Method for analyzing medical image by generating different type of medical image, and electronic device for performing same

Abstract

A method for analyzing a medical image by generating a different type of medical image by an electronic device according to an embodiment of the present application comprises the steps of: acquiring a first type of medical image; generating a second type of medical image by inputting the first type of medical image into a first artificial intelligence model; and calculating a first joint state indicator by inputting the second type of medical image into a second artificial intelligence model.

Description

Method for analyzing medical images by generating different types of medical images and electronic device for performing the same

[0001] The present application relates to a method for generating different types of medical images and analyzing medical images, and to an electronic device for performing the same.

[0002] Because joint space typically narrows when cartilage is damaged, joint space is an important indicator in diagnosing arthritis. In particular, the degree to which joint space narrows compared to normal is used as a key indicator in assessing the severity of osteoarthritis.

[0003] Accordingly, the presence and severity of osteoarthritis can be determined by taking an X-ray image of the area suspected of having arthritis and measuring the joint space through the X-ray image.

[0004] However, when the joint boundaries are unclear due to factors such as the method of imaging, it is difficult to accurately measure the joint space. In such cases, even with identical X-ray images, there can be differences in diagnosis between medical professionals, making accurate diagnosis difficult. Furthermore, it is difficult to identify the progression of the disease and consistent changes during follow-up.

[0005] In the case of standing extended view radiography (AP) of the knee, there are many cases where the joint surface appears tilted, making it difficult to clearly determine the joint space and the reproducibility is poor for each shot, according to research results.

[0006] In contrast, there are research results showing that in flexion view radiography (PA), which is taken from the back with the knee slightly bent, the joint space is clearly distinguished and has higher reproducibility than in standing anteroposterior radiography.

[0007] However, hospitals often only take standing AP X-rays, which limits their ability to accurately assess a patient's arthritis condition. Therefore, there is a need for methods to improve the accuracy of disease diagnosis using standing AP X-rays.

[0008] The problem to be solved by the present invention is to provide a method for generating different types of medical images and analyzing medical images, and an electronic device for performing the same.

[0009] The problems to be solved by the present invention are not limited to the problems described above, and problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the present invention pertains from this specification and the attached drawings.

[0010] A method for analyzing a medical image by generating a different type of medical image by an electronic device according to one embodiment of the present invention may include the steps of acquiring a first type of medical image, inputting the first type of medical image into a first artificial intelligence model to generate a second type of medical image, and inputting the second type of medical image into a second artificial intelligence model to calculate a first joint condition index.

[0011] An electronic device for analyzing a medical image according to an embodiment of the present invention includes a communication unit for acquiring a first medical image, a processor, and a memory, wherein the processor may include a medical image generation unit for generating a second type of medical image from the first type of medical image, a first joint state calculation unit for calculating a first joint state index indicating a state of a joint from the second type of medical image, a first joint state calculation unit for calculating a first joint state index indicating a state of a joint from the first type of medical image, and a joint state analysis unit for analyzing a joint state based on the first joint state index and the second joint state index.

[0012] The solutions to the problems of the present invention are not limited to the solutions described above, and solutions that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention pertains from this specification and the attached drawings.

[0013] According to one embodiment of the present invention, a method for generating different types of medical images and analyzing medical images and an electronic device for performing the same can be provided.

[0014] In addition, according to one embodiment of the present invention, it is possible to analyze the knee joint condition by taking into account the knee flexion X-ray image even by taking only the knee standing X-ray image.

[0015] FIG. 1 is a block diagram briefly showing the configuration of an electronic device according to one embodiment of the present application.

[0016] FIG. 2 is a drawing for explaining various operations of an electronic device according to one embodiment of the present application.

[0017] FIG. 3 is a drawing for explaining an artificial intelligence model of an electronic device according to one embodiment of the present application.

[0018] FIG. 4 is a flowchart illustrating a method for generating another type of medical image and analyzing the medical image according to one embodiment of the present application.

[0019] FIG. 5 is a diagram illustrating a method for generating another type of medical image and determining a joint gap according to one embodiment of the present application.

[0020] FIG. 6 is a diagram illustrating a method for generating another type of medical image and determining a joint gap according to one embodiment of the present application.

[0021] FIG. 7 is a diagram illustrating a method for generating another type of medical image and determining a joint gap according to one embodiment of the present application.

[0022] FIG. 8 is a drawing for explaining a method for displaying joint state analysis results according to one embodiment of the present application.

[0023] FIG. 9 is a drawing for explaining a method for displaying joint state analysis results according to one embodiment of the present application.

[0024] The above-described purposes, features, and advantages of the present application will become more apparent through the following detailed description, taken in conjunction with the accompanying drawings. However, as the present application is susceptible to various modifications and various embodiments, specific embodiments will be illustrated in the drawings and described in detail below.

[0025] Throughout the specification, identical reference numbers, in principle, indicate identical components. Furthermore, components with identical functions within the scope of the same concept shown in the drawings of each embodiment are described using the same reference numbers, and redundant descriptions thereof will be omitted.

[0026] If a detailed description of a known function or configuration related to this application is deemed to unnecessarily obscure the gist of this application, such detailed description will be omitted. Furthermore, numbers (e.g., "first," "second," etc.) used throughout the description of this specification are merely identifiers used to distinguish one component from another.

[0027] In addition, the suffixes "module" and "part" for components used in the following examples are given or used interchangeably only for the convenience of writing the specification, and do not have distinct meanings or roles in themselves.

[0028] In the examples below, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0029] In the examples below, terms such as “include” or “have” mean that a feature or component described in the specification is present, and do not preclude the possibility that one or more other features or components may be added.

[0030] For convenience of explanation, the sizes of components in the drawings may be exaggerated or reduced. For example, the sizes and thicknesses of each component shown in the drawings are arbitrarily shown for convenience of explanation, and the present invention is not necessarily limited to what is shown.

[0031] In some embodiments, where implementations are otherwise feasible, the order of specific processes may differ from the order described. For example, two processes described in succession may be performed substantially simultaneously, or in a reverse order from the order described.

[0032] In the following examples, when components are said to be connected, this includes not only cases where the components are directly connected, but also cases where components are interposed between the components and are indirectly connected.

[0033] For example, when it is said in this specification that components, etc. are electrically connected, it includes not only cases where the components, etc. are directly electrically connected, but also cases where components, etc. are interposed in between and are indirectly electrically connected.

[0034] The present invention is applicable to a wide range of fields. While this specification focuses on a method for analyzing the condition of the knee joint, the present invention is not limited to any specific body part and can be utilized in various medical analyses for joint analysis.

[0035] The AI ​​model according to the present invention may be a generative model among machine learning models. Furthermore, these models can be trained using acquired data. Furthermore, the division of AI models in the present invention is merely intended to enhance understanding of the invention; in reality, there may be one or more models.

[0036]

[0037] Hereinafter, with reference to FIGS. 1 to 9, a method for generating and analyzing another type of medical image of the present application and an electronic device for performing the same will be described. In this specification, it will be assumed and described that the medical image is an X-ray image of the knee joint taken using an X-ray device. In addition, the knee image may be all or part of a standing extended view radiography (AP) taken from the front to the back of the body with the subject standing upright, or a flexion view radiography (PA) taken from the back to the front of the body with the subject bending the knee. The flexion view radiography may be taken by the Rosenberg method in which the knee is bent at 45 degrees and the front of the knee is placed on the camera stand, or by the fixed flexion method in which the thigh is placed on the camera stand and the shin is bent and taken. However, this is merely an example for the convenience of explanation and is not to be construed as limiting thereto. Accordingly, the embodiments described below may also be applied analogically to medical images other than X-ray images of the knee (e.g., CT images).

[0038]

[0039] FIG. 1 is a block diagram briefly showing the configuration of an electronic device according to one embodiment of the present application. The electronic device (100) according to one embodiment of the present application receives a knee standing image, inputs the knee standing image into a learned medical image generation model to generate a knee flexion image, inputs the generated knee flexion image into a learned first joint state analysis model to detect a knee joint area, calculates a first knee joint interval included in the detected knee joint area, inputs the knee standing image into a learned second joint state analysis model to detect a knee joint area, calculates a second knee joint interval included in the detected knee joint area, and analyzes the knee joint state based on the first knee joint interval and the second knee joint interval.

[0040]

[0041] Referring to FIG. 1, an electronic device (100) may include a communication unit (100), a processor (120), and a memory (130).

[0042]

[0043] The communication unit (110) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., a radiographic imaging (X-ray) photographing device), and the performance of communication through the established communication channel. The communication unit (110) may include one or more communication processors that operate independently from the processor (120) (e.g., an application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication unit (110) may include a wireless communication module (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device via a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA), or a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or a WAN). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can use subscriber information (e.g., international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196) to verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199).

[0044]

[0045] The processor (120) may execute software to control at least one other component (e.g., hardware or software component) of the electronic device (100) and perform various data processing or calculations. According to one embodiment, as at least a part of the data processing or calculation, the processor (120) may store a command or data received from another component (e.g., the communication unit (110)) in a volatile memory, process the command or data stored in the volatile memory, and store the resulting data in a non-volatile memory. According to one embodiment, the processor (120) may include a main processor (e.g., a central processing unit or an application processor) or an auxiliary processor (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently therefrom.

[0046] According to one embodiment, the auxiliary processor (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. Such learning may be performed, for example, within the electronic device (100) itself where the artificial intelligence is performed, or may be performed through a separate server (e.g., an external server). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include multiple artificial neural network layers. The artificial neural network may be one of a generative adversarial network (GAN), a Diffusion model, a Vision Transformer series model, a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to or as an alternative to a hardware structure, the artificial intelligence model may also include a software structure.

[0047] The processor (120) can control the overall operation of the electronic device (100). For example, the processor (120) can control an operation of receiving a knee standing image, an operation of inputting the knee standing image into a learned medical image generation model to generate a knee flexion image, an operation of inputting the generated knee flexion image into a learned first joint state analysis model to detect a knee joint area and calculate a first knee joint interval included in the detected knee joint area, an operation of inputting the knee standing image into a learned second joint state analysis model to detect a knee joint area and calculate a second knee joint interval included in the detected knee joint area, and an operation of analyzing a knee joint state based on the first knee observation interval and the second knee joint interval.

[0048]

[0049] The memory (130) can store various data used by at least one component (e.g., the processor (120)) of the electronic device (100). The data may include, for example, input data or output data for software and commands related thereto. The memory (130) may include volatile memory or non-volatile memory. The memory (130) may be provided in a form built into the electronic device (100) or in a form that is detachable.

[0050]

[0051] FIG. 2 is a diagram for explaining various operations of an electronic device according to an embodiment of the present application. Referring to FIG. 2, the electronic device (100) may include a medical image input unit (210), a preprocessing unit (220), a medical image generation unit (230), a first joint state calculation unit (240), a second joint state calculation unit (250), a joint state analysis unit (260), and an analysis information output unit (270).

[0052]

[0053] The medical image input unit (210) can receive a knee X-ray image from an external device. For example, the medical image input unit (210) can receive an X-ray image including a knee joint photographed by an X-ray photographing device. In this case, the knee X-ray image may be a knee standing X-ray image photographed from the front to the back of the body while the subject is standing upright.

[0054]

[0055] The preprocessing unit (220) may perform preprocessing of medical images for image analysis, which will be described later. For example, the preprocessing unit (220) may automatically detect the knee joint region in the medical image. Furthermore, the preprocessing unit (220) may be implemented to perform an operation for correcting the intensity of the medical image. Furthermore, the preprocessing unit (220) may perform an operation for removing noise from the medical image, normalizing it, or aligning it.

[0056]

[0057] The medical image generation unit (230) can input medical images into an artificial intelligence model (medical image generation model) to generate different types of medical images. Specifically, the medical image generation unit (230) can input knee X-ray images into the artificial intelligence model to generate knee X-ray images taken from different angles.

[0058] For example, the medical image generation unit (230) can generate a knee flexion X-ray image from a knee standing X-ray image using an artificial intelligence model (e.g., a Diffusion model or a Generative Adversarial Network (GAN)). Specifically, the medical image generation unit (230) (or any external device) can generate a noisy image by gradually adding noise to the knee X-ray image in the inference step (forward process). Then, the medical image generation unit (230) can train a diffusion model by going through a process of restoring the original knee X-ray image by removing noise from the noisy image step by step in the generation step (reverse process). Specifically, the medical image generation unit (230) can train a diffusion model to generate a knee flexion X-ray image by adding a knee standing X-ray image to the input of the generation step and removing noise.

[0059]

[0060] The first joint state calculation unit (240) can input the knee flexion X-ray image generated by the medical image generation unit (230) into an artificial intelligence model (first joint state analysis model) to analyze the first joint state. Specifically, the first joint state calculation unit (240) can input the knee flexion X-ray image into the artificial intelligence model to determine the knee joint gap area included in the knee flexion X-ray image. In addition, the first joint state calculation unit (240) can calculate the knee joint gap based on the knee joint gap area. The first joint state calculation unit (240) can calculate the first joint state index by determining the rate of decrease in the joint gap and the arthritis grade compared to the normal group based on the calculated knee joint gap. Additionally, the first joint state calculation unit (240) can also analyze an index related to an osteophyte or disease included in the knee flexion X-ray image.

[0061] For example, the first joint state calculation unit (240) can segment and detect a knee joint gap area included in a knee flexion X-ray image using an artificial intelligence model (e.g., a segmentation model). Specifically, the first joint state calculation unit (240) (or any external device) can train a segmentation model based on a knee flexion X-ray image and a label assigned as a knee joint gap area to the knee joint gap area. At this time, the label can be automatically assigned to the knee X-ray image using any software or manually assigned to the knee X-ray image by any operator. More specifically, the first joint state calculation unit (240) can receive a knee flexion X-ray image and be trained so that the difference between the output value and the label related to the knee joint gap area is minimized. Here, the knee flexion X-ray image can be an image in which only the knee joint area is detected from a knee standing X-ray image processed by the preprocessing unit (220).

[0062]

[0063] The second joint status calculation unit (250) can input the knee standing X-ray image into an artificial intelligence model (second joint status analysis model) to analyze the second joint status. Specifically, the second joint status calculation unit (250) can input the knee standing X-ray image into the artificial intelligence model to determine the knee joint gap area included in the knee standing X-ray image. In addition, the second joint status calculation unit (250) can calculate the knee joint gap based on the knee joint gap area. The second joint status calculation unit (250) can calculate the second joint status index by determining the rate of decrease in the joint gap and the arthritis grade compared to the normal group based on the calculated knee joint gap. Additionally, the second joint status calculation unit (250) can also analyze an index related to osteophytes or diseases included in the knee standing X-ray image.

[0064] For example, the second joint state calculation unit (250) can segment and detect a knee joint gap area included in a knee standing X-ray image using an artificial intelligence model (e.g., a segmentation model). Specifically, the second joint state calculation unit (250) (or any external device) can train a segmentation model based on a knee standing X-ray image and a label assigned as a knee joint gap area to the knee joint gap area. At this time, the label can be automatically assigned to the knee X-ray image using any software or manually assigned to the knee X-ray image by any operator. More specifically, the second joint state calculation unit (250) can receive a knee standing X-ray image and be trained to minimize the difference between the output value and the label related to the knee joint gap area. Here, the knee standing X-ray image can be an image in which only the knee joint area is detected from a knee standing X-ray image processed by the preprocessing unit (220).

[0065]

[0066] The joint condition analysis unit (260) can analyze the joint condition based on the first joint condition index and the second joint condition index. Specifically, the joint condition analysis unit (260) can compare the first knee joint gap area detected in the knee flexion X-ray image with the second knee joint gap area detected in the knee standing X-ray image. In addition, the joint condition analysis unit (260) determines the integrated knee joint gap area by considering the weight for the first knee joint gap area and the weight for the second knee joint gap area, thereby calculating the knee joint gap, thereby determining the rate of decrease in the joint gap and the arthritis grade compared to the normal group.

[0067]

[0068] The analysis information output unit (270) can display a knee flexion X-ray image with the knee joint gap area indicated and a knee standing X-ray image with the knee joint gap area indicated. Alternatively, the analysis information output unit (270) can also output the results of comparing the joint status analyzed in the knee flexion X-ray image with the joint status analyzed in the knee standing X-ray image.

[0069]

[0070] FIG. 3 is a diagram illustrating an artificial intelligence model of an electronic device according to an embodiment of the present application. Referring to FIG. 3, the electronic device (100) can generate a flexed knee image from a standing knee image using an image generation model. Meanwhile, although not illustrated in FIG. 3, the electronic device (100) can detect a knee joint region from a standing knee image using a knee joint region detection model and input the detected knee joint region into a medical image generation model. In addition, the electronic device (100) can calculate a first joint state index from a flexed knee image using a first joint state analysis model. In addition, the electronic device (100) can calculate a second joint state index from a standing knee image using a second joint state analysis model. In addition, the electronic device (100) can generate integrated joint state information based on the first joint state index and the second joint state index using an integrated analysis model. In the present invention, the division into a medical image generation model, a first joint state analysis model, a second joint state analysis model, and an integrated analysis model is merely done to enhance understanding of the present invention, and each model may actually be one model or multiple models.

[0071]

[0072] FIG. 4 is a flowchart illustrating a method for generating and analyzing another type of medical image according to one embodiment of the present application. The operations in FIG. 4 are not limited in order, and additional operations may be performed between two adjacent operations. Furthermore, at least some of the operations in FIG. 4 may be omitted. In the present invention, the expression that the electronic device (100) performs a specific operation may mean that the processor (120) of the electronic device (100) performs the specific operation, or that the processor (120) controls other hardware to perform the specific operation.

[0073] FIG. 4 is described in more detail with reference to FIGS. 5 to 9. FIG. 5 is a diagram for explaining a method for generating another type of medical image and determining a joint gap according to an embodiment of the present application. FIG. 6 is a diagram for explaining a method for generating another type of medical image and determining a joint gap according to an embodiment of the present application. FIG. 7 is a diagram for explaining a method for generating another type of medical image and determining a joint gap according to an embodiment of the present application. FIG. 8 is a diagram for explaining a method for displaying a joint state analysis result according to an embodiment of the present application. FIG. 9 is a diagram for explaining a method for displaying a joint state analysis result according to an embodiment of the present application.

[0074]

[0075] Referring to FIG. 4, the electronic device (100) can acquire a first type of medical image (S1000). Specifically, the electronic device (100) can acquire a knee X-ray image captured by an X-ray photographing device. For example, the first type may refer to a knee standing X-ray image captured from the front to the back of the body while the subject is standing upright. In addition, the electronic device (100) can detect a knee joint region in the knee standing X-ray image. In the present specification, acquiring a first type of medical image may refer to detecting a knee joint region in the knee standing X-ray image to acquire a knee joint region image. For example, as shown in FIGS. 5(a), 6(a), and 7(a), the electronic device (100) can receive a knee standing X-ray image and detect a knee joint region, thereby acquiring a first type of medical image.

[0076]

[0077] The electronic device (100) can input a first type of medical image into a first artificial intelligence model to generate a second medical image (S2000). Specifically, the electronic device (100) can input a knee standing X-ray image into a Diffusion model or a Generative Adversarial Network (GAN) to generate a knee flexion X-ray image. For example, the electronic device (100) can generate a knee flexion X-ray image as shown in FIGS. 5(b), 6(b), and 7(b) from the knee standing X-ray image. Referring to FIGS. 5(a) and 5(b), in the knee standing X-ray image (FIG. 5(a)), the joint boundary of the lower right (medial) side (tibia, shinbone) is ambiguous, and the posterior joint surface is obliquely viewed upward, so that the joint space between the upper and lower bones is not clear. However, in the knee flexion X-ray image (FIG. 5(b)), the joint space may be clear. Also, referring to Fig. 6(a) and Fig. 6(b), in the standing knee X-ray image (Fig. 6(a)), the joint borders of the lower ends (tibia, tibia) on the right (medial) and left (lateral) sides are ambiguous, and the posterior joint surface appears obliquely upward, making the joint space between the upper and lower bones unclear. However, in the flexed knee X-ray image (Fig. 6(b)), the joint borders of the lower ends (tibia, tibia) on the left (medial) side are ambiguous, and the posterior joint surface appears obliquely upward, making the joint space between the upper and lower bones unclear. However, in the flexed knee X-ray image (Fig. 7(b)), the joint borders of the lower ends (tibia, tibia) on the left (medial) side are ambiguous, and the posterior joint surface appears obliquely upward, making the joint space between the upper and lower bones unclear. However, in the flexed knee X-ray image (Fig. 7(b)), the joint space may be clear. In this way, knee flexion X-ray images such as those in Fig. 5(b), Fig. 6(b), and Fig. 7(b) can be generated using the knee standing X-ray images, thereby clearly providing the user with the knee joint area.

[0078]

[0079] The electronic device (100) can input a second type of medical image into a second artificial intelligence model to calculate a first joint condition index (S3000). Specifically, the electronic device (100) can detect a knee joint gap area from the second type of medical image based on the second artificial intelligence model (e.g., segmentation model) and calculate a first knee joint gap included in the knee joint gap area. For example, the electronic device (100) can calculate the knee joint gap of the second type of medical image as shown in FIGS. 5(c), 6(c), and 7(c). In addition, the electronic device (100) can determine a rate of decrease in the joint gap and an arthritis grade compared to a normal group based on the calculated knee joint gap to calculate the first joint condition index.

[0080]

[0081] The electronic device (100) can input a first type of medical image into a third artificial intelligence model to calculate a second joint condition index (S4000). Specifically, the electronic device (100) can detect a knee joint gap area from the first type of medical image based on the third artificial intelligence model (e.g., segmentation model) and calculate a second knee joint gap included in the knee joint gap area. Then, the electronic device (100) can calculate a second joint condition index by determining a rate of decrease in the joint gap and an arthritis grade compared to a normal group based on the calculated knee joint gap.

[0082]

[0083] The electronic device (100) can analyze the joint condition based on the first joint condition index and the second joint condition index (S5000). Specifically, the electronic device (100) can compare the first knee joint gap area detected in the second type of medical image with the second knee joint gap area detected in the first type of medical image. Then, the electronic device (100) can determine the integrated knee joint gap area by considering the weight for the first knee joint gap area and the weight for the second knee joint gap area. Alternatively, the electronic device (100) can also guarantee the first joint condition index based on the second joint condition index. That is, the electronic device (100) can calculate the knee joint gap by considering the first joint condition index and the second joint condition index, thereby determining the rate of decrease in the joint gap and the arthritis grade compared to the normal group.

[0084]

[0085] In addition, the electronic device (100) can output integrated joint status information. Specifically, the electronic device (100) can display a second type of medical image and a first type of medical image, each of which indicates a knee joint gap, or both. In addition, the electronic device (100) can output a result of comparing the joint status analyzed in the second type of medical image with the joint status analyzed in the first type of medical image. In addition, the electronic device (100) can output integrated joint status information, as shown in FIGS. 8 and 9 . For example, the electronic device (100) can display the KL grade of the right knee and the likelihood of the KL grade of the left knee. In addition, the electronic device (100) can display a knee joint gap area and a knee joint gap on a knee X-ray image and display and output an osteophyte or disease area.

[0086]

[0087] According to a method for analyzing a medical image by generating a medical image from a different angle according to an embodiment of the present invention and an electronic device for performing the same, there is an advantage in that a knee joint condition can be analyzed by taking only a knee standing X-ray image and considering a knee flexion X-ray image.

[0088]

[0089] The features, structures, effects, etc. described in the embodiments above are included in at least one embodiment of the present invention, and are not necessarily limited to just one embodiment. Furthermore, the features, structures, effects, etc. exemplified in each embodiment can be combined or modified in other embodiments by those skilled in the art to which the embodiments pertain. Therefore, the contents related to such combinations and modifications should be construed as falling within the scope of the present invention.

[0090] In addition, although the above description focuses on the embodiments, these are merely examples and do not limit the present invention. Those skilled in the art to which the present invention pertains will appreciate that various modifications and applications not exemplified above are possible without departing from the essential characteristics of the present embodiments. In other words, each component specifically shown in the embodiments can be modified and implemented. In addition, differences related to such modifications and applications should be interpreted as being included within the scope of the present invention defined in the appended claims.

Claims

1. A method for analyzing medical images by generating different types of medical images using an electronic device, Step of acquiring a first type of medical image; A step of inputting the first type of medical image into the first artificial intelligence model to generate a second type of medical image; A step of inputting the second type of medical image into the second artificial intelligence model to produce a first joint condition index; Medical image analysis method.

2. In paragraph 1, A step of inputting the first type of medical image into a third artificial intelligence model to produce a second joint condition index; Medical image analysis method.

3. In paragraph 2, A step of analyzing a joint condition based on the first joint condition indicator and the second joint condition indicator; further comprising; Medical image analysis method.

4. In paragraph 3, The step of analyzing the joint condition based on the first joint condition indicator and the second joint condition indicator is: A step of correcting the first joint condition indicator based on the second joint condition indicator; Medical image analysis method.

5. In paragraph 2, A step of displaying together a second type of medical image in which the first joint condition indicator is displayed and a first type of medical image in which the second joint condition indicator is displayed; further comprising; Medical image analysis method.

6. In paragraph 2, The first type of medical image is a standing extended view radiography, and the second type of medical image is a flexion view radiography. Medical image analysis method.

7. In paragraph 6, The step of acquiring the first type of medical image comprises: The step of obtaining the above knee standing X-ray image; and A step of detecting a knee joint area in the above knee standing X-ray image; Medical image analysis method.

8. In paragraph 7, The step of inputting the second type of medical image into the second artificial intelligence model and calculating the first joint condition index is Detecting a knee joint gap area from the second type of medical image based on the second artificial intelligence model, and calculating a first knee joint gap included in the knee joint gap area. Medical image analysis method.

9. In paragraph 7, The step of inputting the first type of medical image into the third artificial intelligence model and calculating the second joint condition index is Detecting a knee joint gap area from the first type of medical image based on the third artificial intelligence model and calculating a second knee joint gap included in the knee joint gap area. Medical image analysis method.

10. In paragraph 1, The above first artificial intelligence model is a diffusion model or a generative adversarial network (GAN) generative model that is trained to receive a knee standing X-ray image and output a knee flexion X-ray image. Medical image analysis method.

11. A computer-readable recording medium having recorded thereon a program for executing a method according to any one of claims 1 to 9 on a computer.

12. In an electronic device for analyzing medical images, Communication unit for acquiring first medical images; processor; and memory; including; The above processor, A medical image generation unit for generating a second type of medical image from the first type of medical image; A first joint condition calculation unit for calculating a first joint condition index indicating a condition of a joint from the second type of medical image; A first joint condition calculation unit for calculating a first joint condition index representing the condition of the joint from the first type of medical image; and A joint condition analysis unit that analyzes a joint condition based on the first joint condition indicator and the second joint condition indicator; Electronic devices.

Images