Generation device and generation method

Abstract

To easily acquire desired DICOM data.SOLUTION: The RAG system 20 includes a receiver 21 that receives an image generating request including DICOM data-related information, a determiner 22 that determines DICOM data-generation-related information based on the DICOM data-related information, a generator 23 that generates a prompt for instructing generation of DICOM data based on the DICOM data-generation-related information, and an inputter 24 that inputs the prompt generated by the generator 23 to a generation AI model 31 that generates DICOM data based on the prompt.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] One aspect of the present disclosure relates to a generating device and a generating method. [Background technology]

[0002] Patent document 1 discloses a technology that sends an acquisition request to an image server that stores DICOM data including medical image data and additional information (patient information, examination information, series information, etc.) to acquire patient information and examination information that matches predetermined search conditions, and generates interpretation order information that requests the interpretation of medical images based on the acquired patient information and examination information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-87304 Summary of the Invention [Problem to be solved by the invention]

[0004] Generally, medical data such as DICOM data is personal information, so it is difficult to obtain it for the purpose of utilizing it, and securing a certain amount of data requires time and human resources. Also, while it is possible to obtain DICOM data using a data provision service, it is difficult to obtain the desired DICOM data that meets the conditions you want to use.

[0005] One aspect of the present disclosure has been made in consideration of the above-described circumstances, and aims to provide a generation device and a generation method that can easily acquire desired DICOM data. [Means for solving the problem]

[0006] A generation device according to one aspect of the present disclosure includes a reception unit that receives an image generation request including information about DICOM data, a determination unit that determines information regarding the generation of DICOM data based on the information about the DICOM data, a generation unit that generates a prompt to instruct the generation of DICOM data based on the information about the generation of DICOM data, and a control unit that controls a generation AI model that generates DICOM data based on the prompt generated by the generation unit.

[0007] In a generation device according to one aspect of the present disclosure, information regarding the generation of DICOM data is determined based on information regarding received DICOM data, and a prompt for instructing the generation of DICOM data is generated based on the information regarding the generation of the DICOM data. With this configuration, the prompt is generated according to the information regarding the received desired DICOM data, and the desired DICOM data is generated by inputting the prompt into a generation AI model. Furthermore, this method does not require the use of a data provision service or the like to obtain DICOM data, making it possible to easily obtain DICOM data. As described above, the generation device according to one aspect of the present disclosure makes it possible to easily obtain desired DICOM data. [Effects of the Invention]

[0008] According to one aspect of the present disclosure, desired DICOM data can be easily acquired. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing the device configuration of a DICOM data generation system according to this embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a prompt generated by the RAG system. [Figure 3] FIG. 3 is a diagram showing an example of image data included in DICOM data. [Figure 4]FIG. 4 is a table showing an example of tag information included in DICOM data. [Figure 5] FIG. 5 is a flowchart showing the processing executed by the RAG system. [Figure 6] FIG. 6 is a diagram illustrating an example of a hardware configuration of the RAG system. DETAILED DESCRIPTION OF THE INVENTION

[0010] The present disclosure will be described with reference to the accompanying drawings. Whenever possible, the same parts are designated by the same reference numerals and redundant description will be omitted.

[0011] FIG. 1 is a diagram showing the device configuration of a DICOM data generation system according to this embodiment. The DICOM data generation system shown in FIG. 1 is a system for easily obtaining desired DICOM data by automatically generating DICOM data in response to input information. DICOM (Digital Imaging and Communications in Medicine) is an international standard that defines the format of digital medical image data. DICOM supports medical images such as digital X-rays, digital radiography (DR), computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound. DAICOM images are captured in a lossless format that does not degrade the image data, such as a bitmap RAW format. In the following description, DICOM data is described as including not only image data but also tag information associated with the image data. The tag information is information such as patient information related to the image data. In more detail, the tag information may include various information defined by the standard, such as the format name, data length, a unique instance UID, series, modality, patient information, audio data, and imaging time. DAICOM's communication format conforms to the OSI reference model, and data is encapsulated using the TCP / IP protocol.

[0012] Because medical data such as DICOM data is personal information, it is difficult to obtain it for the purpose of utilization, and securing a certain amount of data requires time and personnel costs. While it is possible to obtain DICOM data using a data provision service, it is difficult to obtain the desired DICOM data that meets the desired conditions. To address this issue, a DICOM data generation system easily generates (acquires) desired DICOM data even in situations where an individual diagnosis is not involved. The DICOM data generated (acquired) by the DICOM data generation system may be used, for example, as training data for medical professionals or as data for clinical trials of medical devices, etc.

[0013] 1, the DICOM data generation system includes a terminal 10, a Retrieval-Augmented Generation (RAG) system 20, and a server device 30, which are configured to be able to communicate with each other via a network including a wireless communication network and a fixed communication network. The RAG system 20 constitutes a generation device that generates a prompt based on information received from the terminal 10. A prompt is information indicating an instruction or question entered by a user in an interactive system such as a dialogue with an AI model or a command line interface (CLI).

[0014] The terminals 10 are devices used by users (e.g., medical professionals) who intend to utilize DICOM data. The terminals 10 are, for example, personal computers, smartphones, tablet terminals, feature phones, server devices, game consoles, etc. Although only two terminals 10 are shown in FIG. 1, the DICOM data generation system may include any number of terminals 10 greater than or equal to two.

[0015] The server device 30 stores a generative AI model 31 and enables the provision of DICOM data using the generative AI model 31. The generative AI model is a model that, in response to a prompt containing input information, generates content according to any one or a combination of the instructions, context, question, and output format indicated by the prompt and returns the content as response information. The prompt may also include input information, in which case the generative AI model 31 generates response information targeted at the input information. The generative AI model 31 may be, for example, an interactive AI that includes a large-scale language model (LLM) and a user interface (UI) for interacting with the user and enables text or voice chat with the user. Examples of such generative AI models include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, and PaLM2. While the present embodiment describes an example in which the server device 30 provides DICOM data using one generative AI model 31, the server device 30 may also provide DICOM data using multiple generative AI models. 1 shows only one server device 30, the DICOM data generation system may include multiple server devices 30. Although the above describes a large-scale language model as an example, other AI models may also be used. The generation AI model 31 generates DICOM data based on prompts.

[0016] The RAG system 20 is configured to include, as functional components, a reception unit 21, a determination unit 22, a generation unit 23, an input unit 24 (control unit), and a storage unit 25. The RAG system 20 inputs a prompt corresponding to input information from the terminal 10 to the server device 30, and relays response information from the server device 30 to the prompt to the terminal 10. The RAG system 20 also has a function to generate a prompt based on the input information from the terminal 10. The function of each functional unit of the RAG system 20 will be described in detail below.

[0017] The reception unit 21 receives an image generation request including information about DICOM data. The reception unit 21 outputs the received information to the determination unit 22. The reception unit 21 receives an image generation request from a user, for example, via the terminal 10. The information about DICOM data refers to various information related to the DICOM data that is ultimately desired to be output from the generation AI model 31.

[0018] The reception unit 21 receives, for example, information about a patient from the terminal 10 as information about the DICOM data. The information about a patient is information about the patient related to the DICOM data. The reception unit 21 may receive, as information about the patient's symptoms (for example, the name of the disease or the symptom itself, such as "stomach pain"), as information about the patient. The reception unit 21 may receive, as information about the patient's images, information indicating the patient's attributes (for example, a woman in her 40s) or information about an image of the patient. The reception unit 21 may receive, as information about the patient's images, the image itself showing the patient's condition (for example, a CT image).

[0019] The reception unit 21 may receive information about equipment related to image acquisition of a patient as information about DICOM data. The information about equipment related to image acquisition of a patient may be information specifying a hospital related to image acquisition of a patient, or information specifying examination equipment (e.g., CT, MR, etc.) related to image acquisition of a patient. The reception unit 21 may receive the information about equipment related to image acquisition of a patient from a user via the terminal 10, or may obtain (receive) the information from information stored in association with each user.

[0020] The receiving unit 21 may receive information regarding the use of the DICOM data as information regarding the DICOM data. The information regarding the use of the DICOM data may include information indicating the purpose for which the DICOM data output from the generative AI model 31 is to be utilized, such as "for clinical trials" or "for training." The information regarding the use of the DICOM data may also include information regarding clinical trials (e.g., the number of data items) or information regarding training (e.g., the difficulty of the training).

[0021] The determination unit 22 determines information related to the generation of DICOM data based on the information related to the DICOM data received by the reception unit 21. The determination unit 22 may determine information instructing the generation of DICOM data (information related to a generation instruction). In particular, the determination unit 22 determines information related to an instruction to generate a prompt related to the generation of DICOM data (for example, information used to generate a prompt).

[0022] The determination unit 22 may select (determine) information to be used for generating the prompt from information related to the DICOM data received by the reception unit 21. For example, the determination unit 22 may determine case data, patient overview (information such as name, date of birth, age, weight, allergies, pregnancy status, etc.), examination equipment (imaging equipment), symptoms, etc. as the information to be used for generating the prompt. The determination unit 22 may determine information indicating the purpose of utilization, such as "for clinical trials" or "for training," as the information to be used for generating the prompt. The determination unit 22 may determine a description of the DICOM data to be generated as the information to be used for generating the prompt.

[0023] The determination unit 22 may determine multiple example data of image data and tag information contained in the DICOM data generated in the generation AI model 31 based on information regarding the DICOM data, and determine the multiple example data as information regarding the generation of the DICOM data (more specifically, information used to generate a prompt).

[0024] The determination unit 22 may determine the plurality of exemplary data based on, for example, information stored in the storage unit 25. In this case, the storage unit 25 stores, for example, a plurality of DICOM data items, each including image data and tag information, associated with each symptom. The storage unit 25 may also store a plurality of DICOM data items, each including image data or tag information, associated with each symptom. Such a plurality of DICOM data items associated with each symptom are registered in advance and stored in the storage unit 25. The determination unit 22 identifies the plurality of DAICOM data items corresponding to the patient's symptoms based on the plurality of DAICOM data items for each symptom stored in the storage unit 25 and information about the patient's symptoms received by the reception unit 21. That is, the determination unit 22 identifies, from the information stored in the storage unit 25, the plurality of DAICOM data items associated with the symptoms indicated in the information about the patient's symptoms received by the reception unit 21. The determination unit 22 then sets the image data and tag information included in the identified plurality of DAICOM data items as the above-described exemplary data. In this way, the rule-based determination method using pre-stored information makes it possible to reliably and easily determine the exemplary data items of image data and tag information.

[0025] The determination unit 22 may determine the plurality of exemplary data using, for example, a learning model stored in the storage unit 25. In this case, the storage unit 25 stores, for example, a learning model generated by associating and learning a plurality of DICOM data sets including image data and tag information with symptoms. The learning model may be generated by associating and learning the exemplary data sets of image data and tag information with symptoms, or may be generated by associating and learning the exemplary data sets of either image data or tag information with symptoms. The learning model may be generated by training, for example, using a graph neural network (GNN) or the like, to approximate the relationship between the pieces of information learned in association with each other. The determination unit 22 inputs the symptoms indicated in the information on the patient's symptoms received by the receiving unit 21 into the learning model, thereby identifying the plurality of DICOM data sets corresponding to the patient's symptoms, and designating the image data and tag information included in the plurality of DICOM data sets as exemplary data. In this way, the vector search-based determination method using the learning model can efficiently determine exemplary data associated with symptoms. For example, if the symptom of a patient received by the receiving unit 21 is "lung cancer," all example data such as tag information within a predetermined distance from the node for "lung cancer" will be efficiently selected.

[0026] The determination unit 22 may, for example, determine output conditions for the DAICOM data based on information regarding the purpose of the DICOM data received by the reception unit 21, and determine the output conditions as information regarding the generation of the DICOM data (more specifically, information used to generate the prompt). For example, when the purpose is "for clinical trials" and the number of data items is specified, the determination unit 22 may determine the number of DAICOM data to be output. Furthermore, the determination unit 22 may determine the number of output sheets for each age group using information indicating the number of onsets by age that is pre-stored or obtained by search. For example, when the purpose is "for training," the determination unit 22 may determine images to be used as example images in the prompt based on the difficulty level of training included in the information regarding the training. For example, example images and difficulty levels (e.g., images of cases where misdiagnosis or the like has occurred are rated as "high") may be pre-associated and stored, and when the difficulty level of the training is "high," example images registered as "high" may be selected.

[0027] The generation unit 23 generates a prompt for instructing the generation AI model 31 to generate DICOM data based on the information regarding the generation of DICOM data determined by the determination unit 22 (information used to generate the prompt). The prompt expresses, in text, for example, the command to be executed by the generation AI model 31 (interactive AI model), the task to be executed by the generation AI model 31, the background and context (e.g., role, condition) to be considered by the generation AI model 31, the question to be answered by the generation AI model 31, and the output format of the response information from the generation AI model 31. The prompt may also include input information to be used as the target of the command and task to be executed by the generation AI model 31. Examples of such input information include data files with file names including a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data is data such as document data, table data, and graph data that can be processed by a default application program.

[0028] FIG. 2 is a diagram illustrating an example of a prompt generated by the RAG system 20. The prompt illustrated in FIG. 2 defines a task, a condition, input information, tag example, image example, and output example. The task is information outlining the command content for the generation AI model 31, and is defined as "Generate DICOM data." The condition is information indicating detailed conditions for the task, and is defined as "Process the lung cancer image in the input information with reference to the image example and generate DICOM lung cancer image data. Process the input information with reference to the patient information and tag example, and generate tag information for the DICOM data." The input information is, for example, information accepted by the reception unit 21 and taken into consideration when executing the task. Here, the input information defines patient information (female in her 40s, lung cancer), equipment information (CT), purpose (for training), and lung cancer image. The tag example and image example are example data determined by the determination unit 22. The tag example is example data of tag information, and a case number, patient name, patient ID, date of birth, etc. are associated with each other. The image example is example data of image data and is an image corresponding to the tag example. The output example is information indicating the structure information (image data, required tag specification) of DICOM data that can be specifically output (created).

[0029] The input unit 24 controls the generative AI model 31 based on the prompt generated by the generation unit 23. The input unit 24 inputs the prompt to the generative AI model 31. The generative AI model 31 generates and outputs DAICOM data in response to the input prompt.

[0030] Fig. 3 is a diagram showing an example of image data included in the DICOM data output from the generating AI model 31. In the example shown in Fig. 3, the image data included in the DICOM data output from the generating AI model 31 is an image equivalent to an actual CT image or the like.

[0031] FIG. 4 is a table showing an example of tag information included in the DICOM data output from the generative AI model 31. The tag information shown in FIG. 4(a) associates a tag name, tag number, presence, and description. Examples of tag names include patient name, patient ID, date of birth, gender, other IDs, patient ID (ID within the sequence of other IDs), patient weight, anonymization method, and reproductive information. Note that "presence" is specified as 1, 2, 3, 1C, or 2C, as shown in FIG. 4(b). "1" and "2" indicate required tags, "3" indicates an optional tag, and "1C" and "2C" indicate conditionally required tags.

[0032] Next, the processing executed by the RAG system 20 will be described with reference to Fig. 5. Fig. 5 is a flowchart showing the processing executed by the RAG system 20.

[0033] As shown in FIG. 5, first, the RAG system 20 receives an image generation request including information about DAICOM data from a user via the terminal 10 (step S1).

[0034] Next, in the RAG system 20, information regarding the generation of DAICOM data is determined based on the information regarding the DAICOM data (step S2).

[0035] Next, in the RAG system 20, a prompt for instructing the generation of DAICOM data is generated based on the information regarding the generation of DAICOM data (step S3).

[0036] Finally, in the RAG system 20, the generated prompt is input to the generation AI model 31 (step S4). As a result, the desired DICOM data is generated based on the prompt generated in response to the information about the received desired DICOM data. For example, by inputting case data (patient overview, symptoms, etc.) as a prompt, it is possible to generate DICOM data tailored to the purpose, and it is also possible to automatically generate images and 3D data tailored to the case, as well as unspecified header information (tag information).

[0037] Next, the effects of the RAG system 20 according to this embodiment will be described.

[0038] The RAG system 20 of this embodiment includes a reception unit 21 that receives an image generation request including information about DICOM data, a determination unit 22 that determines information about the generation of DICOM data based on the information about the DICOM data, a generation unit 23 that generates a prompt to instruct the generation of DICOM data based on the information about the generation of DICOM data, and an input unit 24 that inputs (controls) the prompt generated by the generation unit 23 to a generation AI model 31 that generates DICOM data.

[0039] In the RAG system 20 according to this embodiment, information regarding the generation of DICOM data is determined based on information regarding the received DICOM data, and a prompt for instructing the generation of DICOM data is generated based on the information regarding the generation of the DICOM data. With this configuration, the prompt is generated according to the information regarding the received desired DICOM data, and the desired DICOM data is generated by inputting the prompt into the generation AI model 31. Furthermore, with this method, it is not necessary to obtain DICOM data using a data provision service or the like, and DICOM data can be easily obtained. As described above, the RAG system 20 according to this embodiment allows the desired DICOM data to be easily obtained.

[0040] The receiving unit 21 may receive information about a patient as information about DICOM data, thereby making it possible to easily obtain DICOM data corresponding to the information about the patient.

[0041] The receiving unit 21 may receive information about the symptoms of the patient as the information about the patient, thereby making it possible to easily obtain DAICOM data according to the symptoms of the patient.

[0042] The receiving unit 21 may receive information about an image of the patient as the information about the patient. This makes it possible to easily acquire DAICOM data according to the patient's condition, for example, taking into account the examination image.

[0043] The receiving unit 21 may receive information about equipment related to acquiring images of a patient as information about DICOM data. For example, DICOM data according to the patient's condition can be easily acquired, taking into account the imaging equipment, etc.

[0044] The receiving unit 21 may receive information about the use of the DICOM data as information about the DICOM data, which makes it possible to easily acquire appropriate DICOM data depending on the purpose of use, such as whether the data is for clinical trials or training.

[0045] Based on the information about the DICOM data, the determination unit 22 may determine a plurality of example data of image data and tag information included in the DICOM data generated in the generation AI model 31, and determine the plurality of example data as information about the generation of the DICOM data. In this way, by determining the example data of image data and tag information of the DAICOM data that is finally output based on the information about the DICOM data, it is possible to acquire the desired DAICOM data (corresponding to the information about the accepted DICOM data) with higher accuracy.

[0046] The RAG system 20 further includes a storage unit 25 that stores a plurality of DICOM data items, each including image data and tag information, associated with each symptom. The receiving unit 21 receives information about the patient's symptoms as information about the DICOM data. The determining unit 22 may identify a plurality of DICOM data items corresponding to the patient's symptoms based on the plurality of DICOM data items for each symptom stored in the storage unit 25 and the information about the patient's symptoms received by the receiving unit 21, and set the image data and tag information included in the plurality of DICOM data items as example data. In this way, the plurality of DICOM data items corresponding to the symptoms are identified based on pre-stored rules (data in which the symptoms and DICOM data are associated) and example data is determined, thereby making it possible to reliably and easily determine example data items of image data and tag information.

[0047] The RAG system 20 further includes a memory unit 25 that stores a learning model generated by associating and learning symptoms with multiple DICOM data sets including image data and tag information, and the receiving unit 21 receives information about the patient's symptoms as information about the DICOM data, and the determining unit 22 inputs the symptoms indicated in the information about the patient's symptoms into the learning model to identify multiple DICOM data sets corresponding to the patient's symptoms, and the image data and tag information included in the multiple DICOM data sets may be used as example data. In this way, the learning model, which has previously been learned by associating symptoms with DAICOM data sets, is used to identify multiple DAICOM data sets corresponding to the symptoms and determine example data, thereby making it possible to reliably and easily determine example data for image data and tag information.

[0048] The generating device and generating method of the present disclosure have the following configuration.

[0049] [1] a reception unit that receives an image generation request including information about DICOM data; a determination unit that determines information regarding generation of DICOM data based on information regarding the DICOM data; a generation unit that generates a prompt for instructing generation of DICOM data based on the information regarding generation of the DICOM data; a control unit that controls a generation AI model that generates DICOM data based on the prompt generated by the generation unit; A generating device comprising:

[0050] [2] The generating device according to [1], wherein the receiving unit receives information about a patient as information about the DICOM data.

[0051] [3] The generating device according to [2], wherein the receiving unit receives information about the patient's symptoms as the information about the patient.

[0052] [4] The generating device according to [2] or [3], wherein the receiving unit receives information about an image of the patient as the information about the patient.

[0053] [5] The generating device according to any one of [1] to [4], wherein the receiving unit receives information about equipment related to image acquisition of a patient as information about the DICOM data.

[0054] [6] The generating device according to any one of [1] to [5], wherein the receiving unit receives information about a use of the DICOM data as the information about the DICOM data.

[0055] [7] The generating device according to any one of [1] to [6], wherein the determination unit determines a plurality of example data of image data and tag information to be included in the DICOM data generated in the generating AI model based on information about the DICOM data, and determines the plurality of example data as information related to the generation of the DICOM data.

[0056] [8] The generating device described in [7] further comprises a storage unit for storing multiple DICOM data including image data or tag information associated with each symptom.

[0057] [9] the storage unit stores a plurality of DICOM data including the image data and the tag information; the receiving unit receives information about a patient's symptoms as information about the DICOM data; The determination unit identifies multiple DICOM data corresponding to the patient's symptoms based on multiple DICOM data for each symptom stored in the memory unit and information about the patient's symptoms received by the reception unit, and sets the image data and tag information contained in the multiple DICOM data as the example data. [8] A generation device described in

[0058]

[10] The present invention further includes a storage unit that stores a learning model generated by associating and learning symptoms with a plurality of DICOM data including image data and tag information, the receiving unit receives information about a patient's symptoms as information about the DICOM data; The determination unit inputs symptoms indicated in the information regarding the patient's symptoms into the learning model, thereby identifying multiple DICOM data corresponding to the patient's symptoms, and sets the image data and tag information contained in the multiple DICOM data as the example data.

[0059]

[11] 1. A method for generating a prompt by a generating device, comprising: receiving an image generation request including information about the DICOM data; determining information related to generation of the DICOM data based on the information related to the DICOM data; generating a prompt for instructing generation of DICOM data based on the information regarding generation of the DICOM data; and controlling a generative AI model that generates the DICOM data based on the generated prompt.

[0060] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are connected directly or indirectly (for example, by wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0061] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, election, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocation, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0062] For example, the RAG system 20 constituting the DICOM data generation system according to an embodiment of the present disclosure may function as a computer that performs processing of the control method of the present disclosure. FIG. 6 is a diagram illustrating an example of the hardware configuration of the RAG system 20 according to this embodiment. The RAG system 20 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage device 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like. Note that the RAG system 20 may be configured as a computer device including at least one processor such as a CPU or a GPU, or may be configured as a computer device including multiple processors or may be configured to include multiple computer devices. The terminal 10 and the server device 30 may also have a similar hardware configuration.

[0063] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the RAG system 20 may be configured to include one or more of the apparatuses shown in the figure, or may be configured to exclude some of the apparatuses.

[0064] Each function in the RAG system 20 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0065] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned reception unit 21, determination unit 22, generation unit 23, input unit 24, etc. may be realized by the processor 1001.

[0066] The processor 1001 also loads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with the programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the reception unit 21, the determination unit 22, the generation unit 23, and the input unit 24 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be made for other functional blocks. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0067] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a control method according to an embodiment of the present disclosure.

[0068] Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0069] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the above-mentioned reception unit 21, input unit 24, etc. may be realized by the communication device 1004.

[0070] The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (for example, a touch panel).

[0071] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0072] Furthermore, RAG system 20 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, processor 1001 may be implemented using at least one of these pieces of hardware.

[0073] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI), Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB), System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0074] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0075] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0076] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0077] Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched depending on the implementation. Furthermore, notification of predetermined information (e.g., notification that "X is true") is not limited to being done explicitly, but may be done implicitly (e.g., by not notifying the predetermined information).

[0078] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure may be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure, as defined by the appended claims. Therefore, the description of the present disclosure is for illustrative purposes only and is not intended to be limiting of the present disclosure. For example, while the terminal 10, the RAG system 20, and the server device 30 (devices that store the generative AI model 31) have been described, these configurations (functions) may be implemented entirely in the terminal 10, entirely in a cloud device, or in one or more other terminals and devices. Furthermore, the functions of the RAG system 20 and the functions of the generative AI model 31 may be implemented in the same device or in different devices.

[0079] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0080] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), these wired and / or wireless technologies are included within the definition of transmission media.

[0081] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0082] Note that terms explained in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0083] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0084] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0085] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," etc. may be used interchangeably.

[0086] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0087] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0088] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0089] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0090] Any reference to an element using a designation such as "first," "second," etc., used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0091] When used in this disclosure, the terms "include," "including," and variations thereof are intended to be inclusive, similar to the term "comprising." Furthermore, when used in this disclosure, the term "or" is not intended to be an exclusive or.

[0092] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0093] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different." [Explanation of symbols]

[0094] 21...reception unit, 22...decision unit, 23...generation unit, 24...input unit (control unit), 31...generative AI model.

Claims

1. a reception unit that receives an image generation request including information related to DICOM data; a determination unit that determines information related to generation of DICOM data based on the information related to the DICOM data; a generating unit that generates a prompt for instructing generation of DICOM data based on the information related to the generation of the DICOM data; A control unit controls a generated AI model that generates DICOM data based on the prompt generated by the generation unit; A generating device comprising:

2. The generating device according to claim 1 , wherein the receiving unit receives information about a patient as the information about the DICOM data.

3. The generating device according to claim 2 , wherein the receiving unit receives information about symptoms of the patient as the information about the patient.

4. The generating device according to claim 2 , wherein the receiving unit receives information about an image of the patient as the information about the patient.

5. The generating device according to claim 1 , wherein the receiving unit receives information about equipment related to image acquisition of a patient as the information about the DICOM data.

6. The generating device according to claim 1 , wherein the receiving unit receives information about a use of the DICOM data as the information about the DICOM data.

7. The generating device of claim 1, wherein the determination unit determines a plurality of example data of image data and tag information to be included in the DICOM data generated in the generating AI model based on information regarding the DICOM data, and determines the plurality of example data as information regarding the generation of the DICOM data.

8. The generating device according to claim 7 , further comprising a storage unit that stores a plurality of DICOM data items including image data or tag information associated with each symptom.

9. the storage unit stores a plurality of DICOM data including the image data and the tag information; the receiving unit receives information about a symptom of a patient as information about the DICOM data; The generating device according to claim 8, wherein the determining unit identifies a plurality of DICOM data corresponding to the patient's symptoms based on a plurality of DICOM data for each symptom stored in the memory unit and information regarding the patient's symptoms received by the receiving unit, and sets the image data and tag information contained in the plurality of DICOM data as the example data.

10. The present invention further includes a storage unit that stores a learning model generated by associating and learning a symptom with a plurality of DICOM data including image data and tag information, the receiving unit receives information about a symptom of a patient as information about the DICOM data; The generating device according to claim 7, wherein the determining unit inputs symptoms indicated in the information regarding the patient's symptoms into the learning model to identify multiple DICOM data corresponding to the patient's symptoms, and sets the image data and tag information contained in the multiple DICOM data as the example data.

11. 1. A method for generating a prompt by a generating device, comprising: receiving an image generation request including information regarding the DICOM data; determining information related to generation of DICOM data based on the information related to the DICOM data; generating a prompt for instructing generation of DICOM data based on the information regarding generation of the DICOM data; and controlling a generating AI model that generates the DICOM data based on the generated prompt.

Images