CT original data compression, recovery and storage method and system

Abstract

The invention discloses a CT original data compression, recovery and storage method and system, and the method comprises the following steps: S1, carrying out user interaction and scanning control: enabling a user to preset a storage mode through an interaction unit, starting CT scanning, enabling a data collection system to obtain original data, and enabling an image reconstruction system to synchronously generate a DICOM image; s2, storage mode judgment and branch execution; s3, deleting data and recovering a protection mechanism; s4, an original data recovery process; according to the method, necessary DICOM images are borrowed, original data storage is replaced by residual data, data compression and full utilization of the data are realized, and lossless recovery is supported; a user can flexibly select a storage mode, and the storage cost and the data traceability requirement are balanced; original data writing quantity is reduced in a compression mode, hard disk mechanical loss is remarkably reduced, and the service life of a storage medium is prolonged; double insurance is formed by deleting protection marks and restoring authority control, the risk of deleting key data by mistake is avoided, and the medical data compliance standard is met.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a method and system for compressing, restoring and storing CT raw data. Background Art

[0002] In X-ray tomography (CT) equipment, the amount of data collected by the detector is huge. Especially in CT systems that use photon counting detectors, the amount of data has increased by dozens of times, which has brought extremely high requirements for data storage. On the one hand, the frequent reading and writing operations of massive data will accelerate the aging of the hard disk. On the other hand, in order to meet the hospital's needs for retrospective reconstruction, the original data needs to be preserved for a long time for more potential analysis and research in the future, which further aggravates the storage pressure.

[0003] Therefore, an efficient data storage and management solution is urgently needed to cope with the big data challenges generated by photon counting CT and meet the needs of clinical applications. Summary of the invention

[0004] The purpose of the present invention is to provide a CT raw data compression, recovery and storage method and system to reduce or alleviate the demand of the CT system for raw data storage capacity, thereby extending the service life of the hard disk and ensuring data integrity, and providing a more economical and efficient data storage solution for clinical applications.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for compressing, restoring and storing CT raw data comprises the following steps: S1, user interaction and scanning control, the user presets the storage mode through the interaction unit and starts the CT scan, the data acquisition system obtains the original data, and the image reconstruction system synchronously generates the DICOM image; S2, storage mode determination and branch execution; Mode A (raw data storage): If the user selects the raw data storage mode, the system will write the raw data directly into the storage medium and store it independently from the DICOM images; Mode B (compressed data storage): If the compressed data storage mode is selected, the following sub-process is executed: S2.1 Prediction data generation: The raw data prediction unit calculates the prediction value of the raw data based on the DICOM image through a preset algorithm; S2.2 Residual calculation: Perform pixel-by-pixel difference operation on the predicted data and the original data to generate a residual data matrix; S2.3 Data association tagging: Bind the residual data to the corresponding DICOM image as “residual paired data” and add a deletion protection tag in the DICOM image metadata; S2.4 Residual storage: Only the residual data and the marked DICOM images are saved, and the original data will automatically release the storage space after compression; S3, data deletion and recovery protection mechanism; When a user initiates a DICOM image deletion operation, the system detects whether it is associated with residual data: If there is a deletion protection mark, a pop-up window will be triggered to warn: "This operation will cause the associated original data to be permanently lost. Do you want to continue?" After the user confirms the deletion, the system will simultaneously clear the residual data; if the deletion is cancelled, the complete data chain will be retained; S4, original data recovery process; When the user needs to reconstruct the original data, perform the reverse operation: S4.1 residual data decompression; Read the compression parameter tag in the compressed data packet and call the corresponding decompression module according to the algorithm identifier; If dynamic bit allocation compression is used, the original integer value of the residual data is restored according to the recorded bit width; Perform unsigned inverse operations to restore the positive and negative characteristics of the residual data; S4.2 Data restoration; The decompressed residual data is superimposed with the predicted data to restore the original data. The mathematical expression is: Original data = predicted data + residual data X (-1) 符号标记位 , where: the sign flag bit is generated during the unsigned processing and embedded in the compression parameter tag.

[0006] In a preferred solution, in step S2.1, the preset algorithm includes but is not limited to a forward projection algorithm combined with an inverse correction or a deep learning model, specifically comprising the following steps: S2.1.1 Preset algorithm based on forward projection algorithm combined with inverse correction; Producing projection data by pixel-based orthographic projection, ray-based orthographic projection, or other orthographic projection methods, followed by generating predictions of the original data by inverse correction, which may be done by adding random noise or by inverse calculation through a known correction process; S2.1.2 Prediction algorithm based on deep learning model; Using the pre-trained neural network model, DICOM images are used as input and the predicted values ​​of the original data are directly output; S2.1.3 Model optimization and updating; Dynamically adjust the parameters of the deep learning model based on the feedback from the actual scan data, or update the model through an online learning mechanism to improve prediction accuracy; S2.1.4 Forecast error correction; After the prediction data is generated, the prediction value is locally optimized through the error correction module to reduce the impact of systematic errors and random errors.

[0007] A preferred solution, in step S2.3, further includes the following steps: S2.3.1 Unsigned residual processing; After the residual calculation is completed, the residual data matrix is ​​converted to unsigned, including: Convert negative residuals to non-negative integers through absolute value conversion or offset compensation; Record the conversion rules into the compression parameter tag of the DICOM image metadata for reverse processing during recovery; S2.3.2 Lossless compression algorithm selection and implementation; Based on the statistical characteristics of the residual data, dynamically select one or a combination of the following lossless compression algorithms: A. Compression based on entropy coding: Huffman coding or arithmetic coding is used to optimize the code table for high-frequency small value residuals; B. Differential Pulse Code Modulation (DPCM): differentially encodes adjacent residual pixel values ​​and combines run-length encoding (RLE) to compress continuous zero-value areas; C. Dynamic bit allocation compression: Determine the bit width based on the maximum value of the residual, and truncate high-order redundant zero bits as needed; The compressed residual data is stored as a binary stream and associated with a compression parameter tag.

[0008] In a preferred solution, in step S2.3.2, the specific steps of dynamically selecting a lossless compression algorithm include: S2.3.2.1 Statistical analysis: Analyze the numerical range, distribution density, and statistical characteristics of zero value ratio of residual data; S2.3.2.2 Algorithm matching: Select the optimal compression algorithm combination based on statistical characteristics; S2.3.2.3 Compression efficiency evaluation: Evaluate the compression ratio and computational complexity in real time during the compression process, and dynamically adjust the algorithm parameters; S2.3.2.4 Compression result verification: Ensure that the compressed data can be fully restored when decompressed without information loss.

[0009] A preferred solution, in step S2.4, further includes encapsulating the compressed residual data, the compression parameter label and the marked DICOM image into a compressed data packet and writing it into a storage medium; wherein the encapsulation format of the compressed data packet includes the following contents: S2.4.1 Compressed residual data block: stores the residual data after lossless compression; S2.4.2 DICOM image file: stores the marked DICOM image, including the delete protection flag and compression parameter tag in the metadata; S2.4.3 Compression parameter label: record the residual unsigned processing rules, compression algorithm identifier, dynamic bit allocation information and sign mark bit; S2.4.4 Data verification information: Use CRC verification or hash algorithm to ensure data integrity and consistency.

[0010] In a preferred solution, in step S3, the data deletion and recovery protection mechanism further includes the following steps: S3.1 Data backup: Before the deletion operation is performed, the system automatically backs up the associated residual data and DICOM images to a temporary storage area; S3.2 Deletion log records: record the time of the deletion operation, user information, and key metadata of the deleted data for subsequent audit or recovery; S3.3 Data recovery option: If the user deletes data by mistake, the complete data chain can be restored from the temporary storage area by deleting the log.

[0011] In a preferred solution, in step S4.2, the specific steps of data restoration include: S4.2.1 Prediction data generation: Recalculate the prediction value of the original data based on the DICOM image to ensure that it is consistent with the prediction data during compression; S4.2.2 Residual data superposition: superimpose the decompressed residual data and the predicted data pixel by pixel; S4.2.3 Sign flag bit processing: perform sign recovery on the residual data according to the sign flag bit in the compression parameter tag; S4.2.4 Data Verification: Verify the accuracy of data restoration by comparing the statistical characteristics of the recovered data with the original data.

[0012] In order to better cooperate with the use of the CT raw data compression, recovery and storage method, a CT system using the CT raw data compression, recovery and storage method is also proposed, including a rack unit, a data processing unit and a human-computer interaction unit; The rack unit includes a detector and an X-ray generator; the detector and the X-ray generator are installed opposite to each other, and the scanned object is placed between the detector and the X-ray generator; The data processing unit processes the acquired CT raw data using the CT raw data compression, recovery and storage method; The data processing unit includes an image reconstruction module, a data recovery module and a data storage module; The detector acquires CT raw data and transmits it to the data processing unit; the image reconstruction module of the data processing unit processes the raw data to generate a reconstructed image in DICOM format; the data storage module stores the raw data or residual data according to the instruction of the human-computer interaction unit; the data recovery module restores the raw data using the reconstructed image and residual data as needed; the image reconstruction module performs image reconstruction again using the restored raw data according to the needs of the human-computer interaction unit.

[0013] Due to the application of the above technical solution, the beneficial effects of the present application compared with the prior art are: The present application provides a CT raw data compression, recovery and storage method and system, which use necessary DICOM images and replace the raw data storage with residual data to achieve data compression and full data utilization, and support lossless recovery to meet the integrity requirements of medical image data; users can flexibly choose storage modes to balance storage costs and data traceability requirements, which is especially suitable for research-based medical scenarios that require long-term archiving; the amount of raw data written is reduced in compression mode, which significantly reduces hard disk mechanical wear and extends the service life of storage media; deletion protection marks and recovery permission control form double insurance to avoid the risk of accidental deletion of key data, and meet medical data compliance standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 The figure is a flow chart of a method for compressing, restoring and storing CT raw data of the present invention. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0017] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0018] In the present application, the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings. These terms are mainly used to better describe the present invention and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation.

[0019] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those skilled in the art, the specific meanings of these terms in the present invention can be understood according to specific circumstances.

[0020] In addition, the terms "installed", "set", "provided with", "connected", "connected", and "socketed" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] Embodiment 1 See also Figure 1 The present application provides a method for compressing, restoring and storing CT raw data, comprising the following steps: S1, user interaction and scanning control, the user presets the storage mode through the interaction unit and starts the CT scan, the data acquisition system obtains the original data, and the image reconstruction system synchronously generates the DICOM image; S2, storage mode determination and branch execution; Mode A (raw data storage): If the user selects the raw data storage mode, the system will write the raw data directly into the storage medium and store it independently from the DICOM images; Mode B (compressed data storage): If the compressed data storage mode is selected, the following sub-process is executed: S2.1 Prediction data generation: The raw data prediction unit calculates the prediction value of the raw data based on the DICOM image through a preset algorithm; S2.2 Residual calculation: Perform pixel-by-pixel difference operation on the predicted data and the original data to generate a residual data matrix; S2.3 Data association tagging: Bind the residual data to the corresponding DICOM image as “residual paired data” and add a deletion protection tag in the DICOM image metadata; S2.4 Residual storage: Only the residual data and the marked DICOM images are saved, and the original data will automatically release the storage space after compression; S3, data deletion and recovery protection mechanism; When a user initiates a DICOM image deletion operation, the system detects whether it is associated with residual data: If there is a deletion protection mark, a pop-up window will be triggered to warn: "This operation will cause the associated original data to be permanently lost. Do you want to continue?" After the user confirms the deletion, the system will simultaneously clear the residual data; if the deletion is cancelled, the complete data chain will be retained; S4, original data recovery process; When the user needs to reconstruct the original data, perform the reverse operation: S4.1 residual data decompression; Read the compression parameter tag in the compressed data packet and call the corresponding decompression module according to the algorithm identifier; If dynamic bit allocation compression is used, the original integer value of the residual data is restored according to the recorded bit width; Perform unsigned inverse operations to restore the positive and negative characteristics of the residual data; S4.2 Data restoration; The decompressed residual data is superimposed with the predicted data to restore the original data. The mathematical expression is: Original data = predicted data + residual data X (-1) 符号标记位 , where: the sign flag bit is generated during the unsigned processing and embedded in the compression parameter tag.

[0023] Embodiment 2 The present application provides a method for compressing, restoring and storing CT raw data, comprising the following steps: S1, user interaction and scanning control, the user presets the storage mode through the interaction unit and starts the CT scan, the data acquisition system obtains the original data, and the image reconstruction system synchronously generates the DICOM image; S2, storage mode determination and branch execution; Mode A (raw data storage): If the user selects the raw data storage mode, the system will write the raw data directly into the storage medium and store it independently from the DICOM images; Mode B (compressed data storage): If the compressed data storage mode is selected, the following sub-process is executed: S2.1 Prediction data generation: The raw data prediction unit calculates the prediction value of the raw data based on the DICOM image through a preset algorithm; The preset algorithm includes but is not limited to the forward projection algorithm combined with inverse correction or deep learning model, which specifically includes the following steps: S2.1.1 Preset algorithm based on forward projection algorithm combined with inverse correction: Producing projection data by pixel-based orthographic projection, ray-based orthographic projection or other orthographic projection methods, and then generating predictions of the original data by inverse correction, which adds random noise such as Gaussian noise, Poisson noise, etc., or performs inverse calculations through known correction processes; S2.1.2 Prediction algorithm based on deep learning model; Using the pre-trained neural network model, DICOM images are used as input and the predicted values ​​of the original data are directly output; S2.1.3 Model optimization and updating; Dynamically adjust the parameters of the deep learning model based on the feedback from the actual scan data, or update the model through an online learning mechanism to improve prediction accuracy; S2.1.4 Forecast error correction; After the prediction data is generated, the prediction value is locally optimized through the error correction module to reduce the influence of systematic errors and random errors; S2.2 Residual calculation: Perform pixel-by-pixel difference operation on the predicted data and the original data to generate a residual data matrix; S2.3 Data association tagging: Bind the residual data to the corresponding DICOM image as “residual paired data” and add a deletion protection tag in the DICOM image metadata; S2.3.1 Unsigned residual processing; After the residual calculation is completed, the residual data matrix is ​​converted to unsigned, including: Convert negative residuals to non-negative integers through absolute value conversion or offset compensation; Record the conversion rules into the compression parameter tag of the DICOM image metadata for reverse processing during recovery; S2.3.2 Lossless compression algorithm selection and implementation; Based on the statistical characteristics of the residual data, dynamically select one or a combination of the following lossless compression algorithms: A. Compression based on entropy coding: Huffman coding or arithmetic coding is used to optimize the code table for high-frequency small value residuals; B. Differential Pulse Code Modulation (DPCM): differentially encodes adjacent residual pixel values ​​and combines run-length encoding (RLE) to compress continuous zero-value areas; C. Dynamic bit allocation compression: Determine the bit width based on the maximum value of the residual, and truncate high-order redundant zero bits as needed; The compressed residual data is stored as a binary stream and associated with a compression parameter tag.

[0024] The specific steps of dynamically selecting a lossless compression algorithm include: S2.3.2.1 Statistical analysis: Analyze the numerical range, distribution density, and statistical characteristics of zero value ratio of residual data; S2.3.2.2 Algorithm matching: Select the optimal compression algorithm combination based on statistical characteristics; S2.3.2.3 Compression efficiency evaluation: Evaluate the compression ratio and computational complexity in real time during the compression process, and dynamically adjust the algorithm parameters; S2.3.2.4 Compression result verification: Ensure that the compressed data can be fully restored when decompressed without information loss.

[0025] S2.4 Residual storage: Only the residual data and the marked DICOM images are saved, and the original data automatically releases the storage space after compression; the compressed residual data, compression parameter labels and marked DICOM images are packaged into a compressed data packet and written into the storage medium; The storage structure example is as follows: <plaintext>[Header] |-- DICOM image ID |-- Compression algorithm identifier |-- Unsigned parameters [Body] |-- The encapsulation format of the compressed residual data stream compressed data packet includes the following: S2.4.1 Compressed residual data block: stores the residual data after lossless compression; S2.4.2 DICOM image file: stores the marked DICOM image, including the delete protection flag and compression parameter tag in the metadata; S2.4.3 Compression parameter label: record the residual unsigned processing rules, compression algorithm identifier, dynamic bit allocation information and sign mark bit; S2.4.4 Data verification information: Use CRC verification or hash algorithm to ensure data integrity and consistency.

[0026] S3, data deletion and recovery protection mechanism; When a user initiates a DICOM image deletion operation, the system detects whether it is associated with residual data: If there is a deletion protection mark, a pop-up window will be triggered to warn: "This operation will cause the associated original data to be permanently lost. Do you want to continue?" After the user confirms the deletion, the system will clear the residual data synchronously; if the deletion is cancelled, the complete data chain will be retained; The data deletion and recovery protection mechanism also includes the following steps: S3.1 Data backup: Before the deletion operation is performed, the system automatically backs up the associated residual data and DICOM images to a temporary storage area; S3.2 Deletion log records: record the time of the deletion operation, user information, and key metadata of the deleted data for subsequent audit or recovery; S3.3 Data recovery option: If the user deletes data by mistake, the complete data chain can be restored from the temporary storage area by deleting the log.

[0027] S4, original data recovery process; When the user needs to reconstruct the original data, perform the reverse operation: S4.1 residual data decompression; Read the compression parameter tag in the compressed data packet and call the corresponding decompression module according to the algorithm identifier; If dynamic bit allocation compression is used, the original integer value of the residual data is restored according to the recorded bit width; Perform unsigned inverse operations to restore the positive and negative characteristics of the residual data; S4.2 Data restoration; The decompressed residual data is superimposed with the predicted data to restore the original data. The mathematical expression is: Original data = predicted data + residual data X (-1) sign mark bit , where: the sign mark bit is generated during the unsigned processing and embedded in the compression parameter label; The specific steps of data restoration include: S4.2.1 Prediction data generation: Recalculate the prediction value of the original data based on the DICOM image to ensure that it is consistent with the prediction data during compression; S4.2.2 Residual data superposition: superimpose the decompressed residual data and the predicted data pixel by pixel; S4.2.3 Sign flag bit processing: perform sign recovery on the residual data according to the sign flag bit in the compression parameter tag; S4.2.4 Data Verification: Verify the accuracy of data restoration by comparing the statistical characteristics of the recovered data with the original data.

[0028] Embodiment 3 In order to better cooperate with the use of the CT raw data compression, recovery and storage method, a CT system using the CT raw data compression, recovery and storage method is also proposed, including a rack unit, a data processing unit and a human-computer interaction unit; The rack unit comprises a detector and an X-ray generator; the detector and the X-ray generator are installed relative to each other, and the scanned object is placed between the detector and the X-ray generator, wherein the rack unit is rotatable, or the scanned object is rotatable; The data processing unit processes the acquired CT raw data using a CT raw data compression, recovery and storage method; The data processing unit includes an image reconstruction module, a data recovery module and a data storage module; The detector acquires CT raw data and transmits it to the data processing unit; the image reconstruction module of the data processing unit processes the raw data to generate a reconstructed image in DICOM format; the data storage module stores the raw data or residual data according to the instruction of the human-computer interaction unit; the data recovery module restores the raw data using the reconstructed image and residual data as needed; the image reconstruction module performs image reconstruction again using the restored raw data according to the needs of the human-computer interaction unit.

[0029] The present application provides a CT raw data compression, recovery and storage method and system, which is based on the residual compression technology of DICOM images, uses the reconstructed DICOM images to reversely generate the predicted value of the raw data, and achieves a high compression rate by calculating the residual between the predicted data and the raw data, breaking through the traditional compression method that only relies on the redundancy of the raw data, and forming a "DICOM image-residual data" bidirectional association architecture.

[0030] Through the original data direct storage mode, the original data is directly stored, or the residual compression mode, the residual is unsigned (absolute value / offset conversion); adaptive lossless compression algorithm (entropy coding, bit allocation, etc.); residual data and DICOM image binding package (including compression parameter tags); dual-mode switching logic, compression parameter tag design and packaging structure, a dynamic reversible dual-mode storage strategy is provided.

[0031] The residual association mark and deletion protection instruction are embedded in the DICOM image metadata; the deletion operation triggers double verification: pop-up warning + forced synchronous deletion of residual data, providing a safety control mechanism to prevent accidental deletion.

[0032] The superposition restoration formula of predicted data + symbolized residual is defined to ensure the numerical accuracy of the original data reconstruction, meet the strict consistency requirements of medical imaging diagnosis, and provide mathematical guarantee for lossless recovery.

[0033] The present application provides a CT raw data compression, recovery and storage method and system, which use necessary DICOM images and replace the original data storage with residual data to achieve data compression and full data utilization, and support lossless recovery to meet the integrity requirements of medical image data; users can flexibly select storage modes to balance storage costs and data traceability requirements, which is particularly suitable for research-based medical scenarios that require long-term archiving; the amount of raw data written is reduced in compression mode, which significantly reduces hard disk mechanical loss and extends the service life of the storage medium; the deletion protection mark and recovery authority control form a double insurance to avoid the risk of accidental deletion of key data, which meets the medical data compliance standards. Finally , it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention is described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to replace some of the technical features by equivalents. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.< / plaintext>

Claims

1. A method for compressing, restoring and storing CT raw data, characterized in that: The steps include: S1, user interaction and scanning control, the user presets the storage mode through the interaction unit and starts the CT scan, the data acquisition system obtains the original data, and the image reconstruction system synchronously generates the DICOM image; S2, storage mode determination and branch execution; Mode A (raw data storage): If the user selects the raw data storage mode, the system will write the raw data directly into the storage medium and store it independently from the DICOM images; Mode B (compressed data storage): If the compressed data storage mode is selected, the following sub-process is executed: S2.1 Prediction data generation: The raw data prediction unit calculates the prediction value of the raw data based on the DICOM image through a preset algorithm; S2.2 Residual calculation: Perform pixel-by-pixel difference operation on the predicted data and the original data to generate a residual data matrix; S2.3 Data association tag: Bind the residual data to the corresponding DICOM image as "residual paired data" and add a deletion protection tag in the DICOM image metadata; S2.4 Residual storage: Only the residual data and the marked DICOM images are saved, and the original data will automatically release the storage space after compression; S3, data deletion and recovery protection mechanism; When a user initiates a DICOM image deletion operation, the system detects whether it is associated with residual data: If there is a deletion protection mark, a pop-up window will be triggered to warn: "This operation will cause the associated original data to be permanently lost. Do you want to continue?" After the user confirms the deletion, the system will clear the residual data synchronously; if the deletion is cancelled, the complete data chain will be retained; S4, original data recovery process; When the user needs to reconstruct the original data, perform the reverse operation: S4.1 residual data decompression; Read the compression parameter tag in the compressed data packet and call the corresponding decompression module according to the algorithm identifier; If dynamic bit allocation compression is used, the original integer value of the residual data is restored according to the recorded bit width; Perform unsigned inverse operations to restore the positive and negative characteristics of the residual data; S4.2 Data restoration; The decompressed residual data is superimposed with the predicted data to restore the original data. The mathematical expression is: Original data = predicted data + residual data X (-1) 符号标记位 , where: the sign flag bit is generated during the unsigned processing and embedded in the compression parameter tag.

2. The CT raw data compression, recovery and storage method according to claim 1, characterized in that: In step S2.1, the preset algorithm includes but is not limited to a forward projection algorithm combined with an inverse correction or a deep learning model, specifically including the following steps: S2.1.1 Preset algorithm based on forward projection algorithm combined with inverse correction; Producing projection data by pixel-based orthographic projection, ray-based orthographic projection, or other orthographic projection methods, followed by generating predictions of the original data by inverse correction, which may be done by adding random noise or by inverse calculation through a known correction process; S2.1.2 Prediction algorithm based on deep learning model; Using the pre-trained neural network model, DICOM images are used as input and the predicted values ​​of the original data are directly output; S2.1.3 Model optimization and updating; Dynamically adjust the parameters of the deep learning model based on the feedback from the actual scan data, or update the model through an online learning mechanism to improve prediction accuracy; S2.1.4 Forecast error correction; After the prediction data is generated, the prediction value is locally optimized through the error correction module to reduce the impact of systematic errors and random errors.

3. The CT raw data compression, recovery and storage method according to claim 1, characterized in that: In step S2.3, the following steps are also included: S2.3.1 Unsigned residual processing; After the residual calculation is completed, the residual data matrix is ​​converted to unsigned, including: Convert negative residuals to non-negative integers through absolute value conversion or offset compensation; Record the conversion rules into the compression parameter tag of the DICOM image metadata for reverse processing during recovery; S2.3.2 Lossless compression algorithm selection and implementation; Based on the statistical characteristics of the residual data, dynamically select one or a combination of the following lossless compression algorithms: A. Compression based on entropy coding: Huffman coding or arithmetic coding is used to optimize the code table for high-frequency small value residuals; B. Differential Pulse Code Modulation (DPCM): differentially encodes adjacent residual pixel values ​​and combines run-length encoding (RLE) to compress continuous zero-value areas; C. Dynamic bit allocation compression: Determine the bit width based on the maximum value of the residual, and truncate high-order redundant zero bits as needed; The compressed residual data is stored as a binary stream and associated with a compression parameter tag.

4. The CT raw data compression, recovery and storage method according to claim 3, characterized in that: In step S2.3.2, the specific steps of dynamically selecting a lossless compression algorithm include: S2.3.2.1 Statistical analysis: Analyze the numerical range, distribution density, and statistical characteristics of zero value ratio of residual data; S2.3.2.2 Algorithm matching: Select the optimal compression algorithm combination based on statistical characteristics; S2.3.2.3 Compression efficiency evaluation: Evaluate the compression ratio and computational complexity in real time during the compression process, and dynamically adjust the algorithm parameters; S2.3.2.4 Compression result verification: Ensure that the compressed data can be fully restored when decompressed without information loss.

5. The CT raw data compression, recovery and storage method according to claim 1, characterized in that: In step S2.4, the compressed residual data, the compression parameter label and the marked DICOM image are encapsulated into a compressed data packet and written into a storage medium; wherein the encapsulation format of the compressed data packet includes the following contents: S2.4.1 Compressed residual data block: stores the residual data after lossless compression; S2.4.2 DICOM image file: stores the marked DICOM image, including the delete protection flag and compression parameter tag in the metadata; S2.4.3 Compression parameter label: record the residual unsigned processing rules, compression algorithm identifier, dynamic bit allocation information and sign mark bit; S2.4.4 Data verification information: Use CRC verification or hash algorithm to ensure data integrity and consistency.

6. The CT raw data compression, recovery and storage method according to claim 1, characterized in that: In step S3, the data deletion and recovery protection mechanism further includes the following steps: S3.1 Data backup: Before the deletion operation is performed, the system automatically backs up the associated residual data and DICOM images to a temporary storage area; S3.2 Deletion log records: record the time of the deletion operation, user information, and key metadata of the deleted data for subsequent audit or recovery; S3.3 Data recovery option: If the user deletes data by mistake, the complete data chain can be restored from the temporary storage area by deleting the log.

7. The CT raw data compression, recovery and storage method according to claim 1, characterized in that: In step S4.2, the specific steps of data restoration include: S4.2.1 Prediction data generation: Recalculate the prediction value of the original data based on the DICOM image to ensure that it is consistent with the prediction data during compression; S4.2.2 Residual data superposition: superimpose the decompressed residual data and the predicted data pixel by pixel; S4.2.3 Sign flag bit processing: perform sign recovery on the residual data according to the sign flag bit in the compression parameter tag; S4.2.4 Data Verification: Verify the accuracy of data restoration by comparing the statistical characteristics of the recovered data with the original data.

8. A CT system using a CT raw data compression, recovery and storage method, characterized in that: It includes a rack unit, a data processing unit and a human-computer interaction unit; The rack unit includes a detector and an X-ray generator; the detector and the X-ray generator are installed opposite to each other, and the scanned object is placed between the detector and the X-ray generator; The data processing unit processes the acquired CT raw data using the CT raw data compression, recovery and storage method according to any one of claims 1 to 7; The data processing unit includes an image reconstruction module, a data recovery module and a data storage module; The detector acquires CT raw data and transmits it to the data processing unit; the image reconstruction module of the data processing unit processes the raw data to generate a reconstructed image in DICOM format; the data storage module stores the raw data or residual data according to the instruction of the human-computer interaction unit; the data recovery module restores the raw data using the reconstructed image and residual data as needed; the image reconstruction module performs image reconstruction again using the restored raw data according to the needs of the human-computer interaction unit.

Images