Medical image diagnostic system and control method thereof
The medical image diagnosis system simplifies image quality adjustment by using user-selected anchors and thumbnail images with variable step widths, leveraging Bayesian optimization to efficiently optimize image quality indices, addressing the complexity of n-dimensional adjustments.
Patent Information
- Application Number
- JP2023085805
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-24
- Publication Date
- 2024-12-05
AI Technical Summary
Existing medical image diagnosis systems face challenges in adjusting multiple image quality indicators to achieve optimal image quality, as the process is complex and restrictive, often requiring n-dimensional adjustments which are difficult to optimize effectively.
A medical image diagnosis system that uses a user-selected image quality index as an anchor, generating and displaying thumbnail images with variable step widths to facilitate intuitive adjustment, employing Bayesian optimization to estimate user perception and iteratively refine image quality indices.
Enables easy and efficient adjustment of image quality to achieve optimal results by allowing users to intuitively select and adjust multiple image quality indicators, reducing the complexity and time required to reach desired image quality.
Smart Images

Figure 2024168827000001_ABST
Abstract
Description
[Technical field]
[0001] The embodiments disclosed in this specification and the drawings relate to a medical image diagnostic system and a control method thereof. [Background technology]
[0002] Many medical imaging diagnostic systems, such as ultrasound diagnostic systems, magnetic resonance imaging (MRI) systems, X-ray computed tomography (CT) systems, and positron emission tomography (PET) systems, allow users to adjust the image quality of medical images to suit their preferences.
[0003] However, there are many image quality indices that control image quality, and it is difficult for a user of a medical image diagnostic system to adjust the values of multiple image quality indices to reach optimal image quality. For example, for a given image processing, if there are 60 types of image quality indices that contribute to image quality adjustment and each image quality index can be selected and set from five adjustment values, there may be 5 to the power of 60 combinations of adjustment settings. Even if the many image quality indices are narrowed down to N types of indices that are effective, N-dimensional adjustment is required, and adjustment is still difficult. Therefore, in many medical image diagnostic systems, some sets of image indices are indexed according to the user's preferences, and the index value can be adjusted in several steps as a GUI (Graphical User Interface) of the system. However, when a set of image quality indices is indexed in this way, the degree of freedom of adjustment is considerably restricted.
[0004] There is also a medical image diagnostic system that allows a user to select an image quality index to be adjusted and adjust the value of the image quality index while viewing an image. According to such a medical image diagnostic system, a plurality of thumbnail images rendered in correspondence with each of a plurality of rendering conditions are generated, and a rendering image rendered according to a predetermined rendering condition is generated. If the plurality of thumbnail images generated by this method are displayed as operation buttons on a touch command screen, it is visually easier to understand than adjusting the value of the image quality index by inputting a numerical value or using a knob. However, when a plurality of thumbnail images are displayed in correspondence with each of a plurality of rendering conditions, the step width of the value of the image quality index may be fixed. In such a case, if the step width is large, there is a risk of missing the optimal image quality, and if the step width is small, it takes time and effort to reach the optimal image quality. In other words, if the step width of the value of the image quality index is fixed, it is difficult to reach the optimal image quality.
[0005] There is also a medical image diagnostic system that allows a user to adjust the value of an image quality index by breaking down each of a number of image indices into one-dimensional slider operations while viewing an image, and presenting the results to the user, thereby optimizing an unknown perception function through Bayesian optimization. Although such a medical image diagnostic system allows the image quality adjustment of each dimension to be changed continuously, it is difficult to apply this to a method of adjusting the value of an image quality index by selecting a thumbnail image.
[0006] There is also a medical image diagnostic system that presents a UI (User Interface) that allows the user to adjust one type of image index while viewing the image, has the user adjust this image quality index, and uses Bayesian optimization to predict the user's recognition of image quality and optimize the value of the image quality index. According to such a medical image diagnostic system, multiple image indices cannot be adjusted simultaneously, and image quality adjustment for each dimension changes continuously, so it is difficult to apply the method of adjusting the value of the image quality index by selecting a thumbnail image.
[0007] Furthermore, there is a medical image diagnostic system that breaks down an n-dimensional image quality exploration problem into a series of 2-dimensional image quality exploration subtasks, and allows a user to select an image quality index for each subtask by using thumbnails mapped to 2 dimensions. In such a medical image diagnostic system, the conversion from n-dimensions to 2-dimensions may be formulated as a general method so that it can be applied to various image indices. However, it is clinically desirable that the conversion to each image quality index in medical images is formulated for each image index. Therefore, even when the conversion from n-dimensions to 2-dimensions is formulated as a general method so that it can be applied to various image indices, the difficulty of achieving optimal image quality remains unsolved. [Prior art documents] [Patent documents]
[0008] [Patent Document 1] Patent No. 6608126 [Patent Document 2] JP 2020-159789 A [Patent Document 3] JP 2020-074996 A [Patent Document 4] JP 2004-016612 A [Non-patent literature]
[0009] [Non-Patent Document 1] Y. Koyama, I. Sato, D. Sakamoto, and T. Igarashi, “Sequential line search for efficient visual design optimization by crowds”, ACM Trans. Graph., vol. 36, no. 4, Jul. 2017. [Non-Patent Document 2] Kyurae Kim et al., “Ultrasound Design Gallery: Personalized Enhancement of Medical Ultrasound Images with Preferential Bayesian Optimization”, Pre-print Under review Nov. 2021. [Non-Patent Document 3] Y. Koyama, I. Sato, M. Goto, "Sequential gallery for interactive visual design optimization", ACM Trans. Graph., Vol. 39, no. 4, August 2020. Summary of the Invention [Problem to be solved by the invention]
[0010] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to facilitate image quality adjustment of medical images by a user in a medical image diagnostic system. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]
[0011] A medical image diagnostic system according to an embodiment includes a first image generation unit that uses a value of an image quality index selected by a user as an anchor for a plurality of types of image quality indexes for displaying a medical image, and generates a thumbnail image of the medical image based on the anchor as a first thumbnail image, a first image display unit that displays the first thumbnail image generated by the first image generation unit on a display unit, a second image generation unit that generates a plurality of thumbnail images as second thumbnail images for the medical image by increasing or decreasing the plurality of types of image quality indexes from the anchor, and a second image display unit that displays the plurality of second thumbnail images generated by the second image generation unit on the display unit, and a new image quality index calculation unit that calculates a new image quality index adjusted by a variable step width based on a selection result of the first thumbnail image and the second thumbnail image; and a regeneration display unit that uses a value of an image index corresponding to the first thumbnail image or the second thumbnail image selected by a user from among the first thumbnail image or the plurality of second thumbnail images as a new anchor to cause the first image generation unit to generate a new first thumbnail image and cause the first image display unit to display the new first thumbnail image, and causes the second image generation unit to generate a new second thumbnail image based on the value of the new image quality index calculated by the new image quality index calculation unit and cause the second image display unit to display the new second thumbnail image. [Brief description of the drawings]
[0012] [Figure 1] 1 is a perspective view showing an example of the overall configuration of a medical image diagnostic system according to a first embodiment. [Diagram 2] FIG. 2 is a block diagram showing an example of the configuration of the medical image diagnostic system shown in FIG. [Diagram 3] 3 is a functional block diagram illustrating functions of a control unit of the medical image diagnostic system shown in FIG. 2. [Figure 4] FIG. 4 is a diagram showing an example of an image quality adjustment setting screen displayed on a touch command screen of the medical image diagnostic system according to the first embodiment. [Diagram 5]FIG. 4 is a flowchart illustrating the contents of image quality optimization processing executed by the medical image diagnostic system according to the first embodiment. [Figure 6] FIG. 13 is a diagram showing an example of an image quality adjustment setting screen displayed on a touch command screen of the medical image diagnostic system according to the first modified example. [Figure 7] FIG. 11 is a diagram showing an example of an image quality adjustment setting screen displayed on a touch command screen of the medical image diagnostic system according to the second embodiment. [Figure 8] FIG. 11 is a diagram showing, in three-dimensional coordinates, changes in image quality indexes in the medical image diagnostic system according to the second embodiment. [Figure 9] FIG. 11 is a diagram showing an example of an image quality adjustment setting screen displayed on a touch command screen of a medical image diagnostic system according to Modification 2. [Figure 10] FIG. 11 is a diagram showing an example of an image quality adjustment setting screen displayed on a touch command screen of the medical image diagnostic system according to the third embodiment. [Figure 11] FIG. 11 is a diagram showing an example of an image quality adjustment setting screen displayed on a touch command screen of a medical image diagnostic system according to Modification 3. [Figure 12] FIG. 13 is a diagram illustrating a schematic configuration of a medical image diagnostic system according to a fourth embodiment. [Figure 13] FIG. 13 is a functional block diagram illustrating functions of a control unit of a medical image diagnostic system according to a fourth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0013] Hereinafter, an embodiment of a medical image diagnostic system and a control method thereof will be described with reference to the drawings. In the following description, components having substantially the same functions and configurations are denoted by the same reference numerals, and duplicated descriptions will be given only when necessary.
[0014] Fig. 1 is a perspective view showing an example of the overall configuration of a medical image diagnostic system 100 according to the first embodiment. The medical image diagnostic system 100 shown in Fig. 1 is configured, for example, by an ultrasound diagnostic system. Fig. 2 shows an example of a block configuration diagram of the medical image diagnostic system 100 shown in Fig. 1.
[0015] As shown in Fig. 1, the medical image diagnostic system 100 according to this embodiment is configured to include an ultrasound probe 101, an input device 102, a main display screen 103, and a touch command screen (TCS) 104. As shown in Fig. 2, the medical image diagnostic system 100 is configured to include, in addition to these, a transmitting / receiving unit 201, a B-mode processing unit 202, a Doppler processing unit 203, an image processing unit 204, a memory 205, and a control unit 206 therein.
[0016] The ultrasonic probe 101 is a device (probe) that irradiates an ultrasonic signal to an object to be examined and detects the ultrasonic signal reflected by the object to be examined, and is formed of an electromechanical reversible conversion element. The ultrasonic probe 101 is, for example, a phased array type probe equipped with a plurality of elements arranged in an array at its tip. As a result, the ultrasonic probe 101 converts the supplied pulse drive voltage into an ultrasonic signal and transmits it in a desired direction within the scan area of the object to be examined, and also converts the ultrasonic signal reflected from the object to an echo signal of a corresponding voltage.
[0017] The ultrasonic probe 101 may be a 1D array probe that scans a subject two-dimensionally, or a three-dimensional probe that scans a subject three-dimensionally, that is, a mechanical 4D probe or a 2D array probe. When a three-dimensional probe is used, a specific tomographic image or a multi-planar reconstruction (MPR) display is included in the medical image displayed on the main display screen 103.
[0018] The transmitting / receiving unit 201 has a trigger generating circuit, a delay circuit, a pulser circuit, etc., and supplies a drive signal to the ultrasonic probe 101. The pulser circuit repeatedly generates a rate pulse for forming an ultrasonic signal to be transmitted at a predetermined rate frequency. The delay circuit also provides each rate pulse generated by the pulser circuit with a delay time for each piezoelectric transducer required for focusing the ultrasonic signal generated from the ultrasonic probe 101 into a beam shape and determining the transmission directivity. The trigger generating circuit also applies a drive signal (drive pulse) to the ultrasonic probe 101 at a timing based on the rate pulse. That is, the delay circuit arbitrarily adjusts the transmission direction from the piezoelectric transducer surface by changing the delay time provided to each rate pulse.
[0019] The transmitting / receiving unit 201 has a function capable of instantaneously changing the transmission frequency, transmission drive voltage, etc., in order to execute a predetermined scan sequence based on instructions from the control unit 206, which will be described later. In particular, the change in the transmission drive voltage is realized by an oscillator circuit capable of instantaneously switching its value, or a mechanism for electrically switching between multiple power supply units.
[0020] The transmitting / receiving unit 201 also has an amplifier circuit, an A / D converter, an adder, etc., and performs various processes on the ultrasonic signal, which is the reflected wave received by the ultrasonic probe 101, to generate reflected wave data. The amplifier circuit amplifies the ultrasonic signal, which is the reflected wave, for each channel and performs gain correction processing. The A / D converter A / D converts the gain-corrected ultrasonic signal, which is the reflected wave, to generate digital data, and gives this digital data a delay time required to determine the reception directivity. The adder performs addition processing on the digital data generated by the A / D converter to generate reflected wave data. The addition processing by the adder emphasizes the reflected component from a direction corresponding to the reception directivity of the ultrasonic signal, which is the reflected wave.
[0021] The method of transmission and reception by the transmission and reception unit 201 may be a method of transmitting and receiving a plane wave in addition to a method of focusing an ultrasonic signal into a beam as explained above.
[0022] The B-mode processing unit 202 performs logarithmic amplification, envelope detection processing, logarithmic compression, etc. on the reflected wave data from the transmission / reception unit 201, and generates B-mode information in which the signal intensity of each of multiple sample points is expressed as a change in brightness.
[0023] The Doppler processing unit 203 performs color Doppler on the reflected wave data from the transmission / reception unit 201 to calculate blood flow information, i.e., Doppler information. In the color Doppler method, ultrasonic signals are transmitted and received multiple times on the same scanning line, and a moving target indicator (MTI) filter is applied to the data string at the same position to suppress signals (clutter signals) originating from stationary or slow-moving tissues and extract signals originating from blood flow. In the color Doppler method, Doppler information such as the blood flow speed, blood flow dispersion, and blood flow power are estimated from the blood flow signal.
[0024] The image processor 204 converts the scanning method of the B-mode information and the Doppler information into a scanning method suitable for display (scan conversion) and generates an ultrasound diagnostic image as a medical image. Information indicating the combination, juxtaposition, and display position of each image information, various information for assisting the operation of the medical image diagnostic system 100, which is an ultrasound diagnostic system, and additional information necessary for ultrasound diagnosis such as patient information are also generated together with the ultrasound diagnostic image. The image processor 204 also reduces the size of the processed medical image to generate a thumbnail image for the touch command screen 104, which will be described later.
[0025] The image processing unit 204 includes enhancement image processing (not shown). In this embodiment, the image processing unit 204 performs enhancement image processing using a multi-resolution decomposition process and a nonlinear anisotropic diffusion filter on the generated ultrasound diagnostic image as image processing. By the enhancement image processing using the multi-resolution decomposition process and the nonlinear anisotropic diffusion filter, the image processing unit 204 performs multi-resolution decomposition of the ultrasound diagnostic image, applies a nonlinear anisotropic diffusion filter to each decomposition image, and controls the multi-resolution high-frequency signal using the "edge information" generated in the process of the filter processing. This enhancement image processing can reduce noise or speckle in the image, enhance the edge of the boundary between two tissues, and also perform coherency enhancement to smooth the image around the boundary along the boundary. In other words, the enhancement image processing can apply each image quality index of noise reduction, edge enhancement, and coherency enhancement independently. Furthermore, the image processing unit 204 can also perform enhancement of edge detection degree, brightness, contrast, and high luminance as the enhancement image processing. That is, the enhancement image processing can apply each image quality index of edge detection degree, brightness, contrast, and high luminance enhancement independently. The method of adjusting each image quality index will be described later in detail. The image processing unit 204 can also adjust the image quality of the medical image based on image quality indexes such as gain and resolution other than noise reduction, edge enhancement, consistency enhancement, edge detection degree, brightness, contrast, and high luminance enhancement. Consistency enhancement is also called smoothness enhancement.
[0026] For simplicity of explanation, this embodiment will be described on the assumption that the emphasis image processing is applied only to images corresponding to the ultrasonic B-mode signals sent from the B-mode processing unit 202, but the emphasis image processing can also be applied to various images such as color Doppler, contrast imaging, elastography, attenuation imaging, M-mode, Doppler flow velocity waveforms, etc. Furthermore, the emphasis image processing can be applied not only to tomographic images, but also to rendered images, multiplanar transformation (MPR) images, and three-dimensional voxel images.
[0027] The main display screen 103, in cooperation with the image processing unit 204, converts the image information from there into optical information and displays a medical image on the screen. In the following explanations of each embodiment, an image output to the main display screen 103 will simply be referred to as an output image.
[0028] The memory 205 stores various information including B-mode information and Doppler information described in the description of the image processing unit 204. The memory 205 also appropriately stores information related to trajectories resulting from adjustment of each image quality index, past trajectories, and adjustable ranges of the image quality indexes, which will be described later. This memory 205 constitutes the storage unit in this embodiment.
[0029] The memory 205 may store live information temporarily or may store the acquired live information for a long period of time as evidence. The memory 205 also stores various data such as diagnostic information (e.g., patient ID, doctor's findings, etc.), diagnostic protocols, and various body marks.
[0030] The control unit 206 is a processor that realizes the function of an information processing device, and controls the overall processing of the medical image diagnostic system 100, which is an ultrasound diagnostic system. Specifically, the control unit 206 controls the processing of the transmission / reception unit 201, the B-mode processing unit 202, the Doppler processing unit 203, and the image processing unit 204 based on various setting requests, various control programs, and various data input by the user via the input device 102. Furthermore, the control unit 206 also controls the interface function between the input device 102 and the touch command screen 104.
[0031] The input device 102 is connected to the control unit 206 and has various switches, buttons, a trackball, a mouse, and / or a keyboard, etc., for inputting various instructions from the user, instructions for setting a region of interest (ROI), and instructions for setting various image quality conditions, etc., into the medical image diagnostic system 100.
[0032] The touch command screen 104 is an input / output device that functions both as a user input device and as an output device for providing information and images to the user. The touch command screen 104 outputs user input information to the control unit 206, and also obtains images such as thumbnail images and graphics required for device input from the image processing unit 204. This touch command screen 104 constitutes the display unit in this embodiment.
[0033] The touch command screen 104 may be used in conjunction with one or more user input devices such as a trackball, keyboard, joystick, mouse, and the like known in the art. The touch command screen 104 may also be used in conjunction with other screens, such as non-touch command screens. More than one user input and / or output device may also be provided. For example, the touch command screen 104 may be provided in conjunction with at least one other input device, such as a trackball, keyboard, joystick, or mouse.
[0034] Moreover, the medical image diagnostic system 100 according to this embodiment may be modified so that the main display screen 103 and the touch command screen 104 are the same device. Furthermore, the main display screen 103, the touch command screen 104, and / or the input device 102 may be separate devices that can be connected to the medical image diagnostic system 100 by wire or wirelessly.
[0035] Furthermore, the medical image diagnostic system 100 according to this embodiment may be modified so that the B-mode processing unit 202, the Doppler processing unit 203, the image processing unit 204, the memory 205, and / or the control unit 206 are provided as a function of a server in a location separate from those elements.
[0036] Fig. 3 is a functional block diagram for explaining the functions of the control unit 206 of the medical image diagnostic system 100 according to this embodiment. As shown in Fig. 3, in this embodiment, the control unit 206 includes a first image generating function 206a, a first image display function 206b, a second image generating function 206c, a second image display function 206d, a new image quality index calculating function 206e, and a regeneration display function 206f. The first image generating function 206a corresponds to the first image generating unit in this embodiment, the first image display function 206b corresponds to the first image display unit in this embodiment, the second image generating function 206c corresponds to the second image generating unit in this embodiment, the second image display function 206d corresponds to the second image display unit in this embodiment, the new image quality index calculating function 206e corresponds to the new image quality index calculating unit in this embodiment, and the regeneration display function 206f corresponds to the regeneration display unit in this embodiment.
[0037] In this embodiment, each processing function performed by the first image generating function 206a, the first image display function 206b, the second image generating function 206c, the second image display function 206d, the new image quality index calculating function 206e, and the regeneration display function 206f is stored in the memory 205 in the form of a program executable by a computer. The control unit 206 realizes the function corresponding to each program by reading and executing the program from the memory 205. In other words, the control unit 206 in a state in which each program has been read has each function shown in the control unit 206 in FIG. 3. 3, the first image generating function 206a, the first image display function 206b, the second image generating function 206c, the second image display function 206d, the new image quality index calculating function 206e, and the regeneration display function 206f are realized by a single control unit 206, but the control unit 206 may be configured by combining a plurality of independent processors, and each processor may execute a program to realize these functions. Also, when the first image generating function 206a, the first image display function 206b, the second image generating function 206c, the second image display function 206d, the new image quality index calculating function 206e, and the regeneration display function 206f realize various functions, they appropriately control and use the image processing unit 204, the memory 205, the input device 102, the main display screen 103, and the touch command screen 104.
[0038] <Image quality adjustment setting screen> Next, a description will be given of the image quality optimization process for medical images, which is realized by the medical image diagnostic system 100 according to this embodiment. In the medical image diagnostic system 100 according to this embodiment, the optimal image quality can be easily achieved by executing this image quality optimization process.
[0039] 4 is a diagram showing an example of an image quality adjustment setting screen W10 displayed on the touch command screen 104 of the medical image diagnostic system 100 according to this embodiment. That is, in the medical image diagnostic system 100 according to this embodiment, enhancement image processing is performed by the image processing unit 204 under the control of the control unit 206, and the image quality adjustment setting screen W10 is used as a graphical user interface for this image quality adjustment.
[0040] In the example of Fig. 4, the user can use the image quality adjustment setting screen W10 to perform image quality adjustment related to three types of image quality indices, namely, noise reduction, edge enhancement, and consistency enhancement, by discretely changing the values of the image quality indices. Note that the image quality indices that the user can adjust to display medical images are not limited to these three types, and various image quality indices can be adjusted. Fig. 4 shows a state in which the user has selected three types of image quality indices, namely, noise reduction, edge enhancement, and consistency enhancement, from among these multiple image quality indices, in order to adjust the image quality.
[0041] The first image quality adjustment button 301 to the fourth image quality adjustment button 304 are buttons drawn on the touch command screen 104. In this embodiment, the first image quality adjustment button 301 to the fourth image quality adjustment button 304 are configured with thumbnail images of medical images. These thumbnail images depict a plurality of output images with different image quality based on the data of the same medical image. Note that the thumbnail images may be images obtained by reducing the output image, or images obtained by setting a region of interest (ROI) in the output image and cutting out only the set region of interest.
[0042] Of the first image quality adjustment button 301 to the fourth image quality adjustment button 304 displayed on the touch command screen 104, the first image quality adjustment button 301 displays a thumbnail image that has been subjected to the same image processing as the medical image currently being displayed on the main display screen 103. This thumbnail image becomes the first image quality adjustment button 301. This is the medical image that is the focus of the current image quality adjustment, and in this embodiment, the set of image quality index values for obtaining this image quality is called an "anchor."
[0043] In the example shown in FIG. 4, three types of image quality indexes, namely noise reduction, edge emphasis, and consistency emphasis, are selected as the image quality indexes to be adjusted, and therefore, one each of the noise reduction value, edge emphasis value, and consistency emphasis value is selected as an anchor. Therefore, the "anchor" can also be regarded as a point determined by the values of these image quality indexes. In this way, a thumbnail image of the first image quality adjustment button 301 is generated based on the anchor, which is the value of the image index selected by the user. In addition, the thumbnail image of the first image quality adjustment button 301 is an image that is referred to by the user in order to compare the image quality with each of the thumbnail images of the second image quality adjustment button 302 to the fourth image quality adjustment button 304. Therefore, the thumbnail image of the first image quality adjustment button 301 is also called a reference image. In the following description, the thumbnail image of the first image quality adjustment button 301 is called a reference image. This reference image corresponds to the first thumbnail image in this embodiment.
[0044] By operating this image quality adjustment setting screen W10, the user can increase or decrease each of the image quality indices, noise reduction, edge enhancement, and consistency enhancement, from the anchor. The buttons for increasing or decreasing each of these image quality indices are second image quality adjustment button 302 to fourth image quality adjustment button 304. Specifically, of second image quality adjustment buttons 302 to fourth image quality adjustment buttons 304, second image quality adjustment button 302, which is located on the far left, is the button that the user selects when the value of the image quality index for noise reduction is to be increased or decreased, but the values of the other image quality indices are not to be changed.
[0045] Similarly, the third image quality adjustment button 303, located below the first image quality adjustment button 301 and in the center of the second image quality adjustment button 302 to the fourth image quality adjustment button 304, is a button that the user selects when he or she wants to increase or decrease the value of the image quality index for edge emphasis, but leave the values of the other image quality indexes unchanged. The fourth image quality adjustment button 304, located at the far right of the second image quality adjustment button 302 to the fourth image quality adjustment button 304, is a button that the user selects when he or she wants to increase or decrease the value of the image quality index for consistency emphasis, but leave the values of the other image quality indexes unchanged.
[0046] The thumbnail images displayed as the second image quality adjustment button 302 to the fourth image quality adjustment button 304 are thumbnail images generated based on the values of the respective image quality indices. Therefore, the user can predict the result of the change in the value of the image quality index by looking at the thumbnail images displayed as the second image quality adjustment button 302 to the fourth image quality adjustment button 304. This allows the user to adjust the value of the image quality index more appropriately. Each of the thumbnail images of the second image quality adjustment button 302 to the fourth image quality adjustment button 304 is a candidate image for calculating a new image quality index, which will be described later. Therefore, each of the thumbnail images of the second image quality adjustment button 302 to the fourth image quality adjustment button 304 is also called a candidate image. In the following description, the thumbnail images displayed as buttons for increasing or decreasing each image quality index are also called candidate images. This candidate image corresponds to the second thumbnail image in this embodiment.
[0047] When the user looks at the reference image and candidate images displayed on the touch command screen 104 and selects the image quality adjustment button for the most preferred image among the reference image and candidate images, the control unit 206 calculates a new image quality index based on the selection result.
[0048] Then, the value of the image quality index corresponding to the selected image quality adjustment button is set as a new anchor, a thumbnail image based on the image quality index value of the selected image quality adjustment button is displayed as a reference image, and image processing using the image quality index value corresponding to the selected image quality adjustment button is performed by the image processing unit 204, and the result is displayed as a medical image on the main display screen 103. In addition, the control unit 206 generates and displays a candidate image based on the calculated new image quality index. As described above, this new image quality index is an image quality index for generating a candidate image to be displayed on the touch command screen 104 in the step where the user selects the image quality adjustment button of the most preferred image from the reference image and the candidate images and then selects the next most preferred image. In the following description, this new image quality index is also called the image quality index of the next step.
[0049] 4, for example, when the user presses and selects the second image quality adjustment button 302, the image quality index value corresponding to this second image quality adjustment button 302 becomes the image quality index value of the new anchor. As a result, the thumbnail image of the second image quality adjustment button 302 becomes the thumbnail image of the first image quality adjustment button 301. Then, the control unit 206 calculates a new image quality index based on the selection result of the second image quality adjustment button 302, generates thumbnail images of each of the second image quality adjustment buttons 302 to fourth image quality adjustment buttons 304 based on the calculated new image quality index, and displays the generated thumbnail images as the second image quality adjustment buttons 302 to fourth image quality adjustment buttons 304.
[0050] As described above, the medical image diagnostic system 100 according to the present embodiment is configured, for example, by an ultrasound diagnostic system. In view of the real-time nature of this ultrasound diagnostic system, the image displayed on the main display screen 103 does not need to be a still image. Rather, the B-mode information sent from the B-mode processing unit 202 at a predetermined frame rate may be processed in real time by the image processing unit 204 and displayed as a moving image on the main display screen 103. That is, based on the value of the image quality index of the current anchor selected by the user, the medical image acquired at a predetermined frame rate may be processed in real time by the image processing unit 204 and displayed as a moving image on the main display screen 103. That is, it is also possible to image process the medical image acquired by the image processing unit 204 based on the value of the image quality index corresponding to the reference image, and display the real-time moving image on the main display screen 103.
[0051] In this way, when the user presses and selects one of the first image quality adjustment button 301 to the fourth image quality adjustment button 304, the medical image diagnostic system 100 calculates a new image quality index based on the selection result of the image quality adjustment button, displays the thumbnail image displayed in the selected image quality adjustment button as the first image quality adjustment button 301, and sets the value of the image quality index corresponding to the selected image quality adjustment button as a new anchor. Then, based on the calculated new image quality index, a candidate image is generated, and the generated candidate image is displayed again as the second image quality adjustment button 302 to the fourth image quality adjustment button 304, and waits for the user to press another image quality adjustment button to select it. This allows the user to continuously perform further image quality adjustment, and each time an image quality adjustment button is pressed and selected, a new image quality index is calculated based on the selection result of the image quality adjustment button, and thumbnail images for each of the second image quality adjustment button 302 to the fourth image quality adjustment button 304 are generated based on the calculated new image quality index, so that the step width for adjusting the image quality index value can be made variable, making it easier to reach an optimal image quality.
[0052] When the user reaches the image quality desired on the image quality adjustment setting screen W10 and ends the selection of the image quality index value, the user presses and selects an end button (not shown). This ends the setting of the image quality adjustment of the medical image.
[0053] <Image quality optimization (overview of Bayesian optimization)> As described above, the medical image diagnostic system 100 calculates the image quality index for the next step, that is, the new image quality index, based on the selection result of the thumbnail image displayed as each image quality adjustment button. The following method is used to calculate the new image quality index.
[0054] When calculating the new image quality index, the clinical value of the medical image desired by the user is implicit in the optimization of image quality. The clinical value can be output as a statistical observation value, i.e., preference image quality values, by the user selecting an image with high image quality for the user.
[0055] TIFF2024168827000002.tif17170
number
[0056] TIFF2024168827000005.tif36170
number
[0057] TIFF2024168827000007.tif11170
number
[0058] TIFF2024168827000009.tif45170
[0059] <Image quality optimization (likelihood model for image selection)> As described above, discrete options, that is, thumbnail images based on the values of the image quality indexes, are presented on the touch command screen 104. Therefore, in the Bayesian optimization method according to the present embodiment, the Bradley-Terry-Luce (BTL) model is adopted as a likelihood model for allowing a user to select a thumbnail image with the image quality of the user's preference from the reference images and candidate images displayed on the touch command screen 104.
[0060] TIFF2024168827000010.tif17170
number
[0061] The BTL model can also be applied to comparing three or more items. For example, the probability of selecting A from three items A, B, and C is expressed as in equation (5).
number
[0062] In this embodiment, the BTL model is used as the likelihood model of discrete selection, but the likelihood model of discrete selection is not limited to this. For example, the likelihood model of discrete selection includes the Thurstone-Mosteller model in addition to the BTL model, and in this embodiment, the Thurstone-Mosteller model may be used instead of the BTL model.
[0063] TIFF2024168827000014.tif22170
number
number
[0064] TIFF2024168827000018.tif22170
number
[0065] TIFF2024168827000021.tif11170
number
[0066] TIFF2024168827000024.tif6170
number
[0067] TIFF2024168827000027.tif17170
number
[0068] The acquisition function is not limited to the expectation improvement function, but may be, for example, an Upper Confidence Bounds (UCB) or Probability of Improvement (PI) function.
[0069] Fig. 5 is a flow chart for explaining the contents of the image quality optimization process executed by the medical image diagnostic system 100 according to this embodiment. That is, the process for setting the value of the image quality index explained using Fig. 4 is realized by the medical image diagnostic system 100 executing the image quality optimization process shown in Fig. 5.
[0070] 5 is executed when the user operates the input device 102 or the touch command screen 104 to instruct the medical image diagnostic system 100 to start the image quality optimization process. In other words, this is executed when the user wishes to optimize the image quality of a medical image to be generated in the future.
[0071] As shown in FIG. 5, when the image quality optimization process is executed, first, the medical image diagnostic system 100 generates a reference image (step S10). Specifically, the first image generating function 206a in the control unit 206 of the medical image diagnostic system 100 controls the image processing unit 204 to generate a thumbnail image of the first image quality adjustment button 301 as a reference image based on the value of the image quality index of the anchor. In step S10, the same image quality index value as that of the medical image displayed on the main display screen 103 is used as the image quality index value of this anchor. Note that, when generating the thumbnail image of the first image quality adjustment button 301, the control unit 206 controls the image processing unit 204 to generate a thumbnail image based on the anchor in cooperation with the image processing unit 204. As described above, this reference image corresponds to the first thumbnail image in this embodiment.
[0072] 5, the medical image diagnostic system 100 displays the reference image generated in step S10 (step S12). Specifically, the first image display function 206b in the control unit 206 of the medical image diagnostic system 100 displays a thumbnail image based on the value of the image quality index of the anchor as a first image quality adjustment button 301 on the image quality adjustment setting screen W10 of the touch command screen 104.
[0073] Next, as shown in FIG. 5, the medical image diagnostic system 100 generates candidate images (step S14). Specifically, the second image generating function 206c in the control unit 206 of the medical image diagnostic system 100 increases or decreases the value of the image quality index from the anchor to calculate the image quality index value of each thumbnail image of the second image quality adjustment button 302 to the fourth image quality adjustment button 304, and generates thumbnail images of the second image quality adjustment button 302 to the fourth image quality adjustment button 304 as candidate images based on the calculated image quality index value. In this embodiment, it is necessary to generate three thumbnail images as candidate images in the image quality adjustment setting screen W10 shown in FIG. 4 described above. Note that, similarly to step S10, when generating thumbnail images around the anchor, the control unit 206 controls the image processing unit 204 to generate these thumbnail images in cooperation with the image processing unit 204. As described above, this candidate image corresponds to the second thumbnail image in this embodiment.
[0074] In this embodiment, as shown in FIG. 4 above, it is necessary to calculate three sets of image quality index values to generate thumbnail images for each of the second image quality adjustment button 302 to the fourth image quality adjustment button 304. However, the medical image diagnostic system 100 may calculate two sets of image quality indexes when image quality adjustment is performed for two types of image quality indexes, and may calculate four or more sets of image quality indexes when image quality adjustment is performed for four or more types of image quality indexes.
[0075] Next, as shown in FIG. 5, the medical image diagnostic system 100 displays candidate images (step S16). Specifically, the second image display function 206d in the control unit 206 of the medical image diagnostic system 100 displays thumbnail images of the second image quality adjustment button 302 to the fourth image quality adjustment button generated in step S14 on the image quality adjustment setting screen W10 of the touch command screen 104. In the image quality adjustment setting screen W10 shown in FIG. 4 described above, three thumbnail images are displayed on the touch command screen 104 as the second image quality adjustment button 302 to the fourth image quality adjustment button 304. In this embodiment, as shown in FIG. 4, the three thumbnail images are arranged horizontally below the thumbnail image of the first image quality adjustment button 301 displayed in step S12. By arranging thumbnail images with image quality index values changed around the anchor thumbnail image in this way, the user can intuitively grasp how to change the image quality index value from the current image quality index value to approach the target image quality.
[0076] When the medical image diagnostic system 100 displays thumbnail images of the first image quality adjustment button 301 to the fourth image quality adjustment button 304, it assigns to each thumbnail image the function of an image quality selection button corresponding to the image quality index value of that thumbnail image. In other words, the function of a button for selecting the image quality index value of this anchor is assigned to each thumbnail image.
[0077] Next, as shown in Fig. 5, the medical image diagnostic system 100 accepts the selection of the reference image and the candidate image (step S18). Specifically, the new image quality index calculation function 206e in the control unit 206 of the medical image diagnostic system 100 accepts the selection of the reference image and the candidate image by the user via the input device 102 or the touch command screen 104. In the example shown in Fig. 4, the medical image diagnostic system 100 accepts the selection of the first image quality adjustment button 301 to the fourth image quality adjustment button 304 via the input device 102 or the touch command screen 104.
[0078] TIFF2024168827000030.tif21170
[0079] TIFF2024168827000031.tif21170
[0080] TIFF2024168827000032.tif32170
[0081] TIFF2024168827000033.tif56170
[0082] 5, the medical image diagnostic system 100 displays a new reference image (step S28). Specifically, the regeneration display function 206f in the control unit of the medical image diagnostic system 100 causes the first image display function 206b to display a new thumbnail image based on the image quality index value of the new anchor generated in step S26 as the first image quality adjustment button 301 on the image quality adjustment setting screen W10 of the touch command screen 104.
[0083] 5, the medical image diagnostic system 100 generates new candidate images (step S30). Specifically, the regeneration display function 206f in the control unit of the medical image diagnostic system 100 causes the second image generation function 206c to generate new thumbnail images of the second image quality adjustment button 302 to the fourth image quality adjustment button 304 as new candidate images based on the set of image quality index values constructed by the new image quality index calculation function 206e in step S24.
[0084] TIFF2024168827000034.tif61170
[0085] As in step S10, when generating thumbnail images around the anchor, the control unit 206 controls the image processing unit 204 to generate these thumbnail images in cooperation with the image processing unit 204. As described above, the thumbnail images of the second image quality adjustment button 302 to the fourth image quality adjustment button 304 correspond to the second thumbnail image in this embodiment.
[0086] 5, the medical image diagnostic system 100 displays new candidate images (step S32). Specifically, the regeneration display function 206f in the control unit 206 of the medical image diagnostic system 100 causes the second image display function 206d to display the thumbnail images of the second image quality adjustment button 302 to the fourth image quality adjustment button generated in step 30 as new candidate images on the image quality adjustment setting screen W10 of the touch command screen 104.
[0087] When the medical image diagnostic system 100 displays thumbnail images of the first image quality adjustment button 301 to the fourth image quality adjustment button 304, it assigns to each thumbnail image the function of an image quality selection button corresponding to the image quality index value of that thumbnail image. In other words, the function of a button for selecting the image quality index value of this anchor is assigned to each thumbnail image.
[0088] 5, the medical image diagnostic system 100 displays a medical image using the image quality index value of the selected image quality adjustment button (step S34). Specifically, the regeneration display function 206f in the control unit 206 of the medical image diagnostic system 100 displays a medical image using the image quality index value of the image quality adjustment button selected by the user in step S18 on the main display screen 103. That is, the medical image diagnostic system 100 generates a medical image using the same image quality index value as the image quality index value used when generating a thumbnail image of the first image quality adjustment button 301, and displays the generated medical image on the main display screen 103.
[0089] 5, the medical image diagnostic system 100 judges whether the image quality desired by the user has been reached (step S36). Specifically, the regeneration display function 206f in the control unit 206 of the medical image diagnostic system 100 judges whether the image quality desired by the user has been reached based on whether an end button (not shown) or a continue button (not shown) has been selected.
[0090] Then, when the user presses the continue button and it is determined that the image quality desired by the user has not been reached (step S36: No), the process returns to step S18, and the medical image diagnostic system 100 repeats the processes from step S18 to step S36 until the image quality desired by the user is reached. Note that, in this embodiment, the medical image diagnostic system 100 determines that the image quality desired by the user has not been reached when the user presses the continue button, but it may be configured to determine that the image quality desired by the user has not been reached when the user presses an image quality adjustment button displayed in step S28 and step S32 instead of the continue button.
[0091] On the other hand, when it is determined that the image quality desired by the user is reached by pressing the end button (step S36: Yes), the image quality optimization process according to this embodiment ends. As a result, the medical image displayed on the main display screen 103 becomes an image with high clinical value for the user.
[0092] TIFF2024168827000035.tif32170
[0093] In reality, image processing in the image processing unit 204 of the above-mentioned medical image diagnostic system 100 often involves a plurality of parameters. In such cases, it is necessary to convert the value of the image quality index selected by the user into the parameter used by the image processing unit 204 by calculation. By converting the value of the image quality index into a parameter in this manner, it becomes possible to indirectly use the value of the image quality index selected by the user to adjust the image quality of the medical image.
[0094] For example, in the case of three types of image quality indexes, noise reduction N, edge enhancement E, and consistency enhancement C, if the image quality index is defined as S={N,E,C} and the parameters are defined as P={p1,p2,...,pn}, the transformation by the calculation can be expressed by the function P=F(S). If this function is linear, F can be expressed as a matrix, as P=FS.
[0095] 5, the first image generating function 206a of the control unit 206 in step S10, the second image generating function 206c of the control unit 206 in step S14, and the new image quality index calculation function 206e in step S22 may calculate a plurality of parameters from the value of the image quality index selected by the user, and control the image processing unit 204 based on these calculated parameters to generate various thumbnail images. Alternatively, the first image generating function 206a of the control unit 206 in step S10, the second image generating function 206c of the control unit 206 in step S14, and the new image quality index calculation function 206e in step S22 may output the value of the image quality index selected by the user to the image processing unit 204, and the image processing unit 204 may calculate a plurality of parameters from the value of the image quality index, and generate various thumbnail images based on these calculated parameters.
[0096] [Variation 1] In the first embodiment described above, each value of the image quality index for the next step is calculated based on the selection result of the thumbnail image displayed on each image quality adjustment button, so it is not possible to select whether to increase or decrease the value of the image quality index for the next step, but it is also possible to modify the embodiment so that the user can select whether to increase or decrease the value of the image quality index for the next step. Below, the case where this modification is applied to the first embodiment is referred to as Modification 1, and the differences from the first embodiment described above are described.
[0097] Fig. 6 is a diagram showing an example of an image quality adjustment setting screen W10 displayed on the touch command screen of the medical image diagnostic system 100 according to the first modification, and corresponds to the above-mentioned Fig. 4. As shown in Fig. 6, on the image quality adjustment setting screen W10 according to this modification, switching buttons 302a, 302b, 303a, 303b, 304a, and 304b for switching between increasing and decreasing the image quality index for the next step are displayed below the second image quality adjustment button 302 to the fourth image quality adjustment button 304, respectively.
[0098] TIFF2024168827000036.tif41170
[0099] TIFF2024168827000037.tif27170
[0100] As described above, according to the medical image diagnostic system 100 relating to variant example 1 of this embodiment, the image quality index of the next step can be increased or decreased for the image quality index of the new anchor based on the user's operation by operating the switch button, so that the user can predict the result of the change in the value of the image quality index in advance and avoid changes that are not intended by the user.
[0101] Second Embodiment In the medical image diagnostic system 100 according to the first embodiment described above, examples of the image quality adjustment setting screen W10 displayed on the touch command screen 104 have been described. However, in addition to these described examples, there are other modified examples in which the interface is changed. For example, in the medical image diagnostic system 100 according to the first embodiment described above, medical images in which one type of image quality index has been changed can be confirmed as thumbnail images, but medical images in which two or more types of image quality indexes have been changed simultaneously cannot be confirmed. Therefore, in the second embodiment, an example will be described in which, in one screen displayed on the touch command screen 104, in addition to thumbnail images in which one type of image quality index has been changed, a composite image in which multiple image quality indexes have been changed simultaneously can be confirmed. The following describes the parts that are different from the first embodiment described above.
[0102] FIG. 7 is a diagram showing an example of an image quality adjustment setting screen W20 displayed on the touch command screen 104 of the medical image diagnostic system 100 according to the second embodiment, and corresponds to FIG. 4 in the first embodiment described above. As shown in FIG. 7, in the image quality adjustment setting screen W20 according to this embodiment, in addition to the values of the three types of image quality indices, noise reduction, edge enhancement, and consistency enhancement, the values of all three types of image quality indices, noise reduction, edge enhancement, and consistency enhancement, can be adjusted on one screen. That is, in addition to the image quality adjustment buttons for adjusting the values of the image quality indices of noise reduction, edge enhancement, and consistency enhancement, the image quality adjustment setting screen W20 according to this embodiment has a fifth image quality adjustment button 305 for adjusting the values of all three types of image quality indices, noise reduction, edge enhancement, and consistency enhancement, added thereto. In this way, the image quality adjustment setting screen W20 according to this embodiment displays four image quality adjustment buttons for adjusting the image quality for the three image quality indices, noise reduction, edge enhancement, and consistency enhancement. That is, the number of thumbnail images corresponding to image quality adjustment buttons for adjusting image quality, displayed on the image quality adjustment setting screen W20 according to this embodiment, is equal to or greater than the number of types of image quality indexes.
[0103] Also, as shown in FIG. 7, on the image quality adjustment setting screen W20 of this embodiment, the first image quality adjustment button 301 is located above the second image quality adjustment button, and below the first image quality adjustment button 301, from left to right, the second image quality adjustment button 302, the third image quality adjustment button 303, and the fourth image quality adjustment button 304 are located, and the fifth image quality adjustment button 305 is located above the fourth image quality adjustment button 304.
[0104] TIFF2024168827000038.tif31170
[0105] TIFF2024168827000039.tif22170
[0106] TIFF2024168827000040.tif28170
[0107] TIFF2024168827000041.tif27170
[0108] TIFF2024168827000042.tif27170
[0109] TIFF2024168827000043.tif31170
[0110] As described above, according to the medical image diagnostic system 100 of this embodiment, in addition to adjusting each of the values of the three types of image quality indices, i.e., noise reduction, edge enhancement, and consistency enhancement, the values of all three types of image quality indices, i.e., noise reduction, edge enhancement, and consistency enhancement, can be adjusted on a single screen, making it easy for users to adjust the image quality of medical images.
[0111] [Modification 2] In the second embodiment described above, each value of the image quality index for the next step is calculated based on the selection result of the thumbnail image displayed on each image quality adjustment button, so it is not possible to select whether to increase or decrease the value of the image quality index for the next step, but it is possible to modify the embodiment so that the user can select whether to increase or decrease the value of the image quality index for the next step. Below, the case where this modification is applied to the second embodiment is referred to as Modification 2, and the differences from the second embodiment described above are explained.
[0112] Fig. 9 is a diagram showing an example of an image quality adjustment setting screen W20 displayed on the touch command screen 104 of the medical image diagnostic system 100 according to the second modification, and corresponds to Fig. 7 described above. As shown in Fig. 9, the image quality adjustment setting screen W20 according to this modification has switching buttons 302a, 302b, 303a, 303b, 304a, 304b, 305a, and 305b for switching between increasing and decreasing the image quality index of the next step displayed below each of the second image quality adjustment button 302 to the fifth image quality adjustment button 305. Note that the switching buttons 302a, 302b, 303a, 303b, 304a, and 304b are the same as those in the first modification of the first embodiment described above, and therefore will not be described here.
[0113] TIFF2024168827000044.tif70170
[0114] As described above, according to the medical image diagnostic system 100 of the second variant example, the image quality index of the next step can be increased or decreased for the image quality index of the new anchor based on the user's operation by operating the switch button, so that the user can predict the result of the change in the value of the image quality index in advance and avoid changes that are not intended by the user.
[0115] Third Embodiment In the above-described first and second embodiments, three types of image quality indexes, namely, noise reduction, edge enhancement, and consistency enhancement, are adjusted on one screen, but four types of image quality indexes may be adjusted on one screen. Therefore, in the third embodiment, an example in which four types of image quality indexes can be adjusted on one screen displayed on the touch command screen 104 will be described. The following describes the differences from the above-described first embodiment.
[0116] Fig. 10 is a diagram showing an example of an image quality adjustment setting screen W30 displayed on the touch command screen 104 of the medical image diagnostic system 100 according to the third embodiment, and corresponds to Fig. 4 in the above-mentioned first embodiment. As shown in Fig. 10, in the image quality adjustment setting screen W30 according to this embodiment, in addition to image quality adjustment buttons for adjusting the values of the three types of image quality indexes, namely noise reduction, edge emphasis, and consistency emphasis, a sixth image quality adjustment button 306 for adjusting the value of the image quality index for brightness is added.
[0117] The sixth image quality adjustment button 306 is a button that the user selects when increasing or decreasing the brightness image quality index value but leaving the other image quality index values unchanged. In the example shown in Fig. 10, the sixth image quality adjustment button 306 is, for example, located above the fourth image quality adjustment button 304.
[0118] As described above, according to the medical image diagnostic system 100 of this embodiment, image quality adjustment buttons for adjusting each of the four types of image quality indexes can be displayed on the touch command screen 104, so that the four types of image quality indexes can be adjusted on a single screen, making it possible to adjust many image quality indexes at once, making it easier for users to adjust the image quality of medical images.
[0119] In the above-described third embodiment, four types of image quality indexes can be adjusted on one screen, but five or more types of image quality indexes may be adjustable on one screen if they can be displayed on the touch command screen 104. If five or more types of image quality indexes cannot be displayed on one screen, the user must operate the touch command screen 104 to select which image quality index to display and adjust on one screen among the multiple types of image quality indexes. For example, if there are ten types of image quality indexes that the user can adjust, it is necessary for the user to be able to select four of them.
[0120] [Modification 3] In the first to third embodiments described above, the image quality adjustment setting screens W10, W20, and W30 may be modified to display images at the start of image quality adjustment in order to confirm changes in image quality from images at the start of image quality adjustment in the thumbnail images of the first image quality adjustment button 301 to the sixth image quality adjustment button 306. Below, the case where this modified example is applied to the second embodiment will be referred to as Modification Example 3, and the differences from the second embodiment described above will be described.
[0121] Fig. 11 is a diagram showing an example of an image quality adjustment setting screen W20 displayed on the touch command screen 104 of the medical image diagnostic system 100 according to Modification 3, and corresponds to the above-mentioned Fig. 7. As shown in Fig. 11, the image quality adjustment setting screen W20 according to Modification 3 displays a thumbnail image 401 in addition to the first image quality adjustment button 301 to the fifth image quality adjustment button 305.
[0122] The thumbnail image 401 is an image at the start of image quality adjustment. That is, it is an image to which the value of the image quality index of the thumbnail image of the first image quality adjustment button 301 generated in step S10 of the image quality optimization process described above is applied. This thumbnail image 401 is also called an initial image. As shown in FIG. 11, the thumbnail image 401 is arranged, for example, above the third image quality adjustment button 303. Even if the image quality of the thumbnail images of the first image quality adjustment button 301 to the fifth image quality adjustment button 305 is changed by pressing and selecting any one of the image quality adjustment buttons of the first image quality adjustment button 301 to the fifth image quality adjustment button 305, the thumbnail image 401 does not change in image quality, and an image at the start of image quality adjustment is displayed as the thumbnail image 401 on the touch command screen 104. In addition, in the third modification of this embodiment, no function is assigned to the thumbnail image 401. Therefore, even if the user presses the thumbnail image 401, the image quality of the other thumbnail images of the first image quality adjustment button 301 to the fifth image quality adjustment button 305 will not be changed.
[0123] As described above, the medical image diagnostic system 100 according to variant example 3 displays a thumbnail image 401, which is the image at the start of image quality adjustment, on the image quality adjustment setting screen W20, so that the user can easily compare how the image quality of the image has changed since the start of image quality adjustment.
[0124] Although this modification has been described as a modification of the second embodiment, it can also be applied to the first and third embodiments.
[0125] [Other Modifications of the First to Third Embodiments] In addition, the image processing in the above-mentioned first to third embodiments is based on enhancement image processing using multi-resolution decomposition processing and a nonlinear anisotropic diffusion filter, but the image processing or signal processing may be any of a linear spatial filter, a median filter, input / output curve processing, and gain adjustment processing.
[0126] In addition, the image quality indexes to be optimized in the above-mentioned first to third embodiments are premised on image processing parameters or indexes convertible to parameters in the image processing unit 204, but the image quality indexes to be optimized are not limited to these. In the transmitting / receiving unit 201 of the medical image diagnostic system 100, the ultrasonic transmission / reception conditions that can be changed related to image quality include the transmission waveform (wave number and frequency), the reception center frequency, the reception frequency band, the reception aperture, or the sound speed inside the object preset for the reception signal processing. Therefore, the image quality index to be optimized may be at least any of the resolutions of the transmission waveform (wave number and frequency), the reception center frequency, the reception frequency band, the reception aperture, or the sound speed inside the object preset for the reception signal processing, which are controlled by the transmitting / receiving unit 201 of the medical image diagnostic system 100.
[0127] In the first to third embodiments described above, the reflected signals from the subject are received and processed as ultrasound signals, so the image quality depends on the depth of the subject. Therefore, uniformity of image quality can be expected by setting the image quality indexes described above for each depth. Therefore, a different image quality index may be prepared for each depth, and the medical image diagnostic system 100 may optimize image quality for each depth.
[0128] [Fourth embodiment] The medical image diagnostic system 100 according to the first to third embodiments described above has been described as being configured as an ultrasound diagnostic system, but the image quality optimization process described above can be applied to various medical diagnostic systems, not limited to ultrasound diagnostic systems. Therefore, in the fourth embodiment, the medical image diagnostic system 100 will be described as being applied to a magnetic resonance imaging (MRI) system.
[0129] FIG. 12 is a diagram for explaining the configuration of a medical image diagnostic system 100 according to the fourth embodiment. As shown in FIG. 12, in this embodiment, the medical image diagnostic system 100 is configured by a magnetic resonance imaging system 1100. The medical image diagnostic system 100 configured by the magnetic resonance imaging system 1100 is configured to include, for example, a static magnetic field magnet 1101, a static magnetic field power supply (not shown), a gradient magnetic field coil 1103, a gradient magnetic field power supply 1104, a bed 1105, a bed control circuit 1106, a transmission coil 1107, a transmission circuit 1108, a receiving coil 1109, a receiving circuit 1110, a sequence control circuit 1120, and a data processing device 1200. Note that the subject P (for example, a human body) is shown for ease of understanding and is not included in the configuration of the magnetic resonance imaging system 1100.
[0130] The static magnetic field magnet 1101 is a magnet formed in a hollow, approximately cylindrical shape, and generates a static magnetic field in the internal space. The static magnetic field magnet 1101 is, for example, a superconducting magnet, etc., and is excited by receiving a current from a static magnetic field power supply. The static magnetic field power supply supplies a current to the static magnetic field magnet 1101. As another example, the static magnetic field magnet 1101 may be a permanent magnet, in which case the magnetic resonance imaging system 1100 may not include a static magnetic field power supply. Also, the static magnetic field power supply may be provided separately from the magnetic resonance imaging system 1100.
[0131] The gradient magnetic field coil 1103 is a hollow coil formed in a substantially cylindrical shape, and is disposed inside the static magnetic field magnet 1101. The gradient magnetic field coil 1103 is formed by combining three coils corresponding to the mutually orthogonal X, Y, and Z axes, and these three coils are individually supplied with current from a gradient magnetic field power supply 1104 to generate gradient magnetic fields whose magnetic field strength changes along the X, Y, and Z axes. The gradient magnetic fields of the X, Y, and Z axes generated by the gradient magnetic field coil 1103 are, for example, a slice gradient magnetic field Gs, a phase encoding gradient magnetic field Ge, and a readout gradient magnetic field Gr. The gradient magnetic field power supply 1104 supplies current to the gradient magnetic field coil 1103.
[0132] The bed 1105 includes a top plate 1105a on which the subject P is placed, and under the control of a bed control circuit 1106, the top plate 1105a is inserted into the cavity (imaging port) of the gradient magnetic field coil 1103 with the subject P placed thereon. The bed 1105 is usually installed so that its longitudinal direction is parallel to the central axis of the static magnetic field magnet 1101. Under the control of the data processing device 1200, the bed control circuit 1106 drives the bed 1105 to move the top plate 1105a in the longitudinal direction and up and down directions.
[0133] The transmission coil 1107 is disposed inside the gradient magnetic field coil 1103, and generates a high-frequency magnetic field upon receiving an RF pulse from a transmission circuit 1108. The transmission circuit 1108 supplies the transmission coil 1107 with an RF pulse corresponding to a Larmor frequency determined by the type of target atom and the magnetic field strength.
[0134] The receiving coil 1109 is disposed inside the gradient magnetic field coil 1103, and receives a magnetic resonance signal emitted from the subject P due to the influence of the high frequency magnetic field. Upon receiving the magnetic resonance signal, the receiving coil 1109 outputs the received magnetic resonance signal to the receiving circuit 1110.
[0135] The above-mentioned transmitting coil 1107 and receiving coil 1109 are merely examples. The coils may be configured by combining one or more of a coil having only a transmitting function, a coil having only a receiving function, or a coil having a transmitting and receiving function.
[0136] The receiving circuit 1110 detects a magnetic resonance signal output from the receiving coil 1109, and generates magnetic resonance data based on the detected magnetic resonance signal. Specifically, the receiving circuit 1110 generates magnetic resonance data by digitally converting the magnetic resonance signal output from the receiving coil 1109. The receiving circuit 1110 also transmits the generated magnetic resonance data to the sequence control circuit 1120. The receiving circuit 1110 may be provided on the side of a gantry device that includes a static magnetic field magnet 1101, a gradient magnetic field coil 1103, and the like.
[0137] The sequence control circuit 1120 drives the gradient magnetic field power supply 1104, the transmission circuit 1108, and the reception circuit 1110 based on sequence information transmitted from the data processing device 1200, thereby imaging the subject P. Here, the sequence information is information that defines a procedure for performing imaging. The sequence information defines the strength of the current that the gradient magnetic field power supply 1104 supplies to the gradient magnetic field coil 1103 and the timing of supplying the current, the strength of the RF pulse that the transmission circuit 1108 supplies to the transmission coil 1107 and the timing of applying the RF pulse, the timing at which the reception circuit 1110 detects a magnetic resonance signal, and the like.
[0138] Furthermore, when the sequence control circuit 1120 drives the gradient magnetic field power supply 1104, the transmission circuit 1108, and the reception circuit 1110 to image the subject P, and receives magnetic resonance data from the reception circuit 1110, the sequence control circuit 1120 transfers the received magnetic resonance data to the data processing device 1200.
[0139] The data processing device 1200 performs overall control of the magnetic resonance imaging system 1100 and processes signals received from the sequence control circuit 1120. As shown in Fig. 13, the data processing device 1200 includes a processing circuit 1210, a memory 1201, an input device 1203, and a display 1204. The processing circuit 1210 includes an interface function 1211, a control function 1212, and an image processing function 1213.
[0140] In this embodiment, each processing function performed by the interface function 1211, the control function 1212, and the image processing function 1213 is stored in the memory 1201 in the form of a program executable by a computer. The processing circuit 1210 is a processor that realizes the function corresponding to each program by reading the program from the memory 1201 and executing it. In other words, the processing circuit 1210 in a state in which each program has been read has each function shown in the processing circuit 1210.
[0141] The processing circuit 1210 transmits sequence information to the sequence control circuit 1120 through the interface function 1211, and receives magnetic resonance data from the sequence control circuit 1120. Furthermore, upon receiving the magnetic resonance data, the processing circuit 1210 having the interface function 1211 stores the received magnetic resonance data in the memory 1201.
[0142] The magnetic resonance data stored in the memory 1201 is arranged in k-space by the control function 1212. As a result, the memory 1201 stores the k-space data.
[0143] The memory 1201 stores magnetic resonance data received by a processing circuit 1210 having an interface function 1211, k-space data placed in k-space by a processing circuit 1210 having a control function 1212, image data generated by a processing circuit 1210 having an image processing function 1213, etc.
[0144] The processing circuitry 1210 performs overall control of the magnetic resonance imaging system 1100 using the control function 1212, and controls imaging, image generation, image display, and the like. For example, the processing circuitry 1210 having the control function 1212 receives input of imaging conditions (imaging parameters, etc.) on a GUI, and generates sequence information according to the received imaging conditions. In addition, the processing circuitry 1210 having the control function 1212 transmits the generated sequence information to the sequence control circuit 1120.
[0145] The processing circuitry 1210 reads out the k-space data from the memory 1201 using an image processing function 1213, and performs reconstruction processing such as Fourier transform on the read out k-space data to generate a magnetic resonance image. The image processing function 1213 also performs the emphasized image processing in the first embodiment.
[0146] The processing circuit 1210 acquires data, images, etc. for image processing by the image processing function 1213 from the memory 1201 via the interface function 1211 .
[0147] The input device 1203 accepts various instructions and information input from an operator. The input device 1203 is, for example, a pointing device such as a mouse or a trackball, a selection device such as a mode changeover switch, or an input device such as a keyboard. The input device 1203 also includes a touch command screen formed on a display 1204 described later.
[0148] The display 1204 displays a GUI for receiving input of imaging conditions and images generated by the control function 1212 under the control of the control function 1212, etc. The display 1204 is, for example, a display device such as a liquid crystal display. The display 1204 is an example of a display unit. The display 1204 has a mouse, a keyboard, buttons, a panel switch, a touch command screen, a foot switch, a trackball, a joystick, etc.
[0149] In the magnetic resonance imaging system 1100 described above, similarly to the ultrasound diagnostic systems described in the first to third embodiments, the image quality optimization process shown in FIG. 5 can be executed to change the value of the image quality index and adjust the image quality of the medical image.
[0150] In this case, the medical image for which the value of the image quality index is adjusted is a magnetic resonance image that has been subjected to reconstruction processing from k-space data. For example, image quality indexes for magnetic resonance images include noise reduction, edge enhancement, and consistency enhancement, similar to those in ultrasound diagnostic systems. As a GUI for adjusting the value of the image quality index in the image processing function 1213, the image quality adjustment setting screens W10, W20, and W30 as shown in the first to fourth embodiments described above are formed on the touch command screen on the display 1204.
[0151] The operation and display format of the image quality adjustment setting screens W10, W20, and W30 are the same as those of the first to third embodiments described above, except that the thumbnail images displayed on each image quality adjustment button are generated based on a magnetic resonance image. That is, the image quality optimization process shown in Fig. 5 is executed by the processing circuit 1210, and the value of the image quality index of the image quality optimal for the user is set. When this image quality optimization process is executed, the image processing function 1213 performs the first image generation function 206a, the first image display function 206b, the second image generation function 206c, the second image display function 206d, and the regeneration display function 206f described above, and the control function 1212 performs the new image quality index calculation function 206e.
[0152] As described above, according to the medical image diagnostic system 100 of this embodiment, the medical image diagnostic system 100 can be configured by the magnetic resonance imaging system 1100. In this manner, it is possible to adjust the value of the image quality index for medical images captured by various medical image diagnostic systems, such as an ultrasound diagnostic system, a magnetic resonance imaging system, an X-ray computed tomography system, and a positron emission tomography system.
[0153] The term "processor" used in the above description means a circuit such as a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)). The processor realizes its function by reading and executing a program stored in the memory 205 or 1201. Instead of storing a program in the memory 205 or 1201, the processor may be configured to directly incorporate the program in its circuit. In this case, the processor realizes its function by reading and executing the program incorporated in its circuit. The processor is not limited to being configured as a single processor circuit, and may be configured as a single processor by combining multiple independent circuits to realize its function. Furthermore, the multiple components in FIG. 3 may be integrated into a single processor to realize its function.
[0154] Although several embodiments have been described above, these embodiments are presented only as examples and are not intended to limit the scope of the invention. The novel device and method described in this specification can be implemented in various other forms. In addition, various omissions, substitutions, and modifications can be made to the forms of the device and method described in this specification without departing from the spirit of the invention. The appended claims and their equivalents are intended to include such forms and modifications that fall within the scope and spirit of the invention.
[0155] Regarding the above embodiment, the following supplementary notes are disclosed as one aspect and optional features of the invention.
[0156] (Appendix 1) a first image generating unit that uses a value of an image quality index selected by a user from among a plurality of types of image quality indexes for displaying a medical image as an anchor and generates a thumbnail image of the medical image based on the anchor as a first thumbnail image; a first image display unit that displays the first thumbnail image generated by the first image generation unit on a display unit; a second image generating unit that generates a plurality of thumbnail images as second thumbnail images by increasing or decreasing the plurality of types of image quality indexes from the anchor with respect to the medical image; a second image display unit that displays the plurality of second thumbnail images generated by the second image generation unit on the display unit; a new image quality index calculation unit that allows the first thumbnail image and the second thumbnail image to be selected and calculates a new image quality index adjusted with a variable step width based on a selection result of the first thumbnail image and the second thumbnail image; a regeneration display unit that uses a value of an image index corresponding to the first thumbnail image or the second thumbnail image selected by a user from among the first thumbnail image or the plurality of second thumbnail images as a new anchor to cause the first image generation unit to generate a new first thumbnail image and cause the first image display unit to display the new first thumbnail image, and causes the second image generation unit to generate a new second thumbnail image based on the value of the new image quality index calculated by the new image quality index calculation unit and causes the second image display unit to display the new second thumbnail image.
[0157] (Appendix 2) The second image generating section may generate a composite image based on image indices obtained by increasing or decreasing the plurality of types of image indices from the anchor and combining the image indices, as one of the plurality of second thumbnail images.
[0158] (Appendix 3) The second image display section may display the composite image as one of the plurality of second thumbnail images.
[0159] (Appendix 4) The new image quality index calculation section may switch between increasing and decreasing the new image quality index based on a user operation.
[0160] (Appendix 5) The calculation of the new image quality index may depend on the probability of selection of the first thumbnail image and the second thumbnail image according to a Bradley-Terry-Luce (BTL) model or a Thurstone-Mosteller model.
[0161] (Appendix 6) The calculation of the new image quality index may be optimized by probabilistic inference using Bayes' theorem, the optimization being performed by maximizing an acquisition function.
[0162] (Appendix 7) The probabilistic inference using Bayes' theorem may be performed from a prior distribution model following a Gaussian process.
[0163] (Appendix 8) The first image generation unit and the second image generation unit may calculate a plurality of parameters from the value of the image quality index, and perform image processing or signal processing based on the calculated parameters to generate the first thumbnail image and the second thumbnail image, respectively.
[0164] (Appendix 9) The image processing or signal processing may be any one of a multi-resolution decomposition process, a nonlinear anisotropic diffusion filter, a linear spatial filter, a median filter, an input / output curve process, and a gain adjustment process.
[0165] (Appendix 10) The medical image may be an image captured by an ultrasound diagnostic system.
[0166] (Appendix 11) The first image generation unit and the second image generation unit may calculate a plurality of parameters from the value of the image quality index, transmit and receive ultrasound under conditions of the calculated parameters, and generate the first thumbnail image and the second thumbnail image, respectively.
[0167] (Appendix 12) The condition for transmitting and receiving ultrasonic waves may be any one of a transmission waveform, a reception center frequency, a reception frequency band, a reception aperture, and a sound speed.
[0168] (Appendix 13) In the ultrasound diagnostic system, the image quality index may be optimized for each depth of the subject.
[0169] (Appendix 14) The multiple types of image quality indexes may include any one of noise reduction, edge enhancement, coherency enhancement, edge detection degree, brightness, contrast, gain, high luminance enhancement, and resolution.
[0170] (Appendix 15) The number of the second thumbnail images may be equal to or greater than the number of the types of image quality indexes.
[0171] (Appendix 16) a step of using a value of an image quality index selected by a user as an anchor from among a plurality of types of image quality indexes for displaying a medical image, and generating a thumbnail image of the medical image based on the anchor as a first thumbnail image; displaying the generated first thumbnail image on a display unit; generating a plurality of thumbnail images as second thumbnail images by increasing or decreasing the plurality of types of image quality indexes from the anchor with respect to the medical image; displaying the generated second thumbnail images on the display unit; A step of making the first thumbnail image and the second thumbnail image selectable, and calculating a step width of a new image quality index adjusted with a variable step width based on a selection result of the first thumbnail image and the second thumbnail image; generating a new first thumbnail image using a value of an image index corresponding to the first thumbnail image or the second thumbnail image selected by a user from among the first thumbnail image or the plurality of second thumbnail images as a new anchor, displaying the generated new first thumbnail image, generating a new second thumbnail image based on the calculated value of a step width of the new image quality index, and displaying the generated new second thumbnail image. [Explanation of symbols]
[0172] 100... medical image diagnostic system, 101... ultrasound probe, 102... input device, 103... main display screen, 104... touch command screen, 201... transmitter / receiver, 202... B-mode processing unit, 203... Doppler processing unit, 204... image processing unit, 205... memory, 206... control unit, 1100... magnetic resonance imaging system, 1101... static magnetic field magnet, 1103... gradient magnetic field coil, 1104... gradient magnetic field power supply, 1105... bed, 1105a... tabletop, 1106... bed control circuit, 1107... transmitting coil, 1108... transmitting circuit, 1109... receiving coil, 1110... receiving circuit, 1120... sequence control circuit, 1200... data processing device, 1201... memory, 1203... input device, 1204... display, 1210... processing circuit, W10 to W30... image quality adjustment setting screen
Claims
1. a first image generating unit that uses a value of an image quality index selected by a user from among a plurality of types of image quality indexes for displaying a medical image as an anchor and generates a thumbnail image of the medical image based on the anchor as a first thumbnail image; a first image display unit that displays the first thumbnail image generated by the first image generation unit on a display unit; a second image generating unit that generates a plurality of thumbnail images as second thumbnail images by increasing or decreasing the plurality of types of image quality indexes from the anchor with respect to the medical image; a second image display unit that displays the second thumbnail images generated by the second image generation unit on the display unit; a new image quality index calculation unit that allows the first thumbnail image and the second thumbnail image to be selected and calculates a new image quality index adjusted with a variable step width based on a selection result of the first thumbnail image and the second thumbnail image; a regeneration display unit that uses a value of an image index corresponding to the first thumbnail image or the second thumbnail image selected by a user from among the first thumbnail image or the plurality of second thumbnail images as a new anchor to cause the first image generation unit to generate a new first thumbnail image and cause the first image display unit to display the new first thumbnail image, and causes the second image generation unit to generate a new second thumbnail image based on the value of the new image quality index calculated by the new image quality index calculation unit and causes the second image display unit to display the new second thumbnail image.
2. the second image generating unit generates a composite image based on image indices obtained by increasing or decreasing the plurality of types of image indices from the anchor, as one of the plurality of second thumbnail images; The medical image diagnostic system according to claim 1 , wherein the second image display unit displays the composite image as one of the plurality of second thumbnail images.
3. The medical image diagnostic system according to claim 1 , wherein the new image quality index calculation unit switches between increasing and decreasing the new image quality index based on a user operation.
4. The medical image diagnostic system according to claim 1 , wherein the calculation of the new image quality index depends on a probability of selection of the first thumbnail image and the second thumbnail image according to a Bradley-Terry-Luce (BTL) model or a Thurstone-Mosteller model.
5. 2. The medical image diagnostic system according to claim 1, wherein the calculation of the new image quality index is optimized by probabilistic inference using Bayes' theorem, and the optimization is performed by maximizing an acquisition function.
6. 6. The medical image diagnostic system according to claim 5, wherein the probabilistic inference using Bayes' theorem is performed from a prior distribution model according to a Gaussian process.
7. 2. The medical image diagnostic system according to claim 1, wherein the first image generation unit and the second image generation unit calculate a plurality of parameters from the value of the image quality index, and perform image processing or signal processing based on the calculated parameters to generate the first thumbnail image and the second thumbnail image, respectively.
8. 8. The medical image diagnostic system according to claim 7, wherein the image processing or signal processing is any one of a multi-resolution decomposition process, a nonlinear anisotropic diffusion filter, a linear spatial filter, a median filter, an input / output curve process, and a gain adjustment process.
9. The medical image diagnostic system according to claim 1 , wherein the medical image is an image captured by an ultrasound diagnostic system.
10. 10. The medical image diagnostic system according to claim 9, wherein the first image generation unit and the second image generation unit calculate a plurality of parameters from the value of the image quality index, transmit and receive ultrasound under conditions of the calculated parameters, and generate the first thumbnail image and the second thumbnail image, respectively.
11. 11. The medical image diagnostic system according to claim 10, wherein the condition for transmitting and receiving ultrasonic waves is any one of a transmission waveform, a reception center frequency, a reception frequency band, a reception aperture, and a sound speed.
12. The medical image diagnostic system according to claim 9 , wherein in the ultrasonic diagnostic system, the optimization of the image quality index can be performed for each depth of the subject.
13. 2. The medical image diagnostic system according to claim 1, wherein the plurality of types of image quality indices include any one of noise reduction, edge enhancement, coherency enhancement, edge detection degree, brightness, contrast, gain, high luminance enhancement, and resolution.
14. 2. The medical image diagnostic system according to claim 1, wherein the number of said second thumbnail images is equal to or greater than the number of types of said image quality indexes.
15. a step of using a value of an image quality index selected by a user as an anchor from among a plurality of types of image quality indexes for displaying a medical image, and generating a thumbnail image of the medical image based on the anchor as a first thumbnail image; displaying the generated first thumbnail image on a display unit; generating a plurality of thumbnail images as second thumbnail images by increasing or decreasing the plurality of types of image quality indexes from the anchor with respect to the medical image; displaying the generated second thumbnail images on the display unit; a step of allowing the first thumbnail image and the second thumbnail image to be selected, and calculating a new image quality index adjusted with a variable step width based on a selection result of the first thumbnail image and the second thumbnail image; a step of generating a new first thumbnail image using a value of an image index corresponding to the first thumbnail image or the second thumbnail image selected by a user from among the first thumbnail image or the plurality of second thumbnail images as a new anchor, displaying the generated new first thumbnail image, generating a new second thumbnail image based on the calculated value of the new image quality index, and displaying the generated new second thumbnail image.
Citation Information
Patent Citations
Ultrasonograph
JP2004016612A
Ultrasonic diagnostic device and ultrasonic image adjustment method
JP2020074996A
Radiation image quality adjustment device
JP2020159789A
Ultrasound diagnostic equipment
JP6608126B2
