Multi-modal medical image data storage method and system

Abstract

The invention relates to the field of data storage, and discloses a multi-modal medical image data storage method and system, which are used for solving the problem of data loss or damage caused by unstable electric power when image data is stored, and the method comprises the following steps: acquiring image data through various medical imaging devices, preprocessing the image data, and storing the preprocessed image data into a database; the method comprises the following steps: integrating data of different modalities into a unified format by utilizing labeling, registration and fusion technologies, storing image data integrated into the unified format into a database, compressing and encrypting the image data, and when new data is added, archiving old image data according to use frequency and input time, and storing the old image data into a database; by taking measures in advance before a power problem occurs, the security of image data during storage is effectively improved, and the initiative of data protection is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of data storage, and more specifically to a multimodal medical imaging data storage method and system. Background Art

[0002] Multimodality refers to the multiple types and imaging methods of medical imaging data, which are usually generated by different types of imaging devices. Each imaging device provides imaging data with specific characteristics through different imaging principles and technologies to show the different physiological structures and tissue information of patients. These different modal images combined together can provide more comprehensive and detailed diagnostic information.

[0003] In the modern medical environment, multimodal imaging data such as CT, MRI, and ultrasound are widely used in clinical diagnosis. These data are huge in volume and have high fidelity requirements, so the integrity and security of the storage process are crucial.

[0004] However, during the storage process, unstable power or power outages will directly threaten the security of data, resulting in data loss or damage, which in turn affects the accuracy of diagnosis. Currently, most existing storage systems rely on UPS and backup power supplies, but lack an evaluation system based on multi-parameter power status and device status. Power protection that relies solely on the hardware layer is difficult to fully identify high-risk power environments and take measures in advance before power problems occur, resulting in passive data protection.

[0005] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a multimodal medical image data storage method and system to solve the problems existing in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The multimodal medical image data storage method comprises the following steps:

[0009] Step 1: Obtain imaging data through a variety of medical imaging devices;

[0010] Step 2: Preprocess the image data, including noise filtering, contrast adjustment and spatial registration; integrate the data of different modalities into a unified format using annotation, registration and fusion techniques;

[0011] Step 3: Store the image data in a unified format in a database, and compress and encrypt the image data;

[0012] Step 4: New data is added and old image data is archived according to frequency of use and entry time.

[0013] Preferably, the step of storing the image data integrated into a unified format in a database is:

[0014] Acquire data security data, and obtain a data missing index based on the data security data evaluation, wherein the data security data includes power stability data, high-power equipment switching conditions, equipment temperature data, and circuit aging data;

[0015] Judging the image data storage based on the data missing index;

[0016] When it is determined that the image data can be stored currently, the image data is stored in the database.

[0017] Preferably, the step of obtaining data security data and obtaining a data missing index based on the data security data evaluation is:

[0018] Acquire power stability data, and obtain a power stability coefficient according to the power stability data, wherein the power stability data includes voltage stability data, current stability data, frequency data, total harmonic distortion, and power factor;

[0019] Obtain the switching status of high-power equipment, and obtain the power load change coefficient according to the switching status of the high-power equipment;

[0020] Acquire device temperature data, and obtain device temperature anomaly coefficient based on the device temperature data;

[0021] Acquire circuit aging data, and obtain a circuit aging coefficient according to the circuit aging data;

[0022] The method for obtaining the data missing index based on the power stability coefficient, power load variation coefficient, equipment temperature anomaly coefficient, and circuit aging coefficient is as follows: Wherein, DM represents the data missing index, PS represents the power stability coefficient, CE represents the power load variation coefficient, AT represents the equipment temperature anomaly coefficient, CA represents the circuit aging coefficient, and a1, a2, a3, and a4 represent the weight coefficients of the power stability coefficient, the power load variation coefficient, the equipment temperature anomaly coefficient, and the circuit aging coefficient.

[0023] Preferably, the step of obtaining the power stability coefficient is:

[0024] The voltage data in the detection period is obtained through the power monitoring tool, and the standard deviation of the voltage and the average value of the voltage in the detection period are calculated based on the voltage data in the detection period; the voltage fluctuation rate is calculated based on the standard deviation of the voltage and the average value of the voltage;

[0025] The current data in the detection period is obtained through the power monitoring tool, and the standard deviation of the current and the average value of the current in the detection period are calculated based on the current data in the detection period; the current fluctuation rate is calculated based on the standard deviation of the current and the average value of the current;

[0026] The frequency data in the detection period is obtained through the power monitoring tool, and the standard deviation of the frequency in the detection period and the average value of the frequency are calculated according to the frequency data in the detection period; the frequency fluctuation rate is calculated according to the standard deviation of the frequency and the average value of the frequency;

[0027] The total harmonic distortion and power factor are obtained through power monitoring tools. The method for obtaining the power stability coefficient based on voltage fluctuation rate, current fluctuation rate, frequency fluctuation rate, total harmonic distortion and power factor is as follows: Where PS is the power stability factor, V var Expressed as voltage fluctuation rate, I var Expressed as the current fluctuation rate, f var It is expressed as frequency fluctuation rate, THD means total harmonic distortion, and PF means power factor.

[0028] Preferably, the step of obtaining the power load variation coefficient is:

[0029] Set a power threshold and record devices with power greater than the power threshold as high-power devices;

[0030] Real-time statistics of the number of times high-power equipment is switched on and off during the detection time;

[0031] The power load variation coefficient is calculated based on the number of times the high-power equipment is switched on and off during the detection period.

[0032] Preferably, the circuit aging coefficient acquisition step is:

[0033] Obtaining an initial resistance value and a current resistance value, and calculating a resistance increase rate according to the initial resistance value and the current resistance value;

[0034] The method of obtaining the time since the last circuit maintenance and the circuit aging coefficient according to the resistance increase rate and the time since the last circuit maintenance is as follows: Where CA is the circuit aging coefficient, R rt Expressed as the resistance increase rate, T sm Indicates the time since the last circuit maintenance.

[0035] Preferably, the step of determining the image data storage according to the data missing index is:

[0036] The data missing index is compared with the preset threshold. If the data missing index is less than the preset threshold, it is determined that the current data missing probability is small, and the image data can be stored at present; if the data missing index is greater than or equal to the preset threshold, it is determined that the current data missing probability is high, and the image data cannot be stored at present, and risk processing is performed.

[0037] Preferably, the risk management step is:

[0038] When the data loss index is greater than or equal to a preset threshold, the backup power supply of the data storage device is started, and automatic recovery and data protection measures are started. The automatic recovery and data protection measures include data caching, data backup and I / O control.

[0039] Preferably, a multimodal medical image data storage system comprises:

[0040] An image data acquisition module, used to acquire image data through a medical imaging device and transmit the image data to an image data preprocessing module;

[0041] An image data preprocessing module is used to receive the image data transmitted by the image data acquisition module, preprocess the image data, and transmit the preprocessed image data to the format unification module;

[0042] The format unification module is used to receive the preprocessed image data transmitted by the image data preprocessing module, integrate the image data of different modalities into a unified format, and transmit the image data of the unified format to the data storage module;

[0043] A data storage module, used for receiving the image data in a unified format transmitted by the format unification module, storing the image data in the unified format into a database, and transmitting the database to the data archiving module;

[0044] The data archiving module is used to receive the database transmitted by the data storage module and archive the image data in the database.

[0045] Technical effects and advantages of the present invention:

[0046] Through a variety of medical imaging equipment, image data is acquired and pre-processed. Data of different modalities are integrated into a unified format using annotation, registration, and fusion technologies. The image data integrated into a unified format is stored in a database and compressed and encrypted. When new data is added, old image data is archived based on frequency of use and entry time. By taking measures in advance before power problems occur, the security of image data during storage can be effectively improved, and the initiative of data protection can be strengthened. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is the overall flow chart of the present invention.

[0048] Figure 2 It is the overall structure diagram of the present invention. DETAILED DESCRIPTION

[0049] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The multimodal medical imaging data storage method and system involved in the present invention are not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0050] The present invention provides a multimodal medical image data storage method, comprising the following steps:

[0051] Step 1: Obtain image data through a variety of medical imaging devices, such as CT, MRI, and X-ray. The characteristics of multimodal data are that different devices collect different data formats, resolutions, and imaging methods;

[0052] Step 2: Preprocess the image data, including noise filtering, contrast adjustment, and spatial registration, to ensure that data of different modalities are under the same standard; use annotation, registration, and fusion technology to integrate data of different modalities into a unified format for subsequent unified storage and application;

[0053] In this embodiment, it should be specifically explained that the steps of preprocessing the image data are:

[0054] Use Gaussian filtering to smooth the image and reduce noise, but it will slightly blur the image details. Set the standard deviation parameter of the filter, select the appropriate filter radius, apply the Gaussian filter, calculate the weighted average around each pixel, and generate a smooth image.

[0055] Gaussian filtering is a filtering technique used for image smoothing. It reduces noise by taking a weighted average of the pixel values ​​of each pixel in the image and its neighbors. Gaussian filtering uses a Gaussian function as a weight distribution, so that the weight of the central pixel is the largest, and the weight decreases as the distance from the center increases. This reduces small noise while maintaining the overall outline of the image. Gaussian filtering is widely used to remove random noise, reduce image details, and perform image preprocessing, providing a smoother visual effect for subsequent image analysis.

[0056] Use histogram equalization to adjust the grayscale distribution of the image to make it more uniform and improve the contrast. Calculate the grayscale histogram of the image to obtain the probability distribution of each grayscale level, calculate the cumulative distribution function, and use the cumulative distribution function to remap the grayscale value of the image. Apply the new grayscale value to generate contrast-enhanced image data.

[0057] Histogram equalization is an image enhancement technique used to adjust the grayscale distribution of an image to make it more uniform, thereby improving the overall contrast of the image. This method remaps the pixel grayscale values ​​in the original image to a new distribution range by calculating the cumulative distribution function of the image grayscale, enhancing the dark and bright details, and making the originally low-contrast image visually clearer.

[0058] Elastic registration is used to generate corresponding feature points or feature areas between the reference image and the image to be registered. An image-based non-rigid registration algorithm is used to adjust the image to be registered locally so that it is morphologically aligned with the reference image. A transformation field is applied to transform the image to be registered into the spatial coordinate system of the reference image.

[0059] Elastic registration is an image alignment technique used to spatially align images with deformation or nonlinear differences. Unlike rigid registration, elastic registration gradually adjusts the image to be registered to the shape of the reference image through local deformation to adapt to the complex morphological differences between images, such as the natural deformation of organs or tissues. Elastic registration is usually based on the matching of feature points or feature regions, and is applied to the alignment of dynamic medical images, multimodal images, or image data from different periods to ensure that images in different morphologies can still be accurately superimposed, thereby facilitating subsequent analysis and diagnosis.

[0060] In this embodiment, it should be specifically explained that the steps of integrating data of different modalities into a unified format by using annotation, registration and fusion technology are as follows:

[0061] Identify important anatomical structures or lesion areas in each modality image. Usually, the same area of ​​CT, MRI, PET and other images is used. Use image segmentation technology or manual annotation tools to accurately outline the boundaries of the target area in each modality image. After the annotation is completed, check the consistency of the annotations of each modality to ensure that the shape and position of each annotated area are accurate, providing a reference for registration.

[0062] Select the modality with clear anatomical structure as the reference image, and the other modality images as the images to be registered. For images with large morphological differences, perform local nonlinear transformation and use overlap metrics to evaluate the alignment accuracy to ensure accurate multi-modal image alignment.

[0063] The pixel intensities of each modality are combined and the image information of different modalities is fused into a single image using methods such as weighted averaging and maximum intensity projection.

[0064] Step 3: Store the image data in a unified format in the database, and compress and encrypt the image data to ensure the efficiency and security of data storage;

[0065] In this embodiment, it should be specifically explained that the steps of storing the image data integrated into a unified format in the database are:

[0066] Obtain data security data and obtain the data missing index based on the data security data assessment. The data security data includes power stability data, high-power equipment switching conditions, equipment temperature data, and circuit aging data;

[0067] Judging the image data storage based on the data missing index;

[0068] When it is determined that the image data can be stored currently, the image data is stored in the database.

[0069] In this embodiment, it should be specifically explained that the steps of obtaining data security data and obtaining the data missing index according to the data security data evaluation are as follows:

[0070] Acquire power stability data, and obtain a power stability coefficient according to the power stability data, the power stability data including voltage stability data, current stability data, frequency data, total harmonic distortion and power factor;

[0071] Obtain the switching status of high-power equipment, and obtain the power load change coefficient according to the switching status of the high-power equipment;

[0072] The method for obtaining the device temperature data and obtaining the device temperature anomaly coefficient according to the device temperature data is as follows: AT is the equipment temperature anomaly coefficient, T ct Represents the real-time temperature of the current device, T nl It is expressed as the reference temperature of the equipment in normal state;

[0073] Acquire circuit aging data, and obtain a circuit aging coefficient according to the circuit aging data;

[0074] The method for obtaining the data missing index based on the power stability coefficient, power load variation coefficient, equipment temperature anomaly coefficient, and circuit aging coefficient is as follows: Where DM represents the data loss index, PS represents the power stability coefficient, which reflects the reliability of the power supply system and the stability of the voltage and current. When the coefficient is high, it means that the power supply of the power grid is stable, the voltage fluctuation is small, and the equipment operating environment is stable; at this time, the data writing and storage process in the system is not easily affected by power fluctuations, the data loss index is also correspondingly low, and the data security is higher. However, if the power stability coefficient decreases, it means that the power supply is unstable, the voltage or current fluctuates frequently, and the data storage process may frequently encounter interruptions, I / O errors, etc., resulting in a significant increase in the risk of data loss. Therefore, the power stability coefficient is inversely proportional to the data loss index, which can effectively evaluate the security of the storage process through the power supply status and guide whether to enable the protection mechanism. CE represents the power load variation coefficient, which reflects the frequency and amplitude of load fluctuations in the power supply system. When the coefficient is high, it means that the equipment in the power supply network is frequently started or stopped, and the load power changes sharply, resulting in increased instability of the power grid voltage and current. In the case of severe load fluctuations, the voltage may drop or rise instantly, making the storage device more susceptible to voltage mutations, power outages, or short-term power instability during operation, resulting in data write interruption or storage failure, thereby increasing the data loss index. By monitoring the load variation coefficient, we can predict the fluctuation of the power grid, evaluate the potential power risks in the data storage process, and take corresponding protective measures to reduce the risk of data loss. AT is the device temperature anomaly coefficient, which reflects the degree to which the operating temperature of the storage device deviates from the normal range, usually affected by factors such as unstable power, excessive equipment load, and insufficient heat dissipation. When the temperature anomaly coefficient increases, the internal components of the device (such as hard disk, CPU, memory, etc.) will be in a high temperature state, which is easy to cause hard disk read and write errors, accelerate the aging of storage chips, and even cause the device to automatically shut down or restart, causing data write interruption and data corruption. In addition, long-term high temperature will have an irreversible impact on the stability of the device and increase the potential risk of data loss. Therefore, monitoring the device temperature anomaly coefficient can help determine whether the system environment is suitable for data storage. When the coefficient is too high, cooling measures or data protection mechanisms should be started in time to reduce data loss caused by temperature anomalies. CA is the circuit aging coefficient, which reflects the degree of performance degradation of the circuit due to long-term use or insufficient maintenance, including poor contact, reduced insulation, and increased line resistance. As the circuit aging coefficient increases, the circuit's anti-interference ability and voltage stability decrease, and problems such as current instability and voltage drop are prone to occur, which directly affects the power supply quality of data storage devices. When the aging circuit is subjected to high-power loads or voltage fluctuations, it may not be able to maintain normal power supply, and may even cause short circuits or power outages, resulting in interruption of data writing during storage, data loss, or equipment damage.Therefore, by monitoring the circuit aging coefficient, the reliability of the power system can be evaluated. When the aging coefficient is too high, timely maintenance or circuit replacement measures should be taken to ensure the security and continuity of data storage. a1, a2, a3, and a4 are expressed as weight coefficients of power stability coefficient, power load variation coefficient, equipment temperature anomaly coefficient, and circuit aging coefficient, and a1+a2+a3+a4=1. The specific values ​​of a1, a2, a3, and a4 are determined by professionals based on actual conditions. For example, a1, a2, a3, and a4 can be 0.4, 0.3, 0.2, and 0.1, respectively.

[0075] In this embodiment, it should be specifically explained that the steps for obtaining the power stability coefficient are:

[0076] The voltage data within the detection period is obtained through the power monitoring tool. The detection period is set by professionals and can be 1s or 10s. The standard deviation of the voltage and the average value of the voltage within the detection period are calculated based on the voltage data within the detection period. The method for obtaining the voltage fluctuation rate based on the standard deviation of the voltage and the average value of the voltage is as follows: Where V var Expressed as voltage fluctuation rate, σ V Expressed as the standard deviation of voltage, Expressed as the average value of voltage;

[0077] The current data in the detection period is obtained through the power monitoring tool, and the standard deviation of the current and the average value of the current in the detection period are calculated according to the current data in the detection period; the method for obtaining the current fluctuation rate according to the standard deviation of the current and the average value of the current is: Among them I var Expressed as the current fluctuation rate, σ I Expressed as the standard deviation of the current, Expressed as the average value of the current;

[0078] The frequency data in the detection period is obtained through the power monitoring tool, and the standard deviation and the average value of the frequency in the detection period are calculated according to the frequency data in the detection period; the method for obtaining the frequency fluctuation rate according to the standard deviation and the average value of the frequency is as follows: where f var Expressed as frequency volatility, σ f Expressed as the standard deviation of the frequencies, Expressed as the mean value of frequencies;

[0079] The total harmonic distortion and power factor are obtained through power monitoring tools. The method for obtaining the power stability coefficient based on voltage fluctuation rate, current fluctuation rate, frequency fluctuation rate, total harmonic distortion and power factor is as follows: Where PS is the power stability factor, V var Expressed as voltage fluctuation rate, Ivar Expressed as the current fluctuation rate, f var It is expressed as frequency fluctuation rate, THD is expressed as total harmonic distortion, and PF is expressed as power factor. Using the natural exponential function, the instability index can be "flipped" into a stability coefficient, that is, when all instability factors approach 0, the stability coefficient approaches 1, indicating that the system is very stable. If the instability factors increase, the result of the exponential function will decay rapidly, and the stability coefficient approaches 0, indicating that the system is unstable.

[0080] Total harmonic distortion is a measure of the degree of distortion of a voltage or current waveform relative to an ideal sine wave, usually expressed as a percentage. Total harmonic distortion reflects the relative content of harmonic components (i.e., non-fundamental frequency components) in the power signal. Higher total harmonic distortion indicates that the waveform contains more harmonic distortion, which may affect the normal operation of the power system and equipment.

[0081] The power factor is an indicator that measures the ratio of active power (actual power doing work) to apparent power (the product of voltage and current) in the power system, and usually ranges from 0 to 1. The closer the power factor is to 1, the higher the power utilization rate, the larger the proportion of active power, and the better the efficiency of the power system; conversely, a low power factor means that there is more reactive power in the system, leading to problems such as power waste, equipment heating, and increased transmission losses.

[0082] In this embodiment, it should be specifically explained that the steps for obtaining the power load variation coefficient are:

[0083] Set a power threshold and record devices with power greater than the power threshold as high-power devices;

[0084] Real-time statistics of the number of times high-power equipment is switched on and off during the detection time;

[0085] The method for obtaining the power load variation coefficient according to the number of times the high-power equipment is switched on and off during the detection period is: Where CE is the power load variation coefficient, N S Indicates the number of times a high-power device switches on and off, t j Indicates the detection time period.

[0086] In this embodiment, it should be specifically explained that the steps for obtaining the circuit aging coefficient are:

[0087] The method of obtaining the initial resistance value and the current resistance value and obtaining the resistance increase rate according to the initial resistance value and the current resistance value is as follows: Where R rt Expressed as the resistance increase rate, R ct Expressed as the current resistance value, R il Expressed as initial resistance value;

[0088] Get the time since the last circuit maintenance, usually in months or years. The longer the time, the longer the circuit has not been maintained. Problems such as aging and poor connection may occur, resulting in unstable load. The method to obtain the circuit aging coefficient based on the resistance increase rate and the time since the last circuit maintenance is as follows: Where CA is the circuit aging coefficient, R rt Expressed as the resistance increase rate, T sm It is expressed as the time since the last circuit maintenance. The square root of the resistance increase rate is taken to moderately smooth the impact of the resistance increase, avoiding a small increase from having too much impact on the result. The logarithm of the time since the last maintenance is taken to indicate that as the maintenance time increases, the load change coefficient gradually increases. At the same time, the logarithmic function gradually reduces the increase in the influence of maintenance time on the coefficient, avoiding an infinite increase in the load change coefficient due to too long a time.

[0089] In this embodiment, it should be specifically explained that the steps of determining the image data storage according to the data missing index are:

[0090] The data missing index is compared with the preset threshold. If the data missing index is less than the preset threshold, it is determined that the current data missing probability is small, and the image data can be stored at present; if the data missing index is greater than or equal to the preset threshold, it is determined that the current data missing probability is large, and the image data cannot be stored at present, and risk processing is performed.

[0091] In this embodiment, it should be specifically explained that the risk handling steps are:

[0092] When the data loss index is greater than or equal to the preset threshold, the backup power supply of the data storage device is started, and automatic recovery and data protection measures are started. The automatic recovery and data protection measures include data caching, data backup, and I / O control, etc., to ensure that data loss is minimized before power is restored.

[0093] Step 4: As new data is added, old image data is archived based on usage frequency, entry time, etc. to ensure the system's storage space and access efficiency.

[0094] In this embodiment, it is necessary to specifically explain that the multimodal medical image data storage system includes:

[0095] An image data acquisition module, used to acquire image data through a medical imaging device and transmit the image data to an image data preprocessing module;

[0096] The image data preprocessing module is used to receive the image data transmitted by the image data acquisition module, and preprocess the image data to ensure that the data of different modalities are under the same standard, and transmit the preprocessed image data to the format unification module;

[0097] The format unification module is used to receive the preprocessed image data transmitted by the image data preprocessing module, and integrate the image data of different modalities into a unified format to facilitate subsequent unified storage and application, and transmit the image data in the unified format to the data storage module;

[0098] A data storage module, used for receiving the image data in a unified format transmitted by the format unification module, storing the image data in the unified format into a database, and transmitting the database to the data archiving module;

[0099] The data archiving module is used to receive the database transmitted by the data storage module and archive the image data in the database.

[0100] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0101] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for storing multimodal medical image data, characterized in that: The following steps are involved: Step 1: Obtain imaging data through a variety of medical imaging devices; Step 2: Preprocess the image data, including noise filtering, contrast adjustment and spatial registration; integrate the data of different modalities into a unified format using annotation, registration and fusion techniques; Step 3: Store the image data in a unified format in a database, and compress and encrypt the image data; Step 4: New data is added and old image data is archived according to frequency of use and entry time.

2. The multimodal medical image data storage method according to claim 1, characterized in that: The steps of storing the image data integrated into a unified format in the database are: Acquire data security data, and obtain a data missing index based on the data security data evaluation, wherein the data security data includes power stability data, high-power equipment switching conditions, equipment temperature data, and circuit aging data; Judging the image data storage based on the data missing index; When it is determined that the image data can be stored currently, the image data is stored in the database.

3. The multimodal medical image data storage method according to claim 2, characterized in that: The steps of obtaining data security data and obtaining a data missing index based on the data security data evaluation are as follows: Acquire power stability data, and obtain a power stability coefficient according to the power stability data, wherein the power stability data includes voltage stability data, current stability data, frequency data, total harmonic distortion, and power factor; Obtain the switching status of high-power equipment, and obtain the power load change coefficient according to the switching status of the high-power equipment; Acquire device temperature data, and obtain device temperature anomaly coefficient based on the device temperature data; Acquire circuit aging data, and obtain a circuit aging coefficient according to the circuit aging data; The method for obtaining the data missing index based on the power stability coefficient, power load variation coefficient, equipment temperature anomaly coefficient, and circuit aging coefficient is as follows: Wherein, DM represents the data missing index, PS represents the power stability coefficient, CE represents the power load variation coefficient, AT represents the equipment temperature anomaly coefficient, CA represents the circuit aging coefficient, and a1, a2, a3, and a4 represent the weight coefficients of the power stability coefficient, the power load variation coefficient, the equipment temperature anomaly coefficient, and the circuit aging coefficient.

4. The multimodal medical image data storage method according to claim 3, characterized in that: The steps for obtaining the power stability coefficient are: The voltage data in the detection period is obtained through the power monitoring tool, and the standard deviation of the voltage and the average value of the voltage in the detection period are calculated based on the voltage data in the detection period; the voltage fluctuation rate is calculated based on the standard deviation of the voltage and the average value of the voltage; The current data within the detection period is obtained through the power monitoring tool, and the standard deviation of the current and the average value of the current within the detection period are calculated based on the current data within the detection period; The current fluctuation rate is calculated based on the standard deviation of the current and the average value of the current; The frequency data in the detection period is obtained through the power monitoring tool, and the standard deviation of the frequency in the detection period and the average value of the frequency are calculated according to the frequency data in the detection period; the frequency fluctuation rate is calculated according to the standard deviation of the frequency and the average value of the frequency; The total harmonic distortion and power factor are obtained through power monitoring tools. The method for obtaining the power stability coefficient based on voltage fluctuation rate, current fluctuation rate, frequency fluctuation rate, total harmonic distortion and power factor is as follows: Where PS is the power stability factor, V var Expressed as voltage fluctuation rate, I var Expressed as the current fluctuation rate, f var It is expressed as frequency fluctuation rate, THD means total harmonic distortion, and PF means power factor.

5. The multimodal medical image data storage method according to claim 3, characterized in that: The steps for obtaining the power load variation coefficient are: Set a power threshold and record devices with power greater than the power threshold as high-power devices; Real-time statistics of the number of times high-power equipment is switched on and off during the detection time; The power load variation coefficient is calculated based on the number of times the high-power equipment is switched on and off during the detection period.

6. The multimodal medical image data storage method according to claim 3, characterized in that: The steps for obtaining the circuit aging coefficient are: Obtaining an initial resistance value and a current resistance value, and calculating a resistance increase rate according to the initial resistance value and the current resistance value; The method of obtaining the time since the last circuit maintenance and the circuit aging coefficient according to the resistance increase rate and the time since the last circuit maintenance is as follows: Where CA is the circuit aging coefficient, R rt Expressed as the resistance increase rate, T sm Indicates the time since the last circuit maintenance.

7. The multimodal medical image data storage method according to claim 2, characterized in that: The step of determining the image data storage according to the data missing index is as follows: The data missing index is compared with the preset threshold. If the data missing index is less than the preset threshold, it is determined that the current data missing probability is small, and the image data can be stored at present; if the data missing index is greater than or equal to the preset threshold, it is determined that the current data missing probability is high, and the image data cannot be stored at present, and risk processing is performed.

8. The multimodal medical image data storage method according to claim 7, characterized in that: The steps for risk management are: When the data loss index is greater than or equal to a preset threshold, the backup power supply of the data storage device is started, and automatic recovery and data protection measures are started. The automatic recovery and data protection measures include data caching, data backup and I / O control.

9. A multimodal medical imaging data storage system, characterized in that: The system comprises: An image data acquisition module, used to acquire image data through a medical imaging device and transmit the image data to an image data preprocessing module; An image data preprocessing module is used to receive the image data transmitted by the image data acquisition module, preprocess the image data, and transmit the preprocessed image data to the format unification module; The format unification module is used to receive the preprocessed image data transmitted by the image data preprocessing module, integrate the image data of different modalities into a unified format, and transmit the image data of the unified format to the data storage module; A data storage module, used for receiving the image data in a unified format transmitted by the format unification module, storing the image data in a unified format into a database, and transmitting the database to a data archiving module; The data archiving module is used to receive the database transmitted by the data storage module and archive the image data in the database.

Images