WO2024024179A1

WO2024024179A1 - Imaging assistance device, method, and program

Info

Publication number: WO2024024179A1
Application number: PCT/JP2023/014632
Authority: WO
Inventors: 潤桝本; 裕二地曵
Original assignee: 富士フイルム株式会社
Priority date: 2022-07-29
Filing date: 2023-04-10
Publication date: 2024-02-01

Abstract

According to the present invention, a processor acquires a first image including at least a part of a subject, which is acquired prior to the acquisition of a diagnostic image by an MRI device, presets an imaging condition for the MRI device in the acquisition of the diagnostic image on the basis of the first image, allows the MRI device to capture an image of the subject on the basis of the imaging condition to capture the diagnostic image, and induces a second image including at least a part of the subject, which is imaged under the preset imaging condition, from the diagnostic image.

Description

Photography aids, methods and programs

The present disclosure relates to a photographic assisting device, method, and program.

In recent years, advances in medical equipment such as CT (Computed Tomography) devices and MRI (Magnetic Resonance Imaging) devices have made it possible to perform image diagnosis using higher quality, high resolution medical images. Furthermore, computer-aided diagnosis (CAD) has been put into practical use, which derives the probability of existence of a lesion, position information, etc. by analyzing medical images, and presents this to a doctor such as an image interpreter.

On the other hand, when an MRI apparatus images a subject, a positioning image including at least a part of the subject is obtained prior to obtaining a diagnostic image, and imaging conditions for the diagnostic image are determined based on the positioning image. Techniques for setting (for example, imaging parameters such as the direction of the imaging axis, imaging range, and magnetic strength) are known. For example, Japanese Patent Laid-Open No. 2021-083730 discloses that a positioning image is acquired and displayed, it is determined whether the positioning image includes the entire region of interest of the subject, and if the determination is negative, , a method has been proposed in which a photographing range for re-acquiring the positioning image is set using AI (Artificial Intelligence) or the like, and then the positioning image is re-acquired.

By the way, regarding diagnostic images acquired by an MRI device, the last acquired positioning image is associated with the diagnostic image, and both the positioning image and the diagnostic image are displayed at the time of image interpretation, so that it is possible to understand the overall image and to understand the tomographic plane. The location is specified, etc. Therefore, after resetting the imaging conditions using the positioning image, it is necessary to take another positioning image and confirm the imaging conditions before generating a diagnostic image. Here, obtaining the positioning image requires time for re-photographing and reconstructing the subject, which places a heavy burden on the patient, who is the subject, and also places a heavy burden on the technician who performs the photographing.

The present disclosure has been made in view of the above circumstances, and aims to reduce the burden required for retaking positioning images in an MRI apparatus.

A photographic assisting device according to a first aspect of the present disclosure includes at least one processor,
The processor acquires a first image that includes at least a portion of the subject, the first image being acquired prior to the acquisition of the diagnostic image by the MRI apparatus;
Setting imaging conditions of the MRI apparatus when acquiring a diagnostic image based on the first image,
A diagnostic image is obtained by causing the MRI device to image the subject based on the imaging conditions,
A second image including at least a portion of the subject, captured under the set imaging conditions, is derived from the diagnostic image.

A photographing auxiliary device according to a second aspect of the present disclosure may be such that, in the photographing auxiliary device according to the first aspect, the processor stores the diagnostic image and the second image in a storage.

In the imaging auxiliary device according to the third aspect of the present disclosure, in the imaging auxiliary device according to the first or second aspect, the imaging conditions include the direction of the imaging axis of the subject, the imaging range of the subject, and the imaging in the MRI apparatus. It may include at least one of the parameters.

A photographing assisting device according to a fourth aspect of the present disclosure is a photographing assisting device according to any one of the first to third aspects, wherein the processor performs machine learning to derive photographing conditions from the first image. The photographing conditions may be derived using the learned model.

A photographing assisting device according to a fifth aspect of the present disclosure is a photographing assisting device according to any one of the first to fourth aspects, wherein the processor performs machine learning to derive the second image from the diagnostic image. The second image may be derived using the learned model.

A photography auxiliary device according to a sixth aspect of the present disclosure is a photography auxiliary device according to any one of the first to fifth aspects, wherein the processor derives the second image based on set photography conditions. The image derivation conditions may be derived for the image derivation conditions.

The photographing assistance method according to the present disclosure acquires a first image that includes at least a part of the subject, which is acquired prior to acquiring a diagnostic image by an MRI apparatus,
Setting imaging conditions of the MRI apparatus when acquiring a diagnostic image based on the first image,
A diagnostic image is obtained by causing the MRI device to image the subject based on the imaging conditions,
A second image including at least a portion of the subject, captured under the set imaging conditions, is derived from the diagnostic image.

The imaging assistance program according to the present disclosure includes a step of acquiring a first image including at least a part of the subject, which is acquired prior to acquiring a diagnostic image by an MRI apparatus;
a procedure for setting imaging conditions of an MRI apparatus when acquiring a diagnostic image based on the first image;
a procedure for obtaining a diagnostic image by causing an MRI apparatus to image a subject based on imaging conditions;
The computer is caused to perform a procedure for deriving a second image including at least a portion of the subject, which is photographed under the set photographing conditions, from the diagnostic image.

According to the present disclosure, it is possible to reduce the burden required for retaking positioning images in an MRI apparatus.

A diagram showing a schematic configuration of an MRI imaging system to which an imaging auxiliary device according to an embodiment of the present disclosure is applied. A diagram showing the hardware configuration of the photographic assistance device according to the present embodiment Functional configuration diagram of the photographic assistance device according to this embodiment Diagram showing training data Flowchart showing processing performed in this embodiment A diagram schematically showing the processing performed in this embodiment

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. First, the configuration of an MRI imaging system to which the imaging auxiliary device according to the present embodiment is applied will be described. FIG. 1 is a diagram showing a schematic configuration of an MRI imaging system. In the MRI imaging system shown in FIG. 1, a console 1 including an imaging assistance device according to the present embodiment, an MRI apparatus 2, and an image storage server 3 are connected via a network 4 in a communicable state.

The console 1 is a computer that includes a photographic assistance device according to this embodiment, and has a photographic assistance program according to this embodiment installed therein. The console 1 may be a workstation or a personal computer directly operated by a technician who operates the MRI apparatus 2 to perform diagnosis, or may be a server computer connected thereto via a network. The imaging assistant program is stored in a storage device of a server computer connected to a network or in a network storage in a state that can be accessed from the outside, and is downloaded and installed on the console 1 used by the doctor in response to a request. Alternatively, it is recorded and distributed on a recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory), and installed on the console 1 from the recording medium.

The MRI device 2 is a well-known imaging device that generates a three-dimensional MRI image representing the region of the subject H by photographing the region to be diagnosed. The target site can be any organ of the subject H, such as the brain, heart, lungs, and liver.

The MRI apparatus 2 includes, for example, an annular gantry 2A and an imaging table 2B on which a subject H is placed. Moreover, a static magnetic field magnet, a high frequency magnetic field coil, and a gradient magnetic field coil (all not shown) are built into the MRI apparatus 2. The MRI apparatus 2 has a function of collecting MR data of the subject H by driving a static magnetic field magnet, a high-frequency magnetic field coil, and a gradient magnetic field coil, and generates a three-dimensional MRI image consisting of a plurality of tomographic images by reconstructing the MR data. , a function of transmitting the image data of the generated MRI image to the console 1 , and a function of transmitting the image data of the generated MRI image to the image storage server 3 via the network 4 . Note that the functions executed by the processing circuit are stored in a storage (not shown) of the MRI apparatus 2 as programs executable by a computer, and the processing circuit executes various programs by executing the programs stored in the storage. perform a function.

The image storage server 3 is a computer that stores and manages various data, and is equipped with a large-capacity external storage device and database management software. The image storage server 3 communicates with other devices via a wired or wireless network 4 and sends and receives image data and the like. Specifically, various data including image data of MRI images generated by the MRI apparatus 2 is acquired via the network, and is stored and managed in a recording medium such as a large-capacity external storage device. Note that the storage format of image data and communication between devices via the network 4 are based on protocols such as DICOM (Digital Imaging and Communication in Medicine).

Next, a photographic assisting device according to this embodiment will be explained. FIG. 2 is a diagram showing the hardware configuration of the console 1 including the photographic assisting device according to this embodiment. As shown in FIG. 2, the console 1 includes a CPU (Central Processing Unit) 11, a nonvolatile storage 13, and a memory 16 as a temporary storage area. The console 1 also includes a display 14 such as a liquid crystal display, an input device 15 such as a keyboard, a mouse, a touch panel, and a microphone for inputting voice, and a network I/F (InterFace) 17 connected to the network 4. The CPU 11, storage 13, display 14, input device 15, memory 16, and network I/F 17 are connected to the bus 18. Note that the CPU 11 is an example of a processor in the present disclosure.

The storage 13 is realized by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like. A photography assistance program 12 is stored in a storage 13 as a storage medium. The CPU 11 reads out the photography assistance program 12 from the storage 13, expands it into the memory 16, and executes the expanded photography assistance program 12.

Next, the functional configuration of the photographic assisting device according to this embodiment will be explained. FIG. 3 is a diagram showing the functional configuration of the photographic assistance device according to this embodiment. As shown in FIG. 3, the photographing assistant device 20 includes an image acquisition section 21, a photographing condition setting section 22, a derivation section 23, and a display control section 24. When the CPU 11 executes the photography assistance program 12, the CPU 11 functions as an image acquisition section 21, a photography condition setting section 22, a derivation section 23, and a display control section 24.

The image acquisition unit 21 acquires an MRI image for diagnosis by causing the MRI apparatus 2 to photograph the subject H based on instructions from the input device 15 by the operator. The MRI image for diagnosis will be referred to as a diagnostic image G0 in the following description. Further, the imaging for acquiring the diagnostic image G0 will be referred to as main imaging in the following description. Furthermore, prior to acquiring the diagnostic image G0, the image acquisition unit 21 acquires a first image C1 for setting imaging conditions (hereinafter referred to as a condition setting image) that includes at least a part of the subject H. get. In the following description, the photographing for acquiring the condition setting image will be referred to as preliminary photographing. The first condition setting image C1 is an example of the first image of the present disclosure.

Here, the diagnostic image G0 is composed of a plurality of tomographic images including a desired region of the subject H. The condition setting image is also composed of a plurality of tomographic images like the diagnostic image G0, but since it is an image used to set imaging conditions, the number of tomographic images is smaller than the diagnostic image G0. That is, the condition setting image consists of a tomographic image representing a narrower range of tomographic plane in the subject H than the diagnostic image G0. For example, if the target region is the brain of subject H, the diagnostic image G0 is acquired to include the entire tomographic plane of the brain, but the condition setting image is acquired to include the tomographic plane of a part of the brain. be obtained.

The imaging conditions include the direction in which the tomographic planes of the tomographic images included in the diagnostic image G0 are lined up (hereinafter referred to as the direction of the imaging axis), the range of the tomographic images (hereinafter referred to as the imaging range), and the imaging parameters at the time of main imaging. Can be mentioned. Imaging parameters include the strength of the magnetic field in the MRI apparatus 2 and the type of coil used. In the following description, only the direction of the photographing axis and the photographing range are set as photographing conditions.

Here, the diagnostic image G0 needs to include a region of interest in the subject H that is the target of diagnosis. In this embodiment, a condition setting image is acquired prior to acquiring the diagnostic image G0, and imaging conditions for main imaging are set based on the condition setting image.

When setting imaging conditions for main imaging based on the condition setting image, it is important that the region of interest is included in the condition setting image, but depending on the condition of the subject H at the time of preliminary imaging, , it is possible that part or all of the region of interest is not included in the condition setting image.

The condition setting image is acquired so as to include the center of the magnetic field according to the imaging conditions for preliminary imaging that have been initialized in advance. The subject H may shift from the previously assumed position, and as a result, the region of interest of the subject H may not be sufficiently included in the condition setting image.

In the present embodiment, the photographing condition setting unit 22 sets photographing conditions for actual photographing based on the first condition setting image C1. Specifically, by increasing the resolution of the first condition setting image C1, the number of pixels (voxels) of the tomographic image is increased, and by using the high resolution first condition setting image C1. , determine the direction of the imaging axis to make the region of interest easier to see, and the imaging range that includes the entire region of interest. The direction of the imaging axis and the imaging range may be set by analyzing the high-resolution first condition setting image C1. Note that the process of increasing the resolution of the first condition setting image C1 may be performed by interpolation calculation or may be performed by a well-known super resolution technique. Furthermore, the first condition setting image C1 may be made to have a high resolution by using a learned model that has been subjected to machine learning to generate a high resolution image.

Note that the imaging condition setting unit 22 may set the imaging conditions for the main imaging using, for example, the method described in the above-mentioned Japanese Patent Application Publication No. 2021-083730. In this case, the imaging condition setting unit 22 determines whether or not the entire region of interest is included in the first condition setting image C1, and if it is determined that the region of interest is not included, the imaging condition setting unit 22 The position of the region of interest is estimated based on the image C1. The determination of whether the region of interest is included is made by detecting anatomical feature points included in the first condition setting image C1, pattern matching with a model image such as a standard image of the subject H, etc. It can be carried out. Alternatively, it may be determined whether or not a region of interest is included using a trained model that has been subjected to machine learning to output the position of the region of interest for images that do not include part of the region of interest. .

Then, based on the position of the region of interest included in the first condition setting image C1, the imaging condition setting unit 22 sets the initially set imaging conditions (the direction of the imaging axis and the imaging range) to include the entire region of interest. By changing the following, the shooting conditions for the actual shooting are set.

The imaging condition setting unit 22 displays the first condition setting image C1 on the display 14, and adjusts the direction of the imaging axis and the imaging range on the displayed first condition setting image C1 so as to include the region of interest. The shooting conditions for the actual shooting may be set by receiving an operation from the operator to set the shooting conditions.

In this embodiment, when the imaging condition setting unit 22 sets the imaging conditions for main imaging, the image acquisition unit 21 causes the MRI apparatus 2 to perform the main imaging of the subject H according to the set imaging conditions, thereby diagnosing the subject H. Obtain image G0.

The deriving unit 23 pseudo-derives a second condition setting image C2, which includes at least a portion of the subject H, photographed under the photographing conditions set by the photographing condition setting unit 22, from the diagnostic image G0. The second condition setting image C2 is an example of the second image of the present disclosure.

Specifically, the derivation unit 23 determines the direction of the imaging axis and the imaging direction for deriving the second condition setting image C2 to include the region of interest based on the imaging conditions set by the imaging condition setting unit 22. The range (hereinafter referred to as image derivation condition) is derived. At this time, the image derivation conditions may be derived by extracting the region of interest from the diagnostic image G0. Then, the derivation unit 23 derives a second condition setting image C2 by extracting a tomographic image within a range based on the image derivation conditions from the diagnostic image G0.

Note that the derivation unit 23 includes a learned model constructed by machine learning a neural network so as to derive the second condition setting image C2 from the diagnostic image G0, and uses the learned model to derive the second condition setting image C2. The image C2 may be derived.

FIG. 4 is a diagram showing teacher data for learning a trained model for deriving the second condition setting image C2. As shown in FIG. 4, the teacher data 30 consists of a learning image 31 to be input to the neural network and correct answer data 32. The learning image 31 is an MRI image, and the correct data 32 is a condition setting image acquired prior to acquiring the learning image 31. More specifically, it is an image acquired immediately before acquiring the diagnostic images G0 of various subjects H, and is an image stored in the image storage server 3 together with the diagnostic images G0. The learned model is constructed by using a large amount of such teacher data 30 and by machine learning a neural network so as to output a condition setting image when the diagnostic image G0 is input.

Note that the derivation unit 23 displays the diagnostic image G0 on the display 14, and sets the range of tomographic planes to be included in the second condition setting image C2 from the diagnostic image G0 to the diagnostic image G0 according to instructions from the operator. The second condition setting image C2 may be derived based on the range determined.

The display control unit 24 displays the diagnostic image G0, the first condition setting image C1, and the second condition setting image C2 acquired by photography on the display 14.

Next, the processing performed in this embodiment will be explained. FIG. 5 is a flowchart showing the processing performed in this embodiment, and FIG. 6 is a diagram schematically showing the processing performed in this embodiment. First, in response to an operator's instruction for preliminary imaging, the image acquisition unit 21 causes the MRI apparatus 2 to perform preliminary imaging, and acquires the first condition setting image C1 (step ST1). Next, the photographing condition setting unit 22 sets photographing conditions for main photographing based on the first condition setting image C1 (step ST2).

Subsequently, the image acquisition unit 21 causes the MRI apparatus 2 to perform main imaging according to the operator's instruction for main imaging, or without waiting for the instruction, and obtains the diagnostic image G0 (step ST3). Then, the derivation unit 23 derives the second condition setting image C2 based on the diagnostic image G0 (step ST4). Then, the display control unit 24 displays the diagnostic image G0 and the second condition setting image C2 for confirmation (image display: step ST5). Subsequently, after confirmation by the operator, the diagnostic image G0 and the second condition setting image C2 are transmitted from the network I/F 17 to the image storage server 3 (image transmission: step ST6), and the process ends. The diagnostic image G0 and the second condition setting image C2 are stored in the image storage server 3 in association with each other.

Here, when performing imaging with an MRI apparatus, a positioning image, that is, a condition setting image is acquired, and after setting the imaging conditions, the condition setting image is acquired again, and the main imaging is performed to obtain the diagnostic image G0. It is necessary to acquire the diagnostic image G0 and the condition setting image acquired immediately before acquiring the diagnostic image G0. However, since it takes time for the MRI apparatus 2 to take an image and reconstruct the image, the burden of re-imaging the condition setting image is large.

According to this embodiment, the second condition setting image C2 is derived from the diagnostic image G0 without acquiring the condition setting image again. Therefore, even if preliminary imaging is not performed again, it is possible to obtain the condition setting image obtained immediately before obtaining the diagnostic image G0, although it is a pseudo image. Therefore, the burden required for retaking positioning images in the MRI apparatus can be reduced.

Furthermore, in the embodiment described above, a condition setting image having a narrower cross-sectional plane range than the diagnostic image G0 is acquired, but the present invention is not limited to this. A condition setting image having the same tomographic range as the diagnostic image G0 may be acquired.

Further, in the above embodiment, the hardware structure of the processing unit (Processing Unit) that executes various processes, such as the image acquisition unit 21, the imaging condition setting unit 22, the derivation unit 23, and the display control unit 24, is as follows. The following various processors can be used. As mentioned above, in addition to the CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, the various processors listed above include circuits such as FPGA (Field Programmable Gate Array) after manufacturing. Programmable logic devices (PLDs), which are processors whose configuration can be changed, and specialized electrical devices, which are processors with circuit configurations specifically designed to execute specific processes, such as ASICs (Application Specific Integrated Circuits). Includes circuits, etc.

One processing unit may be composed of one of these various types of processors, or a combination of two or more processors of the same type or different types (for example, a combination of multiple FPGAs or a combination of a CPU and an FPGA). ). Further, the plurality of processing units may be configured with one processor.

As an example of configuring a plurality of processing units with one processor, firstly, as typified by computers such as a client and a server, one processor is configured with a combination of one or more CPUs and software, There is a form in which this processor functions as a plurality of processing units. Second, there are processors that use a single IC (Integrated Circuit) chip, such as System On Chip (SoC), which implements the functions of an entire system including multiple processing units. be. In this way, various processing units are configured using one or more of the various processors described above as a hardware structure.

Furthermore, as the hardware structure of these various processors, more specifically, an electric circuit (Circuitry) that is a combination of circuit elements such as semiconductor elements can be used.

1 Console 2 MRI device 3 Image storage server 4 Network 11 CPU
12 Shooting assistance program 13 Storage 14 Display 15 Input device 16 Memory 17 Network I/F
18 Bus 20 Photography auxiliary device 21 Image acquisition unit 22 Photography condition setting unit 23 Derivation unit 24 Display control unit 30 Teacher data 31 Learning data 32 Correct data C1 First condition setting image C2 Second condition setting image G0 Diagnosis image

Claims

comprising at least one processor;
The processor includes:
Obtaining a first image that includes at least a portion of the subject and that is obtained prior to obtaining a diagnostic image by the MRI device;
setting imaging conditions for the MRI apparatus when acquiring the diagnostic image based on the first image;
Obtaining the diagnostic image by causing the MRI apparatus to image the subject based on the imaging conditions,
A photographing auxiliary device that derives, from the diagnostic image, a second image photographed under the set photographing conditions and including at least a portion of the subject.
The photographing auxiliary device according to claim 1, wherein the processor stores the diagnostic image and the second image in a storage.
The imaging auxiliary device according to claim 1 or 2, wherein the imaging conditions include at least one of a direction of an imaging axis of the subject, an imaging range of the subject, and imaging parameters of the MRI apparatus.
The photographing assistance device according to claim 1 or 2, wherein the processor derives the photographing conditions using a learned model that has been subjected to machine learning to derive the photographing conditions from the first image.
The imaging assistant device according to claim 1 or 2, wherein the processor derives the second image using a learned model that has been subjected to machine learning so as to derive the second image from the diagnostic image.
The photographing auxiliary device according to claim 1 or 2, wherein the processor derives image derivation conditions for deriving the second image based on the set photographing conditions.
Obtaining a first image that includes at least a portion of the subject and that is obtained prior to obtaining a diagnostic image by the MRI device;
setting imaging conditions of the MRI apparatus when acquiring the diagnostic image based on the first image;
Obtaining the diagnostic image by causing the MRI apparatus to image the subject based on the imaging conditions,
A photographing auxiliary method for deriving a second image photographed under the set photographing conditions and including at least a part of the subject from the diagnostic image.
a step of acquiring a first image that includes at least a portion of the subject, the first image being acquired prior to the acquisition of a diagnostic image by the MRI apparatus;
a step of setting imaging conditions of the MRI apparatus when acquiring the diagnostic image based on the first image;
a step of obtaining the diagnostic image by causing the MRI apparatus to image the subject based on the imaging conditions;
A photographing assistant program that causes a computer to execute a procedure of deriving a second image photographed under the set photographing conditions and including at least a part of the subject from the diagnostic image.