Medical image lesion fuzzy positioning method, system, device and storage medium
By analyzing lesion data from previous imaging reports and using three-dimensional spatial location matching technology, the location of lesions is automatically identified in new images, solving the problem of multiple manual reviews in imaging examinations and improving efficiency and accuracy.
Patent Information
- Application Number
- CN202111014743.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-08-31
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2041-08-31
AI Technical Summary
In existing technologies, imaging examinations for progressive diseases require multiple manual reviews of previous imaging reports, lacking precise and proactive prompts, resulting in low efficiency and a high possibility of missed diagnoses.
By acquiring the user's medical imaging information, analyzing previous report data, calculating thin-layer images of the area near the lesion, and identifying the possible location of the lesion in the new image, the system automatically records and displays lesion information using three-dimensional spatial location matching and threshold calculation.
It enables proactive indication of lesion location during a single imaging examination, improving efficiency, reducing the possibility of missed lesions, simplifying operation steps, and is easy to design without affecting the original imaging system workflow.
Smart Images

Figure CN113724820B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical image processing, and in particular to a method, system, device and storage medium for fuzzy positioning of medical image lesions. Background Art
[0002] With the continuous innovation and development of the examination design of medical imaging equipment, the role of imaging examinations in clinical diseases has become increasingly important. The mathematization of medical images has become an indispensable and important part in modern medicine, providing important imaging diagnostic information for clinical diagnosis.
[0003] Generally speaking, imaging diagnosis is independent and a single imaging diagnosis issues an independent report. However, for progressive diseases, multiple imaging examinations are often required at different times to observe the progression of the disease. The examination methods include but are not limited to DR, CT, and MRI. The reference medical history is often a qualitative description of the imaging report, which generally needs to be manually reviewed and lacks precise, active and clear prompts. Summary of the invention
[0004] The present invention provides a method, system, device and storage medium for fuzzy positioning of medical image lesions. The method simplifies the manual review of previous reports and the manual comparison of previous images according to the report contents. When diagnosing new images, the possible lesion locations are actively indicated based on previous examinations and marked on the image.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions:
[0006] A method for fuzzy positioning of medical image lesions comprises the following steps:
[0007] Obtain the user's medical imaging information, and extract the examination method and part of the medical imaging information;
[0008] Search the archived user report data for historical report data with the same inspection method and location as the user;
[0009] According to the physical location of the lesion information in the historical report data, a number of image thin-layer images contained in a specified range near the same lesion are calculated in the medical image information;
[0010] Identify and display image slices in the calculation results.
[0011] As a further improvement of the present invention, the step of obtaining the user's medical imaging information further includes recording the lesion location information; the step of recording the lesion location information specifically includes:
[0012] Record the user's image reading results and submit them;
[0013] Automatically record lesion sequence information, spatial orientation and labels in the report;
[0014] Data archiving of lesion sequence information, spatial location and labels in the record report.
[0015] As a further improvement of the present invention, the recording of the user's image reading results specifically includes:
[0016] When issuing a user report, the lesion values measured by the user will be screened and recorded;
[0017] The lesion value is associated with the user information and medical imaging information.
[0018] As a further improvement of the present invention, after recording the lesion location information, the method further includes saving and managing the recorded information; saving and managing the recorded information specifically includes:
[0019] The recorded information is saved and managed in a storage medium, which includes a local storage space and a network server storage space.
[0020] As a further improvement of the present invention, the method of calculating a plurality of image thin-layer images contained in a specified range near the same lesion in the medical image information according to the physical location of the lesion information in the historical report data specifically includes:
[0021] According to the physical location of the lesion information in the historical report data, one or more examination sequences with the same examination site are matched, and the three-dimensional spatial locations of all lesions in these sequences are extracted; according to the set threshold, the three-dimensional coordinate group of the space cube of all lesions within the threshold range is calculated in sequence, which is recorded as the first cube;
[0022] In the current medical image information inspection sequence, sequentially search for inspection sequences of the same type as the above-mentioned lesions, and calculate the three-dimensional coordinate group of the space cube of the current medical image information inspection sequence, which is recorded as the second cube;
[0023] Calculate the intersecting spatial area of the first cube and the second cube; project the intersecting spatial area to a two-dimensional image thin layer image in the current medical image information inspection sequence, and record it.
[0024] As a further improvement of the present invention, the image thin layer image in the identification calculation result is specifically:
[0025] All recorded areas are marked in the current image thin layer to obtain the area where the lesion may appear.
[0026] A medical image lesion fuzzy positioning system, comprising:
[0027] An acquisition module is used to acquire the user's medical imaging information and extract the examination method and part of the medical imaging information;
[0028] A search module is used to search for historical report data of the same user with the same inspection method and part in the archived user report data;
[0029] A calculation module, for calculating a number of image thin-layer images contained in a specified range near the same lesion in the medical image information according to the physical location of the lesion information in the historical report data;
[0030] The identification module is used to identify and display the image thin layer images in the calculation results.
[0031] As a further improvement of the present invention, the calculation module is specifically used for:
[0032] According to the physical location of the lesion information in the historical report data, one or more examination sequences with the same examination site are matched, and the three-dimensional spatial locations of all lesions in these sequences are extracted; according to the set threshold, the three-dimensional coordinate group of the space cube of all lesions within the threshold range is calculated in sequence, which is recorded as the first cube;
[0033] In the current medical image information inspection sequence, sequentially search for inspection sequences of the same type as the above-mentioned lesions, and calculate the three-dimensional coordinate group of the space cube of the current medical image information inspection sequence, which is recorded as the second cube;
[0034] Calculate the intersecting spatial area of the first cube and the second cube; map the intersecting spatial area to a two-dimensional image thin layer image in the medical imaging information inspection sequence of the current user, and record it.
[0035] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the medical image lesion fuzzy positioning method when executing the computer program.
[0036] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the medical image lesion fuzzy positioning method.
[0037] The beneficial effects of the present invention are embodied in:
[0038] The present invention is based on accurate electronic information description, analyzes and records the lesion data in previous imaging reports, and infers and marks the possible lesion locations in new imaging examinations based on the spatial positions of the previous data of the same user. The present invention provides a method with low design difficulty that can quickly fuzzy match and locate lesions based on previous report data. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] Figure 1 This is a flow chart of the method for fuzzy localization of lesions in medical images;
[0040] Figure 2 This is a flow chart of medical imaging lesion recording in the present invention;
[0041] Figure 3 This is a flowchart of the fuzzy marking of medical images according to the present invention;
[0042] Figure 4 This is a schematic diagram of the structure of a medical image lesion fuzzy positioning system according to a preferred embodiment of the present invention;
[0043] Figure 5 It is a schematic diagram of the structure of an electronic device according to a preferred embodiment of the present invention. DETAILED DESCRIPTION
[0044] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.
[0045] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present application belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention.
[0046] like Figure 1 As shown, the present invention provides a method for fuzzy positioning of medical image lesions, comprising the following steps:
[0047] Obtain the user's medical imaging information, and extract the examination method and part of the medical imaging information;
[0048] Search the archived user report data for historical report data with the same inspection method and location as the user;
[0049] According to the physical location of the lesion information in the historical report data, a plurality of image thin-layer images contained in a specified range near the same lesion are calculated in the medical image information of the user;
[0050] Identify and display image slices in the calculation results.
[0051] The present invention is based on accurate electronic description of information, analyzes and records the lesion data in previous imaging reports, and infers and marks the possible lesion locations in new imaging examinations through the spatial positions of the previous data of the same user.
[0052] As a preferred embodiment, the step of obtaining the user's medical imaging information further includes recording the lesion location information; the step of recording the lesion location information specifically includes:
[0053] Record the user's image reading results and submit them;
[0054] Automatically record lesion sequence information, spatial orientation and labels in the report;
[0055] Data archiving of lesion sequence information, spatial location and labels in the record report.
[0056] The recording of the user's image reading results specifically includes:
[0057] When issuing a user report, the lesion values measured by the user will be screened and recorded;
[0058] The lesion value is associated with the user information and medical imaging information.
[0059] As a preferred embodiment, after recording the lesion location information, the method further includes saving and managing the recorded information; saving and managing the recorded information specifically includes:
[0060] The recorded information is saved and managed in a storage medium, which includes a local storage space and a network server storage space.
[0061] As a preferred embodiment, the method of calculating a plurality of image thin-layer images within a specified range near the same lesion in the medical image information according to the physical location of the lesion information in the historical report data specifically includes:
[0062] According to the physical location of the lesion information in the historical report data, one or more examination sequences with the same examination site are matched, and the three-dimensional spatial locations of all lesions in these sequences are extracted; according to the set threshold, the three-dimensional coordinate group of the space cube of all lesions within the threshold range is calculated in sequence, which is recorded as the first cube A;
[0063] In the examination sequence of the medical imaging information of the current user, the examination sequences of the same type as the above lesions are searched in turn, and the three-dimensional coordinate group of the space cube of the examination sequence of the medical imaging information of the current user is calculated, which is recorded as the second cube B;
[0064] Calculate the intersecting spatial area of the first cube A and the second cube B; map the intersecting spatial area to a two-dimensional image thin layer image in the medical imaging information inspection sequence of the current user, and record it.
[0065] The method of the present invention is described in detail below with reference to specific embodiments.
[0066] The method for fuzzy localization of medical image lesions described in the present invention has the following specific process:
[0067] Step 1, recording the location information of the lesion;
[0068] When issuing a report, the values measured by the user will be screened and recorded, including but not limited to the long and short axes, CT value (maximum, minimum, mean square error, digital mean), Cobb angle, SUV value, lesion area, cardiothoracic ratio, etc.
[0069] The measured values are associated with user information and medical image information. The user information includes but is not limited to name, ID, examination number, etc. The medical image information includes but is not limited to examination part, examination method, examination ID (StudyUID), sequence ID (SeriesInstanceUID), image position spatial coordinates (ImagePosition), etc.
[0070] Specific steps are as follows Figure 2 As shown, the following steps are included:
[0071] 1) Start;
[0072] 2) Record the image reading results and submit them;
[0073] 3) Automatically record the lesion sequence information, spatial location, labels, etc. in the report;
[0074] 4) Archive data;
[0075] 5) End.
[0076] Step 2, save and manage the recorded information;
[0077] The above records are saved in a storage medium, which includes but is not limited to local storage space and network server storage space, for index search.
[0078] Step 4, matching information;
[0079] like Figure 3 As shown, the specific steps are:
[0080] 1) Start reading the film
[0081] 2) Read user information, check method and location;
[0082] 3) Search the archived data for past reports of the same inspection method and part as the user;
[0083] 4) According to the physical location of the lesion information in the previous records, a number of image thin-layer images contained in a specified range near the lesion are calculated in the image;
[0084] 5) Identify the image thin layer images in the calculation results.
[0085] 6) End.
[0086] The specific process is as follows: when opening a new image, first check in the record whether the user has an examination record, match one or more examination sequences with the same examination part, and extract the three-dimensional spatial positions of all lesions in these sequences.
[0087] According to a set threshold (the threshold is set by the user), the three-dimensional coordinate groups of the space cubes of all the above lesions within the range of the threshold are calculated in sequence, which are recorded as the first cube A.
[0088] In the current examination sequence, the examination sequences of the same type as the above lesions are searched in turn, and the three-dimensional coordinate group of the space cube of the sequence in the current examination is calculated, which is recorded as the second cube B.
[0089] Calculate the spatial area where the first cube A and the second cube B intersect.
[0090] The above-mentioned spatial area is projected onto the two-dimensional image thin layer image in the current inspection sequence, and the result may include part or all of one or more image images and be recorded.
[0091] Step 5: Locate the blurred position of the lesion.
[0092] All recorded areas described in the previous step are marked in the current thin-layer image, that is, areas where lesions may appear, to provide diagnostic reference. The present invention is based on accurate electronic information description, analyzes and records lesion data in previous imaging reports, and calculates and marks the possible lesion locations in new imaging examinations based on the spatial positions of the same user's previous data. The specific advantages are:
[0093] First: Active identification;
[0094] An imaging examination contains a large number of thin-layer images. Actively indicating the possible location of lesions can improve efficiency and reduce the possibility of missed detection, which is of practical significance for comparing the progression of progressive diseases.
[0095] Second: The steps are simple;
[0096] The present invention does not require any additional operation steps for the user.
[0097] Third: The design difficulty is small.
[0098] The spatial computing and imaging systems designed by the present invention have low correlation, low difficulty in design and deployment, small changes to the original imaging system logic layer, and no impact on the imaging system process.
[0099] like Figure 4 As shown, another object of the present invention is to provide a medical image lesion fuzzy positioning system, comprising:
[0100] An acquisition module is used to acquire the user's medical imaging information and extract the examination method and part of the medical imaging information;
[0101] A search module is used to search for historical report data of the same user with the same inspection method and part in the archived user report data;
[0102] A calculation module, for calculating a number of image thin-layer images contained in a specified range near the same lesion in the user's medical image information according to the physical location of the lesion information in the historical report data;
[0103] The identification module is used to identify and display the image thin layer images in the calculation results.
[0104] Wherein, the computing module is specifically used for:
[0105] According to the physical location of the lesion information in the historical report data, one or more examination sequences with the same examination site are matched, and the three-dimensional spatial locations of all lesions in these sequences are extracted; according to the set threshold, the three-dimensional coordinate group of the space cube of all lesions within the threshold range is calculated in sequence, which is recorded as the first cube A;
[0106] In the current medical image information inspection sequence, sequentially search for inspection sequences of the same type as the above-mentioned lesions, and calculate the three-dimensional coordinate group of the space cube of the current medical image information inspection sequence, which is recorded as the second cube B;
[0107] Calculate the intersecting spatial area of the first cube A and the second cube B; project the intersecting spatial area to a two-dimensional image thin layer image in the current medical image information inspection sequence, and record it.
[0108] like Figure 5 As shown, the third object of the present invention is to provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the medical image lesion fuzzy localization method when executing the computer program.
[0109] The medical image lesion fuzzy positioning method comprises the following steps:
[0110] Obtain the user's medical imaging information, and extract the examination method and part of the medical imaging information;
[0111] Search the archived user report data for historical report data with the same inspection method and location as the user;
[0112] According to the physical location of the lesion information in the historical report data, a number of image thin-layer images contained in a specified range near the same lesion are calculated in the medical image information;
[0113] Identify and display image slices in the calculation results.
[0114] The fourth object of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the medical image lesion fuzzy positioning method are implemented.
[0115] The medical image lesion fuzzy positioning method comprises the following steps:
[0116] Obtain the user's medical imaging information, and extract the examination method and part of the medical imaging information;
[0117] Search the archived user report data for historical report data with the same inspection method and location as the user;
[0118] According to the physical location of the lesion information in the historical report data, a number of image thin-layer images contained in a specified range near the same lesion are calculated in the medical image information;
[0119] Identify and display image slices in the calculation results.
[0120] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0121] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0122] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A method for fuzzy localization of medical image lesions, characterized in that: The following steps are involved: Obtain the user's medical imaging information, and extract the examination method and part of the medical imaging information; Search the archived user report data for historical report data with the same inspection method and location as the user; According to the physical location of the lesion information in the historical report data, a number of image thin-layer images contained in a specified range near the same lesion are calculated in the medical image information; Identify and display thin-layer images in the calculation results; The step of obtaining the user's medical imaging information also includes recording the lesion location information; the step of recording the lesion location information specifically includes: Record the user's image reading results and submit them; Automatically record lesion sequence information, spatial orientation and labels in the report; Archive the data of lesion sequence information, spatial location and labels in the record report; After recording the lesion location information, the method further includes saving and managing the recorded information; saving and managing the recorded information specifically includes: The recorded information is saved in a storage medium, wherein the storage medium includes a local storage space and a network server storage space; The method of calculating a plurality of image thin-layer images within a specified range near the same lesion in the medical image information according to the physical location of the lesion information in the historical report data specifically includes: According to the physical location of the lesion information in the historical report data, one or more examination sequences with the same examination site are matched, and the three-dimensional spatial locations of all lesions in these sequences are extracted; according to the set threshold, the three-dimensional coordinate group of the space cube of all lesions within the threshold range is calculated in sequence, which is recorded as the first cube; In the current medical image information inspection sequence, sequentially search for inspection sequences of the same type as the above-mentioned lesions, and calculate the three-dimensional coordinate group of the space cube of the current medical image information inspection sequence, which is recorded as the second cube; Calculate the intersecting spatial area of the first cube and the second cube; project the intersecting spatial area to a two-dimensional image thin layer image in the current medical image information inspection sequence, and record it.
2. The method according to claim 1, characterized in that: The recording of the user's image reading results specifically includes: When issuing a user report, the lesion values measured by the user will be screened and recorded; The lesion value is associated with the user information and medical imaging information.
3. The method according to claim 1, characterized in that The image thin layer image in the identification calculation result is specifically: All recorded areas are marked in the current image thin layer to obtain the area where the lesion may appear.
4. A medical image lesion fuzzy positioning system, characterized in that: include: An acquisition module is used to acquire the user's medical imaging information and extract the examination method and part of the medical imaging information; A search module is used to search for historical report data of the same user with the same inspection method and part in the archived user report data; A calculation module, for calculating a number of image thin-layer images contained in a specified range near the same lesion in the medical image information according to the physical location of the lesion information in the historical report data; An identification module is used to identify and display thin-layer images in the calculation results; The step of obtaining the user's medical imaging information also includes recording the lesion location information; the step of recording the lesion location information specifically includes: Record the user's image reading results and submit them; Automatically record lesion sequence information, spatial orientation and labels in the report; Archive the data of lesion sequence information, spatial location and labels in the record report; After recording the lesion location information, the method further includes saving and managing the recorded information; saving and managing the recorded information specifically includes: The recorded information is saved in a storage medium, wherein the storage medium includes a local storage space and a network server storage space; The computing module is specifically used for: According to the physical location of the lesion information in the historical report data, one or more examination sequences with the same examination site are matched, and the three-dimensional spatial locations of all lesions in these sequences are extracted; according to the set threshold, the three-dimensional coordinate group of the space cube of all lesions within the threshold range is calculated in sequence, which is recorded as the first cube; In the current medical image information inspection sequence, sequentially search for inspection sequences of the same type as the above-mentioned lesions, and calculate the three-dimensional coordinate group of the space cube of the current medical image information inspection sequence, which is recorded as the second cube; Calculate the intersecting spatial area of the first cube and the second cube; map the intersecting spatial area to a two-dimensional image thin layer image in the medical imaging information inspection sequence of the current user, and record it.
5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the medical image lesion fuzzy localization method according to any one of claims 1 to 3 when executing the computer program.
6. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the medical image lesion fuzzy localization method according to any one of claims 1 to 3.
