Biomarker calculation apparatus, particle beam therapy system, and biomarker calculation method

Abstract

This biomarker calculation apparatus holds radiation treatment plan information, immune cell number information in which the effect of irradiation with radiation on the number of immune cells in a patient is recorded, and definition information of a prediction model for predicting the time course of the number of immune cells. The prediction model includes internal parameters related to physical characteristics of the patient. The biomarker calculation apparatus determines an internal parameter of the prediction model using the immune cell count information, predicts the time course of the number of immune cells in the patient associated with the radiation therapy using the radiation treatment plan information and the prediction model, and calculates a biomarker correlated with a prognosis on the basis of the result of the prediction.

Description

Biomarker calculation device, particle beam therapy system, and biomarker calculation method Incorporation by Reference

[0001] This application claims priority from Japanese Patent Application No. 2023-193129, filed on November 13, 2023, the contents of which are incorporated herein by reference.

[0002] The present invention relates to a technique for calculating biomarkers for evaluating the prognosis of radiation therapy.

[0003] Lymphocytes, including killer T cells and helper T cells, are responsible for the immune system of the human body and are known to be highly sensitive to radiation. Several reports have shown that patients who have undergone radiation therapy and whose blood lymphocyte count (absolute lymphocyte count: ALC) has a significant decrease have a poor prognosis (see, for example, Non-Patent Document 1).

[0004] These research results suggest that it may be possible to improve the therapeutic effect by formulating a radiation therapy plan that does not reduce ALC. Patent Document 1 discloses a treatment planning method that, with the aim of suppressing lymphocyte count reduction, defines the area that affects ALC due to radiation exposure as the lymphocyte-related organ at risk (LOAR) and imposes dose constraints on this area in the same way as other organs at risk (OAR) (see, for example, Patent Document 1).

[0005] Non-Patent Document 2 discloses a method for determining parameters such as radiation sensitivity and recovery rate of lymphocyte counts, which differ for each patient, using dose indices obtained by treatment planning, such as a dose-volume histogram (DVH), as input.

[0006] US Patent Application Publication No. 2023 / 0094681

[0007] Houat YE. Meta-analysis and Critical Review: Association Between Radio-induced Lymphopenia and Overall Survival in Solid Cancers. Advances in Radiation Oncology. Published online 2023.Jin JY, Mereniuk, et at., A framework for modeling radiation induced lymphopenia in radiotherapy. Radiother Oncol. 2020 Mar;144:105-113.

[0008] Because lymphocyte radiosensitivity varies from person to person, even when the radiation dose is the same, the degree of reduction in lymphocyte count (lymphocyte survival rate) varies. In other words, the LOAR dose constraints obtained in Patent Document 1 may not necessarily be optimal for individual patients. Therefore, radiation therapy that can adapt to individual differences in biological responses, such as lymphocyte radiosensitivity, is needed.

[0009] Furthermore, the technology of Patent Document 1 does not evaluate the extent to which the effect of suppressing the decrease in lymphocyte count affects the patient's prognosis, making it difficult for doctors to determine whether or not therapeutic intervention is necessary.

[0010] A representative example of the invention disclosed in the present application is as follows: A biomarker calculation device comprising an arithmetic unit and a storage device connected to the arithmetic unit, wherein the storage device stores radiation therapy planning information, immune cell count information recording the effect of radiation exposure on the patient's immune cell count, and definition information of a prediction model for predicting the time course of immune cell count, the prediction model including internal parameters related to the patient's physical characteristics, and the biomarker calculation device determines the internal parameters of the prediction model using the immune cell count information, predicts the time course of the patient's immune cell count following radiation therapy using the radiation therapy planning information and the prediction model, and calculates a biomarker correlated with prognosis based on the results of the prediction.

[0011] According to the present invention, it is possible to present biomarkers that are correlated with patient prognosis as information for determining whether or not therapeutic intervention is necessary. Objects, configurations, and effects other than those described above will become apparent from the following description of the examples.

[0012] Fig. 1 is a diagram showing an example of the configuration of a particle therapy system according to Example 1. Fig. 2 is a diagram showing an example of the configuration of a biomarker calculation device according to Example 1. Fig. 3 is a flowchart illustrating an example of biomarker calculation processing executed by the biomarker calculation device according to Example 1. Fig. 4 shows an example of a prediction model used by the biomarker calculation device according to Example 1. Fig. 5 is a diagram showing a prediction result of the time transition of lymphocyte count output by the biomarker calculation device according to Example 1. Fig. 6 is a diagram showing an example of a processing result of the biomarker calculation device according to Example 1. Fig. 7 is a diagram showing an example of a screen displayed by the biomarker calculation device according to Example 1 via a display device.

[0013] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the present invention should not be construed as being limited to the description of the embodiments shown below. Those skilled in the art will readily understand that the specific configuration can be modified within the scope of the concept and spirit of the present invention.

[0014] In the configuration of the invention described below, the same or similar configurations or functions are denoted by the same reference numerals, and redundant explanations will be omitted.

[0015] In this specification, the terms "first," "second," "third," etc. are used to identify components and do not necessarily limit the number or order.

[0016] To facilitate understanding of the invention, the position, size, shape, range, etc. of each component shown in the drawings etc. may not represent the actual position, size, shape, range, etc. Therefore, the present invention is not limited to the position, size, shape, range, etc. disclosed in the drawings etc.

[0017] FIG. 1 is a diagram showing an example of the configuration of a particle beam therapy system 10 according to a first embodiment.

[0018] 1, a particle beam therapy system 10 is a system for performing therapy using particle beams. The particle beams may be, for example, heavy particle beams such as carbon beams or proton beams. Note that the present invention is not limited to the type of particle beam used.

[0019] The particle beam therapy system 10 includes a particle beam therapy device 100, a treatment planning device 110, a biomarker calculation device 120, an inspection device 130, and a display device 140. Each device is connected via a network 150 such as a wide area network (WAN) or a local area network (LAN). The network 150 may be connected via either a wired or wireless method. Note that the method of connection of each device is not limited to a network.

[0020] The testing device 130 is a device for testing the physical condition of the patient 11, such as the number of immune cells. The test is performed at any timing. The testing device 130 of Example 1 measures the number of lymphocytes contained in blood collected from the patient 11. The testing device 130 manages the test results as lymphocyte count information 221 (see FIG. 2). The test is performed multiple times, and the lymphocyte count information 221 stores multiple pieces of test data including the test results and the test dates and times. The testing device 130 that measures lymphocytes as immune cells may be, for example, an electrical resistance blood cell counter.

[0021] The present invention is not limited to lymphocyte count, and may also use white blood cell count, neutrophil count, red blood cell count, or platelet count in the blood. These cells, like lymphocytes, are known to decrease with radiation exposure. Furthermore, a significant decrease in neutrophil counts during radiation therapy increases the risk of infection, which may lead to treatment interruption and is related to the patient's prognosis. The testing device 130 may also test multiple immune cells.

[0022] The treatment planning device 110 is a device for setting a radiation therapy plan for the patient 11 using the particle beam therapy device 100. The treatment planning device 110 manages the set radiation therapy plan as radiation therapy plan information 220 (see FIG. 2 ). The biomarker calculation device 120 calculates biomarkers correlated with prognosis using information related to the physical condition of the patient 11 following treatment. The display device 140 displays various types of information.

[0023] The particle beam therapy system 100 irradiates particle beams to an affected area 12 of a patient 11 in accordance with a radiation therapy plan. The particle beam therapy system 100 is composed of an accelerator 101, a beam transport system 102, a particle beam irradiation system 103, and a treatment table 104.

[0024] The treatment table 104 is a table on which the patient 11 is placed, and can move the affected area 12 of the patient 11 to a predetermined position. The accelerator 101 accelerates charged particles and emits them as a particle beam (charged particle beam). The type of the accelerator 101 is not particularly limited, but may be, for example, a synchrotron accelerator, a cyclotron accelerator, or a synchrocyclotron accelerator. The beam transport device 102 transports the particle beam emitted from the accelerator 101 to the particle beam irradiation device 103.

[0025] The particle beam irradiation device 103 irradiates the particle beam transported by the beam transport device 102 onto the affected area 12 of the patient 11 placed on the treatment couch 104. The particle beam irradiation device 103 includes, for example, two pairs of scanning electromagnets, a dose monitor, and a position monitor (all not shown). The two pairs of scanning electromagnets are installed in directions perpendicular to each other and deflect the particle beam so that the particle beam reaches a desired position in a plane perpendicular to the beam axis of the particle beam at the position of the affected area 12. The dose monitor measures the amount of the irradiated particle beam. The position monitor detects the position through which the particle beam has passed.

[0026] The method of particle beam irradiation by the particle beam irradiation device 103 is not particularly limited. For example, a scanning method or a line scanning method can be used, in which a dose distribution formed by thin particle beams is aligned to irradiate the affected area 12 with a dose distribution that matches the shape of the affected area 12. The irradiation method may be a wobbler method, a double scatterer method in which the particle beam distribution is expanded and then a collimator is used, or a bolus method in which a dose distribution that matches the shape of the affected area 12 is used.

[0027] 1 is merely an example and is not intended to be limiting. For example, the particle therapy system 10 may be configured with only the particle therapy device 100, the biomarker calculation device 120, and the display device 140.

[0028] FIG. 2 is a diagram illustrating an example of the configuration of the biomarker calculation device 120 according to the first embodiment.

[0029] The biomarker calculation device 120 includes an arithmetic unit 200, a storage unit 201, a communication unit 202, an input unit 203, and a display unit 204. The hardware elements are connected via an internal bus 205.

[0030] The arithmetic device 200 is, for example, a processor, and executes various calculations. The arithmetic device 200 operates as a functional unit (module) that realizes a specific function by executing processing in accordance with a program stored in the storage device 201. In the following description, when a process is described using a functional unit as the subject, it indicates that the arithmetic device 200 is executing a program that realizes the functional unit. In this embodiment, the arithmetic device 200 functions as a lymphocyte count prediction unit 210 and a biomarker calculation unit 211.

[0031] The storage device 201 is a semiconductor storage device such as a RAM (Random Access Memory) and a ROM (Read Only Memory), and stores various information and programs executed by the arithmetic device 200. The storage device 201 of the first embodiment stores radiation therapy planning information 220 managed by the treatment planning device 110, lymphocyte count information 221 managed by the inspection device 130, and prediction model information 222. The prediction model information 222 is information for managing a prediction model for predicting the time transition of lymphocyte count. The prediction model will be described later.

[0032] The biomarker calculation device 120 may have a magnetic storage medium such as a hard disk drive (HDD) or a semiconductor storage medium such as a solid state drive (SSD). The programs and information stored in the storage device 201 may be installed from an optical disk such as a digital versatile disk (DVD), a USB memory, or via a network.

[0033] The communication device 202 is a device for communicating with external devices via a network. The input device 203 is a device for receiving various information from an operator, such as a mouse and keyboard. The display device 204 is a device for displaying various information, such as a display.

[0034] The lymphocyte count prediction unit 210 predicts the time course of the lymphocyte count of the patient 11 due to radiation therapy using radiation therapy plan information 220, lymphocyte count information 221, and prediction model information 222 stored in the memory device 201, and stores the prediction results in the memory device 201.

[0035] The biomarker calculation unit 211 uses the prediction results stored in the storage device 201 to calculate biomarkers that are correlated with the prognosis of the patient 11 and stores the calculated biomarkers in the storage device 201 .

[0036] The functional units of the biomarker calculation device 120 may be configured such that multiple functional units are combined into one functional unit, or one functional unit is divided into multiple functional units.

[0037] The functional units may be realized using a virtual computer, a computer system, or dedicated circuits such as a field-programmable gate array (FPGA) and an application-specific integrated circuit (ASIC).

[0038] Next, the operation and processing of the particle beam therapy system 10 will be described.

[0039] First, the operator creates a radiation therapy plan using the treatment planning system 110. The radiation therapy plan is created, for example, as follows.

[0040] First, the operator operates the treatment planning device 110 to set a region of interest (ROI), i.e., a target region (e.g., a tumor) to be irradiated with radiation, and an exclusion region (OAR) to avoid irradiation with radiation, in three-dimensional data of the patient 11 generated using CT images of the patient 11 or the like.

[0041] Next, the operator operates the treatment planning system 110 to set a dose constraint for the ROI. The dose constraint is, for example, a target dose D （ｊ） _Target, OAR maximum dose D （ｊ） The operator also assigns weights w （ｊ） _Traget, w （ｊ） Set _(OAR-D_max).

[0042] Here, the subscript j represents an identification number when there are two or more targets and two or more OARs. Next, the treatment planning system 110 determines the radiation dose that minimizes the objective function number F(x) shown in equation (1). Here, x is a parameter to be optimized, and is a vector whose elements are the radiation dose. Note that the arrow of x is omitted due to notation constraints.

[0043]

[0044] The subscript i indicates the number of the voxel included in each ROI. d_(i, j) is the dose of the i-th voxel. The function θ(x) is a step function, which is 1 if x is positive and 0 otherwise.

[0045] The method for formulating radiation therapy planning information is not limited to the above-described method.

[0046] FIG. 3 is a flowchart illustrating an example of a biomarker calculation process executed by the biomarker calculation device 120 according to the first embodiment.

[0047] After radiation therapy has started in accordance with the radiation therapy planning information 220, the operator instructs the biomarker calculation device 120 to execute processing. It is assumed that during radiation therapy, the number of lymphocytes contained in the blood of the patient 11 is examined by the examination device 130 at any timing.

[0048] The biomarker calculation device 120 acquires the radiation therapy planning information 220 and the lymphocyte count information 221 and stores them in the storage device 201 (step S301).

[0049] Next, the biomarker calculation device 120 constructs a prediction model using the lymphocyte count information 221 and the prediction model information 222 (step S302).

[0050] As a prediction model for predicting the time course of lymphocyte counts, for example, the compartment model described in Non-Patent Document 2 can be used.

[0051] Lymphocytes are abundant in organs such as the bone marrow, spleen, and lymph nodes, and are further supplied to the entire body through the blood circulation. In the compartment model, the circulation of lymphocytes between these organs is divided into areas called compartments, and modeled as the exchange of lymphocytes between compartments. The compartment model can further model the decrease in lymphocyte numbers according to the radiation dose irradiated to each compartment, and the decrease in lymphocytes due to circulation throughout the body.

[0052] FIG. 4 shows an example of a prediction model used by the biomarker calculation device 120 of the first embodiment.

[0053] The prediction model shown in Figure 4 consists of five compartments: bone marrow, spleen, lymph nodes, lungs, and other organs, and circulating blood connecting each compartment. Each compartment is divided into a non-circulating component that continuously retains lymphocytes, and a circulating component that exchanges lymphocytes through the circulating blood. Lymphocytes are constantly produced in the bone marrow, spleen, and lymph nodes. On the other hand, lymphocytes are consumed in the lungs and other organs. The lightning bolt symbol represents particle beam irradiation.

[0054] Internal parameters such as the number and circulation rate of lymphocytes contained in each compartment can be determined from literature values ​​or from equilibrium conditions that do not change when radiation is not irradiated. Furthermore, the number of lymphocytes contained in each compartment is reduced according to the dose value of each compartment. A linear model or a linear-quadratic model can be used to determine the amount of lymphocyte reduction. The prediction model includes internal parameters related to the physical characteristics of the patient 11, which reflect the characteristics of the patient 11 regarding the amount of reduction in lymphocyte count due to radiation exposure. Specifically, the prediction model includes an internal parameter representing the radiosensitivity of lymphocytes (the survival rate of lymphocytes per unit radiation dose). The lymphocyte production rate (recovery rate) in the bone marrow, spleen, etc. may also be included as an internal parameter.

[0055] The prediction model is not limited to the compartment model shown in Fig. 4. For example, a model in which the blood dose is calculated from the radiation therapy planning information 220 and the lymphocyte count decreases accordingly may be used. This prediction model also includes internal parameters that reflect the characteristics of the decrease in lymphocyte count due to radiation exposure in the patient 11.

[0056] Here, a method for determining the internal parameters for reflecting the characteristics of the patient 11 in terms of the amount of decrease in lymphocyte count due to radiation exposure will be described.

[0057] (Step 1) The biomarker calculation device 120 sets initial values ​​for the internal parameters. The initial values ​​may be set randomly or may be set in advance.

[0058] (Step 2) The biomarker calculation device 120 acquires test data indicating the number of lymphocytes contained in non-irradiated blood (first test data) and data indicating the number of lymphocytes contained in irradiated blood (second test data) from the lymphocyte count information 221. The lymphocyte count information 221 may include one piece of first test data and one or more pieces of second test data.

[0059] (Step 3) The biomarker calculation device 120 updates the internal parameters so as to minimize the error between the lymphocyte count at the date and time corresponding to the first test data and the second test data in the time progression of the lymphocyte count output by the prediction model and the lymphocyte count contained in the first test data and the second test data.

[0060] The biomarker calculation device 120 repeatedly executes steps 2 and 3 until the error becomes smaller than a predetermined value.

[0061] Note that test results during treatment do not necessarily have to be used. For example, the results of a radiation irradiation test using blood collected from the patient 11 before treatment may be used. Specifically, by measuring the change in lymphocyte count while changing the dose irradiated to the blood, the relationship between the decrease in lymphocyte count and the radiation dose can be evaluated, and the radiosensitivity of lymphocytes can be determined. The lymphocyte recovery rate may be a statistical value (e.g., average value) obtained by statistically processing past test data, or a literature value. Note that the internal parameters may be input by the operator.

[0062] Next, the biomarker calculation device 120 predicts the time course of the lymphocyte count using the radiation therapy planning information 220 and the prediction model (step S303).

[0063] Next, the biomarker calculation device 120 calculates biomarkers correlated with the prognosis of the patient 11 using the predicted results of the time transition of the lymphocyte count (step S304).

[0064] Various biomarkers are conceivable. For example, the minimum lymphocyte count during treatment could be used as a biomarker. Alternatively, the number of days during which the lymphocyte count is lower than a preset threshold could be used as a biomarker. In the present invention, any biomarker can be calculated using the predicted results of the time course of lymphocyte count.

[0065] The biomarker calculation device 120 displays the biomarker calculation results on the display device 140 (step S305).

[0066] FIG. 5 is a diagram showing the predicted results of the time transition of lymphocyte counts output by the biomarker calculation device 120 of the first embodiment.

[0067] 5 shows the output of a prediction model in which internal parameters were determined using four measurement data included in a period 501. Note that period 501 is the period from the start date of treatment (day 0) to the 23rd day. Graph 502 shows the time progression of the lymphocyte count generated from the measurement data. Graph 503 shows the time progression of the prediction model output by the prediction model.

[0068] FIG. 6 is a diagram showing an example of a processing result of the biomarker calculation device 120 according to the first embodiment.

[0069] FIG. 6 shows the results of biomarker calculations when the present invention was applied to 40 cases of patients with lung cancer who underwent chemoradiotherapy.

[0070] In this example, the biomarker calculated is whether the number of days the lymphocyte count (ALC) reaches 500 counts / μL is 16 days or more. This is because previous research results confirmed that when the number of days the lymphocyte count (ALC) reaches 500 counts / μL is less than 16 days, the prognosis is good, and when the number of days the lymphocyte count (ALC) reaches 500 counts / μL is 16 days or more, the prognosis tends to be poor.

[0071] When the biomarkers calculated by the biomarker calculation device 120 were compared with the biomarkers calculated from blood tests, it was possible to predict whether the number of days until the lymphocyte count (ALC) reached 500 counts / μL would be 16 days or more in 32 of the 40 cases.

[0072] In this example, the internal parameters were determined using lymphocyte count test data obtained at four points during the early stages of treatment, meaning that the patient's prognosis can be predicted with an 80% accuracy rate at about halfway through the entire treatment course, which takes 40-50 days. Based on the calculation results, doctors can determine whether or not they need to take measures, such as modifying the treatment plan.

[0073] FIG. 7 is a diagram showing an example of a screen displayed by the biomarker calculation device 120 of the first embodiment via the display device 140. As shown in FIG.

[0074] The screen 700 displays the predicted results of the time transition of lymphocyte counts and the calculated results of biomarkers.

[0075] The predicted results of the time course of lymphocyte counts are displayed, for example, as a graph with the horizontal axis representing the number of days elapsed since the start of radiation therapy and the vertical axis representing the lymphocyte count. The graph may also be displayed with the actual values ​​used to determine the internal parameters superimposed. When the number of days until the lymphocyte count falls below a threshold is used as a biomarker, the number of days is displayed on screen 700.

[0076] Note that the screen 700 may also display preset threshold values ​​and reference values ​​for determining whether the prognosis is good or bad.

[0077] By referring to the screen 700, the operator can confirm the predicted prognosis of the patient 11 as visual information, thereby assisting the doctor in determining whether or not treatment intervention is necessary.

[0078] The present invention is not limited to the above-described embodiments, but includes various modifications. For example, the above-described embodiments are provided to explain the present invention in detail, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, some of the configurations of each embodiment can be added to, deleted from, or replaced with other configurations.

[0079] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The present invention can also be realized by software program code that implements the functions of the embodiments. In this case, a storage medium on which the program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiments, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media for providing such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, solid-state drives (SSDs), optical disks, magneto-optical disks, CD-Rs, magnetic tape, non-volatile memory cards, and ROMs.

[0080] Furthermore, the program code that realizes the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, perl, Shell, PHP, Python, and Java.

[0081] Furthermore, the program code of the software that realizes the functions of the embodiments may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the processor of the computer may read and execute the program code stored in the storage means or the storage medium.

[0082] In the above-described embodiment, the control lines and information lines are those that are considered necessary for the explanation, and not all control lines and information lines are necessarily shown in the product. All components may be interconnected.

Claims

1. A biomarker calculation device comprising an arithmetic unit and a storage device connected to the arithmetic unit, the storage device storing radiation therapy planning information, immune cell count information recording the effect of radiation exposure on the number of immune cells of a patient, and definition information of a prediction model for predicting the time course of the number of immune cells, the prediction model including internal parameters related to physical characteristics of the patient, the biomarker calculation device determining the internal parameters of the prediction model using the immune cell count information, predicting the time course of the number of immune cells of the patient associated with radiation therapy using the radiation therapy planning information and the prediction model, and calculating a biomarker correlated with prognosis based on the result of the prediction.

2. A biomarker calculation device as described in claim 1, characterized in that the internal parameters include a parameter related to radiation sensitivity that represents the survival rate of the immune cells relative to the radiation exposure dose.

3. A biomarker calculation device according to claim 2, characterized in that the internal parameters include a parameter relating to a generation rate of the immune cells.

4. A biomarker calculation device as described in claim 2, characterized in that the immune cell count information includes test data including the number of at least one of lymphocytes, white blood cells, neutrophils, red blood cells, and platelets contained in the blood, and the test date and time.

5. A biomarker calculation device according to claim 1, characterized in that it provides an interface for presenting the results of the prediction and the calculated biomarkers.

6. A particle beam therapy system comprising: a particle beam therapy device for irradiating a patient with radiation; a biomarker calculation device; and a display device, wherein the biomarker calculation device holds radiation therapy planning information, immune cell count information recording the effect of radiation irradiation on the number of immune cells of the patient, and definition information of a prediction model for predicting the time course of the number of immune cells, the prediction model including internal parameters related to physical characteristics of the patient, the biomarker calculation device determines the internal parameters of the prediction model using the immune cell count information, predicts the time course of the number of immune cells of the patient associated with radiation therapy using the radiation therapy planning information and the prediction model, and calculates a biomarker correlated with prognosis based on the result of the prediction, and the display device displays the calculation results of the biomarker.

7. A biomarker calculation method executed by a biomarker calculation device, the biomarker calculation device having an arithmetic unit and a storage device connected to the arithmetic unit, the storage device storing radiation therapy planning information, immune cell count information recording the effect of radiation exposure on the number of immune cells of a patient, and definition information of a prediction model for predicting the time course of the number of immune cells, the prediction model including internal parameters related to physical characteristics of the patient, the biomarker calculation method comprising the steps of: determining the internal parameters of the prediction model by the biomarker calculation device using the immune cell count information; predicting the time course of the number of immune cells of the patient associated with radiation therapy by using the radiation therapy planning information and the prediction model; and calculating a biomarker correlated with prognosis based on the result of the prediction.

8. A biomarker calculation method as described in claim 7, characterized in that the internal parameters include a parameter relating to radiation sensitivity that represents the survival rate of the immune cells relative to the radiation exposure dose.

9. A biomarker calculation method according to claim 8, characterized in that the internal parameters include a parameter relating to the generation rate of the immune cells.

10. A biomarker calculation method as described in claim 8, characterized in that the immune cell count information includes test data including the number of at least one of lymphocytes, white blood cells, neutrophils, red blood cells, and platelets contained in the blood, and the test date and time.

11. A biomarker calculation method as claimed in claim 7, characterized in that the biomarker calculation device includes a step of presenting the results of the prediction and the calculated biomarkers.

Images