KR102392778B1 - System and Method of Determining Thearpeutic Radiation Dose based on Images - Google Patents

Abstract

The present invention relates to a system and method for determining the therapeutic dose of radiopharmaceuticals for treatment based on an image, and more particularly, predicting and determining the optimal therapeutic dose of radiopharmaceuticals for treatment to a patient using medical images of radiopharmaceuticals for diagnosis It relates to a system and method for determining the therapeutic dose of radiopharmaceuticals for image-based therapy.
According to the present invention, by predicting and determining in advance the optimal therapeutic dose of the radiopharmaceutical to be actually injected into the patient from the diagnostic medical image obtained after the radiopharmaceutical for diagnosis is injected into the patient, it is possible to determine the customized treatment dose for each patient. At the same time, it is possible to safely maximize the treatment efficiency of the patient by evaluating the absorbed dose not only at the target site but also at the non-target site.

Description

System and Method of Determining Thearpeutic Radiation Dose based on Images

The present invention relates to a system and method for determining the therapeutic dose of radiopharmaceuticals for treatment based on an image, and more particularly, predicting and determining the optimal therapeutic dose of radiopharmaceuticals for treatment to a patient using medical images of radiopharmaceuticals for diagnosis It relates to a system and method for determining the therapeutic dose of radiopharmaceuticals for image-based therapy.

Radiopharmaceuticals are being used for diagnostic purposes such as positron emission tomography (PET) and therapeutic purposes to destroy specific tumor tissues due to the increase in cancer and intractable diseases along with the extension of life expectancy. These radiopharmaceuticals are divided into diagnostic radiopharmaceuticals and therapeutic radiopharmaceuticals.

Since radiation generated from radioactive materials affects not only the tumor area but also normal cells, a large amount of radiopharmaceuticals cannot be used at a time, and radiation absorption channel evaluation is necessary for safe and efficient diagnosis and treatment for patients.

However, at present, it is impossible to determine and evaluate the patient's treatment dose prior to treatment using radiopharmaceuticals, so it is difficult to determine how much treatment dose to inject into the patient prior to treatment.

Therefore, before injecting radiopharmaceuticals for treatment, it is necessary to predict and determine the optimal injection dose of safe and appropriate radiopharmaceuticals for each patient in advance.

Korean Patent Laid-Open Patent 10-2015-009915

The problem to be solved by the present invention is by predicting and determining in advance the optimal therapeutic dose of the radiopharmaceutical for treatment to be actually injected into the patient from the diagnostic medical image obtained after the radiopharmaceutical for diagnosis is injected into the patient. It is to provide a system and method for determining the therapeutic dose of radiopharmaceuticals based on an image, which can determine the therapeutic dose of radiopharmaceuticals based on images, which can safely maximize the treatment efficiency of patients by evaluating the absorbed dose not only at the target site but also at the non-target site.

In order to solve the above problems, the present invention provides a diagnostic medical image acquisition unit for acquiring a diagnostic medical image for diagnosis after injecting a diagnostic radiopharmaceutical to a patient; a diagnostic distribution curve obtaining unit for obtaining a diagnostic distribution curve representing the radiation dose over time for each organ of the human body from the diagnostic medical image; a diagnostic distribution curve correction unit for obtaining a correction distribution curve obtained by correcting the diagnostic distribution curve by using a correction coefficient for a rate of change at which the distribution curve changes when a radiopharmaceutical for diagnosis is replaced with a radiopharmaceutical for treatment; an influence coefficient acquisition unit for acquiring an influence coefficient for each organ, which is an effect of radiopharmaceuticals on each surrounding organ, from the diagnostic medical image; and a therapeutic dose prediction unit that calculates the absorbed dose of each organ from the correction distribution curve and the influence coefficient, and determines the absorbed dose as the optimal therapeutic dose of the radiopharmaceutical for the treatment of the patient, for image-based treatment It is characterized by providing a radiopharmaceutical therapeutic dose determination system.

Preferably, the treatment dose prediction unit calculates the cumulative radiation dose from the area of the correction distribution curve, calculates a residual ratio that is a ratio of the cumulative radiation dose to the initial dose of the radiopharmaceutical, and the residual ratio and the influence coefficient It is possible to calculate the absorbed dose for each organ by multiplying by .

Preferably, the influence coefficient acquisition unit may acquire the influence coefficient for each organ through Monte Carlo simulation from the diagnostic medical image using predefined spatial coordinates, voxel size, and density information.

Preferably, the system comprises: a medical treatment image acquisition unit for obtaining a medical treatment image after injecting a therapeutic radiopharmaceutical to the patient by the optimal treatment dose; and a treatment distribution curve obtaining unit for obtaining a treatment distribution curve representing the amount of radiation over time for each organ of the human body from the treatment medical image.

Preferably, the system compares the correction distribution curve with the treatment distribution curve, and compares the correction distribution curve with the treatment distribution curve as a weighted average of the correction distribution curve and the treatment distribution curve with a weight set according to the recording time of the treatment medical image. can be recalibrated.

In addition, in order to achieve the above object, the present invention provides a method performed by a system for determining a therapeutic dose of a radiopharmaceutical for treatment, comprising the steps of (a) acquiring a diagnostic medical image for diagnosis after injecting a radiopharmaceutical for diagnosis into a patient ; (b) obtaining a diagnostic distribution curve representing the radiation dose with respect to time for each organ of the human body from the diagnostic medical image; (c) obtaining a correction distribution curve obtained by correcting the diagnostic distribution curve using a correction coefficient for a rate of change at which the distribution curve changes when a radiopharmaceutical for diagnosis is replaced with a radiopharmaceutical for treatment; (d) obtaining an effect coefficient for each organ, which is the effect of radiopharmaceutical on each organ in the vicinity, from the diagnostic medical image; and (e) calculating the absorbed dose of each organ from the correction distribution curve and the influence coefficient, and determining the absorbed dose as the optimal therapeutic dose of the radiopharmaceutical for the treatment of the patient, image-based treatment A method for determining the therapeutic dose for radiopharmaceuticals for use can be provided.

On the other hand, in order to achieve the above object, the present invention provides a computer-readable recording medium in which a program for realizing the method for determining the therapeutic dose of radiopharmaceuticals for treatment based on the image is recorded.

According to the present invention, by predicting and determining in advance the optimal therapeutic dose of the radiopharmaceutical to be actually injected into the patient from the diagnostic medical image obtained after the radiopharmaceutical for diagnosis is injected into the patient, it is possible to determine the customized treatment dose for each patient. At the same time, it is possible to safely maximize the treatment efficiency of the patient by evaluating the absorbed dose not only at the target site but also at the non-target site.

1 is a block diagram showing a system for determining the therapeutic dose of radiopharmaceuticals for treatment based on an image according to the present invention.
2 is a graph illustrating a time-radiation dose distribution curve.
3 is a diagram showing the influence coefficient for each organ.
4 is a flowchart illustrating a method for determining a therapeutic dose of a radiopharmaceutical for treatment based on an image according to the present invention.

Since the present invention can have various changes and can have various forms, specific embodiments are illustrated in the drawings and described in detail in the text. However, this is not intended to limit the present invention to the specific disclosed form, it should be understood to include all modifications, equivalents and substitutions included in the spirit and scope of the present invention.

Terms such as first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification is present, and includes one or more other features or It should be understood that the existence or addition of numbers, steps, operations, components, parts, or combinations thereof does not preclude the possibility of addition.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

Targeted therapy using radionuclides for treatment is a therapeutic technique used to treat refractory cancer patients.

The therapeutic radionuclide returns to a stable state and emits a high level of energy, which is used to treat patients with the principle of inducing proliferation and death of cancer cells. However, until now, it is impossible to determine and evaluate the patient's treatment dose prior to treatment, so it is difficult to determine how much treatment dose to inject into the patient before treatment.

In general, in the case of radiopharmaceuticals for treatment, gamma rays or single-photon emission computed tomography (SPECT) images are acquired and the radiation distribution is calculated for each area, which can be referred to as a direct evaluation method.

Since the gamma image is obtained as a two-dimensional image, the distribution amount of radiopharmaceuticals located in a three-dimensional space cannot be calculated. On the other hand, SPECT images can calculate the distribution of radiopharmaceuticals in three-dimensional space, but the quality of the images is poor, so it is difficult to accurately evaluate the dose.

On the other hand, the radiation dose evaluation method using surrogate radiopharmaceuticals for diagnosis can be said to be an indirect evaluation method.

A diagnostic radiopharmaceutical in which a therapeutic radionuclide is substituted with a diagnostic surrogate radionuclide has the ability to bind to a target site. This indirect evaluation is a method of indirectly evaluating the amount of radiation in the body using a diagnostic radiopharmaceutical capable of PET (Positron Emission Tomography) imaging.

The indirect evaluation method shows a high level of distribution accuracy because it evaluates the distribution of radiopharmaceuticals in the body based on PET images useful for imaging and quantitative analysis. As the molecular weight and the degree of charge change, there is a disadvantage in that it is not possible to obtain a value that exactly matches the radiation distribution of an actual radiopharmaceutical for treatment. Therefore, even in the case of indirect evaluation, it is difficult to determine the customized treatment dose for each patient.

The present invention relates to a system and method for determining the therapeutic dose of radiopharmaceuticals for treatment based on an image, and image-based treatment for predicting and determining the optimal therapeutic dose of a radiopharmaceutical for treatment to a patient using a medical image of a radiopharmaceutical for diagnosis It relates to a system and method for determining the therapeutic dose of radiopharmaceuticals for use.

Hereinafter, with reference to the accompanying drawings, a preferred embodiment of the present invention will be described in detail. Like reference numerals in each figure indicate like elements.

1 is a block diagram showing a system for determining the therapeutic dose of radiopharmaceuticals for treatment based on an image according to the present invention.

1, the image-based therapeutic radiopharmaceutical treatment dose determination system 100 according to the present invention includes a diagnostic medical image acquisition unit 110, a diagnostic distribution curve acquisition unit 120, and an influence coefficient acquisition unit 130. , the diagnostic distribution curve correction unit 140 and the treatment dose prediction unit 150 , and may further include at least one of the prediction-result comparison unit 160 and the treatment medical image processing unit 170 .

The diagnostic medical image acquisition unit 110 serves to acquire a diagnostic medical image for diagnosis after injecting a diagnostic radiopharmaceutical to a patient.

A diagnostic medical image is obtained after injecting a diagnostic radiopharmaceutical into at least one or more organ regions of a predetermined patient. For the diagnostic medical image, a positron emission tomography-computed tomography (PET-CT) scanner may be used for spatial analysis. A diagnostic medical image obtained using a PET-CT scanner includes a PET image and a CT image, and both images may be used together for analysis.

The diagnostic distribution curve obtaining unit 120 obtains a diagnostic distribution curve representing the radiation dose with respect to time for each organ of the human body from the diagnostic medical image.

The diagnostic distribution curve acquisition unit 120 divides a diagnostic medical image using a CT image in a predefined manner, sets boundaries between organs and regions of interest using anatomical information obtained through the CT image, and responds to time changes. Using the PET image, the position of each divided region and the radiation dose of radioactive isotopes can be obtained.

2 is a graph illustrating a time-radiation dose distribution curve.

Referring to FIG. 2 , the time-radiation dose distribution curve graphically represents the radiation dose measured according to time change in a specific organ or specific area. In the time-radiation dose distribution curve, the x-axis means the change in time, and the y-axis means the measured radiation dose.

Let's go back to FIG. 1 again for description.

As a result, the diagnostic distribution curve acquisition unit 120 obtains a diagnostic distribution curve for the time-radiation dose distribution for each organ region of the human body from the diagnostic medical image obtained after the diagnostic radiopharmaceutical is injected into the patient.

On the other hand, the influence coefficient acquisition unit 130 serves to acquire the influence coefficient for each organ, which is the effect of the injected radiopharmaceutical on each surrounding organ, from the diagnostic medical image.

To this end, the influence coefficient obtaining unit 130 obtains energy distribution for each area by performing Monte Carlo simulation using spatial coordinates, voxel size, and density information defined for each area of the diagnostic medical image as input data. Then, by using the energy distribution, an influence coefficient for each organ, which is an influence factor between each region, is obtained. In this case, a residual ratio to be described later may be further included as input data.

3 is a diagram showing the influence coefficient for each organ, and is a diagram showing the influence coefficient between blood, organs, and tissues.

For example, a patient could be injected with 48.1 MBq of Cu-64 in the liver, 15.28 MBq in the lungs, 0.74 MBq in Tumor 1, 0.74 MBq in Tumor 2, and 9.99 MBq in the background, and the above procedure could be performed. When the above process is performed, the liver effect coefficient is 7.79E+01 mGy/MBq, the liver effect coefficient on the lung is 6.84E-01 mGy/MBq, the liver effect coefficient on tumor 1 is 9.24 mGy/MBq, and the liver The coefficient of influence on tumor 2 can be calculated as 9.08 mGy/MBq.

The diagnostic distribution curve correction unit 140 obtains a correction distribution curve obtained by correcting the diagnostic distribution curve by using a correction coefficient for the rate of change at which the distribution curve changes when a radiopharmaceutical for diagnosis is replaced with a radiopharmaceutical for treatment.

When a therapeutic radionuclide is replaced with a diagnostic surrogate radionuclide capable of imaging, the molecular weight and charge level of the radiopharmaceutical change and do not exactly match the distribution curve of the actual therapeutic radiopharmaceutical. The correction factor according to the substitution of radiopharmaceuticals does not differ for each individual, and the correction factor according to the substituted nuclide can be obtained in advance by test or experiment. As a result, the diagnostic distribution curve correction unit 140 corrects the diagnostic distribution curve using a known correction coefficient representing the change relationship between the time-radiation dose distribution curve of the therapeutic radiopharmaceutical and the time-radiation dose distribution curve of the diagnostic radiopharmaceutical. By obtaining a calibration distribution curve, it is possible to calculate the time-radiation dose distribution curve of the actual therapeutic radiopharmaceutical to be injected into the patient from the time-radiation dose distribution curve of the diagnostic radiopharmaceutical.

The therapeutic dose prediction unit 150 calculates the absorbed dose of each organ from the correction distribution curve and the influence coefficient, and determines the calculated absorbed dose as the optimal therapeutic dose of the radiopharmaceutical for the treatment of the patient.

At this time, the treatment dose prediction unit 150 calculates the cumulative radiation dose from the area of the correction distribution curve, calculates the residual ratio, which is the ratio of the cumulative radiation dose to the initial dose of the radiopharmaceutical, and multiplies the residual ratio and the influence coefficient for each organ The absorbed dose can be calculated.

The following [Equation 1] is an equation for calculating the accumulated radiation dose for each region of the organ, and the cumulative radiation dose for each region may be calculated using the radiation dose measured according to time change.

는 누적 방사선량이고, A(t)는 시간에 따라 측정된 방사선량으로서 전술한 시간-방사선량 분포곡선과 동일하다. In [Equation 1],

is the cumulative radiation dose, and A(t) is the radiation dose measured over time, which is the same as the time-radiation dose distribution curve described above.

The residual ratio is the ratio of the radiation dose injected into the target area and the accumulated radiation dose, and may be calculated using the following [Equation 2].

는 누적 방사선량이고, A₀는 주입된 초기 방사선량을 의미한다.In [Equation 2],

is the cumulative radiation dose, and A ₀ means the initial dose of the injected radiation.

On the other hand, when the above-described optimal therapeutic dose is determined, a therapeutic radiopharmaceutical equivalent to the optimal therapeutic dose may be injected into the patient.

After the radiopharmaceutical for treatment is injected into the patient as much as the optimal treatment dose, the treatment medical image processing unit 170 obtains a medical treatment image for the patient, and shows the radiation dose for each organ of the body from the treatment medical image over time. Obtain a distribution curve.

The medical treatment image processing unit 170 includes a medical treatment image obtaining unit 171 and a treatment distribution curve obtaining unit 173 , and may further include a deep learning learning unit 172 .

The medical treatment image acquisition unit 171 serves to obtain a medical treatment image including at least one of a PET image, a CT image, and a SPECT image of a patient injected with a radiopharmaceutical for treatment.

In this case, the obtained medical treatment image may be obtained by continuously collecting medical images for a long time, or may be obtained by collecting medical images only for a specific time.

Quantitative analysis of medical images includes static medical image analysis, which analyzes the amount of absorption at a specific time after injecting diagnostic or therapeutic radiopharmaceuticals, and dynamic analysis, which quantitatively analyzes the change in absorption rate of radiopharmaceuticals over time after the injection of radiopharmaceuticals. It can be divided into medical image analysis.

Dynamic medical image analysis continuously acquires images while waiting for the radiopharmaceutical to be sufficiently absorbed into the target site after administering the radiopharmaceutical to the patient's body before acquiring the medical image and performing quantitative analysis based on the single acquired medical image. Go through the process. Typically, analysis using ¹⁸ F-FDG belongs to this, and ¹⁸ F-FDG PET imaging is performed by intravenously injecting ¹⁸ F-FDG into the patient's body, and then acquiring the image for about 20 minutes 1 hour later.

Quantitative analysis method using dynamic medical images acquires images at the same time as radiopharmaceuticals are injected and continuously acquires images for a certain period of time. there is. However, unlike static medical images, patients have to lie down on imaging equipment for a long time in order to acquire dynamic medical images, which causes a lot of inconvenience to the patient.

In the case of static medical image analysis, since medical images are acquired for a short period of time, patient discomfort in acquiring medical images can be minimized. However, there is a disadvantage in that it does not reflect information on changes in absorption rate over time of radiopharmaceuticals.

In the case of dynamic medical image analysis, information on changes in absorption rate at the target site of radiopharmaceuticals over time can be accurately evaluated, but there is a problem in that it is a burden to the patient because all medical images over time must be acquired.

If a medical treatment image is obtained using the dynamic medical imaging method, the treatment distribution curve obtaining unit 173 obtains a treatment distribution curve representing the radiation dose with respect to time for each organ of the human body from the treatment medical image through the above-described processes. can do.

On the other hand, when a medical treatment image is obtained using the static medical imaging method, it is not possible to obtain a treatment distribution curve representing the radiation dose with respect to time because information on changes in absorption rate with time of radiopharmaceuticals cannot be known.

In this case, the deep learning learning unit 172 generates images before and after the shooting time from the static medical image obtained by the static medical image method using a deep learning network that has learned a number of various dynamic medical treatment images through deep learning. do.

Then, the treatment distribution curve acquisition unit 173 may obtain a treatment distribution curve through the above-described processes by analyzing the image generated by the deep learning learning unit and the existing static treatment medical image.

Information on a treatment distribution curve obtained from a dynamic treatment medical image or a treatment distribution curve obtained from a static treatment medical image and an image generated through deep learning is transmitted to the prediction-result comparison unit 160 .

The prediction-result comparison unit 160 compares the correction distribution curve with the treatment distribution curve received from the treatment medical image processing unit 170, and weights the correction distribution curve and the treatment distribution curve with a weight set according to the recording time of the treatment medical image. Recalibrate the calibration distribution curve with the mean.

In the case of a treatment medical image obtained in a dynamic manner, since the recording time of the medical image is long, the treatment distribution curve obtained accordingly coincides with the actual treatment distribution curve.

However, in the case of a medical treatment image acquired in a static manner, since the image is taken only for a certain period of time and the image for other times is a medical image generated through deep learning, there may be a deviation from the actual treatment distribution curve.

Therefore, it is possible to recalibrate the correction distribution curve by giving weights according to the length of time taken for medical images, and taking the weighted average of the correction distribution curve and the treatment distribution curve with the weight. For example, in the case of a treatment medical image obtained in a dynamic manner, the treatment distribution curve may have a weight of 1 and the correction distribution curve may have a weight of 0, so that the treatment distribution curve can be used as it is. It is preferable that the weights are set in a direction that increases the weight of the treatment distribution curve and decreases the weight of the correction distribution curve as the length of the time taken for the medical image is longer. Of course, as the length of the imaging time of the medical image becomes shorter, the weight may be set in a direction to decrease the weight of the treatment distribution curve and increase the weight of the correction distribution curve.

In addition, when the re-calibrated correction distribution curve is obtained, the prediction-result comparison unit 160 recalculates the cumulative radiation dose from the area of the re-calibrated correction distribution curve, and the ratio of the cumulative radiation dose to the initial dose of the radiopharmaceutical The residual ratio is recalculated, and the absorbed dose to each organ is recalculated by multiplying the recalculated residual ratio and the influence coefficient. At this time, the recalculated absorbed dose is re-determined as the optimal treatment dose for the patient and can be used as the optimal treatment dose for radiotherapy in the future.

Hereinafter, a method for determining the therapeutic dose of radiopharmaceuticals for treatment based on an image according to the present invention will be described. The image-based therapeutic radiopharmaceutical dose determination method according to the present invention is a method performed by the image-based therapeutic radiopharmaceutical therapeutic dose determination system according to the present invention, and the image-based therapeutic radiopharmaceutical treatment method according to the present invention Since it is essentially the same as the dose determination system, detailed and overlapping descriptions will be omitted. The image-based radiopharmaceutical therapeutic dose determination system 100 according to the present invention will be referred to as a therapeutic dose determination system 100 hereinafter.

4 is a flowchart illustrating a method for determining a therapeutic dose of a radiopharmaceutical for treatment based on an image according to the present invention.

First, the treatment dose determination system 100 obtains a diagnostic medical image for diagnosis after injecting a diagnostic radiopharmaceutical to a patient (S100).

The treatment dose determination system 100 obtains a diagnostic distribution curve representing the radiation dose over time for each organ of the human body from the acquired diagnostic medical image (S200).

Then, the therapeutic dose determination system 100 corrects the diagnostic distribution curve by using a correction coefficient for the rate of change at which the distribution curve changes when the radiopharmaceutical for diagnosis is replaced with the radiopharmaceutical for treatment, and obtains a correction distribution curve ( S300). The therapeutic dose determination system 100 is a correction distribution obtained by correcting the diagnostic distribution curve using a known correction factor indicating the change relationship between the time-radiation dose distribution curve of the therapeutic radiopharmaceutical and the time-radiation dose distribution curve of the diagnostic radiopharmaceutical. By obtaining the curve, it is possible to calculate the time-radiation dose distribution curve of the actual therapeutic radiopharmaceutical to be injected into the patient from the time-radiation dose distribution curve of the diagnostic radiopharmaceutical.

On the other hand, the treatment dose determination system 100 acquires the influence coefficient for each organ, which is the effect of the injected radiopharmaceutical on each surrounding organ, from the diagnostic medical image (S400). As described above, the treatment dose determination system 100 determines the energy distribution for each area by performing a Monte Carlo simulation using spatial coordinates, voxel size, and density information defined for each area of the diagnostic medical image as input data. obtained, and using the energy distribution, an influence coefficient for each organ, which is an influence factor between each region, is obtained. In this case, a residual ratio may be further included as input data.

Then, the therapeutic dose determination system 100 calculates the absorbed dose of each organ from the correction distribution curve and the influence coefficient, and predicts and determines the calculated absorbed dose as the optimal therapeutic dose of the radiopharmaceutical for the treatment of the patient (S500) ). As described above, the treatment dose determination system 100 calculates the cumulative radiation dose from the area of the correction distribution curve, calculates the residual ratio, which is the ratio of the cumulative radiation dose to the initial dose of radiopharmaceuticals, and multiplies the residual ratio and the influence coefficient. The absorbed dose to each organ can be calculated.

On the other hand, when the above-described optimal therapeutic dose is determined, a therapeutic radiopharmaceutical equivalent to the optimal therapeutic dose may be injected into the patient.

When the radiopharmaceutical for treatment as much as the optimal treatment dose is injected into the patient, the treatment dose determination system 100 acquires a medical treatment image for the patient (S600), and from the treatment medical image, the radiation dose for each organ of the human body over time Obtaining a treatment distribution curve representing (S700).

As described above, the medical treatment image may be a dynamic medical image obtained by continuously collecting medical images for a long time, or may be a static medical image obtained by collecting medical images only for a specific time. When the medical treatment image is a static medical image, as described above, images before and after the shooting time from the static medical image obtained by the static medical image method using a deep learning network that learned a number of various dynamic treatment medical images through deep learning can be generated, and a treatment distribution curve can be obtained using the generated image and the static medical image.

When information on the treatment distribution curve is obtained, the treatment dose determination system 100 compares the correction distribution curve with the treatment distribution curve received from the treatment medical image processing unit 170 (S800), and according to the recording time of the treatment medical image The calibration distribution curve is recalibrated with the weighted average of the calibration distribution curve and the treatment distribution curve with the set weight.

When the recalibrated calibration distribution curve is obtained, the treatment dose determination system 100 recalculates the cumulative radiation dose from the area of the recalibrated calibration distribution curve, and calculates the residual ratio, which is the ratio of the cumulative radiation dose to the initial dose of the radiopharmaceutical. It is recalculated, and the absorbed dose to each organ is recalculated by multiplying the recalculated residual ratio and the influence coefficient. It goes without saying that the recalculated absorbed dose is recrystallized as the optimal treatment dose for the patient and can be used as the optimal treatment dose for radiation treatment in the future.

The invention may be practiced as a method, apparatus, system, or the like. The method of the present invention can also be implemented as a computer-readable program, code, application, software, etc. on a computer-readable recording medium. When implemented and executed as software or an application, the constituent means of the present invention are inevitably programs or code segments for executing necessary tasks. The program or code segments may be stored in a computer-readable recording medium or may be transmitted by a computer data signal coupled with a carrier wave in a transmission medium or a communication network.

The computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floppy disks. optical media), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. In addition, the computer-readable recording medium is distributed in a network-connected computer system so that the computer-readable code can be stored and executed in a distributed manner.

In the above, the present invention has been described with reference to the specific embodiments shown in the drawings, but since this is only an example, various modifications and variations will be possible therefrom by those of ordinary skill in the art to which the present invention pertains. Accordingly, the protection scope of the present invention should be interpreted by the claims described below, and all technical ideas within the equivalent and equivalent scope should be interpreted as being included in the protection scope of the present invention.

100: Therapeutic dose determination system
110: diagnostic medical image acquisition unit
120: diagnostic distribution curve acquisition unit
130: influence coefficient acquisition unit
140: diagnostic distribution curve correction unit
150: treatment dose prediction unit
160: prediction-result comparison unit
170: treatment medical image processing unit
171: treatment medical image acquisition unit
172: deep learning learning unit
173: treatment distribution curve acquisition unit

Claims (10)

A diagnostic medical image acquisition unit that acquires a diagnostic medical image for diagnosis after injecting a diagnostic radiopharmaceutical to a patient;
a diagnostic distribution curve obtaining unit for obtaining a diagnostic distribution curve representing the radiation dose over time for each organ of the human body from the diagnostic medical image;
a diagnostic distribution curve correction unit for obtaining a correction distribution curve obtained by correcting the diagnostic distribution curve by using a correction coefficient for a rate of change at which the distribution curve changes when a radiopharmaceutical for diagnosis is replaced with a radiopharmaceutical for treatment;
an influence coefficient acquisition unit for acquiring an influence coefficient for each organ, which is an effect of radiopharmaceuticals on each surrounding organ, from the diagnostic medical image; and
A therapeutic dose prediction unit that calculates the absorbed dose of each organ from the correction distribution curve and the influence coefficient, and determines the absorbed dose as an optimal therapeutic dose of the radiopharmaceutical for treatment for the patient;
The treatment dose prediction unit,
Calculate the cumulative radiation dose from the area of the correction distribution curve, calculate the residual ratio, which is the ratio of the cumulative radiation dose to the initial dose of radiopharmaceuticals, and multiply the residual ratio and the influence coefficient to obtain the absorbed dose for each organ An image-based therapeutic dose determination system for radiopharmaceuticals. delete According to claim 1, wherein the influence coefficient acquisition unit,
An image-based therapeutic radiopharmaceutical treatment dose determination system, characterized in that the effect coefficient for each organ is obtained through Monte Carlo simulation from the diagnostic medical image using predefined spatial coordinates, voxel size, and density information. The method of claim 1, wherein the system comprises:
a therapeutic medical image acquisition unit for acquiring a therapeutic medical image after injecting a therapeutic radiopharmaceutical to the patient as much as the optimal therapeutic dose; and
Image-based radiopharmaceutical treatment dose determination system for treatment, characterized in that it further comprises a treatment distribution curve obtaining unit for obtaining a treatment distribution curve representing the radiation dose over time for each organ of the human body from the treatment medical image. 5. The method of claim 4, wherein the system comprises:
Comparing the correction distribution curve and the treatment distribution curve, and re-calibrating the correction distribution curve with a weighted average of the correction distribution curve and the treatment distribution curve with a weight set according to the recording time of the treatment medical image, characterized in that, An image-based therapeutic dose determination system for radiopharmaceuticals. A method performed by a therapeutic radiopharmaceutical therapeutic dose determination system, the method comprising:
(a) obtaining a diagnostic medical image for diagnosis after injecting a diagnostic radiopharmaceutical into a patient;
(b) obtaining a diagnostic distribution curve representing the radiation dose with respect to time for each organ of the human body from the diagnostic medical image;
(c) obtaining a correction distribution curve obtained by correcting the diagnostic distribution curve by using a correction coefficient for a rate of change at which the distribution curve changes when a radiopharmaceutical for diagnosis is replaced with a radiopharmaceutical for treatment;
(d) obtaining an effect coefficient for each organ, which is the effect of radiopharmaceutical on each organ in the vicinity, from the diagnostic medical image; and
(e) calculating the absorbed dose of each organ from the correction distribution curve and the influence coefficient, and determining the absorbed dose as the optimal therapeutic dose of radiopharmaceuticals for treatment for the patient;
Step (e) is,
Calculate the cumulative radiation dose from the area of the correction distribution curve, calculate the residual ratio, which is the ratio of the cumulative radiation dose to the initial dose of radiopharmaceuticals, and multiply the residual ratio and the influence coefficient to obtain the absorbed dose to each organ A method for determining the therapeutic dose of radiopharmaceuticals for image-based therapy. delete The method of claim 6, wherein step (d) comprises:
An image-based method for determining the therapeutic dose of radiopharmaceuticals for treatment, characterized in that the effect coefficients for each organ are obtained through Monte Carlo simulation from the diagnostic medical image using predefined spatial coordinates, voxel size, and density information. According to claim 6, wherein the method, after step (e),
(f) acquiring a medical treatment image after injecting a therapeutic radiopharmaceutical to the patient as much as the optimal therapeutic dose; and
(g) image-based treatment radiopharmaceutical treatment dose determination method, characterized in that it further comprises the step of obtaining a treatment distribution curve representing the radiation dose with respect to time for each organ of the human body from the medical treatment image. 10. The method of claim 9, wherein the method comprises:
Comparing the correction distribution curve and the treatment distribution curve, and correcting the correction distribution curve with a weighted average of the correction distribution curve and the treatment distribution curve with a weight set according to the recording time of the treatment medical image A method for determining the therapeutic dose of radiopharmaceuticals for treatment based on image, characterized in that.

Images