WO2019143120A1

WO2019143120A1 - Intelligent automatic radiotherapy planning method and system

Info

Publication number: WO2019143120A1
Application number: PCT/KR2019/000636
Authority: WO
Inventors: 주상규; 홍채선; 안용찬
Original assignee: 사회복지법인 삼성생명공익재단
Priority date: 2018-01-17
Filing date: 2019-01-16
Publication date: 2019-07-25
Also published as: KR101968671B1

Abstract

One embodiment of the present invention provides an intelligent automatic radiotherapy planning method comprising the steps of: receiving and storing in a database first information including personal information, diagnosis and examination information, disease stage information, and medical image information on existing patients who have undergone radiotherapy, second information including information on dose and irradiation used in radiotherapy for the patient, and third information on the result derived after performing the radiotherapy according to the second information; generating a therapy plan prediction model by performing artificial intelligence-based correlation and regression analysis on the first to third information; determining a radiotherapy plan, for a new patient, having fourth information including personal information before therapy, diagnosis and examination information, stage information, and medical image information by using the therapy plan prediction model; and storing, in the database, the fourth information and sixth information on the result derived after performing the radiotherapy according to the radiotherapy plan of the new patient.

Description

Intelligent automatic radiotherapy planning method and system

Embodiments of the present invention are directed to a method and system for intelligent automatic radiotherapy planning.

Radiotherapy is a method of delaying, stopping, or even destroying the growth of malignant tissue by damaging or destroying the target tissue using high-energy waves such as x-rays and gamma rays or high-energy particles such as electron beams and proton rays. Radiation therapy is used not only for cancer, but also for benign tumors, medical diseases, and some skin diseases. Recently, a radiotherapy method has been developed in which, instead of the neurosurgical operation method of cutting the skull, a large amount of radiation is irradiated at one time without incision surgery.

More recently, more than 60% of cancer patients have been generalized to receive radiation therapy. Radiation therapy is not only used to treat tumors as such, but also can be used in conjunction with other surgical procedures to treat localized tumors that are large and invasive and difficult to surgically remove, It can be used to make surgical operations easier or to destroy the remaining malignant cells after surgery.

Therefore, precise radiotherapy planning is required, such as determining the location of irradiation and the dose of radiation considering the size and location of the tumor present in the patient's current tissue before irradiating the tumor tissue to the patient. In the past, the optimal radiation treatment plan was derived by setting the location of the tumor using tomographic images and then controlling the irradiation position and the radiation dose based on the experience and the physical knowledge of the dose planner. However, this method is dependent on the ability and experience of the clinician participating in the dose planner and radiotherapy plan, and the quality of the treatment plan results will vary and treatment planning time and work will increase. It is difficult to obtain an excellent treatment plan to investigate the high doses of the tumor while lowering the dose to the surrounding normal organs, particularly in the case of a complicated treatment plan in which the shape of the tumor is complex and the surrounding normal organs are close. It is impossible to predict the outcome of the treatment and it is impossible to establish a customized treatment plan for various patient conditions. In addition, as the time and workload of treatment planning increases, early detection and aggressive treatment planning changes are difficult if the size of the tumor in existing patients changes.

Embodiments of the present invention provide an intelligent automatic radiotherapy planning method and system that can automatically establish a radiotherapy plan.

An embodiment of the present invention is a medical treatment method including first information including personal information, diagnosis and examination information, disease information and medical image information on existing patients who have undergone radiotherapy, and first information including medical image information, Receiving second information including radiation dose information and radiation irradiation information performed on the first information and third information on a result obtained after performing the radiation treatment by the second information, Generating a treatment plan prediction model by performing artificial intelligence-based correlation and regression analysis on the first information to the third information, and generating a treatment plan prediction model by using the treatment plan prediction model, Evaluating and determining a radiation therapy plan of a new patient having fourth information including at least one of disease information and medical image information, A sixth information on the results obtained after performing the radiation therapy according to the plan, including the step of storing in the database, and provides automatic intelligent radiation treatment planning method.

The intelligent automatic radiotherapy plan planning method according to the embodiments of the present invention is a method of predicting a radiotherapy plan plan that can obtain the best result through artificial intelligence algorithm by converting various patient information into a big data Can be generated. Such a treatment plan prediction model can be applied to a new patient's computerized treatment plan to generate the best treatment plan for the patient. In addition, the intelligent automatic radiotherapy planning method automatically establishes an adaptive radiotherapy plan based on various information generated during the treatment. After the treatment is completed, the therapeutic information and the clinical result are input into the victor, It can have a continuous quality improvement.

FIG. 1 is a schematic diagram of a system for intelligent automatic radiotherapy planning according to an embodiment of the present invention. Referring to FIG.

FIG. 2 is a block diagram schematically showing the configuration of an intelligent automatic radiotherapy planning apparatus according to an embodiment of the present invention. Referring to FIG.

3 is a flowchart sequentially illustrating an intelligent automatic radiotherapy treatment planning method according to an embodiment of the present invention.

FIGS. 4 and 5 are diagrams for explaining a method of generating a radiation treatment plan prediction model.

In one embodiment of the present invention, fifth information including medical image information, diagnosis and examination information, and side effect information acquired during treatment of the new patient is received, and the fourth information is compared with the fifth information Further comprising correcting the radiation treatment plan using the treatment plan prediction model and the fifth information when a difference occurs after the radiation treatment, and the sixth information is subjected to the radiation treatment according to the corrected radiation treatment plan And may be information on the result obtained after the operation.

In one embodiment of the present invention, the step of generating the treatment plan prediction model may include generating a first characteristic vector from the first information, generating a second characteristic vector from the second information, Generating a plurality of patterns by combining different factors among the first information and the third information, performing a correlation analysis and a regression analysis on the generated plurality of patterns, Extracting a specific pattern of the first feature vector from the plurality of patterns using the result of the regression analysis and generating a treatment plan prediction model that derives the second feature vector as a result value using the extracted specific pattern Step < / RTI >

In one embodiment of the present invention, the step of generating the treatment plan prediction model may include generating a third feature vector from the third information, and using the third feature vector and the specific pattern to obtain the highest survival rate Can be derived as a result value.

An embodiment of the present invention is a medical treatment method including first information including personal information, diagnosis and examination information, disease information and medical image information on existing patients who have undergone radiotherapy, and first information including medical image information, The second information including the radiation dose information and the radiation source information performed on the first patient, the third information on the result obtained after the radiation therapy is performed by the second information, A communication unit for receiving fourth information including information, diagnosis and inspection information, disease information, and medical image information, and a communication unit for collecting the first information to the fourth information received from the communication unit according to a data standardization format And generating a treatment plan prediction model using the collected first to third information, and based on the generated treatment plan prediction model and the fourth information, It provides an intelligent automated radiation treatment planning system which includes a control unit for determining.

According to an embodiment of the present invention, the communication unit may include fifth information including medical image information, diagnosis and examination information, and side effect information acquired during treatment of the new patient, and fifth information including side effect information, It is possible to receive the sixth information about the result obtained after performing the treatment.

In one embodiment of the present invention, the controller compares the fourth information with the fifth information, and when the difference occurs, corrects the radiation treatment plan using the treatment plan prediction model and the fifth information can do.

In an embodiment of the present invention, the sixth information may be information on a result obtained after performing the radiation therapy according to the corrected radiation therapy plan.

In one embodiment of the present invention, the control unit generates a first feature vector and a second feature vector from the first information and the second information, respectively, and calculates different factors among the first information and the third information And generating a plurality of patterns by performing a correlation analysis and a regression analysis on the generated plurality of patterns, and using the correlation analysis and the result of the regression analysis, And derive a treatment plan prediction model that derives the second feature vector as a result value using the extracted specific pattern.

In one embodiment of the present invention, the control unit generates a third feature vector from the third information, and uses a third feature vector and the specific pattern to obtain a second feature vector having the highest survival rate as a result Value.

One embodiment of the present invention provides a computer program stored on a medium for performing the above method using a computer.

Other aspects, features, and advantages will become apparent from the following drawings, claims, and detailed description of the invention.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention and methods of achieving them will be apparent with reference to the embodiments described in detail below with reference to the drawings. However, the present invention is not limited to the embodiments described below, but may be implemented in various forms.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals refer to like or corresponding components throughout the drawings, and a duplicate description thereof will be omitted .

In the following embodiments, the terms first, second, and the like are used for the purpose of distinguishing one element from another element, not the limitative meaning.

In the following examples, the singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise.

In the following embodiments, terms such as inclusive or possessive are intended to mean that a feature, or element, described in the specification is present, and does not preclude the possibility that one or more other features or elements may be added.

In the following embodiments, when a part of a film, an area, a component or the like is on or on another part, not only the case where the part is directly on the other part but also another film, area, And the like.

In the drawings, components may be exaggerated or reduced in size for convenience of explanation. For example, the size and thickness of each component shown in the drawings are arbitrarily shown for convenience of explanation, and thus the present invention is not necessarily limited to those shown in the drawings.

If certain embodiments are otherwise feasible, the particular process sequence may be performed differently from the sequence described. For example, two processes that are described in succession may be performed substantially concurrently, and may be performed in the reverse order of the order described.

In the following embodiments, when a film, an area, a component, or the like is referred to as being connected, not only the case where the film, the region, and the components are directly connected but also the case where other films, regions, And indirectly connected. For example, in the present specification, when a film, an area, a component, and the like are electrically connected, not only a case where a film, an area, a component, etc. are directly electrically connected but also another film, And indirectly connected electrically.

Referring to FIG. 1, an intelligent automatic radiotherapy planning system according to an embodiment of the present invention may include a server 100, a user terminal 200, an external device 300, and a communication network 400 connecting them. have.

The intelligent automatic radiotherapy plan planning system according to an embodiment of the present invention is a system in which a server 100 receives information necessary for performing a radiotherapy of a patient such as patient information or radiotherapy plan information from an external device 300, Planned Prediction Models can be created to establish an automated radiation treatment plan. In addition, the intelligent automatic radiotherapy planning planning system can further receive the state information and the like after the treatment through the user terminal 200, and apply it to the generation of the radiation treatment plan prediction model.

The external device 300 may refer to various devices that transmit and receive data to and from the server 100 and the user terminal 200 via the communication network 400. Specifically, in the present invention, the external device 300 may be a medical management system that manages clinical information of patients, or a treatment system that generates or manages the radiation treatment plan information. In one embodiment, the external device 300 may be a device for generating medical image information used in a radiation treatment plan. For example, the external device 300 may be a computer tomography (CT) device, an MRI (Magnetic Resonance Imaging) device, a PET (Positron Emission Tomography) device, a CT simulator, . The external device 300 may be a device that provides the server 100 with clinical information or radiotherapy plan information of patients. The external device 300 may be a single number or a plurality.

The user terminal 200 may refer to various devices for transmitting the quality of life evaluation information of the patients to the server 100 after the radiation therapy. At this time, the terminal may be the portable terminal 201 or the personal computer 202.

The user terminal 200 may have display means for displaying the content, and input means for obtaining the user's input on the content. At this time, the input means and the display means can be configured in various ways. For example, the input means may include, but is not limited to, a keyboard, a mouse, a trackball, a microphone, a button, a touch panel,

Here, the information on the quality of life of the patients is information for recording the side effects during or after the radiation therapy and evaluating the quality of life using the information. The quality of life evaluation information may be a set of information that the patients entered through the user terminal 200 to input the degree of symptoms that may be caused by radiation therapy. In addition, the quality of life evaluation information may include skin image information in which the patient imaged the treatment region through a camera (not shown) provided in the user terminal 200.

The user terminal 200 may transmit the set of information to the server 100, and may transmit the processed information to the server 100 as the processed data through a predetermined algorithm.

In the present invention, the communication network 400 connects the server 100, the user terminal 200, and the external device 300. For example, the communication network 400 provides a connection path so that the user terminal 200 can transmit and receive packet data after connecting to the server 100. The communication network 400 may be a wired network such as LANs (Local Area Networks), WANs (Wide Area Networks), MANs (Metropolitan Area Networks), ISDNs (Integrated Service Digital Networks), wireless LANs, CDMA, Bluetooth, But the scope of the present invention is not limited thereto.

In the present invention, the server 100 receives information necessary for performing a patient's radiation therapy, such as patient information or radiation therapy plan information, from the external device 300, generates a radiation treatment plan prediction model, and establishes an automated radiation treatment plan can do. In addition, the server 100 may further receive state information and the like after the treatment through the user terminal 200, and may apply the state information and the like to the generation of the radiation treatment plan prediction model.

FIG. 2 is a block diagram schematically illustrating the configuration of an intelligent automatic radiotherapy planning apparatus 110 according to an embodiment of the present invention.

Referring to FIG. 2, the intelligent automatic radiotherapy planning apparatus 110 according to an embodiment of the present invention may include a communication unit 111, a control unit 112, and a memory 113. In addition, although not shown in the drawing, the intelligent automatic radiotherapy planning apparatus 110 according to an embodiment of the present invention may further include an input / output unit, a program storage unit, and the like.

The communication unit 111 is connected to the intelligent automatic radiotherapy planning apparatus 110 via a wired or wireless connection with other network devices such as the user terminal 200 or the external device 300 to transmit and receive signals such as a control signal or a data signal. Hardware, and software.

The control unit 112 may include any kind of device capable of processing data, such as a processor. Herein, the term " processor " may refer to a data processing apparatus embedded in hardware, for example, having a circuit physically structured to perform a function represented by a code or an instruction contained in the program. As an example of the data processing apparatus built in hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an ASIC (Application-Specific Integrated Circuit, and an FPGA (Field Programmable Gate Array), but the scope of the present invention is not limited thereto.

The memory 113 performs the function of temporarily or permanently storing the data processed by the intelligent automatic radiotherapy planning apparatus 110. The memory 113 may include a magnetic storage medium or a flash storage medium, but the scope of the present invention is not limited thereto.

The intelligent automatic radiotherapy plan planning apparatus 110 may be provided separately from the server 100 according to the role allocation. However, the intelligent automatic radiotherapy plan scheduling apparatus 110 may be provided separately from the server 100 have.

Meanwhile, as described above, the server 100, that is, the intelligent automatic radiotherapy plan establishing apparatus 110 receives information necessary for performing the radiotherapy of the patient, such as patient information or radiotherapy plan information from the external device 300, Radiation Therapy Plan You can create a predictive model to establish an automated radiotherapy plan. In addition, the server 100 may further receive state information and the like after the treatment through the user terminal 200, and may apply the state information and the like to the generation of the radiation treatment plan prediction model.

Hereinafter, a method of generating a treatment plan prediction model in the server 100, that is, the intelligent automatic radiotherapy planning apparatus 110, and automatically establishing a radiation treatment plan will be described with reference to FIGS. 3 to 5. FIG.

FIG. 3 is a flowchart sequentially illustrating an intelligent automatic radiotherapy plan establishment method according to an embodiment of the present invention, and FIGS. 4 and 5 are diagrams illustrating a method of generating a radiation treatment plan prediction model.

3 to 5, the communication unit 111 of the intelligent automatic radiotherapy planning apparatus 110 according to an embodiment of the present invention may transmit first to third information of existing patients from the external device 300 (S100).

At this time, the first information A1 may include personal information about the existing patients who have undergone radiation therapy, diagnosis and examination information, disease information, and medical image information. The personal information, diagnostic and test information, and staging information may be information derived from previously performed medical records of patients. The medical image information may be information generated from the medical image device. For example, a medical imaging apparatus such as a computed tomography (CT) apparatus, a magnetic resonance imaging (MRI) apparatus, a positron emission tomography (PET) apparatus, a CT simulator, The medical image information can be generated by photographing the living body to be examined. The generated medical image information is converted into DICOM (Digital Imaging and Communications in Medicine), and it is shown in the form of a DICOM RT (Radiation Therapy) data file.

The second information A2 may include radiation dose information and radiation irradiation information performed in the radiation therapy on the patient. The second information A2 may be treatment data performed in the radiation therapy and may be a set of parameter information required for radiation therapy. The second information A2 includes not only radiation dose information but also dose constraints, body contouring information, beam modality, dose schedule, beam parameter information such as beam parameters, X-rays, electron beams, types of therapeutic sources such as proton, therapeutic source energy, treatment methods such as three-dimensional and intensity control, beam direction, and the like.

The third information A3 may be information on the result obtained after the radiation therapy is performed by the second information A2. The third information (A3) may be survival rate information or side effect information for existing patients who have undergone radiation therapy. The side effect information of the third information (A3) may be information judged and recorded by a specialist such as a doctor in a medical institution.

The first information A1, the second information A2 and the third information A3 may be stored in the memory 113 as a database (S200).

Next, the control unit 112 generates artificial intelligence-based correlation and regression analysis of the provided first information A1, second information A2, and third information A3 to generate a treatment plan prediction model M (S300). Specifically, the control unit 112 may generate a first characteristic vector 311 from the first information A1 and a second characteristic vector 313 from the second information A2. The first feature vector 311 and the second feature vector 312 may be values for factors that directly or indirectly affect the determination of the treatment plan predictive model (M). For example, the first feature vector 311 and the second feature vector 312 may be values for dose-volume histogram related factors, survival probability related factors, and complication possibility related factors. Alternatively, the first feature vector 311 and the second feature vector 312 may be a set or combination of values that are not one value.

The control unit 112 may generate a plurality of patterns by combining different factors among the first to third information A1 to A3, and may perform correlation analysis and regression analysis on the plurality of generated patterns. The controller 112 may extract a specific pattern for the first feature vector 311 among the plurality of patterns using the correlation analysis and the result of the regression analysis performed. In other words, the specific pattern described above may be a pattern that results from information extracted from existing patients and results in therapeutic results after radiotherapy. The control unit 112 may generate a treatment plan prediction model M that derives a result value B1 in the form of a second feature vector using the extracted specific pattern.

The control unit 112 can generate the third feature vector 313 from the third information A1. The control unit 112 can derive the second feature vector having the highest survival rate as the result value B1 by using the third feature vector 313 and the above-described feature pattern. In other words, when the information on the new patient is inputted after generating the treatment plan prediction model (M), the control unit 112 can output the radiation treatment plan information having the highest survival rate in the form of the second feature vector .

As another example, the control unit 112 may derive a second feature vector having the lowest side effect as a result value B1. Alternatively, the control unit 112 may derive the second feature vector having the highest survival rate and the lowest side effect as the result value B1.

Meanwhile, the control unit 112 may generate the treatment plan prediction model by further reflecting the quality of life evaluation information collected through the user terminal 200 described above. The quality-of-life evaluation information may include information on side effects such as side effects, cough, oral dryness, headache, etc., symptom information, pain information, hair loss or skin reaction information during or after treatment.

The control unit 112 may be configured to classify the first to third information A1 to A3 using a logistic regression, a decision tree, a nearest-neighbor classifier, a kernel discriminate analysis, a neural network, a support vector machine, Algorithm (s) and / or method (s).

The control unit 112 may use an algorithm and / or a method such as Linear regression, Regression tree, Kernel regression, Support vector regression, Deep Learning, etc. to predict a treatment plan.

In addition, the controller 112 may use algorithms and / or methods such as Principal component analysis, Non-negative matrix factorization, Independent component analysis, Manifold learning, and SVD.

The controller 112 may use algorithms and / or schemes such as k-means, hierarchical clustering, mean-shift, self-organizing maps (SOMs)

The controller 112 may use algorithms and / or methods such as Bipartite cross-matching, n-point correlation two-sample testing, and minimum spanning tree for data comparison.

However, the above-described algorithms and / or schemes are illustrative and not intended to limit the scope of the present invention.

Next, the control unit 112 can determine the radiation treatment plan of the new patient having the fourth information A4 before treatment using the treatment plan prediction model M (S400). At this time, the fourth information may be the information of the new patient corresponding to the first information A1. In other words, the fourth information A4 may include personal information of new patients, diagnosis and examination information, staging information, and medical image information. 5, the control unit 112 inputs the fourth information A4 of the new patient to the treatment plan prediction model M, and outputs the second feature vector having the highest survival rate as the result B1. . In addition, the control unit 112 can derive the expected survival rate or the degree of side effect when the radiation therapy is performed through the result value B1 using the treatment plan prediction model M. [

Next, the control unit 112 may receive the fourth information (A4) and the sixth information A6 related to the result obtained after performing the radiation therapy according to the radiation therapy plan of the new patient (S500). At this time, the radiation treatment plan information of the new patient may be a result value first derived from the treatment plan prediction model (M), but may be a corrected result value using the fifth information acquired during the radiation treatment. In other words, radiation therapy can lead to set-up errors due to patient's postural uncertainty, changes in the volume of the treatment, changes in normal tissue and body shape of the patient. The control unit 112 may collect the patient's position error information and calculate the PTV margin of the treatment plan volume reflecting the position error. The fifth information may be information reflecting the redundancy of the treatment plan volume.

If there is a difference between the fifth information and the fourth information, the control unit 112 may correct the radiation therapy plan using the treatment plan prediction model M and the fifth information. The control unit 112 can automatically generate a radiation treatment plan considering the treatment volume reset, the prescribed dose change, and the treatment volume according to the degree of the treatment response.

The next control unit 112 may store the fourth to sixth information (A4 to A6) for the new patient in the database, and update the treatment plan prediction model as new data.

As described above, in the intelligent automatic radiotherapy planning planning method according to the embodiments of the present invention, various patient information that has been treated in the past is converted into Big data, and the best result is obtained through the artificial intelligence algorithm A treatment plan prediction model can be generated. Such a treatment plan prediction model can be applied to a new patient's computerized treatment plan to generate the best treatment plan for the patient. In addition, the intelligent automatic radiotherapy planning method automatically establishes an adaptive radiotherapy plan based on various information generated during the treatment. After the treatment is completed, the therapeutic information and the clinical result are input into the victor, It can have a continuous quality improvement.

Meanwhile, the intelligent automatic radiotherapy planning apparatus according to an embodiment of the present invention can generate the artificial intelligent body contour model using the first information to the third information. This artificial intelligent body profile contour model can be used for planning a new patient's radiation therapy, considering the characteristics of the patient, the stage of the patient, the treatment area, the volume including the gross tumor volume and the clinical treatment volume, It can be created automatically.

The embodiments of the present invention described above can be embodied in the form of a computer program that can be executed on various components on a computer, and the computer program can be recorded on a computer-readable medium. At this time, the medium may be a computer-executable program. Examples of the medium include a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, an optical recording medium such as CD-ROM and DVD, a magneto-optical medium such as a floptical disk, And program instructions including ROM, RAM, flash memory, and the like.

Meanwhile, the computer program may be designed and configured specifically for the present invention or may be known and used by those skilled in the computer software field. Examples of computer programs may include machine language code such as those produced by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like.

The specific acts described in the present invention are, by way of example, not intended to limit the scope of the invention in any way. For brevity of description, descriptions of conventional electronic configurations, control systems, software, and other functional aspects of such systems may be omitted. Also, the connections or connecting members of the lines between the components shown in the figures are illustrative of functional connections and / or physical or circuit connections, which may be replaced or additionally provided by a variety of functional connections, physical Connection, or circuit connections. Also, unless explicitly mentioned, such as "essential "," importantly ", etc., it may not be a necessary component for application of the present invention.

Accordingly, the spirit of the present invention should not be construed as being limited to the above-described embodiments, and all ranges that are equivalent to or equivalent to the claims of the present invention as well as the claims .

According to an embodiment of the present invention, a method for establishing an intelligent automatic radiotherapy plan is provided. In addition, the embodiments of the present invention can be applied to a radiation therapy apparatus that requires an industrial radiation therapy plan.

Claims

The first information including personal information, diagnostic and test information, disease information and medical image information about the existing patients who have undergone radiotherapy and the first information including the radiation dose (Dose) Receiving second information including information and radiation irradiation information, and third information on a result obtained after performing the radiation treatment by the second information, and storing the received third information in a database;

Generating a treatment plan prediction model by performing artificial intelligence-based correlation and regression analysis on the first information, the second information, and the third information;

Evaluating and determining a radiation therapy plan of a new patient having fourth information including personal information before diagnosis, diagnosis and examination information, disease information, and medical image information using the treatment plan prediction model; And

Storing the fourth information and sixth information on the result obtained after performing the radiation therapy according to the radiation therapy plan of the new patient in the database.
The method according to claim 1,

Fifth information including medical image information, diagnosis and examination information, and side effect information acquired during treatment of the new patient is received, and when the fourth information is compared with the fifth information, Correcting the radiotherapy plan using the plan prediction model and the fifth information; Further comprising:

Wherein the sixth information is information on results obtained after performing the radiation therapy according to the corrected radiation treatment plan.
The method according to claim 1,

Wherein the step of generating the treatment plan prediction model comprises:

Generating a first characteristic vector from the first information;

Generating a second feature vector from the second information; And

Generating a plurality of patterns by combining different factors among the first information and the third information, performing a correlation analysis and a regression analysis on the generated plurality of patterns, and performing the correlation analysis and the regression analysis Extracting a specific pattern for the first feature vector among the plurality of patterns using the result and generating a treatment plan prediction model for deriving the second feature vector as a result value using the extracted specific pattern; The method comprising the steps of:
The method of claim 3,

Wherein the step of generating the treatment plan prediction model comprises:

Generating a third feature vector from the third information,

And deriving a second feature vector having the highest survival rate as a result value using the third feature vector and the specific pattern.
The first information including personal information, diagnostic and test information, disease information and medical image information about the existing patients who have undergone radiotherapy and the first information including the radiation dose (Dose) Second information including information and radiation source information, third information relating to a result obtained after the radiation therapy is performed by the second information, personal information before treatment relating to the new patient, diagnosis and examination information, A medical information receiving unit for receiving fourth information including disease information and medical image information; And

Collecting the first information to the fourth information received from the communication unit according to a data standardization format, generating a treatment plan prediction model using the collected first information to third information, And a controller for determining a radiation treatment plan of the new patient based on the prediction model and the fourth information.
6. The method of claim 5,

Wherein the communication unit includes fifth information including medical image information, diagnosis and examination information, and side effect information acquired during the treatment of the new patient, and fifth information including information on the result obtained after performing the radiation therapy according to the radiation treatment plan of the new patient Wherein the second information is further received from the first information processing apparatus.
The method according to claim 6,

Wherein the controller compares the fourth information with the fifth information and corrects the radiation treatment plan using the treatment plan prediction model and the fifth information when a difference occurs.
8. The method of claim 7,

Wherein the sixth information is information about results obtained after performing the radiation therapy according to the corrected radiation treatment plan.
6. The method of claim 5,

Wherein the controller generates a first feature vector and a second feature vector from the first information and the second information, generates a plurality of patterns by combining different factors of the first information and the third information, Performing a correlation analysis and a regression analysis on the generated plurality of patterns, extracting a specific pattern for the first feature vector among the plurality of patterns using the correlation analysis and the result of the regression analysis, And generates a treatment plan prediction model that derives the second feature vector as a result value using the extracted specific pattern.
10. The method of claim 9,

Wherein the control unit generates a third feature vector from the third information and derives a second feature vector having the highest survival rate using the third feature vector and the specific pattern as a result value, Planning system.
A computer program stored on a medium for carrying out the method of any one of claims 1 to 4 using a computer.