Image processing apparatus, radiation image capturing system and program

Abstract

To provide an image processing apparatus, a radiation image capturing system, and a program that can more highly accurately performing discrimination compared to a case where discriminating tomographic images corresponding to focal surfaces including a structure of interest from the tomographic images themselves.SOLUTION: An image processing apparatus 4 comprises: an image acquisition part 30 that acquires projection images obtained by imaging a subject from a plurality of angles with radiation; a tomographic image reconstruction part 31 that reconstructs a plurality of tomographic images from the acquired projection images an interest structure detection part 32 that detects a structure of interest from the plurality of reconstructed tomographic images; an interest structure region derivation part 33 that derives a region of the projection images that corresponds to the detected structure of interest; and a focal surface discrimination part 34 that discriminates, using the derived region of projection images, whether or not the tomographic image whose structure of interest is detected is a tomographic image corresponding to the focal surface of the structure of interest.SELECTED DRAWING: Figure 4

Description

[Technical field]

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

[0002] In recent years, imaging diagnosis using a radiation imaging device (called mammography) that captures the breast has been attracting attention in order to promote early detection of breast cancer. In addition, tomosynthesis imaging has been proposed in mammography, in which a radiation source is moved to irradiate the breast from multiple radiation source positions to capture images, and multiple projection images thus obtained are reconstructed to generate a tomographic image in which a desired tomographic plane is emphasized. 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 moved in a circular or elliptical arc to capture multiple projection images by capturing images of the breast at multiple radiation source positions, and these projection images are reconstructed using a backprojection method such as a simple backprojection method or a filtered backprojection method, or an iterative reconstruction method, to generate a tomographic image.

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

[0004] As a technology utilizing such tomographic images, Patent Document 1 discloses a technology in which a plurality of tomographic images, which are obtained by tomosynthesis imaging and have different distances (height direction positions) from the detection surface of a radiation detector toward the radiation source, are synthesized by an addition method, an averaging method, a maximum value projection method, a minimum value projection method, or the like, to generate a pseudo two-dimensional image (hereinafter referred to as a synthesized two-dimensional image) equivalent to a simple two-dimensional image.

[0005] In addition, Patent Document 2 discloses a tomographic image generating device that aims to improve the image quality of a tomographic image while shortening the calculation time when generating the tomographic image from a plurality of projection images acquired by performing imaging at a plurality of radiation source positions, such as tomosynthesis imaging.

[0006] This tomographic image generating device includes an image acquiring means for acquiring a plurality of projection images corresponding to a plurality of radiation source positions, which are captured by moving a radiation source relatively to a detection means and irradiating a subject with radiation at a plurality of radiation source positions resulting from the movement of the radiation source.The tomographic image generating device also includes a pixel value projecting means for projecting pixel values ​​of the plurality of projection images onto a desired coordinate position on a tomographic plane of the subject based on a positional relationship between the radiation source position and the detection means at the time of capturing each of the plurality of projection images, while retaining pixel values ​​of the plurality of projection images.The tomographic image generating device also includes a pixel value calculating means for calculating a pixel value of the coordinate position of interest based on a plurality of pixel values ​​of the projection images projected into a predetermined range based on the coordinate position of interest on the tomographic plane, thereby generating a tomographic image of the tomographic plane. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2014-128716 A [Patent Document 2] Patent No. 6185023 Summary of the Invention [Problem to be solved by the invention]

[0008] When creating a composite image such as a composite 2D image from a tomographic image or a slab image, which is an image that contains information about a certain range in the vertical direction, that is, information about the thickness, it is necessary to create the image in a state where structures of interest, such as tumors, spicules, calcifications, etc., are highly visible.

[0009] For this reason, it is desirable to identify the tomographic image where the structure of interest is actually located (hereinafter referred to as the "tomographic image corresponding to the focal plane") and create a composite image by emphasizing the identified tomographic image, but the techniques disclosed in Patent Documents 1 and 2 do not take this into consideration and are unable to distinguish the tomographic image. Note that the "focal plane" is ideally, among the tomographic planes where the structure of interest is actually located, a tomographic plane that corresponds to the height of the center where the structure of interest actually exists, or a tomographic plane where the structure of interest is easiest to distinguish compared to other tomographic planes, but is not limited to this.

[0010] It is also possible to consider a method of identifying the tomographic image corresponding to the focal plane from the tomographic image itself, but this method has the problem that it is difficult to distinguish between structures in non-focal planes and the actual structure of interest, and it is not possible to accurately identify the tomographic image corresponding to the focal plane.

[0011] The present disclosure has been made in consideration of the above circumstances, and aims to provide an image processing device, a radiological image capturing system, and a program that can perform such determination with greater accuracy than when determining a tomographic image corresponding to a focal plane containing a structure of interest from the tomographic image itself. [Means for solving the problem]

[0012] 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 projection images obtained by photographing a subject from multiple angles using radiation, reconstructs multiple tomographic images from the acquired projection images, detects a structure of interest from the multiple reconstructed tomographic images, derives a region of the projection image corresponding to the detected structure of interest, and uses the derived region of the projection image to determine whether the tomographic image in which the structure of interest is detected is a tomographic image corresponding to a focal plane of the structure of interest.

[0013] An image processing device according to a second aspect of the present disclosure is the image processing device according to the first aspect, in which a processor creates a composite two-dimensional image from a plurality of tomographic images using a result of the discrimination.

[0014] An image processing device according to a third aspect of the present disclosure is the image processing device according to the first aspect, wherein the processor creates a slab image from a plurality of tomographic images using a result of the discrimination.

[0015] An image processing device of a fourth aspect of the present disclosure is an image processing device of the first aspect, in which a processor uses the results of the discrimination to display a composite two-dimensional image created from multiple tomographic images in conjunction with the corresponding tomographic images.

[0016] An image processing device of a fifth aspect of the present disclosure is an image processing device of the first aspect, in which a processor detects a structure of interest by at least one of a machine learning model and pattern matching using a template image of the target structure of interest.

[0017] An image processing device according to a sixth aspect of the present disclosure is the image processing device according to the first aspect, in which the processor performs the discrimination using a similarity between regions of corresponding projected images.

[0018] An image processing device according to a seventh aspect of the present disclosure is the image processing device according to the sixth aspect, wherein the similarity is a correlation value between regions of corresponding projected images.

[0019] An image processing device of an eighth aspect of the present disclosure is an image processing device of the sixth or seventh aspect, in which a processor determines, for each type of structure of interest, the tomographic image at the height at which the corresponding similarity is maximized for each height in the tomographic image at which the structure of interest is detected, as the tomographic image corresponding to the focal plane.

[0020] An image processing device according to a ninth aspect of the present disclosure is the image processing device according to the first aspect, wherein the structure of interest is at least one of a mass, a spicule, and a calcification.

[0021] In order to achieve the above object, a radiation image capturing system according to a tenth aspect of the present disclosure includes the image processing device according to the first aspect, and a mammography device that acquires a projection image used by the image processing device.

[0022] Furthermore, in order to achieve the above-mentioned object, the program of an eleventh aspect of the present disclosure causes a computer to execute processes of acquiring projection images obtained by photographing a subject from multiple angles using radiation, reconstructing multiple tomographic images from the acquired projection images, detecting a structure of interest from the multiple reconstructed tomographic images, deriving a region of the projection image corresponding to the detected structure of interest, and using the derived region of the projection image to determine whether the tomographic image in which the structure of interest is detected is a tomographic image corresponding to a focal plane of the structure of interest. Effect of the Invention

[0023] According to the present disclosure, the determination can be made with higher accuracy than when a tomographic image corresponding to a focal plane including a structure of interest is determined from the tomographic image itself. [Brief description of the drawings]

[0024] [Figure 1] 1 is a schematic configuration diagram of a radiation image capturing system to which an image processing device according to an embodiment is applied; [Diagram 2] 2 is a diagram showing the mammography apparatus according to the embodiment as viewed in the direction of arrow A in FIG. [Diagram 3] 1 is a block diagram showing an example of an electrical configuration of an image processing apparatus according to an embodiment; [Figure 4] FIG. 2 is a functional block diagram showing a functional configuration of the image processing apparatus according to the embodiment. [Diagram 5] 4A and 4B are diagrams for explaining acquisition of a projection image according to the embodiment. [Figure 6] 4A to 4C are diagrams for explaining generation of a tomographic image according to the embodiment. [Figure 7] 5A to 5C are diagrams for explaining a method for determining a tomographic image corresponding to a focal plane according to the embodiment. [Figure 8]5A to 5C are diagrams for explaining a method for determining a tomographic image corresponding to a focal plane according to the embodiment. [Figure 9] 5 is a flowchart illustrating an example of image processing according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] Hereinafter, an embodiment 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 diagram of a mammography device 1 in the radiographic imaging system 90 as viewed from the direction of arrow A in Fig. 1.

[0026] 1, a radiation image capturing system 90 according to this embodiment is for capturing images of a subject, a breast M, from multiple radiation source positions to obtain multiple radiation images, i.e., multiple projection images, in order to perform tomosynthesis imaging of the breast and generate a tomographic image. The radiation image capturing system 90 according to this embodiment includes a mammography device 1, a console 2, an image storage system 3, and an image processing device 4.

[0027] The mammography device 1 has an arm unit 12 connected to a base (not shown) by a rotation shaft 11. An imaging table 13 is attached to one end of the arm unit 12, and a radiation irradiation unit 14 is attached to the other end so as to face the imaging table 13. The arm unit 12 is configured so that only the end to which the radiation irradiation unit 14 is attached can rotate, which makes it possible to rotate only the radiation irradiation unit 14 while fixing the imaging table 13.

[0028] A radiation detector 15 such as a flat panel detector is provided inside the imaging stand 13. The radiation detector 15 has a radiation detection surface 15A. Also provided inside the imaging stand 13 are a circuit board and the like on which are provided a charge amplifier that converts a charge signal read out from the radiation detector 15 into a voltage signal, a correlated double sampling circuit that samples the voltage signal output from the charge amplifier, and an AD (Analog-Digital) conversion unit that converts the voltage signal into a digital signal.

[0029] 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 the target and filter materials, the tube voltage, the irradiation time, and the like, are controlled by the console 2.

[0030] 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 section 18 that supports the compression plate 17, and a movement mechanism 19 that moves the support section 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.

[0031] The console 2 has a function of controlling the mammography apparatus 1 using imaging orders and various information acquired from a RIS (Radiology Information System) (not shown) or the like via a network such as a wireless communication LAN (Local Area Network) and using 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 a plurality of projection images, as will be described later. As an example, in this embodiment, a server computer is used as the console 2.

[0032] The image storage system 3 is a system that stores image data such as a projection image captured by the mammography device 1. The image storage system 3 extracts from the stored images an image corresponding to a request from the console 2, the image processing device 4, etc., and transmits it to the device that issued the request. A specific example of the image storage system 3 is a PACS (Picture Archiving and Communication System).

[0033] Next, the image processing device 4 according to the present embodiment will be described. First, the hardware configuration of the image processing device 4 according to the present 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, a non-volatile storage 23, and a 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.

[0034] 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, expands it in the memory 26, and executes the expanded image processing program 22.

[0035] The image processing program 22 is stored in a storage device of a server computer connected to the network or in a network storage in an externally accessible state, and is downloaded and installed in a computer constituting the image processing device 4 upon request. Alternatively, the image processing program 22 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 in a computer constituting the image processing device 4 from the recording medium.

[0036] Next, a 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.

[0037] 4, the image processing device 4 according to this embodiment includes an image acquisition section 30, a tomographic image reconstruction section 31, a structure of interest detection section 32, a structure of interest region derivation section 33, a focal plane determination section 34, an image creation section 35, and a display control section 36. The CPU 21 executes the image processing program 22 to function as the image acquisition section 30, the tomographic image reconstruction section 31, the structure of interest detection section 32, the structure of interest region derivation section 33, the focal plane determination section 34, the image creation section 35, and the display control section 36.

[0038] 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.

[0039] 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 unit 12 around the rotation axis 11, irradiates the breast M, which is the subject, with radiation at a plurality of radiation source positions by the movement of the radiation source 16 under predetermined imaging conditions for tomosynthesis imaging, detects the radiation transmitted through the breast M with the radiation detector 15, and obtains a plurality of projection images Gi (i=1 to n, n is the number of radiation source positions, for example, n=15) at the plurality of radiation source positions.

[0040] Fig. 5 is a diagram for explaining acquisition of projection images Gi. As shown in Fig. 5, radiation source 16 is moved to each radiation source position S1, S2, ..., Sn, and radiation source 16 is driven at each radiation source position to irradiate breast M with radiation, and 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 to breast M at each radiation source position S1 to Sn.

[0041] 5, 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.

[0042] 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 a simple back projection method or a filtered back projection method, and generates multiple cross-sectional images Dj (j=1 to m) in 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 pixels corresponding to the set three-dimensional coordinate position in the multiple projection images Gi are reconstructed, and the pixel value of the coordinate position is calculated.

[0043] The structure of interest detection unit 32 detects structures of interest from the multiple tomographic images Dj. In this embodiment, masses, spicules, and calcifications contained in the breast M are detected as structures of interest.

[0044] In the structure of interest detection unit 32 according to the present embodiment, a machine learning model 32A consisting of a neural network that has been machine-learned by deep learning or the like using teacher data so as to extract a structure of interest from each of the tomographic images Dj is used to detect the structure of interest. As the machine learning model 32A, for example, a well-known neural network such as a convolutional neural network (CNN) or a support vector machine (SVM) can be used.

[0045] In this manner, in this embodiment, the structure of interest is detected by the machine learning model 32A, but the present invention is not limited to this. For example, a known computer-aided image diagnosis (i.e., CAD) algorithm may be used to detect the structure of interest from the tomographic image Dj. In the CAD algorithm, a probability (likelihood) indicating that a pixel in the tomographic image Dj is a structure of interest is derived, and a pixel with a probability equal to or greater than a predetermined threshold is detected as the structure of interest. Note that a CAD algorithm is prepared for each type of structure of interest. When a CAD algorithm is applied in this embodiment, a CAD algorithm for mass detection, a CAD algorithm for spicule detection, and a CAD algorithm for calcification detection are prepared.

[0046] In addition, the detection of the structure of interest is not limited to using the machine learning model 32A or using CAD. For example, the structure of interest may be detected from the tomographic image Dj by pattern matching using a template image of the target structure of interest, or by filtering processing using a filter for detecting the structure of interest. Here, when pattern matching is applied, an image of the structure of interest of the type to be extracted that has already been acquired is applied as the template image. In addition, in this embodiment, the structure of interest is detected using only the machine learning model 32A, but this is not limited to this. For example, the structure of interest may be detected using both the machine learning model 32A and pattern matching. Furthermore, in this embodiment, the method of detecting the structure of interest may be switched depending on the type of the structure of interest to be detected.

[0047] Furthermore, as described above, in this embodiment, the target structure of interest is all of the mass, spicules, and calcification, but this is not limiting. For example, any one of the mass, spicules, and calcification, or a combination of two of them, may be used as the target structure of interest.

[0048] The structure of interest region derivation unit 33 derives a region of the projection image Gi corresponding to the structure of interest detected by the structure of interest detection unit 32. The structure of interest region derivation unit 33 according to this embodiment derives a two-dimensional coordinate position of the structure of interest in the corresponding projection image Gi from the position in the tomographic image Dj of the structure of interest detected by the structure of interest detection unit 32, the position in the stacking direction of the tomographic image Dj (the depth direction in which the tomographic planes are lined up), the position of the radiation source 16 at the time of capturing the corresponding projection image Gi, and the position of the detection surface 15A of the radiation detector 15.

[0049] That is, the position of the structure of interest in the tomographic image Dj is detected by the structure of interest detection unit 32, and the positions of the tomographic image Dj, the radiation source 16, and the detection surface 15A are specified in advance. Therefore, the structure of interest region derivation unit 33 according to this embodiment uses these positional relationships to derive, by calculation, the two-dimensional coordinate position of the structure of interest in the projection image Gi when projected onto the detection surface 15A of the radiation detector 15 by the radiation emitted from the radiation source 16 (hereinafter referred to as the "structure of interest position").

[0050] The focal plane discrimination unit 34 uses the region of the projection image Gi derived by the structure of interest region derivation unit 33, i.e., the position of the structure of interest in each projection image Gi, to determine whether the tomographic image Dj in which the structure of interest is detected by the structure of interest detection unit 32 is a tomographic image corresponding to the tomographic plane (hereinafter referred to as the "focal plane") on which the structure of interest is actually located.

[0051] That is, if the tomographic image in which the structure of interest is detected is a tomographic image corresponding to the focal plane, the structure of interest 80 is reflected in approximately the same position in each of the projection images Gi, as shown in Fig. 7 as an example. On the other hand, if the tomographic image in which the structure of interest is detected is a tomographic image corresponding to a plane other than the focal plane (hereinafter referred to as a "non-focal plane"), the focus is shifted, so that the structure of interest 80 reflected in each of the projection images Gi is shifted, as shown in Fig. 8 as an example. Note that Figs. 7 and 8 are diagrams for explaining a method of determining a tomographic image corresponding to a focal plane according to this embodiment.

[0052] Therefore, the focal plane discrimination unit 34 in this embodiment determines whether each of the projection images Gi corresponding to the tomographic image in which the structure of interest is detected is similar to each other, thereby determining whether the tomographic image corresponds to the focal plane.

[0053] The focal plane determination unit 34 according to this embodiment cuts out rectangular regions (hereinafter referred to as "cut-out regions") having the same area and including the structure of interest position derived by the structure of interest region derivation unit 33 from each of the projection images Gi (hereinafter referred to as "target projection images") corresponding to the tomographic images in which the structure of interest is detected. The focal plane determination unit 34 according to this embodiment then determines whether the cut-out regions in the target projection images are similar to each other, thereby determining whether the corresponding tomographic images correspond to the focal plane.

[0054] In the focal plane discrimination unit 34 according to the present embodiment, the determination of whether or not the cut-out regions in the target projection image are similar to each other is performed using the average value of the similarity between the cut-out regions. In addition, in the present embodiment, the correlation value between the corresponding cut-out regions is applied as the similarity.

[0055] As the correlation value between images, various values ​​that can be calculated relatively easily, such as SAD (Sum of Absolute Difference), SSD (Sum of Squared Difference), NCC (Normalized Cross-Correlation), ZNCC (Zero-mean Normalized Cross-Correlation), etc., can be applied, and among these, SAD is applied in this embodiment. That is, in the focal plane discrimination unit 34 according to this embodiment, the correlation value is calculated as the sum of the absolute values ​​of the differences in luminance values ​​of corresponding pixels between each of the cut-out regions for all pixels. However, this is not limited to this form, and it goes without saying that other correlation values ​​such as SSD and NCC may be applied, and a value other than the correlation value that indicates the degree of similarity between each of the cut-out regions may be applied as the similarity.

[0056] Then, the focal plane discrimination unit 34 according to the present embodiment discriminates that the tomographic image at the height where the corresponding similarity (here, correlation value) is maximum for each height in the tomographic image where the structure of interest is detected, is the tomographic image corresponding to the focal plane, for each type of structure of interest. This makes it possible to discriminate high-quality tomographic images for each type of structure of interest.

[0057] The image creation unit 35 creates a composite two-dimensional image from the multiple tomographic images Dj using the result of the discrimination by the focal plane discrimination unit 34.

[0058] In the image creation unit 35 according to the present embodiment, a composite two-dimensional image is created by taking a weighted average for each pixel, where the weight value (0.9 as an example) of the tomographic image determined by the focal plane determination unit 34 to correspond to the focal plane is set to a value greater than the weight value (0.1 as an example) of the tomographic image other than the tomographic image, i.e., the tomographic image corresponding to the non-focal plane. However, the method of creating the composite two-dimensional image is not limited to this averaging method, and an addition method, a maximum value projection method, a minimum value projection method, or the like may be used as the method of creating the composite two-dimensional image.

[0059] For example, when applying minimum intensity projection as a method for creating a composite 2D image, an example of a form in which only the tomographic images to be projected are targeted, excluding the tomographic images corresponding to the non-focal planes.

[0060] In this manner, in this embodiment, a composite two-dimensional image is applied as the image created by the image creation unit 35, but the present invention is not limited to this. For example, a slab image, which is an image having thickness information, may be applied as the image created by the image creation unit 35. In this case, an example of the form may be a form in which a slab image is created using only the tomographic images corresponding to the focal plane.

[0061] The display control unit 36 ​​displays the composite two-dimensional image generated by the image generation unit 35 on the display 24. This composite two-dimensional image is generated by increasing the weighting value of the tomographic image corresponding to the focal plane of the structure of interest compared to the other tomographic images. Therefore, the composite two-dimensional image displayed here is an extremely high-quality image in which artifacts are suppressed and the structure of interest is emphasized.

[0062] In addition, the images created by the image creation unit 35 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 sectional images Dj in conjunction with the corresponding sectional images Dj.

[0063] That is, in general, the number of tomographic images may reach 100 or more depending on the application. Therefore, there is a problem that a relatively long time is required to interpret all the tomographic images.

[0064] Therefore, in this embodiment, the CPU 21 first creates and displays a composite two-dimensional image as described above. In response to this, the operator refers to the displayed composite two-dimensional image and specifies a structure of interest when the structure of interest displayed in the composite two-dimensional image is suspected to be a lesion. In response to this specification, the CPU 21 displays a tomographic image including the specified structure of interest. This makes it possible to significantly reduce the time required to interpret the tomographic image.

[0065] Next, the processing performed in this embodiment will be described. Fig. 9 is a flowchart showing the image processing performed in this embodiment. Note that it is assumed here that a plurality of projection images Gi are acquired and stored in the storage 23 in advance.

[0066] When the input device 25 receives an instruction from an operator to start processing, the image processing program 22 starts to be executed, and thus the image processing shown in FIG. 9 starts.

[0067] First, the image acquisition unit 30 acquires projection images Gi obtained by photographing 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).

[0068] Next, the structure of interest detection unit 32 detects a structure of interest from the reconstructed multiple tomographic images Dj (step 104). Next, the structure of interest region derivation unit 33 derives a region of the projection image corresponding to the detected structure of interest (step 106). Next, the focal plane determination unit 34 uses the derived region of the projection image to determine whether the tomographic image in which the structure of interest is detected is a tomographic image corresponding to the focal plane (step 108).

[0069] Then, the image creation unit 35 creates a composite two-dimensional image from the multiple tomographic images Dj using the results of the above-mentioned determination (step 110). Next, the display control unit 36 ​​displays the composite two-dimensional image on the display 24 (112), and the process ends.

[0070] As described above, the image processing device according to this embodiment acquires projection images obtained by photographing a subject from multiple angles using radiation, reconstructs multiple tomographic images from the acquired projection images, detects a structure of interest from the multiple reconstructed tomographic images, derives an area of ​​the projection image corresponding to the detected structure of interest, and uses the derived area of ​​the projection image to determine whether the tomographic image in which the structure of interest is detected is a tomographic image corresponding to a focal plane. This allows for more accurate determination than when determining a tomographic image corresponding to a focal plane containing the structure of interest from the tomographic image itself.

[0071] Moreover, according to the image processing device of the present embodiment, a composite 2D image is created from a plurality of tomographic images using the result of the above-mentioned discrimination, so that a composite 2D image can be created by emphasizing the structure of interest located on the above-mentioned focal plane, and as a result, a higher quality composite 2D image can be created.

[0072] In addition, the image processing device according to the present embodiment also illustrates an aspect in which a slab image is created from a plurality of tomographic images using the result of the above-mentioned discrimination. Therefore, according to this aspect, a slab image can be created by emphasizing the structure of interest located on the focal plane, and as a result, a slab image of higher quality can be created.

[0073] In addition, the image processing device according to the present embodiment also illustrates a mode in which a composite two-dimensional image created from a plurality of tomographic images and the corresponding tomographic images are displayed in a linked manner using the result of the above-mentioned determination. Therefore, according to this mode, the linked display can be performed more effectively.

[0074] Moreover, according to the image processing device of the present embodiment, the detection of the structure of interest is performed by a machine learning model, and therefore, the structure of interest can be detected with higher accuracy than when the structure of interest is detected without using a machine learning model.

[0075] Moreover, according to the image processing device of the present embodiment, the above-mentioned determination is made using the similarity between the regions of the corresponding projected images, and a correlation value that can be calculated relatively easily is applied as the similarity, so that the above-mentioned determination can be made more easily than when the above-mentioned correlation value is not used.

[0076] In addition, according to the image processing device of the present embodiment, for each type of structure of interest, the tomographic image at the height where the corresponding similarity is maximum for each height in the tomographic image where the structure of interest is detected is determined to be the tomographic image corresponding to the focal plane, so that a high-quality tomographic image can be determined for each type of structure of interest.

[0077] Furthermore, according to the image processing device of this embodiment, at least one of a mass, a spicule, and calcification is applied as a structure of interest, and therefore a composite image in which the applied structure of interest is emphasized can be displayed.

[0078] 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.

[0079] In the above embodiment, the following various processors can be used as the hardware structure of the processing unit that executes various processes, such as the image acquisition unit 30, the tomographic image reconstruction unit 31, the structure of interest detection unit 32, the structure region of interest derivation unit 33, the focal plane discrimination unit 34, the image creation unit 35, and the display control unit 36. As described above, the above various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and a dedicated electric circuit, such as an ASIC (Application Specific Integrated Circuit), which is a processor having a circuit configuration designed specifically for executing specific processes.

[0080] 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.

[0081] As an example of configuring multiple processing units with one processor, first, there is 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 represented by computers such as client and server. Second, there is a form in which a processor is used to realize the functions of the entire system including multiple processing units with one IC (Integrated Circuit) chip, as represented by a system on chip (SoC). In this way, the various processing units are configured using one or more of the above various processors as a hardware structure.

[0082] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0083] 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 be downloaded from an external device via a network.

[0084] From the above description, the invention described in the following appendix can be understood.

[0085] [Appendix 1] at least one processor; The processor, A projection image is obtained by photographing a subject from multiple angles using radiation. Reconstructing a plurality of tomographic images from the acquired projection images; Detecting a structure of interest from the reconstructed tomographic images; Deriving a region of the projection image corresponding to the detected structure of interest; Using the derived region of the projection image, it is determined whether the tomographic image in which the structure of interest is detected is a tomographic image corresponding to a focal plane of the structure of interest. Image processing device. [Appendix 2] The processor, creating a composite two-dimensional image from the plurality of tomographic images using a result of the discrimination; 2. An image processing device as described in claim 1. [Appendix 3] The processor, creating a slab image from the plurality of tomographic images using a result of the discrimination; 3. An image processing device according to claim 1 or 2. [Appendix 4] The processor, using a result of the discrimination, a composite two-dimensional image created from the plurality of tomographic images is displayed in association with the corresponding tomographic images. 4. An image processing device according to claim 1, [Appendix 5] The processor, detecting the structure of interest by at least one of a machine learning model and pattern matching using a template image of the structure of interest of interest; 5. An image processing device according to any one of claims 1 to 4. [Appendix 6] The processor, The determination is performed using a similarity between corresponding regions of the projection images. 6. An image processing device according to any one of claims 1 to 5. [Appendix 7] The similarity is a correlation value between regions of the corresponding projection images. 7. The image processing device according to claim 6. [Appendix 8] The processor, determining, for each type of the structure of interest, the tomographic image at a height at which the corresponding similarity is maximized for each height in the tomographic image at which the structure of interest is detected, as the tomographic image corresponding to the focal plane; 8. The image processing device according to claim 6 or 7. [Appendix 9] The structure of interest is at least one of a mass, a spicule, and a calcification; 9. An image processing device according to any one of claims 1 to 8. [Appendix 10] An image processing device according to any one of claims 1 to 9, a mammography device for acquiring projection images used by the image processing device; A radiation imaging system comprising: [Appendix 11] A projection image is obtained by photographing a subject from multiple angles using radiation. Reconstructing a plurality of tomographic images from the acquired projection images; Detecting a structure of interest from the reconstructed tomographic images; Deriving a region of the projection image corresponding to the detected structure of interest; Using the derived region of the projection image, it is determined whether the tomographic image in which the structure of interest is detected is a tomographic image corresponding to a focal plane of the structure of interest. A program that causes a computer to carry out processing. [Explanation of symbols]

[0086] 1. Mammography equipment 2 Console 3. Image storage system 4. Image Processing Device 11 Rotation axis 12 Arm section 13. Shooting stand 14 Radiation Irradiation Section 15 Radiation detector 15A Detection surface 16 Radiation source 17 Compression plate 18 Support part 19 Moving mechanism 21 CPU 22 Image Processing Programs 23. Storage 24 Display 25 Input Devices 26 Memory 27 Network Interface 28 Bus 30 Image acquisition unit 31 Tomographic image reconstruction unit 32 Interesting Structure Detection Unit 32A Machine Learning Model 33. Region of interest extraction section 34 Focal plane discrimination section 35 Image Creation Department 36 Display control section 80 Interest Structure 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 X0 optical axis

Claims

1. At least one processor; The processor, A projection image is obtained by photographing a subject from multiple angles using radiation. Reconstructing a plurality of tomographic images from the acquired projection images; Detecting a structure of interest from the reconstructed tomographic images; Deriving a region of the projection image corresponding to the detected structure of interest; Using the derived region of the projection image, it is determined whether the tomographic image in which the structure of interest is detected is a tomographic image corresponding to a focal plane of the structure of interest. Image processing device.

2. The processor, creating a composite two-dimensional image from the plurality of tomographic images using a result of the discrimination; The image processing device according to claim 1 .

3. The processor, creating a slab image from the plurality of tomographic images using a result of the discrimination; The image processing device according to claim 1 .

4. The processor, using a result of the discrimination, a composite two-dimensional image created from the plurality of tomographic images is displayed in association with the corresponding tomographic images. The image processing device according to claim 1 .

5. The processor, detecting the structure of interest by at least one of a machine learning model and pattern matching using a template image of the structure of interest of interest; The image processing device according to claim 1 .

6. The processor, The determination is performed using a similarity between corresponding regions of the projection images. The image processing device according to claim 1 .

7. The similarity is a correlation value between regions of the corresponding projection images. The image processing device according to claim 6.

8. The processor, determining, for each type of the structure of interest, the tomographic image at a height at which the corresponding similarity is maximized for each height in the tomographic image at which the structure of interest is detected, as the tomographic image corresponding to the focal plane; 8. The image processing device according to claim 6 or 7.

9. the structure of interest is at least one of a mass, a spicule, and a calcification; The image processing device according to claim 1 .

10. The image processing device according to claim 1 ; a mammography device for acquiring projection images used by the image processing device; A radiation imaging system comprising:

11. A projection image is obtained by photographing a subject from multiple angles using radiation. Reconstructing a plurality of tomographic images from the acquired projection images; Detecting a structure of interest from the reconstructed tomographic images; Deriving a region of the projection image corresponding to the detected structure of interest; Using the derived region of the projection image, it is determined whether the tomographic image in which the structure of interest is detected is a tomographic image corresponding to a focal plane of the structure of interest. A program that causes a computer to carry out processing.

Images