Medical image data storage method and device and storage medium

Abstract

The invention discloses a medical image data storage method and device and a storage medium, and relates to the technical field of electronic digital data processing, and the method comprises the steps: obtaining medical image data collected by a medical device, storing the medical image data in a disk, and generating label information of the medical image data, the label information comprises at least one of a basic label, a semantic label and a prediction label; generating query popularity corresponding to the medical image data according to the label information, and generating a migration condition of the medical image data according to the query popularity; and when the medical image data meets the migration condition, migrating the medical image data from the magnetic disk to a magnetic tape. According to the method, the multi-dimensional labels are automatically added to the medical image data, the query popularity is calculated in real time according to the label information, the migration condition is formulated according to the query popularity, the accuracy of data migration is improved, and intelligent hierarchical storage of hot data remaining and cold data carrying is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of electronic digital data processing, and in particular to a storage method, device, and storage medium for medical imaging data. Background Art

[0002] In scenarios like medical imaging data management, disks are commonly used to store massive amounts of data. However, the long-term use of cold data and the lack of automated lifecycle management lead to high disk-based storage costs. Operations and maintenance personnel often rely on manual scripts or scheduled tasks to manage cold data, which can lead to inaccurate identification of cold data within medical imaging data and lead to mis-migration. Summary of the Invention

[0003] The main purpose of this application is to provide a storage method, device and storage medium for medical imaging data, aiming to solve the technical problem of inaccurate determination of cold data in medical imaging data, which leads to erroneous migration.

[0004] To achieve the above objectives, the present application proposes a method for storing medical imaging data, the method comprising: Acquire medical imaging data collected by a medical device, store the medical imaging data in a disk, and generate label information for the medical imaging data, the label information including at least one of a basic label, a semantic label, and a predicted label; Generating a query popularity corresponding to the medical imaging data according to the tag information, and generating a migration condition for the medical imaging data according to the query popularity; When the medical imaging data meets the migration condition, the medical imaging data is migrated from the disk to the tape.

[0005] In one embodiment, the step of generating label information for the medical image data includes at least one of the following: Extracting features from basic information corresponding to the medical imaging data to obtain basic features, and generating the basic labels based on the basic features, wherein the basic information includes at least device information and patient information; Extracting features from the diagnostic data corresponding to the medical imaging data to obtain diagnostic features, and generating the semantic labels based on the diagnostic features; Image feature extraction is performed on the medical image data to obtain medical image features, and the prediction label is generated according to the medical image features.

[0006] In one embodiment, the step of generating the query popularity corresponding to the medical imaging data according to the tag information includes: Determining a data access mode for the medical imaging data based on the tag information and department access requirements; wherein the data access mode includes at least one of access frequency, access scope, data volume, and predictability; The query heat is determined according to the data access pattern.

[0007] In one embodiment, before the step of migrating the medical imaging data from the disk to the tape, the method further includes: generating a thumbnail corresponding to the medical image data, wherein the resolution of the thumbnail is lower than the resolution of the medical image data; saving the thumbnail in the disk; If a query request for the medical imaging data is received, the thumbnail corresponding to the query request is output.

[0008] In one embodiment, the method further comprises: When the medical image data is stored in the magnetic tape, generating a migration heat of the medical image data according to the tag information; generating a re-migration condition for the medical imaging data according to the re-migration heat; When the medical imaging data meets the migration condition, the medical imaging data is migrated from the magnetic tape to the magnetic disk.

[0009] In one embodiment, the step of generating the re-migration popularity of the medical image data according to the tag information includes: Obtaining access data corresponding to the tag information, the access data including historical access frequency and / or average access time of the associated tag information; The return heat of the medical imaging data is generated according to the tag information, the access data and the current disease epidemic trend.

[0010] In one embodiment, the method further comprises: Upon receiving the patient's registration information in the registration system, generating a query request for the medical imaging data of the department corresponding to the registration information; the registration information includes the patient information and the department type; When the medical imaging data corresponding to the query request is located on the magnetic tape, the medical imaging data is migrated from the magnetic tape to the magnetic disk.

[0011] In one embodiment, after the step of generating a query request for the medical imaging data of the department corresponding to the registration information, the method further includes: Determining a query priority corresponding to the query request according to the patient information and the department type; Determining a transmission bandwidth for data migration based on the query priority; The step of migrating the medical imaging data from the magnetic tape to the magnetic disk comprises: The medical image data is migrated from the magnetic tape to the magnetic disk based on the transmission bandwidth.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage device for medical imaging data, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the medical imaging data storage method as described above.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the medical imaging data storage method described above are implemented.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the medical imaging data storage method as described above.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: By automatically attaching multi-dimensional tags to medical imaging data, and then calculating the query popularity in real time based on the tag information and formulating migration conditions accordingly, the accuracy of data migration is improved, and intelligent hierarchical storage is achieved with hot data retained on disk and cold data returned to tape. This ensures that high-hot medical imaging data is readily accessible on disk to meet clinical rapid retrieval needs, and enables low-hot medical imaging data to be transferred to tape in a timely manner, significantly reducing long-term storage costs. This ensures the continuity of medical services while significantly improving storage resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A flowchart of the first embodiment of the method for storing medical image data of the present application is provided; Figure 2A schematic diagram of a simplified process flow provided in Example 1 of the method for storing medical image data of the present application; Figure 3 A flowchart of the second embodiment of the method for storing medical image data of the present application is provided; Figure 4 A flowchart of the third embodiment of the method for storing medical image data of the present application is provided; Figure 5 A flowchart of a fourth embodiment of the method for storing medical image data of the present application is provided; Figure 6 A flowchart of Embodiment 5 of the method for storing medical image data of this application is provided; Figure 7 A brief flowchart of Embodiment 5 of the method for storing medical image data of this application is provided; Figure 8 Another simplified flowchart provided for Embodiment 5 of the method for storing medical image data of this application; Figure 9 Schematic diagram of the device structure of the hardware operating environment involved in the medical imaging data storage method in the embodiment of the present application.

[0019] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0021] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0022] In scenarios like medical imaging data management, disks are commonly used to store massive amounts of data. However, the long-term use of cold data and the lack of automated lifecycle management lead to high disk-based storage costs. Operations and maintenance personnel often rely on manual scripts or scheduled tasks to manage cold data, which can lead to inaccurate identification of cold data within medical imaging data and lead to mis-migration.

[0023] The main solution of the embodiment of the present application is: obtaining medical imaging data collected by medical equipment, storing the medical imaging data on a disk, and generating label information for the medical imaging data, the label information including at least one of a basic label, a semantic label, and a predicted label; generating query popularity corresponding to the medical imaging data based on the label information, and generating migration conditions for the medical imaging data based on the query popularity; when the medical imaging data meets the migration conditions, migrating the medical imaging data from the disk to the tape.

[0024] In this embodiment, for ease of description, the following description is made with the storage device of medical image data as the execution subject.

[0025] This application provides a solution that improves the accuracy of data migration by automatically attaching multi-dimensional tags to medical imaging data, and then calculating the query popularity in real time based on the tag information and formulating migration conditions accordingly. It realizes intelligent hierarchical storage with hot data retained on disk and cold data returned to tape. It ensures that high-hot medical imaging data is accessible on disk at any time to meet clinical rapid retrieval needs, and enables low-hot medical imaging data to be transferred to tape in a timely manner, greatly reducing long-term storage costs, thereby significantly improving storage resource utilization while ensuring the continuity of medical business.

[0026] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of performing the above functions, a medical imaging data storage device, etc. The following uses a medical imaging data storage device as an example to illustrate this embodiment and the following embodiments.

[0027] Based on this, the present invention provides a method for storing medical imaging data. Figure 1 , Figure 1 This is a flowchart of the first embodiment of the medical image data storage method of the present application.

[0028] In this embodiment, the medical imaging data storage method includes steps S10 to S30: Step S10: acquiring medical imaging data collected by a medical device, storing the medical imaging data in a disk, and generating label information for the medical imaging data, wherein the label information includes at least one of a basic label, a semantic label, and a predicted label.

[0029] In this embodiment, after acquiring medical imaging data collected by a medical device, the medical imaging data is first stored on a disk, and then the medical imaging data is migrated from the disk to a tape. The medical device may be an X-ray device, a CT (Computed Tomography) scan, an MRI (Magnetic Resonance Imaging), an ultrasound device, a nuclear medicine device, an endoscope, or a surgical navigation device or a pathology scanner.

[0030] In one embodiment, basic tags are structured technical parameters extracted from DICOM (Digital Imaging and Communications in Medicine) metadata, providing an objective technical description of medical imaging data. Optionally, basic tags include device information, patient information, examination information, spatial parameters, and more. For example, device information includes the device model; patient information includes patient ID (identification), gender, and examination date; examination information includes examination type and serial number; and spatial parameters include pixel pitch and pitch size.

[0031] In one embodiment, semantic tags are descriptions of clinical significance annotated by professionals, reflecting the medical interpretation of the image. Optionally, semantic tags include diagnostic conclusions, departments, and patient risk levels. For example, diagnostic conclusions include anatomical structure, lesion description, pathological characteristics, and urgency indicators. Departments include department type and department urgency. Patient risk levels include disease severity and urgency of the disease course. For example, the diagnostic conclusion is lung nodules, the department is thoracic surgery, and the patient risk level is low risk.

[0032] In one embodiment, the predicted labels are the results of an analysis of medical imaging data, typically a prospective analysis obtained through the association of AI (Artificial Intelligence) model reasoning and clinical knowledge graphs. Optionally, the predicted labels include lesion properties, texture analysis, and prognosis prediction.

[0033] Step S20 , generating a query popularity corresponding to the medical imaging data according to the tag information, and generating a migration condition for the medical imaging data according to the query popularity.

[0034] In this embodiment, query popularity is used to dynamically assess the urgency and frequency of the need to access medical imaging data. Optionally, query popularity can be determined by factors such as access frequency, access timeliness, access regularity, associated triggers, and department weight. Optionally, when tag information changes, such as when a doctor adds a new follow-up order or a patient schedules a follow-up appointment, query popularity is immediately recalculated. For example, if a patient's follow-up appointment is changed from 6-monthly to 1-month emergency review, the clinical potential demand weight for their imaging doubles, and the popularity value increases immediately.

[0035] Optionally, medical imaging data is archived based on its query popularity and the length of time since the shooting time. For example, data that has not been queried for one consecutive year is archived, or data that was shot three years ago and has low query popularity is archived.

[0036] In an optional embodiment, thumbnails corresponding to the medical image data are generated, with a lower resolution than the actual resolution of the medical image data; the thumbnails are saved to disk; and upon receiving a query request for the medical image data, the thumbnail corresponding to the query request is output. Generating and pushing low-resolution thumbnails before officially migrating high-resolution medical image data allows users to instantly obtain readable images, significantly shortening wait times and improving diagnostic efficiency. This also reduces network load and storage pressure, enabling efficient, low-cost data transfer with preview-first, download-later.

[0037] In this embodiment, the query popularity of the medical imaging data is generated based on at least one of the basic tag, the semantic tag, and the predicted tag.

[0038] In one embodiment, query popularity for medical imaging data is generated based on basic tags. Different basic tags correspond to different query popularity. Optionally, query popularity is obtained by predicting the basic tags based on a prediction model.

[0039] In one embodiment, query popularity for medical imaging data is generated based on semantic tags. Different semantic tags correspond to different query popularity. Optionally, query popularity is obtained by predicting semantic tags based on a prediction model.

[0040] In one embodiment, query popularity for medical imaging data is generated based on the predicted tags. Different predicted tags correspond to different query popularity. Optionally, the query popularity is obtained by predicting the predicted tags based on a prediction model.

[0041] In one embodiment, query popularity for medical imaging data is generated based on basic tags and semantic tags. A first popularity is determined based on the basic tags, a second popularity is determined based on the semantic tags, and the query popularity for the medical imaging data is generated based on the first popularity, the second popularity, and their corresponding weight parameters. Exemplarily, query popularity = first popularity * first weight + second popularity * second weight.

[0042] In one embodiment, query popularity for medical imaging data is generated based on the basic tags and predicted tags. A first popularity is determined based on the basic tags, a third popularity is determined based on the predicted tags, and the query popularity for the medical imaging data is generated based on the first popularity, the third popularity, and their corresponding weight parameters. Exemplarily, query popularity = first popularity * first weight + third popularity * third weight.

[0043] In one embodiment, query popularity for medical imaging data is generated based on semantic tags and predicted tags. A second popularity is determined based on the semantic tags, a third popularity is determined based on the predicted tags, and the query popularity for the medical imaging data is generated based on the second popularity, the third popularity, and their corresponding weight parameters. Exemplarily, query popularity = second popularity * second weight + third popularity * third weight.

[0044] In one embodiment, query popularity for medical imaging data is generated based on basic tags, semantic tags, and predicted tags. A first popularity is determined based on the basic tags, a second popularity is determined based on the semantic tags, and a third popularity is determined based on the predicted tags. The query popularity for medical imaging data is generated based on the first, second, and third popularity values ​​and their corresponding weight parameters. For example, query popularity = first popularity * first weight + second popularity * second weight + third popularity * third weight.

[0045] Optionally, the migration condition includes a retention threshold for the medical imaging data. Different query popularity corresponds to different retention thresholds. The higher the query popularity, the higher the retention threshold. Conversely, the lower the query popularity, the lower the retention threshold.

[0046] Optionally, the migration condition includes a reference heat threshold of a type corresponding to the medical imaging data. Optionally, the reference heat threshold may be an average heat value of the medical imaging data of the type.

[0047] For clinical emergencies, such as public health events, migration conditions can be adjusted. When the 24-hour popularity of a certain type of image increases by more than 200%, a circuit breaker is automatically triggered, suspending the migration process of this type of image. Images that have been migrated to tape are automatically migrated back to disk, giving priority to using idle bandwidth without affecting normal diagnosis and treatment, ensuring high-speed access in emergency situations.

[0048] Optionally, the query popularity of the medical imaging data is determined based on the tag information and the doctor's access data. Base popularity is determined based on the tag information, and a modified popularity is determined based on the medical access data. The query popularity is then determined based on the sum of the base and modified popularity. When a doctor accesses medical imaging data and encounters slow loading due to data already migrated to tape, the system prompts lightweight options, such as whether the access is urgent. If the user selects "yes," the modified popularity is determined based on the urgency and / or the corresponding number of accesses.

[0049] Optionally, the search popularity of medical imaging data can be determined based on tag information and archiving regulations. Migration conditions can then be automatically calibrated annually based on the image retention period specified in the medical data archiving regulations. If regulations require the retention period for medical imaging data to be extended from 15 to 20 years, the migration conditions for medical imaging data will need to be adjusted accordingly to avoid compliance risks associated with migration.

[0050] Step S30: When the medical imaging data meets the migration condition, the medical imaging data is migrated from the disk to the tape.

[0051] In this embodiment, when the medical imaging data does not meet the migration condition, the medical imaging data is stored in a magnetic tape.

[0052] Optionally, the migration condition includes a storage time threshold for the medical imaging data. If the storage time of the medical imaging data is greater than or equal to the storage time threshold, the medical imaging data is determined to meet the migration condition; if the storage time of the medical imaging data is less than the storage time threshold, the medical imaging data is determined to not meet the migration condition.

[0053] In this embodiment, referring to Figure 2 After obtaining the medical imaging data collected by the medical device, the medical imaging data is stored in the disk. When the access timestamp of the data is determined to exceed the preset storage time threshold, the medical imaging data is migrated from the disk to the tape.

[0054] Optionally, the migration condition includes a reference heat threshold for the type of medical imaging data. Optionally, the reference heat threshold may be the average heat value of medical imaging data of that type. When the query heat of the medical imaging data is greater than or equal to the reference heat threshold, the medical imaging data is determined not to meet the migration condition. When the query heat of the medical imaging data is less than the reference heat threshold, the medical imaging data is determined to meet the migration condition.

[0055] In one embodiment, when multiple medical imaging data simultaneously meet the migration conditions, they are sorted based on the ratio of query popularity to storage cost, that is, the ratio of query popularity to storage space occupation, and low-value and high-occupancy data are migrated first.

[0056] In one embodiment, the medical imaging data and the corresponding timestamp are written to a storage medium, and a storage location mark of the metadata of the medical imaging data is generated. The storage location mark in the metadata is used to determine the storage medium where the surveillance video is located; after the medical imaging data is migrated to the storage medium, the storage location mark in the metadata is updated.

[0057] In the technical solution of this embodiment, medical imaging data collected by medical equipment is obtained, the medical imaging data is stored on a disk, and label information for the medical imaging data is generated, the label information including at least one of a basic label, a semantic label, and a predicted label; the query popularity corresponding to the medical imaging data is generated based on the label information, and the migration conditions for the medical imaging data are generated based on the query popularity; when the medical imaging data meets the migration conditions, the medical imaging data is migrated from the disk to the tape. By automatically attaching multi-dimensional labels to the medical imaging data, and then calculating the query popularity in real time based on the label information and formulating the migration conditions accordingly, the accuracy of data migration is improved, and intelligent hierarchical storage is achieved, with hot data retained on disk and cold data returned to tape. This ensures that high-hot medical imaging data is readily accessible on the disk to meet clinical rapid retrieval needs, while also enabling low-hot medical imaging data to be promptly transferred to tape, significantly reducing long-term storage costs. This significantly improves storage resource utilization while ensuring medical business continuity.

[0058] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment can be referred to the above introduction and will not be described in detail later. Figure 3 , step S10 includes: Step S11, extracting features from basic information corresponding to the medical imaging data to obtain basic features, and generating the basic labels based on the basic features, wherein the basic information includes at least device information and patient information; Step S12, extracting features from the diagnostic data corresponding to the medical image data to obtain diagnostic features, and generating the semantic labels based on the diagnostic features; Step S13: performing image feature extraction on the medical image data to obtain medical image features, and generating the prediction label according to the medical image features.

[0059] In this embodiment, basic features include device parameter features, patient information features, and examination parameter features. For example, device parameter features include slice thickness and matrix size. Patient information features include age, gender, and ID, while examination parameter features include sequence type, number of frames, and dose.

[0060] Diagnostic features are clinically meaningful descriptions assigned by physicians based on a combination of lower-level features and medical knowledge. Examples of diagnostic features include ground-glass opacities, consolidation, cavitation, calcifications, fat density, fluid level, mass effect, enhancement pattern, restricted diffusion, and perfusion abnormalities.

[0061] Medical image features refer to objective, quantifiable visual or physical attributes that are directly extracted or observable from the medical image data itself. Medical image features include visual features and structural features. Among them, visual features include morphological features, intensity features, and texture features. For example, morphological features include size, area, volume, perimeter, diameter, shape, position, direction, boundary, contour, etc. Intensity features include average intensity, maximum intensity, minimum intensity, intensity distribution, density contrast between a specific area and the background or normal tissue, etc. Texture features include describing the grayscale change pattern of a local area of ​​the image, etc. Commonly used methods include grayscale co-occurrence matrix, wavelet transform, local binary pattern, etc. Structural features are used to describe more complex structural patterns or spatial relationships within organs, tissues or lesions. For example, vascular distribution pattern, bronchial wall thickening, interlobular septum thickening, deformation or displacement of specific anatomical structures, and spatial arrangement pattern.

[0062] In one embodiment, a basic feature extraction model is used to extract basic information corresponding to medical imaging data to obtain basic features, and basic labels are generated based on the basic features. A semantic feature extraction model is used to extract diagnostic data corresponding to the medical imaging data to obtain diagnostic features, and semantic labels are generated based on the diagnostic features. An image feature extraction model is used to extract image features from the medical imaging data to obtain medical image features, and predicted labels are generated based on the medical image features. Different feature extraction models are trained using corresponding types of data.

[0063] In the technical solution of this embodiment, features are automatically extracted from the three levels of basic information, diagnostic text and images, and three types of labels, namely basic, semantic and predictive, are generated to achieve full-dimensional characterization. This makes the subsequent query popularity calculation based on the label information more accurate, and the migration strategy more intelligent, ensuring that high-value images are immediately accessible while avoiding low-value data from occupying expensive disks for a long time, thereby significantly reducing operation and maintenance costs while improving storage efficiency.

[0064] Based on the first or second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiment can be referred to the above introduction and will not be described in detail later. Figure 4 , step S20 includes: Step S21, determining a data access mode of the medical imaging data based on the tag information and the department's access requirements; wherein the data access mode includes at least one of access frequency, access scope, data volume, and predictability; Step S22: determining the query popularity according to the data access pattern.

[0065] In this embodiment, the department visit requirements include the purpose of the department visit, timeliness requirements, frequency, scope, etc. For example, the departments include emergency, outpatient, inpatient, radiology, specialist consultation, scientific research, teaching, administration, etc.

[0066] A data access pattern for the medical imaging data is generated based on the tag information and department access requirements. Optionally, the data access pattern includes at least one of access sequence, access frequency, access timeliness, access scope, data volume, access regularity, and predictability. Optionally, query popularity for the medical imaging data is generated based on a combination of access pattern elements, particularly access frequency, access scope, data volume, and predictability.

[0067] In one embodiment, the data type of medical imaging data and department access requirements are input into a prediction model to obtain a data access pattern output by the prediction model, and the prediction model is trained by the data type of medical history data and department access requirements.

[0068] In an optional embodiment, the data access pattern is determined based on the tag information. Optionally, a mapping table between tag information and data access patterns is established, with different tag information corresponding to different data access patterns. Optionally, the data volume and access scope are determined based on the examination type in the tag information, and the access timeliness and access frequency are determined based on the urgency level in the tag information. The access timeliness and access frequency are determined based on the patient status in the tag information. Patient statuses include emergency, outpatient, inpatient, and discharged. The access frequency and predictability are determined based on the timestamp in the tag information, where access frequency typically decays exponentially over time. Predictability: Recent data access is more active but may not be very regular, while access to older data is typically low-frequency and has poor regularity. The access timeliness and access frequency are determined based on the diagnostic status in the tag information. Diagnostic statuses include preliminary report, reviewed report, revised report, and no report. The access scope, predictability, and access frequency are determined based on the relevance tags in the tag information. Relevance tags include tumor follow-up, postoperative review, teaching case, and scientific research case.

[0069] In an optional embodiment, the data access mode is determined according to the department's access requirements. Optionally, a mapping table of the relationship between department access requirements and data access modes is created. Different departments have different access requirements, and different department access requirements correspond to different data access modes. Optionally, when the department includes the emergency department, it is determined that the access timeliness is extremely high and immediate access is required; it is determined that the access frequency is high and the images of the current patient may be accessed multiple times in a short period of time; the access scope is focused on the current emergency examination and may quickly browse key historical films; the predictability is low and depends on the emergency flow and the suddenness of the case. Optionally, when the department includes the outpatient department, it is determined that the access timeliness is high and timely access is required during the patient's consultation period; the access frequency is concentrated in the patient's appointment period. The access scope mainly accesses the examinations related to this visit and necessary historical comparisons; the predictability is high and there is a certain regularity according to the appointment schedule. Optionally, when the department includes an inpatient ward, the access timeliness is medium, and visits are required for ward rounds and treatment plan formulation; the access frequency is high, and multiple visits may be required during hospitalization, especially when the condition changes; the access scope is related to the current hospitalization and important historical images; the predictability is medium, which is related to ward rounds and treatment plans. Optionally, when the department includes the radiology department, the access timeliness is determined to be high, and images need to be read efficiently for diagnosis; the access frequency is very high, and after the medical imaging data is uploaded, the physician needs to read, analyze, and write reports, and may review them repeatedly; the access scope requires a complete examination of the data set, and may need to compare historical images. The data volume is large, and the complete sequence needs to be loaded; the predictability is high, and it is usually processed in the order of the work list, and it is batch-based.

[0070] In an optional embodiment, a relationship mapping table among tag information, department access requirements, and data access modes is established, and different tag information corresponds to different data access modes.

[0071] In an optional embodiment, query popularity is determined based on the data access pattern, and a mapping relationship table between the data access pattern and query popularity is established. Optionally, when the data access pattern is high frequency and high timeliness, the scope is focused and the query popularity is determined to be high. When the data access pattern is medium frequency and medium timeliness, the query popularity is determined to be medium. When the data access pattern is low frequency and low timeliness, the query popularity is determined to be low.

[0072] In the technical solution of this embodiment, the department access requirements and multi-dimensional tags are integrated into a model to dynamically portray a data access pattern that is closer to the actual business, making the heat assessment more accurate and the hot and cold classification more reasonable. This not only avoids high-value hot data from being misjudged as cold data and affecting the diagnosis and treatment efficiency, but also prevents low-value cold data from occupying expensive disks for a long time, thereby maximizing storage resource utilization and reducing the total cost of ownership while ensuring the clinical experience.

[0073] Based on any one of the first to third embodiments of the present application, in the fourth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be described in detail later. Figure 5 , the method comprising: Step S40, when the medical image data is stored in the magnetic tape, generating the migration heat of the medical image data according to the tag information; Step S50, generating a relocation condition for the medical imaging data according to the relocation heat; Step S60 , when the medical imaging data meets the migration condition, migrating the medical imaging data from the magnetic tape to the magnetic disk.

[0074] Optionally, the medical imaging data can be migrated back on demand, and the data can be unfrozen and migrated back when the medical imaging data is needed, so as to migrate the medical imaging data from the tape to the disk.

[0075] In one embodiment, the relocation popularity of medical imaging data is generated based on the query popularity of the corresponding medical imaging data. Optionally, relocation popularity = query popularity × timeliness factor + associated access gain - storage cost factor. The timeliness factor = 1 / (current time - last access timestamp + 1). For example, the timeliness factor of recently frequently accessed data is close to 1, while that of obsolete data is close to 0. The associated access gain is weighted by the number of associations if the current type of medical imaging data is frequently accessed simultaneously with other medical imaging data. The storage cost factor is the access latency cost of tape cold storage and is a fixed penalty value.

[0076] In an optional embodiment, the re-migration heat of medical imaging data migrated from tape to disk is determined based on tag information. Optionally, a corresponding tag type is determined based on the tag information, and different tag types correspond to different re-migration heats. For example, when the urgency is critical, the re-migration heat is +0.8, requiring rapid re-migration to a high-speed disk. When the patient's status is emergency, the re-migration heat is +0.7, requiring real-time access by the emergency department. When the relevance is tumor follow-up, the re-migration heat is +0.5, indicating a high historical comparison requirement.

[0077] Optionally, different migration strategies correspond to different re-migration hotness levels. For example, if the re-migration hotness level is ≥ 1.5, real-time migration is required for emergency data access and intraoperative urgent needs. If the re-migration hotness level is 1.0-1.5, scheduled migration is performed for inpatient rounds and outpatient appointments. If the re-migration hotness level is 0.5-1.0, off-peak migration is performed, and scientific research data is preloaded and historical comparisons are performed. If the re-migration hotness level is < 0.5, no migration is performed, and tape storage is maintained.

[0078] In an optional embodiment, access data corresponding to the tag information is obtained, and the access data includes historical access frequency and / or average access time of the associated tag information; and the return heat of the medical imaging data is generated based on the tag information, access data and current disease epidemic trends.

[0079] It should be noted that historical access frequency is obtained through PACS (Picture Archiving and Communication System) log analysis. The average tag access time is calculated by calculating the average delay from request to opening of medical imaging data of the same tag, which is used to measure clinical urgency. Disease epidemic trends are determined based on reports from regional CDCs or nosocomial infection departments and are used to dynamically prioritize data for related diseases.

[0080] Optionally, the first modified popularity = historical access frequency weight × log (access frequency) + time decay coefficient × (1 / average access time). The historical access frequency weight assigns a higher base value to high-frequency access data; the time decay coefficient = e^(-0.1 × (current time - last access time) / 30). The shorter the average access time, the more urgent the clinical need.

[0081] The query popularity of medical imaging data is determined based on the tag information, and the second revised popularity of the medical imaging data is determined based on the current disease epidemic trends. The return popularity of the medical imaging data is determined based on the sum of the query popularity, the first revised popularity, and the second revised popularity.

[0082] In the technical solution of this embodiment, after the medical imaging data has been migrated to tape, the migration heat is continuously calculated. Once there is a centralized retrieval demand in clinical or scientific research, automatic migration is triggered, and the relevant data is quickly transferred back to the disk. This not only prevents doctors from waiting for a long time due to occasional high-frequency access to cold-stored data, but also avoids the waste of disk resources caused by a one-time full migration, realizes refined cold and hot classification according to demand, and further balances access efficiency and storage costs.

[0083] Based on any one of the first to fourth embodiments of the present application, in the fifth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be described in detail later. Figure 6 , the method comprising: Step S70: upon receiving the patient's registration information from the registration system, generating a query request for the medical imaging data of the department corresponding to the registration information; the registration information includes the patient information and the department type; Step S80: When the medical imaging data corresponding to the query request is located on the magnetic tape, the medical imaging data is migrated from the magnetic tape to the magnetic disk.

[0084] Make an appointment to migrate medical imaging data. According to the patient's registration information, the medical imaging data of the department where the patient is registered and related departments will be migrated to the disk in advance. The medical imaging data can be quickly read at the actual time of medical consultation.

[0085] In this embodiment, referring to Figure 7 The registration system is connected to the storage system in communication. When it receives registration information, it generates a registration event. When the data corresponding to the registration event is on the disk, there is no need to migrate the data. When the data corresponding to the registration event is on the tape, the data in the tape library needs to be migrated to the disk.

[0086] Optionally, a migration strategy is determined based on the department type in the registration information, and medical imaging data is migrated from tape to disk according to the migration strategy. For example, when the department is the emergency department, the migration content is all images, the migration time is immediate migration, and the migration strategy is preemptive transmission channel. When the department is orthopedics, the migration content is the last three X-rays, the migration time is one hour before the appointment, and the migration strategy is 3D reconstruction preprocessing. When the department is obstetrics, the migration content is ultrasound sequences, the migration time is 30 minutes before the appointment, and the migration strategy is dynamic video preloading.

[0087] Optionally, during migration, if it is an emergency, it is transmitted through a real-time broadband channel. If it is not an emergency, it is determined whether the remaining diagnosis time is less than the preset duration. If so, the priority channel is selected. If not, it is determined whether the data size is less than the preset data volume. If so, it is migrated through a standard channel. If not, it is migrated in batches.

[0088] In an optional embodiment, the query priority corresponding to the query request is determined based on the patient information and department type; the transmission bandwidth used for data migration is determined based on the query priority; and the medical imaging data is migrated from the tape to the disk based on the transmission bandwidth.

[0089] In one embodiment, referring to Figure 8 In the case of insufficient bandwidth, when low-priority tasks are running, the bandwidth of low-priority tasks is reduced to release bandwidth for high-priority tasks. When there are no low-priority tasks running, emergency bandwidth reservation is enabled, such as borrowing bandwidth reserved for scientific research or teaching.

[0090] Optionally, the data migration speed is determined based on query priority. The ratio of transmission bandwidth to data migration speed plus protocol overhead is ≥ data migration speed + protocol overhead. The data migration speed is the rate at which data is read from the tape and transferred to the disk buffer. Protocol overhead is the additional cost of data transmission. Therefore, a higher migration speed requirement requires a greater bandwidth, while a lower migration speed requirement requires a smaller bandwidth.

[0091] In the technical solution of this embodiment, the patient's registration information is instantly converted into an image query request for the corresponding department, and the data is automatically migrated to the disk when it is found that the data is still resident on the tape. This allows doctors to transfer historical images into high-speed storage before the patient arrives for examination. This eliminates the waiting time caused by tape loading delays, improves medical efficiency, and avoids the high storage costs brought about by the permanent storage of all images on the disk, thereby achieving the best balance between improving patient experience and optimizing resource utilization.

[0092] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the storage method of medical imaging data of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0093] The present application provides a storage device for medical imaging data, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the medical imaging data storage method of the above-mentioned embodiment 1.

[0094] Reference below Figure 9, which shows a schematic diagram of the structure of a medical imaging data storage device suitable for implementing embodiments of the present application. The medical imaging data storage device in the embodiments of the present application may include, but is not limited to, mobile terminals such as laptop computers, tablet computers (PADs), portable multimedia players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 9 The storage device for medical imaging data shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0095] like Figure 9 As shown, the medical image data storage device may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the medical image data storage device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: input devices 1007, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication devices 1009. The communication device 1009 can allow the medical image data storage device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a medical image data storage device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems can be implemented or provided instead.

[0096] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0097] The medical imaging data storage device provided in this application, utilizing the medical imaging data storage method of the aforementioned embodiment, can resolve the technical issue of inaccurate cold data determination within medical imaging data, leading to erroneous migration. Compared to the prior art, the beneficial effects of the medical imaging data storage device provided in this application are the same as those of the medical imaging data storage method provided in the aforementioned embodiment. Other technical features of the medical imaging data storage device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0098] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0099] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0100] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, and the computer-readable program instructions are used to execute the medical imaging data storage method in the above-mentioned embodiment.

[0101] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0102] The computer-readable storage medium may be included in a storage device for medical imaging data, or may exist independently without being incorporated into a storage device for medical imaging data.

[0103] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the storage device of medical imaging data, the storage device of medical imaging data: by automatically attaching multi-dimensional tags to medical imaging data, and then calculating the query popularity in real time based on the tag information and formulating migration conditions accordingly, the accuracy of data migration is improved, and intelligent hierarchical storage of hot data on disk and cold data on tape is realized, which ensures that high-hot medical imaging data is accessible on disk at any time to meet clinical rapid retrieval needs, and enables low-hot medical imaging data to be transferred to tape in a timely manner, greatly reducing long-term storage costs, thereby significantly improving storage resource utilization while ensuring the continuity of medical business.

[0104] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0106] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0107] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for storing medical image data. This computer-readable storage medium can address the technical issue of inaccurate cold data determination within medical image data, leading to erroneous migration. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the medical image data storage method provided in the aforementioned embodiments and are not further elaborated here.

[0108] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned medical imaging data storage method when executed by a processor.

[0109] The computer program product provided in this application can resolve the technical problem of inaccurate cold data identification in medical imaging data, which can lead to erroneous migration. Compared to the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the medical imaging data storage method provided in the above-mentioned embodiment, and are not further elaborated here.

[0110] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for storing medical image data, characterized in that: The storage method of the medical imaging data includes: Acquire medical imaging data collected by a medical device, store the medical imaging data in a disk, and generate label information for the medical imaging data, the label information including at least one of a basic label, a semantic label, and a predicted label; Generating a query popularity corresponding to the medical imaging data according to the tag information, and generating a migration condition for the medical imaging data according to the query popularity; When the medical imaging data meets the migration condition, the medical imaging data is migrated from the disk to the tape.

2. The method for storing medical image data according to claim 1, wherein: The step of generating label information of the medical image data includes at least one of the following: Extracting features from basic information corresponding to the medical imaging data to obtain basic features, and generating the basic labels based on the basic features, wherein the basic information includes at least device information and patient information; Extracting features from the diagnostic data corresponding to the medical imaging data to obtain diagnostic features, and generating the semantic labels based on the diagnostic features; Image feature extraction is performed on the medical image data to obtain medical image features, and the prediction label is generated according to the medical image features.

3. The method for storing medical image data according to claim 1, wherein: The step of generating the query popularity corresponding to the medical imaging data according to the tag information includes: Determining a data access mode for the medical imaging data based on the tag information and department access requirements; wherein the data access mode includes at least one of access frequency, access scope, data volume, and predictability; The query heat is determined according to the data access pattern.

4. The method for storing medical image data according to claim 1, wherein: Before the step of migrating the medical imaging data from the disk to the tape, the method further includes: generating a thumbnail corresponding to the medical image data, wherein the resolution of the thumbnail is lower than the resolution of the medical image data; saving the thumbnail in the disk; If a query request for the medical imaging data is received, the thumbnail corresponding to the query request is output.

5. The method for storing medical image data according to claim 1, wherein: The method further comprises: When the medical image data is stored in the magnetic tape, generating a migration heat of the medical image data according to the tag information; generating a re-migration condition for the medical imaging data according to the re-migration heat; When the medical imaging data meets the migration condition, the medical imaging data is migrated from the magnetic tape to the magnetic disk.

6. The method for storing medical image data according to claim 5, wherein: The step of generating the re-migration heat of the medical imaging data according to the tag information includes: Obtaining access data corresponding to the tag information, the access data including historical access frequency and / or average access time of the associated tag information; The return heat of the medical imaging data is generated according to the tag information, the access data and the current disease epidemic trend.

7. The method for storing medical image data according to claim 1, wherein: The method further comprises: Upon receiving the patient's registration information in the registration system, generating a query request for the medical imaging data of the department corresponding to the registration information; the registration information includes the patient information and the department type; When the medical imaging data corresponding to the query request is located on the magnetic tape, the medical imaging data is migrated from the magnetic tape to the magnetic disk.

8. The method for storing medical image data according to claim 7, wherein: After the step of generating a query request for the medical imaging data of the department corresponding to the registration information, the method further includes: Determining a query priority corresponding to the query request according to the patient information and the department type; Determining a transmission bandwidth for data migration based on the query priority; The step of migrating the medical imaging data from the magnetic tape to the magnetic disk comprises: The medical image data is migrated from the magnetic tape to the magnetic disk based on the transmission bandwidth.

9. A storage device for medical imaging data, characterized in that: The medical imaging data storage device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the medical imaging data storage method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the medical imaging data storage method according to any one of claims 1 to 8 are implemented.

Images