KR102177567B1 - Method for generating bone image and apparatus using the same - Google Patents

Abstract

The present disclosure relates to a method for generating a bone image performed by a computing device. The method for generating a bone image performed by a computing device may comprise the steps of: (a) receiving input of target bone age; (b) obtaining a first candidate bone image and a second candidate bone image for generating a bone image corresponding to the target bone age; (c) obtaining a first feature vector and a second feature vector for each of the first candidate bone image and the second candidate bone image based on a pre-learned readout model; (d) synthesizing the first feature vector and the second feature vector to generate a third feature vector corresponding to the target bone age; and (e) generating a target bone image corresponding to the target bone age based on the third feature vector.

Description

Bone image generation method and apparatus using the same {METHOD FOR GENERATING BONE IMAGE AND APPARATUS USING THE SAME}

The present invention relates to a bone image generation method and an apparatus using the same.

In general, various evaluation methods for reading bone age are performed by comparing bone images representing each age.

In the case of using the database-based representative bone image by age, the reading result may be different for each reader for the age that does not exist in the representative bone image or the intermediate age (e.g., 10.4 years, 21.3 years, etc.). have.

In the case of an artificial neural network that extracts a feature vector of an input image and reads a bone age based on this, it may be learned based on prepared training data. In this case, there is a high possibility that performance will deteriorate for ages in which some training data is missing.

An object of the present invention is to provide a means for assisting the reading of the bone image by generating a bone image corresponding to an age that is not in a database using a previously stored bone image.

In addition, an object of the present invention is to provide a reading model learning method capable of improving reading accuracy of a reading model that extracts feature vectors from a bone image.

The characteristic configuration of the present invention for achieving the object of the present invention as described above and realizing the characteristic effects of the present invention described later is as follows.

According to an aspect of the present invention, a method for generating a bone image performed by a computing device includes the steps of: (a) receiving a target bone age; (b) obtaining a first candidate bone image and a second candidate bone image for generating a bone image corresponding to the target bone age; (c) obtaining a first feature vector and a second feature vector for each of the first candidate bone image and the second candidate bone image, based on a pre-learned readout model; (d) synthesizing the first feature vector and the second feature vector to generate a third feature vector corresponding to the target bone age; And (e) generating a target bone image corresponding to the target bone age based on the third feature vector.

According to an embodiment, the pre-learned readout model is pre-trained to output a feature vector of an input bone image based on a processed learning bone image, and the processed learning bone image is obtained from the first learning bone image. By synthesizing the learning bone image and the second learning bone image, the third bone age corresponding to the age between the first bone age corresponding to the first learning bone image and the second bone age corresponding to the second learning bone image It may be generated by generating a third learning goal image corresponding to.

A computing device for generating a bone image according to an aspect includes: a communication unit for receiving an input for a target bone age; And a processor for generating a target bone image corresponding to the target bone age, wherein the processor comprises a first feature vector for each of the first candidate bone image and the second candidate bone image based on a pre-learned read model And obtaining a second feature vector, synthesizing the first feature vector and the second feature vector to generate a third feature vector corresponding to the target bone age, and based on the third feature vector, the target bone age A target goal image corresponding to may be generated.

According to an embodiment of the present invention, accuracy of bone age reading may be improved by additionally providing a bone image corresponding to an age that is not in a database.

In addition, based on an improved learning method using processed learning data, it is possible to provide a remarkable effect of improving the performance of a readout model that is learned to extract a feature vector from a bone image.

According to the present invention, there is a potential effect that it is possible to innovate the workflow in the medical field by ultimately improving the accuracy of diagnosis by medical staff and providing a reference bone image corresponding to an individual age.

In addition, in the present invention, medical images used in hospitals in the prior art can be utilized as they are, and the method of the present invention is of course not dependent on a specific type of image or platform.

The accompanying drawings, which are attached to be used in the description of the embodiments of the present invention, are only some of the embodiments of the present invention, and to those of ordinary skill in the technical field to which the present invention belongs (hereinafter referred to as "common technician") Other drawings may be obtained on the basis of these drawings without efforts to reach the invention.
1 is a conceptual diagram schematically showing an exemplary configuration of a computing device that performs a method for generating a bone image according to the present invention.
2 is an exemplary block diagram showing hardware or software components of a computing device that performs a bone image generation method according to the present invention.
3 is a flowchart illustrating a method of generating a bone image according to an exemplary embodiment.
4 is a diagram illustrating an example of performing a method of generating a bone image according to an exemplary embodiment.
5 is a diagram showing the distribution of feature vectors according to age.
6 is a diagram illustrating an example of an interface to which a method for generating a bone image according to an exemplary embodiment is applied.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The detailed description of the present invention to be described later refers to the accompanying drawings, which illustrate specific embodiments in which the present invention may be practiced in order to clarify the objects, technical solutions, and advantages of the present invention. These embodiments are described in detail enough to enable a person skilled in the art to practice the present invention.

The term "image" or "image data" used throughout the detailed description and claims of the present invention refers to multidimensional data composed of discrete image elements (eg, pixels in a 2D image and voxels in a 3D image). Refers to. For example, "image" refers to an X-ray image, (cone-beam) computed tomography, magnetic resonance imaging (MRI), ultrasound, or any other medical image known in the art. It may be a medical image of a subject, that is, a subject collected by the system. Also, an image may be provided in a non-medical context, such as a remote sensing system, an electron microscopy, and the like.

Throughout the detailed description and claims of the present invention, an'image' refers to an image that can be seen by the eye (e.g., displayed on a video screen) or (e.g., a file corresponding to a pixel output such as a CT, MRI detector). It is a term referring to digital representations.

Throughout the detailed description and claims of the present invention, the'DICOM (Digital Imaging and Communications in Medicine; Medical Digital Imaging and Communication)' standard is a generic term for various standards used for digital image expression and communication in medical devices. Standards are published by a coalition committee formed by the American Radiological Society (ACR) and the American Electrical Industry Association (NEMA).

In addition, throughout the detailed description and claims of the present invention, the term'picture archiving and communication system (PACS)' refers to a system that stores, processes, and transmits according to the DICOM standard, and X-ray, CT , Medical image images acquired using digital medical imaging equipment such as MRI are stored in DICOM format and can be transmitted to terminals inside and outside the hospital through a network, and reading results and medical records can be added to this.

And, throughout the detailed description and claims of the present invention,'learning' or'learning' is a term that refers to performing machine learning through computing according to a procedure. It will be appreciated by those of skill in the art that it is not intended to be referred to.

And throughout the detailed description and claims of the present invention, the word'comprise' and variations thereof are not intended to exclude other technical features, additions, components or steps. In addition,'one' or'one' is used in more than one meaning, and'another' is limited to at least a second or more.

Other objects, advantages, and features of the present invention to those skilled in the art will appear, partly from the present disclosure, and partly from the practice of the present invention. The examples and drawings below are provided by way of example and are not intended to limit the invention. Therefore, the details disclosed in this specification with respect to a specific structure or function are not to be construed in a limiting sense, but only representatives that provide guidance for a person skilled in the art to variously implement the present invention with any detailed structures that are substantially suitable. It should be interpreted as basic data.

Moreover, the present invention covers all possible combinations of the embodiments indicated herein. It should be understood that the various embodiments of the present invention are different from each other, but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be embodied in other embodiments without departing from the spirit and scope of the present invention in relation to one embodiment. In addition, it is to be understood that the location or arrangement of individual components in each disclosed embodiment may be changed without departing from the spirit and scope of the present invention. Accordingly, the detailed description to be described below is not intended to be taken in a limiting sense, and the scope of the present invention, if properly described, is limited only by the appended claims, along with all scopes equivalent to those claimed by the claims. Like reference numerals in the drawings refer to the same or similar functions over several aspects.

Unless otherwise indicated in this specification or clearly contradicting the context, items referred to in the singular encompass the plural unless otherwise required by that context. In addition, in describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the subject matter of the present invention, a detailed description thereof will be omitted.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings in order to allow those skilled in the art to easily implement the present invention.

1 is a conceptual diagram schematically showing an exemplary configuration of a computing device that performs a method for generating a bone image according to the present invention.

Referring to FIG. 1, a computing device 100 according to an embodiment of the present invention includes a communication unit 110 and a processor 120, and is directly or indirectly connected to an external computing device (not shown) through the communication unit 110. Can communicate with enemies.

Specifically, the computing device 100 is a device that may include components of typical computer hardware (eg, computer processor, memory, storage, input device and output device, and other conventional computing devices; routers, switches, etc.) Electronic communication devices; electronic information storage systems such as network-attached storage (NAS) and storage area networks (SANs) and computer software (i.e., allowing computing devices to function in a specific way) Instructions) to achieve the desired system performance.

The communication unit 110 of such a computing device can transmit and receive requests and responses to and from other computing devices to which it is linked. As an example, such requests and responses may be made by the same transmission control protocol (TCP) session. However, the present invention is not limited thereto, and may be transmitted/received as, for example, a user datagram protocol (UDP) datagram. In addition, in a broad sense, the communication unit 110 may include a keyboard, a mouse, other external input devices, printers, displays, and other external output devices for receiving commands or instructions.

In addition, the processor 120 of the computing device may include a micro processing unit (MPU), a central processing unit (CPU), a graphics processing unit (GPU) or a tensile processing unit (TPU), a cache memory, and a data bus. ), and the like. In addition, it may further include an operating system and a software configuration of an application that performs a specific purpose.

In the following description, the image of the present invention targets a bone image, and the bone image targets a bone X-ray image as an example, but the scope of the present invention is not limited thereto, and is applied to all general types of bone images. It will be readily understood by those skilled in the art that this is possible and can be applied in the process of reading the bone age of a target image.

2 is an exemplary block diagram showing hardware or software components of a computing device that performs a bone image generation method according to the present invention.

The individual modules shown in FIG. 2 may be implemented by interlocking, for example, the communication unit 110 or the processor 120 included in the computing device 100, or the communication unit 110 and the processor 120. Will be able to understand.

In a brief overview of the configuration of the method and apparatus according to the present invention with reference to FIG. 2, the computing device 100 may include a target bone age information receiving module 210 as its component. The target bone age information receiving module 210 may receive target bone age information from an input device included in the computing device and an interlocked user terminal.

Based on the target bone age information acquired through the target bone age information receiving module 210, the feature vector obtaining module 220 may acquire a feature vector for generating a bone image corresponding to the target bone age information.

According to an embodiment, the feature vector acquisition module 220 may include a pre-learned reading model to extract a feature vector from an input bone image and read a bone age based thereon. Pre-trained readout models are, for example, DNN (Deep Neural Network), CNN (Convolutional Neural Network), DCNN (Deep Convolution Neural Network), RNN (Recurrent Neural Network), RBM (Restricted Boltzmann Machine), DBN (Deep Belief). Network), SSD (Single Shot Detector), YOLO (You Only Look Once), etc. can be used, it will be understood by those of ordinary skill in the art. The types of artificial neural networks that can be used in the present invention are not limited to the examples presented, and any artificial neural network that can be learned to extract a feature vector from a bone image based on the labeled learning data, and read the bone age based on this. It will be understood by those of ordinary skill in the art that it may include.

The feature vector acquisition module 220 may acquire at least two or more candidate bone images corresponding to the target bone age, and extract a feature vector corresponding to the bone image through a pre-learned readout model. For example, when the target bone age is 4 years old, the feature vector acquisition module acquires a first candidate bone image corresponding to age 3 and a second candidate bone image corresponding to age 5, and obtains a first candidate bone image corresponding to each image. A feature vector and a second feature vector may be extracted.

According to another embodiment, the feature vector obtaining module 220 may obtain a first feature vector and a second feature vector corresponding to a target bone age from among feature vectors that have been databased. According to an embodiment, a feature vector corresponding to each age may be databaseized, and when the target age is 4 years, the feature vector acquisition module 220 includes a feature vector corresponding to 3 years old and a feature vector corresponding to 5 years old. Can be obtained from the database.

The synthesis module 230 may generate a third feature vector corresponding to a target age by synthesizing the first feature vector and the second feature vector obtained through the feature vector obtaining module 220. Specifically, the combining module 230 may preferentially determine whether to synthesize the first feature vector and the second feature vector based on a predetermined condition. For example, the synthesis module 230 may determine whether to synthesize the first feature vector and the second feature vector based on Equation 1.

는 제1 특징 벡터에 대응되는 제1 레이블(나이),

는 제2 특징 벡터에 대응되는 제2 레이블(나이),

은 미리 설정된 임계값을 나타낼 수 있다.

Is a first label (age) corresponding to the first feature vector,

Is a second label (age) corresponding to the second feature vector,

May represent a preset threshold.

은 합성 결과의 정확성을 위해 미리 설정되는 임계값일 수 있다. 구체적으로, 10세에 대응되는 특징 벡터를 생성하기 위하여 1세에 대응되는 특징 벡터 및 19세에 대응되는 특징 벡터를 사용하는 경우보다, 9세에 대응되는 특징 벡터 및 11세에 대응되는 특징 벡터를 이용하는 것이 보다 정확도가 높은 결과가 산출될 수 있다. 따라서, 컴퓨팅 장치는 소정의 임계값에 따라 특징 벡터의 합성 여부를 결정할 수 있다.

May be a threshold value set in advance for the accuracy of the synthesis result. Specifically, a feature vector corresponding to 9 years old and a feature vector corresponding to 11 years old than when using a feature vector corresponding to 1 year old and a feature vector corresponding to 19 years old to generate a feature vector corresponding to 10 years old The use of may yield higher accuracy results. Accordingly, the computing device may determine whether to synthesize feature vectors according to a predetermined threshold.

According to another embodiment, when the interval between the labels of the feature vectors is less than or equal to a threshold value, the synthesis module 230 may determine whether to proceed with the synthesis according to a predetermined probability.

When it is determined to synthesize the feature vector based on Equation 1, the synthesizing module 230 may synthesize the feature vector and the label corresponding to the feature vector based on Equation 2.

,

,

는 각각 제1 특징 벡터, 제2 특징 벡터, 제3 특징 벡터이고,

,

,

는 각각 제1 특징 벡터에 대응되는 제1 레이블, 제2 특징 벡터에 대응되는 제2 레이블, 제3 특징 벡터에 대응되는 제3 레이블을 의미하고,

는 합성 정도를 나타내는 임의의 변수일 수 있으며, 예를 들어,

는 beta 분포를 따르는 변수일 수 있다.

,

,

Is a first feature vector, a second feature vector, and a third feature vector, respectively,

,

,

Denotes a first label corresponding to a first feature vector, a second label corresponding to a second feature vector, and a third label corresponding to a third feature vector, respectively,

May be any variable indicating the degree of synthesis, for example,

May be a variable following the beta distribution.

A third feature vector and a third label (age) corresponding thereto may be determined based on Equations 2 and 3.

It will be understood by those of ordinary skill in the art that the method of synthesizing by the synthesizing module 230 may include any data synthesis method including a method using linear interpolation or a fully connected layer.

The bone image generation and transmission module 240 may generate a bone image corresponding to the target age based on the third feature vector generated through the synthesis module 230. Specifically, the bone image generation and transmission module 240 may include an artificial neural network model such as CycleGAN and BiBigGAN, and may generate a bone image corresponding to a target age based on this. A person of ordinary skill in the art can easily understand that the bone image generation and transmission module 240 is not limited to the example presented, and may be implemented through any method of generating a bone image based on a feature vector.

The bone image generation and transmission module 240 may store the generated bone image in a database or provide it to an external entity. When a bone image is provided to an external entity, the bone image generation and transmission module 240 may provide a bone image generated to the external entity using a predetermined display device or the like, or through an provided communication unit. Here, the external entity includes a user, an administrator, and a medical professional in charge of the computing device 100, but it should be understood that any subject that requires a bone image for the target age is included. something to do. For example, the external entity may be an external AI device including a separate artificial intelligence (AI) hardware and/or software module that utilizes the bone image. In addition,'external' in an external entity is not intended to exclude an embodiment in which an AI hardware and/or software module using the bone image is integrated into the computing device 100, but the method of the present invention It should be noted that the bone image, which is the result of the hardware and/or software module to be performed, was used to suggest that it can be used as input data for other methods. That is, the external entity may be the computing device 100 itself.

Although the components shown in FIG. 2 are illustrated as being realized in one computing device for convenience of description, it will be understood that a plurality of computing devices 100 performing the method of the present invention may be configured to interlock with each other.

3 is a flowchart illustrating a method of generating a bone image according to an exemplary embodiment.

Referring to FIG. 3, the computing device may receive an input of a target goal age through a communication unit in step 310.

The computing device may obtain a first candidate bone image and a second candidate bone image for generating a bone image corresponding to the target bone age in step 320. If the target bone age is included between the bone age corresponding to the first candidate bone image and the bone age corresponding to the second candidate bone image, the computing device may determine the bone age of the first candidate bone image and the bone age of the second candidate bone image. At least one of the first candidate bone image and the second candidate bone image may be obtained again so that the interval between ages is less than or equal to a predetermined interval. This is to improve the accuracy of the calculation result by using the bone image corresponding to the age close to the target bone age in the process of generating the image corresponding to the target bone age as described above.

The computing device may acquire a first feature vector and a second feature vector for each of the first candidate bone image and the second candidate bone image, based on the read model learned in advance in step 330. As described above, the pre-learned readout model may be an artificial neural network trained to obtain a feature vector from the input bone image and read the age of the input bone image based on this.

The pre-learned readout model may be learned to output a feature vector of the input bone image based on the processed learning bone image. A method in which the reading model is learned to read the age of the bone image by using the bone image labeled with the corresponding age as training data can be easily understood by a person skilled in the art. The pre-learned reading model used in the present invention may be learned using a processed learning bone image to improve reading accuracy. Specifically, the processed learning bone image may further include a third learning bone image generated by synthesizing the first learning bone image and the second learning bone image acquired on the learning bone image. The third learning bone image may correspond to a third bone age corresponding to an age between the first bone age corresponding to the first learning bone image and the second bone age corresponding to the second learning bone image. The processed learning data may include all elements corresponding to individual ages compared to existing learning data. The present invention has a remarkable effect of providing a more accurate reading result through a reading model learned using processed learning data.

The computing device may generate a third feature vector corresponding to the target bone age by synthesizing the first feature vector and the second feature vector in step 340. The computing device may generate a third feature vector by interpolating the first feature vector and the second feature vector, and the method of generating the third feature vector is not limited to the presented example as described above.

In operation 350, the computing device may generate a target bone image corresponding to the target bone age based on the third feature vector.

4 is a diagram illustrating an example of performing a method of generating a bone image according to an exemplary embodiment.

A system for reading bone age through an image may provide a reader with a reference bone image corresponding to an individual age, and the reader may read the age of the input bone image through comparison with the reference bone image. In the absence of the reference bone image 410 corresponding to 3 years old as shown on the left among the reference bone images stored in the database, it may be difficult for the reader to read the bone age of the corresponding age group. In addition, in the case of an infant with a very fast development rate, since the difference in bone development can be large even after a few months, even if a reference bone image corresponding to 1 year old and a reference bone image corresponding to 2 years old are used, 1 to 2 Predicting the bone age of an infant between three years can be very difficult.

The computing device 420 receives the first candidate bone image 431 and the second candidate bone image 432 corresponding to the second generation in order to generate the missing reference bone image of 3 years old, and based on this, the 3 A bone image 440 corresponding to three may be generated.

The computing device 420 may generate a bone image corresponding to a target age based on a feature vector previously stored through labeling based on age in the database as well as the presented method. In this case, in the process of generating the bone image corresponding to the target age, the computing device 420 may generate the bone image through only information on the target bone age without receiving the bone image.

5 is a diagram showing the distribution of feature vectors according to age.

Referring to FIG. 5, a graph 510 may be a distribution of feature vectors for a male bone image, and a graph 520 may be a distribution of feature vectors for a female bone image. Each of the points 511 and 512 included in the graphs 510 and 520 may correspond to a feature vector of an individual bone image, and the colors of the points 511 and 512 may indicate a corresponding age. Referring to graphs 510 and 520, it can be seen that points 511 and 512 corresponding to similar ages are distributed in adjacent regions. When considering this distribution, it can be understood that the feature vector calculated through the synthesis of the feature vectors of the adjacent age can reveal the characteristics of the target age.

6 is a diagram illustrating an example of an interface to which a method for generating a bone image according to an exemplary embodiment is applied.

Referring to FIG. 6, reference bone images 621, 622, and 623 of a similar age to the current bone image 620 may be provided through the interface 610. Reference bone images 621, 622, and 623 corresponding to each age may be previously stored in a database. In the reading process, when a reference bone image between the ages of 10 and 11 is requested, the reader may request to generate a reference bone image corresponding to the age based on a user input to the graphic object 630. When a user input for the graphic object 630 is made, a graphic object 640 for inputting a target age may be displayed on the screen. The computing device may generate a reference goal image 650 corresponding to the target age and display it on the screen.

Based on the description of the above embodiment, one of ordinary skill in the art can realize that the method and/or processes of the present invention, and the steps thereof, can be implemented in hardware, software, or any combination of hardware and software suitable for a specific application. Can understand the point clearly. The hardware may include a general-purpose computer and/or a dedicated computing device, or a specific computing device or special features or components of a specific computing device. The processes may be realized by one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors or other programmable devices, with internal and/or external memory. In addition, or as an alternative, the processes can be configured to process application specific integrated circuits (ASICs), programmable gate arrays, programmable array logic (PAL) or electronic signals. May be implemented with any other device or combination of devices. Furthermore, the objects of the technical solution of the present invention or parts contributing to the prior art may be implemented in the form of program instructions that can be executed through various computer components and recorded in a machine-readable recording medium. The machine-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the machine-readable recording medium may be specially designed and configured for the present invention, or may be known to and usable by a person skilled in the computer software field. Examples of machine-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROM, DVD, Blu-ray, and magnetic-optical media such as floptical disks. (magneto-optical media), and hardware devices specially configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include a processor, a processor architecture, or a heterogeneous combination of different hardware and software combinations, as well as any one of the aforementioned devices, or storage and compilation or interpreting to be executed on a machine capable of executing any other program instructions. Can be made using a structured programming language such as C, an object-oriented programming language such as C++, or a high-level or low-level programming language (assembly, hardware description languages and database programming languages and technologies), machine code, This includes not only bytecode but also high-level language code that can be executed by a computer using an interpreter or the like.

Thus, in an aspect according to the present invention, when the above-described method and combinations thereof are performed by one or more computing devices, the method and combinations of methods may be implemented as executable code that performs each step. In another aspect, the method may be implemented as systems that perform the steps, and the methods may be distributed in several ways across devices or all functions may be integrated into one dedicated, standalone device or other hardware. In yet another aspect, the means for performing the steps associated with the processes described above may include any hardware and/or software described above. All such sequential combinations and combinations are intended to be within the scope of this disclosure.

For example, the hardware device can be configured to operate as one or more software modules to perform the processing according to the present invention, and vice versa. The hardware device may include a processor such as MPU, CPU, GPU, TPU, which is coupled with a memory such as ROM/RAM for storing program instructions and configured to execute instructions stored in the memory, and may include an external device and a signal It may include a communication unit that can send and receive. In addition, the hardware device may include a keyboard, a mouse, and other external input devices for receiving commands written by developers.

In the above, the present invention has been described by specific matters such as specific components and limited embodiments and drawings, but this is provided only to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments, Anyone with ordinary knowledge in the technical field to which the present invention pertains can make various modifications and variations from this description.

Therefore, the spirit of the present invention is limited to the above-described embodiments and should not be defined, and all modifications equivalently or equivalently to the claims as well as the claims to be described later fall within the scope of the spirit of the present invention. I would say.

Such equivalently or equivalently modified ones will include, for example, a logically equivalent method capable of producing the same result as that of carrying out the method according to the present invention, the true meaning and scope of the present invention. Is not to be limited by the above-described examples, and should be understood in the broadest possible meaning by law.

Claims (7)

In the bone image generation method performed by a computing device,
Receiving an input of a target bone age;
Obtaining a first candidate bone image and a second candidate bone image for generating a bone image corresponding to the target bone age;
Obtaining a first feature vector and a second feature vector for each of the first candidate bone image and the second candidate bone image based on a pre-learned readout model;
Generating a third feature vector corresponding to the target bone age by synthesizing the first feature vector and the second feature vector; And
Generating a target bone image corresponding to the target bone age based on the third feature vector
Including,
Generating the third feature vector,
Through the sum of the first label corresponding to the bone age of the first candidate bone image to which a first weight is assigned, and the second label corresponding to the bone age of the second candidate bone image to which the second weight is assigned. Determine the first weight and the second weight so that the generated third label corresponds to the target bone age,
Generating the third feature vector based on a sum of the first feature vector to which the first weight is assigned and the second feature vector to which the second weight is assigned.
The method of claim 1,
The pre-trained reading model,
Based on the processed learning bone image, it is pre-trained to output a feature vector of the input bone image,
The processed learning goal image,
A first learning bone image, a second learning bone image, and a third learning bone image generated based on the synthesis of the first learning bone image and the second learning bone image,
The third bone age corresponding to the third learning bone image,
A bone image generation method included between a first bone age corresponding to the first learning bone image and a second bone age corresponding to the second learning bone image.
delete The method of claim 1,
Generating the third feature vector,
When the distance between the first label and the second label is less than a predetermined threshold, generating the third feature vector based on the first feature vector and the second feature vector,
When the interval is greater than or equal to the predetermined threshold value, a third feature vector is not generated.
A computer program, stored on a machine-readable non-transitory recording medium, comprising instructions embodied to cause a computing device to perform the method of any one of claims 1, 2 and 4.
In the computing device for generating a bone image,
A communication unit for receiving an input for the target bone age; And
Processor for generating a target goal image corresponding to the target goal age
Including,
The processor,
Obtaining a first feature vector and a second feature vector for each of the first candidate bone image and the second candidate bone image based on the pre-learned readout model,
Synthesizing the first feature vector and the second feature vector to generate a third feature vector corresponding to the target bone age,
Based on the third feature vector, a target bone image corresponding to the target bone age is generated,
The processor,
Through the sum of the first label corresponding to the bone age of the first candidate bone image to which a first weight is assigned, and the second label corresponding to the bone age of the second candidate bone image to which the second weight is assigned. Determine the first weight and the second weight so that the generated third label corresponds to the target bone age,
And generating the third feature vector based on a sum of the first feature vector to which the first weight is assigned and the second feature vector to which the second weight is assigned.
The method of claim 6,
The pre-trained reading model,
Based on the processed learning bone image, it is pre-trained to output a feature vector of the input bone image,
The processed learning goal image,
A first learning bone image, a second learning bone image, and a third learning bone image generated based on the synthesis of the first learning bone image and the second learning bone image,
The computing device, wherein the third bone age corresponding to the third learning bone image is included between a first bone age corresponding to the first learning bone image and a second bone age corresponding to the second learning bone image.

Images