Image processing device, method for operating image processing device, recording medium, and medical image processing system

Abstract

The invention provides an image processing device, an operation method of the image processing device, a recording medium, and a medical image processing system. An image processing device is provided with: a processing unit (110) that acquires user identification information; (112) acquiring a first imaging condition; (100) acquiring a first image to which a first imaging condition is applied; (130) a first de-noised image is generated by performing de-noising processing on the first image using the first de-noising intensity; (120) acquiring, as a first signal-to-noise ratio, a second signal-to-noise ratio corresponding to a second imaging condition that is the same as or close to the first imaging condition from among the second signal-to-noise ratios corresponding to the plurality of second imaging conditions; and (122) setting the de-noising intensity based on the first signal-to-noise ratio as the first de-noising intensity.

Description

Technical Field

[0001] The present invention relates to an image processing device, a working method of the image processing device, a program and a medical image processing system. Background Art

[0002] Patent document 1 describes a medical imaging device that uses an MRI device as an imaging device. In the medical imaging device described in the document, when the noise level varies in each image region, a denoising filter with a relatively high strength is applied to a region with a relatively high noise level, and a denoising filter with a relatively low strength is applied to a region with a relatively low noise level. MRI is the abbreviation of Magnetic Resonance Imaging.

[0003] Furthermore, the medical imaging apparatus described in Patent Document 1 stores the relationship between the region selection mode and the imaging conditions selected by the user. Thus, when the same imaging conditions as those applied in the past are applied, the region selection mode selected in the past can be selected.

[0004] In addition, the medical imaging device described in Patent Document 1 has a slide bar that establishes a corresponding relationship between an area selection mode and each sliding position. The user can slide the slide bar while viewing the high-quality image displayed on the display device and stop the sliding position to select the area selection mode that obtains the desired high-quality image.

[0005] Patent Document 1: Japanese Patent Application Publication No. 2022-6869

[0006] However, in the image processing device involved in the prior art, the denoising intensity is set before shooting, and the denoising process is applied to the image generated after the shooting is completed. When the user confirms the image to which the denoising is applied and wants to change the denoising intensity, the denoising intensity is reset and the shooting is performed again. In actual clinical scenes, it is not realistic to perform reshooting.

[0007] Furthermore, the denoising intensity recommended by the manufacturer of the image processing device is not necessarily consistent with the preference of users such as doctors and technicians, and it is desirable to optimize the denoising intensity that meets the user's preference. Summary of the invention

[0008] The present invention has been made in view of such circumstances, and its object is to provide an image processing device, an operating method of the image processing device, a program, and a medical image processing system that implement denoising processing with a denoising intensity that suits user preference.

[0009] The image processing device involved in the first embodiment of the present invention comprises a processor, and the processor performs the following processing: obtaining user identification information; obtaining a first camera condition applicable to a camera device; obtaining a first image captured and generated using the camera device applying the first camera condition; setting a first denoising intensity applicable in denoising processing of the first image; and performing denoising processing on the first image applying the first denoising intensity to generate a first denoised image, the processor performs the following processing: from a plurality of second signal-to-noise ratios derived from each of a plurality of second images generated in a plurality of past camera shots for each user in which a plurality of second camera conditions were applied, obtaining a second signal-to-noise ratio corresponding to a second camera condition that is the same as the first camera condition, or a second camera condition that is close to the first camera condition, as the first signal-to-noise ratio, and setting the denoising intensity derived based on the first signal-to-noise ratio as the first denoising intensity.

[0010] According to the image processing device involved in the first aspect, from among a plurality of second signal-to-noise ratios derived from a plurality of second images generated in a plurality of past photography sessions for each user and associated with a second photography condition in past photography, a second signal-to-noise ratio corresponding to a second photography condition that is the same as the first photography condition or a second photography condition that is close to the first photography condition is obtained as the first signal-to-noise ratio. Thus, denoising processing is implemented in which a first denoising intensity corresponding to the first signal-to-noise ratio preferred by the user is applied.

[0011] In the image processing device involved in the second embodiment, in the image processing device of the first embodiment, the processor can perform the following processing: referring to a signal-to-noise ratio database that stores each of a plurality of second imaging conditions in association with a plurality of second signal-to-noise ratios, and obtaining a first signal-to-noise ratio corresponding to a second imaging condition that is the same as the first imaging condition, or a second imaging condition that is close to the first imaging condition.

[0012] An image processing device according to a third aspect is the image processing device according to the second aspect, wherein the processor may perform processing such that, when the first denoising strength is changed, the signal-to-noise ratio database is updated according to the changed second denoising strength.

[0013] In the image processing device involved in the fourth embodiment, in the image processing device described in any one of the first to third embodiments, the processor can perform the following processing: perform multiple denoising processes with different denoising intensities on the first image to generate multiple third denoised images; derive a third signal-to-noise ratio from each of the multiple third denoised images; and set the third denoising intensity applicable to the third denoised image with the third signal-to-noise ratio having the smallest difference from the derived first signal-to-noise ratio as the first denoising intensity.

[0014] In the image processing device involved in the fifth embodiment, in the image processing device described in any one of the first to third embodiments, the processor can perform the following processing: calculate the fourth signal-to-noise ratio based on the first image; and use a function representing the relationship between the signal-to-noise ratio and the denoising intensity to set the fourth denoising intensity corresponding to the fourth signal-to-noise ratio as the first denoising intensity.

[0015] In the image processing device involved in the 6th mode, in the image processing device described in any one of the 1st to 5th modes, the processor can perform the following processing: displaying the first denoised image on the display device; displaying options representing the evaluation of the first denoising intensity applicable in the denoising processing of the first denoised image on the display device; obtaining a first evaluation signal representing the evaluation of the first denoising intensity selected from the options; and feeding back the evaluation of the first denoising intensity represented by the first evaluation signal to the setting of the first denoising intensity.

[0016] In the image processing device involved in the 7th mode, in the image processing device described in any one of the 1st to 6th modes, the processor can perform the following processing: apply the 5th imaging condition that is the same as the 1st imaging condition, or the 5th imaging condition that is close to the 1st imaging condition, apply the 1st denoising intensity to the past image that was captured and generated in the past to perform denoising processing, and display the generated 5th denoised image on the display device; obtain the 5th evaluation signal representing the evaluation of the 5th denoising intensity applied in the denoising processing of the 5th denoised image; and determine whether to maintain or change the 1st denoising intensity based on the evaluation of the 5th denoising intensity represented by the 5th evaluation signal.

[0017] The image processing device according to the eighth aspect is the image processing device according to the seventh aspect, wherein the past image may be a normal image generated by imaging a normal imaging subject in the past.

[0018] The image processing device involved in the 9th mode is an image processing device of the 7th mode. The past image can be applied with the 6th imaging condition which is the same as the 1st imaging condition, or the 6th imaging condition which is close to the 1st imaging condition, and the same imaging subject image generated by past imaging of the same imaging subject is applied, and the processor performs the following processing: the 6th denoised image in which the denoising process is performed on the same imaging subject image, and the 6th denoising intensity applied in the denoising process performed on the same imaging subject image are displayed on the display device.

[0019] In the image processing device involved in the tenth method, in the image processing device of the ninth method, the processor can perform the following processing: obtain a sixth evaluation signal representing an evaluation of a sixth denoising intensity; and determine whether to maintain or change the first denoising intensity based on the evaluation of the sixth denoising intensity represented by the sixth evaluation signal.

[0020] The working method of the image processing device involved in the 11th embodiment of the present invention is applicable to a computer with a processor, and the processor performs the following processing: obtaining user identification information; obtaining a first camera condition applicable to a camera device; obtaining a first image captured and generated using the camera device applicable to the first camera condition; setting a first denoising intensity applicable in the denoising process of the first image; and performing denoising on the first image using the first denoising intensity to generate a first denoised image, when the first denoising intensity is set, from a plurality of second signal-to-noise ratios derived from each of a plurality of second images generated in a plurality of past camera shots for each user in which a plurality of second camera conditions were applied, a second signal-to-noise ratio corresponding to a second camera condition that is the same as the first camera condition, or a second camera condition that is close to the first camera condition, is obtained as the first signal-to-noise ratio, and the denoising intensity derived based on the first signal-to-noise ratio is set as the first denoising intensity.

[0021] The program involved in the 12th mode of the present invention enables a computer to implement the following functions: obtaining user identification information; obtaining a first camera condition applicable to a camera device; obtaining a first image captured and generated using the camera device applicable to the first camera condition; setting a first denoising intensity applicable in denoising processing of the first image; and performing denoising processing on the first image using the first denoising intensity to generate a first denoised image, wherein the function of setting the first denoising intensity is: from each of a plurality of second signal-to-noise ratios derived from a plurality of second images generated in a plurality of past camera shots for each user in which a plurality of second camera conditions were applied, obtaining a second signal-to-noise ratio corresponding to a second camera condition that is the same as the first camera condition, or a second camera condition that is close to the first camera condition, as the first signal-to-noise ratio, and setting the denoising intensity derived based on the first signal-to-noise ratio as the first denoising intensity.

[0022] A tangible, non-transitory, computer-readable recording medium storing the program according to the twelfth aspect is also included in the present invention.

[0023] The medical image processing system involved in the 13th embodiment of the present invention comprises an image processing device for performing prescribed image processing on a medical image generated by imaging a test subject using an imaging device, the image processing device comprising a processor, the processor performing the following processing: obtaining user identification information; obtaining a first imaging condition applicable to the imaging device; obtaining a first image generated by imaging using the imaging device applicable to the first imaging condition; setting a first denoising intensity applicable in the denoising processing of the first image; and performing denoising processing on the first image using the first denoising intensity to generate a first denoised image, the processor performing the following processing: obtaining a second signal-to-noise ratio corresponding to a second imaging condition that is the same as the first imaging condition, or a second imaging condition that is close to the first imaging condition, from a plurality of second signal-to-noise ratios derived from each of a plurality of second images generated in a plurality of past imaging times in which a plurality of second imaging conditions were applied for each user, as the first signal-to-noise ratio, and setting the denoising intensity derived based on the first signal-to-noise ratio as the first denoising intensity.

[0024] Effects of the Invention

[0025] According to the present invention, from among a plurality of second signal-to-noise ratios derived from a plurality of second images generated in a plurality of past photography sessions for each user and associated with a second photography condition in past photography, a second signal-to-noise ratio corresponding to a second photography condition that is the same as the first photography condition or a second photography condition that is close to the first photography condition is obtained as the first signal-to-noise ratio. Thus, denoising processing is performed with a first denoising intensity corresponding to the first signal-to-noise ratio preferred by the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is an overall configuration diagram of an MRI apparatus according to an embodiment.

[0027] Figure 2 Yes means Figure 1 A functional block diagram of the electrical structure of the computer is shown.

[0028] Figure 3 Yes means Figure 2 A block diagram of the hardware structure of the computer's electrical structure is shown.

[0029] Figure 4 This is a flowchart showing the procedure for constructing the SN ratio database according to the first example.

[0030] Figure 5 This is a flowchart showing the procedure for constructing the SN ratio database according to the second example.

[0031] Figure 6 This is a flowchart showing the procedure of the image processing method involved in the embodiment.

[0032] Figure 7Yes means Figure 2 A functional block diagram of a first configuration example of a denoising strength acquisition unit shown in FIG.

[0033] Figure 8 This is an illustration of the background of the area of ​​interest.

[0034] Fig. 9 It is an explanatory diagram of the pixel value of the background noise.

[0035] Fig.10 Yes means Figure 2 A functional block diagram of a second configuration example of the denoising strength acquisition unit shown in FIG.

[0036] Fig.11 This is a table showing the results of calculating the SN ratios of denoised images generated by applying a plurality of denoising intensities to numerical phantoms having different SN ratios.

[0037] Fig.12 It is an explanatory diagram showing a function of denoising strength.

[0038] Fig.13 This is a functional block diagram showing the electrical structure of a computer according to the first modification.

[0039] Fig.14 This is an explanatory diagram showing an example of a user interface used for feedback of denoising intensity.

[0040] Fig.15 This is an explanatory diagram showing a first example of a confirmation screen before automatic adjustment of the denoising intensity.

[0041] Fig.16 It is an explanatory diagram showing a second example of the confirmation screen before automatic adjustment of the denoising intensity.

[0042] Explanation of symbols

[0043] 20-computer, 30-output device, 50-external storage device, 52-SN ratio database, 100-image acquisition unit, 102-image reconstruction unit, 104-standardization unit, 110-user ID acquisition unit, 112-camera condition acquisition unit, 120-SN ratio acquisition unit, 122-denoising intensity acquisition unit, 130-denoising processing unit, 132-learning model, 140-denoised image output unit. DETAILED DESCRIPTION

[0044] Hereinafter, the preferred embodiments of the present invention will be described in detail according to the accompanying drawings. In addition, in the following description and the accompanying drawings, the same constituent elements are marked with the same symbols, and repeated descriptions are omitted. Furthermore, when multiple constituent elements are cited in the following embodiments, it can be interpreted as including at least one of the multiple constituent elements.

[0045] [First embodiment]

[0046] [Configuration example of MRI apparatus]

[0047] Figure 1 : is an overall structural diagram of the MRI device involved in the embodiment. Below, as an embodiment of the present invention, the MRI device is described, but the technology of the present invention can also be applied to equipment such as X-ray CT devices and positron emission tomography devices. In addition, CT is the abbreviation of Computed Tomography. The positron emission tomography device can also be called PET, which is the abbreviation of the English symbol Positron Emission Tomography.

[0048] Figure 1 The MRI apparatus 1 shown includes a measuring device 10, a computer 20, an output device 30, an input device 40, and an external storage device 50. The measuring device 10 includes a static magnetic field coil 11, a gradient magnetic field coil 12, and a gradient magnetic field power supply 15. The static magnetic field coil 11 generates a static magnetic field in a space where a subject is placed. The gradient magnetic field coil 12 gives a magnetic field gradient to the static magnetic field generated by the static magnetic field coil 11. The gradient magnetic field power supply 15 is a driving power supply for the gradient magnetic field coil 12.

[0049] The measuring device 10 includes a transmitting coil 13, a receiving coil 14, a transmitter 16, and a receiver 17. The transmitting coil 13 generates a high-frequency magnetic field in a measurement region of a subject. The transmitter 16 supplies a pulse current as an excitation current to the transmitting coil 13. The receiving coil 14 receives a nuclear magnetic resonance signal generated from the subject. The receiver 17 transmits the nuclear magnetic resonance signal received by the receiving coil 14 to a computer 20. In addition, the nuclear magnetic resonance signal can be called an echo signal.

[0050] In the MRI apparatus 1, there are vertical magnetic field methods and horizontal magnetic field methods according to the direction of the static magnetic field generated. The static magnetic field coil 11 adopts various forms according to the magnetic field method. The gradient magnetic field coil 12 has a plurality of coils that generate a gradient magnetic field in each of the three axial directions orthogonal to each other. Each of the plurality of coils provided in the gradient magnetic field coil 12 is driven by a gradient magnetic field power supply 15. Due to the application of the gradient magnetic field, position information is added to the nuclear magnetic resonance signal generated from the subject.

[0051] in addition, Figure 1 In the example, a mode in which the transmission coil 13 and the reception coil 14 are separately provided is shown, but a mode in which one coil having the function of the transmission coil 13 and the function of the reception coil 14 is provided may be also used.

[0052] The measuring device 10 is provided with a sequence control device 18. The sequence control device 18 controls the operation of the gradient magnetic field power supply 15 and the transmitter 16 to control the generation timing of the gradient magnetic field and the high-frequency magnetic field. The sequence control device 18 controls the operation of the receiver 17 to control the reception timing of the nuclear magnetic resonance signal and perform the measurement. The timing diagram applied to the control of the sequence control device 18 is called an imaging sequence, which is pre-set according to the measurement and stored in a storage device etc. provided in the computer 20.

[0053] The computer 20 is preferably a computer having a processor such as a CPU, a memory, a storage device, etc. The computer 20 functions as a control device that controls the operation of each part of the measurement device 10 via the sequence control device 18. In addition, the computer 20 functions as a computing device that performs computational processing on the nuclear magnetic resonance signal received via the receiver 17 and the sequence control device 18, and obtains an image signal of a predetermined imaging area. The computer 20 may be a device constituting the MRI device 1, or may be an external device independent of the MRI device 1.

[0054] The computer 20 is electrically connected to an output device 30, an input device 40, and an external storage device 50 in a data-communicative manner. The output device 30 may be a display for displaying the result of the calculation process executed by the computer 20.

[0055] The output device 30 may be a liquid crystal display, an organic EL display, a projector, etc. The output device 30 may also be a suitable combination of these devices. In addition, organic EL may be referred to as OEL using the abbreviation of Organic Electro-Luminescence.

[0056] The input device 40 is an interface for the operator to input conditions and parameters used in measurement and calculation processing. Examples of the input device 40 include a keyboard and a mouse. A display device that functions as the output device 30 and the input device may be integrated using a touch panel display. The operator can use the input device 40 to input parameters such as the number of echoes to be measured, the echo time, and the echo interval.

[0057] The external storage device 50 stores data used in various calculations performed by the computer 20, data derived as a result of calculations, conditions and parameters applied in calculations, and programs for executing calculations, etc. The external storage device 50 may implement a part of the functions of the internal storage device of the computer 20, or the internal storage device of the computer 20 may implement a part of the functions of the external storage device 50.

[0058] Regarding the nuclear magnetic resonance signal acquired using the measuring device 10, noise caused by the characteristics of the MRI device 1 and the imaging conditions is superimposed on the signal from the subject. The noise superimposed on the nuclear magnetic resonance signal deteriorates the image quality of the image of the subject generated from the nuclear magnetic resonance signal. The computer 20 has a function of performing a process of reducing the noise superimposed on the nuclear magnetic resonance signal, i.e., a noise reduction process, as a signal processing of the nuclear magnetic resonance signal. The noise reduction process can be called a denoising process.

[0059] The denoising process is applied to a learned model such as CNN. In addition, CNN is the abbreviation of Convolution Neural Network. The external storage device 50 stores an SN ratio database used when deriving the filter strength applied in the denoising process. The filter strength can be called denoising strength.

[0060] In the SN ratio database, the SN ratio of image preference of each user such as a doctor or a technician is stored in association with the imaging conditions applied when imaging the subject. The SN ratio database can read the SN ratio of image preference using the imaging conditions as an index.

[0061] In addition, the SN ratio can be called the signal-to-noise ratio. Figure 1 The SN ratio database is omitted in the figure. The SN ratio database is marked with a symbol 52 and is shown in the figure. Figure 2 In addition, Figure 1 The measuring device 10 shown is an example of an imaging device, and the computer 20 is an example of an image processing device and an example of a constituent element of a medical image processing system.

[0062] [Computer Configuration Example]

[0063] Figure 2 Yes means Figure 1 The computer 20 is provided with an image acquisition unit 100. The image acquisition unit 100 acquires Figure 1 The image is represented by the nuclear magnetic resonance signal transmitted by the receiver 17 shown. Figure 2 The image acquired by the image acquisition unit 100 described in the illustrated embodiment is an example of the first image.

[0064] The computer 20 includes an image reconstruction unit 102. The image reconstruction unit 102 generates a reconstructed image based on the image acquired by the image acquisition unit 100. As an example of a reconstructed image generated based on an image, a two-dimensional tomographic image can be cited. Here, the term "image" includes the meaning of image data representing an image. The term "data" can include the meaning of referring to a circuit as a signal.

[0065] The computer 20 includes a normalization unit 104. The normalization unit 104 performs normalization processing on the pixel value of each pixel constituting the reconstructed image by applying a predetermined normalization constant. The details of the normalization processing will be described later.

[0066] The computer 20 includes a user ID acquisition unit 110. The user ID acquisition unit 110 acquires a user ID used for user identification for performing denoising processing on the standardized reconstructed image. The user ID is information for identifying the user, such as the user name and the identification number of each user. The user ID acquisition unit 110 may adopt a method of using a reader to read the user ID represented by a barcode or a two-dimensional code. In addition, the user ID described in the embodiment is an example of user identification information. ID is an abbreviation of Identification.

[0067] The computer 20 includes an imaging condition acquisition unit 112. The imaging condition acquisition unit 112 acquires imaging conditions suitable for imaging the subject. Imaging refers to the function of the measuring device 10 of irradiating the subject with electromagnetic waves from the static magnetic field coil 11 and the like, and acquiring nuclear magnetic resonance signals using the receiver 17. Examples of imaging conditions include the number of imaging matrices and sequences. In addition, the imaging conditions acquired by the imaging condition acquisition unit 112 described in the embodiment are an example of the first imaging condition.

[0068] The computer 20 includes an SN ratio acquisition unit 120. The SN ratio acquisition unit 120 reads the SN ratio corresponding to the imaging target part, the user ID, and the imaging condition from the SN ratio database 52 that stores the SN ratios associated with the imaging conditions for each user. The SN ratio read from the SN ratio database 52 is used for calculation processing as the SN ratio preferred by each user corresponding to the imaging condition. In addition, the imaging target part can be interpreted as the anatomical structure of the imaging target.

[0069] That is, in the SN ratio database 52, the SN ratios measured for the MR images generated in the past multiple imagings are associated with the imaging parts and imaging conditions attached to the MR images, and are stored for each user. The imaging parts and imaging conditions can be in DICOM format. In addition, the MR image generated by the past imaging described in the embodiment is an example of the second image, and the imaging condition of the past image is an example of the second imaging condition.

[0070] The SN ratio acquisition unit 120 searches the SN ratio database 52 using the imaging target part, user ID, and imaging condition as indexes, and reads the SN ratio of each user preference corresponding to them. In addition, the SN ratio database 52 described in the embodiment is an example of a signal-to-noise ratio database. The multiple SN ratios stored in the SN ratio database 52 described in the embodiment are an example of multiple second signal-to-noise ratios, and the SN ratio SN0 read from the SN ratio database 52 is an example of a first signal-to-noise ratio obtained from the multiple second signal-to-noise ratios.

[0071] The computer 20 includes a denoising intensity acquisition unit 122. The denoising intensity acquisition unit 122 acquires the denoising intensity applicable to the denoising process based on the SN ratio SN0 read from the SN ratio database 52. The details of acquiring the denoising intensity will be described later. In addition, the denoising intensity applicable to the denoising process described in the embodiment is an example of the first denoising intensity.

[0072] The normalization unit 104 performs normalization processing on the reconstructed image using the SN ratio acquired from the SN ratio acquisition unit 120 and the denoising intensity acquired from the denoising intensity acquisition unit 122 .

[0073] The computer 20 includes a denoising unit 130. The denoising unit 130 performs denoising on the normalized reconstructed image to generate a denoised image. The denoised image is generated by removing at least a part of the noise from the reconstructed image including the noise.

[0074] The denoising processing unit 130 includes a learned learning model 132. The learning model 132 applies CNN. The learning model 132 is learned and generated as follows: if an image including noise is input as learning data using an image including noise as input data and an image with noise removed as correct answer data, an image with noise removed is output. The generation of the learning model 132 may be performed using a computer independent of the computer 20, or may be performed using a learning model generation unit included in the computer 20. In the case where the computer 20 includes a learning model generation unit, the computer 20 may perform re-learning of the learning model 132. In addition, the implementation of the application Figure 2 The denoised image generated by the denoising process performed by the denoising processing unit 130 is an example of a first denoised image.

[0075] The computer 20 includes a denoised image output unit 140. The denoised image output unit 140 converts the denoised image generated by the denoising processing unit 130 into a signal format suitable for the output device 30, and outputs the signal to the output device 30. For example, when the output device 30 is a display, the denoised image output unit 140 converts the denoised image into a video signal and outputs the video signal to the output device 30.

[0076] Figure 3 Yes means Figure 2The block diagram of the hardware structure of the electrical structure of the computer shown in FIG. The computer applicable to computer 20 may be a personal computer or a workstation. The computer may be a virtual machine. Computer 20 may be composed of multiple computers.

[0077] The computer 20 includes a processor 202, a memory 204 as a main storage device, a storage 206 as an auxiliary storage device, an input / output interface 208, and a bus 210. The processor 202 includes a CPU. The processor 202 may include a GPU. In addition, CPU is the abbreviation of Central Processing Unit. GPU is the abbreviation of Graphics Processing Unit.

[0078] The processor 202 is connected to the memory 204, the storage 206, and the input / output interface 208 via the bus 210. The input device 40 and the output device 30 are connected to the computer 20 via the input / output interface 208.

[0079] The processor 202 executes the program stored in the memory 204 to implement various functions. The input and output interface 208 includes a communication interface that can be connected to a network, and a connection interface that can be connected to an external device. As an example of a network, a local area network in a medical facility can be cited. As a connection interface that can be connected to an external device, for example, a universal serial bus and HDMI can be used. In addition, the universal serial bus uses the abbreviation of Universal Serial Bus and can be called USB. HDMI is the abbreviation of High-Definition Multimedia Interface. USB and HDMI are registered trademarks.

[0080] The processor 202 communicates with various external devices of the MRI apparatus 1 via the input / output interface 208 to transmit and receive necessary information. In addition, illustration of various external devices is omitted.

[0081] The output device 30 may include a display that displays various information in addition to the medical image captured by the MRI device 1. The output device 30 is used as a part of the GUI when receiving input from the input device 40. In addition, the output device 30 is not limited to one, and may be a multi-display having a plurality of displays. GUI is an abbreviation of Graphical User Interface.

[0082] [Construction of SN ratio database]

[0083] Figure 4FIG. 1 is a flowchart showing the construction procedure of the SN ratio database involved in the first example. Figure 2 In constructing the SN ratio database 52 shown, an information processing device suitable for a computer is used, and the following sequence is applied. The construction sequence of the SN ratio database involved in the first example is applicable to the case where past images are prepared for multiple test subjects. The past images mentioned here refer to MR images that were captured and generated in the past.

[0084] In the first information input step S10, a past image is input to the information processing device. In the first information input step S10, a user ID and imaging conditions for each of a plurality of past images are input to the information processing device.

[0085] In the past image selection step S12, selection information of past images subjected to the denoising process preferred by the user is input to the information processing device. For example, in the past image selection step S12, one or more past images subjected to the denoising process preferred by the user may be selected from past images subjected to the denoising process. In the past image selection step S12, one or more past images subjected to the denoising process preferred by the user may be selected from a plurality of past images generated by subjecting any past image to the denoising process with different denoising intensities.

[0086] In the SN ratio calculation step S14, the SN ratio of the past image selected in the past image selection step S12 is calculated. The details of calculating the SN ratio will be described later. A known method can be applied to calculate the SN ratio.

[0087] In the SN ratio storage step S16, the imaging part and imaging conditions are associated with the SN ratio calculated in the SN ratio calculation step S14 and stored for each user. Figure 1 An external storage device 50 is shown. Figure 4 The order of constructing the SN ratio database 52 shown above can also be applied as the order of updating the SN ratio database 52 .

[0088] Figure 5 This is a flowchart showing the procedure for constructing the SN ratio database according to the second example. The procedure for constructing the SN ratio database according to the second example is suitable for preparing a plurality of past images with different denoising intensities for the same subject.

[0089] exist Figure 5 In the construction order of the SN ratio database shown in the figure, replace Figure 4 The second information input step S11 is executed after the first information input step S10 shown in the figure. In the second information input step S11, the imaging part, the user ID and the imaging conditions are input for each of a plurality of past images of the same test subject.

[0090] After the second information input step S11, the past image selection step S12, the SN ratio calculation step S14, and the SN ratio storage step S16 are executed to construct the SN ratio database 52. The processing of the past image selection step S12, the SN ratio calculation step S14, and the SN ratio storage step S16 is similar to that of the previous image selection step S12. Figure 4 The construction procedure of the SN ratio database involved in the second example shown is the same, and the description thereof is omitted here.

[0091] [Details of the denoising process]

[0092] Figure 6 The flowchart shows the sequence of the image processing method involved in the embodiment. In the image processing method applicable to the MRI apparatus 1 involved in the embodiment, the denoising intensity applicable to the denoising process is automatically set with reference to the SN ratio of the MR images taken by the same user in the past. In addition, the image processing method involved in the embodiment is understood as the working method of the image processing apparatus.

[0093] In the third information input step S100, Figure 2 The image acquisition unit 100 shown acquires the processing target image. The information of the imaging part can be acquired when acquiring the processing target image. In addition, in the third information input step S100, the user ID acquisition unit 110 acquires the user ID of the user who performed the imaging to acquire the processing target image. In addition, in the third information input step S100, the imaging condition acquisition unit 112 acquires the imaging condition applied in the imaging to acquire the processing target image.

[0094] In the SN ratio acquisition step S102, the SN ratio acquisition unit 120 refers to the SN ratio database 52 using the user ID and the imaging condition acquired in the third information input step S100 as an index, and acquires the user's preferred SN ratio SN0 from the SN ratio database 52. The user's preferred SN ratio SN0 is an example of the first signal-to-noise ratio.

[0095] In the case where the SN ratio corresponding to the user ID and the imaging condition is not stored in the SN ratio database 52, the SN ratio of past images with similar imaging conditions for the same user can also be obtained. Examples of similar imaging conditions include imaging conditions in which a portion of a plurality of constituent elements is consistent, and imaging conditions in which the index value difference is within a specified range. That is, similar imaging conditions can be understood as having a difference in the setting of the SN ratio and the setting of the denoising intensity to the extent that the same result as the same imaging condition can be obtained.

[0096] In the denoising process step S104, the normalizing unit 104 applies the SN ratio SN0 obtained in the SN ratio acquisition step S102 and the denoising intensity corresponding to the SN ratio SN0 to perform normalization on the target image for denoising. In the denoising process step S104, the denoising unit 130 performs denoising on the image after the normalization using the learning model 132. Figure 6 The AI ​​denoising shown here means denoising processing using the learning model 132. In addition, AI is an abbreviation for Artificial Intelligence.

[0097] In the denoised image output step S106, the denoised image output unit 140 converts the denoised image subjected to the denoising process into an output format of the output device 30 and outputs the denoised image to the output device 30. When the denoised image is output in the denoised image output step S106, the sequence of the image processing method ends.

[0098] [Specific example of denoising intensity adjustment]

[0099] [Multi-stage type]

[0100] Figure 7 Yes means Figure 2 The denoising strength acquisition unit 122 includes a denoised image generation unit 212 , an SN ratio calculation unit 213 , an SN ratio comparison unit 214 , and a denoising strength output unit 215 .

[0101] The denoised image generation unit 212 uses Figure 2 The image reconstruction unit 102 shown applies a plurality of denoising intensities different from each other to the reconstructed image Ir generated thereby to generate a plurality of temporary denoised images. Figure 7 The example shows that three different denoising strengths D are used. a , denoising intensity D b And denoising strength D. And generate three examples of temporary denoised images.

[0102] The SN ratio calculation unit 213 calculates the SN ratio of each of the plurality of denoised images generated by the denoised image generation unit 212 . Figure 7 Calculate SN as shown in the example a , SN b and SN c As the applicable denoising strength D a , denoising intensity D b and denoising strength D c An example of the SN ratio of each denoised image.

[0103] The SN ratio comparison unit 214 compares the SN ratio SN0 acquired as the SN ratio of the user's preference corresponding to the imaging condition with the SN ratio SN calculated by the SN ratio calculation unit 213. a SN vs SN b and SN vs SN c SN vs SN a SN vs SN b When any one of the SN ratios SN and SN is the same as the SN ratio SN0, the SN ratio that is the same as the SN ratio SN0 is set as the comparison result.

[0104] In SN than SN a SN vs SN b and SN vs SN c If any of the SN ratios is not consistent with SN0, then a SN vs SN b and SN vs SN c The SN ratio closest to the SN ratio SN0 is set as the comparison result. The SN ratio closest to the SN ratio SN0 is the SN ratio with the smallest absolute value of the difference from the SN ratio SN0.

[0105] The denoising intensity output unit 215 outputs the denoising intensity applied to the temporary denoised image for which the SN ratio as the comparison result of the SN ratio comparison unit 214 is calculated. a When the SN ratio is the same as or closest to the SN ratio SN0, the denoising intensity output unit 215 outputs the denoising intensity D a .

[0106] [Specific example of SN ratio calculation method]

[0107] A specific example of the SN ratio calculation method applied in the SN ratio calculation unit 213 will be described. In an MR image, the SN ratio can be calculated by utilizing the characteristic that the background noise level is proportional to the noise level of the entire MR image.

[0108] Figure 8 This is an illustration of the background of the area of ​​interest. Figure 8 The middle figure shows the region of interest Roi (Region of interest) and the background Bg (Background) in the denoised image Id, which is a reconstructed image to which AI denoising is applied. Fig. 9 It is an explanatory diagram of the pixel value of the background noise. Fig. 9 The figure in FIG. 2 shows a histogram of pixel values ​​of the denoised image Id. In the graph showing the histogram of pixel values ​​of the denoised image Id, the horizontal axis represents the pixel value and the vertical axis represents the frequency.

[0109] Figure 7 The SN ratio calculation unit 213 shown extracts Figure 8 The denoised image Id shown in FIG. 1 shows a region of interest Roi, extracts the background Bg of the region of interest Roi, and estimates the pixel value of the noise of the background Bg. The background Bg of the region of interest Roi is understood to be the air region covering the region of interest Roi, that is, the surrounding area of ​​the organ or the like. Fig. 9 The pixel value Nv of the noise of the background Bg shown is a pixel value at which the frequency of the histogram of the pixel values ​​of the denoised image Id becomes a peak. In addition, the pixel value Nv of the noise is understood as a signal value of the noise.

[0110] The SN ratio calculation unit 213 calculates the median value of the pixel values ​​exceeding 0 in the denoised image Id as the signal value Sv when calculating the SN ratio. The signal value Sv may be the average value of the pixel values ​​exceeding 0 in the denoised image Id. The SN ratio calculation unit 213 calculates Sv / Nv as the SN ratio of the denoised image Id.

[0111] In addition, use Figure 7 The plurality of temporary denoised images generated by the denoised image generating unit 212 shown in FIG. 1 are examples of the third denoised image. a SN vs SN b and SN vs SN c This is an example of the third signal-to-noise ratio. The denoising intensity D output from the denoising intensity output unit 215 is a This is an example of the third denoising intensity.

[0112] [Adjustment of denoising strength during normalization]

[0113] Denoising strength Figure 2 The input image input to the normalization unit 104 is set to I0, and the output image output from the normalization unit 104 is set to I0. n .

[0114] If the median value of pixel values ​​exceeding 0 in the input image I0 is set to Minput(I0) and the pixel value of the background noise is set to Nv, the SN ratio SNR is expressed as SNR=Minput(I0) / Nv.

[0115] If the denoising intensity is set to D, the output image I of the normalization unit 104 n Represented as I n ={1 / Minput(I0)}×{a×(SNR / D)+b}×I0. In addition, a and b are predetermined constants derived by performing experiments or the like.

[0116] For example, when the denoising intensity is adjusted to three levels: weak, medium, and strong, as the output image I is determined nThe denoising intensity D value that works by using the denoising intensity coefficient in is set to 0.5, 1.0 and 1.5.

[0117] [No-stage type]

[0118] Fig.10 Yes means Figure 2 A functional block diagram of a second configuration example of the denoising strength acquisition unit shown in FIG. Figure 2 The denoising strength acquisition unit 122 shown in FIG. 1 includes an SN ratio calculation unit 220 and a denoising strength calculation unit 222. The SN ratio calculation unit 220 calculates the denoising strength using Figure 2 SN ratio SNIr of the reconstructed image Ir generated by the image reconstruction unit 102 is shown.

[0119] The denoising strength calculation unit 222 calculates the denoising strength D represented by a function f(SNIr, SN0) having as parameters the SN ratio SNIr of the reconstructed image Ir and the SN ratio SN0 preferred by the user. The denoising strength D calculated by the denoising strength calculation unit 222 is applied to the normalization process of the reconstructed image Ir by the normalization unit 104.

[0120] The reconstructed image Ir subjected to the normalization process is used in the denoising process unit 130. Figure 2 The learning model 132 shown is subjected to denoising processing and is output using the denoised image output unit 140 .

[0121] In addition, use Fig.10 The SN ratio SNIr output by the SN ratio calculation unit 220 shown in the figure is an example of the fourth signal-to-noise ratio. Furthermore, the denoising intensity D shown in the figure is an example of the fourth denoising intensity.

[0122] [Specific example of calculating denoising strength]

[0123] Fig.11 This is a table showing the results of calculating the SN ratios of denoised images generated by applying a plurality of denoising intensities to numerical phantoms having different SN ratios. Fig.11 The table shown exemplifies the case where the number of the SN ratio of the numerical phantom is M and the number of the denoising strength is N. M and N are integers of 1 or more.

[0124] from Fig.11 The numerical phantoms shown have a SN ratio of SN1 to SN ratio of SN M The values ​​of the range of SN ratios of the reconstructed image Ir to be subjected to the denoising process are applied respectively. N The values ​​in the range used in the denoising process for the reconstructed image Ir are respectively applied.

[0125] Fig.12 is an illustration of a function that represents the denoising strength. Fig.12In the case where the SN ratio of the numerical phantom is SN1 and the denoising intensity ranges from D1 to D5, the denoising intensity D = ∑(a i ×SN i ) is shown as a curve graph. In addition, i is a subscript from 11 to MN, a i is a predetermined constant.

[0126] about Fig.11 As shown, the ratio from SN to SN1 to SN to SN M Each of them is pre-stored to represent Fig.12 The function representing the denoising intensity D shown in the figure. The function representing the denoising intensity D can be stored in a storage device provided in the computer 20, or can be stored in an external device such as an external storage device 50. In addition, the function representing the denoising intensity D shown in the figure is an example of a function representing the relationship between the signal-to-noise ratio and the denoising intensity.

[0127] Fig.10 The denoising strength calculation unit 222 shown in FIG. Fig.11 The SN ratios shown are SN1 to SN ratios M The SN ratio SNIr of the reconstructed image Ir calculated by the SN ratio calculation unit 220 is the same as or the SN ratio having the smallest absolute value of difference from the SN ratio SNIr is searched. The denoising strength calculation unit 222 calculates the denoising strength D corresponding to the SN ratio obtained as the search result using i ×SN i ) is used to determine the denoising strength D value of the SN ratio SN0 that the user prefers.

[0128] [First Modification of Embodiment]

[0129] Fig.13 This is a functional block diagram showing the electrical structure of a computer according to the first modification. Fig.13 The computer 20A shown has a function of updating the SN ratio database stored in the external storage device 50. That is, the computer 20A includes a denoising strength update unit 150 that updates the SN ratio database.

[0130] When the denoising strength update unit 150 acquires an input signal indicating an update of the denoising strength inputted using the input device 40 , the denoising strength update unit 150 updates the SN ratio of the user's preference stored in the SN ratio database 52 .

[0131] Fig.14 This is an explanatory diagram showing an example of a user interface used for feedback of denoising intensity. Fig.14 The viewer screen 300 shown uses Fig.13 The output device 30 shown is a display.

[0132] The viewer screen 300 includes an image display area 302 for displaying a denoised image Id, that is, a reconstructed image Ir, which is subjected to denoising processing, and an evaluation display area 304 for displaying an evaluation of the denoising strength. Fig.14 In the figure, just right, weak, and strong are displayed as evaluations of the denoising strength, and a check box 306 is displayed for each of the three types of evaluations.

[0133] The user who sees the denoised image Id displayed on the viewer screen 300 can check any one of the plurality of check boxes 306 displayed on the evaluation display area 304 using the mouse constituting the input device 40. The user's check is fed back to the next and subsequent imaging.

[0134] In the next subsequent shooting, when the denoising intensity is changed according to the feedback result and the changed denoising intensity is selected as just right, the user's preferred SN ratio stored in the SN ratio database 52 is automatically updated. That is, the SN of the denoised image for which the denoising intensity is evaluated as just right is stored in the SN ratio database 52 as the new user's preferred SN ratio.

[0135] In addition, the denoised image for which the denoising intensity described in the embodiment is evaluated as being just right is an example of the second denoised image. The denoising intensity applied to the second denoised image is an example of the second denoising intensity. Fig.14 The output device 30 displayed on the viewer screen 300 is an example of a display device, and the check box 306 shown in the figure is an example of an option indicating the evaluation of the first denoising strength. The signal indicating the evaluation of the first denoising strength described in the embodiment is an example of the first evaluation signal.

[0136] [Second Modification of Embodiment]

[0137] The computer involved in the second modification has a function of displaying a preview of the denoised image ID when the denoising intensity is automatically adjusted. When there is no problem with the denoising intensity of the previewed denoised image ID, the image is started. On the other hand, when there is a problem with the denoising intensity, the user changes the denoising intensity. When the denoising intensity is changed, the SN ratio of the user's preference stored in the SN ratio database 52 is automatically updated.

[0138] Fig.15 3 is an explanatory diagram showing a first example of a confirmation screen before automatic adjustment of denoising intensity. The confirmation screen 330 involved in the first example includes an image display area 332 for displaying a preview of the denoised image ID, a denoising intensity evaluation input area 334 for inputting an evaluation of the denoising intensity, and an OK button 336 that is clicked when the denoising intensity evaluation input is confirmed. The denoising intensity evaluation input area 334 includes five check boxes 338 that are checked when any of the five levels of denoising intensity is selected.

[0139] Fig.15 The denoised image Id shown is a past MR image obtained by imaging an arbitrary healthy person, and is a past MR image obtained by applying imaging conditions that are the same as or close to the imaging conditions of this imaging to the MR image of the same part as the imaging object of this imaging. The denoised image shown in the figure is subjected to denoising processing with an automatically adjusted denoising intensity.

[0140] The user who sees the preview of the denoised image ID displayed on the image display area 332 can change the denoising intensity by checking any of the five check boxes 338 and clicking the OK button 336. On the other hand, if there is no problem with the denoising intensity of the preview of the denoised image ID, the user does not change the checked check box 338 but clicks the OK button 336, the denoising intensity automatically set is maintained, and the image capture is started.

[0141] In addition, it is shown in Fig.15 The past MR image on the confirmation screen 330 shown is an example of the fifth denoised image, and is an example of a normal image obtained by imaging a normal imaging subject in the past. The imaging condition that is the same as or close to the imaging condition of this imaging described in the embodiment is an example of the fifth imaging condition that is the same as the first imaging condition, or a fifth imaging condition that is close to the first imaging condition. The evaluation signal when the user changes the checkbox described in the embodiment is an example of the fifth evaluation signal, and the denoising intensity when the user changes the checkbox is an example of the fifth denoising intensity.

[0142] Fig.16 It is an explanatory diagram showing a second example of the confirmation screen before automatic adjustment of the denoising intensity. Fig.16 The image display area 332 shown displays a denoised image ID, which is an MR image obtained by past imaging of the same subject as the imaging object, and in which denoising processing is performed with a denoising intensity automatically adjusted according to the SN ratio preferred by the user.

[0143] In the denoising strength evaluation input area 334, a check mark is added to the denoising strength applicable to the denoised image Id displayed in the image display area 332. The user can check whether the denoising strength is appropriate by viewing the denoised image Id displayed in the image display area 332.

[0144] If the user determines that the denoising intensity is appropriate and clicks the OK button 336, the automatically set denoising intensity is maintained and imaging is started. On the other hand, if the user determines that the denoising intensity needs to be changed and checks the unchecked checkbox, the denoised image Id to which the checked denoising intensity is applied is redisplayed.

[0145] When it is determined that the denoising intensity applied to the redisplayed denoised image Id is appropriate, imaging is started, and the SN ratio of the user's preference stored in the SN ratio database 52 is automatically updated.

[0146] In addition, the test subject who is the same as the test subject of the imaging object described in the embodiment is an example of the same imaging object. Fig.16 The MR image obtained by the past imaging shown is an example of the same imaging target image, and the denoised image obtained by performing the denoising process on the MR image obtained by the past imaging is an example of the sixth denoised image.

[0147] Fig.16 The denoising intensity applied in the denoising process of the MR image generated by the past imaging shown in the figure is an example of the sixth denoising intensity. The imaging condition applied to the MR image generated by the past imaging shown in the figure is an example of the sixth imaging condition which is the same as the first imaging condition, or the sixth imaging condition which is close to the first imaging condition. The evaluation signal when the user changes the checkbox described in the embodiment is an example of the sixth evaluation signal.

[0148] [Effects of the Embodiments]

[0149] The MRI apparatus 1 according to the embodiment can obtain the following effects. [1]

[0151] For each user such as a doctor, the SN ratio of the reconstructed image Ir generated by past imaging is referred to to obtain the user's preferred SN ratio SN0, and the denoising intensity D applicable to the denoising processing of the reconstructed image Ir is automatically set. The reconstructed image Ir is obtained by re-shooting according to the user's preferred SN ratio SN0.

[0152] Thus, a denoising process is performed to which a denoising intensity D corresponding to the SN ratio SN0 of the user's preference stored in advance is applied, and a preferred denoised image Id is acquired. [2]

[0154] When the denoising intensity D is automatically set, the SN ratio SN0 preferred by the user is obtained, and the denoising intensity D applicable to the denoised image Id having the same SN ratio as the SN ratio SN0 preferred by the user or the denoising intensity D applicable to the denoised image Id having an SN ratio close to the SN ratio SN0 preferred by the user is determined from among the denoising intensities of multiple stages. Thus, the denoising process is performed in which the denoising intensity D corresponding to the SN ratio SN0 preferred by the user is applied from among the multiple denoising intensities D prepared in advance, and the preferred denoised image Id is obtained. [3]

[0156] When the denoising intensity D is automatically set, the SN ratio preferred by the user is obtained, and the function f(SNIr, SN0) representing the denoising intensity with the SN ratio as a parameter is applied to determine the denoising intensity D corresponding to the SN ratio SN0 preferred by the user. Thus, a denoising process is performed in which the denoising intensity D corresponding to the SN ratio preferred by the user is applied from among the denoising intensity D represented by the function f(SNIr, SN0) with the SN ratio as a parameter, and a preferred denoised image Id is obtained. [4]

[0158] The preview of the denoised image Id is displayed using a display functioning as the output device 30. The viewer screen 300 displaying the preview has a check box 306 for inputting an evaluation of the denoising intensity D of the denoised image Id.

[0159] Thus, the user who sees the preview of the denoised image Id can click the check box 306 to input an evaluation of the denoising intensity D of the denoised image Id. [5]

[0161] When an evaluation that the denoising strength is appropriate is input to the denoised image Id with the changed denoising strength D, the user's preferred SN ratio stored in the SN ratio database 52 is updated. Thus, the user's preferred SN ratio stored in the SN ratio database 52 is updated based on the user's evaluation of the denoising strength. [6]

[0163] The confirmation screen 330, which is a setting screen for imaging conditions before imaging, displays a denoised image ID that has been subjected to denoising processing by applying the automatically set denoising intensity D to a past image of the same part obtained by imaging a healthy person in the past, and the denoising intensity D. If there is no problem with the denoising intensity D, imaging is started. On the other hand, if there is a problem with the denoising intensity D, the denoising intensity D is changed. If the denoising intensity D is changed, the SN ratio of the user's preference stored in the SN ratio database 52 is updated.

[0164] This makes it possible to confirm the denoising strength in advance, and to update the SN ratio of the user's preference stored in the SN ratio database 52 according to the change in the denoising strength. [7]

[0166] The denoised image Id and denoising intensity D of a past image are displayed on a confirmation screen 330, which is a setting screen for the shooting conditions before shooting. The past image is a past image of the test subject who is the shooting object, and is a past image that applies the same shooting conditions as the current shooting conditions, or a past image that applies shooting conditions close to the current shooting conditions.

[0167] This allows the user to confirm the denoising intensity applied in the denoising process of past images, and to determine whether the denoising intensity D applied to the current image capture is appropriate. [8]

[0169] The confirmation screen 330 displays a check box for each of the plurality of denoising intensities D. Thus, the user can input a change instruction for the denoising intensity D by checking the check box using the input device 40 . [9]

[0171] When the denoising intensity D is changed, the SN ratio preferred by the user stored in the SN ratio database 52 is updated. Thus, the SN ratio preferred by the user stored in the SN ratio database 52 is updated according to the change in the denoising intensity.

[0172] [About the hardware structure of each processing unit]

[0173] Figure 2 The computer 20 and Fig.13 The hardware structure of the processing unit (processing unit) that performs various processing, such as the image acquisition unit 100, image reconstruction unit 102, standardization unit 104, user ID acquisition unit 110, camera condition acquisition unit 112, SN ratio acquisition unit 120, denoising intensity acquisition unit 122, denoising processing unit 130 and denoised image output unit 140 in the computer 20A shown is, for example, the various processors (processor) shown below.

[0174] Various processors include general-purpose processors that execute programs and function as various processing units, such as CPUs, GPUs, and FPGAs (Field Programmable Gate Arrays); processors whose circuit structures can be changed after manufacturing, such as programmable logic devices (PLDs) and ASICs (Application Specific Integrated Circuits); and processors with circuit structures specifically designed to execute specific processing, such as dedicated circuits.

[0175] A processing unit can be composed of one of these various processors, or it can be composed of two or more processors of the same type or different types. For example, a processing unit can be composed of multiple FPGAs, or a combination of CPU and FPGA, or a combination of CPU and GPU. In addition, multiple processing units can be composed of one processor. As an example of multiple processing units composed of one processor, first, as represented by computers such as clients and servers, there is a method of constituting a processor by a combination of one or more CPUs and software, and the processor functions as multiple processing units. Second, as represented by a system on chip (System On Chip: SoC), there is a method of using a processor that uses an IC (Integrated Circuit: Integrated Circuit) chip to implement the functions of the entire system including multiple processing units. In this way, various processing units are composed of more than one of the above-mentioned various processors as a hardware structure.

[0176] Furthermore, more specifically, the hardware structure of these various processors is a circuit (circuitry) formed by combining circuit elements such as semiconductor elements.

[0177] [About the program that makes the computer work]

[0178] A program that enables a computer to implement part or all of the processing functions of the computer 20 in the implementation example and the computer 20A in the variation example of the implementation example can be recorded on a CD, a disk, or a semiconductor memory or other tangible non-temporary information storage medium, i.e., a computer-readable medium, and the program can be provided through the information storage medium.

[0179] Furthermore, instead of providing the program in a tangible, non-transitory computer-readable medium, the program signal may be provided as a download service using telecommunication lines such as the Internet.

[0180] Furthermore, part or all of the processing functions in the computer 20 and the like may be realized by cloud computing, and may be provided as SaaS (Software as a Service).

[0181] The present invention is not limited to the above-described embodiments, and various modifications are possible without departing from the gist of the technical concept of the present invention.

Claims

1. An image processing device comprising a processor, wherein the processor performs the following processing: Obtain user identification information; Acquiring a first imaging condition applicable to the imaging device; acquiring a first image captured and generated using the imaging device to which the first imaging condition is applied; setting a first denoising intensity to be applied in denoising the first image; and applying the first denoising intensity to perform denoising processing on the first image to generate a first denoised image, The processor performs the following processing: From a plurality of second signal-to-noise ratios derived from each of a plurality of second images generated in a plurality of past imaging conditions for each user under which a plurality of second imaging conditions were applied, a second signal-to-noise ratio corresponding to a second imaging condition that is the same as the first imaging condition or a second imaging condition that is close to the first imaging condition is obtained as the first signal-to-noise ratio, A denoising intensity derived based on the first signal-to-noise ratio is set as the first denoising intensity.

2. The image processing device according to claim 1, wherein: The processor performs the following processing: With reference to a signal-to-noise ratio database storing each of the plurality of second imaging conditions in association with the plurality of second signal-to-noise ratios, the first signal-to-noise ratio corresponding to the second imaging condition that is the same as the first imaging condition or the second imaging condition that is close to the first imaging condition is obtained.

3. The image processing device according to claim 2, wherein: The processor performs the following processing: When the first denoising strength is changed, the signal-to-noise ratio database is updated according to the changed second denoising strength.

4. The image processing device according to claim 1, wherein: The processor performs the following processing: Performing a plurality of denoising processes with different denoising intensities on the first image to generate a plurality of third denoised images; deriving a third signal-to-noise ratio from each of the plurality of third denoised images; and A third denoising intensity applied to the third denoised image for deriving the third signal-to-noise ratio having the smallest difference from the first signal-to-noise ratio is set as the first denoising intensity.

5. The image processing device according to claim 1, wherein: The processor performs the following processing: Calculating a fourth signal-to-noise ratio based on the first image; and A fourth denoising intensity corresponding to a fourth signal-to-noise ratio is set as the first denoising intensity using a function indicating a relationship between the signal-to-noise ratio and the denoising intensity.

6. The image processing device according to claim 1, wherein: The processor performs the following processing: Displaying the first denoised image on a display device; causing the display device to display an option indicating an evaluation of the first denoising intensity applied in denoising processing on the first denoised image; acquiring a first evaluation signal indicating an evaluation of the first denoising intensity selected from the options; and The evaluation of the first denoising intensity indicated by the first evaluation signal is fed back to the setting of the first denoising intensity.

7. The image processing device according to claim 1, wherein: The processor performs the following processing: Applying a fifth imaging condition that is the same as the first imaging condition or a fifth imaging condition that is close to the first imaging condition, applying the first denoising intensity to a past image generated by past imaging to perform denoising processing, and causing the generated fifth denoised image to be displayed on a display device; acquiring a fifth evaluation signal indicating an evaluation of a fifth denoising intensity applied in denoising processing on the fifth denoised image; and Whether to maintain or change the first denoising intensity is determined based on the evaluation of the fifth denoising intensity indicated by the fifth evaluation signal.

8. The image processing device according to claim 7, wherein: The past image is a normal image generated by photographing a normal imaging object in the past.

9. The image processing apparatus according to claim 7, wherein: The past image is applied with a sixth imaging condition that is the same as the first imaging condition, or a sixth imaging condition that is close to the first imaging condition, and is applied with an image of the same imaging subject generated by imaging the same imaging subject in the past. The processor performs the following processing: A sixth denoised image obtained by performing denoising processing on the same imaging target image and a sixth denoising intensity applied to the denoising processing performed on the same imaging target image are displayed on a display device.

10. The image processing device according to claim 9, wherein: The processor performs the following processing: acquiring a sixth evaluation signal indicating an evaluation of the sixth denoising strength; and Whether to maintain or change the first denoising intensity is determined based on the evaluation of the sixth denoising intensity indicated by the sixth evaluation signal.

11. A method for operating an image processing device, which is applicable to a computer having a processor, The processor performs the following processing: Obtain user identification information; Acquiring a first imaging condition applicable to the imaging device; acquiring a first image captured and generated using the imaging device to which the first imaging condition is applied; setting a first denoising intensity to be applied in denoising the first image; and applying the first denoising intensity to perform denoising processing on the first image to generate a first denoised image, When the first denoising intensity is set, From a plurality of second signal-to-noise ratios derived from each of a plurality of second images generated in a plurality of past imaging conditions for each user under which a plurality of second imaging conditions were applied, a second signal-to-noise ratio corresponding to a second imaging condition that is the same as the first imaging condition or a second imaging condition that is close to the first imaging condition is obtained as the first signal-to-noise ratio, A denoising intensity derived based on the first signal-to-noise ratio is set as the first denoising intensity.

12. A non-transitory computer-readable recording medium having a program recorded thereon, The program enables the computer to perform the following functions: Obtain user identification information; Acquiring a first imaging condition applicable to the imaging device; acquiring a first image captured and generated using the imaging device to which the first imaging condition is applied; setting a first denoising intensity to be applied in denoising the first image; and applying the first denoising intensity to perform denoising processing on the first image to generate a first denoised image, The function for setting the first denoising strength is: From a plurality of second signal-to-noise ratios derived from each of a plurality of second images generated in a plurality of past imaging conditions for each user under which a plurality of second imaging conditions were applied, a second signal-to-noise ratio corresponding to a second imaging condition that is the same as the first imaging condition or a second imaging condition that is close to the first imaging condition is obtained as the first signal-to-noise ratio, A denoising intensity derived based on the first signal-to-noise ratio is set as the first denoising intensity.

13. A medical image processing system comprising an image processing device for performing predetermined image processing on a medical image generated by imaging a subject using an imaging device, The image processing device includes a processor, and the processor performs the following processing: Obtain user identification information; Acquiring a first imaging condition applicable to the imaging device; acquiring a first image captured and generated using the imaging device to which the first imaging condition is applied; setting a first denoising intensity to be applied in denoising the first image; and applying the first denoising intensity to perform denoising processing on the first image to generate a first denoised image, The processor performs the following processing: From a plurality of second signal-to-noise ratios derived from each of a plurality of second images generated in a plurality of past imaging conditions for each user under which a plurality of second imaging conditions were applied, a second signal-to-noise ratio corresponding to a second imaging condition that is the same as the first imaging condition or a second imaging condition that is close to the first imaging condition is obtained as the first signal-to-noise ratio, A denoising intensity derived based on the first signal-to-noise ratio is set as the first denoising intensity.

Images