DICOM file processing method and device, equipment, medium and product

Abstract

The invention provides a DICOM file processing method and device, equipment, a medium and a product. The method comprises the steps of obtaining a to-be-processed DICOM file, and performing anomaly detection and preprocessing on the to-be-processed DICOM file; according to the preprocessed non-abnormal DICOM file, analyzing the non-abnormal DICOM file to obtain analyzed multi-modal image data and metadata, and carrying out persistence processing on the analyzed multi-modal image data and metadata; identifying an image type of the multi-modal image data, and calling a data display template corresponding to the image type; and screening target metadata associated with the image type from the metadata after persistence processing, and filling the target metadata and the analyzed multi-modal image data into a data display template to form an image display report. The metadata of the DICOM file can be quickly obtained, and the overall efficiency of medical image data processing, image reading convenience and the standardization level of image report generation are improved.

Description

Technical Field

[0001] This disclosure relates to the field of medical image processing technology, and in particular to a method, apparatus, device, medium, and product for processing DICOM files. Background Technology

[0002] DICOM (Digital Imaging and Communications in Medicine) is an international standard format for the storage and transmission of medical images. DICOM files use a binary encapsulation structure, encoding pixel data and metadata into a single file.

[0003] Currently, clinical and research personnel who need to obtain metadata from DICOM files must rely on specialized software that supports the DICOM protocol to manually open, view, and record each case. When there is a need for large-scale data processing, manual case-by-case viewing will result in inefficiency, high labor costs, and limited information utilization. Summary of the Invention

[0004] This disclosure provides a DICOM file processing method, apparatus, device, medium, and product to quickly obtain DICOM file metadata, thereby improving the overall efficiency of medical image data processing, the convenience of image reading, and the standardization of image report generation.

[0005] According to one aspect of this disclosure, a method for processing DICOM files is provided, comprising: Obtain the DICOM file to be processed, and perform anomaly detection and preprocessing on the DICOM file. The DICOM file includes multimodal image data and metadata in binary form. For the preprocessed DICOM file without anomalies, the DICOM file without anomalies is parsed to obtain the parsed multimodal image data and metadata, and the parsed multimodal image data and metadata are persisted. Identify the image type of the multimodal image data and call the data display template corresponding to the image type; The target metadata associated with the image type is filtered from the persistent metadata, and the target metadata and the parsed multimodal image data are used to fill the data display template to form an image display report.

[0006] According to another aspect of this disclosure, a DICOM file processing apparatus is provided, the apparatus comprising: The file acquisition module is used to acquire the DICOM file to be processed, and to perform anomaly detection and preprocessing on the DICOM file to be processed. The DICOM file includes multimodal image data and metadata in binary form. The file parsing module is used to parse the preprocessed anomaly-free DICOM file to obtain the parsed multimodal image data and metadata, and to persist the parsed multimodal image data and metadata. The image type recognition module is used to identify the image type of the multimodal image data and call the data display template corresponding to the image type. The image display report generation module is used to filter target metadata associated with the image type from the persistent metadata, and fill the data display template with the target metadata and the parsed multimodal image data to form an image display report.

[0007] According to another aspect of this disclosure, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the DICOM file processing method according to any embodiment of this disclosure.

[0008] According to another aspect of this disclosure, a computer-readable storage medium is provided that stores computer instructions for causing a processor to execute and implement the DICOM file processing method according to any embodiment of this disclosure.

[0009] According to another aspect of this disclosure, a computer program product is provided, which, when executed by a processor, implements the DICOM file processing method as described in any of the embodiments of this disclosure.

[0010] This disclosure embodiment acquires a DICOM file to be processed, performs anomaly detection and preprocessing on the DICOM file, which includes multimodal image data and metadata in binary form. Anomaly detection and preprocessing ensure the integrity and validity of input data, improving the stability and accuracy of medical image processing. For the preprocessed anomaly-free DICOM file, it is parsed to obtain parsed multimodal image data and metadata, which are then persisted. Persistence allows for data reuse after a single parsing. The image type of the multimodal image data is identified, and the corresponding data display template is called to achieve automated adaptation and display of multimodal images, improving image reading efficiency. Target metadata associated with the image type is filtered from the persisted metadata, and the target metadata and parsed multimodal image data are used to fill the data display template, forming an image display report. By filtering associated target metadata and filling the template with multimodal image data to generate a report, report format standardization and automated generation are achieved, improving the standardization of image reports and the efficiency of generating image display reports. By detecting and preprocessing anomalies in DICOM files and parsing them, the parsed data is persisted, and then an image presentation report is generated using a data display template. This solves the technical problems of cumbersome DICOM data viewing processes and low efficiency due to repetitive parsing, enabling rapid acquisition of DICOM file metadata and improving the overall efficiency of medical image data processing, ease of image reading, and standardization of image report generation.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this disclosure and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a DICOM file processing method according to an embodiment of this disclosure; Figure 2 This is a flowchart of a DICOM file processing method according to an embodiment of this disclosure; Figure 3This is a schematic diagram of the structure of a DICOM file processing device according to an embodiment of this disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this disclosure. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0017] Figure 1 This flowchart illustrates a DICOM file processing method provided in this embodiment. This embodiment is applicable to situations where image data in an imaging device needs to be stored as a DICOM file, and the data in the file needs to be displayed using a display template. This method can be executed by the DICOM file processing device in this embodiment, which can be implemented in software and / or hardware. This device can be integrated into electronic devices such as computer equipment, servers, mobile terminals, processors, surgical robots, or surgical navigation devices. Figure 1 As shown, the method specifically includes the following steps: S110: Obtain the DICOM file to be processed, perform anomaly detection and preprocessing on the DICOM file to be processed. The DICOM file includes multimodal image data and metadata in binary form.

[0018] In this embodiment of the disclosure, a DICOM file can be specifically understood as a medical image file packaged in accordance with the DICOM international standard. This file is a standardized file format output by imaging equipment such as CT (Computed Tomography), MRI (Magnetic Resonance Imaging), and ultrasound. A DICOM file is a binary file that integrates multimodal image data and metadata in binary form.

[0019] Multimodal image data consists of binary image data generated by different medical imaging devices and stored according to the DICOM standard. It provides the raw data foundation for subsequent image analysis. Metadata is structured non-image data encapsulated in DICOM files and defined according to the DICOM standard label specification. Metadata includes, but is not limited to, basic patient information, basic examination information, image sequence information, and SOP (Service-Object Pair) instance information. The metadata is associated with the corresponding multimodal image data, providing data support for image analysis, archiving and retrieval, modality recognition, and standardized report generation.

[0020] Specifically, the process involves acquiring images generated by medical imaging equipment and encapsulating them into DICOM files in the standard DICOM format. Anomaly detection and preprocessing are then performed on the DICOM files to be processed, resulting in preprocessed DICOM files free of anomalies. Finally, the process of acquiring the DICOM files and standardizing the data format through anomaly detection and preprocessing improves the stability and success rate of subsequent DICOM parsing and image display report generation, ensuring data reliability throughout the entire process.

[0021] Optionally, the DICOM file to be processed is subjected to anomaly detection and preprocessing, including at least one of the following: reading the file header identifier of the DICOM file and performing validity detection on the DICOM file based on the file header identifier; parsing the file header length of the DICOM file and performing file header anomaly detection on the DICOM file based on the file header length; parsing the image basic parameters of the multimodal image data in the DICOM file and performing image anomaly detection on the DICOM file based on the image basic parameters; and performing redundancy removal processing on DICOM files without anomalies.

[0022] In this embodiment of the disclosure, the file header identifier is a fixed binary sequence as defined by the DICOM format. The fixed binary sequence is represented in hexadecimal as 0x44, 0x49, 0x43, and 0x4D, and is a format identifier unique to DICOM files. The validity check is a process of verifying whether the file to be processed is a legitimate DICOM file, excluding non-DICOM files, forged files, or invalid files with corrupted headers.

[0023] The header length can be understood as the number of bytes occupied by the header section as defined by the DICOM standard. The standard range for header length is 80 bytes to 65536 bytes. The header length value can be used to determine if the header has been truncated, padded abnormally, or has format distortions. Header anomaly detection is the process of verifying whether the parsed header length value exceeds the standard range, thereby determining whether the DICOM header has issues such as truncation, padded abnormalities, or format distortions.

[0024] Image fundamental parameters can be understood as the core parameters described in the DICOM file that characterize the properties of the multimodal image data itself. These parameters include, but are not limited to, the frame rate and number of frames in a sequence for moving images, the number of modalities and resolution of each modality for multimodal images, and the resolution and pixel depth for still images. They are key quantitative indicators characterizing the legality and integrity of multimodal image data. Image anomaly detection is an operation that verifies the compliance of image fundamental parameters and determines whether there are anomalies in the image data. Image anomaly detection is used to filter out abnormal DICOM files with distorted image content or missing parameters.

[0025] Redundancy removal can be understood as the operation of deleting irrelevant binary redundant data from a file. For example, it involves deleting invalid padding data at the end of a file, temporary identifier data left over from transmission, and redundant frame data left over from multimedia video transmission, resulting in a standardized preprocessed DICOM file for subsequent data parsing.

[0026] Specifically, the file header identifier of the DICOM file is read. The existence of the file header identifier is verified to determine if the file is a valid DICOM file. If the identifier does not exist, the file is deemed invalid, stored in the invalid file log, and skipped from subsequent parsing steps. If the identifier exists, the validity check is passed. By verifying the file header identifier of the DICOM file, non-compliant files can be filtered out at the front end of the process, preventing invalid data from entering subsequent parsing stages and improving overall processing efficiency and data reliability.

[0027] The file header length of a DICOM file is parsed. If the parsed header length exceeds the standard range, it is considered a formatting error file, stored in the error log, and marked as "header length error." If the header length conforms to the standard, the file header error detection passes. By verifying whether the DICOM file header length conforms to the standard range, formatting issues such as header truncation and padding errors can be accurately identified.

[0028] The basic image parameters of multimodal image data in DICOM files are parsed. For example, the frame rate and number of frames in the sequence of moving images are parsed; the number of modalities and the resolution of each modality in multimodal images are parsed; and the resolution of still images is parsed. These parameters are verified to ensure they conform to the value ranges for the corresponding multimedia image type in the DICOM standard. If a parameter exceeds a reasonable range, it is determined as an "abnormal multimedia image parameter," and the error is recorded in the error log with the error type marked. If the parameters are normal, the image anomaly detection is passed. Verifying whether the basic image parameters conform to the DICOM standard range can filter out files with abnormal parameters and distorted data at the image content level, ensuring the authenticity and validity of the multimodal image data subsequently parsed.

[0029] DICOM files that pass validity checks, header anomaly checks, and image anomaly checks are considered anomaly-free DICOM files. Redundancy removal is then performed on these anomaly-free DICOM files. Irrelevant binary redundant data is removed from the DICOM file. For example, invalid padding data at the end of the file, temporary identifier data remaining from transmission, and redundant frame data remaining from multimedia image transmission are removed to obtain a pre-processed anomaly-free DICOM file, which is then used for subsequent DICOM file parsing.

[0030] S120: For the preprocessed DICOM file without anomalies, parse the DICOM file without anomalies to obtain the parsed multimodal image data and metadata, and perform persistent processing on the parsed multimodal image data and metadata.

[0031] In this embodiment, an anomaly-free DICOM file can be specifically understood as a DICOM file that has undergone anomaly detection and preprocessing. An anomaly-free DICOM file has a valid format, complete structure, parameters conforming to the DICOM standard, and no redundant or invalid data. Anomaly-free DICOM files provide a high-quality, highly reliable data foundation for subsequent parsing, persistence, and report display, reducing anomaly processing and optimizing storage efficiency.

[0032] Specifically, for the preprocessed, anomaly-free DICOM files, the files are parsed to obtain the parsed multimodal image data and metadata. The parsed multimodal image data and metadata are then persisted to ensure stable data retention and retrieval.

[0033] Optionally, the DICOM file includes a binary stream, which includes labels, data lengths, and data content for multiple data elements; the data elements include metadata and multimodal image data.

[0034] In this embodiment, the binary stream is a continuous binary data sequence encapsulated according to the DICOM standard protocol, consisting of multiple data elements concatenated sequentially. The binary stream includes labels for multiple data elements, data length, and data content. The label of each data element is a unique identifier assigned to each type of data element in the DICOM standard, used to identify the type of data element. For example, 0x0010, 0x0010 can represent the patient's name, and 0x0008, 0x0060 can represent the examination type. The data length is a numerical value representing the number of bytes occupied by the data values ​​in the data content. Based on the data length, the data content can be accurately located, avoiding parsing out-of-bounds errors or data truncation, and enabling accurate reading of the data content. The data content is the core content, uniquely identified by the label and defined by the data length, carrying the actual business information in the DICOM file binary stream. The data elements include metadata and multimodal image data.

[0035] Optionally, parsing the anomaly-free DICOM file to obtain parsed multimodal image data and metadata includes: reading binary tags based on tag length in the binary stream of the DICOM file; mapping the binary tag content to text tags based on a tag mapping configuration file, wherein the tag mapping configuration file includes a preset value dictionary and a mapping relationship between binary tags; obtaining the data length corresponding to the binary tag; determining the start and end offset addresses of the data content corresponding to the data element based on the data length; reading binary data content from the binary stream based on the start and end offset addresses of the data content; and converting the binary data content into metadata or multimodal image data.

[0036] In this embodiment, the binary tag can be specifically understood as a tag stored in the binary stream of a DICOM file in a preset byte binary encoding format. For example, the preset byte can be 4 bytes. The binary tag is the underlying identifier of the data element type and needs to be mapped to text tags through a preset value dictionary in the tag mapping configuration file. The tag mapping configuration file can be specifically understood as a pre-built standardized configuration file. The tag mapping configuration file includes the mapping relationship between the preset value dictionary and the binary tags, which can convert the binary tags in the binary stream into text tags with business semantics. It is the core configuration carrier for realizing the readability of binary tags. The text tag can be specifically understood as a tag with business semantics after conversion by the tag mapping configuration file. The text tag is obtained by mapping the binary tag. The preset value dictionary can be specifically understood as a data dictionary in the tag mapping configuration file used to establish the mapping relationship with the binary tags and realize the semantic conversion of the tags. For example, 0x0010, 0x0010 is mapped to the text tag "PatientName", and 0x0008, 0x0060 is mapped to the text tag "Modality". The preset value dictionary is the core data basis for realizing the conversion of binary tags into semantic text tags.

[0037] The starting offset address can be understood as the address at which the data content corresponding to a data element begins to be read from the DICOM file binary stream. The starting offset address is calculated based on the data length corresponding to the binary tag and is used to locate and read the starting position of the corresponding binary data content from the binary stream. The ending offset address can be understood as the address at which the data content corresponding to a data element ends to be read from the DICOM file binary stream. The ending offset address is calculated from the data length and, together with the starting offset address, defines the range of binary data content that can be read from the binary stream.

[0038] Specifically, when parsing a normal DICOM file, the binary stream corresponding to the DICOM file is read. Bytes are extracted from the binary stream according to a preset tag length to obtain the binary tags of the data elements. Then, a pre-built tag mapping configuration file is called. Based on the mapping relationship between the preset value dictionary and binary tags in the configuration file, the original encoded content of the binary tags is converted into text tags with business semantics. After completing the mapping from binary tags to text tags, the data length of the data element corresponding to the binary tag is obtained according to the content of the data length field in the binary stream. Based on the value of this data length, the start and end offset addresses of the data content corresponding to the current data element in the DICOM file binary stream are calculated. Using the start offset address as the starting point and the end offset address as the ending point, the binary data content within this address range is precisely extracted from the DICOM file binary stream to obtain the original binary data of the data element. According to the data element type represented by the text tag, the read binary data content is format-converted into metadata or multimodal image data, completing the parsing of the normal DICOM file and obtaining structured multimodal image data and metadata.

[0039] Optionally, the starting offset address of the data content is The end offset address of the data content is Wherein, S is the starting offset address of the data content of the current data element; n is the header length of the DICOM file; n is the number of data elements parsed before the current data element; m is the tag length; This is the length value corresponding to the data length item of the i-th parsed data element; This represents the length of the data content of the i-th parsed data element. The length of the current data element.

[0040] In this embodiment of the disclosure, the number of parsed data elements can be specifically understood as the total number of data elements in the DICOM file binary stream that are located before the currently parsed data element and have already been parsed. The number of parsed data elements is denoted by parameter n, which is used to accurately locate the starting offset address of the data content of the current data element.

[0041] Specifically, when calculating the starting and ending offset addresses of the data content, precise calculations are performed by combining the structural characteristics of the DICOM file with the cumulative length of the parsed data elements. The formula for calculating the starting offset address S of the data content of the currently parsed data element is as follows: in, n is the header length of the DICOM file; n is the number of data elements parsed before the current data element; m is the tag length. This is the length value corresponding to the data length item of the i-th parsed data element; This represents the length of the data content of the i-th parsed data element. This represents the data length of the current data element. For the current data element to be parsed, the ending offset address can be calculated based on its data length and starting offset address. The formula is shown below: in, This is the length value corresponding to the data length item of the current data element, representing the total number of bytes occupied by the data content of this data element in the DICOM file binary stream. It is used in conjunction with the starting offset address to calculate the ending offset address of the data content.

[0042] Optionally, the parsed multimodal image data and metadata are persisted, including: downloading the parsed multimodal image data to a local device and storing it in a memory associated with the image viewing device; and structuring the parsed metadata according to the image type and storing it in a document database.

[0043] In this embodiment, the memory associated with the image viewing device can be understood as a local or remote storage medium that has a data communication connection with the image viewing device, belongs to the same image viewing system architecture, and can be directly read and written by the image viewing device. This memory is used to persistently store the parsed multimodal image data, ensuring the efficiency and stability of the image viewing device in retrieving image data. The document database can be understood as a database that can organize and store document data. This database can store structured metadata, used to persistently store the structured metadata corresponding to the multimodal images, realizing efficient management and related queries of metadata. Structured processing can be understood as a standardized processing process that, according to preset standardization rules, output format requirements, and structured templates, performs format regularization, field unification, classification organization, and association identification on the data. Through this processing, the parsed data, which originally lacked a unified organizational form, is transformed into a standardized data form with a fixed field structure, unified naming rules, and clear relationships, ensuring the standardization, consistency, and retrieval of the data output.

[0044] Specifically, the parsed multimodal image data and metadata undergo persistent processing. This involves downloading the parsed multimodal image data locally and storing it in a memory associated with the corresponding image viewing device. For the metadata, standardization is first performed based on the corresponding image type, combined with preset standardization rules and structured output templates. The metadata undergoes format standardization, field unification, and classification, and an association identifier is established between the metadata and the corresponding multimodal image data, transforming scattered parsed metadata into standardized data with fixed fields and clear relationships. The structured metadata is stored in a document database, enabling categorized storage, rapid retrieval, and unified management of the metadata. Simultaneously, based on the association identifiers in the metadata, a correspondence is established with the multimodal image data in the memory, enabling linked querying and retrieval of image data and metadata. For example, a JSON format output template can be constructed, where the parsed result of each DICOM file corresponds to a JSON object containing metadata fields, an image type field, a unique image ID field, and the corresponding image file path.

[0045] S130 identifies the image type of the multimodal image data and calls the data display template corresponding to the image type.

[0046] In this embodiment, image type can be specifically understood as an image type used to distinguish different business attributes and display requirements. For example, image types include, but are not limited to, CT images, MR images, ultrasound images, and X-ray images. Different image types correspond to different data display templates, enabling differentiated and adapted image display. The data display template can be specifically understood as a pre-configured display template matching various image types. This template includes display controls adapted to the corresponding image type, parameter display areas, image rendering methods, layout proportions, and interactive control logic. After being invoked, it can load, render, and visualize the target multimodal image data and associated metadata according to preset rules, ensuring a unified display style for images of the same type.

[0047] Specifically, based on the parsed data, the image type of the image to be displayed is identified. According to the identified image type, a corresponding data display template is matched and called from a pre-set template library. The image is then displayed according to the adapted template, ensuring that different image types are presented in a style that meets their display requirements, while maintaining a consistent display interface format and interactive logic for the same image type.

[0048] S140: Filter the target metadata associated with the image type from the persistent metadata, fill the data display template with the target metadata and the parsed multimodal image data to form an image display report.

[0049] In this embodiment, the target metadata can be specifically understood as metadata filtered from persistently stored metadata that is associated with the image type of the current multimodal image. This target metadata is adapted to the display requirements of the corresponding data display template. The image display report can be specifically understood as a report used to uniformly present the multimodal image content and corresponding target metadata. This report has image viewing, metadata retrieval, and clinical image reading interaction functions, providing image reading equipment with a uniformly formatted and information-complete image reading and data presentation carrier.

[0050] Specifically, target metadata related to image types is selected from the persistent metadata. The target metadata and the parsed multimodal image data are then used to populate the corresponding positions in the data display template, generating an image display report. The target metadata and multimodal image data are precisely partitioned and populated into the corresponding template positions to ensure a neat report layout, clear information hierarchy, and improved convenience and readability.

[0051] Optionally, the multimodal imaging data includes at least one of CT data, MRI data, X-ray data, ultrasound data, and nuclear medicine data; the target metadata associated with the CT data includes at least one of dose and quality control parameters, scanning and reconstruction parameters, image attributes, CT image processing derived information, and radiation dose assessment values; the target metadata associated with the MRI data includes at least one of sequence baseline parameters, equipment and scanning parameters, enhancement information, and enhancement region markers; the target metadata associated with the X-ray data includes at least one of exposure and quality control parameters, image attributes, artifact markers, and typical site adaptation markers; the target metadata associated with the ultrasound data includes at least one of equipment and probe parameters, scanning parameters, and functional information; and the target metadata associated with the nuclear medicine data includes at least one of tracer and acquisition parameters, acquisition and reconstruction parameters, image attributes, and metabolic analysis markers.

[0052] In this embodiment, dose and quality control parameters can be specifically understood as core parameters related to radiation dose and image quality control during CT scanning. Dose and quality control parameters include, but are not limited to, slice thickness, tube voltage, tube current, and dose index; these parameters characterize the scan dose level and basic image quality. Scan and reconstruction parameters can be specifically understood as core parameters related to the CT scan range and image reconstruction strategy. Scan and reconstruction parameters include, but are not limited to, scan range and reconstruction algorithm. Image attributes can be specifically understood as the digital structure and spatial feature parameters of the CT image. Image parameters include, but are not limited to, image matrix and voxel size. Image attributes characterize the resolution, size, and spatial distribution characteristics of the CT image. CT image processing derived information can be specifically understood as information generated by processing the original CT image. CT image processing derived information includes, but is not limited to, image segmentation accuracy corresponding to slice thickness, denoising / enhancing preprocessing markers, etc., used to reflect the image post-processing status and subsequent analysis usability. Radiation dose assessment values ​​can be specifically understood as numerical values ​​used to quantitatively assess the radiation dose level received by the examinee, which can be used for radiation safety management and scan quality evaluation.

[0053] The fundamental sequence parameters can be understood as the sequence control parameters upon which MRI imaging depends. These parameters include, but are not limited to, sequence type, TR value (Repetition Time), TE value (Echo Time), slice thickness, slice spacing, and matrix size. For example, sequence types can be T1WI (T1 Weighted Imaging), T2WI (T2 Weighted Imaging), FLAIR (Fluid Attenuated Inversion Recovery), and DWI (Diffusion Weighted Imaging). These fundamental sequence parameters characterize the basic methods and fundamental image features of MRI imaging. The equipment and scanning parameters can be understood as the configuration parameters of the MRI equipment itself and related parameters during the scanning process. These parameters include, but are not limited to, field strength and field of view. For example, field strength can be 1.5T, 3.0T, etc. These parameters characterize the imaging capabilities and scanning range of the MRI equipment, and other basic scanning conditions. Contrast information can be understood as information related to the use of contrast agents during MRI scanning. Enhancement information includes, but is not limited to, whether enhancement is used and the type of contrast agent. Enhancement information is used to distinguish between plain and enhanced scans and to record the use of contrast agents. Enhancement region marking can be specifically understood as information used to identify and locate enhanced regions in MRI images. Enhancement region marking includes, but is not limited to, marking of enhanced areas and enhancement extent.

[0054] Exposure and quality control parameters can be specifically understood as parameters related to exposure control and quality control during X-ray imaging. These parameters include, but are not limited to, exposure parameters, detector type, whether a grid is included, and whether it is digitized. Exposure and quality control parameters characterize X-ray imaging conditions and basic image quality. Image attributes can be specifically understood as the basic characteristic parameters of the X-ray image itself. Image attributes include, but are not limited to, image size, FOV (field of view), and projection angle. Artifact markings can be specifically understood as information used to mark and indicate artifact regions present in X-ray images. Artifact markings include, but are not limited to, markings related to metallic obstruction artifacts, motion artifacts, and noise artifacts. Artifact markings are used to identify interfering areas that affect image quality, providing a reference for image interpretation and subsequent processing. Typical site adaptation markings can be specifically understood as marking information used to identify the examination site to which the X-ray image is adapted. Typical site adaptation markings include, but are not limited to, markings for the chest, abdomen, limbs, spine, and skull. Typical site adaptation markings are used to clearly identify the examination site corresponding to the image, facilitating image classification and retrieval.

[0055] Equipment and probe parameters can be specifically understood as parameters related to the configuration of ultrasound equipment and probes during ultrasound imaging. These parameters include, but are not limited to, probe type and imaging mode. For example, probe types can be convex array, linear array, intracavitary, etc. Imaging modes can be B-mode (Brightness mode), Doppler mode, and M-mode (Motion mode). Equipment and probe parameters characterize the working conditions and imaging capabilities of ultrasound equipment and probes, providing a basis for image quality control and image analysis. Scanning parameters can be specifically understood as parameters related to the scanning method during ultrasound imaging. Scanning parameters include, but are not limited to, scan depth, gain, and focus position. Scanning parameters provide a basis for image interpretation and subsequent analysis. Functional information can be specifically understood as information reflecting tissue motion, blood flow, and organ functional status during ultrasound imaging. Functional information includes, but is not limited to, whether color Doppler is used, whether spectral Doppler is used, and blood flow velocity information in Doppler mode. Functional information characterizes the physiological or pathological functional characteristics of tissues and organs, providing a basis for functional assessment.

[0056] Tracers and acquisition parameters can be specifically understood as parameters related to tracer use and image acquisition conditions during nuclear medicine imaging. Tracers and acquisition parameters include, but are not limited to, the type of radioactive tracer, injection dose, acquisition time, and acquisition time point. For example, the type of radioactive tracer could be 99mTc (technetium-99m) or 18F-FDG (fluorodeoxyglucose). Tracers and acquisition parameters are used to characterize the drug conditions and data acquisition rules for nuclear medicine imaging, providing fundamental support for image reconstruction and quantitative analysis. Acquisition and reconstruction parameters can be specifically understood as parameters related to image data acquisition and subsequent image reconstruction during nuclear medicine imaging. Acquisition and reconstruction parameters include, but are not limited to, acquisition methods and reconstruction algorithms. For example, acquisition methods could be static acquisition, dynamic acquisition, or gated acquisition. Reconstruction algorithms could be OSEM (Ordered Subsets Expectation Maximization) or iterative algorithms. Acquisition and reconstruction parameters are used to characterize the acquisition rules and reconstruction strategies for nuclear medicine images, providing fundamental guarantees for image quality, spatial resolution, and quantitative analysis. Image attributes can be understood as the fundamental features and structural information of a nuclear medicine image itself. Image attributes include, but are not limited to, three-dimensional voxel data and time-to-radioactivity curves. Image attributes provide the foundation for image display, post-processing, and quantitative analysis. Metabolic analysis markers can be understood as information that identifies the metabolic level of tissues in nuclear medicine images. Metabolic analysis markers include, but are not limited to, SUV (Standardized Uptake Value). Metabolic analysis markers are used to quantitatively assess the metabolic state of tissues.

[0057] The technical solution of this embodiment obtains a DICOM file to be processed, performs anomaly detection and preprocessing on the DICOM file, which includes multimodal image data and metadata in binary form. Anomaly detection and preprocessing ensure the integrity and validity of input data, improving the stability and accuracy of medical image processing. For the preprocessed anomaly-free DICOM file, it is parsed to obtain parsed multimodal image data and metadata, which are then persisted. Persistence allows for multiple uses of data after a single parsing. The image type of the multimodal image data is identified, and the corresponding data display template is called to achieve automated adaptation and display of multimodal images, improving image reading efficiency. Target metadata associated with the image type is filtered from the persisted metadata, and the target metadata and parsed multimodal image data are used to fill the data display template, forming an image display report. By filtering associated target metadata and filling the template with multimodal image data to generate a report, report format standardization and automated generation are achieved, improving the standardization of image reports and the efficiency of generating image display reports. By detecting and preprocessing anomalies in DICOM files and parsing them, the parsed data is persisted, and then an image presentation report is generated using a data display template. This solves the technical problems of cumbersome DICOM data viewing processes and low efficiency due to repetitive parsing, enabling rapid acquisition of DICOM file metadata and improving the overall efficiency of medical image data processing, ease of image reading, and standardization of image report generation.

[0058] Figure 2 This is a flowchart of a DICOM file processing method provided in this embodiment. This embodiment discloses the process of verifying a processed DICOM file, such as... Figure 2 As shown, the method specifically includes the following steps: S210: Obtain the DICOM file to be processed, perform anomaly detection and preprocessing on the DICOM file to be processed. The DICOM file includes multimodal image data and metadata in binary form.

[0059] S220: For the preprocessed DICOM file without anomalies, parse the DICOM file without anomalies to obtain the parsed multimodal image data and metadata, and perform persistent processing on the parsed multimodal image data and metadata.

[0060] S230 identifies the image type of multimodal image data and calls the data display template corresponding to the image type.

[0061] S240: Filter the target metadata associated with the image type from the persistent metadata, fill the data display template with the target metadata and the parsed multimodal image data, and form an image display report.

[0062] S250 determines the verification DICOM file in the processed DICOM file based on a set ratio.

[0063] In this embodiment, the set ratio can be specifically understood as a pre-set sampling ratio for extracting a corresponding number of files as verification objects from all processed DICOM files. This ratio can be flexibly adjusted according to needs. For example, the set ratio can be 5%. Verifying DICOM files can be specifically understood as sampling files from the processed DICOM files according to the set ratio. Extracting and verifying DICOM files is used to check and verify the accuracy, completeness, and validity of the DICOM file processing flow and processing results.

[0064] Specifically, a predetermined percentage of DICOM files are extracted from the processed DICOM files according to a pre-set ratio, and these extracted DICOM files are used as verification DICOM files. For example, when the set ratio is 5%, 5% of the processed DICOM files are extracted as verification DICOM files. By using this method of sampling verification files according to a set ratio, it is not necessary to perform full verification on all processed DICOM files, which significantly reduces the amount of verification data, lowers the verification computational overhead, and significantly improves the overall verification efficiency.

[0065] S260, based on the parsed multimodal image data and metadata corresponding to the DICOM file and the standard parsed multimodal image data and standard parsed metadata corresponding to the DICOM file, the parsing results are verified to obtain the verification index, which includes at least one of the parsing accuracy, missing rate and completeness accuracy.

[0066] In this embodiment, the standard parsed multimodal image data can be specifically understood as the benchmark image data used to verify the DICOM file. The standard parsed multimodal image data is a verified, distortion-free, and anomaly-free true and correct image parsing result, used as a reference benchmark for verifying this parsing result. The standard parsing metadata can be specifically understood as the benchmark metadata used to verify the DICOM file. The standard parsing metadata contains complete and accurate standard metadata content, used for comparison and verification with the actually parsed metadata.

[0067] Verification metrics can be understood as indicators used to quantitatively evaluate the accuracy and completeness of DICOM file parsing results. They are calculated by comparing actual parsed data with standard parsed data to objectively reflect the execution effect and error level of the parsing process. Verification metrics include at least one of parsing accuracy, missing data rate, and completeness accuracy, providing standardized judgment criteria for parsing result verification. Parsing accuracy is a numerical value used to quantitatively reflect the precision of DICOM file parsing results. Parsing accuracy can intuitively determine the matching degree between actual parsed data and standard parsed data, providing a core quantitative basis for controlling the accuracy of the parsing process. Missing data rate is a numerical value used to quantitatively reflect the degree of data loss during DICOM file parsing. Missing data rate can accurately locate the missing parsing of required metadata and core multimodal image data in the parsing stage, providing targeted references for optimizing the parsing process. Completeness accuracy is a numerical value used to quantitatively reflect the degree of complete restoration of standard parsed data by the DICOM file parsing results. Completeness accuracy can comprehensively evaluate the parsing completeness of multimodal image data, ensuring the effectiveness and completeness of the parsed image data.

[0068] It should be noted that required metadata is core metadata that ensures the effective use of DICOM file parsing results. This includes basic information such as patient identification, examination equipment information, and image modality type. Missing information will directly prevent the parsing results from being displayed, analyzed, or used in subsequent applications. Core multimodal image data is key image data that characterizes the core features of multimodal images and determines the integrity and usability of the image data. For example, core multimodal image data includes core information such as image resolution, pixel depth, and frame sequence structure. Missing or incorrectly parsed data will directly affect the complete reconstruction of the image and subsequent accurate analysis.

[0069] Specifically, the parsing results are verified based on the parsed multimodal image data and metadata corresponding to the DICOM file, combined with the standard parsed multimodal image data and standard parsed metadata corresponding to the DICOM file. Verification metrics include at least one of parsing accuracy, missing data rate, and completeness accuracy. Among these, parsing accuracy... The calculation formula is as follows: in, To parse the correct number of metadata entries; To determine the correct number of multimodal image data entries; The total number of metadata entries participating in the verification; This represents the total number of multimodal image data entries used for validation. Missing rate. The calculation formula is as follows: in, The number of required metadata entries that were not parsed; This represents the number of core multimodal image data points that were not parsed. This represents the total number of required metadata entries that are required for validation. This represents the total number of core multimodal image data entries used in the verification. Completeness and accuracy. The calculation formula is as follows: in, To parse the complete number of multimedia image data entries; This represents the total number of multimodal image data entries used for verification.

[0070] S270, based on the verification index, update at least one of the tag mapping configuration file and offset address calculation method during the DICOM file parsing process.

[0071] Specifically, if the parsing accuracy, missing data rate, and completeness accuracy are all greater than or equal to the corresponding preset thresholds, the parsing process passes the verification. If any of these indicators is less than the corresponding preset threshold, the core reasons for parsing errors, missing data, or incomplete image parsing during the DICOM file parsing process are analyzed based on the calculated results of the parsing accuracy, missing data rate, and completeness accuracy. If it is determined that the label mapping configuration file has deviations or omissions in the label mapping rules for metadata and multimodal image data in the DICOM file, the mapping relationships and label matching rules in the label mapping configuration file are corrected and updated. If it is determined that the offset address calculation method has errors in calculating the data storage address in the DICOM file, the algorithm logic and calculation parameters of the offset address calculation method are optimized and updated. If it is determined that both of the above problems exist simultaneously, the label mapping configuration file and the offset address calculation method are updated simultaneously to improve the accuracy and completeness of subsequent DICOM file parsing.

[0072] The technical solution of this embodiment involves acquiring a DICOM file to be processed, performing anomaly detection and preprocessing on the DICOM file, which includes multimodal image data and metadata in binary form. For the preprocessed anomaly-free DICOM file, the file is parsed to obtain parsed multimodal image data and metadata, which are then persisted. The image type of the multimodal image data is identified, and the corresponding data display template is invoked. Target metadata associated with the image type is filtered from the persisted metadata, and the target metadata and the parsed multimodal image data are used to fill the data display template, forming an image display report. A verification DICOM file is determined based on a set ratio among the processed DICOM files, which reduces the verification workload while ensuring the representativeness of the verification results, and allows the verification data to truly reflect the overall parsing quality of the DICOM file. The parsing results are verified by comparing the parsed multimodal image data and metadata corresponding to the verified DICOM file with the standard parsed multimodal image data and standard parsed metadata corresponding to the verified DICOM file, resulting in verification metrics. These metrics include at least one of parsing accuracy, missing data rate, and completeness accuracy. Comparing the actual parsed data with the standard parsed data and calculating the verification metrics allows for a quantitative and precise evaluation of the parsing results. Updating at least one of the label mapping configuration file and offset address calculation method during the DICOM file parsing process based on the verification metrics enables precise targeted optimization of the parsing process, addressing parsing problems at their root, improving the adaptability of the parsing configuration, and ensuring the stability and efficiency of subsequent parsing. This technical solution, by verifying the processed DICOM file and updating at least one of the label mapping configuration file and offset address calculation method in reverse according to the verification metrics, achieves closed-loop optimization of the DICOM file parsing process, fundamentally solving problems such as low accuracy, missing core data, and incomplete image parsing, thereby improving the quality of multimodal image data parsing.

[0073] Based on the above embodiments, an optional example is provided, which can be used in a scenario where DICOM files are parsed and image display reports are generated.

[0074] First, the imaging equipment acquires and converts the data into a DICOM format file. Anomaly detection and preprocessing are then performed on the DICOM file. In the binary stream of the DICOM file, binary tags are read according to their length, and the binary tag content is mapped to text tags based on the tag mapping configuration file. The data length corresponding to the binary tag is obtained, and the start and end offset addresses of the data content corresponding to the data element are determined based on the data length. Binary data content is read from the binary stream based on the start and end offset addresses of the data content, and the binary data content is converted into metadata or multimodal image data, resulting in parsed multimodal image data and metadata. The parsed multimodal image data is downloaded locally and stored in the memory associated with the image viewing device. The parsed metadata is structured according to the image type and stored in the document database. The parsed multimodal image data is first identified to determine its corresponding image type. Based on the image type, a pre-configured data display template matching the image type is called. From the persistently stored metadata, target metadata associated with the current image type and used for report display is selected. Finally, the selected target metadata and the parsed multimodal image data are combined and populated into the called data display template to complete the generation of the image display report.

[0075] Secondly, when DICOM files need to be verified, a verification DICOM file is determined from the processed DICOM files according to a set ratio. The parsing results are verified based on the parsed multimodal image data and metadata corresponding to the verification DICOM file, and the standard parsed multimodal image data and standard parsed metadata corresponding to the verification DICOM file, to obtain verification indicators. If the verification fails, at least one of the tag mapping configuration file and offset address calculation method during the DICOM file parsing process is updated based on the verification indicators.

[0076] Figure 3 This is a schematic diagram of a DICOM file processing device provided in an embodiment of this disclosure. This embodiment is applicable to situations where image data in an imaging device needs to be stored as a DICOM file, and the data in the file needs to be displayed using a display template. This device can be implemented using software and / or hardware, and can be integrated into any device that provides DICOM file processing functionality, such as… Figure 3 As shown, the DICOM file processing device specifically includes: a file acquisition module 310, a file parsing module 320, an image type recognition module 330, and an image display report generation module 340.

[0077] The file acquisition module 310 is used to acquire the DICOM file to be processed, and to perform anomaly detection and preprocessing on the DICOM file to be processed. The DICOM file includes multimodal image data and metadata in binary form. The file parsing module 320 is used to parse the preprocessed anomaly-free DICOM file to obtain the parsed multimodal image data and metadata, and to persist the parsed multimodal image data and metadata. The image type recognition module 330 is used to identify the image type of the multimodal image data and call the data display template corresponding to the image type; The image display report generation module 340 is used to filter the target metadata associated with the image type from the persistent metadata, and fill the data display template with the target metadata and the parsed multimodal image data to form an image display report.

[0078] The technical solution of this embodiment obtains a DICOM file to be processed, performs anomaly detection and preprocessing on the DICOM file, which includes multimodal image data and metadata in binary form. Anomaly detection and preprocessing ensure the integrity and validity of input data, improving the stability and accuracy of medical image processing. For the preprocessed anomaly-free DICOM file, it is parsed to obtain parsed multimodal image data and metadata, which are then persisted. Persistence allows for multiple uses of data after a single parsing. The image type of the multimodal image data is identified, and the corresponding data display template is called to achieve automated adaptation and display of multimodal images, improving image reading efficiency. Target metadata associated with the image type is filtered from the persisted metadata, and the target metadata and parsed multimodal image data are used to fill the data display template, forming an image display report. By filtering associated target metadata and filling the template with multimodal image data to generate a report, report format standardization and automated generation are achieved, improving the standardization of image reports and the efficiency of generating image display reports. By detecting and preprocessing anomalies in DICOM files and parsing them, the parsed data is persisted, and then an image presentation report is generated using a data display template. This solves the technical problems of cumbersome DICOM data viewing processes and low efficiency due to repetitive parsing, enabling rapid acquisition of DICOM file metadata and improving the overall efficiency of medical image data processing, ease of image reading, and standardization of image report generation.

[0079] Optionally, based on the above embodiments, the file acquisition module 310 is configured to: read the file header identifier of the DICOM file and perform validity detection on the DICOM file based on the file header identifier; parse the file header length of the DICOM file and perform file header anomaly detection on the DICOM file based on the file header length; parse the image basic parameters of the multimodal image data in the DICOM file and perform image anomaly detection on the DICOM file based on the image basic parameters; and perform redundancy removal processing on DICOM files without anomalies.

[0080] Optionally, based on the above embodiments, the DICOM file includes a binary stream, which includes labels, data lengths, and data content of multiple data elements; the data elements include metadata and multimodal image data.

[0081] Optionally, based on the above embodiments, the file parsing module 320 is configured to: read binary tags based on tag length in the binary stream of the DICOM file; map the binary tag content to text tags based on a tag mapping configuration file, wherein the tag mapping configuration file includes a preset value dictionary and a mapping relationship between binary tags; obtain the data length corresponding to the binary tag; determine the start offset address and end offset address of the data content corresponding to the data element based on the data length; read binary data content from the binary stream based on the start offset address and end offset address of the data content; and convert the binary data content into metadata or multimodal image data.

[0082] Optionally, based on the above embodiments, the starting offset address of the data content is: The end offset address of the data content is Wherein, S is the starting offset address of the data content of the current data element; n is the header length of the DICOM file; n is the number of data elements parsed before the current data element; m is the tag length; This is the length value corresponding to the data length item of the i-th parsed data element; This represents the length of the data content of the i-th parsed data element. The length of the current data element.

[0083] Optionally, based on the above embodiments, the file parsing module 320 is further configured to: download the parsed multimodal image data to a local device and store it in a memory associated with the image viewing device; and perform structured processing on the parsed metadata according to the image type and store it in a document database.

[0084] Optionally, based on the above embodiments, the device further includes a file verification module, configured to: determine a verification DICOM file in the processed DICOM file based on a set ratio; verify the parsing results based on the parsed multimodal image data and metadata corresponding to the verification DICOM file and the standard parsed multimodal image data and standard parsed metadata corresponding to the verification DICOM file, and obtain a verification index, wherein the verification index includes at least one of parsing accuracy, missing rate, and integrity accuracy; and update at least one of the tag mapping configuration file and offset address calculation method during the DICOM file parsing process based on the verification index.

[0085] Optionally, based on the above embodiments, the multimodal imaging data includes at least one of CT data, MRI data, X-ray data, ultrasound data, and nuclear medicine data; the target metadata associated with the CT data includes at least one of dose and quality control parameters, scanning and reconstruction parameters, image attributes, CT image processing derived information, and radiation dose assessment values; the target metadata associated with the MRI data includes at least one of sequence baseline parameters, equipment and scanning parameters, enhancement information, and enhancement region markers; the target metadata associated with the X-ray data includes at least one of exposure and quality control parameters, image attributes, artifact markers, and typical site adaptation markers; the target metadata associated with the ultrasound data includes at least one of equipment and probe parameters, scanning parameters, and functional information; and the target metadata associated with the nuclear medicine data includes at least one of tracer and acquisition parameters, acquisition and reconstruction parameters, image attributes, and metabolic analysis markers.

[0086] The above-described products can perform the methods provided in any embodiment of this disclosure, and have the corresponding functional modules and beneficial effects for performing the methods.

[0087] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0088] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0089] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0090] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as DICOM file processing methods.

[0091] In some embodiments, the DICOM file processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the DICOM file processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the DICOM file processing method by any other suitable means (e.g., by means of firmware).

[0092] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0093] Computer programs used to implement the methods of this disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0094] In the context of this disclosure, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0095] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0096] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0097] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0098] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0099] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the DICOM file processing method according to any embodiment of this disclosure.

[0100] In implementing a computer program product, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A DICOM file processing method characterized by, The method comprises the following steps: acquiring a DICOM file to be processed, performing anomaly detection and preprocessing on the DICOM file to be processed, wherein the DICOM file comprises multi-modal image data and metadata in binary form; for the preprocessed DICOM file without anomaly, parsing the DICOM file without anomaly to obtain parsed multi-modal image data and metadata, and performing persistent processing on the parsed multi-modal image data and metadata; identifying the image type of the multi-modal image data, and calling a data display template corresponding to the image type; screening target metadata associated with the image type from the persistent processed metadata, filling the data display template with the target metadata and the parsed multi-modal image data, and forming an image display report.

2. The method of claim 1, wherein, The anomaly detection and preprocessing on the DICOM file to be processed comprises at least one of the following: reading the file header identifier of the DICOM file, and performing validity detection on the DICOM file based on the file header identifier; parsing the file header length of the DICOM file, and performing file header anomaly detection on the DICOM file based on the file header length; parsing the image basic parameters of the multi-modal image data in the DICOM file, and performing image anomaly detection on the DICOM file based on the image basic parameters; performing redundancy removal processing on the DICOM file without anomaly.

3. The method of claim 1, wherein, The DICOM file comprises a binary stream, and the binary stream comprises tags, data lengths and data contents of a plurality of data elements; the data elements comprise metadata and multi-modal image data; The parsing of the DICOM file without anomaly to obtain parsed multi-modal image data and metadata comprises the following steps: in the binary stream of the DICOM file, reading a binary tag based on the tag length, and mapping the binary tag content to a text tag based on a tag mapping configuration file, wherein the tag mapping configuration file comprises a mapping relationship between a preset value dictionary and a binary tag; obtaining the data length corresponding to the binary tag, determining the starting offset address and the ending offset address of the data content corresponding to the data element based on the data length, reading binary data content from the binary stream based on the starting offset address and the ending offset address of the data content, and converting the binary data content to metadata or multi-modal image data.

4. The method of claim 3, wherein, The start offset address of the data content is , and the end offset address of the data content is ; Wherein, the S is the start offset address of the data content of the current data element; is the file header length of the DICOM file; n is the number of data elements that have been parsed before the current data element; m is the tag length; is the length value corresponding to the data length item of the i th parsed data element; is the length value of the data content of the i th parsed data element; is the data length of the current data element.

5. The method of claim 1, wherein, The persistent processing on the parsed multi-modal image data and metadata comprises the following steps: downloading the parsed multi-modal image data to a local device, and storing the parsed multi-modal image data in a storage associated with a reading device; performing structured processing on the parsed metadata according to the image type, and storing the parsed metadata in a document database.

6. The method of claim 1, wherein, The method further comprises the following steps: determining a verification DICOM file in the processed DICOM files based on a set proportion; The DICOM file is parsed to obtain parsed multi-modal image data and metadata corresponding to the DICOM file, and the parsed multi-modal image data and metadata are compared with standard parsed multi-modal image data and standard parsed metadata corresponding to the DICOM file to obtain a check index, the check index including at least one of parsing accuracy, missing rate, and integrity accuracy. At least one of a tag mapping configuration file and an offset address calculation method used in the DICOM file parsing process is updated based on the check index.

7. The method of claim 1, wherein, The multi-modal image data includes at least one of CT data, MRI data, X-ray data, ultrasound data, and nuclear medicine data. The target metadata associated with the CT data includes at least one of dose and quality control parameters, scanning and reconstruction parameters, image attributes, CT image processing derived information, and radiation dose evaluation values. The target metadata associated with the MRI data includes at least one of sequence basic parameters, device and scanning parameters, enhancement information, and enhancement region labels. The target metadata associated with the X-ray data includes at least one of exposure and quality control parameters, image attributes, artifact labels, and typical site adaptation labels. The target metadata associated with the ultrasound data includes at least one of device and probe parameters, scanning parameters, and functional information. The target metadata associated with the nuclear medicine data includes at least one of tracer and acquisition parameters, acquisition and reconstruction parameters, image attributes, and metabolic analysis labels.

8. A DICOM file processing apparatus characterized by comprising: The method comprises: a file acquisition module configured to acquire a DICOM file to be processed, perform anomaly detection and preprocessing on the DICOM file to be processed, and store multi-modal image data and metadata in the DICOM file in binary form; a file parsing module configured to parse a preprocessed DICOM file without anomalies to obtain parsed multi-modal image data and metadata, and perform persistent processing on the parsed multi-modal image data and metadata; an image type identification module configured to identify an image type of the multi-modal image data, and call a data display template corresponding to the image type; an image display report generation module configured to filter target metadata associated with the image type from the persistent metadata, fill the target metadata and the parsed multi-modal image data into the data display template, and form an image display report.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the DICOM file processing method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the DICOM file processing method of any one of claims 1-7 when executed by the processor.

11. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program, when executed by the processor, implements the DICOM file processing method of any one of claims 1-7.

Images