A digital image analysis method and system in medical informationization

Abstract

The present invention relates to a digital image analysis method and system in medical informationization, the method comprising: an intelligent terminal acquires digital images in real time, and acquires local analysis results of digital images by setting up a local analysis database in the intelligent terminal; an intelligent server acquires archived digital image information from each intelligent terminal, obtains an updated analysis database based on the archived digital image information, and updates the local analysis database of the intelligent terminal based on the updated analysis database. The present invention utilizes the intelligent analysis results of the cloud server by regularly downloading the analysis database, so that the local terminal with limited resources can make full use of image information resources and promote the development of medical informationization.

Description

Technical Field

[0001] The present invention belongs to the field of smart medical technology, and in particular relates to a digital image analysis method and system in medical informationization. Background Art

[0002] With the continuous advancement of science and technology, the service methods of various industries are also undergoing earth-shaking changes. More and more intelligent devices are replacing manual services to provide people with more efficient and convenient intelligent services, and the medical field has always been a part of it that has attracted much attention.

[0003] Medical informatization maintains a high-speed construction with an annual growth rate of 20%. The rapid development of medical informatization has promoted the popularization of indoor health monitoring networks. In hospitals, a large amount of medical data is generated every day. These medical data usually include basic information of patients, imaging data generated by various medical equipment applied to patients, and diagnosis results made by doctors based on imaging data.

[0004] With the popularization of IoT terminal devices in the medical field, various wearable body sensors and medical devices are used in medical services. These IoT terminal devices can collect a large amount of medical data and upload it to remote cloud servers through the network for data processing and analysis, providing patients with accurate and fast medical services. In particular, with the rapid development of artificial intelligence technology, remote cloud servers can use artificial intelligence technology when processing and analyzing data, and carry out in-depth processing of data with the support of computing power and storage capacity.

[0005] Under the above three backgrounds, the development of computer technology has provided more and more support for medical assistance operations. The medical examination process performed on patients usually involves complex real-time operations and judgments, which requires the timeliness and real-time nature of medical information. It is even more necessary to provide real-time support for medical informatization, but the current medical informatization system in my country still faces many problems. Since medical data may not be uploaded in time, the uploading and downloading of data are restricted by the network, which creates obstacles to the real-time processing of medical data. In addition, since the data used for calculation is stored on the cloud server, when the amount of medical data is large and it is increasing, it also puts a lot of pressure on the storage space of the cloud server. In addition, artificial intelligence models are flourishing, but the specific applicability is difficult to say, and the efficiency of data processing using AI models is currently very low, which makes it difficult to meet the real-time and urgent needs of hospitals for medical data.

[0006] Therefore, how to make full use of the intelligent analysis results of the cloud server when local terminal resources are limited, analyze digital images through its own limited processing capabilities, and ultimately promote the development of medical informatization is a technical problem to be solved.

[0007] Based on the above problems, the present invention utilizes the intelligent analysis results of the cloud server by regularly downloading the analysis database, so that the local terminal with limited resources can fully utilize the image information resources and promote the development of medical informationization. Summary of the invention

[0008] In order to solve the above problems in the prior art, the present invention proposes a digital image analysis method and system in medical informationization, the method comprising:

[0009] Step S1: the smart terminal acquires the digital image in real time, and acquires the local analysis result of the digital image by setting up a local analysis database in the smart terminal; the local analysis result is applied to the digital image information in real time and presented on the smart terminal;

[0010] The step S1 specifically includes the following steps:

[0011] Step S11: the intelligent terminal acquires a digital image in real time, performs edge detection on the image data using multiple edge detection methods, and merges the edge detection results to obtain an edge area;

[0012] Step S12: performing binarization processing on the edge region based on a specific direction; specifically, by comparing the grayscale values ​​of any pixel in the edge region with the adjacent pixel in the specific direction to obtain a binary comparison value, and filling the binary comparison value into the corresponding pixel position to form a binary region corresponding to the edge region; in the comparison process, if the difference between the grayscale values ​​of the pixel and the adjacent pixel in the specific direction meets the binarization condition, the binary comparison value of the pixel is set to 1, otherwise, it is set to 0;

[0013] Step S13: taking each pixel in the binary area as a target pixel in turn and constructing a sliding window, sliding the window in multiple positions based on the position of the target pixel, and comparing the sliding window content with the local analysis database during the sliding process to obtain a control value; the multi-position sliding is to make the target pixel located at multiple positions in the sliding window, and perform multiple separate comparisons to obtain a control value;

[0014] Step S14: performing edge comparison modification on the target pixel P based on the comparison value, and using the modification result as the local analysis result;

[0015] Step S15: applying the modification result to the digital image information in real time and presenting it on the smart terminal; specifically: updating the grayscale value of the corresponding pixel in the digital image information based on the modification result of the target pixel, and presenting it on the smart terminal;

[0016] Step S2: The intelligent server obtains archived digital image information from each intelligent terminal, obtains an updated analysis database based on the archived digital image information, and updates the local analysis database of the intelligent terminal based on the updated analysis database.

[0017] Furthermore, the binarization condition is a preset condition that can be modified.

[0018] Furthermore, the binarization conditions change as the image analysis program is updated and modified.

[0019] Furthermore, the image data acquired in real time is a medical digital image.

[0020] Furthermore, the image data acquired in real time is medical image data.

[0021] A digital image analysis system in medical informationization includes: an intelligent server and an intelligent terminal; the intelligent server is used to implement the above-mentioned digital image analysis method in medical informationization; the intelligent terminal is used to send a digital image analysis request in medical informationization to the intelligent server.

[0022] Furthermore, the intelligent server is a big data server.

[0023] A digital image analysis platform in medical informationization includes a processor, the processor is coupled to a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the digital image analysis method in medical informationization is implemented.

[0024] A computer-readable storage medium includes a program, which, when executed on a computer, enables the computer to execute the digital image analysis method in medical informationization.

[0025] A big data server is configured to execute the digital image analysis method in medical informationization.

[0026] The beneficial effects of the present invention include:

[0027] (1) By regularly downloading the analysis database, the intelligent analysis results of the cloud server can be utilized, so that the local terminal with limited resources can make full use of the image information resources; by binarizing the edge area based on a specific direction, the gray value effect length is maintained during the analysis of the digital image, thereby avoiding premature loss of information. At the same time, it can also support the conversion of image analysis problems into 0, 1 calculation problems under the constraints of consistency conditions, reducing the complexity of subsequent calculations, making data analysis independent of the specific type of object of interest;

[0028] (2) The sliding window is set to slide around the target pixel based on the specific position. By changing the position of the anchor position in the sliding window, the position of the pixel in the edge is considered, thereby increasing the stability of the analysis result. It is also convenient to convert the comparison of images or matrices into the comparison of two specific data values, supporting the execution of the digital image analysis method in limited resource terminals. Furthermore, the edge analysis results are integrated at different weight levels through quantitative calculation, and the analysis results are refined on the basis of the existing edge analysis results.

[0029] (3) By adjusting the size of the anchor position set, the accuracy of the analysis results is increased in a spiral shape. When the edge detection result obtained by analysis has a high accuracy, a larger anchor position set size can be set. Otherwise, a smaller size can be set. Of course, the increase in size will bring about a greater amount of calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present application, but do not constitute an improper limitation of the present invention. In the drawings:

[0031] Figure 1 This is a schematic diagram of the digital image analysis method in medical informationization provided by the present invention.

[0032] Figure 2 A schematic diagram of adjacent pixels in a specific direction provided by the present invention.

[0033] Figure 3 A schematic diagram of a sliding window based on an anchor position (1,1) provided by the present invention. DETAILED DESCRIPTION

[0034] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the illustrative embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0035] The present invention proposes a digital image analysis method and system in medical informationization, as shown in the attached Figure 1 As shown, the method comprises the following steps:

[0036] Step S1: the smart terminal acquires a digital image in real time, and acquires a local analysis result of the digital image through an image analysis program set locally in the smart terminal; the local analysis result is applied to the digital image information in real time and presented on the smart terminal;

[0037] Preferably: the intelligent terminal sets the image analysis program by downloading from the intelligent server, and obtains the local analysis result through the image analysis program and the digital image acquired in real time; the image analysis program includes an analysis model and an analysis database;

[0038] Preferably: the image data acquired in real time is a medical digital image;

[0039] Preferably: the image data acquired in real time is ultrasonic image data;

[0040] The step S1 specifically includes the following steps:

[0041] Step S11: the intelligent terminal acquires a digital image in real time, performs edge detection on the image data using multiple edge detection methods, and merges the edge detection results to obtain an edge area;

[0042] The step S11 specifically includes the following steps:

[0043] Step S111: using multiple image edge detection methods to perform edge detection analysis on the digital image to obtain multiple edge analysis results; the above edge detection methods are common edge detection methods in the prior art;

[0044] Step S112: combining multiple edge analysis results to obtain an edge region; specifically: taking a corresponding pixel point set formed after combining the edge analysis results as the edge region;

[0045] Preferably: during the merging process of edge analysis results, if there is a connected area whose size is smaller than the preset area size, and the connected area is a closed area surrounded by edge pixels, the connected area is included in the edge area;

[0046] Step S12: performing binarization processing on the edge region based on a specific direction; specifically, by comparing the grayscale values ​​of any pixel in the edge region with the adjacent pixel in the specific direction to obtain a binary comparison value, and filling the binary comparison value into the corresponding pixel position to form a binary region corresponding to the edge region; in the comparison process, if the difference between the grayscale values ​​of the pixel and the adjacent pixel in the specific direction meets the binarization condition, the binary comparison value of the pixel is set to 1, otherwise, it is set to 0;

[0047] Preferably: for the pixels at the boundary, the grayscale values ​​of the pixels can be compared with those of the adjacent pixels in a specific direction in the original image to obtain a binary value, or set to a missing value or 0;

[0048] By performing binarization processing on the edge area based on a specific direction, the image analysis problem is converted into a 0, 1 calculation problem, which reduces the complexity of subsequent calculations and makes the data analysis independent of the specific object type of interest;

[0049] As attached Figure 2As shown, for pixel P1, its neighboring pixels in a specific direction are P2, P3, and P4, wherein the dot exemplifies the direction of the center of the object of interest, and the specific direction is the direction toward the center of the object of interest; Figure 2 The example in the figure shows the case where 8 are adjacent.

[0050] Preferably, the specific direction includes a first direction and a second direction; wherein the first direction is a direction toward the center of the object of interest; the second direction is a direction away from the center of the object of interest; that is, as the specific direction changes, the binary comparison value changes;

[0051] Preferably, the center is a geometric center;

[0052] Preferably, the binarization condition is that there are any adjacent pixels or pixels that satisfy a preset ratio, so that the difference between the gray value of the pixel and the gray value of any adjacent pixel is greater than or equal to the difference threshold;

[0053] Alternatively: the binarization condition is that there are any adjacent pixels or pixels that satisfy a preset ratio, so that the difference between the grayscale value of the pixel and the grayscale value of any adjacent pixel is within a preset difference range; of course, this difference range may include multiple discontinuous value ranges;

[0054] Preferably: the adjacent pixels are 4, 8, 16, or 64 adjacent;

[0055] Step S13: constructing a sliding window based on the sliding window by taking each pixel in the binary area as the target pixel in turn, sliding the window in multiple positions based on the target pixel position, and obtaining a control value based on the comparison between the window content and the local analysis database; the step S13 specifically includes the following steps:

[0056] Step S131: obtaining an unprocessed anchor position set i; the anchor position set includes one or more anchor positions; the anchor position is the position of the target pixel in the sliding window; for example: at position (2,3);

[0057] Preferably: an anchor position set is pre-set; the number and positions of anchor positions contained in the anchor position set are different, and the largest anchor position set contains all sliding window positions;

[0058] Preferably: the larger the value of the anchor position set i is, the more elements there are in it;

[0059] Preferably: the anchor position set and the anchor position in each anchor position set are one or more;

[0060] Preferably: the initial value of the anchor position set is set to an anchor position set that only includes the center position of the sliding window as the anchor position; if the sliding window is set to 3*3, then the initial anchor position set only includes one anchor position, which is position (2,2);

[0061] Step S132: obtaining any unprocessed pixel in the edge area as a target pixel;

[0062] Step S133: sequentially setting the target pixel at the anchor position and constructing a sliding window according to the anchor position, so that the target pixel in the sliding window is located at the anchor position of the sliding window, and the sliding window size is N*N; wherein: N is a preset value;

[0063] As attached Figure 3 As shown in the figure, "x" indicates the edge area, and "-" indicates the non-edge area. In the 3*3 sliding window marked with a double-line frame, the example of constructing a sliding window with the anchor position (1,1) is shown, which is the position marked by "P".

[0064] Step S134: Compare the binarized region in the sliding window with the region sample in the analysis database. When the binarized region hits the region sample, obtain the control value corresponding to the region sample, and use the control value as the candidate control value corresponding to the unprocessed anchor position set i of the target pixel. ; where: j is the number of the candidate control value corresponding to the anchor position set i; control value Indicates the probability value of the target pixel in the hit binary area being an edge element;

[0065] The binary region at this time can be regarded as a matrix; so this comparison is a comparison between matrices; and because the matrix contains only 0 and 1 elements, it can actually be converted into a comparison of numerical values ​​or strings;

[0066] Preferably: when the element values ​​and their distribution in the binary region are the same as those in the regional sample, it is determined that the regional sample hits;

[0067] Alternatively: convert the element value in the binary area into two values, convert the area sample into two values, and compare the two values ​​to determine whether they are hit; the conversion method is to read from the element at the (1,1)th position of the binary area to the anchor position, use the read 0, 1 values ​​as the first value, read from the position next to the anchor position to the element at the (N,N)th position, and use the read 0, 1 values ​​as the first value; the reading method is row first and then column; for example: if 011 is read, the corresponding value is 3;

[0068] Preferably: before executing step S1, update the local analysis database of the intelligent terminal in advance; save the regional samples and their corresponding control values ​​in the analysis database; correspondingly, perform periodic analysis on the big data at the intelligent server end; extract the binary region of the big data digital image and its corresponding target pixel position (anchor position), and the probability value (here the determination can be an approved determination, an expert determination, etc.) of the target pixel being determined as an edge pixel when the target pixel position is in the corresponding binary region (at this time, the pixel value of the pixel position is arbitrary and does not need to be matched), and regard the probability value as the control value corresponding to the binary region; cluster the binary region and its corresponding control value to form a regional sample (that is, select a representative binary region and its corresponding control value); obviously, the above-mentioned binary region is the same as in step S134, and a corresponding P position, that is, an anchor position, is set; in fact, the number of anchor positions set can adjust the amount of calculation and storage requirements in the process of digital image analysis;

[0069] Step S135: determine whether all anchor positions in the anchor position set i have been constructed, if yes, proceed to the next step, otherwise, return to step S133;

[0070] Step S136: determine whether there is any unprocessed anchor position set, if yes, set i=i+1 and return to step S131; otherwise, end;

[0071] Preferably: if the number of elements in the anchor position set i is equal to the sliding window size N*N, then there is no unprocessed anchor position set;

[0072] Step S14: Based on the control value The target pixel P is modified by edge comparison; specifically: the gray value of the target pixel P is modified by the following formula (1): Make modifications; among which: is the adjustment coefficient of anchor position set i; is the number of hits of regional samples when processing the anchor position set i; Less than or equal to the number of anchor positions in anchor position set i ;

[0073] (1);

[0074] Preferably, the adjustment coefficient is a preset value, for example: ;

[0075] Alternative: The control value based on The target pixel P is subjected to edge comparison modification; specifically, the edge detection result of the target pixel P is modified by using the following formula (2): Make modifications; among which: is the adjustment coefficient of anchor position set i; is the number of hits of the regional samples in the anchor position set i; Less than or equal to the number of anchor positions in anchor position set i ;

[0076] (2);

[0077] Preferred: Edge detection results The larger the value of is, the more it tends to detect the edge-oriented pixel points, and vice versa, the further away from the edge-oriented pixel points.

[0078] By changing the position of the anchor position in the sliding window, the situation of the pixel position in the edge is considered to increase the stability of the analysis result; it is also convenient to convert the comparison of images or matrices into the comparison of two specific data values, supporting the execution of the digital image analysis method in limited resource terminals;

[0079] By adjusting the size of the anchor position set, the accuracy of the analysis result is increased spirally. When the edge detection result obtained by analysis is highly accurate, a larger anchor position set size can be set. On the contrary, when the sample data result is increasingly accurate, a smaller size can be set. Of course, the increase in size will bring about a greater amount of calculation; a trade-off can be made as needed.

[0080] Step S15: using the modification result as a local analysis result to act on the digital image information in real time and presenting it on the smart terminal; specifically: modifying the grayscale value of the corresponding pixel in the digital image information based on the grayscale value of the target pixel and presenting it on the smart terminal;

[0081] Alternatively: the step S15 specifically includes: based on the modified edge detection result of the target pixel, rendering the image position of the corresponding pixel in the digital image information and presenting it on the smart terminal to highlight the presentation of the edge pixel point;

[0082] Based on the real-time acquired digital image information and the real-time acquired pixel value or edge detection result of the target pixel, it can assist the user of the information-based intelligent terminal;

[0083] Step S2: the intelligent server obtains archived digital image information from each intelligent terminal, obtains an updated analysis database based on the archived digital image information, and updates the local analysis database of the intelligent terminal based on the updated analysis database;

[0084] Preferably: different analysis databases are set for different types of objects of interest;

[0085] Based on the same inventive concept, the present invention also provides a digital image analysis system in medical informationization, the system comprising: an intelligent server and an intelligent terminal; the server is used to implement the above-mentioned digital image analysis method in medical informationization; the intelligent terminal is used to send a digital image analysis request in medical informationization to the intelligent server;

[0086] Preferably: the intelligent server is a big data server; the number of the intelligent server is one or more;

[0087] Preferably: the intelligent terminal is a computing terminal located in the hospital, a mobile terminal located at the patient's side, etc.;

[0088] A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of a programming language, including an assembled or interpreted language, a declarative or procedural language, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple collaborative files (e.g., files storing one or more modules, subroutines, or code portions). A computer program can be deployed to execute on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

[0089] It will be appreciated by those skilled in the art 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. Furthermore, 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.

[0090] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the 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 generate 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 1A device that provides the functions specified in a block or multiple blocks.

[0091] 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 comprising 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.

[0092] 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 A step that specifies a function in one or more boxes.

[0093] 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 digital image analysis method in medical informationization, It is characterized in that The method comprises: Step S1: the smart terminal acquires the digital image in real time, and acquires the local analysis result of the digital image by setting up a local analysis database in the smart terminal; the local analysis result is applied to the digital image information in real time and presented on the smart terminal; The step S1 specifically includes the following steps: Step S11: the intelligent terminal acquires a digital image in real time, performs edge detection on the image data using multiple edge detection methods, and merges the edge detection results to obtain an edge area; Step S12: performing binarization processing on the edge area based on a specific direction; Specifically, a binary comparison value is obtained by comparing the grayscale value of any pixel in the edge area with the grayscale value of the adjacent pixel in a specific direction, and the binary comparison value is filled into the corresponding pixel position to form a binary area corresponding to the edge area; During the comparison process, if the difference between the grayscale value of a pixel and an adjacent pixel in a specific direction satisfies the binarization condition, the binary comparison value of the pixel is set to 1, otherwise, it is set to 0; Step S13: taking each pixel in the binary area as a target pixel in turn and constructing a sliding window, sliding the window in multiple positions based on the position of the target pixel, and comparing the sliding window content with the local analysis database during the sliding process to obtain a control value; the multi-position sliding is to make the target pixel located at multiple positions in the sliding window, and perform multiple separate comparisons to obtain a control value; Step S14: performing edge comparison modification on the target pixel based on the comparison value, and using the modification result as the local analysis result; Step S15: applying the modification result to the digital image information in real time and presenting it on the smart terminal; specifically: updating the grayscale value of the corresponding pixel in the digital image information based on the modification result of the target pixel, and presenting it on the smart terminal; Step S2: The intelligent server obtains archived digital image information from each intelligent terminal, obtains an updated analysis database based on the archived digital image information, and updates the local analysis database of the intelligent terminal based on the updated analysis database.

2. The digital image analysis method in medical informationization according to claim 1, It is characterized in that The binarization condition is a preset condition that can be modified.

3. The digital image analysis method in medical informationization according to claim 2, It is characterized in that The binarization conditions change as the image analysis program is updated and modified.

4. The digital image analysis method in medical informationization according to claim 3, It is characterized in that The image data acquired in real time is a medical digital image.

5. The digital image analysis method in medical informationization according to claim 3, It is characterized in that The image data acquired in real time is medical image data.

6. A digital image analysis system in medical informationization, It is characterized in that include: An intelligent server and an intelligent terminal; the intelligent server is used to implement the digital image analysis method in medical informationization described in any one of claims 1 to 5; The intelligent terminal is used to send a digital image analysis request in medical informationization to the intelligent server.

7. The digital image analysis system in medical informationization according to claim 6, It is characterized in that The intelligent server is a big data server.

8. A digital image analysis platform in medical informationization, It is characterized in that It includes a processor, the processor is coupled to a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the digital image analysis method in medical informationization described in any one of claims 1-5 is implemented.

9. A computer-readable storage medium, It is characterized in that It comprises a program which, when executed on a computer, enables the computer to execute the digital image analysis method in medical informationization as described in any one of claims 1 to 5.

10. A big data server, It is characterized in that The big data server is configured to execute the digital image analysis method in medical informationization as described in any one of claims 1-5.

Images