JP2011172821A - Device and method for radiation-therapy planning - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a radiation-therapy planning device for efficiently performing the radiation therapy. <P>SOLUTION: The device includes: first to seventh memory parts which respectively store planning information, therapy process information, calendar information for each of the therapy processes, restriction information of the therapy process, protocol information, patient information and pattern information; a first schedule-making part which makes a schedule of the therapy process of a base point according to information of the first to fourth memory parts; a second schedule-making part which makes a schedule of the therapy processes other than the base point until a start date of irradiation according to the information of the first to fourth memory parts and the schedule of the therapy process of the base point; a pattern initial-solution generating part which generates an initial solution of an allocation pattern according to information of the fifth to seventh memory parts; a pattern-evaluating part which calculates an evaluated value of the pattern based on the information of the first to seventh memory parts; a pattern-improving part which improves the allocation pattern by using the evaluated value; a third schedule-making part which makes a schedule after the second day of the irradiation according to the information of the first to seventh memory parts and the improved pattern; and a display part which displays the therapy schedule. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention is intended to automatically plan a treatment schedule that is easy for the operator to understand when performing radiation therapy such as particle beam therapy, the daily work amount is as constant as possible, and can treat as many patients as possible. It relates to radiation therapy planning.

  Radiation therapy is an advanced medical treatment for cancer. Surgery is unnecessary and the burden on the patient is low. This treatment starts from reception of a new patient, and as shown in FIG. 3, outpatient examination adaptation judgment, treatment policy decision, fixing device creation, CT simulation, detailed treatment plan, case study meeting, compensation filter, new patient measurement, There are many steps from rehearsal to treatment irradiation. As the number of patients increases, it has become necessary to efficiently plan in advance how many patients can be treated. Conventionally, an annual frame (a table like Excel) is created manually based on the facility capacity and the proportion of treatment protocol (site) in advance, and each time a new patient enters, the frame corresponding to the patient's treatment protocol is assigned to the doctor. Will fill up. The annual number of patients can be determined by creating an annual treatment window.

  Effective use of radiation therapy equipment is indispensable because the equipment costs (construction and operation costs) are high. In addition, it is becoming necessary to treat as many patients as possible in society.

  A patient's treatment schedule depends on the treatment protocol. There are 20 or more types of treatment protocols in which the number of times of irradiation is determined depending on the treatment site and situation. Hereinafter, it is referred to as a protocol. In radiotherapy, the number of times of irradiation is determined by the protocol, and the treatment is in line with the determined process. In addition, if the treatment is interrupted halfway and the sun is released, the effect of the treatment will change, so it is necessary to create a schedule to prevent this from happening. Among radiotherapy, in particular, particle beam therapy has a long irradiation period of about 20 days and requires long-term scheduling.

  Because of these characteristics, when treatment is started in the order of acceptance of patients accepted as in the current hospital system, extremely crowded days occur or the number of patients exceeding the capacity of the hospital is reserved. Even if it is done, it may not be understood, or the schedule may be ignored ignoring restrictions in the treatment process. Irradiation machines are very expensive and take time to build, so they cannot be increased or decreased suddenly. Some scheduling is required to ensure that as many patients as possible can be treated without exceeding the number of patients that can be worked in the hospital.

  In the case of radiotherapy, unlike general treatment, there is no need to change the treatment method and treatment period according to the condition and progress of each patient. It is done. Therefore, if it is assumed that the frequency of visiting patients and the proportion of the protocol of the patients can be predicted, it is possible to prepare a schedule in advance.

  On the other hand, if the work to be performed every day is different for a medical staff who performs medical work, the staff must check the work of the day, so that mistakes are likely to occur and become a burden. Although it is sufficient to create a rule that determines the work to be performed on the day of the week, this method makes it difficult to create a treatment frame suitable for holidays, maintenance, and an exceptional calendar unique to hospitals. Also, some treatment protocols are infrequent and may be entered every few weeks. For these reasons, scheduling cannot be performed well just by deciding the work to be performed on each day of the week. Furthermore, it is desirable that the number of patients on a daily basis be as constant as possible in order to perform stable operations.

  The hospital information system that has already been introduced mainly manages the results of examinations and treatments performed on patients using electronic medical records, and is designed to create a detailed treatment plan over a long period of several months. Not. In addition, a system that manages a series of inspection flows, such as a health checkup system, has a short planning period of 1 or 2 days, and schedules each person just by managing the flow so that the order is not mistaken. There is no need. In addition, there is an existing scheduling system, but there are few systems (Patent Document 1) that can automatically plan long-term (annual, half-year) plans at the same time in radiotherapy planning, and the scheduling method created from the viewpoint that it is easy for the staff to understand not exist.

Japanese Patent Application No. 2009-212190 JP 2000-222507 A Japanese Patent Laid-Open No. 11-253565

Sato et al., “Radiotherapy device scheduling system based on two-step method using genetic algorithm”, IEICE D-1 Vo. J83-D-1, no. 10, PP1033-1042, October 2000

  As described above, conventionally, planning related to radiation therapy is not handled by hospital information systems and health checkup systems, and relies on human hands with experience and trial and error of doctors.

  With regard to long-term planning, the existing scheduling method changed the work to be performed every day and burdened the staff, so there was a problem of making a plan easy for the staff to understand. In addition, there is a problem of minimizing the need to manually change the created schedule by automatically creating a schedule corresponding to an exceptional calendar such as holidays and maintenance. In addition, there was a problem of reducing the increase or decrease in the number of patients every day as much as possible.

  The present invention relates to a pattern generation apparatus characterized in that the same protocol is assigned as much as possible on the same day of the week and the number of patients on each day is as constant as possible with respect to the problem of automatic generation of a schedule in radiotherapy scheduling And a radiotherapy planning device that has the ability to create schedules that feature day-of-the-week shifts even if there is an exceptional schedule, making it easier for staff to understand and making daily work as constant as possible And to provide a method.

  One aspect of the present invention is a radiotherapy planning apparatus that creates a long-term treatment frame for radiotherapy, and includes a first storage unit that stores planning information in which a planning period is set, a base treatment process, and other A second storage unit that stores treatment process information that defines a treatment process; a third storage unit that stores calendar information of each treatment process that defines a calendar of possible dates in the planning period of each treatment process; and each treatment A fourth storage unit for storing constraint information of a treatment process that stores constraints on irradiation dates and irradiation, and a fifth storage unit for storing protocol information that defines a treatment protocol indicating a treatment site and the number of treatments; A sixth storage unit for storing patient information defining the ratio of the number of patients for each treatment protocol, and an assigned pattern for assigning the treatment protocol A seventh storage unit that stores pattern information that defines a repetition period of the first and a first schedule generation unit that reads each piece of information from the first to fourth storage devices and creates a schedule for a treatment process that serves as a base point; Then, each information is read from the first to fourth storage units, and based on the read information and the generated treatment process schedule as a base point, a treatment process schedule up to the irradiation start date is created for treatment processes other than the base point Each of the second schedule creation unit, the pattern initial solution generation unit that reads each information from the fifth to seventh storage units and generates an initial solution of the allocation pattern, and the first to seventh storage units. When the information is read and the pattern improvement unit gives a predetermined allocation pattern, the pattern evaluation unit that calculates the evaluation value of the pattern based on the read information; and the pattern The pattern initial solution generated by the pattern initial solution generation unit and each information are read from the first to seventh storage units, and the allocation pattern is determined by optimization using the evaluation value calculated by the pattern evaluation unit. Read the information from the pattern improvement unit to be improved and the storage units 1 to 7, and create a schedule for the second and subsequent days of irradiation based on the read information and the pattern improved by the pattern improvement unit Provided is a radiation treatment planning apparatus comprising a schedule creation unit, a schedule storage unit for storing the created radiation treatment schedule, and a schedule display unit for displaying the radiation treatment schedule.

  It is possible to create a plan that allows the staff to easily understand the daily work at high speed and high density for the annual treatment frame. It is possible to generate a frame in which there is no variation in the proportion of treatment protocols and the variation in the number of patients on a daily basis is minimized.

  Only the base treatment process is set, the number of people to be performed per day, the ratio of the protocol, the number of days between the treatment start process and other treatment processes, and the calendar of each treatment process are given, and the schedule is automatically generated. The Even if there are exceptional schedules such as holidays and maintenance, a schedule that does not shift the day of the week can be created.

  By optimization, a protocol that is performed a plurality of times within the repetition period is preferably performed on the same day of the week, and may be biweekly. In addition, the number of patients treated every day should be as constant as possible. The repetitive pattern can be created automatically by designating a part (or all) of the repetitive pattern.

  In addition, it is possible to estimate the number of patients that can be treated annually and to analyze the facility capacity of where the bottleneck is in terms of facilities and resources, and to support the efficient operation of expensive treatment equipment, and also to support the hospital side. It is also effective from a macro perspective as a country in which it exists.

1 is a block diagram of a radiation therapy planning apparatus according to a first embodiment of the present invention. It is a flowchart which shows the flow of a process of the radiotherapy planning apparatus of FIG. It is a figure which shows the process of radiation therapy. It is a flowchart of initial solution generation. It is a flowchart which performs a neighborhood search as an example of the optimization performed with a pattern production apparatus. It is a flowchart of closed frame generation. It is a figure which shows the planning information memorize | stored in the planning information storage device. It is a figure which shows the treatment process information memorize | stored in the treatment process information storage device. It is a figure which shows the scheduling rule memorize | stored in the scheduling rule information storage apparatus. It is a figure which shows the pattern information memorize | stored in the pattern information storage device. It is a figure which shows the protocol and patient information which are memorize | stored in the protocol information storage apparatus. It is a figure which shows the initial allocation information memorize | stored in the initial allocation information storage device by a user. It is a figure which shows the setting of the closed frame memorize | stored in the closed frame setting information storage apparatus. It is a figure which shows the calendar | calendar of each treatment process memorize | stored in the calendar storage apparatus of each treatment process. It is a figure which shows the reliable number of persons in the treatment process of a reference point. It is a figure which shows the example of an allocation pattern. It is a figure which shows the schedule result of the treatment process used as a reference point. It is a figure which shows the scheduling result to an irradiation start date. It is a figure which shows the final scheduling result. It is a figure which shows the example of data in which the upper limit of the number of persons who can work on each day is defined in the irradiation treatment process. It is a flowchart in case the upper limit of the number of people who can work on each day other than the standard treatment process is defined.

(First embodiment)
With reference to FIG. 1, a radiation treatment planning apparatus when there is no initial assignment by a user and a closed frame is not generated will be described as a first embodiment. As shown in FIG. 1, the radiation treatment planning apparatus stores planning information for storing planning information in which a period for which treatment is planned, that is, a planning period (for example, one year, six months, 140 days in the present embodiment) is set. Part 11 and the base treatment process (for example, the fixing device creation process in the treatment process of FIG. 3) and other treatment processes (CT simulation, detailed treatment plan, case study meeting, compensation filter, new patient measurement in FIG. 3) Treatment process information storage unit 12 for storing treatment process information defining each process, rehearsal and treatment irradiation), and a calendar for storing calendar information of each treatment process defining a calendar of possible days in the planning period of each treatment process Stores information storage unit 13 and constraint information on treatment steps for storing constraints on dates and irradiation between treatment steps. Constraint information storage unit 14 is provided that. These four storage units 11 to 14 are connected to the schedule creation module 15.

  The schedule creation module 15 creates only the schedule of the treatment process as the base point, creates a schedule 17 for the treatment process as the base point, and creates a schedule of the treatment process up to the irradiation start date other than the base point. The treatment process schedule creation unit 18 and the pattern created by the pattern creation module 16 are used as inputs to create a schedule for the second and subsequent irradiation days, and a schedule creation unit 19 for the second and subsequent days of irradiation. The pattern creation module 16 includes a pattern initial solution generation unit 20 that generates an initial solution of an assigned pattern, a pattern improvement unit 21 that optimizes a pattern, and a pattern evaluation unit 22 that evaluates a pattern given from the pattern improvement unit. An allocation pattern as shown in FIG. 16 is generated by optimization. The allocation pattern is a table that defines on which day the treatment process serving as the base point of each protocol is performed within a predetermined repetition period (for example, the repetition period shown in FIG. 10), and an example is shown in FIG. . The treatment process as a base point is performed for a predetermined number of people on the day when the work can be performed on the calendar (schedule) of each treatment process. The assignment pattern indicates that each protocol assigns the number of people in the repetition period to any day in the repetition period. In the assignment pattern shown in FIG. 16, two weeks are taken, and there is a second time of the start of month 1 and the second time of month 2, and it is shown which protocol is assigned in the assignment of two weeks. For example, if the head 16 is given on the month 1, the protocol for the head 16 can be assigned if the starting treatment process is started on the first week of Monday. Therefore, the treatment process that is the base point is started on Monday, and irradiation is started after the number of days that are freed up while being designated by the constraint information storage unit 14 that stores the constraint information of the treatment process. Done.

  Moreover, the patient information which stores the protocol information storage part 23 which stores the protocol information which prescribed | regulated the treatment protocol which shows the treatment site | part and the frequency | count of irradiation as shown in FIG. 11, and the ratio of the number of patients of each protocol. A storage unit 24; a pattern information storage unit 25 that stores pattern information that defines a repetition period of the allocation pattern; and an initial allocation information storage that stores initial allocation information by the user when the user designates partial allocation of the pattern. Part 26 is provided. These storage units 23 to 26 are connected to the schedule creation unit 19 on and after the second day of irradiation of the pattern creation module 16 and the schedule creation module 15. In addition, the ratio of the number of patients in each protocol may be manual or automatic, the ratio of patients who were treated by the previous year, the ratio of patients who were treated during the same period of the previous year, Or the ratio predicted from the data up to the previous year is used.

  In the pattern creation module 16, an initial pattern solution is generated from the information read from the storage units 23 to 26, and optimization is performed by the pattern improvement unit 21. The pattern evaluation unit 22 evaluates a pattern obtained during the optimization and calculates an evaluation value.

  The radiotherapy planning apparatus is further connected to a closed frame setting information storage unit 27 that stores closed frame setting information, the closed frame setting information storage unit 27, and a schedule creation unit 19 on and after the second day of irradiation. A closed frame schedule creation unit 28 for creating a frame schedule is provided. The closed frame schedule creation unit 28 is connected to the schedule display device 30 via the schedule storage unit 29.

  Below, the outline | summary of a process of the radiation planning apparatus of the said structure is demonstrated using the flowchart of FIG.

  First, the information in the storage units 11 to 13, that is, the planning information (FIG. 7), the treatment process information (FIG. 8), and the calendar information (FIG. 14) are read for the treatment process that is the base point, and the base point of the schedule creation device 15. The process schedule creation unit 17 creates a schedule (FIG. 17) of a treatment process as a base point (S12). In FIG. 14, a day that is 1 indicates a day on which the treatment process can be performed, and a day that is 0 indicates an impossible day. In this case, the treatment process which is the base point of each day is performed for the number of people given by the user on a workable day according to the calendar of the treatment process. That is, it is not performed on the day when the treatment process as the base point cannot be performed, and the corresponding treatment frame is not created. Therefore, when a schedule is generated for a certain allocation pattern, the protocol corresponding to the day when the treatment process as the base point cannot be performed is ignored, and the number of this frame is reduced.

  In the schedule creation, specifically, when the radiation therapy planning apparatus is started up, the user is prompted to read input data from the storage units 11 to 13 in the display device 30. The user performs, for example, a key operation in order to read information from the storage units 11 to 13 in accordance with a display instruction of the display device 30 (S11). The schedule creation unit 17 for the base treatment process creates a schedule for performing the base treatment process for the determined number of people based on the calendar (S12).

Next, the schedule creation unit 18 of the treatment process up to the base point of the schedule creation device 15 and the irradiation start date creates a base point and a schedule up to the start of irradiation (FIG. 18) (S13). In these processes (S13), since the date for performing the treatment process as the base point is fixed, the number of days left between the dates determined by the scheduling rule (FIG. 9) is left and the date for performing another treatment process. Decide.

  The day corresponding to Rule 1 indicates that there are more days that the treatment process p can be performed in this week than in a normal week, or a day when the treatment process serving as a base point is absent. Further, the day corresponding to Rule 3 indicates that there are few days on which the treatment process p can be performed in this week. In this case, a schedule for a plurality of days is scheduled for the day after the holiday so that the shift from the next week is not affected.

  Each frame of the schedule output by the schedule creation unit 18 of the treatment process up to the irradiation start date is in a state where the protocol to be performed in this frame is not fixed. Since the number of irradiations is determined when a protocol is assigned to each frame, a schedule for the second and subsequent irradiation days can be created. Therefore, radiotherapy schedule creation can be considered as a problem of assigning a predetermined number of protocols to this set of frames.

  When assigning a protocol, if the set of weeks in the repetition period is M, assigning the same protocol (number of irradiations) to the same period frame | M | You can create a treatment window. The period | M | is given in consideration of the number of types of protocols for creating a frame and the ratio of the number of patients for each protocol, and is stored in the pattern information storage unit 25.

| M | Since the same protocol is assigned every week, it is possible to create a frame that is evenly included in each protocol during the planning period. Assigning a protocol to any day in the repeat period means to create a schedule by assigning the same protocol to all frames of the same period. The allocation pattern (FIG. 16) is a pattern that defines this allocation method, and a schedule can be created when one allocation pattern is given. Therefore, it is possible to consider an optimization problem (minimization problem) having an objective function expressed by the following equation by expressing a solution with an allocation pattern.

Next, pattern initial solution generation performed by the pattern initial solution generation unit 20 will be described.
It is determined whether or not an initial assignment is specified after step S13 (S14). If this determination is Yes, initial allocation is set (S15), and pattern initial solution generation is performed (S16). If the determination is No, the pattern initial solution generation is performed directly.

In the initial solution generation, an executable solution is generated by a greedy method considering the objective functions of g ₂ (x) and g ₃ (x), and g ₁ (x) is not considered. g ₂ (x) is an objective function for assigning the same day of the week as much as possible even when the weeks are different, and g ₃ (x) is an objective function for assigning a protocol with a large number of people as evenly as possible on each day.

First, consider g ₃ (x). Hereinafter, let Z be a set of integers. When looking at patients in the repeat period with each protocol, the number of days in the repeat period | I | and the number of people in each protocol | P _k |

When real r _k is present as a, may to allocate equally in the repeating period assign at least r _k's or the patient's total daily in the repeating period. From _{this, | P k | ≧ | I} | about to become all of the protocol k, determine the r _k, assign each r _k people in all of the day during the period repetition of the patient's protocol k. Here, this step is referred to as a step of allocating each day during the repetition period.

Next, consider g ₂ (x). Let P ^* _{k be} the set of patients that have not yet been assigned in each protocol k. When looking at each protocol, the number of weeks in the repetition period | M | and the number of people who have not yet been assigned for each protocol | P ^* _k |

When the real number h _k is present to be, in order to assign as much as possible the same day of the week be different week, on the day of in the repeating period that it does not reach the assigned number of people, still allocation of protocol k on the same day of the week for all of the week By performing the operation of assigning undecided patients _hk times, the number of people assigned to the same day of the week can be increased. Considering to improve g ₃ (x), the days assigned from the first to the h _k times of assigning patients who have not yet been assigned to protocol k on the same day of every week are all different. However, the same protocol k is assigned as evenly as possible. In addition, since it is better to allocate as many as possible at the time of allocation, the day of the week to be allocated is determined using a random number. This step is expressed here as allocation to each week in the allocation period.

Finally, patients who have not yet been allocated, the remaining allocated number of persons by assigning the date the repeating period is not reached d _i, feasible solution is generated. Similar to the step of allocating each week during the allocation period, random numbers are allocated as much as possible at the time of allocation.

The initial solution generation method considering g ₂ (x) and g ₃ (x) is shown below.

    Step 1: Assign to each protocol on each day during the repeat period.

    Step 2: Assign to each protocol for each week in the repeat period.

    Step 3: Allocate patients who have not been assigned yet.

  In Step 2 and Step 3, since selection is performed using random numbers from the next selection candidates of the greedy method, the proposed initial solution generation method can be regarded as a kind of randomized greedy method. The solution generated will vary from trial to trial.

Next, the initial solution generation will be specifically described with reference to the flowchart of FIG.
When the initial solution generation is started, a random number seed is acquired (S31). All days are initialized as unallocated (S32), and the number of days in the repetition period is calculated (S33). The number u [k] currently unallocated in each protocol k is calculated (S34).

The process of loop k (k = 1; k <belong; k ++) is started (S35), and it is determined whether u [k] is greater than the number of days in the repetition period (S35). Belong indicates the number of protocol types, and k ++ means a process of incrementing k. When the determination is Yes, _{r k} is calculated (S37). Assign a _{r k} who has been calculated in all of the day (S38). The currently unassigned number of people u [k] is updated (S39). Here, the process of loop k ends.

The process of loop k (k = 1; k <belong; k ++) is started (S41), and it is determined whether u [k] is larger than the number of weeks in the repetition period (S42). If this determination is Yes, hk is calculated (S43). It is determined whether there is a day of the week that has not reached the allocated number (S44). If this determination is Yes, a day of the week that has not reached the allocated number is selected with a random number (S45). If the determination is No, the process proceeds to the process of loop k (k = 1; k <belong; k ++) (S49). If the day does not reach the assigned number in step S45 is selected, assigning a h _k persons all days (S46). The currently unallocated number u [k] is updated (S47). Here, the process of loop k ends.

  The process of loop k (k = 1; k <belong; k ++) is started (S49), and u [k]> 0 is determined (S50). If this determination is Yes, a day that has not reached the allocated number of people is selected with a random number (S51), and if the determination is No, the process ends. When a day that has not reached the allocated number is selected in step S51, a patient is assigned on the selected day (S52). The currently unassigned number of people u [k] is updated (S53). The process of loop k ends. Thereafter, the entire process ends.

Next, pattern improvement will be described.
When the pattern initial solution is generated as described above, the pattern improvement is performed in the pattern improvement unit 21 (S17). In this pattern improvement, by expressing the pattern initial solution as an allocation pattern, it is possible to model an optimization problem in which the protocol in all the repetition periods is assigned to the day in the repetition period with the objective function being f (x). Therefore, the allocation pattern can be optimized by a solution based on the combinatorial optimization technique. Commercial tools such as ILOG's CPLEX can also be used. Here, an optimization method based on neighborhood search, which is one of the combination optimization methods, is shown.

  The neighborhood search is a solution shown by a flowchart as shown in FIG. When some feasible solution x is given to the optimization problem, a solution set obtained by adding some change to x is U (x). U (x) indicates the range of change (search range) from the solution x and is called the vicinity of x.

  Neighbor search (local search) starts with an appropriate feasible solution, and if there is a solution x ′ that improves the objective function over x in the neighborhood, the operation of moving to x = x ′ This method is repeated until the solution does not improve.

The neighborhood search will be specifically described with reference to the flowchart of FIG. Let F ^* = f (x). It is determined whether there is an ungenerated solution in the vicinity of x (S62). When this determination is Yes, a solution that has not yet been generated among the solutions in the vicinity of x is selected, and the solution is set as x ′ (S63). When the solution is generated, the schedule S ′ is generated and f (x ′) is calculated (S64). Thereafter, F ^* <f (x ′) is determined (S65). If this determination is Yes, F ^* = F (x), S ^* = S ′, and x ^* = x ′ are set (S66). Next, it is determined whether x ^* has been updated in the vicinity of x (S67). The determination in step S67 is also performed when the determinations in steps S62 and S65 are No. If this determination is Yes, x = x ^* is set (S68). Thereafter, the process returns to step S62. If the determination in step S67 is No, the schedule S ^* is output and the process ends (S69).

  The solution obtained by the neighborhood search is called a local optimum solution in the neighborhood U (x). The allocation pattern improvement unit 21 can perform pattern optimization by improving using the next neighborhood.

  Neighborhood: Protocol k assigned to m-th day of week w and protocol k 'assigned to m'-day day w', protocol k 'assigned to m-day day w, m'-th week Solution set obtained by assigning protocol k to day of week w ′.

  Next, schedule generation (S18) after the second irradiation day will be described. In particle beam therapy, since treatment cannot normally be interrupted during irradiation, irradiation is basically performed according to a calendar from the start date of irradiation. On the other hand, in some hospitals, there may be a restriction that irradiation is performed 4 times or less per week for each patient. At this time, in the week where each patient can be irradiated five times a week, some patients are irradiated on Monday, Tuesday, Wednesday, and Thursday and rest on Friday, and the rest of the patients are closed on Monday. Irradiate on Tuesday, Wednesday, Thursday and Friday. In other words, even if irradiation is possible on the same Monday on the calendar, if there is a holiday in this week and Monday is the irradiation day, there will be no processing that takes Monday off, and if irradiation is possible five times a week Only some patients need to be put on Monday. If all patients are irradiating on Mondays, the number of patients on Friday will be extremely low. Furthermore, in a week in which irradiation can be performed five times a week, it is better to irradiate the patient on the Monday as much as possible for a patient whose number of irradiations ends in the middle of this week. This is to reduce the extra burden by reducing the patient's hospital stay.

  The processes up to the above are basic processes performed by the radiation therapy planning apparatus. Next, processing that can be added to the basic processing will be described.

(Second embodiment)
As a second embodiment, a case where there is an initial assignment by a user will be described. This process assignment is performed in step S15 of FIG. The allocation pattern (FIG. 16) generates an initial solution and is optimized by the planning device even if the user does not specify anything. However, the user may specify a part or all of the allocation pattern and perform scheduling. it can. There are two types of designation methods, one that is designated as the initial solution and one that is fixed. As shown in the example shown in FIG. 12, the protocol and the starting date of the treatment process as the base point are repeated ( Fig. 10) Specify in the middle day, and select either the initial solution or the fixed solution. Designating as an initial solution assigns the protocol designated by the user to the designated location, and the pattern initial solution generation unit 20 generates the remaining patterns. The obtained allocation pattern is optimized by the pattern improvement unit 21 and is improved when a better pattern can be generated by changing the given initial solution. In the case of fixation, the protocol designated by the user is not improved by optimization, and only the protocol that is not fixed is optimized.

(Third embodiment)
A case where a closed frame is generated will be described as a third embodiment. In the frame behind the planning period, a phenomenon occurs in which irradiation cannot be scheduled for the number of times determined by the allocation pattern, and the protocol determined by the allocation pattern cannot be allocated. These frames are called unassigned frames. At this time, as a frame that can be used when there is a matching patient regardless of the protocol, by creating a frame in which only the number of irradiations is determined without setting a protocol, the frame behind the planning period can also be efficiently Make it available.

  In the closed frame generation, it is determined whether or not the closed frame is filled after the schedule creation (S18) on and after the second day of irradiation in the flowchart of FIG. 2 (S19). If this determination is Yes, processing for filling the remaining frame with the closed frame is performed (S21). In this case, the type of the number of times of irradiation created as a closed frame is input as 12, 12, 4, 2, or 1 as shown in FIG. At this time, a closed frame having the maximum number of irradiations that can be performed in an unallocated frame is allocated, scheduling is performed in the same manner as the schedule creation on and after the second day, and the schedule is output (S21). If the determination in step S19 is No, the schedule is output.

  Next, closed frame generation will be specifically described with reference to the flowchart of FIG.

  The closed frame list c [] is sorted in descending order of the number of times of irradiation (S81). The first closed frame is taken and set as d (S82). Thereafter, processing of loop i (i = 0; i <current total number of frames; i ++) is started (S83). It is determined whether the frame i is unallocated (S84). If this determination is Yes, it is determined whether the number of times of irradiation of the frame i can be executed. If this determination is Yes, the closed frame d is assigned to the frame i, the number of times of irradiation is set (S86), 1 is added to i, and the processing of the loop i is continued. If the determination in step S84 is No, 1 is added to i and the processing in loop i is continued. When the processing of the loop i is completed for all i (S87), the entire processing is completed.

  If the determination in step S85 is No, it is determined whether c [] has an element next to d (S88). If this determination is Yes, the element next to c [] is taken as d (S89), and the process proceeds to step S85. If the determination in step 88 is No, the currently unassigned frame is deleted (S90), and the process ends.

  It is determined whether there is a schedule change after the schedule is output (S22). If this determination is Yes, the final schedule (FIG. 19) is output.

(Fourth embodiment)
As a fourth embodiment, a description will be given of a modification in the case where the upper limit of the number of persons who can work on each day is determined for treatment steps other than the reference treatment step. As an example, it is assumed that the upper limit of the number of irradiations on each day is determined in the calendar information storage unit 13 that stores calendar information of each treatment process, as shown in FIG. The flow in this case will be described according to FIG.

 First, a schedule is created according to the first embodiment assuming that there is no upper limit on the number of people to be irradiated (S91). Since the schedule obtained at this time does not consider the upper limit of the number of irradiation, there is a possibility that the number of irradiation will be exceeded someday. If the result of determination in S92 is No, there is no day in which the number of irradiated persons is exceeded in the obtained schedule, so the solution is obtained and the schedule is output and the process ends. If it is Yes, the number of people who can work on each day given to the standard treatment process is reduced (S93). In this case, it may be reduced by one person on every day, or may be reduced on some days according to a rule such as every other day or every week. When the number of persons who can work in the standard treatment process is updated, the process returns to S91, and the procedure for creating the schedule is repeated assuming that there is no upper limit on the number of irradiation persons.

  The methods of the present invention described in the first to fourth embodiments can be executed by a computer, and as programs that can be executed by the computer, magnetic disks (flexible disks, hard disks, etc.), optical disks It can also be stored and distributed in a recording medium such as a semiconductor memory (CD-ROM, DVD, etc.).

  The present invention is not limited to the above-described embodiments as they are, and can be embodied by modifying the constituent elements without departing from the scope of the invention in the implementation stage. In addition, various inventions can be formed by appropriately combining a plurality of components disclosed in the embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, constituent elements over different embodiments may be appropriately combined.

  DESCRIPTION OF SYMBOLS 11 ... Planning information storage part, 12 ... Treatment process information storage part, 13 ... Calendar information storage part of each treatment process, 14 ... Restriction information storage part of treatment process, 15 ... Schedule creation module, 16 ... Pattern creation module, 17 ... Schedule creation unit for treatment process as a base point, 18 ... Schedule creation unit for treatment process until the start of irradiation, 19 ... Schedule creation unit for the second and subsequent days of irradiation, 20 ... Pattern initial solution generation unit, 21 ... Pattern improvement unit, DESCRIPTION OF SYMBOLS 22 ... Pattern evaluation part, 23 ... Protocol information storage part, 24 ... Patient information storage part, 25 ... Pattern information storage part, 26 ... Initial allocation information storage part by a user, 27 ... Closed frame setting information storage part, 28 ... Closed frame Scheduling creation unit, 29... Schedule storage unit, 30 schedule display unit.

Claims (10)

A radiotherapy planning device for creating a long-term treatment frame for radiotherapy,
A first storage unit for storing planning information in which a planning period is set;
A second storage unit for storing treatment process information defining a treatment process as a base point and other treatment processes;
A third storage unit that stores calendar information of each treatment process that defines a calendar of possible days in the planning period of each treatment process;
A fourth storage unit for storing constraint information of the treatment process for storing constraints on irradiation dates and irradiation between each treatment process;
A fifth storage unit for storing protocol information defining a treatment protocol indicating a treatment site and the number of treatments;
A sixth storage unit for storing patient information that defines a proportion of the number of patients for each treatment protocol;
A seventh storage unit for storing pattern information defining a repetition period of an assignment pattern to which a treatment protocol is assigned;
A first schedule creating unit that reads each information from the first to fourth storage devices and creates a schedule of a treatment process as a base point;
Each information is read from the first to fourth storage units, and a treatment process schedule up to the irradiation start date is created for treatment processes other than the base point based on the read information and the generated base process schedule. A second schedule creation unit;
A pattern initial solution generation unit that reads each piece of information from the fifth to seventh storage units and generates an initial solution of an allocation pattern;
A pattern evaluation unit that reads each piece of information from the first to seventh storage units and calculates an evaluation value of the pattern based on the read information when the pattern improvement unit gives a predetermined allocation pattern;
The pattern initial solution generated by the pattern initial solution generation unit and each information are read from the first to seventh storage units, and the allocation pattern is optimized by using the evaluation value calculated by the pattern evaluation unit. The pattern improving unit to be improved;
A third schedule creating unit that reads each information from the storage units 1 to 7 and creates a schedule for the second and subsequent days of irradiation based on the read information and the pattern improved by the pattern improving unit;
A schedule storage unit for storing the created radiation treatment schedule;
A schedule display unit for displaying the radiation treatment schedule;
A radiation therapy planning apparatus comprising:   An eighth storage unit that stores closed frame setting information; reads information from the eighth storage unit; and sets a closed frame schedule based on the read information and the schedule created by the third schedule creation unit. The radiotherapy planning apparatus according to claim 1, further comprising a fourth schedule creation unit that creates and stores the created schedule in the schedule storage unit.   The pattern improvement unit sets a repetition period by a multiple of 7, automatically generates an allocation pattern within the repetition period, and performs scheduling according to this pattern, whereby a schedule in which work is fixed as much as possible on the day of the week is set. The radiotherapy planning apparatus according to claim 1, wherein the radiotherapy planning apparatus is generated.   The radiotherapy planning according to any one of claims 1 to 3, wherein scheduling is performed by the second schedule creation unit so as not to deviate even if there is a specific schedule such as a holiday. apparatus.   By generating an allocation pattern by the pattern initial solution generation unit, the pattern improvement unit, and the pattern evaluation unit and performing optimization by a combination optimization method, even in the pattern as much as possible for each protocol, the day of the week is aligned, The radiotherapy planning apparatus according to claim 1, wherein a schedule that realizes the maximum value minimization of the number of patients on each day is generated.   An eighth storage unit for storing initial allocation information by the user when the user designates a partial allocation of the pattern, wherein the pattern initial solution generation unit reads the information from the eighth storage unit; The radiotherapy planning apparatus according to any one of claims 1 to 5, wherein optimization can be performed by designating a part or all of an assignment pattern as an initial solution or a fixed one. A radiotherapy planning method for creating a long-term treatment frame for radiotherapy,
Storing the planning information in which the first storage device sets the planning period;
Storing treatment process information defining a treatment process and other treatment processes as a base point of the second storage device;
A third storage device storing calendar information of each treatment process defining a calendar of possible dates in the planning period of each treatment process;
Storing constraint information of a treatment process in which a fourth storage device stores a date to be opened between each treatment process and restrictions on irradiation;
Storing a protocol information defining a treatment protocol indicating a treatment site and the number of treatments in a fifth storage device;
A sixth storage device storing patient information defining the percentage of patients for each treatment protocol;
Storing pattern information defining a repetition period of an allocation pattern to which a seventh storage device assigns treatment protocols;
A first schedule creation device reading each piece of information from the first to fourth storage devices and creating a schedule of a treatment process as a base point;
The second schedule creation device reads each information from the first to fourth storage units, and based on the read information and the schedule of the treatment process that is the generated base point, up to the irradiation start date for the treatment process other than the base point Creating a treatment process schedule;
A pattern initial solution generator reading each piece of information from the fifth to seventh storage units and generating an initial solution of the assigned pattern;
When the pattern evaluation device reads each information from the first to seventh storage units and the pattern improvement unit gives a predetermined allocation pattern, a step of calculating an evaluation value of the pattern based on the read information;
The pattern improvement device reads each information from the pattern initial solution generated by the pattern initial solution generation unit and the first to seventh storage units, and uses the evaluation value calculated by the pattern evaluation unit to optimize Improving the allocation pattern through optimization; and
A step in which a third schedule creation device reads each information from the storage units 1 to 7 and creates a schedule for the second and subsequent days of irradiation based on the read information and the pattern improved by the pattern improvement unit;
Storing a radiation treatment schedule in which a schedule storage device is created;
A schedule display device displaying the radiation treatment schedule;
A radiation therapy planning method comprising:  A pattern initial solution generating device reading information from an eighth storage device for storing initial allocation information by the user when the user designates partial allocation of the pattern; The radiotherapy planning method according to claim 7, further comprising the step of performing optimization by designating as an initial solution or fixed.   The fourth schedule creation device further includes reading closed frame setting information from the ninth storage device, and creating a closed frame schedule based on the read information and the schedule created by the third schedule creation device, The radiotherapy planning method according to claim 7.   When the upper limit number of people that can be treated in a treatment process other than the standard treatment process is determined by the third storage unit, the schedule created by the third schedule creation device exceeds the upper limit number of people that can be treated. The radiation treatment planning method according to claim 7, further comprising a step of creating a schedule by reducing the number of workers in the standard treatment process.

Images