Information processing apparatus, method, and program product

Abstract

An information processing apparatus, method, and program product are provided. The present invention addresses the problem of appropriately detecting feature points when setting an imaging range in an information processing device, method, and program. The processor acquires a camera image generated by capturing a moving image of a subject on a bed by a camera, and selects one detection model from a plurality of detection models including a first detection model and a second detection model configured to detect a plurality of feature points on the subject included in the camera image. The first detection model pays attention to the frame rate at the time of detecting the feature points, the second detection model pays attention to the accuracy at the time of detecting the feature points, a plurality of feature points on the subject included in the camera image are detected by the selected detection model, and the imaging range of the subject is determined on the basis of the plurality of feature points.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, method, and program. Background Art

[0002] In recent years, due to the development of medical devices such as CT (Computed Tomography) devices and MRI (Magnetic Resonance Imaging) devices, higher-quality and higher-resolution three-dimensional images have been used in image diagnosis.

[0003] In imaging devices such as CT devices and MRI devices, when performing imaging of a subject, in order to determine the imaging range, positioning imaging is performed before the formal imaging for obtaining a three-dimensional image, thereby obtaining a two-dimensional positioning image (localization image). The operator (engineer, etc.) of the imaging device sets the imaging range at the time of formal imaging while observing the localization image.

[0004] Before the positioning imaging, the operator sets the imaging range of the positioning imaging of the subject on the examination table. For example, a cross-shaped laser is irradiated onto the subject, the scanning start position of the positioning imaging is set, and the scanning end position of the positioning imaging is set so as to be an imaging range corresponding to the imaging part. At the time of positioning imaging, when the examination table moves from the initial position of the examination table to the scanning start position, the scanning of the positioning imaging is started, and when the examination table moves to the scanning end position, the scanning of the positioning imaging is ended. After the operator sets the imaging range of the formal imaging based on the localization image obtained by the positioning imaging, the formal imaging is performed to obtain a three-dimensional image.

[0005] Here, when setting the imaging range at the time of positioning imaging, the subject is photographed by a camera provided above the examination table, feature points such as both ankles, both waists, both elbows, and both shoulders of the subject are detected, and the imaging range is determined based on the detected feature points. At this time, a learned detection model constructed by a machine learning neural network is used in the detection of the feature points.

[0006] On the other hand, a method has been proposed in which when applying a learned model to a medical image, a plurality of different learned models for performing different processes are prepared, and which learned model to use is selected according to the situation, thereby efficiently performing the processing of the medical image (for example, refer to Patent Document 1).

[0007] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2021-079013

[0008] As described above, when positioning the photographic range by photographing the subject with a camera, sometimes the subject moves on the examination couch. In particular, the head of the subject is likely to move. When detecting feature points from the image captured by the camera using a detection model, if the subject moves, it may not be possible to detect the feature points with high precision. Also, sometimes a blanket is placed over the subject for photographing, and in this case, since a part of the subject is covered, it may not be possible to detect the feature points. Summary of the Invention

[0009] The present invention has been made in view of the above circumstances, and an object thereof is to appropriately detect feature points when setting the photographic range.

[0010] The information processing apparatus according to the present invention includes at least one processor.

[0011] The processor performs the following processing:

[0012] Obtain a camera image generated by photographing a moving image of a subject on an examination couch with a camera;

[0013] Select one detection model from a plurality of detection models including a first detection model and a second detection model that are configured to detect a plurality of feature points on the subject included in the camera image. The first detection model focuses on the frame rate when detecting feature points, and the second detection model focuses on the accuracy when detecting feature points;

[0014] Detect a plurality of feature points on the subject included in the camera image by the selected detection model; and

[0015] Determine the photographic range of the subject based on the plurality of feature points.

[0016] In addition, in the information processing apparatus according to the present invention, the processor may select a detection model according to the photographic part of the subject.

[0017] Further, in the information processing apparatus according to the present invention, the processor may perform the following processing: determine the detection accuracy of the feature points, and when the detection accuracy is above a reference, determine the photographic range based on the feature points, and when the detection accuracy is lower than the reference, issue a warning.

[0018] Furthermore, in the information processing apparatus according to the present invention, the processor may perform the following processing: detect the movement of the subject from the camera image; and

[0019] When the movement of the subject is above a reference, determine the photographic range based on the feature points detected using the first detection model, and when the movement of the subject is less than the reference, determine the photographic range based on the feature points detected using the second detection model.

[0020] Also, in the information processing apparatus according to the present invention, the processor may select a first detection model to detect feature points from the camera image, and detect the movement of the subject based on the feature points.

[0021] Also, in the information processing apparatus according to the present invention, the processor may perform the following processing: determine the detection accuracy of the feature points, and if the detection accuracy is above a reference, determine the shooting range based on the feature points, and if the detection accuracy is lower than the reference, issue a warning.

[0022] Also, in the information processing apparatus according to the present invention, the processor may perform the following processing: select a first detection model to detect feature points from the camera image, and determine the detection accuracy of the feature points. If the detection accuracy is above a first reference, determine the shooting range based on the feature points detected using the first detection model. If the detection accuracy is lower than the first reference, select a second detection model and determine the shooting range based on the feature points detected using the second detection model.

[0023] Also, in the information processing apparatus according to the present invention, the processor may be a device that performs the following processing: determine the detection accuracy of the feature points detected using the second detection model. If the detection accuracy is above a second reference, determine the shooting range based on the feature points. If the detection accuracy is lower than the second reference, issue a warning.

[0024] Also, in the information processing apparatus according to the present invention, the processor may also derive the moving distance of the examination table based on the shooting range.

[0025] Also, in the information processing apparatus according to the present invention, the processor may perform the following processing: display a human body image simulating a human body on the display, and draw a shooting start line and a shooting end line based on the shooting range on the human body image.

[0026] Also, in the information processing apparatus according to the present invention, the shooting range may also be the shooting range when shooting a positioning image acquired before the formal shooting of the subject.

[0027] Also, in the information processing apparatus according to the present invention, the following features may be provided: the amount of computation of the first detection model is less than that of the second detection model, the processing speed for detecting feature points is faster than that of the second detection model, the amount of computation of the second detection model is more than that of the first detection model, the processing speed for detecting feature points is slower than that of the first detection model, but the detection accuracy is high.

[0028] In the information processing method according to the present invention, the computer performs the following processing:

[0029] Obtain a camera image generated by photographing a moving image of a subject on an examination table by a camera;

[0030] Select one detection model from multiple detection models including a first detection model and a second detection model configured to detect a plurality of feature points on a subject included in a camera image. The first detection model focuses on the frame rate when detecting the feature points, and the second detection model focuses on the accuracy when detecting the feature points;

[0031] Detect a plurality of feature points on the subject included in the camera image through the selected detection model; and

[0032] Determine the photographing range of the subject based on the plurality of feature points.

[0033] An information processing program according to the present invention causes a computer to execute the following steps:

[0034] Obtain a camera image generated by photographing a moving image of a subject on an examination bed with a camera;

[0035] Select one detection model from multiple detection models including a first detection model and a second detection model configured to detect a plurality of feature points on a subject included in a camera image. The first detection model focuses on the frame rate when detecting the feature points, and the second detection model focuses on the accuracy when detecting the feature points;

[0036] Detect a plurality of feature points on the subject included in the camera image through the selected detection model; and

[0037] Determine the photographing range of the subject based on the plurality of feature points.

[0038] Advantages of the Invention

[0039] According to the present invention, when setting the photographing range, it is possible to appropriately detect feature points according to the condition of the subject. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a perspective view showing an outline of a CT apparatus to which an information processing apparatus according to a first embodiment of the present invention is applied.

[0041] Figure 2 It is a view of the CT apparatus to which the information processing apparatus according to the first embodiment is applied as viewed from the side.

[0042] Figure 3 It is a view showing a schematic structure of the information processing apparatus according to the first embodiment.

[0043] Figure 4 It is a view showing a functional structure of the information processing apparatus according to the first embodiment.

[0044] Figure 5 It is a view for explaining feature points.

[0045] Figure 6 is a diagram showing a schematic view of a scan start line and a scan end line being displayed.

[0046] Figure 7 is a flowchart showing the processing performed in the first embodiment.

[0047] Figure 8 is a diagram showing the functional configuration of an information processing apparatus according to the second embodiment.

[0048] Figure 9 is a flowchart showing the processing performed in the second embodiment.

[0049] Figure 10 is a flowchart showing the processing performed in the third embodiment.

[0050] Symbol Explanation

[0051] 1 - CT apparatus, 2 - gantry, 3 - examination table, 3A - examination table part, 3B - base part, 3C - drive part, 4 - console, 5 - opening, 7 - camera, 10, 10A - information processing apparatus, 11 - CPU, 12 - information processing program, 13 - storage device, 14 - display, 15 - input device, 16 - memory, 17 - network I / F, 18 - bus, 20 - imaging control part, 21 - camera control part, 22 - selection part, 23 - feature point detection part, 24 - imaging range determination part, 25 - movement detection part, H - subject. Detailed Embodiment

[0052] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. Figure 1 is a perspective view showing an overview of a CT apparatus to which an information processing apparatus according to the first embodiment of the present invention is applied, Figure 2 is a view of a CT apparatus to which an information processing apparatus according to the first embodiment of the present invention is applied, as viewed from the side. As Figure 1 and Figure 2 shown, the CT apparatus 1 according to the present embodiment includes a gantry 2, an examination table 3, and a console 4.

[0053] The gantry 2 has a tunnel - shaped structure with an opening 5 in the center thereof. Inside the gantry 2, an X - ray source unit that emits X - rays and a detection unit that detects X - rays and generates a radiation image (both not shown) are provided. The X - ray source unit and the detection unit can rotate along the annular shape of the gantry 2 while maintaining a facing position relationship with each other. Also, inside the gantry 2, a control unit that controls the operation of the CT apparatus 1 is provided.

[0054] The examination table 3 has an examination table portion 3A on which the subject lies, a base portion 3B that supports the examination table portion 3A, and a drive portion 3C that reciprocally moves the examination table portion 3A in the direction of arrow A. The examination table portion 3A can slide relative to the base portion 3B in the direction of arrow A by the drive portion 3C. When taking a CT image, the examination table portion 3A slides, whereby the subject H lying on the examination table portion 3A is conveyed into the opening 5 of the gantry 2.

[0055] In addition, a camera 7 is provided above the examination table 3. The camera 7 is a camera capable of taking an RGB color image by detecting the reflected light of the subject H. The camera 7 has a lens and an imaging element such as a CCD (Charge Coupled Device), and obtains a camera image as a moving image by taking the subject H on the examination table 3 at a preset frame rate, and outputs it to the console 4. In addition, the camera 7 may be a camera that integrates an RGB camera and an NIR (Near InfraRed) camera. In this case, the NIR camera is a stereo camera and can obtain information on the depth direction of the subject H through parallax. By setting the NIR camera of the camera 7 as a stereo camera, information on the depth direction of the subject H on the examination table 3 can be obtained. In addition, even when the amount of light is insufficient, the NIR camera can take a picture. Therefore, when the brightness in the examination room is insufficient for the RGB camera to take a picture, the subject H can be photographed by the NIR camera.

[0056] The driving of the gantry 2, the driving of the examination table 3, and the photographing of the subject H by the camera 7 are performed by the operator's input from the console 4. The console 4 contains the information processing device according to the present embodiment.

[0057] Next, the information processing device according to the first embodiment contained in the console 4 will be described. First, with reference to Figure 3 , the hardware structure of the information processing device according to the first embodiment will be described. As Figure 3 shown, the information processing device 10 is a computer such as a workstation, a server computer, and a personal computer, and includes a CPU (Central Processing Unit) 11, a non-volatile storage device 13, and a memory as a temporary storage area 16. In addition, the information processing device 10 includes a display 14 such as a liquid crystal display, input devices 15 such as a keyboard and a mouse, and interfaces such as a network I / F (InterFace) 17 connected to the CT device 1. The CPU 11, the storage device 13, the display 14, the input devices 15, the memory 16, and the network I / F 17 are connected to a bus 18. In addition, the CPU 11 is an example of the processor in the present invention. The display 14 and the input devices 15 are also shown in Figure 1and Figure 2 in

[0058] The storage device 13 is implemented by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, etc. The information processing program 12 installed in the information processing apparatus 10 is stored in the storage device 13 as a storage medium. The CPU 11 reads out the information processing program 12 from the storage device 13, expands it into the memory 16, and executes the expanded information processing program 12.

[0059] In addition, the information processing program 12 is stored in a storage device of a server computer connected to a network or a network storage in a state accessible from the outside, and is downloaded and installed in the computer constituting the information processing apparatus 10 as needed. Alternatively, it is recorded on a recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory), distributed, and installed from the recording medium in the computer constituting the information processing apparatus 10.

[0060] Next, the functional structure of the information processing apparatus according to the first embodiment will be described. Figure 4 is a diagram showing the functional structure of the information processing apparatus according to the first embodiment. As Figure 4 shown, the information processing apparatus 10 includes a photographing control unit 20, a camera control unit 21, a selection unit 22, a feature point detection unit 23, and a photographing range determination unit 24. Further, by the CPU 11 executing the information processing program 12, the CPU 11 functions as the photographing control unit 20, the camera control unit 21, the selection unit 22, the feature point detection unit 23, and the photographing range determination unit 24.

[0061] The photographing control unit 20 controls the photographing unit, the detection unit, and the control unit provided on the gantry 2 according to an instruction from the input device 15 to photograph the subject H. In addition, when performing a CT scan, in order to determine the photographing range, a positioning scan is performed before the formal scan for obtaining a three-dimensional CT image. The positioning scan is performed by photographing the subject H while fixing the photographing unit and the detection unit.

[0062] At the time of positioning photography, the imaging range of the subject H is set as described later, and the examination table 3 is moved to the opening 5 of the gantry 2 in such a way as to image the set imaging range, thereby performing positioning photography. The positioning image obtained by the positioning photography is a two-dimensional image included in the imaging range set for the subject H. The positioning image is displayed on the display 14. The operator observes the positioning image displayed on the display 14 and sets the imaging range for the formal photography. After setting the imaging range, the operator gives an instruction for the formal photography from the input device 15, and thereby the formal photography is performed to obtain a three-dimensional CT image of the subject H. The obtained positioning image and CT image are stored in the storage device 13.

[0063] The camera control unit 21 controls the photography of the subject H on the examination table 3 based on the camera 7. The photography of the subject H based on the camera 7 is performed to set the imaging range at the time of positioning photography. The photography of the subject H based on the camera 7 starts from the preparation stage before photography. That is, the camera control unit 21 starts the photography based on the camera 7 from the moment before the subject H lies supine on the examination table 3, so that the camera 7 acquires a camera image. And when the operator gives an instruction to start the positioning photography, the camera control unit 21 stops the photography based on the camera 7. The acquired camera image is stored in the memory 16 in order to determine the imaging range described later.

[0064] The selection unit 22 selects one detection model from the first detection model 22A and the second detection model 22B that are configured to detect a plurality of feature points on the subject H included in the camera image acquired by the camera 7. The first detection model 22A is a detection model that emphasizes the frame rate when detecting feature points. The second detection model 22B is a model that emphasizes the accuracy when detecting feature points. The first detection model 22A and the second detection model 22B are constructed by a machine learning neural network.

[0065] "Emphasizing the frame rate" means, for example, by reducing the amount of data to be processed, or omitting operations, etc., to increase the processing speed for detecting feature points. Since the first detection model 22A emphasizes the frame rate, it uses a model with a small amount of computation and a high processing speed for detecting feature points.

[0066] "Emphasizing the accuracy" means, without reducing the amount of data or omitting operations, although the operation time is long, to increase the accuracy of detecting feature points. Since the second detection model 22B emphasizes the accuracy, it has a large amount of computation and a slower processing speed than the first detection model 22A, but uses a model with a higher accuracy for detecting feature points than the first detection model 22A.

[0067] The first detection model 22A uses a neural network with a structure that requires less computational effort and can perform feature point detection processing at high speed. The second detection model 22B uses a neural network with a structure that requires more computational effort but can detect feature points with higher accuracy than the first detection model 22A. For either neural network, training images are also used for learning. The training images are obtained by photographing a human body using the camera 7 and include the entire body of the human body, and 17 feature points are known. In addition, in the same manner as in the case of performing an actual examination, for example, training images are obtained by photographing a person wearing an examination gown using the camera 7.

[0068] In addition, neural networks with the same structure can also be used in the first detection model 22A and the second detection model 22B. In this case, different training images are used for learning the neural network in the first detection model 22A and the second detection model 22B. For example, the first training image used in the learning of the first detection model 22A can be an image with a relatively low resolution. On the other hand, the second training image used in the learning of the second detection model 22B can be an image with a resolution greater than that of the first training image.

[0069] In the first embodiment, the selection unit 22 selects either the first detection model 22A or the second detection model 22B according to the photographed part of the subject H. Here, the photographed parts of the subject H include the head, chest, abdomen, lower limbs, and the whole body, etc. However, the head is likely to move during shooting, while the chest or abdomen is not likely to move during shooting. Therefore, when the photographed part is the head or the whole body including the head, the selection unit 22 selects the first detection model 22A that focuses on the frame rate. On the other hand, when the photographed part is the abdomen or the lower limbs, it is often the case that a blanket is covered for shooting. Therefore, the selection unit 22 selects the second detection model 22B that focuses on accuracy and is easier to detect feature points.

[0070] In addition, in the present embodiment, a table associating the photographed part with the detection model to be selected is stored in the storage device 13. The selection unit 22 refers to this table and selects the detection model corresponding to the photographed part.

[0071] In addition, the photographed part of the subject H is included in the examination form provided by the doctor during shooting. The operator refers to the examination form and sets the photographed part using the input device 15.

[0072] The feature point detection unit 23 detects feature points from the camera image using the detection model selected by the selection unit 22. Figure 5 It is a diagram for explaining feature points. As Figure 5As shown, in the present embodiment, the first detection model 22A and the second detection model 22B are configured to detect 17 feature points on the subject H included in the camera image. The 17 feature points are both eyes, nose, both ears, both shoulders, both elbows, both hands, both waists, both knees, and both feet. Additionally, it can also be set to use 18 feature points by adding the point in the middle of the collarbones to these 17 feature points.

[0073] The first detection model 22A and the second detection model 22B derive the probability representing each of the 17 feature points for each pixel in the camera image. Moreover, for each of the 17 feature points, the feature point detection unit 23 detects the pixel that derives the highest probability as the feature point. For example, when detecting the right eye as a feature point, the feature point detection unit 23 compares the probabilities of being the right eye for all the pixels in the camera image derived by the first detection model 22A and the second detection model 22B, and detects the pixel with the highest probability as the feature point of the right eye.

[0074] The photographing range determination unit 24 determines the photographing range of the subject H during positioning photography based on the 17 feature points detected by the feature point detection unit 23. Therefore, the photographing range determination unit 24 first determines the detection accuracy of the feature points detected by the feature point detection unit 23. As described above, for each of the 17 feature points, the feature point detection unit 23 detects the pixel that derives the highest probability as the feature point. The higher the probability output by the detection model for the detected feature point, the better the detection accuracy. Therefore, the photographing range determination unit 24 compares the representative value of the probabilities derived by the detection model for the 17 feature points with a preset threshold, and determines that the detection accuracy is good when the representative value is above the threshold, and the detection accuracy is poor when the representative value is less than the threshold.

[0075] As the representative value, it is possible to use the average value, the median value, the weighted average value corresponding to the photographing part, etc., but it is not limited to these. Also, in the first detection model 22A that emphasizes the frame rate and the second detection model 22B that emphasizes the accuracy, even if the same camera image is input, the probability of deriving the feature points becomes smaller in the first detection model 22A. Therefore, it can also be set that when the first detection model 22A is selected, a smaller threshold is used than when the second detection model 22B is selected.

[0076] When it is determined that the detection accuracy is good, the imaging range determination unit 24 performs processing to determine the imaging range. On the other hand, when it is determined that the detection accuracy is poor, the imaging range determination unit 24 performs warning display on the display 14. Here, if the subject H makes excessive movements, or the subject H is covered with a thick blanket, or the entire body of the subject H is not included in the imaging range of the camera 7, regardless of which detection model is used, the feature points cannot be detected with high accuracy, resulting in deterioration of the detection accuracy. In this case, the imaging range determination unit 24 determines that the detection accuracy is poor.

[0077] In addition, when the warning display has been performed, the operator manually sets the imaging range for positioning imaging. That is, the operator measures the distance from the initial position of the examination table 3 to the scan start line, and further measures the distance between the scan start line and the scan end line, and inputs the measured distances from the input device 15. Based on the input distances, the movement of the examination table 3 during positioning imaging is controlled. The scan start line is an example of the start line of imaging, and the scan end line is an example of the end line of imaging.

[0078] Hereinafter, the processing for determining the imaging range by the imaging range determination unit 24 will be described. For example, when the imaging part is the head, the imaging range is from the top of the head to the end of the jaw of the positioning image. Therefore, the imaging range determination unit 24 sets the line connecting the eyes or ears among the feature points detected by the feature point detection unit 23, and further sets the scan start line at the top of the head and the scan end line between the jaw and the shoulders. Then, based on the distance relationship between the line connecting the eyes or ears and the scan start line and the scan end line, the distance D1 between the scan start line and the scan end line is derived. The range of the distance D1 between the scan start line and the scan end line becomes the imaging range.

[0079] Here, before positioning imaging, the examination table 3 is at the initial position, and the subject H lies supine on the examination table 3. Therefore, from the camera image, the distance from the end of the examination table 3 to the top of the head of the subject H can be known. Therefore, the imaging range determination unit 24 calculates the distance D2 from the end of the examination table 3 to the top of the head of the subject H as the movement amount of the examination table 3 from the initial position to the scan start line, that is, the movement amount of the examination table 3 until the top of the head of the subject H reaches the scan position in the CT apparatus 1.

[0080] If the imaging range is determined, the imaging range determination unit 24 displays the scan start line and the scan end line on the human body diagram, that is, the schematic diagram, displayed on the display 14. Figure 6 is a diagram showing the schematic diagram with the start line and the end line displayed. As Figure 6As shown, a scanning start line 31 and a scanning end line 32 are shown in the schematic diagram 30. The operator confirms the scanning start line and the scanning end line displayed on the display 14. After confirmation, if it is determined, the operator uses the input device 15 to give an instruction to start the positioning photography.

[0081] According to the instruction to start the positioning photography, the information of the distances D1 and D2 is output to the CT apparatus 1. In the photographing control unit 20, the CT apparatus 1 is controlled in such a manner that the scanning of the positioning photography starts after the driving unit 3C moves the examination table 3 by the distance D2, and the scanning of the positioning photography ends when the driving unit 3C moves the examination table 3 by the distance D1.

[0082] The positioning image obtained by the positioning photography is displayed on the display 14. The operator confirms the positioning image displayed on the display 14 and sets the photographing range of the formal photography in the positioning image. Thereafter, the formal photography is performed by giving a photography instruction of the formal photography using the input device 15, and a three-dimensional CT image of the photographing part of the subject H is obtained within the set photographing range of the formal photography.

[0083] Next, the processing performed in the first embodiment will be described. Figure 7 It is a flowchart showing the processing performed in the first embodiment. The processing is started by giving an instruction to start the photography by the input device 15, and the selection unit 22 determines the photographing part included in the checklist (step ST1). Moreover, the selection unit 22 selects either the first detection model 22A or the second detection model 22B according to the determined photographing part (select detection model; step ST2).

[0084] Next, the camera control unit 21 starts to obtain a camera image based on the photography by the camera 7 (step ST3), and the feature point detection unit 23 detects feature points from the camera image using the detection model selected by the selection unit 22 (step ST4). Next, the photographing range determination unit 24 determines the detection accuracy of the feature points (step ST5). When it is determined that the detection accuracy is good, the photographing range determination unit 24 determines the photographing range at the time of the positioning photography according to the feature points (step ST6), and depicts the scanning start line and the scanning end line at the time of the positioning photography on the schematic diagram displayed on the display 14 (depict line; step ST7). On the other hand, when it is determined that the detection accuracy is poor, the photographing range determination unit 24 performs a warning display (step ST8). When the warning display has been performed, the information processing apparatus 10 ends the photographing range determination process. In this case, as described above, the operator manually sets the photographing range of the positioning photography.

[0085] Next, it is determined whether the operator has given an instruction to start the positioning photography (step ST9). If step ST9 is negative, the process returns to step ST3, and the processes after step ST3 are repeated. If step ST9 is affirmative, the camera control unit 21 stops the photography based on the camera 7 (step ST10), and the information processing device 10 ends the photography range determination process.

[0086] After that, the positioning image is acquired by the positioning photography performed by the photography control unit 20 and displayed on the display 14. After the operator confirms the positioning image, the photography range for the formal photography is set. Moreover, the formal photography is performed by the operator giving an instruction for the formal photography from the input device 15, thereby acquiring a three-dimensional CT image of the subject H.

[0087] In this way, in the first embodiment, the detection model for detecting the feature points is selected according to the photography part. Therefore, in the case where the photography part is the head or the like that often moves during shooting, the first detection model 22A that emphasizes the frame rate can be selected. In the case where the photography part is the abdomen or the like that moves little but is often covered with a blanket or the like during shooting, the second detection model 22B that emphasizes the accuracy can be selected. Therefore, when setting the photography range, the feature points can be appropriately detected according to the photography part. As a result, the photography range at the time of positioning photography can be appropriately determined using the detected feature points.

[0088] Next, a second embodiment of the present invention will be described. In addition, the hardware structure of the information processing device based on the second embodiment is the same as that of the first embodiment described above, and thus the detailed description thereof is omitted here. Figure 8 FIG. is a diagram showing the functional structure of the information processing device based on the second embodiment. In Figure 8 , the same reference numerals are given to the same structures as Figure 4 and the detailed description thereof is omitted. The information processing device 10A based on the second embodiment is different from the first embodiment in that it includes a movement detection unit 25 that detects the movement of the subject H.

[0089] The movement detection unit 25 detects the movement of the subject H. Specifically, the two-dimensional movement of the feature points detected by the feature point detection unit 23 is detected between temporally adjacent frames in the camera image. In addition, in the second embodiment, the selection unit 22 first selects the first detection model 22A that emphasizes the frame rate, and the feature point detection unit 23 uses the first detection model 22A to detect the feature points. Regarding the feature points for detecting the movement of the subject H, the feature points corresponding to the photography part may also be used. For example, in the case where the photography part is the head, the nose, both eyes, or both ears can be used. In the case where the photography part is the chest, both shoulders and the roots of the left and right feet can be used. In addition, as the movement, the representative value of all the movements of 17 feature points may be obtained.

[0090] When the detected movement is above a preset threshold, the movement detection unit 25 determines that the movement is large, and when it is less than the threshold, the movement detection unit 25 determines that the movement is small.

[0091] In the second embodiment, if the movement detection unit 25 determines that the movement of the subject H is small, the selection unit 22 selects the second detection model 22B that emphasizes accuracy to replace the first detection model 22A. The feature point detection unit 23 uses the second detection model 22B selected by the selection unit 22 to detect feature points, and the photographing range determination unit 24 determines the photographing range using the detected feature points. On the other hand, if the movement detection unit 25 determines that the movement of the subject H is large, the feature point detection unit 23 continues to use the first detection model 22A for detecting the feature points for detecting movement to detect feature points, and the photographing range determination unit 24 determines the photographing range using the detected feature points.

[0092] Next, the processing performed in the second embodiment will be described. Figure 9 It is a flowchart showing the processing performed in the second embodiment. For example, the processing is started by an instruction to start photographing by the input device 15, and the camera control unit 21 starts photographing based on the camera 7 to obtain a camera image (step ST21). Next, the selection unit 22 selects the first detection model 22A that emphasizes the frame rate (step ST22), and the feature point detection unit 23 detects feature points from the camera image using the detection model selected by the selection unit 22 (step ST23)

[0093] Next, the movement detection unit 25 uses the feature points detected by the feature point detection unit 23 to detect the movement of the subject H (step ST24), and thus determines whether the movement is large (step ST25). If the movement of the subject H is small and step ST25 is negated, the selection unit 22 selects the second detection model 22B that emphasizes accuracy to replace the first detection model 22A (step ST26). Next, the feature point detection unit 23 detects feature points from the camera image (step ST27), and the photographing range determination unit 24 determines the detection accuracy of the feature points (step ST28). If step ST25 is affirmed, it proceeds to step ST28, and the photographing range determination unit 24 determines the detection accuracy of the feature points detected in step ST23.

[0094] When it is determined that the detection accuracy is good, the photographing range determination unit 24 determines the photographing range at the time of positioning photographing based on the feature points (step ST29), and based on the determined photographing range, depicts the scanning start line and the scanning end line at the time of positioning photographing on the schematic diagram displayed on the display 14 (depiction line; step ST30). On the other hand, when it is determined that the detection accuracy is poor, the photographing range determination unit 24 performs a warning display (step ST31). When the warning display has been performed, the information processing apparatus 10A ends the photographing range determination process. In this case, as described above, the operator manually sets the photographing range of the positioning photographing.

[0095] Next, it is determined whether the operator has given an instruction to start the positioning photographing (step ST32). If step ST32 is negative, the process returns to step ST21, and the processes after step ST21 are repeated. If step ST32 is affirmative, the camera control unit 21 stops the photographing based on the camera 7 (step ST33), and the information processing apparatus 10A ends the photographing range determination process.

[0096] Thus, in the second embodiment, it is set that the movement of the subject H is detected. In the case of large movement, the first detection model 22A that emphasizes the frame rate is used, and in the case of small movement, the second detection model 22B that emphasizes the accuracy is used to detect the feature points. Therefore, when setting the photographing range, the feature points can be appropriately detected according to the movement of the subject. As a result, the photographing range at the time of positioning photographing can be appropriately determined using the detected feature points.

[0097] Next, a third embodiment of the present invention will be described. In addition, the hardware structure and the functional structure of the information processing apparatus based on the third embodiment are the same as those of the information processing apparatus based on the first embodiment described above, and thus the detailed description thereof is omitted here. In the third embodiment, first, the feature points are detected by the first detection model 22A that emphasizes the frame rate, and the detection accuracy of the feature points is determined. In the case of poor detection accuracy, the second detection model 22B that emphasizes the accuracy is used instead of the first detection model 22A, which is different from the first embodiment.

[0098] Next, the processing performed in the third embodiment will be described. Figure 10 is a flowchart showing the processing performed in the third embodiment. For example, the processing is started by an instruction to start photographing by the input device 15, and the camera control unit 21 starts photographing based on the camera 7 to acquire a camera image (step ST41). Next, the selection unit 22 selects the first detection model 22A that emphasizes the frame rate (step ST42), and the feature point detection unit 23 uses the detection model selected by the selection unit 22 to detect feature points from the RGB camera image (step ST43)

[0099] Next, the photographing range determination unit 24 determines the detection accuracy of the feature points (step ST44). When the photographing range determination unit 24 determines that the detection accuracy is poor, the selection unit 22 selects the second detection model 22B that emphasizes accuracy to replace the first detection model 22A (step ST45). Next, the feature point detection unit 23 detects feature points from the camera image (step ST46), and the photographing range determination unit 24 determines the detection accuracy of the feature points (step ST47).

[0100] When it is determined that the detection accuracy is good, the photographing range determination unit 24 determines the photographing range at the time of positioning photography based on the feature points (step ST48), and according to the determined photographing range, depicts the scanning start line and the scanning end line at the time of positioning photography on the schematic diagram displayed on the display 14 (drawing line; step ST49). On the other hand, when it is determined that the detection accuracy is poor, the photographing range determination unit 24 performs a warning display (step ST50). When the warning display has been performed, the information processing device 10 ends the photographing range determination process. In this case, as described above, the operator manually sets the photographing range of the positioning photography.

[0101] In addition, when the photographing range determination unit 24 determines in step ST44 that the detection accuracy is good, the process proceeds to step ST48, and the processes after step ST48 are performed.

[0102] Next, it is determined whether the operator has given an instruction to start the positioning photography (step ST51). If step ST51 is negated, the process returns to step ST41, and the processes after step ST41 are repeated. If step ST51 is affirmed, the camera control unit 21 stops the photography based on the camera 7 (step ST52), and the information processing device 10 ends the photographing range determination process.

[0103] Thus, in the third embodiment, it is set that first, the feature points are detected by the first detection model 22A that emphasizes the frame rate. When the detection accuracy of the feature points is good, the first detection model 22A that emphasizes the frame rate is continued to be used. When the detection accuracy of the feature points is poor, the second detection model 22B that emphasizes accuracy is used to detect the feature points. Therefore, when setting the photographing range, the feature points can be accurately detected according to the detection accuracy of the feature points. As a result, the photographing range at the time of positioning photography can be accurately determined using the detected feature points.

[0104] In addition, in each of the above embodiments, the information processing device based on the present invention is applied to a CT device, but it is not limited thereto. If it is a photographing device that acquires a positioning image for setting a photographing range before formal photography, the information processing device based on the present invention can also be applied to an MRI device or the like.

[0105] Further, in each of the above-described embodiments, it is assumed that the information processing apparatus includes the photographing control unit 20, but this is not limitative. The photographing control unit 20 may be provided separately from the information processing apparatus.

[0106] Further, in each of the above-described embodiments, a detection model for detecting feature points is selected from the first detection model 22A and the second detection model 22B, but this is not limitative. For example, for a detection model that emphasizes frame rate, multiple detection models with different processing speeds for detecting feature points may be used. Also, for a detection model that emphasizes accuracy, multiple detection models with different accuracies of feature point detection may be used.

[0107] Further, in the above-described embodiment, for example, as the hardware structure of a processing unit (Processing Unit) that executes various processes such as the photographing control unit 20, the camera control unit 21, the selection unit 22, the feature point detection unit 23, the photographing range determination unit 24, and the movement detection unit 25, various processors (Processor) shown below can be used. As described above, among the above various processors, in addition to a general-purpose processor, i.e., a CPU, that executes software (program) and functions as various processing units, there are also processors such as FPGA (Field Programmable Gate Array), which is a programmable logic device (Programmable Logic Device) whose circuit structure can be changed after manufacturing, and ASIC (Application Specific Integrated Circuit), which is a dedicated circuit such as a processor having a circuit structure designed specifically for executing a specific process.

[0108] One processing unit may be constituted by one of these various processors, or may be constituted by a combination of two or more processors of the same type 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 constituted by one processor.

[0109] As an example of constituting multiple processing units by one processor, first, there is a method as represented by a computer such as a client and a server, in which one processor is constituted by a combination of one or more CPUs and software, and this processor functions as multiple processing units. Second, there is a method as represented by a system on chip (SoC), in which a processor that realizes the functions of the entire system including multiple processing units using one IC (Integrated Circuit) chip is used. Thus, various processing units are constituted using one or more of the above various processors as a hardware structure.

[0110] In addition, as the hardware structure of these various processors, more specifically, circuitry formed by combining circuit elements such as semiconductor elements can be used.

[0111] The following are the appended items of the present invention.

[0112] (Appended Item 1)

[0113] An information processing apparatus including at least one processor,

[0114] wherein the processor performs the following processing:

[0115] obtaining a camera image generated by photographing a subject on an examination bed with a camera;

[0116] selecting one detection model from a plurality of detection models including a first detection model and a second detection model configured to detect a plurality of feature points on the subject included in the camera image, the first detection model emphasizing the frame rate when detecting the feature points, and the second detection model emphasizing the accuracy when detecting the feature points;

[0117] detecting the plurality of feature points on the subject included in the camera image by the selected detection model; and

[0118] determining a photographing range of the subject based on the plurality of feature points.

[0119] (Appended Item 2)

[0120] The information processing apparatus according to Appended Item 1, wherein

[0121] the processor selects the detection model according to the photographing part of the subject.

[0122] (Appended Item 3)

[0123] The information processing apparatus according to Appended Item 1 or 2, wherein

[0124] the processor performs the following processing: determining the detection accuracy of the feature points, and when the detection accuracy is above a reference, determining the photographing range based on the feature points, and when the detection accuracy is lower than the reference, giving a warning.

[0125] (Appended Item 4)

[0126] The information processing apparatus according to Appended Item 1, wherein

[0127] the processor performs the following processing: detecting the movement of the subject based on the camera image; and

[0128] When the movement of the subject is above the reference, the photographing range is determined based on the feature points detected using the first detection model. When the movement of the subject is less than the reference, the photographing range is determined based on the feature points detected using the second detection model.

[0129] (Supplementary Note 5)

[0130] The information processing apparatus according to Supplementary Note 3, wherein

[0131] The processor selects the first detection model to detect the feature points from the camera image, and detects the movement of the subject based on the feature points.

[0132] (Supplementary Note 6)

[0133] The information processing apparatus according to Supplementary Note 4 or 5, wherein

[0134] The processor performs the following processing: determines the detection accuracy of the feature points. When the detection accuracy is above the reference, the photographing range is determined based on the feature points. When the detection accuracy is lower than the reference, a warning is issued.

[0135] (Supplementary Note 7)

[0136] The information processing apparatus according to Supplementary Note 1, wherein

[0137] The processor performs the following processing: selects the first detection model to detect the feature points from the camera image, and determines the detection accuracy of the feature points. When the detection accuracy is above the first reference, the photographing range is determined based on the feature points detected using the first detection model. When the detection accuracy is lower than the first reference, the second detection model is selected, and the photographing range is determined based on the feature points detected using the second detection model.

[0138] (Supplementary Note 8)

[0139] The information processing apparatus according to Supplementary Note 7, wherein

[0140] The processor performs the following processing:

[0141] Determines the detection accuracy of the feature points detected using the second detection model. When the detection accuracy is above the second reference, the photographing range is determined based on the feature points. When the detection accuracy is lower than the second reference, a warning is issued.

[0142] (Supplementary Note 9)

[0143] The information processing apparatus according to any one of appended items 1 to 8, wherein,

[0144] The processor derives the moving distance of the examination table according to the photographing range.

[0145] (Appended item 10)

[0146] The information processing apparatus according to any one of appended items 1 to 9, wherein,

[0147] The processor performs the following processing: displaying a human body image simulating a human body on a display, and depicting a photographing start line and a photographing end line based on the photographing range on the human body image.

[0148] (Appended item 11)

[0149] The information processing apparatus according to any one of appended items 1 to 10, wherein,

[0150] The photographing range is a photographing range when photographing a positioning image obtained before the formal photographing of the subject.

[0151] (Appended item 12)

[0152] The information processing apparatus according to any one of appended items 1 to 11, wherein,

[0153] The amount of computation of the first detection model is less than that of the second detection model, and the processing speed for detecting the feature points is faster than that of the second detection model. The amount of computation of the second detection model is more than that of the first detection model, and the processing speed for detecting the feature points is slower than that of the first detection model, but the detection accuracy is high.

[0154] (Appended item 13)

[0155] An information processing method, wherein,

[0156] A computer performs the following processing:

[0157] Obtaining a camera image generated by dynamically photographing a subject on an examination table by a camera;

[0158] Selecting one detection model from a plurality of detection models including a first detection model and a second detection model configured to detect a plurality of feature points on the subject included in the camera image. The first detection model focuses on the frame rate when detecting the feature points, and the second detection model focuses on the accuracy when detecting the feature points;

[0159] Detecting the plurality of feature points on the subject included in the camera image by the selected detection model; and

[0160] Determine the photography range of the subject based on the plurality of feature points.

[0161] (Supplementary Note Item 14)

[0162] An information processing program that causes a computer to execute the following steps:

[0163] Obtain a camera image generated by photographing a subject on an examination bed with a camera;

[0164] Select one detection model from a plurality of detection models including a first detection model and a second detection model configured to detect a plurality of feature points on the subject included in the camera image, the first detection model focusing on the frame rate when detecting the feature points, and the second detection model focusing on the accuracy when detecting the feature points;

[0165] Detect the plurality of feature points on the subject included in the camera image by the selected detection model; and

[0166] Determine the photography range of the subject based on the plurality of feature points.

Claims

1. An information processing device comprising at least one processor, The processor performs the following processing: acquiring a camera image generated by performing dynamic image photography of a subject on a diagnostic couch by a camera; selecting one detection model from a plurality of detection models including a first detection model and a second detection model constructed to detect a plurality of feature points on the subject included in the camera image, wherein the first detection model focuses on a frame rate when detecting the feature points, and the second detection model focuses on accuracy when detecting the feature points; detecting the plurality of feature points on the subject contained in the camera image by using the selected detection model; and An imaging range of the subject is determined based on the plurality of feature points.

2. The information processing device according to claim 1, wherein: The processor selects the detection model according to the imaging part of the subject.

3. The information processing device according to claim 1 or 2, wherein: The processor performs the following processing: determining the detection accuracy of the feature points, determining the photographing range based on the feature points when the detection accuracy is above a reference, and issuing a warning when the detection accuracy is lower than the reference.

4. The information processing device according to claim 1, wherein: The processor performs the following processing: detecting movement of the subject based on the camera image; and When the subject's movement is greater than the benchmark, the photographic range is determined based on the feature points detected using the first detection model. When the subject's movement is less than the benchmark, the photographic range is determined based on the feature points detected using the second detection model.

5. The information processing device according to claim 3, wherein: The processor selects the first detection model to detect the feature points from the camera image, and detects movement of the subject based on the feature points.

6. The information processing device according to claim 4, wherein: The processor performs the following processing: determining the detection accuracy of the feature points, determining the photographing range based on the feature points when the detection accuracy is above a reference, and issuing a warning when the detection accuracy is lower than the reference.

7. The information processing device according to claim 1, wherein: The processor performs the following processing: selects the first detection model to detect the feature points from the camera image, and determines the detection accuracy of the feature points; when the detection accuracy is above the first benchmark, determines the photographic range based on the feature points detected using the first detection model; when the detection accuracy is lower than the first benchmark, selects the second detection model, and determines the photographic range based on the feature points detected using the second detection model.

8. The information processing device according to claim 7, wherein: The processor performs the following processing: The detection accuracy of the feature points detected using the second detection model is determined, and when the detection accuracy is greater than a second standard, the photographing range is determined based on the feature points, and when the detection accuracy is lower than the second standard, a warning is issued.

9. The information processing device according to claim 1, wherein: The processor derives a moving distance of the diagnostic bed based on the imaging range.

10. The information processing device according to claim 1, wherein: The processor performs processing such as displaying a human body image simulating a human body on a display and drawing a photographing start line and a photographing end line based on the photographing range on the human body image.

11. The information processing device according to claim 1, wherein: The imaging range is an imaging range when capturing a positioning image acquired before performing a main imaging of the subject.

12. The information processing device according to claim 1, wherein: The first detection model has less computational complexity than the second detection model, and its processing speed for detecting the feature points is faster than that of the second detection model. The second detection model has more computational complexity than the first detection model, and its processing speed for detecting the feature points is slower than that of the first detection model, but has high detection accuracy.

13. An information processing method, wherein: The computer performs the following processing: acquiring a camera image generated by performing dynamic image photography of a subject on a diagnostic couch by a camera; selecting one detection model from a plurality of detection models including a first detection model and a second detection model constructed to detect a plurality of feature points on the subject included in the camera image, wherein the first detection model focuses on a frame rate when detecting the feature points, and the second detection model focuses on accuracy when detecting the feature points; detecting the plurality of feature points on the subject contained in the camera image by using the selected detection model; and An imaging range of the subject is determined based on the plurality of feature points.

14. An information processing program product causing a computer to execute the following steps: acquiring a camera image generated by performing dynamic image photography of a subject on a diagnostic couch by a camera; selecting one detection model from a plurality of detection models including a first detection model and a second detection model constructed to detect a plurality of feature points on the subject included in the camera image, wherein the first detection model focuses on a frame rate when detecting the feature points, and the second detection model focuses on accuracy when detecting the feature points; detecting the plurality of feature points on the subject contained in the camera image by using the selected detection model; and An imaging range of the subject is determined based on the plurality of feature points.

Images