Ultrasonic diagnostic apparatus
Through learning models, the image quality adjustment parameters in specific areas of ultrasonic tomography images are determined, which solves the problem of inadequate image quality adjustment in various regions in the prior art, realizes the adaptive processing of ultrasonic tomography images, and improves the image quality and diagnosis. Effect.
Patent Information
- Application Number
- CN202410561063.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-05-26
- Filing Date
- 2024-05-08
- Publication Date
- 2024-12-03
AI Technical Summary
When the existing ultrasonic diagnostic devices form ultrasonic tomographic images, it is difficult to adaptive image quality adjustments according to the characteristics of different regions, resulting in the contrast and spatial resolution not meeting the needs of each organ.
The learning model is used to determine the image quality adjustment parameters in a specific area. By training the model, the image quality adjustment parameters are output to output appropriate image adjustment parameters, and the image quality adjustment processing of different areas is performed in the signal processing and image forming section. Ensure that the picture quality of each area meets specific needs.
The adaptive image quality adjustment of ultrasonic tomography images in each area is realized, the contrast and spatial resolution of the image are improved, and the accuracy and visibility of diagnosis are enhanced.
Smart Images

Figure CN119055276A_ABST
Abstract
Description
Technical Field
[0001] This specification discloses an improvement in an ultrasonic diagnostic device. Background Art
[0002] Conventionally, there is known an ultrasonic diagnostic apparatus that transmits and receives ultrasonic waves toward a subject, forms an ultrasonic tomographic image based on the received signals obtained thereby, and displays the formed ultrasonic tomographic image (i.e., B-mode image) on a display. Conventionally, a technology for improving the image quality of ultrasonic tomographic images in ultrasonic diagnostic apparatuses has been proposed.
[0003] For example, Patent Document 1 discloses an ultrasonic diagnostic apparatus capable of automatically applying appropriate image quality improvement processing based on changes in the signal amount of a subject. In the ultrasonic diagnostic apparatus, the signal-to-noise ratio (S / N ratio) is improved in particular according to the depth-dependent changes in the echo signal from the subject. Also, Patent Document 2 discloses an ultrasonic imaging system that takes channel data or beamforming data from an ultrasonic probe as input, uses the output of a neural network trained to form an ultrasonic tomographic image, and adjusts the ultrasonic tomographic image formed according to the beamforming data. Also, Patent Document 3 discloses a medical image processing apparatus that cuts out different image areas from a plurality of medical images having different noise levels, and synthesizes the plurality of image areas to obtain a high-quality medical image.
[0004] Patent Document 1: Japanese Patent Application Publication No. 2020-114294
[0005] Patent Document 2: Japanese Patent Application No. 2020-503142
[0006] Patent Document 3: Japanese Patent Application Publication No. 2022-6869
[0007] Before forming an ultrasonic tomographic image, various processing is performed on the received signal. By adjusting the parameters related to these processing to appropriate values, a high-quality ultrasonic tomographic image can be formed. In addition, even after the ultrasonic tomographic image is formed, the ultrasonic tomographic image is sometimes subjected to high-quality processing. In this case as well, by adjusting the parameters related to the high-quality processing to appropriate values, a high-quality ultrasonic tomographic image can be formed.
[0008] In this specification, processing of received signals for forming ultrasonic tomographic images and processing for improving the image quality of the formed ultrasonic tomographic images are collectively referred to as image quality adjustment processing. Furthermore, parameters related to processing of received signals for forming ultrasonic tomographic images and parameters related to processing for improving the image quality of the formed ultrasonic tomographic images are collectively referred to as image quality adjustment parameters.
[0009] Here, the content of the appropriate image quality adjustment processing may be different for each region in the ultrasonic tomographic image. In other words, the appropriate image quality adjustment parameters may be different for each region in the ultrasonic tomographic image. Although not limited to this, for example, a region including kidneys in the ultrasonic tomographic image generally requires high contrast, so the appropriate image quality adjustment processing for this region becomes a processing to achieve high contrast, while on the other hand, a region including liver in the ultrasonic tomographic image generally requires high spatial resolution, so the appropriate image quality adjustment processing for this region becomes a processing to achieve high spatial resolution. Summary of the invention
[0010] An object of the ultrasonic diagnostic apparatus disclosed in the present specification is to provide an ultrasonic diagnostic apparatus capable of performing adaptive image quality adjustment processing on each region in an ultrasonic tomographic image.
[0011] The ultrasonic diagnostic apparatus disclosed in the present specification is characterized in that it includes: a specific region determining unit that determines a specific region corresponding to a portion of an ultrasonic tomographic image corresponding to the ultrasonic data in a data space of ultrasonic data obtained by transmitting and receiving ultrasonic waves to a subject; a specific parameter determining unit that determines a specific parameter as an image quality adjustment parameter for the specific region based on an output of a learning model when the ultrasonic data in the specific region is input into a learning model, the learning model being trained to use learning data including ultrasonic data obtained by transmitting and receiving ultrasonic waves to a subject and a teacher image adjustment parameter to be used in image quality adjustment processing for the ultrasonic data, and outputting an image adjustment parameter suitable for the ultrasonic data based on the input ultrasonic data; and an image quality adjustment processing unit that performs image quality adjustment processing for adjusting image quality in the specific region of the ultrasonic tomographic image on the ultrasonic data in the specific region based on the specific parameter, and performs image quality adjustment processing for adjusting image quality outside the specific region of the ultrasonic tomographic image on the ultrasonic data outside the specific region using a prescribed parameter for image quality adjustment different from the specific parameter.
[0012] According to this configuration, specific parameters suitable for a specific region are determined based on the output of a learning model to which ultrasonic data in a specific region is input. Furthermore, image quality adjustment processing can be performed using specific parameters for ultrasonic data in the specific region, and image quality adjustment processing can be performed using prescribed parameters for ultrasonic data outside the specific region. Thus, adaptive image quality adjustment processing for each region in an ultrasonic tomographic image is achieved.
[0013] Preferably, the image quality adjustment processing unit forms the ultrasonic tomographic image in the specific region with the image quality adjusted by using an image forming model using the specific parameter as a weight parameter.
[0014] According to this configuration, it is possible to form an ultrasonic cross-sectional image in a specific region subjected to image quality adjustment processing using an image formation model.
[0015] It is preferable that the image quality adjustment processing unit performs an image quality smoothing process for smoothly changing the image quality at a boundary between the inside of the specific area and the outside of the specific area.
[0016] According to this configuration, the image quality can be smoothly changed at the boundary between the inside of the specific area and the outside of the specific area on the ultrasonic tomographic image.
[0017] Preferably, the device further comprises: a display control unit configured to display on the display unit a first ultrasonic tomographic image on which the image quality adjustment process based on the specific parameter is performed within the specific area and an image quality adjustment process based on the prescribed parameter is performed outside the specific area, and a second ultrasonic tomographic image on which the image quality adjustment process based on the prescribed parameter is performed for the entire area.
[0018] According to this configuration, the user can compare the first ultrasonic cross-sectional image and the second ultrasonic cross-sectional image.
[0019] Preferably, the specific region specifying unit specifies the specific region in accordance with an instruction from a user of the ultrasonic diagnostic apparatus.
[0020] According to this configuration, the user can set the image quality adjustment process for a desired area and the image quality adjustment process for other areas to different processes.
[0021] Preferably, the image quality adjustment processing unit executes image quality adjustment processing for adjusting image quality in the specific region of the ultrasonic tomographic image according to an image quality adjustment policy corresponding to an instruction from a user of the ultrasonic diagnostic apparatus.
[0022] According to this configuration, the user can perform image quality adjustment processing on ultrasound data in a specific area according to a desired image quality adjustment policy.
[0023] Preferably, the specific parameter determination unit stores in a memory a combination of user identification information for uniquely identifying a user of the ultrasonic diagnostic apparatus, a part of the subject included in a specific area determined according to an instruction from the user, and the image quality adjustment policy indicated by the user for the specific area; and when the specific area including the part is determined according to the instruction of the user, the image quality adjustment processing unit performs image quality adjustment processing for adjusting the image quality in the specific area of the ultrasonic tomographic image according to the user identification information of the user in the memory and the image quality adjustment policy associated with the part.
[0024] According to this configuration, the user does not need to indicate image quality adjustment policies one by one, and can perform image quality adjustment processing of ultrasound data in a specific area according to a desired image adjustment policy.
[0025] Effects of the Invention
[0026] According to the ultrasonic diagnostic apparatus disclosed in this specification, it is possible to provide an ultrasonic diagnostic apparatus capable of performing adaptive image quality adjustment processing on each region in an ultrasonic tomographic image. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 This is a schematic diagram of the structure of the ultrasonic diagnostic apparatus according to this embodiment.
[0028] Figure 2 It is a diagram showing a first example of a specific area determination screen.
[0029] Figure 3 It is a diagram showing a second example of the specific area determination screen.
[0030] Figure 4 This is a conceptual diagram showing a process of determining specific parameters using a learning model.
[0031] Figure 5 This is a conceptual diagram showing a process of forming an ultrasonic tomographic image based on specific parameters using an image generation model.
[0032] Figure 6 This is a graph showing the weight of the image quality adjustment process at the boundary between the specific area and the outside of the specific area.
[0033] Figure 7 The diagram shows a display example of an ultrasonic tomographic image in which the image quality adjustment process based on a specific parameter is executed in a specific region and an ultrasonic tomographic image in which the image quality adjustment process based on a predetermined parameter is executed in the entire region.
[0034] Figure 8 This is a diagram showing an example of an image quality adjustment policy determination screen.
[0035] Explanation of symbols
[0036] 10-ultrasonic diagnostic device, 12-ultrasonic probe, 14-transceiver, 16-signal processing unit, 18-image forming unit, 20-display control unit, 22-display, 24-input interface, 26-memory, 28-learning model, 30-control unit, 32-specific area determination unit, 34-specific parameter determination unit, 40-image formation model. DETAILED DESCRIPTION
[0037] Figure 1 1 is a schematic diagram of the configuration of an ultrasonic diagnostic apparatus 10 according to the present embodiment. The ultrasonic diagnostic apparatus 10 is a medical apparatus installed in a medical institution such as a hospital and used for ultrasonic examination.
[0038] The ultrasonic diagnostic apparatus 10 is an apparatus that scans an ultrasonic beam on a subject and generates an ultrasonic image based on the received signal obtained thereby. In particular, in the present embodiment, the ultrasonic diagnostic apparatus 10 forms an ultrasonic tomographic image (B-mode image) by converting the amplitude intensity of the reflected wave from the scanning surface into brightness based on the received signal. In addition, the ultrasonic diagnostic apparatus 10 can also form other ultrasonic images such as a Doppler image that represents the movement speed of tissue in the subject based on the difference (Doppler shift) in the frequency of the transmitted wave and the received wave.
[0039] In addition, the transceiver 14, the signal processing unit 16, the image forming unit 18, the display control unit 20, the specific area determination unit 32, and the specific parameter determination unit 34 of the ultrasonic diagnostic device 10 are composed of a processor. The processor is composed of at least one of a general-purpose processing device (such as a CPU (Central Processing Unit), etc.) and a dedicated processing device (such as a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a programmable logic device, etc.). As a processor, it is not composed of a single processing device, but can be composed of the cooperation of a plurality of processing devices existing in physically separated locations. In addition, the above-mentioned units can also be realized by the cooperation of hardware such as a processor and software.
[0040] The ultrasonic probe 12 is a device that transmits and receives ultrasonic waves to a subject. The ultrasonic probe 12 has a transducer element array composed of a plurality of transducer elements that transmit and receive ultrasonic waves to a subject.
[0041] The transceiver 14 transmits a transmission signal to the ultrasonic probe 12 (specifically, each transducer element of the transducer element array) under the control of the control unit 30 (described later). As a result, ultrasonic waves are transmitted from each transducer element toward the subject.
[0042] Furthermore, the transceiver 14 receives a reception signal from each vibration element that receives the reflected wave from the subject. The transceiver 14 has an adder and a plurality of delays corresponding to each vibration element, and a phase-aligning and adding process is performed by the adder and the plurality of delays to align and add the phases of the reception signals from each vibration element. Thus, a reception beam signal is formed in which information representing the signal intensity of the reflected wave from the subject is arranged in the depth direction of the subject. In this specification, the reception signal output by each vibration element before the phase-aligning and adding process is referred to as a channel signal, and the reception signal after the phase-aligning and adding process is referred to as a reception beam signal as described above. Furthermore, the reception signal before being converted into data on the coordinate space of the ultrasonic tomographic image by the image forming unit 18 described later may also be collectively referred to as an RF (Radio Frequency) signal.
[0043] For the image quality adjustment process described later, the reception beam signal before the signal processing by the signal processing unit 16 may be temporarily stored in the memory 26 or a memory (not shown) provided in the ultrasonic diagnostic apparatus 10 .
[0044] The signal processing unit 16 performs various signal processing including filtering processing using a bandpass filter or detection processing on the reception beam signal from the transceiver unit 14. The various signal processing in the signal processing unit 16 is processing that can affect the image quality of the ultrasonic tomographic image formed by the image forming unit 18. That is, the signal processing unit 16 performs image quality adjustment processing on the reception beam signal. The image quality adjustment processing performed by the signal processing unit 16 is performed based on the image quality adjustment parameter. The image quality adjustment parameter referenced by the signal processing unit 16 can be set by the user of the ultrasonic diagnostic apparatus 10. In the present embodiment, the image quality adjustment parameter referenced by the signal processing unit 16 can be determined by the specific parameter determination unit 34 described later.
[0045] The image forming unit 18 forms an ultrasonic tomographic image (B-mode image) based on the received beam signal processed by the signal processing unit 16. First, the image forming unit 18 transforms the received beam signal into data on the coordinate space of the ultrasonic image. In this specification, the transformed data is referred to as a coordinate transformation signal. Then, the image forming unit 18 forms an ultrasonic tomographic image based on the coordinate transformation signal.
[0046] The image forming unit 18 performs high-quality processing, i.e., image quality adjustment processing, on the formed ultrasonic tomographic image. The image quality adjustment processing performed by the image forming unit 18 is also performed based on the image quality adjustment parameters. The image quality adjustment parameters referred to by the image forming unit 18 may be set by the user of the ultrasonic diagnostic apparatus 10, but in this embodiment, the image quality adjustment parameters referred to by the image forming unit 18 may be determined by the specific parameter determination unit 34.
[0047] For the image quality adjustment process described later, the ultrasonic tomographic image before the image quality adjustment process by the image forming unit 18 may be temporarily stored in the memory 26 or a memory (not shown) provided in the ultrasonic diagnostic apparatus 10 .
[0048] The display control unit 20 controls the display 22 to display the ultrasonic tomographic image formed by the image forming unit 18 and other various information. The display 22 as a display unit is a display composed of, for example, a liquid crystal display or an organic EL (ElectroLuminescence).
[0049] The input interface 24 is constituted by, for example, buttons, a trackball, a touch panel, etc. The input interface 24 is used to input user commands into the ultrasonic diagnostic apparatus 10 .
[0050] The memory 26 is configured to include a HDD (Hard Disk Drive), an SSD (Solid State Drive), an eMMC (embedded Multi Media Card), or a ROM (Read Only Memory). The memory 26 stores an ultrasonic diagnostic program for operating each part of the ultrasonic diagnostic device 10. In addition, the ultrasonic diagnostic program can also be stored in a computer-readable non-temporary storage medium such as a USB (Universal Serial Bus) memory or a CD-ROM. The ultrasonic diagnostic device 10 can read and execute the ultrasonic diagnostic program from such a storage medium.
[0051] And, if Figure 1 As shown, a learning model 28 is stored in the memory 26. The learning model 28 is, for example, a CNN (Convolutional Neural Network) or the like, but may be any model as long as it fulfills the function described below.
[0052] The learning model 28 is trained to use learning data including ultrasonic data obtained by transmitting and receiving ultrasonic waves to a subject and teacher image adjustment parameters to be used in image quality adjustment processing for the ultrasonic data, and output image adjustment parameters suitable for the ultrasonic data based on the input ultrasonic data. The ultrasonic data included in the learning data of the learning model 28 includes channel signals, receiving beam signals, coordinate transformation signals, and ultrasonic tomographic images. In the present embodiment, the learning processing of the learning model 28 is performed by a learning processing device different from the ultrasonic diagnostic device 10, and the fully learned learning model 28 is stored in the memory 26. However, it is also possible to provide the ultrasonic diagnostic device 10 with a learning processing unit (in Figure 1 (not shown in the figure), the learning processing unit performs a learning process of the learning model 28. In this case, the ultrasonic diagnostic apparatus 10 becomes a learning processing apparatus.
[0053] The details of the learning process of the learning model 28 are as follows. The processor of the learning processing device inputs the ultrasonic data as the learning data into the learning model 28. The learning model 28 predicts and outputs the image quality adjustment parameters suitable for the input ultrasonic data. The processor of the learning processing device changes the parameters in the learning model 28 so as to reduce the difference between the output data of the learning model 28 and the teacher image adjustment parameters included in the learning data. The learning model 28 is trained by repeating such a process. The fully trained learning model 28 can predict the image adjustment parameters suitable for the input ultrasonic data with high accuracy.
[0054] The control unit 30 is configured to include at least one of a general-purpose processor (e.g., a CPU (Central Processing Unit), etc.) and a special-purpose processor (e.g., a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a programmable logic device, etc.). The control unit 30 may not be composed of a single processing device, but may be composed of a plurality of processing devices that are physically separated. The control unit 30 controls each unit of the ultrasonic diagnostic apparatus 10 according to the ultrasonic diagnostic program stored in the memory 26.
[0055] The specific region specifying unit 32 specifies a specific region corresponding to a portion of an ultrasonic tomographic image corresponding to the ultrasonic data (in other words, an ultrasonic tomographic image formed based on the ultrasonic data, or, when the ultrasonic data is an ultrasonic tomographic image, the ultrasonic data itself) in the data space of the ultrasonic data obtained by transmitting and receiving ultrasonic waves to the subject, that is, a channel signal, a reception beam signal, a coordinate transformation signal, or an ultrasonic tomographic image. Figure 1 In the figure, the specific area determination unit 32 is illustrated to receive ultrasonic data (i.e., receiving beam signals) from the signal processing unit 16, but as mentioned above, the ultrasonic data can be various signals, so the specific area determination unit 32 can receive a channel signal as ultrasonic data from the transceiver unit 14, and can also receive a coordinate transformation signal or an ultrasonic tomographic image as ultrasonic data from the image forming unit 18.
[0056] As a first method of specifying a specific region, the specific region specifying unit 32 can specify the specific region by analyzing ultrasonic data (here, in particular, received beam signals, coordinate conversion signals, or ultrasonic tomographic images).
[0057] For example, a region-specific learning model is prepared in advance, which is a region-specific learning model that is learned using ultrasound data and learning data including the position and name of a part (organ, etc.) included in the ultrasound data, and is trained to predict and output the position and name of the part included in the ultrasound data based on the input ultrasound data. Based on this, the specific region determination unit 32 can determine the specific region based on the output of the learned region-specific learning model when the ultrasound data of the processing target is input.
[0058] Furthermore, for example, partial ultrasonic data representing a desired specific region may be prepared as template data, similarities between each portion of the ultrasonic data of the treatment target and the template data may be calculated, and a region having the largest similarity equal to or greater than a threshold may be identified as the specific region.
[0059] As a second method of specifying a specific region, the specific region specifying unit 32 can specify a specific region in accordance with an instruction from a user of the ultrasonic diagnostic apparatus 10 .
[0060] For example, the image forming unit 18 forms a segmented image by dividing the ultrasonic tomographic image into a plurality of regions (for example, corresponding to each organ) using a conventional technique such as using a learning model, and Figure 2 As shown in FIG. 1 , the display control unit 20 displays the formed segmented image SEI on the display 22. Figure 2In the example of FIG. 1 , a segmented image SEI including a liver region, a gallbladder region, and a kidney region is shown. Based on this, the user uses a cursor to select a desired region from the displayed segmented image SEI. The specific region determination unit 32 determines the region of the segmented image SEI selected by the user as a specific region.
[0061] Then, the image forming unit 18 determines one or more region names (for example, organ names) included in the ultrasonic tomographic image using a conventional technique such as a learning model, and Figure 3 As shown in FIG. 1 , the display control unit 20 displays the region name list RL, which is a list of determined region names, together with the ultrasonic tomographic image USI on the display 22. On this basis, the user selects a desired region from the displayed region name list RL using a cursor. The specific region specifying unit 32 specifies the region selected by the user as a specific region.
[0062] The method of determining the specific area according to the instruction from the user is not limited to the above method. For example, the user can directly designate the specific area on the ultrasonic tomographic image displayed on the display 22 using a cursor or the like.
[0063] Return to Figure 1 The specific parameter determination unit 34 determines the specific parameters that are the image quality adjustment parameters for the specific area determined by the specific area determination unit 32 , using the learned learning model 28 .
[0064] Specifically, the specific parameter determination unit 34 cuts out specific region data as ultrasonic data within a specific region from the ultrasonic data of the processing object (i.e., the channel signal, the reception beam signal, the coordinate transformation signal, or the ultrasonic tomographic image). Figure 4 As shown, the specific parameter determination unit 34 inputs the specific area data into the learned learning model 28. The learning model 28 predicts and outputs the image quality adjustment parameter suitable for the input specific area data. The specific parameter determination unit 34 determines the specific parameter based on the output of the learning model 28.
[0065] Here, it should be noted that the specific parameter determination unit 34 inputs only the specific region data, which is a part of the ultrasonic data, into the learning model 28, rather than inputting the entire ultrasonic data into the learning model 28. Thus, the learning model 28 predicts and outputs the image quality adjustment parameter specifically for the specific region data, rather than the entire ultrasonic data. That is, it can be said that the specific parameter is an image quality adjustment parameter specifically for the specific region.
[0066] For example, when the specific area is a kidney area, the kidney area requires high contrast, so as a specific parameter, a parameter such as a filter processing that can achieve a reduction in dynamic range or a filter processing that emphasizes high contrast is determined. Also, for example, when the specific area is a liver area, the liver area requires substantially smooth depiction, so as a specific parameter, a parameter such as TGC (Time Gain Compensation) that can achieve uniform brightness from shallow to deep, or a filter processing that emphasizes high spatial resolution is determined. Also, for example, when the specific area is a gallbladder area, the gallbladder area requires the ability to detect abnormalities such as polyps, so as a specific parameter, a parameter such as a filter processing that can achieve reduction of artifacts such as multiple reflection artifacts that hinder the detection of abnormalities is determined. Also, for example, when the specific area is a breast area, the breast area requires diagnosis of the breast area, so as a specific parameter, a parameter such as making only the breast area to be diagnosed a high-definition image and reducing the brightness of other areas so as not to hinder the diagnosis is determined.
[0067] The signal processing unit 16 or the image forming unit 18 as the image quality adjustment processing unit performs the image quality adjustment process on the ultrasound data in the specific region based on the specific parameter determined by the specific parameter determination unit 34 .
[0068] First, the image quality adjustment processing of the signal processing unit 16 is described. The signal processing unit 16 performs image quality adjustment processing on the received beam data before signal processing that is stored based on the specific parameters determined by the specific parameter determination unit 34. Specifically, the signal processing unit 16 performs image quality adjustment processing on the received beam signal within the specific area based on the specific parameters, and performs image quality adjustment processing on the received beam signal outside the specific area using a prescribed parameter for image quality adjustment that is different from the specific parameters. The prescribed parameter for image quality adjustment may be, for example, a parameter set in advance by a user, or a parameter predetermined in the ultrasonic diagnostic apparatus 10, etc. In this way, the signal processing unit 16 can become an image quality adjustment processing unit.
[0069] Next, the image quality adjustment processing of the image forming unit 18 will be described. The image forming unit 18 performs the image quality adjustment processing on the ultrasonic tomographic image before the image quality adjustment processing that is stored based on the specific parameters determined by the specific parameter determination unit 34. Specifically, the image forming unit 18 performs the image quality adjustment processing on the ultrasonic tomographic image in the specific area based on the specific parameters, and performs the image quality adjustment processing on the ultrasonic tomographic image outside the specific area using a prescribed parameter for image quality adjustment that is different from the specific parameters. Here, too, the prescribed parameter for image quality adjustment may be, for example, a parameter set in advance by the user, or a parameter predetermined in the ultrasonic diagnostic apparatus 10. In this way, the image forming unit 18 can also serve as an image quality adjustment processing unit.
[0070] As described above, the signal processing unit 16 or the image forming unit 18 performs different image quality adjustment processing based on different image quality adjustment parameters on the ultrasound data in the specific area and the ultrasound data outside the specific area. Thus, it is possible to perform adaptive image quality adjustment processing on each area in the ultrasonic tomographic image. For example, the kidney area as a specific area can be subjected to image quality adjustment processing such that the contrast becomes high, and the image quality adjustment processing is performed in other areas so that the contrast does not become too high and becomes appropriate.
[0071] Furthermore, the specific region specifying unit 32 specifies the specific region in accordance with the instruction from the user, whereby the user can set the image quality adjustment process for the desired region and the image quality adjustment process for other regions to different processes.
[0072] In particular, in the present embodiment, for example, even for regions corresponding to the same organ, it is possible to perform image quality adjustment processing on each ultrasonic data using different specific parameters. For example, it is assumed that the liver region is determined as the first specific region in the first ultrasonic data, and the liver region is similarly determined as the second specific region in the second ultrasonic data different from the first ultrasonic data. In this case, if the contents of the first ultrasonic data in the first specific region and the second ultrasonic data in the second specific region are different, the learning model 28 can output different image quality adjustment parameters when the first ultrasonic data in the first specific region is input and when the second ultrasonic data in the second specific region is input. Thus, according to the present embodiment, different image quality adjustment processing can be performed on the same liver region according to the ultrasonic data.
[0073] Furthermore, the specific parameter determination unit 34 inputs only the specific region data in the ultrasonic data into the learning model 28, rather than inputting the entire ultrasonic data into the learning model 28. This can reduce the amount of calculation for predicting and outputting the specific parameter by the learning model 28.
[0074] In the present embodiment, the image forming unit 18 forms an ultrasonic tomographic image for a specific area based on the received beam data, and then performs image quality adjustment processing on the ultrasonic tomographic image based on specific parameters. Figure 5 As shown, the image forming unit 18 as the image quality adjustment processing unit may also be configured to form an ultrasonic tomographic image in a specific region with adjusted image quality by using an image forming model 40 that uses specific parameters as weight parameters. The image forming model 40 may be a learning model such as a GAN (Generative Adversarial Network). In this case, it is preferred to pre-train the learning model 28 so that the form of the output data becomes a form suitable for the image forming model 40.
[0075] In the present embodiment, the image forming unit 18 performs image quality adjustment processing of ultrasonic tomographic images in a specific area based on specific parameters or formation processing of ultrasonic tomographic images in a specific area using the image formation model 40 , but these processes may be performed by the specific parameter determination unit 34 .
[0076] In the present embodiment, different image quality adjustment processes are performed in the specific area and outside the specific area. Therefore, it is possible that the difference in image quality becomes significant at the boundary between the specific area and outside the specific area. Therefore, it is preferable that the signal processing unit 16 or the image forming unit 18 as the image quality adjustment processing unit performs an image quality smoothing process for smoothly changing the image quality at the boundary between the specific area and outside the specific area.
[0077] Figure 6 is a graph showing the weight of the image quality adjustment process at the boundary between the specific area and the outside of the specific area. Figure 6 In FIG. 1 , a boundary B between the inside and outside of the specific area is shown by a single-point chain line, the left side of the boundary B is outside of the specific area, and the right side of the boundary B is within the specific area. A certain area near the boundary B outside the specific area and inside the specific area is called a boundary area BR. The solid line graph represents the weight of the image quality adjustment process using a specific parameter in the specific area, and the dotted line graph represents the weight of the image quality adjustment process using a specified parameter outside the specific area.
[0078] like Figure 6 As shown in FIG. 1 , in the specific area outside the boundary area BR, the weight of the image quality adjustment process using the specific parameters is "1", and the weight of the image quality adjustment process using the specified parameters is "0". This means that the image quality adjustment process using only the specific parameters is performed on the ultrasound data in the specific area outside the boundary area BR. Figure 6 In the curve graph (from right to left in FIG. 1 ), the weight of the image quality adjustment process using the specific parameters gradually decreases, and on the contrary, the weight of the image quality adjustment process using the prescribed parameters increases. This means that in the boundary area BR, the result of the image quality adjustment process using the specific parameters and the result of the image quality adjustment process using the prescribed parameters are synthesized according to their respective weights. In the present embodiment, this process is equivalent to image quality smoothing processing. Outside the specific area other than the boundary area BR, the weight of the image quality adjustment process using the specific parameters is "0", and the weight of the image quality adjustment process using the prescribed parameters is "1". This means that the image quality adjustment process using only the specific parameters is performed on the ultrasonic data in the specific area other than the boundary area BR.
[0079] Thus, in the boundary region BR, by combining the result of the image quality adjustment process using specific parameters and the result of the image quality adjustment process using prescribed parameters, the image quality can be smoothly changed at the boundary between the inside and outside of the specific region on the ultrasonic tomographic image.
[0080] The display control unit 20 displays the ultrasonic tomographic image subjected to the image quality adjustment process on the display 22. Figure 7 As shown, the display control unit 20 preferably displays the first ultrasonic tomographic image USI-h in which the image quality adjustment process based on the specific parameter is performed on the specific area and the image quality adjustment process based on the prescribed parameter is performed on the outside of the specific area, and the second ultrasonic tomographic image USI-n in which the image quality adjustment process based on the prescribed parameter is performed on the entire area on the display 22. Thus, the user can compare the first ultrasonic tomographic image USI-h and the second ultrasonic tomographic image USI-n.
[0081] In order to display the second ultrasonic tomographic image USI-n on the display 22, the signal processing unit 16 performs image quality adjustment processing using predetermined parameters on the entire received frame signal of one frame, and the image forming unit 18 performs image quality adjustment processing using predetermined parameters on the entire formed ultrasonic tomographic image. Thus, the second ultrasonic tomographic image USI-n is formed.
[0082] As described above, sometimes the appropriate image quality adjustment processing for each region of the ultrasonic tomographic image is different from each other, but sometimes there are multiple appropriate image quality adjustment processing for a certain region. For example, when the specific region is a kidney region, the appropriate image quality adjustment processing for the kidney region includes processing for increasing the resolution, processing for improving the contrast, or processing for increasing the depth. These processings are performed using different image adjustment parameters (i.e., specific parameters).
[0083] Therefore, the signal processing unit 16 or the image forming unit 18 as the image quality adjustment processing unit preferably performs image quality adjustment processing for adjusting the image quality in a specific region of the ultrasonic tomographic image according to an image quality adjustment policy corresponding to an instruction from a user of the ultrasonic diagnostic apparatus 10 .
[0084] As a premise, the learning model 28 is trained to use the learning data including the ultrasound data, the image quality adjustment policy, and the teacher image adjustment parameters to be used in the image quality adjustment processing for the ultrasound data in accordance with the image quality adjustment policy, and outputs the image adjustment parameters suitable for the ultrasound data in accordance with the image quality adjustment policy based on the input ultrasound data and the image quality adjustment policy. This can be realized by configuring one learning model 28 to accept the image quality adjustment policy, or by training a different learning model 28 for each image quality adjustment policy.
[0085] Figure 8 This is a diagram showing an example of an image quality adjustment policy determination screen. Figure 8 The example is an example in which the user selects the kidney region as the specific region from the region name list RL. The display control unit 20 further displays a policy list PL on the display 22, which shows the policy list PL suitable for the selected specific region (in Figure 8 The specific parameter determination unit 34 includes a plurality of image quality adjustment policies for image quality adjustment processing of the ultrasound data (in the example of the kidney region). When the user selects a desired image adjustment policy from the policy list PL, the specific parameter determination unit 34 inputs the specific region data corresponding to the kidney region as the specific region and the image adjustment policy selected by the user into the learning model 28. The learning model 28 predicts and outputs image quality adjustment parameters that are suitable for the input specific region data and follow the input image adjustment policy. The specific parameter determination unit 34 determines the specific parameters based on the output of the learning model 28. Thereafter, the signal processing unit 16 or the image forming unit 18 performs image quality adjustment processing on the ultrasound data in the specific region based on the specific parameters.
[0086] It is considered that the same user often performs image quality adjustment processing according to the same image adjustment policy on a specific region including the same part of the subject. Therefore, in the present embodiment, it is preferable that the signal processing unit 16 or the image forming unit 18 as the image quality adjustment processing unit stores the image adjustment policy selected by a certain user for a specific region including a certain part, and then, when the specific region including the part is determined according to the instruction of the user, the image adjustment policy for the newly determined specific region can be determined based on the image adjustment policy selected by the user in the past for the specific region including the part.
[0087] Specifically, whenever a user Figure 8 When an image adjustment policy is selected in the image quality adjustment policy determination screen shown in FIG. 1 , the specific parameter determination unit 34 displays the user ID as user identification information that uniquely identifies the user, the part of the subject included in the specific area determined according to the instruction from the user (in Figure 8 in the example of "kidney"), and the image quality adjustment policy indicated by the user for the specific area (in Figure 8 In the example of "improving contrast"), the combinations are accumulated and stored in the policy database constructed in the memory 26 (in Figure 1 In addition, the user ID of the user can be determined by the control unit 30 authenticating the user when the user starts using the ultrasonic diagnostic apparatus 10.
[0088] Furthermore, for example, for other ultrasonic data, when the specific parameter determination unit 34 determines a specific region including the part (in this case, "kidney") according to the user's instructions, the specific parameter determination unit 34 refers to the policy database to determine the user ID of the user and the image adjustment policy associated with the part. In this case, "improve contrast" is determined. Thereafter, the specific parameter determination unit 34 inputs the specific region data corresponding to the kidney region as the specific region and the determined image adjustment policy into the learning model 28, and determines the specific parameter based on the output of the learning model 28. Of course, the specific parameter is an image adjustment parameter that follows the determined image adjustment policy. Thereafter, the signal processing unit 16 or the image forming unit 18 performs image quality adjustment processing on the ultrasonic data in the specific region based on the specific parameter (in other words, in accordance with the determined image adjustment policy).
[0089] As a result, the user does not need to indicate image quality adjustment policies one by one, and can perform image quality adjustment processing of ultrasound data in a specific area according to a desired image adjustment policy.
[0090] As mentioned above, although the embodiment according to the present invention has been described, the present invention is not limited to the above-mentioned embodiment, and various modifications can be made without departing from the gist of the present invention.
Claims
1. An ultrasonic diagnostic device, characterized in that: have: a specific region specifying unit that specifies, in a data space of ultrasonic data obtained by transmitting and receiving ultrasonic waves to a subject, a specific region corresponding to a portion of an ultrasonic tomographic image corresponding to the ultrasonic data; a specific parameter determination unit that determines the specific parameter as the image quality adjustment parameter for the specific area based on the output of the learning model when the ultrasound data in the specific area is input into the learning model, the learning model being trained to use the learning data including the ultrasound data obtained by transmitting and receiving ultrasound to a subject and the teacher image adjustment parameter to be used in the image quality adjustment process for the ultrasound data, and outputting the image adjustment parameter suitable for the ultrasound data based on the input ultrasound data; and The image quality adjustment processing unit performs image quality adjustment processing for adjusting the image quality within the specific area of the ultrasonic tomographic image on the ultrasonic data within the specific area based on the specific parameter, and performs image quality adjustment processing for adjusting the image quality outside the specific area of the ultrasonic tomographic image on the ultrasonic data outside the specific area using a prescribed parameter for image quality adjustment different from the specific parameter.
2. The ultrasonic diagnostic apparatus according to claim 1, wherein: The image quality adjustment processing unit forms the ultrasonic tomographic image in the specific region with the image quality adjusted by using an image forming model using the specific parameter as a weight parameter.
3. The ultrasonic diagnostic apparatus according to claim 1, wherein: The image quality adjustment processing unit performs an image quality smoothing process for smoothly changing the image quality at a boundary between the inside of the specific area and the outside of the specific area.
4. The ultrasonic diagnostic apparatus according to claim 1, wherein: Also available: The display control unit displays on the display unit a first ultrasonic tomographic image in which the image quality adjustment process based on the specific parameter is performed on the specific area and an image quality adjustment process based on the prescribed parameter is performed on the area outside the specific area, and a second ultrasonic tomographic image in which the image quality adjustment process based on the prescribed parameter is performed on the entire area.
5. The ultrasonic diagnostic apparatus according to claim 1, wherein: The specific region specifying unit specifies the specific region in accordance with an instruction from a user of the ultrasonic diagnostic apparatus.
6. The ultrasonic diagnostic apparatus according to claim 1, wherein: The image quality adjustment processing unit executes an image quality adjustment process for adjusting the image quality in the specific region of the ultrasonic tomographic image according to an image quality adjustment policy corresponding to an instruction from a user of the ultrasonic diagnostic apparatus.
7. The ultrasonic diagnostic apparatus according to claim 6, wherein: The specific parameter determination unit stores in a memory a combination of user identification information that uniquely identifies a user of the ultrasonic diagnostic apparatus, a part of the subject included in a specific area determined according to an instruction from the user, and the image quality adjustment policy indicated by the user for the specific area. When the specific area including the part is determined according to the instruction of the user, the image quality adjustment processing unit performs image quality adjustment processing for adjusting the image quality in the specific area of the ultrasonic tomographic image according to the user identification information of the user in the memory and the image quality adjustment policy associated with the part.
