X-ray imaging device and image processing method

Abstract

The present invention provides an X-ray imaging apparatus and an image processing method. The X-ray imaging apparatus includes an X-ray irradiation unit, an X-ray detection unit, and an image processing unit. The image processing unit includes an extracted image generation unit that generates an extracted image by extracting a bone region of a diagnostic target site from an X-ray image; and a bone region supplementation unit that segments a region including an obturator foramen from the extracted image, thereby distinguishing the obturator foramen and supplementing the foramen of the bone region including an iliac wing region. The obturator foramen region corresponds to the obturator foramen, a physiological orifice of the pelvis of a subject, and the iliac wing region corresponds to the iliac wing of the ilium of the pelvis of the subject.

Description

Technical Field

[0001] The present invention relates to an X-ray imaging device and an image processing method, and in particular to an X-ray imaging device and an image processing method for extracting a bone region of a subject. Background Art

[0002] Conventionally, there is known a method for measuring bone density by extracting a region (bone region) including the femur and pelvis. For example, such a method is disclosed in Japanese Patent Application Laid-Open No. 07-284020.

[0003] In the bone density measurement method described in Japanese Patent Application Laid-Open No. 07-284020, soft tissue and bone are distinguished from captured X-ray images, and the bone density of the region encompassing the femur and pelvis is measured using the DEXA method (Dual Energy X-ray Absorptiometry). In this method, a binary image is generated based on a predetermined threshold value to distinguish between bone and soft tissue based on the pixel density of the X-ray image. Because the soft tissue and bone portions in this binary image contain noise, the binary image is subjected to noise removal processing such as smoothing.

[0004] Here, when generating a binary image (extracted image) for extracting a bone portion (bone region) from an acquired X-ray image, sometimes the thin bone portion such as the ilium on the upper side of the pelvis is processed as a soft tissue that is not a bone. In addition, in addition to the ilium, sometimes the area where bones actually exist is processed as an area of ​​soft tissue (background area). In this case, a plurality of isolated points or areas (holes) are included in the bone area. Therefore, it is necessary to exclude isolated points and areas from the generated extracted image. However, since there is an obturator foramen as a physiological hole in the lower part of the pelvis, in the noise removal process such as smoothing such as the bone density measurement method described in the above-mentioned Japanese Patent Laid-Open No. 07-284020, it is impossible to distinguish the obturator foramen area corresponding to the obturator foramen from the hole inside the bone area, making it difficult to accurately extract the area corresponding to the actual bone part. Summary of the Invention

[0005] The present invention has been made to solve the above-mentioned problems, and one object of the present invention is to provide an X-ray imaging apparatus and an image processing method that can accurately extract a region corresponding to an actual bone while identifying the obturator foramen of the pelvis.

[0006] To achieve the above-mentioned object, an X-ray imaging apparatus according to a first aspect of the present invention comprises: an X-ray irradiation unit that irradiates X-rays toward a diagnostic target portion of a subject, including a femur and a pelvis; an X-ray detection unit that detects the X-rays irradiated from the X-ray irradiation unit; and an image processing unit that extracts a bone region of the diagnostic target portion from an X-ray image formed by the X-rays detected by the X-ray detection unit, wherein the image processing unit includes: an extracted image generation unit that generates an extracted image obtained by extracting the bone region of the diagnostic target portion from the X-ray image; and a bone region supplementation unit that segments a region including an obturator foramen region from the extracted image generated by the extracted image generation unit, thereby supplementing the orifice portion of the bone region including an iliac wing region while distinguishing the obturator foramen region, the obturator foramen region being a region corresponding to the obturator foramen, which is a physiological cavity in the subject's pelvis, and the iliac wing region being a region corresponding to the iliac wing of the ilium of the subject's pelvis. In addition, the "supplementation of the hole portion of the bone area" mentioned here means that when there is an area (hole portion) judged to be an area other than the bone (background area) inside the bone area judged to be a bone in the extracted image, the area other than the bone included in the bone area is removed by filling the hole portion.

[0007] The image processing method of the second aspect of the present invention includes the following steps: irradiating a diagnostic object part of a subject including a femur and a pelvis with X-rays; detecting the irradiated X-rays; generating an extracted image obtained by extracting a bone area of ​​the diagnostic object part from an X-ray image formed by the detected X-rays; and dividing a region including an obturator foramen from the generated extracted image, thereby identifying the obturator foramen while supplementing the hole portion of the bone region including the iliac wing region, wherein the obturator foramen region is a region corresponding to the obturator foramen as a physiological hole in the pelvis of the subject, and the iliac wing region is a region corresponding to the iliac wing of the ilium of the pelvis of the subject.

[0008] In the X-ray imaging device of the first aspect and the image processing method of the second aspect, a region including the obturator foramen is segmented from the generated extracted image, thereby identifying the obturator foramen while supplementing foramina in the bone region including the iliac wing region. The obturator foramen region is a region corresponding to the obturator foramen, a physiological orifice of the subject's pelvis. The iliac wing region is a region corresponding to the iliac wing of the ilium of the subject's pelvis. By segmenting the region including the obturator foramen from the extracted image, isolated points and regions (foramina) in the bone outside the obturator foramen region can be distinguished relative to the obturator foramen region. Therefore, it is possible to distinguish foramina in the bone region to be supplemented from the obturator foramen region while supplementing foramina in the bone region including the iliac wing region, a region where foramina are more likely to occur due to thin bones. As a result, it is possible to accurately extract a region corresponding to the actual bone region while identifying the obturator foramen of the pelvis. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a diagram showing the configuration of the X-ray imaging apparatus according to the first embodiment.

[0010] Figure 2 It is a diagram for explaining an X-ray image according to the first embodiment.

[0011] Figure 3 This is a diagram for explaining the generation of an extracted image based on the learned model according to the first embodiment.

[0012] Figure 4 It is a diagram for explaining the extraction image and the target image according to the first embodiment.

[0013] Figure 5 This is a supplementary diagram for explaining the hole portion in the bone region of the first embodiment.

[0014] Figure 6 It is a diagram for explaining acquisition of a partial image in the first embodiment.

[0015] Figure 7 It is a diagram for explaining the identification of the closed cell region in the first embodiment.

[0016] Figure 8 This is a diagram for explaining the generation of a recognition result image according to the first embodiment.

[0017] Figure 9 This is a diagram for explaining an example of removing a hand portion of a subject included in an extraction image according to the first embodiment.

[0018] Figure 10 This is a flowchart for explaining the image processing method according to the first embodiment.

[0019] Figure 11 It is a diagram showing the configuration of an X-ray imaging apparatus according to a second embodiment.

[0020] Figure 12 It is a diagram for explaining the extracted image and the target image according to the second embodiment.

[0021] Figure 13 This is a diagram for explaining the generation of a recognition result image according to the second embodiment. DETAILED DESCRIPTION

[0022] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

[0023] [First embodiment]

[0024] (Structure of X-ray Radiography Apparatus)

[0025] Reference Figures 1 to 9 An X-ray imaging apparatus 100 according to a first embodiment of the present invention will be described.

[0026] like Figure 1 As shown, the X-ray imaging apparatus 100 in the first embodiment includes an X-ray irradiation unit 1, an X-ray detection unit 2, and a control unit 3. The control unit 3 is an example of an "image processing unit" in the claims.

[0027] The X-ray irradiation unit 1 irradiates X-rays to the diagnostic target part including the femur and pelvis of the subject 101. The X-ray detection unit 2 detects the X-rays irradiated from the X-ray irradiation unit 1. The X-ray imaging device 100 is used, for example, to measure the bone density of the subject 101. In the first embodiment, the X-ray irradiation unit 1 is configured to irradiate two types of X-rays having different energies to the diagnostic target part including the femur and pelvis of the subject 101. In addition, in the measurement of bone density, the DEXA method (Dual Energy X-ray Absorptiometry method) is used to distinguish between bone components and other tissues using two types of X-rays having different energies.

[0028] The X-ray irradiation unit 1 includes an X-ray source 1a. The X-ray source 1a is an X-ray tube connected to a high voltage generator (not shown) and generates X-rays when a high voltage is applied. The X-ray source 1a is arranged so that the X-ray emission direction faces the detection surface of the X-ray detection unit 2.

[0029] The X-ray detector 2 detects X-rays emitted from the X-ray irradiator 1 and transmitted through the subject 101, and outputs a detection signal corresponding to the intensity of the detected X-rays. The X-ray detector 2 is composed of, for example, an FPD (Flat Panel Detector).

[0030] The control unit 3 includes, as functional components, an image acquisition unit 31, an extracted image generation unit 32, a bone region supplementation unit 33, a partial image acquisition unit 34, a target image acquisition unit 35, an obturator region identification unit 36, and a bone density measurement unit 37. Specifically, the control unit 3 functions as the image acquisition unit 31, the extracted image generation unit 32, the bone region supplementation unit 33, the partial image acquisition unit 34, the target image acquisition unit 35, the obturator region identification unit 36, and the bone density measurement unit 37 by executing a program. The image acquisition unit 31, the extracted image generation unit 32, the bone region supplementation unit 33, the partial image acquisition unit 34, the target image acquisition unit 35, the obturator region identification unit 36, and the bone density measurement unit 37 are functional blocks within the control unit 3 as software, and are configured to function based on command signals from the control unit 3 as hardware. The control unit 3 is, for example, a computer including a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like.

[0031] (Bone Density Measurement by the Control Department)

[0032] In the first embodiment, the control unit 3 performs the following operations on the X-ray image 10 (see FIG. 1 ) formed by the X-rays detected by the X-ray detection unit 2. Figure 2 ) to extract the bone region of the diagnostic target site. Specifically, the control unit 3 extracts the bone region of the diagnostic target site from the X-ray image 10 formed by two types of X-rays with different energies to measure the bone density of the diagnostic target site. Furthermore, the control unit 3 is configured to extract the region corresponding to the actual bone portion from the X-ray image 10, and based on the acquired X-ray image 10 and the extracted bone region, measure the bone density of the entire bone portion of the diagnostic target site included in the X-ray image 10 according to the pixel values ​​of the X-ray image 10.

[0033] like Figure 2 As shown, the image acquisition unit 31 (control unit 3) acquires an X-ray image 10 of the diagnostic target region of the subject 101, including the femur and pelvis, based on the X-rays detected by the X-ray detection unit 2. For example, the X-ray image 10 is an energy subtraction image obtained by calculating the difference between images acquired using two types of X-rays with different energies. The X-ray image 10 is generated based on X-rays emitted under conditions set by an examination operator, such as a physician or radiographer, such as the position of the subject 101 and the tube voltage of the X-ray source 1a.

[0034] like Figure 3 As shown, the extracted image generation unit 32 (control unit 3) generates an extracted image 11 obtained by extracting the bone region of the diagnostic target site from the X-ray image 10. Specifically, the extracted image generation unit 32 generates the extracted image 11 from the X-ray image 10 based on a learned model 110 generated by machine learning. For example, semantic segmentation based on deep learning is used as machine learning. The learned model 110 is generated by machine learning using multiple input teacher X-ray images 111 and multiple teacher output binary images 112. The multiple input teacher X-ray images 111 include X-ray images of the diagnostic target site including the femur and pelvis, and the multiple teacher output binary images 112 include binary images configured to correspond to each of the multiple input teacher X-ray images 111 so as to be able to distinguish between bone regions and background regions. In semantic segmentation based on deep learning, deep learning is used, for example, based on U-net. In addition, learning of the learned model 110 is performed by a learning device separate from the X-ray imaging device 100. Alternatively, FCN (Fully Convolutional Network) may be used as a learning method.

[0035] like Figure 4 As shown, extracted image 11 is a binary image configured to distinguish, from X-ray image 10, bone regions inferred as bones, and background regions inferred as other than bones, based on learned model 110. For example, in extracted image 11, pixels inferred as bone regions are represented by white, while pixels inferred as background regions are represented by black. In extracted image 11 generated based on learned model 110, the interior of the white bone regions contains multiple isolated black background regions. Similarly, the interior of the black background regions contains multiple isolated white bone regions.

[0036] In addition, the extracted image 11 includes an iliac wing region 11a and an obturator foramen region 11b. The iliac wing region 11a is a region corresponding to the iliac wing of the ilium, which is the head side of the pelvis of the subject 101. The bones of the ilium (iliac wing) of the pelvis are relatively thin, so sometimes a black hole is included in (inside) the white bone region in the extracted image 11. On the other hand, the obturator foramen region 11b is a region corresponding to the obturator foramen, which is the leg side of the pelvis of the subject 101. The obturator foramen is a physiological hole in the pelvis of the subject 101. The obturator foramen region 11b is actually a hole in the bone, so it becomes a black hole included in (inside) the white bone region in the extracted image 11. That is, sometimes a state is formed in which holes are included in (inside) the bone regions of both the portion corresponding to the iliac wing and the portion corresponding to the obturator foramen in the extracted image 11.

[0037] Supplementary information on the bone area

[0038] In the first embodiment, the bone region supplementation unit 33 (control unit 3) divides the region including the obturator region 11b from the extracted image 11 generated by the extracted image generation unit 32, thereby supplementing the foramen of the bone region including the iliac wing region 11a while distinguishing the obturator region 11b. Specifically, in the first embodiment, the bone region supplementation unit 33 is configured to: Figure 6 ) and the target image 12 acquired by the target image acquisition unit 35, thereby identifying the obturator region 11b in the partial image 14 and supplementing the holes in the bone region in the target image 12. Specifically, the bone region supplementing unit 33 is configured to identify the obturator region 11b in the partial image 14 and supplement the holes in the bone region in the target image 12 based on the obturator region 11b identified by the obturator region identification unit 36. Details of the acquisition of the partial image 14 and the identification of the obturator region 11b will be described later.

[0039] In the first embodiment, the target image acquisition unit 35 (control unit 3) acquires a target image 12 including at least the iliac wing region 11a separately from the partial image 14 from the extracted image 11 generated by the extracted image generation unit 32. Specifically, in the first embodiment, the target image acquisition unit 35 acquires a target image 12 including both the iliac wing region 11a and the obturator foramen region 11b from the extracted image 11. In other words, the target image acquisition unit 35 acquires the entire extracted image 11 as the target image 12. In other words, in the first embodiment, the target image acquisition unit 35 acquires the generated extracted image 11 and uses it directly as the target image 12. The target image 12 is acquired from the generated extracted image 11 to perform processing for supplementing (filling) holes in the bone region.

[0040] like Figure 5As shown, in the first embodiment, the bone region supplementation unit 33 (control unit 3) supplements the holes in the bone region 13 in the target image 12 (extracted image 11). Specifically, the bone region supplementation unit 33 extracts contours based on the pixel values ​​in the target image 12. For example, based on the pixel values ​​of the pixels constituting the image, the bone region supplementation unit 33 extracts pixels whose pixel values ​​differ from those of adjacent pixels as contours. Furthermore, the bone region supplementation unit 33 measures the area (number of pixels) of all the multiple (11) regions (regions 12a, 12b, ..., 12k) enclosed by the extracted contours. The bone region supplementation unit 33 identifies the region with the largest area (region 12a) from among the multiple regions (regions 12a to 12k) enclosed by the extracted contours in the target image 12 as the bone region 13. Furthermore, the bone region supplementation unit 33 supplements the holes within the bone region 13 by excluding (filling) the region (hole) included inside the identified bone region 13 (region 12a). Specifically, the identified bone region 13 is obtained as a region that does not include black dots or regions (holes) representing the background region.

[0041] Identification of closed cell areas

[0042] like Figure 6 As shown, in the first embodiment, the partial image acquisition unit 34 (control unit 3) acquires the partial image 14 including the obturator area 11b from the extracted image 11 separately from the object image 12 to divide the obturator area 11b corresponding to the obturator foramen of the pelvis of the subject 101 as a physiological hole.

[0043] In the first embodiment, the partial image acquisition unit 34 (control unit 3) is configured to acquire a partial image 14 from the extracted image 11, excluding the iliac wing region 11a, corresponding to the iliac wing of the ilium, the cranial portion of the pelvis of the subject 101, and including the obturator foramen region 11b, corresponding to the obturator foramen, the crus portion of the pelvis of the subject 101. When generating the extracted image 11 using the learned model 110, the ilium, the upper portion of the pelvis, is prone to including a black background region. Therefore, the partial image acquisition unit 34 acquires the portion excluding the iliac wing region 11a as the partial image 14.

[0044] Specifically, in the first embodiment, the partial image acquisition unit 34 (control unit 3) acquires a partial image 14 including a leg-side image by dividing the extracted image 11 into a head-side image including the iliac wing region 11a and a leg-side image including the obturator foramen region 11b at a predetermined ratio. For example, the partial image 14 is acquired by dividing the lower (leg-side) two-thirds of the substantially square extracted image 11 at a predetermined ratio. That is, the partial image acquisition unit 34 acquires the partial image 14 such that the ratio of the longitudinal length L1 of the extracted image 11 to the longitudinal length L2 of the partial image 14 is 3:2. Furthermore, the predetermined ratio (two-thirds) can be changed depending on the size of the extracted image 11 (X-ray image 10) and the position of the subject 101 within the extracted image 11 (X-ray image 10).

[0045] Furthermore, in the first embodiment, as Figure 7 As shown, the obturator region identification unit 36 ​​(control unit 3) identifies the obturator region 11b in the partial image 14. The obturator region identification unit 36 ​​extracts the contour of the partial image 14 and identifies the obturator region 11b by excluding, from the plurality of regions (regions 14b, 14c, ..., 14e) enclosed by the contour line, two layers of regions (regions 14d and 14e) enclosed by the contour line, which are the regions enclosed by the contour line inside the regions enclosed by the contour line. In addition, in the first embodiment, the obturator region identification unit 36 ​​is configured to identify, on the inner side of the contour line of the bone region in the partial image 14 (the contour line of region 14a), the largest region whose area is larger than a prescribed threshold value from among a plurality of regions (regions 14b to 14e) surrounded by the contour line as the obturator region 11b, wherein the prescribed threshold value is determined in a manner corresponding to the obturator foramen of the subject 101.

[0046] For example, similar to the supplementation process performed on the hole portion of the bone region 13 in the object image 12 by the bone region supplementation unit 33, the obturator region identification unit 36 ​​(control unit 3) extracts the contour line based on the pixel value in the partial image 14. Furthermore, the obturator region identification unit 36 ​​measures the area (number of pixels) of each of the multiple (5) regions (regions 14a to 14e) surrounded by the extracted contour line. The obturator region identification unit 36 ​​identifies the region with the largest area from all the measured regions (regions 14a to 14e) as the bone region in the partial image 14. For example, the obturator region identification unit 36 ​​obtains Figure 7 The area 14a is used as the bone area in the partial image 14.

[0047] Furthermore, the obturator region identification unit 36 ​​(control unit 3) excludes the region surrounded by two layers of the contour line from the regions surrounded by the contour line (regions 14b to 14e) inside the contour line of the bone region in the partial image 14 (the contour line of region 14a). Specifically, Figure 7 Regions 14b and 14c are regions directly (single layer) surrounded by the bone region (region 14a). Figure 7 Regions 14d and 14e are the inner regions of region 14c. That is, Figure 7 Regions 14d and 14e are located inside the outline of the bone region (region 14a) and are further enclosed inside region 14c, forming a double-enclosed region between regions 14a and 14c. Thus, the obturator region identification unit 36 ​​excludes the double-enclosed region (regions 14d and 14e) from the plurality of regions (regions 14b to 14e) inside the outline of the bone region (region 14a).

[0048] Furthermore, the obturator region identification unit 36 ​​(control unit 3) excludes the region surrounded by two layers (regions 14d and 14e) and identifies the largest region with an area larger than a predetermined threshold value from the regions not excluded (regions 14b and 14c) surrounded by the bone region (region 14a), as the obturator region 11b. The predetermined threshold value is, for example, 1000 pixels. Furthermore, the captured X-ray image 10 is, for example, a square with one side approximately 500 pixels. That is, the partial image 14 is approximately a rectangle with a length of 330 pixels and a width of 500 pixels. Furthermore, the predetermined threshold value can be, for example, a predetermined ratio such as 1% of the area of ​​the partial image 14.

[0049] By performing the above-mentioned processing, the closed cell region identification unit 36 ​​(control unit 3) can Figure 7 The region 14c is identified as the closed cell region 11b from among the plurality of regions 14a to 14e in the partial image 14.

[0050] <Regarding the Generation of Recognition Result Images and the Measurement of Bone Density>

[0051] like Figure 8As shown, in the first embodiment, the bone region supplementation unit 33 (control unit 3) generates a recognition result image 15 based on the obturator foramen region 11b included in the partial image 14 and the bone region 13 supplemented with foramen. This recognition result image 15 represents the region corresponding to the actual bone portion of the diagnostic target site, including the femur and pelvis. Specifically, the bone region supplementation unit 33 excludes the obturator foramen region 11b identified by the obturator foramen region identification unit 36 ​​from the bone region 13 supplemented with foramen, thereby generating the recognition result image 15. In other words, by generating the recognition result image 15, the bone region supplementation unit 33 identifies the obturator foramen region 11b while supplementing the foramen in the bone region. Furthermore, in the recognition result image 15, the region corresponding to the actual bone portion of the diagnostic target site of the subject 101 is shown in white, while the background region, representing soft tissue other than bone, is shown in black. Specifically, recognition result image 15 is an image obtained by removing the obturator foramen 11b from extracted image 11, excluding isolated black dots and regions (foramen) within the white bone region, and excluding isolated white dots and regions within the black background region. In other words, recognition result image 15 is an image obtained by extracting (recognizing) the region corresponding to the actual bone while distinguishing (recognizing) the obturator foramen of the pelvis from extracted image 11.

[0052] In addition, if Figure 9 As shown, in a case where the extracted image 11 includes, for example, an area 11c corresponding to the hand of the subject 101, the image processing performed by the control unit 3 of the first embodiment can also be used to obtain an image, i.e., a recognition result image 15, which is obtained by extracting (identifying) the area corresponding to the actual bone part (including the femur and the diagnostic object part of the pelvis) while identifying the obturator foramen of the pelvis from the extracted image 11.

[0053] Then, the bone density measuring unit 37 of the control unit 3 measures the bone density of the diagnostic target area of ​​the subject 101 based on the X-ray image 10 and the recognition result image 15. For example, the bone density measuring unit 37 determines the area in the X-ray image 10 corresponding to the actual bone of the subject 101 based on the recognition result image 15, and measures the pixel values ​​of the X-ray image 10, thereby measuring the bone density of the entire diagnostic target area of ​​the subject 101, including the femur and pelvis.

[0054] (Regarding the Image Processing Method of the First Embodiment)

[0055] Next, refer to Figure 10 The control flow related to the image processing method performed by the X-ray imaging apparatus 100 according to the first embodiment will be described. Steps 301 to 309 represent control processing performed by the control unit 3 .

[0056] First, in step 301, X-rays are irradiated to the diagnostic target site including the femur and pelvis of the subject 101. Specifically, two types of X-rays having different energies are irradiated to the diagnostic target site.

[0057] Next, in step 302, the emitted X-rays are detected.

[0058] Next, in step 303, an extracted image 11 is generated by extracting the bone region of the diagnostic target site from the X-ray image 10 formed by the detected X-rays. Specifically, the extracted image 11 is generated from the X-ray image 10 based on the learned model 110 generated through machine learning. The process then proceeds to steps 304 and 306.

[0059] In step 304, a target image 12 including at least the iliac wing region 11a corresponding to the iliac wing of the ilium of the pelvis of the subject 101 is acquired from the generated extraction image 11. Specifically, the target image 12 including both the obturator foramen region 11b and the iliac wing region 11a is acquired.

[0060] Next, in step 305, the holes in the bone region 13 in the acquired target image 12 are supplemented. Specifically, a contour is extracted based on the pixel values ​​in the target image 12. Furthermore, the largest region (region 12a) is identified as the bone region 13 from among the multiple regions (regions 12a to 12k) enclosed by the extracted contour, thereby supplementing the holes in the identified bone region 13 in the target image 12. The process then proceeds to step 308.

[0061] In step 306, a partial image 14 including the obturator foramen region 11b is acquired separately from the target image 12 from the extracted image 11. This acquisition is performed by dividing the region including the obturator foramen region 11b, which corresponds to the obturator foramen, a physiological orifice of the pelvis of the subject 101. Specifically, the partial image 14 is acquired while excluding the iliac wing region 11a, which corresponds to the iliac wing of the ilium, a portion of the pelvis of the subject 101 on the head side, and including the obturator foramen region 11b, which corresponds to the obturator foramen, a portion of the pelvis of the subject 101 on the leg side. For example, the partial image 14 is acquired by dividing the extracted image 11 at a predetermined ratio (two-thirds) into a head-side image including the iliac wing region 11a and a leg-side image including the obturator foramen region 11b. The partial image 14 consists of the leg-side image including the obturator foramen region 11b.

[0062] Next, in step 307, the obturator region 11b included in the acquired partial image 14 is identified. Specifically, a contour line is extracted based on the pixel values ​​in the partial image 14. Furthermore, the region with the largest area (region 14a) is obtained from the multiple regions (regions 14a to 14e) surrounded by the extracted contour line as the bone region in the partial image 14. Furthermore, within the contour line of the bone region (region 14a) in the partial image 14, the region 14c, which is the largest region with an area larger than a predetermined threshold value, is identified as the obturator region 11b by excluding the regions (regions 14d and 14e) surrounded by the contour line in two layers from the multiple regions (regions 14b to 14e) surrounded by the contour line. The predetermined threshold value is determined in a manner corresponding to the obturator of the subject 101. Then, the process proceeds to step 308.

[0063] In step 308, a recognition result image 15 is generated based on the obturator foramen region 11b and the bone region 13 supplemented with holes included in the partial image 14. This recognition result image 15 represents the region corresponding to the actual bone portion of the diagnostic target site, including the femur and pelvis. Specifically, the partial image 14 is obtained from the extracted image 11 by segmenting the region including the obturator foramen region 11b. This generates the recognition result image 15 by distinguishing the obturator foramen region 11b based on the identified obturator foramen region 11b in the partial image 14 while compensating for holes in the bone region.

[0064] Next, in step 309 , the bone density of the diagnostic target site including the femur and pelvis of the subject 101 is measured based on the generated recognition result image 15 and the X-ray image 10 .

[0065] [Effects of the First Embodiment]

[0066] In the first embodiment, the following effects can be obtained.

[0067] In the X-ray imaging apparatus 100 of the first embodiment, as described above, the region including the obturator foramen 11b is segmented from the generated extracted image 11. This allows for the identification of the obturator foramen 11b while supplementing the holes in the bone region 13, including the iliac wing region 11a. The obturator foramen 11b corresponds to the obturator foramen, a physiological orifice in the pelvis of the subject 101, while the iliac wing region 11a corresponds to the iliac wing of the ilium in the pelvis of the subject 101. By segmenting the region including the obturator foramen 11b from the extracted image 11, isolated points and regions (holes) in the bone outside the obturator foramen 11b can be distinguished from the obturator foramen 11b. Consequently, the holes in the bone region 13 to be supplemented can be supplemented, including the iliac wing region 11a, where holes are more likely to occur due to the thinness of the bone, while distinguishing the holes in the bone region 13 to be supplemented from the obturator foramen 11b. As a result, the region corresponding to the actual bone can be accurately extracted while the obturator foramen 11b is identified.

[0068] In addition, in the first embodiment, by configuring as follows, further effects as described below can be obtained.

[0069] Specifically, in the first embodiment, the control unit 3 (image processing unit) further includes a partial image acquisition unit 34 that acquires a partial image 14 including the obturator foramen 11b from the extracted image 11 by segmenting the region including the obturator foramen 11b; and a target image acquisition unit 35 that acquires the target image 12 including at least the iliac wing region 11a separately from the partial image 14. The bone region supplementation unit 33 (control unit 3) is configured to supplement the foramen of the bone region 13 in the target image 12 while identifying the obturator foramen 11b in the partial image 14 based on the partial image 14 acquired by the partial image acquisition unit 34 and the target image 12 acquired by the target image acquisition unit 35. With this configuration, the region including the obturator foramen 11b can be easily segmented from the extracted image 11 based on the partial image 14 including the obturator foramen 11b. Furthermore, since target image 12, which includes at least iliac wing region 11a, is acquired from extracted image 11, the holes in bone region 13 in target image 12 can be easily supplemented, including iliac wing region 11a, where holes are likely to form due to thin bones. As a result, holes in bone region 13 in target image 12 can be easily supplemented while easily identifying obturator foramen region 11b in partial image 14.

[0070] Furthermore, in the first embodiment, as described above, the partial image acquisition unit 34 (control unit 3) is configured to acquire a partial image 14 from the extracted image 11 in a manner that excludes the iliac wing region 11a, which corresponds to the iliac wing of the ilium, the cranial portion of the pelvis of the subject 101, and includes the obturator foramen region 11b, which corresponds to the obturator foramen, the crus portion of the pelvis of the subject 101. The portion of the iliac wing region 11a corresponding to the iliac wing of the ilium is a relatively thin bone region, and therefore, isolated points and regions (holes) are likely to appear in the bone region of the extracted image 11. Consequently, the holes included in the bone region, generated by the image processing used to generate the extracted image 11, make it difficult to identify the obturator foramen that actually exists in the pelvis. In contrast, in the first embodiment, the partial image acquisition unit 34 is configured to acquire a partial image 14 from the extracted image 11, excluding the iliac wing region 11a, corresponding to the iliac wing of the ilium, which is the cranial portion of the pelvis of the subject 101, and including the obturator foramen region 11b, corresponding to the obturator foramen, which is the crus-side portion of the pelvis of the subject 101. With this configuration, the acquired partial image 14 does not include the iliac wing region 11a, allowing accurate discrimination between the obturator foramen region 11b and the foramen included in the iliac wing region 11a in the partial image 14. Therefore, by generating the partial image 14 without including the iliac wing region 11a, it is possible to more accurately extract the region corresponding to the actual bone.

[0071] Furthermore, in the first embodiment, as described above, the partial image acquisition unit 34 (control unit 3) is configured to acquire a partial image 14 consisting of the leg image including the obturator foramen 11b by dividing the extracted image 11 at a predetermined ratio into a head image including the iliac wing region 11a and a leg image including the obturator foramen 11b. With this configuration, by dividing the extracted image 11 at the predetermined ratio, the partial image 14 can be generated without including the iliac wing region 11a and including the obturator foramen 11b. Therefore, complex computational processing is not required to generate the partial image 14, making it easier to generate the partial image 14. Consequently, the burden of the control processing required to identify the obturator foramen 11b can be minimized.

[0072] Furthermore, in the first embodiment, as described above, the bone region supplementation unit 33 (control unit 3) is configured to extract the contour of the target image 12 and identify the largest region (region 12a) as the bone region 13 from among the multiple regions (regions 12a to 12k) enclosed by the extracted contour in the target image 12, thereby supplementing the holes in the bone region 13 in the target image 12. With this configuration, by identifying the largest region (region 12a) as the bone region 13, the bone region 13, including the femur and pelvis, can be easily identified. Therefore, even if the size and shape of the pelvis and femur vary depending on the subject 101, the bone region 13 can be easily identified by selecting the largest region (region 12a) as the bone region 13. Consequently, even if the size and shape of the pelvis and femur vary depending on the subject 101, the holes in the bone region 13 can be easily supplemented. In addition, even if the background area outside the bone area 13 includes small noise that is determined to be a bone area or the hand of the subject 101, etc., by obtaining the area with the largest area (area 12a) as the bone area 13, it is possible to easily exclude noise that is further outside the bone area 13 (area 12a).

[0073] Furthermore, in the first embodiment, as described above, the control unit 3 (image processing unit) includes the obturator region identification unit 36, which identifies the obturator region 11b in the partial image 14. The obturator region identification unit 36 ​​(control unit 3) is configured to extract the contour of the partial image 14 and, within the contour of the bone region (region 14a) in the partial image 14, identify the region with the largest area from among the multiple regions (regions 14b to 14e) surrounded by the contour as the obturator region 11b. The bone region supplementation unit 33 (control unit 3) is configured to supplement the pores of the bone region 13 in the target image 12 while distinguishing the obturator region 11b in the partial image 14 based on the obturator region 11b identified by the obturator region identification unit 36. With this configuration, the obturator region 11b can be easily identified by identifying the region with the largest area within the contour of the bone region (region 14a) in the partial image 14. Therefore, even when the size and shape of the obturator region 11b in the extracted image 11 vary, the obturator region 11b can be easily identified. Furthermore, a doctor or other inspector can automatically identify the obturator region 11b while visually checking the extracted image 11, without having to select an area corresponding to the obturator region 11b. This reduces the burden on the inspector to identify the obturator region 11b.

[0074] Furthermore, in the first embodiment, as described above, the obturator region identification unit 36 ​​(control unit 3) is configured to extract the contour of the partial image 14 and, within the contour of the bone region (region 14a) in the partial image 14, identify, from among the multiple regions (14b to 14e) enclosed by the contour, a region whose area exceeds a predetermined threshold value, as the obturator region 11b. The predetermined threshold value is determined to correspond to the obturator of the subject 101. This configuration allows regions with an area greater than the predetermined threshold value to be identified as the obturator region 11b, thereby preventing regions smaller than the predetermined threshold from being identified as the obturator region 11b. Consequently, it is possible to prevent excessively small regions from being identified as the obturator region 11b, thereby enabling high-precision identification of the obturator region 11b in the partial image 14.

[0075] Furthermore, in the first embodiment, as described above, the obturator region identification unit 36 ​​(control unit 3) is configured to extract the contour of the partial image 14 and identify the obturator region 11b within the contour of the bone region (region 14a) in the partial image 14 by excluding the two-layered regions (regions 14d and 14e) surrounded by the contour from the plurality of regions (regions 14b to 14e) surrounded by the contour. The two-layered regions (regions 14d and 14e) are regions surrounded by the contour within the region surrounded by the contour. Here, the obturator foramen of the pelvis is extracted from the extracted image 11 as a background region included in the bone region. In contrast, in the first embodiment, the obturator region identifying unit 36 ​​is configured to identify the obturator region 11b within the contour of the bone region (region 14a) in the partial image 14 by excluding two regions (regions 14d and 14e) surrounded by the contour from the multiple regions (regions 14b to 14e) surrounded by the contour. These regions (regions 14d and 14e) are the regions within the contour. This configuration eliminates the two regions (regions 14d and 14e) surrounded by the contour, thereby preventing bone regions included in the background region within the bone region (region 14a) from being identified as the obturator region 11b. This prevents regions that do not correspond to the obturator region from being identified as the obturator region 11b, allowing regions corresponding to the obturator region to be identified as the obturator region 11b with greater accuracy.

[0076] Furthermore, in the first embodiment, as described above, the target image acquisition unit 35 (control unit 3) is configured to acquire a target image 12 that includes both the obturator foramen 11b and the iliac wing region 11a. This configuration allows for the supplementation of holes in the region encompassing both the obturator foramen 11b and the iliac wing region 11a. Therefore, not only holes in the iliac wing region 11a can be supplemented, but also holes near the obturator foramen 11b. As a result, even when holes exist near the obturator foramen 11b, the bone region supplementation unit 33 (control unit 3) can accurately supplement the holes in the bone region. Furthermore, the phrase "near the obturator foramen 11b" herein refers to both the obturator foramen 11b itself and the vicinity of the location of the obturator foramen 11b.

[0077] Furthermore, in the first embodiment, as described above, the extracted image generator 32 (control unit 3) is configured to generate an extracted image 11 obtained by extracting the bone region of the diagnostic target site from the X-ray image 10 based on the learned model 110 generated through machine learning. The bone region supplementation unit 33 (control unit 3) is configured to supplement the holes in the bone region 13 by extracting contours based on pixel values ​​in the target image 12. With this configuration, when generating the extracted image 11 from the X-ray image 10, the learned model 110 generated through machine learning is used, thereby enabling the generation of an extracted image 11 that distinguishes between bone and background with greater accuracy. Furthermore, since the bone region supplementation unit 33 is configured to supplement the holes in the bone region 13 by extracting contours based on pixel values, supplementation can be performed without previously performing machine learning to generate the learned model. Therefore, supplementation of the holes in the bone region 13 can be performed using an algorithm based on a rule base, thereby reducing the effort required to prepare for learning the learned model.

[0078] Furthermore, in the first embodiment, as described above, the X-ray irradiation unit 1 is configured to irradiate the diagnostic target site with two types of X-rays having different energies, and the control unit 3 (image processing unit) is configured to extract the bone region of the diagnostic target site from the X-ray image 10 formed by the two types of X-rays having different energies, thereby measuring the bone density of the bone region of the diagnostic target site. With this configuration, even when extracting the bone region 13 from the X-ray image 10 formed by the two types of X-rays having different energies to measure bone density, the control unit 3 can automatically perform the process of extracting the bone region 13. Therefore, unlike when manually extracting the bone region 13, the workload of the examination operator, such as a physician, for extracting the bone region 13 can be reduced.

[0079] [Effects of the Image Processing Method of the First Embodiment]

[0080] The image processing method of the X-ray imaging apparatus 100 according to the first embodiment can provide the following effects.

[0081] In the image processing method of the first embodiment, as configured above, a region including the obturator foramen 11b is segmented from the generated extracted image 11. This allows for identification of the obturator foramen 11b, a region corresponding to the obturator foramen, a physiological orifice in the pelvis of the subject 101, while supplementing holes in the bone region 13 including the iliac wing region 11a. The obturator foramen 11b corresponds to the obturator foramen, a physiological orifice in the pelvis of the subject 101, while the iliac wing region 11a corresponds to the iliac wing of the ilium in the pelvis of the subject 101. By segmenting the region including the obturator foramen 11b from the extracted image 11, isolated points and regions (holes) in the bone outside the obturator foramen 11b can be identified relative to the obturator foramen 11b. Consequently, holes in the bone region 13 to be supplemented, including the iliac wing region 11a, where holes are more likely to form due to the thinness of the bone, can be supplemented while distinguishing the holes in the bone region 13 to be supplemented from the obturator foramen 11b. As a result, it is possible to provide an image processing method capable of accurately extracting a region corresponding to an actual bone part while distinguishing the obturator foramen of the pelvis.

[0082] [Second embodiment]

[0083] Next, refer to Figures 11-13 The structure of an X-ray imaging apparatus 200 according to a second embodiment of the present invention will be described. Unlike the first embodiment, which acquires a target image 12 including both the iliac wing region 11a and the obturator foramen region 11b, this second embodiment acquires a target image 212 including the iliac wing region 11a without including the obturator foramen 11b.

[0084] like Figure 11 As shown, the X-ray imaging device 200 of the second embodiment includes a control unit 203. Similar to the control unit 3 of the first embodiment, the control unit 203 is, for example, a computer including a CPU, a GPU, a ROM, and a RAM. In addition, the control unit 203 includes a bone region supplement unit 233 and an object image acquisition unit 235 as functional structures. That is, the control unit 203 functions as the bone region supplement unit 233 and the object image acquisition unit 235 by executing a program. In addition, the bone region supplement unit 233 and the object image acquisition unit 235 are functional blocks as software, and are configured to function based on a command signal from the control unit 203 as hardware. In addition, the other structures of the control unit 203 are the same as those of the control unit 3 of the first embodiment. In addition, the control unit 203 is an example of an "image processing unit" in the claims.

[0085] like Figure 12As shown, in the second embodiment, the target image acquisition unit 235 (control unit 203) is configured to acquire a target image 212 that excludes the obturator foramen 11b and includes the iliac wing region 11a. Specifically, the target image acquisition unit 235 segments the upper (head) third of the extracted image 11 to acquire the target image 212. In other words, the X-ray imaging apparatus 200 of the second embodiment is configured to segment the extracted image 11 into the upper (head) and lower (leg) portions at a 1:2 ratio, thereby acquiring the upper (head) portion as the target image 212 and the lower (leg) portion as the partial image 14.

[0086] Moreover, if Figure 13 As shown, the bone region supplementation unit 233 (control unit 203) performs the same processing as in the first embodiment on the acquired target image 212, thereby supplementing the holes in the bone region 213 in the target image 212. Specifically, as in the first embodiment, the bone region supplementation unit 233 extracts the contour of the target image 212 and identifies the largest region among the multiple regions (regions 212a, 212b, ..., 212g) enclosed by the extracted contour as the bone region 213, thereby supplementing the holes within the bone region 213. Furthermore, as in the first embodiment, the partial image 14 is acquired by the partial image acquisition unit 34.

[0087] Furthermore, the bone region supplementation unit 233 (control unit 203) generates a recognition result image 215 based on the obturator region 11b included in the partial image 14 and the bone region 213 supplemented with the hole by the bone region supplementation unit 233. This recognition result image 215 represents the region corresponding to the actual bone portion of the diagnostic target site, including the femur and pelvis. Specifically, the bone region supplementation unit 233 generates the recognition result image 215 by combining the target image 212 supplemented with the hole with the bone region 213 and the partial image 14 acquired by the partial image acquisition unit 34. In other words, the recognition result image 215 is an image in which the hole portion of the region corresponding to the target image 212 in the extracted image 11 has been supplemented, while the hole portion of the region corresponding to the partial image 14 in the extracted image 11 has not been supplemented. Alternatively, the partial image acquisition unit 34 may acquire the entire extracted image 11 as a partial image and superimpose the object image 212 of the hole portion supplemented with the bone region 213 on the entire extracted image 11 , i.e., the partial image, to generate the recognition result image 215 .

[0088] In this way, in the second embodiment, the bone area supplementation unit 233 (control unit 203) is configured to synthesize the partial image 14 acquired in a manner including the obturator area 11b with the object image 212 supplemented with the hole portion, thereby dividing the area including the obturator area 11b from the extracted image 11 while supplementing the hole portion of the bone area 213 including the iliac wing area 11a.

[0089] The other structures of the second embodiment are the same as those of the first embodiment.

[0090] [Effects of the Second Embodiment]

[0091] In the second embodiment, the following effects can be obtained.

[0092] In the second embodiment, as described above, the target image acquisition unit 235 (control unit 203) is configured to acquire a target image 212 that excludes the obturator foramen 11b and includes the iliac wing region 11a. With this configuration, the target image acquisition unit 235 acquires the target image 212 without the obturator foramen 11b. Therefore, by supplementing all the foramina included in the target image 212, it is possible to easily supplement the foramina that are not included while identifying the obturator foramen 11b. Therefore, it is possible to easily suppress the supplementation (filling) of the obturator foramen 11b that corresponds to an obturator foramen that is a foramen that actually exists in the bone of the human body. As a result, it is possible to accurately supplement the foramina in the bone region 13 in the extracted image 11 while identifying the obturator foramen that corresponds to the actual bone. Other effects of the second embodiment are the same as those of the first embodiment.

[0093] [Modification]

[0094] The embodiments disclosed herein are to be considered in all respects as illustrative and non-restrictive. The scope of the present invention is not indicated by the description of the embodiments described above, but by the claims, and includes all modifications (variations) within the meaning and scope equivalent to the claims.

[0095] For example, in the first and second embodiments described above, the bone region supplementation units 33 and 233 (control units 3 and 203) are configured to supplement the pore portion of the bone region 13 (213) in the target image 12 (212) while identifying the obturator region 11b in the partial image 14 based on the partial image 14 acquired by the partial image acquisition unit 34 and the target image 12 (212) acquired by the target image acquisition unit 35 (235). However, the present invention is not limited to this. For example, a configuration may be employed in which the region including the obturator region is acquired by specifying coordinates in the extracted image without acquiring an image.

[0096] Furthermore, in the first and second embodiments described above, the partial image acquisition unit 34 (control unit 3, 203) acquires the partial image 14 from the extracted image 11 so as to exclude the iliac wing region 11a and include the obturator foramen region 11b. However, the present invention is not limited to this. For example, the obturator foramen region identification unit may also be configured to acquire the partial image so as to include the iliac wing region. In other words, the partial image may be acquired so as to include at least the obturator foramen region.

[0097] In addition, in the first and second embodiments described above, the partial image acquisition unit 34 (control unit 3, 203) acquires the partial image 14 by segmenting the extracted image 11 at a predetermined ratio. However, the present invention is not limited to this. For example, the extracted image may be segmented based on specific predetermined numerical values ​​(pixel values) rather than at a predetermined ratio to acquire the partial image. Alternatively, the partial image may be acquired by segmenting the extracted image not only in the vertical direction but also in the horizontal direction. Alternatively, the partial image may be generated by extracting a predetermined region from the extracted image.

[0098] In the first and second embodiments described above, the bone region supplementation units 33 and 233 (control units 3 and 203) are configured to identify the region with the largest area from among the multiple regions surrounded by the extracted contour lines of the target image 12 (212) as the bone region 13 (213). However, the present invention is not limited to this. For example, a configuration may be employed in which regions with an area greater than a predetermined threshold value are synthesized to identify the region as a bone region.

[0099] Furthermore, in the first embodiment described above, the obturator region identification unit 36 ​​(control unit 3) identifies, within the contour of the bone region in the partial image 14, the largest region whose area exceeds a predetermined threshold value from among the multiple regions enclosed by the contour line, as the obturator region 11b. The predetermined threshold value is determined to correspond to the obturator foramen of the subject 101. However, the present invention is not limited to this. For example, the predetermined threshold value may be omitted, and the largest region may be identified as the obturator region. Alternatively, instead of the largest region, regions with an area greater than the predetermined threshold value may be identified as the obturator region.

[0100] Furthermore, in the first embodiment described above, an example is shown in which the obturator region identifying unit 36 ​​(control unit 3) is configured to identify the obturator region 11b within the contour of the bone region in the partial image 14 by excluding the region enclosed twice by the contour from the plurality of regions enclosed by the contour. However, the present invention is not limited to this. For example, the region enclosed twice by the contour need not be excluded. In other words, the obturator region may be identified from a plurality of regions including the region enclosed twice by the contour.

[0101] Furthermore, in the first and second embodiments described above, an example is shown in which the extracted image generator 32 (control unit 3, 203) generates an extracted image 11 by extracting the bone region of the diagnostic target site from the X-ray image 10 based on the learned model 110 generated by machine learning. However, the present invention is not limited to this. For example, an extracted image may be generated from an X-ray image based on an algorithm generated by a rule base.

[0102] Furthermore, in the first and second embodiments described above, the control units 3 and 203 (image processing unit) are configured to extract the bone region of the diagnostic target site from the X-ray image 10 formed using two types of X-rays with different energies to measure the bone density of the bone region of the diagnostic target site. However, the present invention is not limited to this. For example, the control unit 3 and 203 (image processing unit) may also extract the bone region of the diagnostic target site from the X-ray image formed using a single type of X-ray.

[0103] In the first and second embodiments described above, the control unit 3, 203 (image processing unit) is illustrated as a computer including a CPU, GPU, RAM, and ROM. However, the present invention is not limited to this. For example, the control unit (image processing unit) may include an FPGA (Field-Programmable Gate Array) configured for image processing.

[0104] Furthermore, in the first embodiment described above, the image acquisition unit 31, the extracted image generation unit 32, the bone region supplementation unit 33, the partial image acquisition unit 34, the target image acquisition unit 35, the obturator region identification unit 36, and the bone density measurement unit 37 are shown as functional components (software) of the control unit 3 (image processing unit). However, the present invention is not limited to this. For example, the image acquisition unit, the extracted image generation unit, the bone region supplementation unit, the partial image acquisition unit, the target image acquisition unit, the obturator region identification unit, and the bone density measurement unit may each be implemented as a separate component (e.g., hardware such as a GPU or FPGA).

[0105] Furthermore, in the first embodiment described above, the image acquisition unit 31, the extracted image generation unit 32, the bone region supplementation unit 33, the partial image acquisition unit 34, the target image acquisition unit 35, the obturator region identification unit 36, and the bone density measurement unit 37 are shown as a functional configuration of a single (shared) control unit 3 (image processing unit). However, the present invention is not limited to this. For example, the image acquisition unit, the extracted image generation unit, the bone region supplementation unit, the partial image acquisition unit, the target image acquisition unit, the obturator region identification unit, and the bone density measurement unit may each be a functional configuration of a separate control unit (CPU).

[0106] [Way]

[0107] It should be understood by those skilled in the art that the above-described exemplary embodiments are specific examples of the following aspects.

[0108] (Item 1)

[0109] An X-ray imaging device comprising:

[0110] an X-ray irradiation unit for irradiating X-rays toward a diagnosis target portion of the subject including the femur and pelvis;

[0111] an X-ray detection unit that detects the X-rays emitted from the X-ray irradiation unit; and

[0112] an image processing unit that extracts a bone region of the diagnosis target site from an X-ray image formed by the X-rays detected by the X-ray detection unit;

[0113] Wherein, the image processing unit includes:

[0114] an extracted image generating unit configured to generate an extracted image by extracting the bone region of the diagnosis target site from the X-ray image; and

[0115] A bone region supplementing unit divides an area including an obturator foramen area from the extracted image generated by the extracted image generating unit, thereby distinguishing the obturator foramen area while supplementing the hole portion of the bone region including an iliac wing area, wherein the obturator foramen area is an area corresponding to the obturator foramen as a physiological hole in the pelvis of the subject, and the iliac wing area is an area corresponding to the iliac wing of the ilium of the pelvis of the subject.

[0116] (Item 2)

[0117] In the X-ray imaging apparatus described in item 1,

[0118] The image processing unit further includes: a partial image acquisition unit that acquires a partial image including the obturator region by dividing the extracted image into a region including the obturator region; and a subject image acquisition unit that acquires a subject image including at least the iliac wing region separately from the partial image.

[0119] The bone region supplementing unit is configured to supplement the hole portion of the bone region in the target image while identifying the obturator region in the partial image based on the partial image acquired by the partial image acquisition unit and the target image acquired by the target image acquisition unit.

[0120] (Item 3)

[0121] In the X-ray imaging apparatus described in item 2,

[0122] The partial image acquisition unit is configured to acquire the partial image from the extracted image in a manner that does not include the iliac wing area and includes the obturator foramen area, wherein the iliac wing area is an area corresponding to the iliac wing of the ilium, which is a head side part of the pelvis of the subject, and the obturator foramen area is an area corresponding to the obturator foramen, which is a leg side part of the pelvis of the subject.

[0123] (Item 4)

[0124] In the X-ray imaging apparatus described in item 2 or 3,

[0125] The partial image acquisition unit is configured to acquire the partial image by dividing the extracted image into a head side image including the iliac wing region and a leg side image including the obturator region at a predetermined ratio, the partial image being composed of the leg side image including the obturator region.

[0126] (Item 5)

[0127] In the X-ray imaging device described in any one of items 2 to 4,

[0128] The bone region supplementing unit is configured to extract a contour line of the target image and identify the largest region as the bone region from among a plurality of regions of the target image surrounded by the extracted contour line, thereby supplementing the hole portion of the bone region in the target image.

[0129] (Item 6)

[0130] In the X-ray imaging device described in any one of items 2 to 5,

[0131] The image processing unit includes a closed pore region identifying unit configured to identify the closed pore region in the partial image.

[0132] The obturator region identifying unit is configured to extract the contour line of the partial image, identify the region with the largest area from among a plurality of regions surrounded by the contour line inside the contour line of the bone region in the partial image as the obturator region,

[0133] The bone region supplementing unit is configured to supplement the hole portion of the bone region in the target image while identifying the obturator region in the partial image based on the obturator region identified by the obturator region identifying unit.

[0134] (Item 7)

[0135] In the X-ray imaging apparatus described in item 6,

[0136] The obturator region identification unit is configured to extract the contour line of the partial image, and identify, inside the contour line of the bone region in the partial image, an area whose area is larger than a prescribed threshold value from a plurality of regions surrounded by the contour line as the obturator region, wherein the prescribed threshold value is determined in a manner corresponding to the obturator foramen of the subject.

[0137] (Item 8)

[0138] In the X-ray imaging apparatus described in item 6 or 7,

[0139] The obturator region identification unit is configured to extract the contour line of the partial image, and identify the obturator region by excluding the region surrounded by the contour line in two layers from the multiple regions surrounded by the contour line on the inner side of the contour line of the bone region in the partial image, wherein the region surrounded by the contour line in two layers is the region surrounded by the contour line inside the region surrounded by the contour line.

[0140] (Item 9)

[0141] In the X-ray imaging device described in any one of items 2 to 8,

[0142] The target image acquisition unit is configured to acquire the target image including both the obturator foramen region and the iliac wing region.

[0143] (Item 10)

[0144] In the X-ray imaging device described in any one of items 2 to 8,

[0145] The target image acquisition unit is configured to acquire the target image excluding the obturator foramen region and including the iliac wing region.

[0146] (Item 11)

[0147] In the X-ray imaging device described in any one of items 2 to 10,

[0148] The extracted image generating unit is configured to generate the extracted image by extracting the bone region of the diagnostic target site from the X-ray image based on a learned model generated by machine learning.

[0149] The bone region supplementing unit is configured to extract a contour line based on pixel values ​​in the target image, thereby supplementing the hole portion in the bone region.

[0150] (Item 12)

[0151] In the X-ray imaging device described in any one of items 2 to 11,

[0152] The X-ray irradiation unit is configured to irradiate two types of X-rays with different energies toward the diagnosis target site.

[0153] The image processing unit is configured to perform processing for extracting the bone region of the diagnosis target site from the X-ray image formed by the two X-rays having different energies, thereby measuring the bone density of the bone portion of the diagnosis target site.

[0154] (Item 13)

[0155] An image processing method comprises the following steps:

[0156] irradiating X-rays to the subject's diagnostic area, including the femur and pelvis;

[0157] Detecting the emitted X-rays;

[0158] generating an extracted image obtained by extracting a bone region of the diagnosis target site from an X-ray image formed by the detected X-rays; and

[0159] An area including the obturator foramen is divided from the generated extracted image, thereby identifying the obturator foramen area while supplementing the hole portion of the bone area including the iliac wing area. The obturator foramen area is an area corresponding to the obturator foramen as a physiological hole in the pelvis of the subject, and the iliac wing area is an area corresponding to the iliac wing of the ilium of the pelvis of the subject.

Claims

1. An X-ray imaging device comprising: an X-ray irradiation unit for irradiating X-rays toward a diagnosis target portion of the subject including the femur and pelvis; an X-ray detection unit that detects the X-rays emitted from the X-ray irradiation unit; as well as an image processing unit that extracts a bone region of the diagnosis target site from an X-ray image formed by the X-rays detected by the X-ray detection unit; in, The image processing unit includes: an extracted image generating unit configured to generate an extracted image by extracting the bone region of the diagnosis target site from the X-ray image; as well as A bone region supplementing unit divides an area including an obturator foramen area from the extracted image generated by the extracted image generating unit, thereby distinguishing the obturator foramen area while supplementing the hole portion of the bone region including an iliac wing area, wherein the obturator foramen area is an area corresponding to the obturator foramen as a physiological hole in the pelvis of the subject, and the iliac wing area is an area corresponding to the iliac wing of the ilium of the pelvis of the subject.

2. The X-ray imaging device according to claim 1, wherein The image processing unit further includes: a partial image acquisition unit that acquires a partial image including the obturator region by dividing the extracted image into a region including the obturator region; and a subject image acquisition unit that acquires a subject image including at least the iliac wing region separately from the partial image. The bone region supplementing unit is configured to supplement the hole portion of the bone region in the target image while identifying the obturator region in the partial image based on the partial image acquired by the partial image acquisition unit and the target image acquired by the target image acquisition unit.

3. The X-ray imaging device according to claim 2, wherein: The partial image acquisition unit is configured to acquire the partial image from the extracted image in a manner that does not include the iliac wing area and includes the obturator foramen area, wherein the iliac wing area is an area corresponding to the iliac wing of the ilium, which is a head side part of the pelvis of the subject, and the obturator foramen area is an area corresponding to the obturator foramen, which is a leg side part of the pelvis of the subject.

4. The X-ray imaging device according to claim 2 or 3, characterized in that The partial image acquisition unit is configured to acquire the partial image by dividing the extracted image into a head side image including the iliac wing region and a leg side image including the obturator region at a predetermined ratio, the partial image being composed of the leg side image including the obturator region.

5. The X-ray imaging device according to claim 2 or 3, characterized in that The bone region supplementing unit is configured to extract a contour line of the target image and identify the largest region as the bone region from among a plurality of regions of the target image surrounded by the extracted contour line, thereby supplementing the hole portion of the bone region in the target image.

6. The X-ray imaging device according to claim 2 or 3, characterized in that The image processing unit includes a closed pore region identifying unit configured to identify the closed pore region in the partial image. The obturator region identifying unit is configured to extract the contour line of the partial image, identify the region with the largest area from among a plurality of regions surrounded by the contour line inside the contour line of the bone region in the partial image as the obturator region, The bone region supplementing unit is configured to supplement the hole portion of the bone region in the target image while identifying the obturator region in the partial image based on the obturator region identified by the obturator region identifying unit.

7. The X-ray imaging device according to claim 6, wherein The obturator region identification unit is configured to extract the contour line of the partial image, and identify an area having an area larger than a specified threshold from a plurality of areas surrounded by the contour line inside the contour line of the bone area in the partial image as the obturator region, wherein the specified threshold is determined in a manner corresponding to the obturator foramen of the subject.

8. The X-ray imaging device according to claim 6, wherein The obturator region identification unit is configured to extract the contour line of the partial image, and identify the obturator region by excluding the region surrounded by the contour line in two layers from the multiple regions surrounded by the contour line on the inner side of the contour line of the bone region in the partial image, wherein the region surrounded by the contour line in two layers is the region surrounded by the contour line inside the region surrounded by the contour line.

9. The X-ray imaging device according to claim 2 or 3, characterized in that The target image acquisition unit is configured to acquire the target image including both the obturator foramen region and the iliac wing region.

10. The X-ray imaging device according to claim 2 or 3, characterized in that The target image acquisition unit is configured to acquire the target image excluding the obturator foramen region and including the iliac wing region.

11. The X-ray imaging device according to claim 2 or 3, characterized in that The extracted image generating unit is configured to generate the extracted image by extracting the bone region of the diagnostic target site from the X-ray image based on a learned model generated by machine learning. The bone region supplementing unit is configured to extract a contour line based on pixel values ​​in the target image, thereby supplementing the hole portion in the bone region.

12. The X-ray imaging device according to claim 2 or 3, characterized in that The X-ray irradiation unit is configured to irradiate two types of X-rays with different energies toward the diagnosis target site. The image processing unit is configured to perform processing for extracting the bone region of the diagnosis target site from the X-ray image formed by the two X-rays having different energies, thereby measuring the bone density of the bone portion of the diagnosis target site.

13. An image processing method comprising the following steps: irradiating X-rays to the subject's diagnostic area, including the femur and pelvis; Detecting the emitted X-rays; generating an extracted image obtained by extracting a bone region of the diagnosis target site from an X-ray image formed by the detected X-rays; and An area including the obturator foramen is divided from the generated extracted image, thereby identifying the obturator foramen area while supplementing the hole portion of the bone area including the iliac wing area. The obturator foramen area is an area corresponding to the obturator foramen, a physiological hole in the pelvis of the subject, and the iliac wing area is an area corresponding to the iliac wing of the ilium of the pelvis of the subject.

Images