Real-time processing method for missing data of regional radiation monitor

Abstract

The application discloses a real-time processing method for missing data of a regional radiation monitor, and relates to the technical field of data processing. The method comprises the following steps: acquiring in-door radiation sequence data and out-door radiation sequence data generated in the operation process of the regional radiation monitor in a historical time period; determining a drug injection time based on fluctuation characteristics of the in-door radiation sequence data; determining an out-door performance time based on a time correspondence relationship between the drug injection time, the in-door radiation sequence data and the out-door radiation sequence data; comparing a plurality of suspected out-door performance times before a current time with the out-door performance time in the historical time period to obtain a real probability of the suspected out-door performance time; judging a radiation fluctuation completeness degree of the in-door radiation sequence data processed by a linear interpolation method based on the real probability; and generating a required data compensation measure based on the radiation fluctuation completeness degree. The application achieves the technical effect of improving the judgment accuracy of abnormal radiation events.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and specifically to a method for real-time processing of missing values ​​in regional radiation monitoring data. Background Technology

[0002] A regional radiation monitoring instrument is an intelligent device used for real-time monitoring of X-rays, beta, and gamma rays in and around nuclear medicine departments, radioactive workplaces, and surrounding environments. It typically consists of a main unit and multiple wireless sub-units, and can be deployed over a wide area to achieve continuous monitoring of the environment from local to high dose rates. It is widely used in radiation protection, radioactive source management, and radiation safety supervision. During the operation and monitoring of regional radiation monitoring instruments, due to the presence of thick concrete walls, lead shielding doors, and complex spatial layouts in radioactive workplaces such as nuclear medicine departments, wireless signals are easily blocked or attenuated. In addition, electromagnetic interference, excessive communication distance, or network congestion can all lead to interruption or packet loss in data transmission between the main unit and sub-units, resulting in missing monitoring data.

[0003] Currently, the main approach to solving this problem using relevant technologies is through interpolation algorithms. These algorithms only perform simple compensation based on the continuity of data between different time points. If a regional radiation monitoring instrument is installed in the injection room, the radiation level will change rapidly when the patient is given medication, resulting in sudden changes in radiation levels. The processing method of these algorithms will produce a large deviation, thus affecting the accurate judgment and safety warning of abnormal radiation events. Summary of the Invention

[0004] To address the technical problem that in related technologies, compensation for radiation sequence data solely through interpolation algorithms can lead to significant deviations when sudden changes in radiation levels occur, thus affecting the accurate judgment and safety warning of abnormal radiation events, this invention provides a real-time processing method for missing values ​​in regional radiation monitoring instrument data.

[0005] The specific technical solution adopted is as follows:

[0006] Acquire the radiation sequence data inside and outside the door generated during the operation of the regional radiation monitoring instrument within a historical time period;

[0007] The timing of drug injection was determined based on the fluctuation characteristics of the radiation sequence data within the gate.

[0008] Based on the time correspondence between drug injection time, radiation sequence data inside the door and radiation sequence data outside the door, the time of manifestation outside the door is determined. The time of manifestation outside the door refers to the moment when the radiation value changes the most when the patient leaves the injection room.

[0009] By comparing multiple suspected out-of-door performance moments before the current moment with out-of-door performance moments within a historical time period, the true probability of the suspected out-of-door performance moment is obtained.

[0010] Based on the true probability, determine the completeness of radiation fluctuations in the in-gate radiation sequence data processed by linear interpolation.

[0011] Based on the integrity of radiation fluctuations, data compensation measures are generated to meet the requirements.

[0012] In one possible implementation of this application, determining the drug injection time based on the fluctuation characteristics of intragate radiation sequence data includes:

[0013] Obtain all first maxima from the radiation sequence data inside the door, and use the time corresponding to each first maxima as the suspected drug injection time.

[0014] Based on the degree of change in radiation value within a first preset time period before the suspected drug injection time, the pre-injection radiation level at each suspected drug injection time is calculated.

[0015] Based on the degree of change in radiation value within the first preset time period after the suspected drug injection time, the post-injection radiation level at each suspected drug injection time is calculated.

[0016] The timing of drug injection is determined based on the radiation levels after injection, before injection, and the radiation value at the suspected injection time.

[0017] In one possible implementation of this application, the post-injection radiation level at each suspected drug injection time is calculated based on the degree of radiation value change within a first preset time period after the suspected drug injection time, including:

[0018] The radiation value change index and the first radiation value are determined at each time within the first preset time period after the suspected drug injection time. The radiation value change index at the current time is the absolute value of the difference between the radiation value at the previous time and the radiation value at the current time.

[0019] Calculate the minimum exponential value of radiation value change within the time interval between the suspected drug injection time and each other time interval;

[0020] The normalized value of the difference between the radiation value change index and the minimum value of the radiation value change index is multiplied by the first radiation value to calculate the post-injection radiation level at each suspected drug injection time.

[0021] In one possible implementation of this application, determining the drug injection time based on the post-injection radiation level, the pre-injection radiation level, and the radiation value at the suspected drug injection time includes:

[0022] The degree of radiation retention at each suspected drug injection time was calculated based on the difference between the radiation level after injection and the radiation level before injection.

[0023] Based on the degree of radiation retention during injection and the radiation value at the suspected drug injection time, the injection probability at each suspected drug injection time is calculated.

[0024] Based on the injection probability, clusters are formed for each suspected drug injection time, and drug injection times are selected from the clusters obtained after clustering.

[0025] In one possible implementation of this application, the timing of the external manifestation is determined based on the time correspondence between the drug injection time, the internal radiation sequence data, and the external radiation sequence data, including:

[0026] Determine multiple first moments located between two adjacent drug injection moments;

[0027] Establish a neighborhood window of a preset length centered on the first moment;

[0028] For any given first moment, based on the difference in radiation values ​​between the two moments on either side of the first moment in the neighborhood window, the first probability that the current first moment is the time to leave is calculated.

[0029] Mark the first moment corresponding to the maximum value of the first probability as the exit moment between two adjacent drug injection moments;

[0030] Obtain multiple second maxima in the radiation sequence data outside the door. For any exit time, mark the time corresponding to the second maxima closest to the exit time as the exit time.

[0031] In one possible implementation of this application, the first probability that the current first time is the time of departure is calculated based on the difference in radiation values ​​at various times on both sides of the first time within the neighborhood window, including:

[0032] Determine the first mean of the radiation values ​​at each time point to the left of the first time point within the neighborhood window, and the second mean of the radiation values ​​at each time point to the right of the first time point;

[0033] Calculate the pre-injection radiation level at the time preceding the first drug injection.

[0034] Based on the difference between the first mean and the second mean, and the difference between the second mean and the pre-injection radiation level, the first probability that the current first moment is the time to leave is calculated.

[0035] In one possible implementation of this application, multiple suspected out-of-door behavior moments prior to the current moment are compared with out-of-door behavior moments within a historical time period to obtain the true probability of the suspected out-of-door behavior moment, including:

[0036] Obtain all second maxima from the previous exit time to the current time in the radiation sequence data outside the door, and mark each second maxima as a suspected time of outside the door manifestation;

[0037] Based on the changes in radiation values ​​at various times before the suspected external manifestation time, the first radiation surge degree at each suspected external manifestation time is calculated, and the second radiation surge degree at each external manifestation time within the historical time period is calculated.

[0038] Calculate the difference in radiation values ​​between the current suspected external manifestation time and each external manifestation time in the historical time period, as well as the first difference between the first radiation surge degree and the second radiation surge degree;

[0039] The maximum value of the ratio between the inversely proportional normalized value of the radiation difference and the absolute value corresponding to the first difference is taken as the true probability of the moment when the suspected outside behavior occurs.

[0040] In one possible implementation of this application, the degree of first radiation surge at each suspected external manifestation time is calculated based on the radiation value changes at various times prior to the suspected external manifestation time, including:

[0041] Calculate the second difference between the radiation values ​​at each time point before the suspected external manifestation and the mean of the corresponding radiation values ​​in the external radiation sequence data;

[0042] Multiply the normalized value of the second difference by the slope value of the change in radiation value at each time before the suspected external manifestation time to obtain the first radiation surge degree at each suspected external manifestation time.

[0043] In one possible implementation of this application, determining the completeness of radiation fluctuations in gate-interpolated radiation sequence data based on true probability includes:

[0044] The true probability is compared with a preset probability threshold, and based on the comparison results, the inferred time of outside the door is selected from each suspected time of outside the door.

[0045] If a presumed time of external manifestation is determined, then calculate the third difference between the post-injection radiation level at the suspected time of drug injection and the radiation value at the presumed time of external manifestation.

[0046] Based on the injection probability of suspected drug injection time, the third difference, the inferred time of external manifestation, and the average radiation value within the second preset time period after each time of external manifestation, the completeness of radiation fluctuation at each suspected drug injection time within the time interval between the previous time of external manifestation and the current time is calculated.

[0047] In one possible implementation of this application, data compensation measures for generating required data based on the integrity of radiation fluctuations include:

[0048] The integrity level of radiation fluctuations is compared with a preset integrity threshold;

[0049] If the integrity of the radiation fluctuation is greater than the preset integrity threshold, the linear interpolation method is deemed effective as a compensation method for the radiation sequence data inside the gate, and the radiation sequence data inside the gate is considered complete monitoring data.

[0050] If the integrity of radiation fluctuations is less than or equal to the preset integrity threshold, and data loss still exists after data compensation using linear interpolation, a data supplementation warning will be reported.

[0051] The present invention has, but is not limited to, the following technical effects:

[0052] By acquiring radiation sequence data inside and outside the door generated during the operation of the regional radiation monitoring instrument in a historical time period, the drug injection time is determined based on the fluctuation characteristics of the radiation sequence data inside the door. Then, by using the time correspondence between the drug injection time and the radiation sequence data inside and outside the door, the time of suspected external manifestations is determined.

[0053] Then, by comparing the suspected external manifestation time with the external manifestation time in the historical time period, the true probability of the suspected external manifestation time is determined. The true probability is used to determine the integrity of the radiation fluctuation of the radiation sequence data inside the door. Based on the integrity of the radiation fluctuation, it is determined whether the monitored radiation sequence data needs to be compensated, and the required data compensation measures are generated to avoid affecting the accurate judgment and safety warning of abnormal radiation events due to inaccurate data. Attached Figure Description

[0054] Figure 1 This is a flowchart illustrating the first embodiment of the real-time processing method for missing data values ​​of the regional radiation monitoring instrument in this application.

[0055] Figure 2 This is a schematic diagram of the overall implementation process of the real-time processing method for missing values ​​in regional radiation monitoring instrument data in this application.

[0056] Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application. Detailed Implementation

[0057] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0058] This application provides a method for real-time processing of missing data values ​​from a regional radiation monitoring instrument. In the first embodiment of this method, referring to... Figure 1 The methods include:

[0059] Step S10: Obtain the radiation sequence data inside the door and the radiation sequence data outside the door generated during the operation of the regional radiation monitoring instrument within the historical time period;

[0060] Step S20: Determine the drug injection time based on the fluctuation characteristics of the in-gate radiation sequence data;

[0061] Step S30: Based on the time correspondence between the drug injection time, the radiation sequence data inside the door and the radiation sequence data outside the door, determine the time of manifestation outside the door, where the time of manifestation outside the door represents the time when the patient walks out of the injection room when the radiation value changes the most.

[0062] Step S40: Compare multiple suspected out-of-door performance moments before the current moment with out-of-door performance moments within the historical time period to obtain the true probability of the suspected out-of-door performance moments;

[0063] Step S50: Based on the true probability, determine the completeness of radiation fluctuations in the in-gate radiation sequence data processed by linear interpolation.

[0064] Step S60: Based on the integrity of radiation fluctuations, generate the required data compensation measures.

[0065] This embodiment aims to determine the completeness of radiation fluctuations in the radiation sequence data within the gate, thereby determining whether the monitored radiation sequence data needs compensation based on the completeness of the radiation fluctuations, and generating the required data compensation measures to avoid affecting the accurate judgment and safety warning of abnormal radiation events due to inaccurate data.

[0066] Step S10: Obtain the radiation sequence data inside the door and the radiation sequence data outside the door generated during the operation of the regional radiation monitoring instrument within the historical time period.

[0067] As an example, the real-time processing method for missing data values ​​of a regional radiation monitor can be applied to a real-time processing device for missing data values ​​of a regional radiation monitor. This device belongs to a real-time processing system for missing data values ​​of a regional radiation monitor, which in turn belongs to a real-time processing equipment for missing data values ​​of a regional radiation monitor.

[0068] As an example, in the various functional areas of the nuclear medicine department, the injection room is where radiopharmaceuticals are directly handled and introduced into the patient's body. In a short period of time, radiopharmaceuticals with high activity will be exposed to the air and around people. If the operation is not done properly during the dispensing, extraction and injection process (such as needle residue or drug spillage), the local dose rate will increase significantly in a short time. Therefore, the injection room is the most likely place to have radiation levels exceeding the standard.

[0069] Therefore, the injection room is a relatively enclosed space with thick walls and shielding materials, which significantly attenuates or obstructs wireless communication signals. Simultaneously, frequent operations by medical staff, patient entry and exit, and equipment movement within the injection room can cause the detector sub-units to be blocked or interfered with for short periods, increasing the instability of data transmission. Therefore, compared to waiting areas or examination rooms, the area radiation monitoring instrument in the injection room is more prone to data loss due to poor remote wireless communication. The application scenario addressed in this application is the indoor and outdoor use of the injection room. The area radiation monitoring instrument consists of a main unit and multiple wireless sub-units. In the implementation scenario of this application, the wireless sub-units are installed both inside and outside the injection room.

[0070] As an example, the environment outside the door is relatively open and will not be affected by the thick shielding walls of the injection room or the strong signal attenuation of the door. From the perspective of communication stability and data integrity, the data transmission of the external sub-unit is more reliable than that of the internal sub-unit in the injection room. Since the external sub-unit mainly monitors the radiation outside the door and cannot specifically monitor the situation inside the injection room, the internal and external sub-units need to cooperate to determine whether the detection data of the detector is missing.

[0071] As an example, the radiation sequence data inside the door is the daily radiation sequence data of the intra-door sub-unit of the injection room during its historical operation; the radiation sequence data outside the door is the daily radiation sequence data of the intra-door sub-unit of the injection room during its historical operation. The acquisition frequency of the above sequence data is once per second, and each moment corresponds to one second.

[0072] Step S20: Determine the drug injection time based on the fluctuation characteristics of the in-gate radiation sequence data.

[0073] As an example, the process of injecting radiopharmaceuticals into patients in an injection room is divided into several stages. Before the patient arrives at the injection room, the radiation level is usually close to the environmental background level (background radiation level refers to the normal radiation level produced in an environment not considered to be radioactively contaminated), and the monitor readings are stable. When the patient enters the injection room, the radiation level is still close to the environmental background level since the patient has not yet received the injection. When the radiopharmaceutical is injected, as the drug enters the patient's body through the needle, the monitor reading will show a significant spike. After the peak, the monitoring value will decrease, but it will not return to the environmental background level; instead, it will remain at a relatively high level. When the patient leaves the injection room, the radiation level in the injection room will drop rapidly. Therefore, based on the fluctuations in the radiation sequence data inside the room, the peak radiation value at the time of the patient's injection can be extracted to determine the timing of the drug injection.

[0074] The step S20, which involves real-time processing of missing data from the regional radiation monitoring instrument, further includes steps S21 to S24, including:

[0075] Step S21: Obtain all first maxima in the radiation sequence data inside the gate, and use the time corresponding to each first maxima as the suspected drug injection time.

[0076] As an example, the first maximum value can be the maximum value of each sequence value in the radiation sequence data inside the door. When the staff injects drugs into the patient, the radiation value usually reaches a peak value at this time. Therefore, the time corresponding to the maximum value is taken as the suspected drug injection time. Then, the actual drug injection time is determined by the changes of various radiation indicators at the suspected drug injection time.

[0077] Step S22: Based on the degree of change in radiation value within a first preset time period before the suspected drug injection time, calculate the pre-injection radiation level at each suspected drug injection time.

[0078] As an example, the pre-injection radiation level mainly refers to the radiation level before drug injection, or it can be the environmental background value. The first preset time period can be 1 minute, 3 minutes, etc., and there is no specific limitation.

[0079] As an example, the radiation level at the current moment can be determined based on the degree of change in radiation levels over a period of time prior to the suspected drug injection.

[0080] Step S23: Based on the degree of change in radiation value within a first preset time period after the suspected drug injection time, calculate the post-injection radiation level at each suspected drug injection time.

[0081] As an example, post-injection radiation level also refers to the radiation level over a period of time after drug injection. The calculation methods for pre-injection and post-injection radiation levels are the same. Here, we will take the calculation method for post-injection radiation level as an example for detailed explanation.

[0082] Step S23 includes:

[0083] The radiation value change index and the first radiation value are determined at each time within a first preset time period after the suspected drug injection time. The radiation value change index at the current time is the absolute value of the difference between the radiation value at the previous time and the radiation value at the current time.

[0084] Calculate the minimum value of the radiation value change index within the time interval between the suspected drug injection time and each other time interval.

[0085] As an example, the calculation method is the same for the radiation value change index at each moment within the first preset time period. The first radiation value represents the radiation value at each moment within the first preset time period.

[0086] As an example, the minimum value of the radiation value change index represents the average value of the radiation value change index corresponding to each time point within the time interval between the suspected drug injection time and each other time point. If there are no other times within this time interval, the average value of the radiation value change index between the current time point and the suspected drug injection time point is taken.

[0087] The normalized value of the difference between the radiation value change index and the minimum value of the radiation value change index is multiplied by the first radiation value to calculate the post-injection radiation level at each suspected drug injection time.

[0088] As an example, with the first Taking a suspected drug injection moment as an example, the radiation level after injection The calculation method can be:

[0089]

[0090] In the formula, For the first Radiation levels after injection at a suspected drug injection time; This indicates the first preset time period, which is set to 3 minutes here, based on the data collection frequency. The value is 180, meaning that the first preset time period includes 180 moments. For the first The day after the suspected drug injection moment The exponent of change in radiation value per second (obtained by taking the absolute value of the difference between the radiation value at the previous moment and the radiation value at the current moment for any given time as the exponent of change in radiation value at that moment). For the first The suspected drug injection moment was followed by the [number]th [time]. The minimum value of the exponential change of all radiation values ​​within a time interval of seconds. Indicates the first The day after the suspected drug injection moment The radiation value per second is calculated using the softmax() function, which represents the normalization function and has a range of (0, 1). Similarly, the post-injection radiation levels at other suspected drug injection times can be calculated.

[0091] Step S24: Determine the time of drug injection based on the radiation level after injection, the radiation level before injection, and the radiation value at the suspected time of drug injection.

[0092] Step S24 includes:

[0093] The degree of radiation retention at each suspected drug injection time was calculated based on the difference between the radiation level after injection and the radiation level before injection.

[0094] As an example, if the suspected injection time is the actual drug injection time, then because there will be significant changes in radiation levels in the patient's body before and after the injection, the difference between the radiation levels before and after the injection can be used to quantify the characteristics of the changes in radiation levels and determine the degree of radiation retention after injection.

[0095] As an example, with the first Taking a suspected injection moment as an example, the degree of radiation retention after injection. The calculation method can be:

[0096]

[0097] In the formula, For the first The level of radiation retention at a suspected injection moment For the first Post-injection radiation levels at a suspected injection time; For the first The pre-injection radiation level at one suspected injection moment is obtained, and norm() represents the normalization process. Similarly, the injection radiation retention level at other suspected drug injection moments can be obtained.

[0098] Based on the degree of radiation retention during injection and the radiation value at the suspected drug injection time, the injection probability at each suspected drug injection time is calculated.

[0099] As an example, when the radiation level at the suspected injection moment is relatively high, and the radiation value at the suspected injection moment is also high, it indicates that an actual injection has occurred. Based on this, the injection probability at each suspected injection moment can be calculated.

[0100] As an example, with the first Taking a suspected injection moment as an example, the probability of injection. The calculation method is as follows:

[0101]

[0102] In the formula, For the first The probability of injection at a suspected injection time. For the first The level of radiation retention at a suspected injection moment; For the first The radiation value at each suspected injection moment is normalized using norm(). Similarly, the injection probability at other suspected drug injection moments can be calculated.

[0103] Based on the injection probability, clusters are formed for each suspected drug injection time, and drug injection times are selected from the clusters obtained after clustering.

[0104] As an example, after obtaining the injection probability of the suspected injection time, since there is a large difference between the injection probability of the real injection time and the non-real injection time, clustering is used to distinguish between the real injection time and the non-real injection time.

[0105] Specifically, the injection probabilities of all suspected injection times are clustered using K-means, where K=2. The cluster with the largest mean injection probability is denoted as the injection time cluster, and each suspected injection time in the injection time cluster is denoted as a drug injection time.

[0106] Step S30: Based on the time correspondence between the drug injection time, the radiation sequence data inside the door and the radiation sequence data outside the door, determine the time of manifestation outside the door, where the time of manifestation outside the door represents the moment when the patient walks out of the injection room and the radiation value changes the most.

[0107] As an example, for the external host, the changes in the external host during the injection of a single patient are as follows: before the patient enters the injection room, the reading of the external host is basically close to the background level; during the injection, when the injection operation occurs inside, the radiation value of the external host will not change significantly due to the obstruction of the door and shielding; when the patient leaves the injection room after the injection, as the patient walks from inside the door to outside with the radionuclide in their body, the external host will show a significant short-term peak, and then gradually drop back to the level when the patient is away. It should be noted that this short-term peak can be used as a marker event for the patient leaving the injection room.

[0108] However, although the external control unit is located outside the injection room, it is still within the nuclear medicine department. Many patients with radioactive drugs in their bodies pass through, causing the maximum values ​​in the external radiation sequence data obtained by the external control unit to include not only the radiation values ​​of patients leaving the injection room but also the radiation values ​​of patients passing by the injection room door. In order to accurately determine whether a patient was receiving a radioactive drug injection in the injection room when data is missing, it is necessary to determine which maximum values ​​were actually caused by patients leaving the injection room based on historical data. Therefore, based on the time correspondence between the drug injection time, the radiation sequence data inside the door, and the radiation sequence data outside the door, the suspected external manifestation time is determined. The suspected external manifestation time can be represented by the time when the maximum value detected by the external control unit is when the patient leaves the door.

[0109] Step S30 includes:

[0110] Determine multiple first moments located between two adjacent drug injection moments.

[0111] Establish a neighborhood window of a preset length centered on the first moment.

[0112] For any given first moment, the probability that the current first moment is the time of departure is calculated based on the difference in radiation values ​​between the two moments on either side of the first moment in the neighborhood window.

[0113] As an example, there are multiple moments between two adjacent drug injection moments, which are called the first moments. For any first moment, a neighborhood window of a preset length (which can be 7) is established with that moment as the center, and it is denoted as the neighborhood window of that moment.

[0114] As an example, for any first moment, based on the difference in radiation values ​​on both sides of the current moment, it is determined whether the current moment is the time to leave, and the first probability that the current moment may be the time to leave is calculated, where the first probability can be 0.5, 0.7, etc., and there is no specific limitation.

[0115] The step of calculating the first probability that the current first moment is the departure moment based on the difference in radiation values ​​at various times on both sides of the first moment within the neighborhood window includes:

[0116] Determine the first mean of the radiation values ​​at each time point to the left of the first time point within the neighborhood window, and the second mean of the radiation values ​​at each time point to the right of the first time point.

[0117] Calculate the pre-injection radiation level at the time preceding the first drug injection.

[0118] Based on the difference between the first mean and the second mean, and the difference between the second mean and the pre-injection radiation level, the first probability that the current first moment is the time to leave is calculated.

[0119] As an example, the first mean is the average of the radiation values ​​at each time point to the left of the first time point in the neighborhood window, and similarly, the second mean is the average of the radiation values ​​at each time point to the right of the first time point.

[0120] As an example, the time interval between two adjacent drug injection moments is... Taking the first moment as an example, the first probability The calculation method can be:

[0121]

[0122] In the formula, For the first The probability of the first moment of departure; In the first In the first moment of the neighborhood window, the first The first mean of the left-side radiation values ​​at the first moment; In the first In the first moment of the neighborhood window, the first The second mean of the radiation values ​​on the right side at the first moment; For the first The pre-injection radiation level at the time preceding the first injection moment; The normalization object is all first moments between the two injection moments. .

[0123] Because the time interval between the patient leaving the closed door is extremely short, the radiation level of the sub-unit inside the door changes significantly before and after the patient leaves. The radiation level is relatively high, and because the radiation level monitored by the sub-unit inside the door returns to the environmental background level after the patient leaves, i.e., the radiation level before the patient's injection, therefore... It will be very small.

[0124] The first moment corresponding to the maximum value of the first probability is marked as the exit moment between two adjacent drug injection moments.

[0125] Obtain multiple second maxima in the radiation sequence data outside the door. For any exit time, mark the time corresponding to the second maxima closest to the exit time as the exit time.

[0126] As an example, for any two injection times, the time with the highest probability of leaving the house is denoted as the leaving time of the previous drug injection time between the two injection times.

[0127] Specifically, for any exit time, all second maxima are obtained from the outside radiation sequence data, and the time corresponding to the second maxima closest to that exit time is taken as an outside performance time.

[0128] Step S40: Compare multiple suspected out-of-door performance moments before the current moment with out-of-door performance moments within the historical time period to obtain the true probability of the suspected out-of-door performance moments.

[0129] As an example, the suspected time of exiting the door is the time corresponding to all the maximum values ​​between the previous exit time and the current time in the exit radiation sequence data. By comparing the degree of change of radiation values ​​between the suspected time of exiting the door and the time of exiting the door in the historical time period, the probability that the suspected time of exiting the door is the actual time of exiting the door is determined, which is the true probability.

[0130] Step S40 includes:

[0131] Obtain all second maxima from the previous exit time to the current time in the outside radiation sequence data, and mark each second maxima as a suspected outside manifestation time.

[0132] As an example, when data is missing in the door-inside submachine sequence, all second maxima between the previous exit time and the current time are obtained from the door-outside radiation sequence data. The second maxima represent the maximum values ​​in the sequence values ​​between the previous exit time and the current time in the door-outside radiation sequence data, and each second maxima is marked as a suspected door-outside performance time.

[0133] Based on the changes in radiation values ​​at various times before the suspected external manifestation time, the first radiation surge degree at each suspected external manifestation time is calculated, and the second radiation surge degree at each external manifestation time within the historical time period is calculated.

[0134] As an example, the change in radiation value at each moment before the suspected external manifestation can be the change in radiation value at each moment within the previous 10 seconds. The degree of radiation surge mainly indicates the degree of increase in radiation between different moments. When the degree of radiation surge is greater, it means that the degree of change in radiation value between two moments is greater. The calculation method of the first degree of radiation surge and the second degree of radiation surge is the same. Here, we will use the calculation method of the first degree of radiation surge as an example.

[0135] The step of calculating the first radiation surge at each suspected external manifestation time based on the radiation value changes at various times prior to the suspected external manifestation time includes:

[0136] Calculate the second difference between the radiation values ​​at each time point before the suspected external manifestation and the mean of the corresponding radiation values ​​in the external radiation sequence data.

[0137] Multiply the normalized value of the second difference by the slope value of the change in radiation value at each time before the suspected external manifestation time to obtain the first radiation surge degree at each suspected external manifestation time.

[0138] As an example, the second difference represents the difference between the radiation values ​​at various times within a period of time before the suspected external manifestation and the average value of the corresponding radiation values ​​in the external radiation sequence data.

[0139] As an example, with the first Taking a suspected instance of external manifestation as an example, the first sudden increase in radiation level The calculation method can be:

[0140]

[0141] In the formula, It is 10 seconds, or 10 moments; For the first The moment before what appeared to be an out-of-door performance The radiation value at each moment; This is the mean of the radiation sequence data outside the door, which is mainly used here to describe the radiation level of the environmental background value; Indicates the second difference. For the first The moment before what appeared to be an out-of-door performance The slope value of the change at each moment (obtained by subtracting the radiation value of the previous moment from the radiation value at that moment).

[0142] in, As a weight, the main goal is to quantify the degree of sudden increase based on the steep slope of the change in radiation value.

[0143] Calculate the difference in radiation values ​​between the current suspected external manifestation time and each external manifestation time in the historical time period, as well as the first difference between the first radiation surge degree and the second radiation surge degree.

[0144] The maximum value of the ratio between the inversely proportional normalized value of the radiation difference and the absolute value corresponding to the first difference is taken as the true probability of the moment when the suspected outside behavior occurs.

[0145] As an example, after determining the first radiation surge degree of each suspected out-of-door performance moment, it is necessary to compare the first radiation surge degree of each suspected out-of-door performance moment with the second radiation surge degree of the actual out-of-door performance moment. At the same time, in order to reduce the influence of the radiation amplitude on the slope similarity calculation, the similarity of radiation is introduced. When the radiation is similar and the radiation surge degree is also similar, then the suspected out-of-door performance moment is more likely to be the actual out-of-door performance moment.

[0146] Since the types of drugs injected into different patients in the injection room may vary, it is sufficient to obtain the true probability of a suspected out-of-door manifestation moment as long as it has a high similarity to a real out-of-door manifestation moment. Therefore, the maximum value is used to obtain the true probability of a suspected out-of-door manifestation moment.

[0147] As an example, with the first Taking a suspected out-of-the-door performance as an example, the true probability... The calculation method can be:

[0148]

[0149] In the formula, For the first The radiation value at a suspected moment outside the door; Of all the moments in history that can be seen from outside the door, the first The radiation value displayed outside the door at any given moment; For the first The degree of the first radiation surge at the moment of suspected external manifestation; This represents the difference in radiation values. Indicates the first difference. Of all the moments in history that can be seen from outside the door, the first The degree of the second radiation surge at the moment of the external manifestation; For the first A suspected out-of-door performance moment relative to all out-of-door performance moments The maximum value of , where exp is the natural constant.

[0150] Step S50: Based on the true probability, determine the completeness of radiation fluctuations in the gate radiation sequence data processed by linear interpolation.

[0151] As an example, the monitored data is missing at this time. The radiation sequence data inside the door is compensated / interpolated by linear interpolation. It is also necessary to determine whether the radiation sequence data inside the door of the sub-machine has complete radiation fluctuation characteristics after being processed by linear interpolation.

[0152] Step S50 includes:

[0153] The true probability is compared with a preset probability threshold, and based on the comparison results, the inferred out-of-door performance time is selected from each suspected out-of-door performance time.

[0154] As an example, the preset probability threshold can be 0.8, 0.9, etc., and there is no specific limitation.

[0155] As an example, taking a preset probability threshold of 0.8 as an example, if the actual probability of a suspected out-of-door performance moment is greater than 0.8, then the suspected out-of-door performance moment with a probability greater than 0.8 is recorded as the inferred out-of-door performance moment.

[0156] If a presumed time of external manifestation is determined, then the third difference between the post-injection radiation level at the suspected drug injection time and the radiation value at the presumed time of external manifestation is calculated.

[0157] As an example, if there is a presumed moment of external manifestation, indicating the actual existence of injection behavior, it is necessary to obtain the internal radiation sequence data between the previous injection behavior and the current injection behavior, and to make a judgment on the internal radiation sequence data.

[0158] As an example, the determination of fluctuation integrity is mainly based on the presence or absence of the following parameters: the short-term peak value at the moment of injection, which reflects the strongest radiation exposure during drug injection and is directly related to operational safety risks and short-term dose shocks (a manifestation of injection probability); the plateau value during the post-injection residence phase, which represents the stable radiation level formed indoors after the patient carries radionuclides and is an important basis for assessing the environmental continuous dose rate and long-term exposure of personnel (a manifestation of post-injection radiation level); and the recovery process after the patient leaves, which reflects whether there is residual pollution or waste indoors and can help determine whether the operation is standardized and whether the environmental recovery is timely (predicting whether the environmental background value returns after the time of the outside appearance).

[0159] As an example, firstly, the injection probability of the suspected injection time, the radiation level after injection at the suspected injection time, and the radiation value at the predicted outside-gate time are obtained within the time interval from the previous outside-gate performance time to the predicted outside-gate performance time after interpolation. The third difference represents the difference between the radiation value at the suspected drug injection time and the radiation value at the predicted outside-gate performance time.

[0160] Based on the injection probability of suspected drug injection time, the third difference, the inferred time of external manifestation, and the average radiation value within the second preset time period after each time of external manifestation, the completeness of radiation fluctuation at each suspected drug injection time within the time interval between the previous time of external manifestation and the current time is calculated.

[0161] As an example, for any suspected injection time within the time interval, the current fluctuation integrity S is calculated as follows:

[0162]

[0163] In the formula, The probability of injection at the suspected injection time; The radiation level after injection at the suspected injection time; To infer the radiation values ​​of the radiation sequence outside the door at the moment of the external manifestation; This represents the third difference. To estimate the mean radiation value of the radiation sequence inside the door within 3 seconds after the moment of the external manifestation; The mean of the radiation values ​​of the "inside-door radiation sequence within 3 seconds after the last 3 seconds" for all historical outside-door manifestation moments is used to describe the background environmental value when the patient leaves, and exp is the natural constant.

[0164] in, This is because both the indoor radiation level during the post-injection stay and the instantaneous peak value when the patient leaves and passes the external radionuclide both reflect the radiation contribution of the radionuclide in the patient's body to the surrounding environment, so they are similar. Therefore, combining... The integrity of the reaction data after interpolation.

[0165] Step S60: Based on the integrity of radiation fluctuations, generate the required data compensation measures.

[0166] As an example, corresponding data compensation measures can be generated based on the integrity of radiation fluctuations to avoid false alarms due to missed data measurements.

[0167] Step S60 includes:

[0168] The integrity of radiation fluctuations is compared with a preset integrity threshold.

[0169] If the integrity of the radiation fluctuation is greater than the preset integrity threshold, the linear interpolation method is deemed effective for compensating for the radiation sequence data within the gate, and the radiation sequence data within the gate is considered complete monitoring data.

[0170] As an example, the preset integrity threshold can be 0.8, 0.9, etc., and there is no specific limitation.

[0171] As an example, taking a preset integrity threshold of 0.9 as an example, if If the value is greater than 0.9, it is considered that although there was a brief data gap in the radiation sequence within the gate, after interpolation to complete it, it did not have a significant impact on radiation monitoring, and the monitoring data still has strong integrity. The radiation sequence data within the gate is considered complete monitoring data.

[0172] If the integrity of radiation fluctuations is less than or equal to the preset integrity threshold, and data loss still exists after data compensation using linear interpolation, a data supplementation warning will be reported.

[0173] As an example, if If the value is less than or equal to 0.9, it is considered that the patient received an injection, but the monitoring device did not perform effective monitoring. An alarm needs to be triggered to prompt the doctor to use a portable radiation inspection device to conduct supplementary measurements on the corresponding patient and the surrounding environment.

[0174] As an example, if the true probability of all suspected out-of-door manifestations is less than 0.8, then it is assumed that no patients have entered or exited so far, and the interpolation result is maintained.

[0175] Specifically, the overall implementation flowchart of this application is as follows: Figure 2 As shown, firstly, external radiation sequence data and internal radiation sequence data are acquired. Then, the injection time is screened based on the fluctuation characteristics of the internal radiation sequence data. Based on the injection time, the external manifestation time in the external radiation sequence is located. Then, the probability of actual injection is determined based on the fluctuation of the external radiation sequence and the similarity between the external manifestation time and the external manifestation time. By interpolating the monitored data and judging the completeness of the interpolated data, different remedial measures are implemented according to the different degrees of completeness.

[0176] This application provides a real-time processing method for missing values ​​in regional radiation monitoring data. In this embodiment, by acquiring the radiation sequence data inside and outside the door generated during the operation of the regional radiation monitoring instrument within a historical time period, the drug injection time is determined based on the fluctuation characteristics of the radiation sequence data inside the door. Then, by using the time correspondence between the drug injection time and the radiation sequence data inside and outside the door, the suspected time of external manifestation is determined. Finally, by comparing the suspected time of external manifestation with the time of external manifestation within the historical time period, the true probability of the suspected time of external manifestation is determined. The true probability is used to determine the integrity of the radiation fluctuation in the radiation sequence data inside the door. Based on the integrity of the radiation fluctuation, it is determined whether the monitored radiation sequence data needs compensation, and the required data compensation measures are generated to avoid affecting the accurate judgment and safety warning of abnormal radiation events due to inaccurate data.

[0177] Reference Figure 3 ,Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application.

[0178] like Figure 3 As shown, the real-time processing device for missing data values ​​from the radiation monitoring instrument in this area may include: a processor 1001, a memory 1003, and a communication bus 1002. The communication bus 1002 is used to establish communication between the processor 1001 and the memory 1003.

[0179] Optionally, the real-time processing device for missing data from the radiation monitoring instrument in this area may also include a user interface, a network interface, a camera, RF (Radio Frequency) circuitry, sensors, a WiFi module, etc. The user interface may include a display screen and an input submodule such as a keyboard; optional user interfaces may also include standard wired or wireless interfaces. The network interface may include standard wired or wireless interfaces (such as a Wi-Fi interface).

[0180] Those skilled in the art will understand that Figure 3 The structure of the real-time processing device for missing data values ​​of the regional radiation monitor shown in the figure does not constitute a limitation on the real-time processing device for missing data values ​​of the regional radiation monitor. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0181] like Figure 3 As shown, the memory 1003, serving as a storage medium, may include an operating system, a network communication module, and a real-time processing program for missing data values ​​from the regional radiation monitor. The operating system is a program that manages and controls the hardware and software resources of the real-time processing device for missing data values ​​from the regional radiation monitor, supporting the operation of the real-time processing program for missing data values ​​from the regional radiation monitor, as well as other software and / or programs. The network communication module is used to enable communication between the various components within the memory 1003, as well as communication with other hardware and software in the real-time processing system for missing data values ​​from the regional radiation monitor.

[0182] exist Figure 3 In the real-time processing device for missing data values ​​of the regional radiation monitor shown, the processor 1001 is used to execute the real-time processing program for missing data values ​​of the regional radiation monitor stored in the memory 1003, and implement the steps of the real-time processing method for missing data values ​​of the regional radiation monitor as described above.

[0183] The specific implementation of the real-time processing device for missing data values ​​of regional radiation monitoring instruments in this application is basically the same as the embodiments of the real-time processing method for missing data values ​​of regional radiation monitoring instruments described above, and will not be repeated here.

[0184] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0185] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0186] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0187] The above are merely preferred embodiments of this application and do not limit the scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the scope of protection of this application.

[0188] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0189] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for real-time processing of missing values ​​in regional radiation monitoring instrument data, characterized in that, The method includes: Acquire the radiation sequence data inside and outside the door generated during the operation of the regional radiation monitoring instrument within a historical time period; The timing of drug injection is determined based on the fluctuation characteristics of the radiation sequence data within the gate. Based on the time correspondence between the drug injection time, the radiation sequence data inside the door and the radiation sequence data outside the door, the time of manifestation outside the door is determined, wherein the time of manifestation outside the door represents the time when the radiation value changes the most when the patient leaves the injection room; By comparing multiple suspected out-of-door performance moments before the current moment with out-of-door performance moments within a historical time period, the true probability of suspected out-of-door performance moments can be obtained. Based on the true probability, the completeness of radiation fluctuations in the in-gate radiation sequence data processed by linear interpolation is determined. Based on the integrity of the radiation fluctuations, generate the required data compensation measures; The data compensation measures generated based on the integrity of the radiation fluctuations include: The integrity level of the radiation fluctuations is compared with a preset integrity threshold. If the integrity of the radiation fluctuation is greater than the preset integrity threshold, it is determined that the linear interpolation method is effective for compensating the radiation sequence data inside the door, and the radiation sequence data inside the door belongs to the complete monitoring data. If the integrity of the radiation fluctuation is less than or equal to the preset integrity threshold, and it is determined that there are still missing data after the linear interpolation method is used to compensate for the radiation sequence data inside the door, a data supplementation warning will be reported to prompt the doctor to use a portable radiation inspection device to supplement the measurement of the corresponding patient and the on-site environment.

2. The real-time processing method for missing data values ​​of a regional radiation monitoring instrument as described in claim 1, characterized in that, Determining the drug injection time based on the fluctuation characteristics of the intragate radiation sequence data includes: Obtain all first maxima in the radiation sequence data inside the gate, and use the time corresponding to each first maxima as the suspected drug injection time. Based on the degree of change in radiation value within a first preset time period before the suspected drug injection time, the pre-injection radiation level at each of the suspected drug injection times is calculated. Based on the degree of change in radiation value within a first preset time period after the suspected drug injection time, the post-injection radiation level at each of the suspected drug injection times is calculated. The timing of drug injection is determined based on the radiation levels after injection, before injection, and the radiation value at the suspected time of drug injection.

3. The real-time processing method for missing data values ​​of a regional radiation monitoring instrument as described in claim 2, characterized in that, The calculation of the post-injection radiation level at each suspected drug injection time, based on the degree of radiation value change within a first preset time period after the suspected drug injection time, includes: The radiation value change index and the first radiation value are determined at each time within a first preset time period after the suspected drug injection time, wherein the radiation value change index at the current time is the absolute value of the difference between the radiation value at the previous time and the radiation value at the current time. Calculate the minimum exponential value of radiation value change within the time interval between the suspected drug injection time and each other time interval; The normalized value of the difference between the radiation value change index and the minimum value of the radiation value change index is multiplied by the first radiation value to calculate the post-injection radiation level at each of the suspected drug injection times.

4. The real-time processing method for missing data values ​​of a regional radiation monitoring instrument as described in claim 2, characterized in that, The determination of the drug injection time based on the post-injection radiation level, the pre-injection radiation level, and the radiation value at the suspected drug injection time includes: Based on the difference between the radiation level after injection and the radiation level before injection, the degree of radiation retention at each of the suspected drug injection times is calculated. Based on the degree of radiation retention during injection and the radiation value at the suspected drug injection time, the injection probability at each of the suspected drug injection times is calculated. Based on the injection probability, each of the suspected drug injection times is clustered, and the drug injection time is selected from the clusters obtained after clustering.

5. The real-time processing method for missing data values ​​of a regional radiation monitoring instrument as described in claim 2, characterized in that, The determination of the external manifestation time based on the time correspondence between the drug injection time, the intra-door radiation sequence data, and the external radiation sequence data includes: Determine multiple first moments located between two adjacent drug injection moments; A neighborhood window of a preset length is established centered on the first moment. For any given first moment, based on the difference in radiation values ​​at each moment on either side of the first moment within the neighborhood window, the first probability that the current first moment is the time to leave is calculated. Mark the first moment corresponding to the maximum value of the first probability as the exit moment between two adjacent drug injection moments; Obtain multiple second maxima in the radiation sequence data outside the door. For any given exit time, mark the time corresponding to the second maxima closest to the exit time as the exit time.

6. The real-time processing method for missing data values ​​of a regional radiation monitoring instrument as described in claim 5, characterized in that, The calculation of the first probability that the current first moment is the departure moment based on the difference in radiation values ​​at various times on both sides of the first moment within the neighborhood window includes: Determine the first mean of the radiation values ​​at each time point to the left of the first time point in the neighborhood window, and the second mean of the radiation values ​​at each time point to the right of the first time point; Calculate the pre-injection radiation level at the time preceding the first drug injection. Based on the difference between the first mean and the second mean, and the difference between the second mean and the pre-injection radiation level, the first probability that the current first moment is the time to leave is calculated.

7. The real-time processing method for missing data values ​​of a regional radiation monitoring instrument as described in claim 5, characterized in that, The step of comparing multiple suspected instances of outside-door behavior before the current time with instances of outside-door behavior within a historical time period to obtain the true probability of a suspected instance of outside-door behavior includes: Obtain all second maxima from the previous exit time to the current time in the radiation sequence data outside the door, and mark each second maxima as a suspected time of outside the door manifestation; Based on the changes in radiation values ​​at various times before the suspected external manifestation time, the first radiation surge degree at each of the suspected external manifestation times is calculated, and the second radiation surge degree at each external manifestation time within the historical time period is calculated. Calculate the difference in radiation values ​​between the current suspected external manifestation time and each external manifestation time in the historical time period, as well as the first difference between the first radiation surge degree and the second radiation surge degree; The maximum value of the ratio between the inversely proportional normalized value of the radiation value difference and the absolute value corresponding to the first difference is taken as the true probability of the suspected external manifestation moment.

8. The real-time processing method for missing data values ​​of a regional radiation monitoring instrument as described in claim 7, characterized in that, The calculation of the first radiation surge degree at each of the suspected external manifestation times, based on the radiation value changes at various times prior to the suspected external manifestation time, includes: Calculate the second difference between the radiation values ​​at each time point before the suspected external manifestation time and the mean of the corresponding radiation values ​​in the external radiation sequence data; Multiply the normalized value of the second difference by the slope value of the corresponding change in radiation value at each time before the suspected external manifestation time to obtain the first radiation surge degree at each of the suspected external manifestation times.

9. The real-time processing method for missing data values ​​of a regional radiation monitoring instrument as described in claim 5, characterized in that, The determination of the completeness of radiation fluctuations in the in-gate radiation sequence data processed by linear interpolation based on the true probability includes: The true probability is compared with a preset probability threshold, and based on the comparison result, the inferred time of the outside behavior is selected from each of the suspected times of the outside behavior. If a presumed time of external manifestation is determined, then calculate the third difference between the post-injection radiation level at the suspected drug injection time and the radiation value at the presumed time of external manifestation. Based on the injection probability of the suspected drug injection time, the third difference, the inferred time of external manifestation, and the average radiation value within a second preset time period after each time of external manifestation, the completeness of radiation fluctuations at each of the suspected drug injection times within the time interval between the previous time of external manifestation and the current time is calculated.

Images