CN117316396A - Medical image multi-sequence contrast labeling method and system based on DICOM standard - Google Patents
Medical image multi-sequence contrast labeling method and system based on DICOM standard Download PDFInfo
- Publication number
- CN117316396A CN117316396A CN202311175951.8A CN202311175951A CN117316396A CN 117316396 A CN117316396 A CN 117316396A CN 202311175951 A CN202311175951 A CN 202311175951A CN 117316396 A CN117316396 A CN 117316396A
- Authority
- CN
- China
- Prior art keywords
- medical image
- labeling
- image file
- sequence
- image data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000002372 labelling Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000003384 imaging method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000013526 transfer learning Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- CYTYCFOTNPOANT-UHFFFAOYSA-N Perchloroethylene Chemical compound ClC(Cl)=C(Cl)Cl CYTYCFOTNPOANT-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000000586 desensitisation Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- JXSJBGJIGXNWCI-UHFFFAOYSA-N diethyl 2-[(dimethoxyphosphorothioyl)thio]succinate Chemical compound CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC JXSJBGJIGXNWCI-UHFFFAOYSA-N 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000009206 nuclear medicine Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a medical image multi-sequence contrast labeling method and system based on a DICOM standard, and relates to the technical field of medical image processing. The method comprises the following steps: acquiring medical image data, and arranging and managing the medical image data according to a DICOM standard to obtain a corresponding medical image file; deleting the metadata related to privacy in the medical image file; extracting pixel data in a medical image file for multi-sequence comparison; and performing target labeling on pixel data in the medical image file based on a preset target labeling model. The invention manages the medical image data based on DICOM standard, and realizes the multi-sequence contrast labeling of the medical image data; meanwhile, privacy security of the image data in the labeling process can be considered.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to a medical image multi-sequence contrast labeling method and system based on a DICOM standard.
Background
Tomographic medical images such as CT and MR are important means for non-invasively examining the internal tissue structure of a patient's organ, and are also a very important non-invasive means for researching and analyzing the pathological histological characteristics of lesions. In analyzing and diagnosing with these images, the physician first needs to annotate the images to determine the region of interest. However, the labeling of medical imaging regions of interest in current clinical practice is very dependent on expert experience and is a subjective, time-consuming task. Furthermore, primary doctors are unable to accurately and efficiently mark regions of interest in medical images.
Although some medical image labeling software is available to assist doctors in labeling regions of interest, similar existing technologies include medical image processing software such as Osirix, horos, 3D slice, radiAnt, etc., but these software all have some drawbacks: firstly, they require the operations of professionals, with high use costs; secondly, the interfaces of the software are complex, a certain learning curve is needed, and the software does not accord with the analysis and diagnosis habits of doctors; finally, because these software can access the patient's personal information and medical record data, there are privacy and security risks.
Disclosure of Invention
In order to overcome the above problems or at least partially solve the above problems, the present invention provides a medical image multi-sequence contrast labeling method and system based on DICOM standard, which manages medical image data based on DICOM standard to realize medical image data multi-sequence contrast labeling; meanwhile, privacy security of the image data in the labeling process can be considered.
In order to solve the technical problems, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a medical image multi-sequence contrast labeling method based on DICOM standard, comprising the following steps:
acquiring medical image data, and performing arrangement management on the medical image data according to a DICOM standard to obtain a corresponding medical image file, wherein the medical image file comprises metadata and pixel data;
deleting the metadata related to privacy in the medical image file;
extracting pixel data in a medical image file for multi-sequence comparison;
and performing target labeling on pixel data in the medical image file based on a preset target labeling model.
According to the invention, medical image data are reasonably arranged by combining with the DICOM standard, so that a medical image file with a hierarchical structure is formed to perform standardized management on patient image data, the subsequent processing of privacy data is facilitated, the subsequent sequence comparison and labeling are performed only on the image data in the medical image file, the safety of data labeling is ensured, and the user privacy data leakage is avoided; meanwhile, the invention performs the comparison of the multi-sequence medical image data, and a plurality of sequences are placed in adjacent windows for observation, thereby being beneficial to quickly and accurately finding out the boundary of the region of interest, performing comprehensive and accurate data comparison and improving the accuracy of the subsequent target labeling.
Based on the first aspect, further, the method for performing target labeling on pixel data in a medical image file based on the preset target labeling model includes the following steps:
and sequentially extracting pixel data in each sequence in the medical image file based on a preset target labeling model, and labeling the target on the corresponding pixel data.
Based on the first aspect, the method for managing the arrangement of the medical image data according to the DICOM standard further comprises the following steps:
according to the DICOM standard, medical image data are sequentially organized into a patient folder, an examination folder, a sequence folder and a slice file according to a hierarchy, so that a final medical image file is obtained.
Based on the first aspect, the medical image multi-sequence contrast labeling method based on the DICOM standard further comprises the following steps:
constructing an initial annotation model based on the SAM model and the transfer learning;
and acquiring and carrying out knowledge energization according to the medical image data, and carrying out optimization training on the initial annotation model to construct a target annotation model.
In a second aspect, the invention provides a medical image multi-sequence contrast labeling system based on DICOM standard, comprising an image data arrangement module, a privacy data processing module, a multi-sequence contrast module and a target labeling module, wherein:
the image data arrangement module is used for acquiring medical image data, and carrying out arrangement management on the medical image data according to a DICOM standard so as to obtain a corresponding medical image file, wherein the medical image file comprises metadata and pixel data;
the privacy data processing module is used for deleting the metadata related to privacy in the medical image file;
the multi-sequence comparison module is used for extracting pixel data in the medical image file to carry out multi-sequence comparison;
the target labeling module is used for labeling the target on the pixel data in the medical image file based on a preset target labeling model.
The system reasonably arranges the medical image data by combining with the DICOM standard through the matching of the image data arranging module, the multi-sequence comparison module, the target labeling module and other modules to form the medical image file with a hierarchical structure, so that the standardized management of the patient image data is realized, the subsequent processing of privacy data is facilitated, the sequence comparison and labeling are carried out only on the image data in the medical image file, the safety of data labeling is ensured, and the leakage of privacy data of a user is avoided; meanwhile, the invention performs the comparison of the multi-sequence medical image data, and a plurality of sequences are placed in adjacent windows for observation, thereby being beneficial to quickly and accurately finding out the boundary of the region of interest, performing comprehensive and accurate data comparison and improving the accuracy of the subsequent target labeling.
In a third aspect, the present application provides an electronic device comprising a memory for storing one or more programs; a processor; the method of any of the first aspects described above is implemented when one or more programs are executed by a processor.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as in any of the first aspects described above.
The invention has at least the following advantages or beneficial effects:
the invention provides a medical image multi-sequence contrast labeling method and a system based on the DICOM standard, which are used for reasonably arranging medical image data by combining with the DICOM standard to form a medical image file with a hierarchical structure so as to carry out standardized management on patient image data, and also facilitate the subsequent processing of privacy data, and only carry out sequence contrast and labeling on image data in the medical image file, thereby ensuring the security of data labeling and avoiding the leakage of privacy data of users; meanwhile, the invention performs the comparison of the multi-sequence medical image data, and a plurality of sequences are placed in adjacent windows for observation, thereby being beneficial to quickly and accurately finding out the boundary of the region of interest, performing comprehensive and accurate data comparison and improving the accuracy of the subsequent target labeling.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a medical image multi-sequence contrast labeling method based on DICOM standard according to an embodiment of the invention;
FIG. 2 is a schematic block diagram of a medical image multi-sequence contrast labeling system based on DICOM standard according to an embodiment of the invention;
fig. 3 is a block diagram of an electronic device according to an embodiment of the present invention.
Reference numerals illustrate: 100. an image data arrangement module; 200. a privacy data processing module; 300. a multi-sequence comparison module; 400. a target labeling module; 101. a memory; 102. a processor; 103. a communication interface.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the description of the embodiments of the present invention, "plurality" means at least 2.
Examples:
as shown in fig. 1, in a first aspect, an embodiment of the present invention provides a medical image multi-sequence contrast labeling method based on DICOM standard, which includes the following steps:
s1, acquiring medical image data, and arranging and managing the medical image data according to DICOM (Digital Imaging andCommunications in Medicine) standard to obtain a corresponding medical image file; the medical image file includes metadata including privacy sensitive fields, imaging parameters fields, and other ancillary fields, and pixel data. DICOM standards are standards for digital medical image transmission, display and storage established by the american society of radiology (American College of Radiology, ACR) and the national electronics manufacturers association (National Electrical ManufactorersAssociation, NEMA). The DICOM standard defines the composition format and exchange method of images and their related information, and with this standard, one can set up an interface on the image device to complete the input/output work of image data. The DICOM standard is based on an industrial standard of computer networks that can help to more efficiently transfer exchanged digital images between medical imaging devices including not only CT, MR, nuclear medicine and ultrasound examinations, but also CR, film digitizing systems, video acquisition systems, HIS/RIS information management systems, and the like.
Further, the method comprises the steps of: according to the DICOM standard, medical image data are sequentially organized into a patient folder, an examination folder, a sequence folder and a slice file according to a hierarchy, so that a final medical image file is obtained.
In some embodiments of the invention, the medical image data is formatted in accordance with the file format of the DICOM standard organization: 1 a plurality of examinations under the patient, 1 scanning (1 scanning into 1 sequence) in 1/examination, 1 sequence contains the section (layer) of a plurality of serial numbers, is favorable to storing source file and mark file separation, and mark file only need to store patient serial number (after encryption), inspection ID, serial number, mark position point, because the source file is according to DICOM standard organization, can find original image file and the interest area of mark promptly according to above-mentioned mark information, and the file of storing above-mentioned mark information obviously has little storage space demand, greatly reduced storage space. In the prior art, other software storage labels do occupy a storage space, however, the file is arranged according to the DICOM standard, all simple information can find the original image and the interest area of the labels, the storage space is small, the searching speed is high, and the file is fast to load to a software interface after being found.
Meanwhile, medical image data arranged based on DICOM standard can well realize privacy protection. The image files are organized according to the DICOM standard, so that accurate, rapid and unified desensitization encryption is facilitated. The DICOM standard specifies which fields are related to individuals, such as a candidate Name, address, telephone, etc., other suspected fields such as Other candidate IDs, etc., can be deleted directly (i.e., desensitized), and candidate IDs can be encrypted if they need to be reserved; in addition, the folder names of DICOM files derived from PACS may also contain sensitive information (such as names, etc.), and according to DICOM standard, patient folders, examination folders, sequence folders, and individual slices are processed sequentially, and then the file storage route is followed to clean up the files containing privacy and even rename the folders and image files, such as naming the patient folders with encrypted IDs, naming the examination folders and sequence folders with examination UID (unique ID, randomly generated character string of the imaging device); the slice is a DICOM image file of the most basic layer, and the common suffix is · dcm, but the suffix is not limited to · dcm; however, since the slices in a sequence are numbered (this number is a metadata item in the DICOM video file), the naming of slice files may be forced to be named by number and the suffix specification to be dcm (non-dcm slice files may be forced to be converted to dcm files). The DICOM file contains metadata and pixel data, and the metadata contains the sensitive fields, imaging parameter digital segments and the like.
S2, deleting the metadata related to privacy in the medical image file.
S3, extracting pixel data in the medical image file to perform multi-sequence comparison; and extracting pixel data in the medical image file by taking the sequence folder as a unit for display, and allowing each sequence to independently adjust the contrast so as to carry out multi-sequence comparison.
In some embodiments of the present invention, the focus may be observed to determine the boundary of the region of interest by combining the imaging advantages of each sequence, for example, the FLAIR and T2 weighted two sequences in MR each have drawbacks, and the two sequences may be observed in adjacent windows, which helps to quickly and accurately find the boundary of the region of interest, and the label is marked in one of the sequence windows, which greatly improves the doctor's observation effect and efficiency. Pixel data in a plurality of sequences of medical image files in a single examination are extracted and processed/converted into images (visualized in sequence) so that multiple sequence collation, patient folder, examination folder, sequence folder, individual slices, can be performed, all organized/organized based on DICOM standards.
And S4, performing target labeling on pixel data in the medical image file based on a preset target labeling model.
Further, the method comprises the steps of: and sequentially extracting pixel data in each sequence in the medical image file based on a preset target labeling model, and labeling the target on the corresponding pixel data.
According to the invention, medical image data are reasonably arranged by combining with the DICOM standard to form a medical image file with a hierarchical structure, so that standardized management is carried out on patient image data, the subsequent processing of privacy data is facilitated, the sequential comparison and labeling are carried out only on the image data in the medical image file, the safety of data labeling is ensured, and the leakage of privacy data of users is avoided; meanwhile, the invention performs the comparison of the multi-sequence medical image data, and a plurality of sequences are placed in adjacent windows for observation, thereby being beneficial to quickly and accurately finding out the boundary of the region of interest, performing comprehensive and accurate data comparison and improving the accuracy of the subsequent target labeling.
Based on the first aspect, the medical image multi-sequence contrast labeling method based on the DICOM standard further comprises the following steps:
constructing an initial annotation model based on the SAM model and the transfer learning;
and acquiring and carrying out knowledge energization according to the medical image data, and carrying out optimization training on the initial annotation model to construct a target annotation model.
In order to further improve the target labeling efficiency in the medical image data, the SAM is combined and a migration learning method is adopted for modeling, the medical image data is used for enabling the knowledge of clinical experts, and the weak supervision type medical image data labeling is realized. The accurate labeling of the target area can be realized in an auxiliary way through a boundary box of the target area and even a pixel point.
In some embodiments of the present invention, automatic target labeling may be performed based on a target labeling model, and target labeling may also be performed manually on the compared images.
Referring to fig. 2, in a second aspect, an embodiment of the present invention provides a medical image multi-sequence contrast labeling system based on DICOM standard, which includes an image data arrangement module 100, a privacy data processing module 200, a multi-sequence contrast module 300, and a target labeling module 400, wherein:
the image data arrangement module 100 is configured to obtain medical image data, and perform arrangement management on the medical image data according to a DICOM standard to obtain a corresponding medical image file, where the medical image file includes metadata and pixel data, and the metadata includes a privacy sensitive field and an imaging parameter field;
the privacy data processing module 200 deletes the metadata related to privacy in the medical image file;
the multi-sequence comparison module 300 is used for extracting pixel data in the medical image file to perform multi-sequence comparison; and extracting pixel data in the medical image file by taking the sequence folder as a unit for display, and independently adjusting the contrast of each sequence to perform multi-sequence comparison.
The target labeling module 400 is configured to perform target labeling on pixel data in the medical image file based on a preset target labeling model.
The system reasonably arranges medical image data by combining DICOM standards through the cooperation of a plurality of modules such as the image data arranging module 100, the privacy data processing module 200, the multi-sequence comparison module 300 and the target labeling module 400, so as to form a medical image file with a hierarchical structure, thereby facilitating the subsequent differentiated management of image data and privacy data, and only performing sequence comparison and labeling on the image data in the medical image file, ensuring the security of data labeling and avoiding the leakage of private data of users; meanwhile, the invention performs the comparison of the multi-sequence medical image data, and a plurality of sequences are placed in adjacent windows for observation, thereby being beneficial to quickly and accurately finding out the boundary of the interested region, being better convenient for medical staff to check the condition of the related patient, and performing comprehensive and accurate data comparison and subsequent target labeling.
The invention can help medical staff to realize efficient data comparison and target labeling, and better check the condition of patients. After the system is started, a user can only select a DICOM file button, select a folder which needs to be opened and is filled with the DICOM file after clicking the DICOM file button, load and display the DICOM file on an interface after clicking the DICOM file button, and at the moment, the buttons on the menu bar can be clicked. When a button in the left tree area is selected and clicked (in the basic unit of sequence), a DICOM file of the sequence stored in the button is displayed in the area where the image is displayed on the right side. The user can set the window level and window width, so that the image in the area for displaying the image can be correspondingly changed; the multi-screen window display can be performed, the image in the image area can be enlarged and reduced, the image in the image area can be displayed in a moving mode according to requirements, the whole sequence can be dynamically turned over, and linkage can be maintained among the sequences. For the images in the image area, the corresponding marked files can be checked, the images can be marked and stored, and the marked images can be subjected to operations such as marking and erasing.
As shown in fig. 3, in a third aspect, an embodiment of the present application provides an electronic device, which includes a memory 101 for storing one or more programs; a processor 102. The method of any of the first aspects described above is implemented when one or more programs are executed by the processor 102.
And a communication interface 103, where the memory 101, the processor 102 and the communication interface 103 are electrically connected directly or indirectly to each other to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 101 may be used to store software programs and modules that are stored within the memory 101 for execution by the processor 102 to perform various functional applications and data processing. The communication interface 103 may be used for communication of signaling or data with other node devices.
The Memory 101 may be, but is not limited to, a random access Memory (Random Access Memory, RAM), a Read Only Memory (ROM), a programmable Read Only Memory (Programmable Read-Only Memory, PROM), an erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), an electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
The processor 102 may be an integrated circuit chip with signal processing capabilities. The processor 102 may be a general purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
In the embodiments provided in the present application, it should be understood that the disclosed method and system may be implemented in other manners. The above-described method and system embodiments are merely illustrative, for example, flow charts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program which, when executed by the processor 102, implements a method as in any of the first aspects described above. The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (7)
1. A medical image multi-sequence contrast labeling method based on DICOM standard is characterized by comprising the following steps:
acquiring medical image data, and performing arrangement management on the medical image data according to a DICOM standard to obtain a corresponding medical image file, wherein the medical image file comprises metadata and pixel data;
deleting the metadata related to privacy in the medical image file;
extracting pixel data in a medical image file for multi-sequence comparison;
and performing target labeling on pixel data in the medical image file based on a preset target labeling model.
2. The method for multi-sequence contrast labeling of medical images based on DICOM standard according to claim 1, wherein the method for labeling targets on pixel data in medical image files based on a preset target labeling model comprises the following steps:
and sequentially extracting pixel data in each sequence in the medical image file based on a preset target labeling model, and labeling the target on the corresponding pixel data.
3. The method for marking multiple sequences of medical images according to claim 1, wherein the method for managing the arrangement of medical image data according to the DICOM standard comprises the steps of:
according to the DICOM standard, medical image data are sequentially organized into a patient folder, an examination folder, a sequence folder and a slice file according to a hierarchy, so that a final medical image file is obtained.
4. The method for multi-sequence contrast labeling of medical images based on DICOM standard of claim 1, further comprising the steps of:
constructing an initial annotation model based on the SAM model and the transfer learning;
and acquiring and carrying out knowledge energization according to the medical image data, and carrying out optimization training on the initial annotation model to construct a target annotation model.
5. The medical image multi-sequence contrast labeling system based on the DICOM standard is characterized by comprising an image data arrangement module, a privacy data processing module, a multi-sequence contrast module and a target labeling module, wherein:
the image data arrangement module is used for acquiring medical image data, and carrying out arrangement management on the medical image data according to a DICOM standard to obtain a corresponding medical image file, wherein the medical image file comprises metadata and pixel data, and the metadata comprises privacy sensitive fields, imaging parameter fields and other auxiliary fields;
the privacy data processing module is used for deleting the metadata related to privacy in the medical image file;
the multi-sequence comparison module is used for extracting pixel data in the medical image file to carry out multi-sequence comparison;
the target labeling module is used for labeling the target on the pixel data in the medical image file based on a preset target labeling model.
6. An electronic device, comprising:
a memory for storing one or more programs;
a processor;
the method of any of claims 1-4 is implemented when the one or more programs are executed by the processor.
7. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311175951.8A CN117316396A (en) | 2023-09-13 | 2023-09-13 | Medical image multi-sequence contrast labeling method and system based on DICOM standard |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311175951.8A CN117316396A (en) | 2023-09-13 | 2023-09-13 | Medical image multi-sequence contrast labeling method and system based on DICOM standard |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117316396A true CN117316396A (en) | 2023-12-29 |
Family
ID=89241688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311175951.8A Pending CN117316396A (en) | 2023-09-13 | 2023-09-13 | Medical image multi-sequence contrast labeling method and system based on DICOM standard |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117316396A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109686423A (en) * | 2018-11-06 | 2019-04-26 | 众安信息技术服务有限公司 | A kind of medical imaging mask method and system |
| CN110993064A (en) * | 2019-11-05 | 2020-04-10 | 北京邮电大学 | Deep learning-oriented medical image labeling method and device |
| CN112509115A (en) * | 2020-11-26 | 2021-03-16 | 中国人民解放军战略支援部队信息工程大学 | Three-dimensional time-varying unconstrained reconstruction method and system for dynamic scene of sequence image |
| CN113628297A (en) * | 2021-08-06 | 2021-11-09 | 青岛市妇女儿童医院 | COVID-19 deep learning diagnosis system based on attention mechanism and transfer learning |
| CN113627518A (en) * | 2021-08-07 | 2021-11-09 | 福州大学 | Method for realizing multichannel convolution-recurrent neural network electroencephalogram emotion recognition model by utilizing transfer learning |
| CN114242210A (en) * | 2021-12-01 | 2022-03-25 | 沈阳东软智能医疗科技研究院有限公司 | Medical image data management method, device, equipment and storage medium |
| CN115713805A (en) * | 2022-11-01 | 2023-02-24 | 方龙辉 | Body-building action recognition monitoring method and system |
-
2023
- 2023-09-13 CN CN202311175951.8A patent/CN117316396A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109686423A (en) * | 2018-11-06 | 2019-04-26 | 众安信息技术服务有限公司 | A kind of medical imaging mask method and system |
| CN110993064A (en) * | 2019-11-05 | 2020-04-10 | 北京邮电大学 | Deep learning-oriented medical image labeling method and device |
| CN112509115A (en) * | 2020-11-26 | 2021-03-16 | 中国人民解放军战略支援部队信息工程大学 | Three-dimensional time-varying unconstrained reconstruction method and system for dynamic scene of sequence image |
| CN113628297A (en) * | 2021-08-06 | 2021-11-09 | 青岛市妇女儿童医院 | COVID-19 deep learning diagnosis system based on attention mechanism and transfer learning |
| CN113627518A (en) * | 2021-08-07 | 2021-11-09 | 福州大学 | Method for realizing multichannel convolution-recurrent neural network electroencephalogram emotion recognition model by utilizing transfer learning |
| CN114242210A (en) * | 2021-12-01 | 2022-03-25 | 沈阳东软智能医疗科技研究院有限公司 | Medical image data management method, device, equipment and storage medium |
| CN115713805A (en) * | 2022-11-01 | 2023-02-24 | 方龙辉 | Body-building action recognition monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rotemberg et al. | A patient-centric dataset of images and metadata for identifying melanomas using clinical context | |
| RU2543563C2 (en) | Systems and methods for clinical decision support | |
| US8369585B2 (en) | Automatic classification of information in images | |
| US20060155577A1 (en) | System and method for anatomically based processing of medical imaging information | |
| CN111161822A (en) | Medical image artificial intelligence diagnosis data management system and management method thereof | |
| US20050038678A1 (en) | Method and system for intelligent qualitative and quantitative analysis for medical diagnosis | |
| RU2711305C2 (en) | Binding report/image | |
| US11194853B2 (en) | Rapid cross-validated ground truth annotation of large image datasets for image analytics | |
| JP6885896B2 (en) | Automatic layout device and automatic layout method and automatic layout program | |
| US10977796B2 (en) | Platform for evaluating medical information and method for using the same | |
| US20230088543A1 (en) | Systems and methods for dynamic data processing and graphical user interface processing | |
| JP2017513590A (en) | Method and system for visualization of patient history | |
| US20060072797A1 (en) | Method and system for structuring dynamic data | |
| US20140204242A1 (en) | Exam review facilitated by clinical findings management with anatomical tagging | |
| Jha et al. | Information and artificial intelligence | |
| JP7080304B2 (en) | Learning support device, learning support method, learning support program, region of interest discrimination device, region of interest discrimination method, region of interest discrimination program and trained model | |
| US20040015372A1 (en) | Method and system for processing and aggregating medical information for comparative and statistical analysis | |
| JP2022058397A (en) | Medical image processing device, medical image processing method and medical image processing program | |
| Depeursinge et al. | Suppl 1: prototypes for content-based image retrieval in clinical practice | |
| JP6845071B2 (en) | Automatic layout device and automatic layout method and automatic layout program | |
| Roth et al. | Multispecialty enterprise imaging workgroup consensus on interactive multimedia reporting current state and road to the future: HIMSS-SIIM collaborative white paper | |
| US11094062B2 (en) | Auto comparison layout based on image similarity | |
| CN117316396A (en) | Medical image multi-sequence contrast labeling method and system based on DICOM standard | |
| Müller et al. | D9. 1: Report on image use behaviour and requirements | |
| US10741283B2 (en) | Atlas based prior relevancy and relevancy model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |