the rate of change of the smoothed brightness gradient. Image processing device. [Appendix 2] The processor: generating a composite two-dimensional image of the breast using the detected location of the calcified lesions; 2. The image processing device according to claim 1. [Appendix 3] The degree of variation is a standard deviation or variance of the rate of change of the luminance gradient for each local region. 10. The image processing device according to claim 1 or 2. [Appendix 4] The processor: The smoothing is performed by multiplying the inverse of the degree of variation by the rate of change of the luminance gradient. 4. An image processing device according to any one of claims 1 to 3. [Appendix 5] The processor: deriving the rate of change of the luminance gradient by filtering using a gradient convergence filter; 5. An image processing device according to any one of claims 1 to 4. [Appendix 6] The processor: As the gradient concentration filter, one of a filter having isotropic weighting and a filter having anisotropic weighting is applied. The image processing device according to claim 5. [Appendix 7] An image processing device according to any one of Supplementary Note 1 to Supplementary Note 6; a radiographic image capturing device that captures a radiographic image used by the image processing device; A radiation imaging system including: [Appendix 8] A radiological image is obtained by imaging the breast with radiation, smoothing the rate of change of the luminance gradient using a degree of variation indicating the degree of variation for each local region in the rate of change of the luminance gradient in the acquired radiographic image; and detecting the position of the calcified lesion in the radiological image by performing threshold processing using a predetermined threshold on the rate of change of the smoothed brightness gradient. A program that causes a computer to perform a process. [Explanation of symbols]

[0093] 1. Mammography equipment 2 Console 3. Image storage system 4. Image processing device 11 Rotation axis 12 Arm section 13 Photo stand 14 Radiation irradiation unit 15 Radiation detector 15A detection surface 16 Radiation source 17 Compression plate 18 Support part 19 Moving mechanism 21 CPU 22 Image Processing Program 23 Storage 24 displays 25 Input Devices 26 memory 27 Network I / F 28 Bus 30 Image acquisition unit 31 Tomographic image reconstruction unit 32 Leveling Section 33 Calcification detection unit 34 Image Creation Department 35 Display control unit 60 Gradient Concentration Filter 70 Radiological images 90 Radiation Imaging System Dj (j=1~m), Dj tomographic image Gi(i=1~n), Gi projection image M Breast Si(i=1~n) Source position Sc reference source position X pixel of interest Xc rate of change X0 optical axis

Claims

1. at least one processor; The processor: A radiological image is obtained by imaging the breast with radiation, smoothing the rate of change of the luminance gradient using a degree of variation indicating the degree of variation for each local region in the rate of change of the luminance gradient in the acquired radiographic image; and detecting the position of the calcified lesion in the radiological image by performing threshold processing using a predetermined threshold on the rate of change of the smoothed brightness gradient. Image processing device.

2. The processor: generating a composite two-dimensional image of the breast using the detected location of the calcified lesions; The image processing device according to claim 1 .

3. The degree of variation is a standard deviation or variance of the rate of change of the luminance gradient for each local region.

3. The image processing device according to claim 1.

4. The processor: The smoothing is performed by multiplying the inverse of the degree of variation by the rate of change of the luminance gradient.

3. The image processing device according to claim 1.

5. The processor: deriving the rate of change of the luminance gradient by filtering using a gradient convergence filter; 3. The image processing device according to claim 1.

6. The processor: As the gradient concentration filter, one of a filter having isotropic weighting and a filter having anisotropic weighting is applied. The image processing device according to claim 5 .

7. The image processing device according to claim 1 or 2; a radiographic image capturing device that captures a radiographic image used by the image processing device; A radiation imaging system including:

8. A radiological image is obtained by imaging the breast with radiation, smoothing the rate of change of the luminance gradient using a degree of variation indicating the degree of variation for each local region in the rate of change of the luminance gradient in the acquired radiographic image; and detecting the position of the calcified lesion in the radiological image by performing threshold processing using a predetermined threshold on the rate of change of the smoothed brightness gradient. A program that causes a computer to perform a process.

Images