Bladder volume measuring system and bladder volume measuring method in system

Abstract

The present invention relates to a bladder volume measuring system and a bladder volume measuring method. The bladder volume measuring method comprises steps of: calculating a probability value indicating whether a corresponding unit region of respective unit regions constituting an ultrasound image is included in a region of interest, by using a preset region of interest extraction algorithm; obtaining a weight for the probability value for each unit region constituting the ultrasound image, by using a preset weighting function; and calculating and providing an area or a volume for the region of interest by using the probability values and the weights for all the unit regions constituting the ultrasound image.

Description

Bladder volume measurement system and bladder volume measurement method in the system

[0001] The present invention relates to a bladder volume measurement system, and more particularly, to a bladder volume measurement system configured to measure bladder volume more accurately by extracting a bladder region from an ultrasound image using a region of interest extraction algorithm and measuring the bladder volume using a probability value for each pixel of the ultrasound image obtained as a result of the extraction and a weight by a preset weighting function, and a bladder volume measurement method in the system.

[0002] This invention was supported by the Korea Medical Device Research and Development Institute funded by the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health and Welfare, and the Ministry of Food and Drug Safety of the Republic of Korea (Project No. 1711194192, RS-2020-KD000043).

[0003] In general, an ultrasound system is a system that examines the internal state of an object by emitting an ultrasound signal to the object to be inspected by using the piezoelectric effect of a transducer, and then receiving the ultrasound signal that is reflected from the discontinuous surface of the object and returning, and then converting the received ultrasound signal into an electrical signal and outputting it to a predetermined imaging device. These ultrasound systems are widely used for medical diagnosis, non-destructive testing, underwater exploration devices, etc. In particular, a technology is widely used to extract a region of interest, such as a specific organ or lesion, from a medical image acquired using an ultrasound system, and to measure the size of the extracted region of interest to determine or diagnose the patient's condition.

[0004] Meanwhile, measuring bladder urine volume is an essential element in examining bladder abnormalities or urinary incontinence. Furthermore, to prevent urinary retention that may occur after surgery, bladder urine volume is measured prior to catheterization. It is also used as a guideline for voiding training. The volume of urine filled in the bladder is equal to the volume of the bladder. Therefore, bladder urine volume can be determined by measuring bladder volume. Furthermore, an ultrasound scanner can be used to measure bladder volume.

[0005] In this way, an ultrasound scanner for measuring the amount of urine in a bladder acquires ultrasound signals for sector-shaped scan planes including the bladder, acquires two-dimensional or three-dimensional ultrasound images from the ultrasound signals for the scan planes, extracts a bladder region as a region of interest from the ultrasound images, calculates the area or volume of the bladder using information about the extracted bladder regions, and estimates the amount of urine in the bladder using this. Fig. 1 is an example of a bladder volume measurement system using an ultrasound scanner, and Fig. 2 is an example of a two-dimensional ultrasound image acquired using the bladder volume measurement system of Fig. 1.

[0006] Various extraction algorithms have been proposed for extracting the bladder region of interest (ROI) from 2D or 3D ultrasound images. These algorithms utilize artificial intelligence models and machine learning algorithms, or analyze the amplitude or intensity of ultrasound signals to extract the desired ROI.

[0007] However, dedicated ultrasound scanners for bladder volume measurement are manufactured as compact and portable devices that can be easily transported, resulting in low-resolution ultrasound images. Consequently, the images acquired by ultrasound scanners for bladder volume measurement have significant pixel or voxel sizes due to their low resolution. This not only causes a partial volume effect but also causes the boundaries of regions of interest or lesions to become ambiguous. Furthermore, ultrasound scanners used to acquire medical images generate a significant amount of noise and artifacts. Consequently, it is generally difficult to accurately extract regions of interest from low-resolution ultrasound medical images. Furthermore, these issues also make it difficult to accurately measure the area or volume of the bladder from regions of interest extracted from ultrasound images.

[0008] Meanwhile, when using a machine learning algorithm among the aforementioned region of interest extraction algorithms, each pixel in the ultrasound image or each preset unit region is provided in the form of a probability value that it will be included in the region of interest. Then, by binarizing the probability value according to the extraction algorithm, the region of interest is finally extracted from the ultrasound image. Even if the result is not given as a probability depending on the extraction algorithm, the size of the pixel value is used during the calculation process. Even in this case, if the size is normalized to the largest pixel value, it can be regarded as a type of probability value.

[0009] FIG. 3 (a) is a two-dimensional ultrasound image obtained using a bladder volume measurement system, (b) displays some of the probability values ​​output for each pixel of the two-dimensional ultrasound image of (a) using a machine learning algorithm, (c) converts the probability values ​​of (b) into pixel values, and (d) is an image reconstructed using the pixel values ​​of (c). As shown in FIG. 3 (b), the output probability values ​​have a value between 0.0 and 1.0, and when the probability is 1.0, it means that the probability that the corresponding pixel is a bladder is 100%. FIG. 3 (d) is an image reconstructed by converting the probability values ​​of 0.0 to 1.0 for each pixel of the ultrasound image shown in (a) into pixel values ​​of 0 to 255.

[0010] In order to obtain the area or volume of the bladder, which is a region of interest, from an ultrasound image, a conventional general technique detects a boundary from an image such as (a) of Fig. 4 and uses a binarization method. The binarization method separates the region of interest from the background region using a preset threshold. Fig. 4 (a) is a 2D ultrasound image, (b) is an image reconstructed with the probability values ​​output by the extraction algorithm, (c) is an image binarized by setting the threshold to 0.5, and (d) is an image binarized by setting the threshold to 0.4. In Fig. 4 (c), the number of pixels above the threshold is 2554, and in Fig. 4 (d), the number of pixels above the threshold is 2661. As illustrated in Fig. 4, the boundary position of the region of interest changes depending on the threshold, and the extracted region of interest also changes, so the area or volume of the region of interest calculated using this also changes. That is, when using a binarization method, the area or volume of the region of interest changes very sensitively depending on the threshold value set for binarization, so the setting of the threshold value has a great impact on the reliability of the final result value obtained.

[0011] In order to solve the above-mentioned problem, the purpose of the present invention is to provide a bladder volume measurement system and a bladder volume measurement method configured to accurately measure the area or volume of the region of interest by applying a region of interest extraction algorithm to an ultrasound image to extract the region of interest, and using a probability value for each pixel output as a result of the extraction and a weight by a preset weighting function according to the distribution of the probability value.

[0012] According to a first aspect of the present invention for achieving the above-described technical problem, a bladder volume measurement system comprises: an ultrasonic probe configured to receive ultrasonic signals for obtaining an ultrasonic image using an ultrasonic transducer; and a control unit configured to measure and provide an area or volume for a region of interest included in the ultrasonic signals received from the ultrasonic probe; wherein the control unit generates an ultrasonic image using the ultrasonic signals received from the ultrasonic probe, infers a probability value that each unit region constituting the ultrasonic image is included in the region of interest using a preset region of interest extraction algorithm, obtains a weight value using a preset weighting function according to a distribution of the probability value, and then calculates and provides an area or volume for the region of interest using the probability values ​​and weights for all unit regions constituting the ultrasonic image.

[0013] In the bladder volume measurement system according to the first aspect described above, it is preferable that the control unit obtains weights for unit regions constituting the ultrasound image using the weighting function, multiplies the unit area or unit volume of each unit region constituting the ultrasound image by the weight of the corresponding unit region to obtain a weighted area or weighted volume of each unit region, and calculates the area or volume for the region of interest by adding up the weighted areas or weighted volumes of all unit regions constituting the ultrasound image.

[0014] In the bladder volume measurement system according to the first aspect described above, it is preferable that the weighting function be a function having a first threshold and a second threshold, assigning a preset minimum weight to a probability value smaller than the first threshold, assigning a preset maximum weight to a probability value larger than the second threshold, and linearly or nonlinearly assigning weights to probability values ​​between the first threshold and the second threshold within the range of the minimum weight and the maximum weight.

[0015] In the bladder volume measurement system according to the first aspect described above, it is preferable that the minimum weight is '0' and the maximum weight is '1'.

[0016] A bladder volume measurement method according to a second aspect of the present invention is a bladder volume measurement method performed by a control unit of a bladder volume measurement system that measures and provides a bladder volume using an ultrasonic signal, comprising: (a) generating an ultrasound image using ultrasonic signals received from an ultrasound probe; (b) inferring a probability value that each unit region constituting the ultrasound image is included in a region of interest using a preset region of interest extraction algorithm; (c) obtaining weights for each unit region constituting the ultrasound image using a preset weighting function, and then calculating and providing an area or volume for the region of interest using the probability values ​​and weights for all unit regions constituting the ultrasound image.

[0017] In the bladder volume measurement method according to the second aspect described above, it is preferable that the step (c) comprises: (c1) a step of obtaining weights for unit regions constituting the ultrasound image using the weighting function; (c2) a step of obtaining a weighted area or weighted volume of each unit region by multiplying the unit area or unit volume of each unit region constituting the ultrasound image by the weight of the corresponding unit region; and (c3) a step of calculating an area or volume for a region of interest by adding up the weighted areas or weighted volumes of all unit regions constituting the ultrasound image.

[0018] In the bladder volume measurement method according to the second aspect described above, it is preferable that the weighting function be a function having a first threshold value and a second threshold value, assigning a preset minimum weight to a probability value smaller than the first threshold value, assigning a preset maximum weight to a probability value larger than the second threshold value, and linearly or nonlinearly assigning weights to probability values ​​between the first threshold value and the second threshold value within the range of the minimum weight and the maximum weight.

[0019] A bladder volume measurement system according to a third aspect of the present invention comprises: an ultrasonic probe configured to receive ultrasonic signals for obtaining an ultrasonic image using an ultrasonic transducer; and a control unit configured to measure and provide an area for a region of interest included in the ultrasonic signals received from the ultrasonic probe; wherein the control unit analyzes the ultrasonic signals received from the ultrasonic probe to detect an anterior wall point and a posterior wall point of the bladder, sets an anterior wall boundary area including a preset anterior and posterior area of ​​the anterior wall point of the bladder, sets a posterior wall boundary area including a preset anterior and posterior area of ​​the posterior wall point of the bladder, sets a weight for each position of the ultrasonic signal based on the anterior wall boundary area and the posterior wall boundary area, and calculates and provides an area or volume for the bladder region using the weights for each position of the ultrasonic signal.

[0020] In the bladder volume measurement system according to the third aspect described above, it is preferable that the control unit sets a weight for a position prior to the start point of the front wall boundary region to a preset minimum weight, sets a weight for each position of the front wall boundary region based on the difference in the intensity of the ultrasonic signal between the start point and the end point of the front wall boundary region, sets a weight for each position between the front wall boundary region and the back wall boundary region to a preset maximum weight, sets a weight for each position of the back wall boundary region based on the difference in the intensity of the ultrasonic signal between the start point and the end point of the back wall boundary region, and sets a weight for a position subsequent to the end point of the back wall boundary region to a preset minimum weight.

[0021] A bladder volume measurement method according to a fourth aspect of the present invention is a bladder volume measurement method performed by a control unit of a bladder volume measurement system that measures and provides a bladder volume using an ultrasonic signal, comprising: (a) analyzing an ultrasonic signal received from an ultrasonic probe to detect an anterior wall point and a posterior wall point of the bladder; (b) setting an anterior wall boundary area including a preset anterior and posterior area of ​​the anterior wall point of the bladder, and setting a posterior wall boundary area including a preset anterior and posterior area of ​​the posterior wall point of the bladder; (c) setting a weight for each position of the ultrasonic signal based on the anterior wall boundary area and the posterior wall boundary area; (d) calculating and providing an area or volume for a bladder area using the weight for each position of the ultrasonic signal.

[0022] In the bladder volume measuring method according to the fourth aspect described above, it is preferable that step (c) comprises: (c1) a step of setting a weight for a position prior to the start point of the anterior wall boundary region to a preset minimum weight; (c2) a step of setting a weight for each position of the anterior wall boundary region based on the difference in the intensity of the ultrasound signal between the start point and the end point of the anterior wall boundary region; (c3) a step of setting a weight for each position between the anterior wall boundary region and the back wall boundary region to a preset maximum weight; (c4) a step of setting a weight for each position of the back wall boundary region based on the difference in the intensity of the ultrasound signal between the start point and the end point of the back wall boundary region; (c5) a step of setting a weight for a position subsequent to the end point of the back wall boundary region to a preset minimum weight.

[0023] The bladder volume measurement system according to the present invention measures the area or volume of the region of interest using probability values ​​and weights for all pixels constituting the ultrasound image in the final step of extracting the region of interest from the ultrasound image using a region of interest extraction algorithm. In this way, the bladder volume measurement system according to the present invention measures the area or volume of the region of interest using probability values ​​and weights for all pixels constituting the ultrasound image without performing binarization, thereby reducing the sensitivity according to threshold setting and improving the accuracy of the measurement.

[0024] Fig. 1 is an example of a bladder volume measurement system using an ultrasound scanner, and Fig. 2 is a two-dimensional ultrasound image obtained using the bladder volume measurement system of Fig. 1.

[0025] Figure 3 (a) is a two-dimensional ultrasound image obtained using a bladder volume measurement system, (b) displays some of the probability values ​​output for each pixel of the two-dimensional ultrasound image of (a) using a machine learning algorithm, (c) displays some of the probability values ​​of (b) converted into pixel values, and (d) is an image reconstructed using the pixel values ​​of (c).

[0026] Figure 4 (a) is a two-dimensional ultrasound image, (b) is an image reconstructed with probability values ​​output by an extraction algorithm, (c) is an image binarized by setting the threshold to 0.5, and (d) is an image binarized by setting the threshold to 0.4.

[0027] FIG. 5 is a flowchart sequentially illustrating a method for a control unit to measure the area or volume of a bladder, which is a region of interest, in a bladder volume measurement system according to a first embodiment of the present invention.

[0028] FIG. 6 is a graph exemplarily showing a weighting function having a first threshold value and a second threshold value in a bladder volume measurement system according to a first embodiment of the present invention.

[0029] Figure 7 shows a geometric model for one pixel or voxel obtained from a bladder volume measurement system.

[0030] FIG. 8 is a graph illustrating a bladder area for a single ultrasonic reception signal in a bladder volume measurement system according to a second embodiment of the present invention.

[0031] Hereinafter, with reference to the attached drawings, a bladder volume measurement system and a bladder volume measurement method in the system according to a preferred embodiment of the present invention will be described in detail.

[0032] <Example 1>

[0033] A bladder volume measurement system according to a first embodiment of the present invention comprises an ultrasonic probe configured to transmit and receive ultrasonic signals for obtaining an ultrasonic image using an ultrasonic transducer, and a control unit configured to measure and provide a size of a region of interest included in ultrasonic signals received from the ultrasonic probe. The region of interest measured by the control unit of the bladder volume measurement system according to the present invention means a bladder, and the volume of the bladder extracted from the ultrasonic signal and measured represents the amount of urine filled in the bladder.

[0034] The above ultrasonic probe may be configured with a plurality of transducers in an array form inside, or may be configured with one or more transducers and motors for rotating the transducers along a scan plane. That is, a plurality of transducers are arranged at preset intervals and ultrasonic signals are sequentially acquired from each transducer, or ultrasonic signals are acquired by sequentially rotating the transducers by a preset angle using a motor. In general, an ultrasonic transducer injects ultrasonic signals into an inspection object, and the injected ultrasonic signals are reflected from the inspection object. Then, the ultrasonic probe acquires ultrasonic signals reflected from the inspection object and provides them to the control unit.

[0035] Hereinafter, a method by which a control unit of a bladder volume measurement system according to a first embodiment of the present invention measures and provides a size of a region of interest included in ultrasonic signals received from an ultrasonic probe will be described in more detail. FIG. 5 is a flowchart sequentially illustrating a method by which a control unit measures an area or volume of a region of interest in a bladder volume measurement system according to the first embodiment of the present invention.

[0036] Referring to FIG. 5, the control unit generates a fan-shaped two-dimensional ultrasound image using ultrasonic signals received from the ultrasonic probe (step 500).

[0037] Next, using a region of interest extraction algorithm, such as a machine learning algorithm, a probability value of each unit region constituting the ultrasound image being included in the region of interest is obtained (step 510). Here, the unit region may be composed of one or more pixels of the ultrasound image, or may be composed of one or more voxels.

[0038] There are various methods for extracting region of interest (ROI). These include: Threshold Method, which divides an image into foreground and background based on a single threshold; Edge Detection Method, which classifies edge pixels in the image and selects them for a separate class based on edge pixels; Clustering Based Method, which starts with sheet pixels and then expands the region centered around those pixels based on similarity criteria; and Deep Learning Based Method, which uses machine learning algorithms to learn the characteristics of objects in the image and then uses the algorithm to classify the segments as objects or background.

[0039] In general, the output of the aforementioned extraction algorithm is given as a probability value indicating the likelihood that the pixel or unit area is included in the region of interest. For example, if the pixel is very likely to be the region of interest, the probability will be a large value close to 1, and if it is very likely that the pixel is not the region of interest but the background, the probability will be a small value close to 0. In particular, since pixels near the border of the region of interest have both the possibility of being the region of interest and the possibility of being the background area, the probability value will be a value between 0 and 1, around 0.5. If the output of the region of interest extraction algorithm is not given as a probability value, each output value can be converted into a probability value by normalizing it to the largest value among the output values.

[0040] Next, in order to obtain a weight for each probability value, a preset weighting function is used to obtain a weight (w) for the probability value (p) for the unit areas constituting the ultrasound image (step 520). Here, the weighting function is characterized by being a function that has a first threshold value (t1) and a second threshold value (t2), and assigns a preset minimum weight to a probability value (p) smaller than the first threshold value, assigns a preset maximum weight to a probability value larger than the second threshold value, and linearly or nonlinearly assigns weights to probability values ​​between the first threshold value and the second threshold value within the range of the minimum weight and the maximum weight. The minimum weight may be set to '0', and the maximum weight may be set to '1'.

[0041] Here, the first threshold and the second threshold are values ​​that take into account system characteristics including noise, artifacts, etc., and pixels having a probability value lower than the first threshold are considered as background areas, and pixels having a probability value higher than the second threshold are considered as areas of interest. Fig. 6 is a graph exemplarily showing a weighting function having a first threshold (Th1) and a second threshold (Th2) in a bladder volume measurement system according to the first embodiment of the present invention.

[0042] An example of the above weighting function can be expressed by the mathematical expression 1 below.

[0043]

[0044] In Equation 1, the weights are derived using a linear equation, but this is merely an example. Therefore, depending on system performance, various modified mathematical equations other than the linear equation can be used.

[0045] Next, the unit area or unit volume of each unit area is multiplied by the weight (w) for the unit areas to obtain the weighted area or weighted volume for each unit area (step 530).

[0046] Figure 7 shows a geometric model for one pixel obtained in a bladder volume measurement system. Point O is the location of the ultrasound transducer of the bladder scanner, and point X is the pixel center of the obtained ultrasound image of the bladder scanner. One pixel in the image of the ultrasound bladder scanner becomes one voxel indicated by the thick line in the figure. Here, p is the pixel size in the depth direction, and d is the length from point O to the pixel center X. Δφ is the angle between the ultrasound cross-sectional images obtained from the bladder scanner, and θ1 and θ2 are the scan angles of the ultrasound scan line of the bladder volume measurement system. The volume ΔV' of this pixel (voxel) can be calculated using mathematical equation 2 for calculating the volume of a rectangular pyramid.

[0047]

[0048] In the proposed method, the weighted volume ΔV of this voxel is obtained by multiplying this volume ΔV' by the weight (w) calculated above.

[0049]

[0050] Next, the weighted areas or weighted volumes for each unit area are added together to finally calculate the total area or total volume for the area of ​​interest (step 540).

[0051] Although the first and second thresholds set in this embodiment affect the calculation of the area or volume of the region of interest, the sensitivity to the threshold is much lower compared to the conventional technique of separating the background region and the region of interest by a binarization method. This is because the method according to this embodiment applies weights to the probability values ​​of unit areas on the border between the background region and the region of interest in consideration of the distance from the center of the region of interest, etc. when calculating the area or volume of the region of interest. Therefore, in the bladder volume measurement method according to this embodiment, even if the first and second thresholds of the weighting function are slightly changed, the final result value does not change significantly.

[0052] However, when using a binarization method according to a conventional technique, since a single threshold value is used to separate the region of interest and the background region, the final result for calculating the total area or total volume is very sensitive to the threshold value. For example, in a conventional technique using a binarization method, when the threshold value is set to 0.5, a pixel with a probability value of 0.51 is included in the region of interest and is weighted as 1 to be included 100%, but a pixel with a probability value of 0.49 is weighted as 0 and is not reflected at all. However, in the present embodiment, all pixels with probability values ​​of 0.51 and 0.49 are weighted and included in the calculation of the area or volume, so that pixels on the ambiguous boundary between the region of interest and the background region can also be reflected in the calculation.

[0053] In accordance with the present invention, the performance of a method for calculating a volume using probability values ​​and weights for all pixels and a method for calculating a volume using binarization according to a conventional technique will be examined. To compare the performance of the method according to the present invention and the method according to the conventional technique, the ultrasound image of Fig. 2 is used. The volume of the bladder, which is a region of interest, was calculated using the method according to the present invention and the method according to the conventional technique using 12 ultrasound images including the image illustrated in Fig. 2, and the results are as shown in the table below.

[0054]

[0055] Here, the conventional method obtained the volume by setting the thresholds to 0.4 and 0.5, respectively. When the threshold is set to 0.5, the volume is 161 ml, and when the threshold is set to 0.4, the volume is 176 ml, so the difference is 16 ml, or 9.1%. However, in the method according to the present invention, when the first and second thresholds are set to 0.1 and 0.9, respectively, the volume is 170 ml, and when the first and second thresholds are set to 0.15 and 0.85, respectively, the volume is 169 ml, so the difference is 1 ml, or 0.6%. Through these measurements, it can be confirmed that the conventional technology using the binarization method has a very high sensitivity to threshold setting, which makes it highly likely that errors will occur, whereas the method according to the present invention has almost no sensitivity to threshold setting and has high reliability.

[0056] <Example 2>

[0057] Hereinafter, a bladder volume measurement system according to a second embodiment of the present invention will be described in detail. The bladder volume measurement system according to the second embodiment of the present invention has the same structure as the bladder volume measurement system according to the first embodiment described above, but the region of interest extraction algorithm used by the control unit is different. Therefore, a bladder volume measurement method performed by the control unit of the bladder volume measurement system according to the second embodiment of the present invention will be described in more detail.

[0058] A bladder volume measurement method according to a second embodiment is characterized by analyzing an ultrasound signal to detect an anterior wall point and a posterior wall point of the bladder, and applying a weight to the surrounding area to measure the volume of the bladder area. Conventional techniques analyze the intensity of ultrasound signals to detect the anterior and posterior wall positions of the bladder, regard the entire area between the detected anterior and posterior wall positions of the bladder as the bladder area, and regard the other area as a background area to measure the size of the bladder. However, when detecting the anterior and posterior wall positions according to such conventional techniques, the anterior and posterior wall positions may change very sensitively depending on the threshold value, and as a result, the bladder volume measurement may also change very sensitively. Considering these problems, the bladder volume measurement method in the bladder volume measurement system according to the present embodiment is characterized by analyzing the intensity of an ultrasound signal to detect an anterior wall point and a posterior wall point of the bladder, setting an anterior wall boundary area and a posterior wall boundary area for the surrounding areas of the anterior wall point and the posterior wall point, and applying a weight to each position of the anterior wall boundary area and the posterior wall boundary area to measure the volume of the bladder area.

[0059] Hereinafter, a bladder volume measurement method in a bladder volume measurement system according to a second embodiment of the present invention will be described in more detail. FIG. 8 is a graph illustrating a bladder area for a single ultrasonic reception signal in a bladder volume measurement system according to a second embodiment of the present invention.

[0060] First, using the ultrasound signal intensity, the anterior wall point (FWP) and the posterior wall point (BWP) of the bladder are detected.

[0061] Next, the anterior wall boundary area of ​​the bladder is set including the preset anterior and posterior sections (P1 to P2) based on the anterior wall point (FWP) of the bladder, and the posterior wall boundary area of ​​the bladder is set including the preset anterior and posterior sections (P3 to P4) based on the posterior wall point (BWP) of the bladder.

[0062] Next, based on the front wall boundary area and the back wall boundary area, a weight (w) is set for each position (p) of the ultrasonic signal. One embodiment of a method for setting a weight for each position is as follows.

[0063] The previous position ( p < P1 ) of the starting point of the front wall boundary area sets the weight (w) to the minimum weight. Here, the minimum weight can be set to '0' (w = 0).

[0064] For each position (P1 < p < P2) of the front wall boundary region, a weight (w) is set for each position of the front wall boundary region based on the difference in ultrasonic signal intensity (S1, S2) between the start point (P1) and the end point (P2) of the front wall boundary region according to mathematical expression 4.

[0065]

[0066] Each position (P2 < p < P3) between the front wall boundary area and the back wall boundary area sets the weight (w) to the maximum weight. Here, the maximum weight can be set to '1' (w=1).

[0067] For each position (P3 < p < P4) of the back wall boundary region, a weight (w) is set for each position of the back wall boundary region based on the difference in ultrasonic signal intensity (S3, S4) between the start point (P3) and the end point (P4) of the back wall boundary region according to mathematical expression 5.

[0068]

[0069] The position (p > P4) after the end point (P4) of the back wall boundary area sets the weight (w) to the minimum weight. Here, the minimum weight can be set to '0' (w=0).

[0070] The weights for each location can be set through the process described above.

[0071] Based on the detection of the front and back walls of the bladder from the ultrasound signal and the weight information of the adjacent area, the volume can be calculated in the same manner as in Fig. 7 by adding information on multiple ultrasound scan lines forming a cross-section and information on multiple cross-sections.

[0072] While the present invention has been described above with reference to preferred embodiments thereof, these are merely illustrative and not limiting. Those skilled in the art will appreciate that various modifications and applications not exemplified above are possible without departing from the essential characteristics of the present invention. Furthermore, any differences related to such modifications and applications should be construed as being within the scope of the present invention as defined in the appended claims.

Claims

1. An ultrasonic probe configured to receive ultrasonic signals for obtaining an ultrasonic image using an ultrasonic transducer; and A control unit for measuring and providing an area of ​​a region of interest included in ultrasonic signals received from the ultrasonic probe; The above control unit, Generating an ultrasound image using ultrasound signals received from the above ultrasound probe, Using a preset region of interest extraction algorithm, for each unit region constituting the ultrasound image, a probability value that the unit region is included in the region of interest is inferred, A bladder volume measurement system characterized in that it calculates and provides an area or volume for the region of interest by using a weighting function preset according to the distribution of probability values ​​and the probability values ​​and weights for all unit regions constituting the ultrasound image.

2. In the first paragraph, the control unit Using the above weighting function, weights are calculated for the probability values ​​for the unit areas constituting the ultrasound image, The weighted area or weighted volume of each unit area is obtained by multiplying the unit area or unit volume of each unit area constituting the ultrasound image by the weight of the unit area. A bladder volume measurement system characterized in that the area or volume for a region of interest is calculated by adding the weighted areas or weighted volumes of all unit regions constituting the ultrasound image.

3. In the first paragraph, the weighting function is It has a first threshold value and a second threshold value, A preset minimum weight is given to probability values ​​less than the first threshold, A preset maximum weight is given to probability values ​​greater than the second threshold, A bladder volume measurement system characterized in that the probability value between the first threshold value and the second threshold value is a function that linearly or nonlinearly assigns weights within the minimum weight range and the maximum weight range.

4. A bladder volume measurement system, characterized in that in the third paragraph, the minimum weight is '0' and the maximum weight is '1'.

5. In the first paragraph, the region of interest extraction algorithm, A bladder volume measurement system characterized by extracting a region of interest from an ultrasound image using a machine learning algorithm.

6. In a bladder volume measurement method performed by a control unit of a bladder volume measurement system that measures and provides the volume of the bladder using an ultrasonic signal, (a) a step of generating an ultrasound image using ultrasound signals received from an ultrasound probe; (b) a step of inferring a probability value that each unit area constituting the ultrasound image is included in the region of interest using a preset region of interest extraction algorithm; (c) a step of calculating weights using a preset weighting function according to the distribution of probability values ​​for each unit area, and then calculating and providing an area or volume for the area of ​​interest using the probability values ​​and weights for all unit areas constituting the ultrasound image; A method for measuring bladder volume, characterized by comprising:

7. In paragraph 6, step (c) is, (c1) A step of obtaining weights of probability values ​​for unit areas constituting the ultrasound image using the weighting function; (c2) A step of multiplying the unit area or unit volume of each unit area constituting the ultrasound image by the weight of the unit area to obtain the weighted area or weighted volume of each unit area; (c3) A step of calculating the area or volume for the region of interest by adding the weighted areas or weighted volumes of all unit regions constituting the ultrasound image; A method for measuring bladder volume, characterized by comprising:

8. In the 6th paragraph, the weighting function is It has a first threshold value and a second threshold value, A preset minimum weight is given to probability values ​​less than the first threshold, A preset maximum weight is given to probability values ​​greater than the second threshold, A bladder volume measurement method characterized in that the probability value between the first threshold value and the second threshold value is a function that linearly or nonlinearly assigns weights within the minimum weight range and the maximum weight range.

9. An ultrasonic probe configured to receive ultrasonic signals for obtaining an ultrasonic image using an ultrasonic transducer; and A control unit for measuring and providing an area of ​​a region of interest included in ultrasonic signals received from the ultrasonic probe; The above control unit, By analyzing the ultrasound signal received from the above ultrasound probe, the anterior wall point and the posterior wall point of the bladder are detected, Set an anterior wall boundary area including a preset anterior and posterior area of ​​a point on the anterior wall of the bladder, and set a posterior wall boundary area including a preset anterior and posterior area of ​​a point on the posterior wall of the bladder. Based on the front wall boundary area and the back wall boundary area, a weight is set for each location of the ultrasonic signal, A bladder volume measurement system characterized in that it calculates and provides an area or volume for a bladder region using weights for each location of an ultrasound signal.

10. In the 9th paragraph, the control unit The weight for the previous position of the starting point of the front wall boundary area is set to the preset minimum weight, The weight for each location in the front wall boundary area is set based on the difference in ultrasonic signal intensity between the start and end points of the front wall boundary area. The weight for each position between the front wall boundary area and the back wall boundary area is set to the preset maximum weight, The weight for each position in the back wall boundary area is set based on the difference in ultrasonic signal intensity between the start and end points of the back wall boundary area. A bladder volume measurement system characterized in that the weight for the subsequent position of the end point of the back wall boundary area is set to the minimum weight.

11. In paragraph 9, the region of interest extraction algorithm, A bladder volume measurement system characterized by extracting a region of interest from an ultrasound image using a machine learning algorithm.

12. A bladder volume measurement method performed by a control unit of a bladder volume measurement system that measures and provides the volume of the bladder using an ultrasonic signal, (a) a step of analyzing an ultrasound signal received from an ultrasound probe to detect an anterior wall point and a posterior wall point of the bladder; (b) a step of setting an anterior wall boundary region including a preset anterior and posterior region of a point on the anterior wall of the bladder, and setting a posterior wall boundary region including a preset anterior and posterior region of a point on the posterior wall of the bladder; (c) a step of setting a weight for each location of the ultrasonic signal based on the front wall boundary area and the back wall boundary area; (d) a step of calculating and providing an area or volume for the bladder region using weights for each location of the ultrasound signal; A method for measuring bladder volume, characterized by comprising:

13. In paragraph 12, step (c) is, (c1) A step of setting the weight for the previous position of the starting point of the front wall boundary area to a preset minimum weight; (c2) A step of setting a weight for each position of the front wall boundary area based on the difference in ultrasonic signal intensity between the start point and the end point of the front wall boundary area; (c3) A step of setting the weight for each position between the front wall boundary area and the back wall boundary area to a preset maximum weight; (c4) A step of setting the weight for each position of the back wall boundary area based on the difference in the ultrasonic signal intensity between the start point and the end point of the back wall boundary area; (c5) A step of setting the weight for the subsequent position of the end point of the back wall boundary area to the minimum weight; A method for measuring bladder volume, characterized by comprising:

Images