Measuring apparatus, measurement system, measuring method and program
The measuring device uses a trained model for ultrasound image processing to accurately distinguish and measure the inferior vena cava's inner diameter, addressing the challenge of differentiation from the abdominal aorta and reducing measurement variations.
Patent Information
- Application Number
- JP2023073424
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-04-27
- Publication Date
- 2024-11-08
AI Technical Summary
Distinguishing and measuring the inner diameter of the inferior vena cava from the abdominal aorta in ultrasound images is challenging, particularly due to variations in recognition and measurement techniques among technicians.
A measuring device that utilizes a trained model for ultrasound image processing to distinguish the inferior vena cava from adjacent blood vessels, measures the inner diameter based on detected contours, and calculates maximum and minimum values from multiple images, employing machine learning for accurate identification and measurement.
Enables precise recognition and measurement of the inferior vena cava's inner diameter, reducing variations and ensuring accurate differentiation from the abdominal aorta, with improved measurement consistency and accuracy.
Smart Images

Figure 2024158312000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a measurement device, a measurement system, a measurement method, and a program. [Background technology]
[0002] Conventionally, an ultrasonic probe is pressed against a living body to obtain an ultrasonic image of a region of interest within the living body. When the region of interest from which an ultrasonic image is to be obtained moves approximately periodically within the living body, there is a technique for tracking the region of interest by changing the position and pressing angle of the ultrasonic probe (see, for example, Patent Document 1). In addition, there is a system that uses the technique described in Patent Document 1 to focus ultrasonic waves on the tracked region of interest and cauterize the affected area. This type of treatment is known as HIFU (High Intensity Focused Ultrasound) treatment, and is currently mainly used for the treatment of prostate cancer. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2016-158890 A Summary of the Invention [Problem to be solved by the invention]
[0004] A skilled technician performs diagnosis on the ultrasound image acquired by tracking the region of interest. One specific example of diagnosis is measurement of the inner diameter of the inferior vena cava. When measuring the inner diameter of the inferior vena cava, it is first necessary to distinguish the inferior vena cava from the abdominal aorta among the blood vessels shown in the ultrasound image. However, it is difficult for anyone other than a skilled technician to distinguish between the inferior vena cava and the abdominal aorta. In addition, even for a skilled technician, it is not easy to measure the inner diameter by tracking the same cross section of the inferior vena cava, and there is a problem that variations occur due to the habits of each technician.
[0005] The present invention has been made in consideration of the above-mentioned circumstances, and aims to provide a measuring device, a measuring system, a measuring method, and a program that are capable of recognizing the blood vessel to be measured separately from adjacent blood vessels and measuring the inner diameter of the blood vessel to be measured. [Means for solving the problem]
[0006] (1) One aspect of the present invention is a measuring device comprising: an acquisition unit that acquires an ultrasound image that visualizes the echo of ultrasound output by a measurement probe contacted with an animal to be measured; a detection unit that detects the contours of the animal's organs and the contours of blood vessels that fluctuate in sync with the organs that are displayed in the acquired ultrasound image; and a measurement unit that measures the inner diameter of the blood vessels based on the detected contours of the blood vessels.
[0007] (2) Also, one aspect of the present invention is the measuring device of (1) described above, wherein the acquisition unit acquires a plurality of ultrasound images in which the same measurement object is measured at different times, and the measurement unit further includes a calculation unit that measures the inner diameter of the blood vessel for each of the acquired ultrasound images and calculates a maximum value and a minimum value among the measured inner diameters.
[0008] (3) Also, one aspect of the present invention is a measuring device as described above in (1) or (2), wherein the detection unit detects the blood vessels that are the subject of measurement and blood vessels that are not the subject of measurement, and the measurement unit measures the inner diameter of the blood vessels that are the subject of measurement and does not measure the inner diameter of the blood vessels that are not the subject of measurement.
[0009] (4) Furthermore, in one aspect of the present invention, in the measurement device described in (3) above, the blood vessel to be measured is the inferior vena cava, and the blood vessel not to be measured is the abdominal aorta.
[0010] (5) Also, one aspect of the present invention is a measuring device according to any one of (1) to (4) above, wherein the detection unit includes a trained model that has been trained in advance by supervised learning using the ultrasound image, the contour of the animal's organ determined corresponding to the ultrasound image, and the contour of the blood vessels that change in sync with the organ as teacher data, and the trained model detects the contour of the animal's organ and the contour of the blood vessels that change in sync with the organ based on the ultrasound image acquired by the acquisition unit.
[0011] (6) Furthermore, one aspect of the present invention is the measuring device described in (5) above, wherein the trained model is pre-trained using the ultrasound image and the contours of blood vessels that are not the target of measurement as teacher data, and detects the contours of blood vessels that are not the target of measurement based on the ultrasound image acquired by the acquisition unit.
[0012] (7) In another aspect of the present invention, in the measuring device described in (6) above, the trained model uses at least the thickness of the blood vessel wall and the distance from the animal's organ as features to detect and distinguish between the blood vessels that are the target of measurement and blood vessels that are not the target of measurement.
[0013] (8) Furthermore, one aspect of the present invention is a measuring device according to any one of (1) to (7) above, wherein the measuring unit measures an inner diameter of the blood vessel at a predetermined position identified based on an organ of the animal.
[0014] (9) Moreover, in one aspect of the present invention, in the measurement device described in any one of (1) to (8) above, the measurement unit identifies an area of interest in each of both walls of the detected contour of the blood vessel, calculates the inclination of the blood vessel in each of the two identified areas of interest, and measures the line segment between the contours of the blood vessel among the lines that intersect perpendicularly to the average of the calculated inclinations of the blood vessel as the inner diameter of the blood vessel.
[0015] (10) Another aspect of the present invention is a measurement system comprising: a measurement probe that detects a signal to be measured from the animal to be measured; a driving device that moves the measurement probe relative to the animal to be measured; a measurement device described in any of (1) to (8) above; and a control device that controls the driving device to move the measurement probe to a position based on the detected contours of the animal's organs and the contours of the blood vessels.
[0016] (11) Also, one aspect of the present invention is a measurement method having an acquisition step of acquiring an ultrasound image that visualizes the echo of ultrasound output by a measurement probe contacted with an animal to be measured, a detection step of detecting the contours of the animal's organs and the contours of blood vessels that fluctuate in synchronization with the organs that are displayed in the acquired ultrasound image, and a measurement step of measuring the inner diameter of the blood vessels based on the detected contours of the blood vessels.
[0017] (12) Another aspect of the present invention is a program that causes a computer to execute an acquisition step of acquiring an ultrasound image that visualizes the echo of ultrasound output by a measurement probe contacted with an animal to be measured, a detection step of detecting the contours of the animal's organs and the contours of blood vessels that fluctuate in sync with the organs that are displayed in the acquired ultrasound image, and a measurement step of measuring the inner diameter of the blood vessels based on the detected contours of the blood vessels. Effect of the Invention
[0018] According to the present invention, the blood vessel to be measured can be recognized separately from adjacent blood vessels, and the inner diameter of the blood vessel to be measured can be measured. [Brief description of the drawings]
[0019] [Figure 1] FIG. 1 is a diagram for explaining an overview of a measurement system according to an embodiment. [Diagram 2] 5 is a diagram for explaining the flow of a measurement process performed by a measurement device according to an embodiment. FIG. [Diagram 3] FIG. 2 is a functional configuration diagram showing an example of a functional configuration of a measurement device according to an embodiment. [Figure 4] 4A and 4B are diagrams illustrating an example of an ultrasound image output by the measurement device according to the embodiment. [Diagram 5] FIG. 2 is a first diagram showing an example of the inferior vena cava and abdominal aorta shown in an ultrasound image according to an embodiment. [Figure 6] FIG. 2 is a second diagram showing an example of the inferior vena cava and abdominal aorta shown in an ultrasound image relating to an embodiment. [Figure 7] FIG. 11 is a first diagram for explaining a case where the inner diameter of the inferior vena cava is measured based on the inclination of a region of interest in the measurement process according to the embodiment. [Figure 8] FIG. 2 is a second diagram for explaining a case where the inner diameter of the inferior vena cava is measured based on the inclination of the region of interest in the measurement process according to the embodiment. [Figure 9] FIG. 13 is a third diagram for explaining a case where the inner diameter of the inferior vena cava is measured based on the inclination of the region of interest in the measurement process according to the embodiment. [Figure 10] 4 is a flowchart showing an example of a series of operations of the measurement system according to the embodiment. [Figure 11] 1 is a block diagram showing an example of an internal configuration of a measurement device according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0020] [Embodiment] Hereinafter, the measurement device, the measurement system, the measurement method, and the program according to the aspects of the present invention will be described in detail with reference to the accompanying drawings, with preferred embodiments presented. Note that the aspects of the present invention are not limited to these embodiments, and include those with various modifications or improvements. In other words, the components described below include those that a person skilled in the art can easily imagine, and those that are substantially the same. In addition, the components described below can be appropriately combined. In addition, various omissions, substitutions, or modifications of the components can be made within the scope of the present invention. In addition, in the following drawings, in order to make each configuration easier to understand, the scale and number, etc. of each structure may be different from the scale and number, etc. of the actual structure.
[0021] FIG. 1 is a diagram for explaining an overview of a measurement system according to an embodiment. First, an overview of the measurement system 1 will be explained with reference to the figure. The measurement system 1 includes a measurement device 10, a control device 20, a driving device 30, a measurement probe 40, an examination table 60, a display device 71, and an input device 72. The measurement system 1 includes these devices to measure a specific part (for example, an organ, a blood vessel, etc.) of the subject S. In the following description, a part of the subject S that is a measurement target of the measurement system 1 may be referred to as a part of interest. In the following description, an operator who operates the measurement system 1 may be referred to as an operator O. Note that a specific device may operate the measurement system 1 instead of the operator O.
[0022] Specifically, the measurement performed by the measurement system 1 may be imaging the area of interest by a predetermined method. More specifically, the measurement performed by the measurement system 1 may be X-ray fluoroscopy, CT (Computed Tomography), MRI (Magnetic Resonance Imaging), SPECT (Single Photon Emission Computed Tomography)-CT, tomosynthesis, or the like. In the following description, an example in which the measurement system 1 performs an ultrasonic examination will be described. After the measurement is performed by the measurement system 1, a predetermined treatment based on the result of the measurement may be performed.
[0023] In the following description, an example will be described in which the subject S to be measured by the measurement system 1 is a human. However, the present embodiment is not limited to this example, and the subject S may be an animal other than a human.
[0024] The subject S is placed on the examination table 60 with the side to be measured of the area to be measured (for example, the inferior vena cava adjacent to the liver) facing the measurement probe 40. The subject S lies, for example, on his / her back on the examination table 60. By having the subject S lie on his / her back on the examination table 60, it becomes possible to measure the area of interest from the front of the subject S. The examination table 60 is driven by the drive device 30, and the horizontal and vertical positions and angles can be changed.
[0025] The driving device 30 changes the relative position between the subject S and the measurement probe 40 by changing the horizontal and vertical position and angle of the examination table 60. Note that the driving device 30 may change the horizontal and vertical position and angle of the measurement probe 40 instead of or in addition to changing the position and angle of the examination table 60.
[0026] The positional relationship of the measurement probe 40 with the subject S is controlled by the control device 20, and the measurement probe 40 is pressed against the subject S. The measurement probe 40 detects a signal to be measured from the subject S. Specifically, when the measurement system 1 performs an ultrasound examination, the measurement probe 40 acquires an ultrasound image from the subject S. The measurement probe 40 outputs the acquired ultrasound image to the measurement device 10. In the following description, the measurement probe 40 may be simply referred to as a probe.
[0027] The measuring device 10 acquires an ultrasound image from the measuring probe 40. The measuring device 10 detects a blood vessel to be measured that is shown in the acquired ultrasound image, and performs a measurement based on the detected blood vessel. The measurement based on the detected blood vessel may be, for example, measuring the inner diameter of the blood vessel. The blood vessel to be measured may be the inferior vena cava.
[0028] The control device 20 outputs control signals to the drive device 30 and the measurement probe 40 based on the results of measurement by the measurement device 10. The control device 20 controls the relative relationship between the measurement probe 40 and the subject S by outputting the control signal. The results of measurement by the measurement device 10 may be, for example, the position of a blood vessel to be measured that is displayed on an ultrasound image acquired by the measurement probe 40.
[0029] The driving device 30 includes a driving mechanism (not shown). The driving mechanism includes components such as a motor, a gear, a pinion, and a rack. The driving device 30 controls the positional relationship between the subject S and the measurement probe 40. The driving device 30 controls the positional relationship to move the measurement probe 40 to a position of the subject S to be measured.
[0030] The display device 71 and the input device 72 are a user interface with the operator O. The display device 71 may be, for example, a liquid crystal display, an organic EL (Electroluminescence) display, or the like. The input device 72 accepts operations from the operator O. The input device 72 may be, for example, a keyboard, a touch panel, or a microphone, or the like. The display device 71 displays ultrasound images acquired by the measurement probe 40, results of measurements based on the ultrasound images, and the like. The input device 72 accepts operations from the operator O. The operations may be based on a display screen displayed on the display device 71, or may be operations required to operate the measurement system 1.
[0031] FIG. 2 is a diagram for explaining the flow of the measurement process performed by the measurement device according to the embodiment. The flow of the measurement process performed by the measurement device 10 will be described with reference to the same figure. In the following description, an example in which the measurement device 10 measures the inner diameter of the inferior vena cava will be described. However, this embodiment is not limited to this example, and can be applied to a wide range of other measurements. It is preferable that the blood vessels to be measured by the measurement device 10 fluctuate in synchronization with a specific organ. Note that the inferior aorta in the following specific example fluctuates in synchronization with the liver.
[0032] FIG. 2(A) is an example of an ultrasound image measured by the measurement probe 40. The measurement device 10 performs segmentation processing based on such an ultrasound image. In the segmentation processing, the contours of each organ are identified. In the illustrated example, the contours of the liver and the inferior vena cava (IVC) are each identified. FIG. 2(B) shows the contours of the liver and the inferior aorta cava. FIG. 2(C) shows the contours of the liver. FIG. 2(D) shows the contours of the inferior aorta cava.
[0033] As shown in the figure, the measuring device 10 may first identify the outlines of the liver and the inferior aorta as shown in Fig. 2(B), and then identify the outline of the liver as shown in Fig. 2(C) and the outline of the inferior aorta as shown in Fig. 2(D). Alternatively, the measuring device 10 may directly identify the outline of the liver as shown in Fig. 2(C) and the outline of the inferior aorta as shown in Fig. 2(D). In this case, Fig. 2(B) can be said to be an auxiliary view for explanation.
[0034] Next, the measuring device 10 identifies the measurement location of the inner diameter. Here, the results may vary depending on the measurement location of the inner diameter. Therefore, the measuring device 10 fixes the measurement location of the inner diameter to reduce the variation from measurement to measurement. The measurement location is identified based on the position of an adjacent organ. An adjacent organ is an organ with which the blood vessel to be measured fluctuates in synchronous fashion. When the blood vessel to be measured is the inferior vena cava, the adjacent organ is specifically the liver.
[0035] In order to identify the location where the inner diameter is to be measured, the measuring device 10 identifies a predetermined location in the liver. In the illustrated example, the center of gravity of the liver is expressed by two-dimensional coordinates (x LM ,y LM ) is specified. The specified liver center of gravity is illustrated in FIG. 2(E). Here, it is effective to use the liver center of gravity when the entire liver contour is projected on the ultrasound image. However, when a part of the liver contour is cut off from the ultrasound image, there is a risk that the position of the center of gravity may change due to a change in the imaging location. Therefore, instead of specifying the liver center of gravity, for example, a position at a predetermined distance from the left end of the liver contour may be specified. By specifying the position of the liver in this way, it is possible to suppress a change in the measurement location due to a change in the imaging location.
[0036] Next, the measurement device 10 identifies a measurement point on the blood vessel (inferior vena cava) to be measured based on the identified position of the liver (e.g., the center of gravity, or a position a predetermined distance away from the left end). The measurement point on the blood vessel is illustrated in FIG. 2(F). In the illustrated example, the point having the same x coordinate as the center of gravity of the liver and intersecting with the upper wall of the inferior vena cava is represented by two-dimensional coordinates (xLM The point that has the same y coordinate as the center of gravity of the liver and intersects with the inferior wall of the inferior vena cava is shown as a two-dimensional coordinate (x LM , y2). The distance between these two coordinates is the measured inner diameter of the inferior vena cava.
[0037] Specifically, the inner diameter of the inferior vena cava is calculated by d=|y1-y2|. The calculated inner diameter of the inferior vena cava is displayed superimposed on the ultrasound image that was the subject of measurement (i.e., the ultrasound image shown in FIG. 2(A)). An image in which the inner diameter is displayed is shown in FIG. 2(G). This image may be displayed on a display device 71. This image may also show bounding boxes indicating the positions of the detected organs (liver and inferior vena cava) and their classes, likelihoods, etc. If other organs are detected, these may also be shown.
[0038] FIG. 3 is a functional configuration diagram showing an example of the functional configuration of a measuring device according to an embodiment. An example of the functional configuration of a measuring device 10 will be described with reference to the diagram. The measuring device 10 includes an image acquisition unit 11, a detection unit 12, a measurement unit 13, a storage unit 14, a calculation unit 15, and an output unit 16. Each of these functional units is realized, for example, by using an electronic circuit. Furthermore, each functional unit may include a storage means such as a semiconductor memory or a magnetic hard disk device inside as necessary. Furthermore, each function may be realized by a computer having a CPU (Central Processing Unit) and software.
[0039] The image acquisition unit 11 acquires an ultrasound image measured by the measurement probe 40. The measurement probe 40 acquires an ultrasound image in a state where it is in contact with the subject S. In this embodiment, the subject S is not limited to a human being, but may be any animal that is the subject of measurement. The ultrasound image can also be said to be an image that visualizes the echo of the ultrasound output by the measurement probe 40. The ultrasound image acquired by the image acquisition unit 11 shows the organs of the subject S and the blood vessels that change in synchronization with the organs. In the following description, the image acquisition unit 11 may be simply referred to as an acquisition unit.
[0040] The detection unit 12 detects the contours of the organs and the contours of the blood vessels displayed in the ultrasound image acquired by the image acquisition unit 11, by distinguishing between them. The detection unit 12 may perform the detection process by machine learning. When performing the detection process by machine learning, the detection unit 12 may include a trained model (not shown). The trained model is trained in advance by supervised learning using predetermined teacher data in a learning stage. The teacher data used for learning is an ultrasound image, a contour of an animal's organ determined corresponding to the ultrasound image, and a contour of a blood vessel that changes in synchronization with the organ, which are associated with each other. In addition, the trained model detects the contours of the animal's organs and the contours of the blood vessels that change in synchronization with the organ, by distinguishing between them, based on the ultrasound image acquired by the image acquisition unit 11, in an inference stage.
[0041] Here, the ultrasound image acquired by the image acquisition unit 11 may show a blood vessel to be measured and a blood vessel that is not a measurement target. Also, either the blood vessel to be measured or the blood vessel that is not a measurement target may be shown. The detection unit 12 detects the blood vessel to be measured and the blood vessel that is not a measurement target by distinguishing them from each other. Therefore, when the detection process is performed by machine learning, it is preferable that the blood vessel that is not a measurement target is trained to be able to be detected by distinguishing it from the blood vessel that is a measurement target in the learning stage. More specifically, the trained model included in the detection unit 12 is trained in advance in the learning stage using data including blood vessels that are not a measurement target as teacher data. The data including blood vessels that are not a measurement target is data that is an ultrasound image and a blood vessel contour that is determined in correspondence with the ultrasound image, and that is associated with the contour of the blood vessel that is not a measurement target. The trained model thus trained can detect the contour of the blood vessel that is not a measurement target in the inference stage based on the ultrasound image acquired by the image acquisition unit 11. The blood vessel to be measured may be, for example, the inferior vena cava, and the blood vessel that is not a measurement target may be, for example, the abdominal aorta.
[0042] Any feature may be used in the machine learning. Specifically, examples of the feature may include the thickness of the blood vessel wall and the distance from an animal's organ (e.g., the human liver). By learning these as feature values, it is possible to distinguish and detect a blood vessel that is a measurement target (e.g., the inferior vena cava) from a blood vessel that is not a measurement target (e.g., the abdominal aorta).
[0043] The measuring unit 13 measures the inner diameter of the blood vessel based on the contour of the blood vessel detected by the detecting unit 12. The inner diameter of the blood vessel may be, for example, the width in the vertical direction of the image when the blood vessel is projected in the horizontal direction of the ultrasound image. In this case, it may be the distance from the upper wall to the lower wall of the blood vessel at the same x coordinate. Specifically, the inner diameter of the blood vessel may correspond to the inclination of the blood vessel. More specifically, the inner diameter of the blood vessel may correspond to the inclination of one wall of the blood vessel and the inclination of the other wall of the blood vessel.
[0044] Here, the detection unit 12 may detect blood vessels that are the measurement target and blood vessels that are not the measurement target by distinguishing them from each other. When the detection unit 12 detects a blood vessel that is the measurement target, the measurement unit 13 measures the inner diameter of the blood vessel. When the detection unit 12 detects a blood vessel that is not the measurement target, the measurement unit 13 does not measure the inner diameter of the blood vessel.
[0045] The location measured by the detection unit 12 may be based on the position of the liver, as described with reference to Figures 2(E) and 2(F). In other words, the measurement unit 13 may measure the inner diameter of the blood vessel at a predetermined position identified based on the organs of the animal. The predetermined position may be, for example, the center of gravity of the liver shown in the ultrasound image, or a position at a predetermined distance from the left end of the liver.
[0046] The storage unit 14 stores the inner diameter of the blood vessel measured by the measurement unit 13. Here, in this embodiment, the measurement device 10 performs measurements on ultrasound images continuously acquired in real time. Therefore, the storage unit 14 stores the inner diameter of the blood vessel measured by the measurement unit 13 for the ultrasound images continuously acquired in real time. The measured inner diameter value of the blood vessel may be associated with time information when the ultrasound image to be measured was acquired.
[0047] The calculation unit 15 calculates the maximum and minimum values of the inner diameters of the blood vessels stored in the storage unit 14. In this case, the image acquisition unit 11 acquires multiple ultrasound images in which the same measurement target is measured at different times, and the measurement unit 13 measures the inner diameter of the blood vessel for each of the acquired multiple ultrasound images and stores the measurement results in the storage unit 14. The calculation unit 15 calculates the maximum and minimum values of the multiple inner diameters measured by the measurement unit 13. The values calculated by the calculation unit 15 are not limited to the maximum and minimum values, and other statistically calculated values such as an average value may be calculated.
[0048] The output unit 16 outputs the values calculated by the calculation unit 15. The values calculated by the calculation unit 15 include a maximum value and a minimum value. Therefore, it can be said that the output unit 16 outputs the maximum value and the minimum value calculated by the calculation unit 15. The output unit 16 may output the ultrasound image currently acquired by the measurement probe 40 together with the maximum value and the minimum value. The output unit 16 may also output the ultrasound image currently acquired by the measurement probe 40, which is an image on which information (numeric information) related to the maximum value and the minimum value is superimposed.
[0049] 4 is a diagram showing an example of an ultrasound image output by the measuring device according to the embodiment. The figure shows an example of an output result output by the measuring device 10. As shown in the figure, the output result output by the measuring device 10 displays a plurality of pieces of information superimposed on the image currently acquired by the measuring probe 40.
[0050] Specifically, the figure shows a bounding box indicating the position of the liver. The bounding box indicates the class of the liver, "major-liver". The bounding box also indicates the likelihood of the liver, "1.00". Similarly, the figure shows a bounding box indicating the position of the inferior vena cava. The bounding box indicates the class of the inferior vena cava, "major-ivc". The bounding box also indicates the likelihood of the inferior vena cava, "0.49".
[0051] The measured inner diameter of the inferior vena cava is shown in the lower left of the figure. Specifically, it is written "inner diameter: 13.1 mm." In other words, the measured inner diameter of the inferior vena cava is 13.1 mm (millimeters). In addition, the figure shows the position where the inner diameter of the inferior vena cava was measured by a thick vertical line. The vertical line is shown inside the bounding box of the inferior vena cava.
[0052] The speed at which images are captured by the measurement probe 40 is shown in the lower right of the figure. Specifically, "FPS=15.0" is written. That is, the measurement probe 40 acquires ultrasound images at a speed of 15.0 [FPS (Frames Per Second)]. That is, in the illustrated example, 15 ultrasound images are acquired per second, and the inner diameter of the blood vessel is measured and the measurement result is updated every time an ultrasound image is acquired.
[0053] Next, with reference to Fig. 5 and Fig. 6, a specific example of a detection result when blood vessels to be measured and blood vessels not to be measured are detected while being distinguished from each other will be described. Fig. 5 is a first diagram showing an example of the inferior vena cava and abdominal aorta projected on an ultrasound image according to an embodiment. Fig. 6 is a second diagram showing an example of the inferior vena cava and abdominal aorta projected on an ultrasound image according to an embodiment. With reference to these diagrams, an example of a case where the inferior vena cava is projected on an ultrasound image as a blood vessel to be measured, and an example of a case where the abdominal aorta is projected on an ultrasound image as a blood vessel not to be measured will be described.
[0054] FIG. 5(A) shows an example of an ultrasound image in which the inferior vena cava is projected. FIG. 5(B) shows an example of an ultrasound image in which the abdominal aorta is projected. FIG. 6 shows an example of a detection result after object detection processing is performed by the detection unit 12 on the ultrasound images of FIG. 5(A) and FIG. 5(B). In FIG. 6(A), the outline of the liver (major-liver) and the outline of the inferior vena cava (major-ivc) are detected. The part detected as the liver and the part detected as the inferior vena cava are hatched for explanation. In FIG. 6(B), the outline of the liver (major-liver) and the outline of the abdominal aorta are detected. The part detected as the liver and the part detected as the abdominal aorta are hatched for explanation. As shown in the figure, the positional relationship between the liver and the inferior vena cava and the positional relationship between the liver and the abdominal aorta are different from each other. The detection unit 12 learns the positional relationship between the liver and the inferior vena cava or the abdominal aorta as a feature amount, and detects the type of blood vessel (inferior vena cava or abdominal aorta) with high accuracy.
[0055] Next, a modified example for measuring the inner diameter of a blood vessel with higher accuracy will be described with reference to Figs. 7 to 9. In the above-described embodiment, the inner diameter of the blood vessel is measured in the vertical direction of the ultrasound image. Here, the direction of the blood vessel is not necessarily displayed in the horizontal direction in the ultrasound image. For example, when the blood vessel is displayed tilted horizontally, if the inner diameter of the blood vessel is measured in the vertical direction of the ultrasound image, the measured diameter may be larger than the actual diameter. Therefore, in this modified example, the measurement direction is determined according to the tilt of the upper wall of the blood vessel and the tilt of the lower wall of the blood vessel. The detailed procedure will be described below.
[0056] FIG. 7 is a first diagram for explaining a case where the inner diameter of the inferior vena cava is measured based on the inclination of the region of interest in the measurement process according to the embodiment. In the figure, the parts of the ultrasound image other than the inferior vena cava are shown with hatching. The measurement unit 13 first determines the region of interest. In the figure, a specific point SP that is a point according to the position of the liver is shown. The specific point SP may be the center of gravity of the liver or a point a predetermined distance away from the left end of the liver. In addition, in the figure, for the purpose of explanation, a line extending vertically downward from the specific point SP is drawn as a line L1. The measurement unit 13 specifies, as a first region of interest ROI1, a region having a center at a point vertically below the specific point SP (a point on the line L1) and a center at a point intersecting with the upper wall of the blood vessel. In addition, the measurement unit 13 specifies, as a second region of interest ROI2, a region having a center at a point vertically below the specific point SP (a point on the line L1) and a center at a point intersecting with the lower wall of the blood vessel.
[0057] FIG. 8 is a second diagram for explaining a case where the inner diameter of the inferior vena cava is measured based on the inclination of the region of interest in the measurement process according to the embodiment. Next, the measurement unit 13 calculates the inclination of the upper wall in the first region of interest ROI1. FIG. 8(A) shows the inclination of the upper wall of the blood vessel inside the first region of interest ROI1. The inclination of the upper wall of the blood vessel is shown as line L21. The inclination of the line L21 can also be expressed as y1 / x1. Next, the measurement unit 13 calculates the inclination of the upper wall in the second region of interest ROI2. FIG. 8(B) shows the inclination of the upper wall of the blood vessel inside the second region of interest ROI2. The inclination of the lower wall of the blood vessel is shown as line L22. The inclination of the line L22 can also be expressed as y2 / x2.
[0058] FIG. 9 is a third diagram for explaining a case where the inner diameter of the inferior vena cava is measured based on the inclination of the region of interest in the measurement process according to the embodiment. Next, the measurement unit 13 calculates the inclination of the blood vessel based on the inclination of the upper wall calculated in the first region of interest ROI1 and the inclination of the lower wall calculated in the second region of interest ROI2. As an example, the measurement unit 13 calculates the average of the inclination of the upper wall calculated in the first region of interest ROI1 and the inclination of the lower wall calculated in the second region of interest ROI2 as the inclination of the blood vessel. In FIG. 9, a line having the calculated inclination of the blood vessel is shown as line L3. The inclination of line L3 can also be expressed as y3 / x3. Next, the measurement unit 13 specifies a line that intersects with line L1 perpendicularly to line L3 as the radial direction of the blood vessel. In the figure, the radial direction of the blood vessel is shown as line L4. The measuring unit 13 measures the distance from a point on the line L4 where it intersects with the upper wall of the blood vessel to a point on the line L4 where it intersects with the lower wall of the blood vessel as the inner diameter of the blood vessel.
[0059] In other words, the measurement unit 13 identifies an area of interest in each of the walls of the detected blood vessel contour, calculates the inclination of the blood vessel in each of the two identified areas of interest, and measures the line segment between the blood vessel contours that intersects perpendicularly to the average of the calculated blood vessel inclinations as the inner diameter of the blood vessel.
[0060] 10 is a flowchart showing an example of a series of operations of the measurement system 1 according to the embodiment, which will be described with reference to the drawing.
[0061] (Step S11) First, the image acquiring unit 11 of the measuring device 10 acquires an ultrasound image captured by the measuring probe 40. This process may be referred to as an acquiring process or an acquiring step.
[0062] (Step S12) Next, the detection unit 12 of the measuring device 10 detects objects such as organs or blood vessels included in the ultrasound image acquired by the image acquisition unit 11. The objects such as organs or blood vessels detected by the detection unit 12 include organs such as the liver, and blood vessels such as the inferior vena cava and abdominal aorta. This process may be referred to as a detection process or a detection step.
[0063] (Step S13) Next, if the measurement device 10 detects a blood vessel to be measured (for example, the inferior vena cava; IVC), the process proceeds to step S14. If the measurement device 10 does not detect a blood vessel to be measured, the process proceeds to step S15.
[0064] (Step S14) Next, the measurement unit 13 of the measurement device 10 measures the inner diameter of the blood vessel to be measured (e.g., the inferior vena cava; IVC). The measurement of the inner diameter may be performed using a measurement method as described with reference to Figs. 7 to 9. This process may be referred to as a measurement process or a measurement step.
[0065] (Step S15) If the blood vessel to be measured is not detected, the control device 20 of the measurement system 1 controls the driving device 30 to move the position of the measurement probe to a position where the blood vessel to be measured is displayed on the ultrasound image. The position where the blood vessel to be measured is displayed on the ultrasound image may be a position based on the contour of the detected organ and the contour of the blood vessel.
[0066] FIG. 11 is a block diagram showing an example of the internal configuration of the measuring device according to the embodiment. At least some of the functions of the measuring device 10 can be realized using a computer. As shown in the figure, the computer includes a central processing unit 901, a RAM 902, an input / output port 903, input / output devices 904 and 905, and a bus 906. The computer itself can be realized using existing technology. The central processing unit 901 executes instructions included in a program read from the RAM 902 or the like. The central processing unit 901 writes data to the RAM 902, reads data from the RAM 902, and performs arithmetic and logical operations according to each instruction. The RAM 902 stores data and programs. Each element included in the RAM 902 has an address and can be accessed using the address. Note that RAM is an abbreviation for "random access memory." The input / output port 903 is a port through which the central processing unit 901 exchanges data with an external input / output device or the like. The input / output devices 904 and 905 are input / output devices. Input / output devices 904 and 905 exchange data with the central processing unit 901 via an input / output port 903. A bus 906 is a common communication path used within the computer. For example, the central processing unit 901 reads and writes data from and to a RAM 902 via the bus 906. Also, for example, the central processing unit 901 accesses the input / output port via the bus 906.
[0067] [Summary of the embodiment] According to the above-described embodiment, the measuring device 10 includes the image acquisition unit 11, which acquires an ultrasound image in which the echo of the ultrasound output by the measuring probe 40 in contact with the animal to be measured is visualized, the detection unit 12 detects the contours of the animal's organs shown in the acquired ultrasound image and the contours of the blood vessels that fluctuate in synchronization with the organs, and the measuring unit 13 measures the inner diameter of the blood vessel based on the detected contours of the blood vessels. Here, when measuring the inner diameter of the inferior vena cava, a blood vessel such as the abdominal aorta may be mistakenly shown in the ultrasound image, and it is not easy even for a skilled technician to distinguish these blood vessels that are not the measurement target from the blood vessels that are the measurement target. According to this embodiment, for example, the inferior vena cava is a blood vessel that fluctuates in synchronization with the liver, and the position of the inferior vena cava that is the measurement target is detected. In addition, the inner diameter of the inferior vena cava is measured based on the detected position. Therefore, according to this embodiment, the blood vessel to be measured can be recognized as being distinguished from adjacent blood vessels, and the inner diameter of the blood vessel to be measured can be measured.
[0068] Moreover, according to the embodiment described above, the image acquisition unit 11 acquires multiple ultrasound images of the same measurement target at different times, and the measurement unit 13 measures the inner diameter of the blood vessel for each of the acquired multiple ultrasound images. Moreover, the measurement device 10 includes a calculation unit 15, which calculates the maximum and minimum values of the multiple measured inner diameters. That is, according to this embodiment, the measurement device 10 measures the inner diameter, maximum and minimum values of the blood vessel. Here, a single measurement based on one ultrasound image may cause variation in the measurement results. According to this embodiment, the inner diameter, maximum and minimum values of the blood vessel are measured, so that it is possible to provide measurement results with less variation.
[0069] Furthermore, according to the embodiment described above, the detection unit 12 detects blood vessels to be measured (e.g., the inferior vena cava) and blood vessels not to be measured (the abdominal aorta) by distinguishing between them, and the measurement unit 13 measures the inner diameter of the blood vessels to be measured and does not measure the inner diameter of the blood vessels not to be measured. That is, according to this embodiment, blood vessels not to be measured are also detected. Therefore, according to this embodiment, it is possible to accurately detect whether or not a blood vessel is to be measured.
[0070] According to the embodiment described above, the blood vessel to be measured is the inferior vena cava, and the blood vessel not to be measured is the abdominal aorta. Therefore, according to the embodiment, the inner diameter of the inferior vena cava, which is the measurement target, can be measured, and a situation in which the inner diameter of the abdominal aorta, which is not the measurement target, is erroneously measured can be prevented.
[0071] According to the embodiment described above, the detection unit 12 includes a trained model trained in advance by supervised learning using an ultrasound image, an outline of an animal's organ determined corresponding to the ultrasound image, and an outline of a blood vessel that changes in synchronization with the organ as teacher data. The trained model detects the outline of the animal's organ and the outline of a blood vessel that changes in synchronization with the organ based on the ultrasound image acquired by the image acquisition unit 11. That is, according to this embodiment, object detection is performed using a machine learning algorithm. Therefore, according to this embodiment, the blood vessel to be measured can be identified with high accuracy.
[0072] According to the embodiment described above, the trained model is trained in advance using an ultrasound image and the contour of a blood vessel that is not a measurement target, which is determined in correspondence with the ultrasound image, as training data, and detects the contour of the blood vessel that is not a measurement target based on the ultrasound image acquired by the acquisition unit. That is, according to this embodiment, the trained model is trained using training data for blood vessels that are not a measurement target. Therefore, according to this embodiment, it is possible to prevent a situation in which the inner diameter of a blood vessel that is not a measurement target is measured by mistake.
[0073] According to the embodiment described above, the trained model distinguishes between blood vessels to be measured and blood vessels not to be measured by using at least the thickness of the blood vessel wall and the distance from the animal's organs as feature quantities. Here, blood vessels such as the inferior vena cava and the abdominal aorta have different blood vessel wall thicknesses. Also, the distance from the inferior vena cava to the liver and the distance from the abdominal aorta to the liver are different from each other. Therefore, according to this embodiment, by using at least the thickness of the blood vessel wall and the distance from the animal's organs as feature quantities, the blood vessel to be measured can be accurately detected. Therefore, according to this embodiment, it is possible to prevent a situation in which the inner diameter of a blood vessel that is not a measurement target is measured by mistake.
[0074] Also, according to the embodiment described above, the measurement unit 13 measures the inner diameter of the blood vessel at a predetermined position specified based on the animal's organ. That is, the measurement unit 13 measures the inner diameter at the predetermined position in multiple measurements. Here, the measurement results of the inner diameter of the blood vessel may differ depending on the measurement location, and the measurement results may vary. According to this embodiment, it is also possible to follow and measure the same cross section of the blood vessel. Therefore, according to this embodiment, the variation in the measurement results can be reduced.
[0075] According to the embodiment described above, the measurement unit 13 specifies an area of interest in each of both walls of the contour of the detected blood vessel, calculates the inclination of the blood vessel in each of the two specified areas of interest, and measures the line segment between the contours of the blood vessel among the lines perpendicular to the average of the calculated inclinations of the blood vessel as the inner diameter of the blood vessel. That is, according to this embodiment, the inner diameter can be measured in a direction according to the inclination of the blood vessel. Here, the inclination of the upper wall and the inclination of the lower wall of the blood vessel may differ from each other. According to this embodiment, the inner diameter is measured according to the inclination of the upper wall and the inclination of the lower wall of the blood vessel. Therefore, according to this embodiment, the inner diameter of the blood vessel can be measured with high accuracy.
[0076] Furthermore, according to the embodiment described above, the measurement system 1 includes the measurement probe 40, which detects a signal to be measured from the animal to be measured, the drive unit 30, which moves the measurement probe 40 relative to the animal to be measured, and the control unit 20, which controls the drive unit 30 to move the measurement probe 40 to a position based on the detected outline of the animal's organ and the outline of the blood vessel. According to this embodiment, by adopting such a configuration, it is possible to follow and measure the same cross section of the blood vessel to be measured. Also, according to this embodiment, by following and measuring the same cross section of the blood vessel, it becomes possible to take appropriate measures for the cross section.
[0077] In addition, all or part of the functions of each unit of the measuring device 10 in the above-mentioned embodiment may be realized by recording a program for realizing these functions on a computer-readable recording medium, reading the program recorded on the recording medium into a computer system, and executing it. Note that the "computer system" referred to here includes hardware such as an OS and peripheral devices.
[0078] In addition, the term "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, and storage units such as hard disks built into computer systems. Furthermore, the term "computer-readable recording medium" may also include those that dynamically hold a program for a short period of time, such as a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line, and those that hold a program for a certain period of time, such as a volatile memory inside a computer system that serves as a server or client in such cases. Furthermore, the above program may be one that realizes part of the above-mentioned functions, or may be one that can realize the above-mentioned functions in combination with a program already recorded in the computer system.
[0079] The above describes an embodiment of the present invention with reference to the drawings. However, the specific configuration is not limited to the above-described embodiment, and design changes and the like are also included within the scope that does not deviate from the gist of the present invention. Furthermore, each of the above-described embodiments may be an independent embodiment, or any of the embodiments may be combined. [Explanation of symbols]
[0080] 1... measurement system, 10... measurement device, 20... control device, 30... drive device, 40... measurement probe, 60... examination table, 71... display device, 72... input device, S... subject, 11... image acquisition unit, 12... detection unit, 13... measurement unit, 14... storage unit, 15... calculation unit, 16... output unit
Claims
1. an acquisition unit that acquires an ultrasound image that visualizes the echo of ultrasound outputted by a measurement probe that is in contact with an animal to be measured; a detection unit that detects the contours of the organs of the animal projected in the acquired ultrasound image and the contours of blood vessels that fluctuate in synchronization with the organs; a measuring unit that measures an inner diameter of the blood vessel based on the detected contour of the blood vessel; A measuring device comprising:
2. The acquisition unit acquires a plurality of ultrasound images obtained by measuring a same measurement object at different times, The measurement unit measures an inner diameter of the blood vessel for each of the acquired multiple ultrasound images, The measuring device further includes a calculation unit that calculates a maximum value and a minimum value of the measured inner diameters.
2. The measuring device of claim 1.
3. The detection unit detects the blood vessels to be measured and blood vessels that are not to be measured, The measurement unit measures the inner diameter of the blood vessel that is the measurement target, and does not measure the inner diameter of the blood vessel that is not the measurement target. The measuring device according to claim 1 or 2.
4. The blood vessel to be measured is the inferior vena cava, The blood vessels not to be measured are the abdominal aorta, 4. The measuring device according to claim 3.
5. the detection unit includes a trained model that has been trained in advance by supervised learning using the ultrasound image, a contour of an organ of the animal determined in correspondence with the ultrasound image, and a contour of a blood vessel that varies in synchronization with the organ as training data; The trained model detects a contour of an organ of the animal and a contour of a blood vessel that varies in synchronization with the organ, based on the ultrasound image acquired by the acquisition unit. The measuring device according to claim 1 or 2.
6. The trained model is trained in advance using the ultrasound image and a contour of a blood vessel that is not a measurement target, which is determined in correspondence with the ultrasound image, as training data, and detects the contour of the blood vessel that is not a measurement target based on the ultrasound image acquired by the acquisition unit.
6. The measuring device according to claim 5.
7. The trained model distinguishes between blood vessels that are targets of measurement and blood vessels that are not targets of measurement, using at least the thickness of the blood vessel wall and the distance from the organ of the animal as features.
7. The measuring device according to claim 6.
8. The measurement unit measures an inner diameter of the blood vessel at a predetermined position identified based on an organ of the animal. The measuring device according to claim 1 or 2.
9. The measurement unit specifies a region of interest in each of both walls of the contour of the detected blood vessel, calculates the inclination of the blood vessel in each of the two specified regions of interest, and measures, as the inner diameter of the blood vessel, a line segment between the contours of the blood vessel among lines perpendicularly intersecting the average of the calculated inclinations of the blood vessel. The measuring device according to claim 1 or 2.
10. the measurement probe for detecting a signal to be measured from the animal to be measured; a drive device for moving the measurement probe relative to the animal to be measured; The measuring device according to claim 1 or 2, a control device that controls the drive device to move the measurement probe to a position based on the detected contour of the animal's organ and the contour of the blood vessel; A measurement system comprising:
11. an acquisition step of acquiring an ultrasound image that visualizes the echo of ultrasound outputted by a measurement probe contacted with an animal to be measured; a detection step of detecting the contour of an organ of the animal projected in the acquired ultrasound image and the contour of a blood vessel that fluctuates in synchronization with the organ; a measuring step of measuring an inner diameter of the blood vessel based on the detected contour of the blood vessel; A measurement method having the following characteristics.
12. On the computer, An acquisition step of acquiring an ultrasound image that visualizes the echo of ultrasound outputted by a measurement probe contacted with an animal to be measured; a detection step of detecting the contour of an organ of the animal projected in the acquired ultrasound image and the contour of a blood vessel that fluctuates in synchronization with the organ; a measuring step of measuring an inner diameter of the blood vessel based on the detected contour of the blood vessel; A program that executes the following.
Citation Information
Patent Citations
Ultrasound systems and methods for identifying blood vessels
JP2017524455A
In-vivo motion tracking device
JP2016158890A
