Data management method and system based on tumor comprehensive diagnosis and treatment

Abstract

The invention relates to a data management method and system based on comprehensive tumor diagnosis and treatment, and belongs to the technical field of data management. The method comprises the following steps: acquiring uterus image data and clinical data of a patient, adding a timestamp to obtain a time sequence image and time sequence clinical data, and calculating time sequence uterus tumor morphological data through a tumor identification model; constructing admission record data according to the time sequence uterine tumor morphological data and the time sequence clinical data, obtaining disease course, operation records and system log data, and adding timestamps; the file retrieval times and the latest retrieval time are counted according to system log data, and admission records, disease courses and operation record data are stored in a local space through a classified storage model; and obtaining hospital discharge record data, accessing to obtain hospital discharge patient information, retrieving a local space according to the hospital discharge patient information, and transferring the hospital admission record, disease course and operation record data of the hospital discharge patient to a cloud storage server. And efficient management and storage of tumor diagnosis and treatment data are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of data management, and in particular relates to a data management method and system based on comprehensive diagnosis and treatment of tumors. Background Art

[0002] With the continuous development of medical technology, the diagnosis and treatment of cervical cancer has become more and more complex and diverse. At present, in the comprehensive diagnosis and treatment of cervical cancer, there are problems such as scattered data and chaotic management.

[0003] A large amount of cervical cancer patient data, including imaging data, clinical data, medical history data, and surgical record data, is stored in different systems and devices, making it difficult to effectively integrate and utilize them. This not only increases the difficulty for doctors to find and analyze data, but also affects the accurate judgment of patients' conditions and the formulation of treatment plans.

[0004] At the same time, the traditional data management method lacks the time series management of data and cannot clearly present the development and change process of cervical cancer. Moreover, it is inefficient in data storage and retrieval and cannot meet the needs of quickly and accurately obtaining patient information. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention provides a data management method and system based on comprehensive diagnosis and treatment of tumors.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] Acquire the patient's uterine imaging data and clinical data, add timestamps to the uterine imaging data and clinical data to obtain time-series imaging data and time-series clinical data, and calculate the time-series uterine tumor morphology data through a tumor recognition model based on the time-series imaging data;

[0008] Construct admission record data according to the time-series uterine tumor morphology data and the time-series clinical data, obtain medical course data, surgical record data, and system log data, and add timestamps to the admission record data, the medical course data, the surgical record data, and the system log data to obtain time-series admission record data, time-series medical course data, time-series surgical record data, and time-series system log data;

[0009] Perform data statistics based on the time series system log data to obtain the number of file retrievals and the most recent file retrieval time, and store the time series admission record data, the time series disease course data, and the time series surgical record data into an integrated storage space through a classification storage model based on the number of file retrievals and the most recent file retrieval time;

[0010] Obtain discharge record data, access the discharge record data to obtain discharged patient information, search the integrated storage space according to the discharged patient information data to obtain discharged patient admission record data, discharged patient chronological course data, and discharged patient surgical record data, and transfer the discharged patient admission record data, the discharged patient chronological course data, and the discharged patient surgical record data to a cloud storage server.

[0011] Specifically, the clinical data includes marker examination data, clinical manifestation data, gynecological examination data, and diagnostic report data.

[0012] Specifically, the integrated storage space includes a fast access storage layer and a secondary storage layer.

[0013] Specifically, the classification storage model first sorts the chronological admission record data, the chronological medical course data, and the chronological surgical record data according to the number of file retrieval times to obtain primary sorting data, sorts the primary sorting data according to the most recent retrieval time of the file to obtain ultimate sorting data, divides the ultimate sorting data according to the storage size of the fast access layer to obtain the frequently accessed data and the infrequently accessed data, stores the frequently accessed data in the fast access storage layer, and stores the infrequently accessed data in the secondary storage layer.

[0014] Specifically, constructing the admission record data according to the time-series uterine tumor morphology data and the time-series clinical data includes:

[0015] Decomposing the time series clinical data to obtain the patient information data and disease data;

[0016] An admission record template is obtained, and the patient information data, the disease data, and the time-series uterine tumor morphology data are parallelly spliced ​​according to the admission record template to obtain the admission record data.

[0017] Specifically, the specific calculation steps of the tumor recognition model are:

[0018] Preprocessing the time-series image data to obtain preprocessed image data, acquiring a tumor region of interest template image, and convolving the preprocessed image data with the tumor region of interest template image to obtain a tumor lesion region image;

[0019] The tumor lesion region image is intercepted according to the minimum circumscribed rectangle to obtain a lesion image, a detail magnified image is calculated according to the lesion image by using a histogram equalization algorithm, tumor detail features are obtained according to the detail magnified image by using a morphology-based edge feature extraction technology, and morphological features are calculated according to the tumor detail features;

[0020] Performing statistical calculations on the detailed magnified image to obtain a grayscale histogram feature matrix;

[0021] An adjusted image is obtained by grayscale adjustment based on the detail magnified image, and the grayscale co-occurrence matrix of the adjusted image is calculated. Shear wave transform features are calculated by shear wave exchange algorithm based on the adjusted image. The morphological features, the grayscale histogram feature matrix, the grayscale co-occurrence matrix, and the shear wave transform features are spliced ​​to obtain a feature matrix. Tumor classification data is obtained by calculation through a classifier based on the feature matrix. The time series uterine tumor morphology data is constructed based on the tumor classification data, the tumor detail features, and the morphological features.

[0022] Specifically, the key features of the gray level co-occurrence matrix include second-order moment, moment of inertia, entropy, correlation, non-similarity, and inverse difference moment.

[0023] A data management system based on comprehensive diagnosis and treatment of tumors using the data management method based on comprehensive diagnosis and treatment of tumors, comprising: a data acquisition module, a data processing module, a data storage module, and a data transfer module;

[0024] The data acquisition module is used to acquire the patient's uterine imaging data and clinical data, add timestamps to the uterine imaging data and clinical data to obtain time-series imaging data and time-series clinical data, and calculate the time-series uterine tumor morphology data through a tumor recognition model based on the time-series imaging data;

[0025] The data processing module is used to construct admission record data according to the time-series uterine tumor morphology data and the time-series clinical data, obtain medical course data, surgical record data, and system log data, and add timestamps according to the admission record data, the medical course data, the surgical record data, and the system log data to obtain time-series admission record data, time-series medical course data, time-series surgical record data, and time-series system log data;

[0026] The data storage module is used to perform data statistics based on the time series system log data to obtain the number of file retrievals and the most recent file retrieval time, and store the time series admission record data, the time series disease course data, and the time series surgical record data into an integrated storage space through a classification storage model based on the number of file retrievals and the most recent file retrieval time;

[0027] The data transfer module is used to obtain discharge record data, access the discharge record data to obtain discharged patient information, search the integrated storage space according to the discharged patient information data to obtain discharged patient admission record data, discharged patient chronological course data, and discharged patient surgical record data, and transfer the discharged patient admission record data, the discharged patient chronological course data, and the discharged patient surgical record data to a cloud storage server.

[0028] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the data management method based on comprehensive diagnosis and treatment of tumors as described above is implemented.

[0029] A storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute the data management method based on comprehensive tumor diagnosis and treatment as described above.

[0030] The beneficial effects of the present invention are:

[0031] (1) An integrated storage space is provided and divided into a fast access storage layer and a secondary storage layer. Data about patients in different devices are collected and classified and integrated according to patient information. Data statistics are performed based on the time series system log data to obtain the number of file retrievals and the time when the file was most recently retrieved. According to the number of file retrievals and the time when the file was most recently retrieved, the patient's medical condition data is classified and stored in the integrated storage space through a classification storage model, thereby realizing information hierarchical management and reducing system retrieval time.

[0032] (2) Obtain the discharged patient information, search the integrated storage space based on the discharged patient information, and transfer all the discharged patient's medical data to the cloud storage space, thereby reducing the storage capacity of the integrated storage space, realizing patient data sharing, and improving the system's retrieval speed.

[0033] (3) A tumor recognition model is provided, and the time-series uterine tumor morphology data is obtained by calculating the time-series image data through the tumor recognition model, which clearly presents the development and change process of cervical tumors. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0035] Figure 1 The figure is a flow chart of a data management method based on comprehensive diagnosis and treatment of tumors according to the present invention. DETAILED DESCRIPTION

[0036] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0037] See also Figure 1 , a data management method based on comprehensive diagnosis and treatment of tumors;

[0038] Acquire the patient's uterine imaging data and clinical data, add timestamps to the uterine imaging data and clinical data to obtain time-series imaging data and time-series clinical data, and calculate the time-series uterine tumor morphology data through a tumor recognition model based on the time-series imaging data;

[0039] Construct admission record data according to the time-series uterine tumor morphology data and the time-series clinical data, obtain medical course data, surgical record data, and system log data, and add timestamps to the admission record data, the medical course data, the surgical record data, and the system log data to obtain time-series admission record data, time-series medical course data, time-series surgical record data, and time-series system log data;

[0040] Perform data statistics based on the time series system log data to obtain the number of file retrievals and the most recent file retrieval time, and store the time series admission record data, the time series disease course data, and the time series surgical record data into an integrated storage space through a classification storage model based on the number of file retrievals and the most recent file retrieval time;

[0041] Obtain discharge record data, access the discharge record data to obtain discharged patient information, search the integrated storage space according to the discharged patient information data to obtain discharged patient admission record data, discharged patient chronological course data, and discharged patient surgical record data, and transfer the discharged patient admission record data, the discharged patient chronological course data, and the discharged patient surgical record data to a cloud storage server.

[0042] Specifically, the clinical data includes marker examination data, clinical manifestation data, gynecological examination data, and diagnostic report data.

[0043] Specifically, the integrated storage space includes a fast access storage layer and a secondary storage layer. The fast access layer is smaller than the secondary storage layer and is used to store frequently accessed data; the secondary storage layer is used to store infrequently accessed data.

[0044] Specifically, the classification storage model first sorts the chronological admission record data, the chronological medical course data, and the chronological surgical record data according to the number of file retrieval times to obtain primary sorting data, sorts the primary sorting data according to the most recent retrieval time of the file to obtain ultimate sorting data, divides the ultimate sorting data according to the storage size of the fast access layer to obtain the frequently accessed data and the infrequently accessed data, stores the frequently accessed data in the fast access storage layer, and stores the infrequently accessed data in the secondary storage layer.

[0045] Specifically, constructing the admission record data according to the time-series uterine tumor morphology data and the time-series clinical data includes:

[0046] Decomposing the time series clinical data to obtain the patient information data and disease data;

[0047] An admission record template is obtained, and the patient information data, the disease data, and the time-series uterine tumor morphology data are parallelly spliced ​​according to the admission record template to obtain the admission record data.

[0048] Specifically, the specific calculation steps of the tumor recognition model are:

[0049] Preprocessing the time-series image data to obtain preprocessed image data, obtaining a tumor region of interest template image, and convolving the preprocessed image data with the tumor region of interest template image to obtain a tumor lesion region image; the preprocessing includes noise filtering, image enhancement, and interpolation;

[0050] The image of the tumor lesion region is intercepted according to the minimum circumscribed rectangle to obtain a lesion image, a detail magnified image is calculated according to the lesion image by a histogram equalization algorithm, a tumor detail feature is obtained according to the detail magnified image by a morphology-based edge feature extraction technology, and a morphological feature is calculated according to the tumor detail feature; the tumor detail feature includes the perimeter, area, and centroid coordinates of the tumor lesion region;

[0051] The morphological feature calculation formula is:

[0052]

[0053] Among them, D is the morphological feature, C is the perimeter, A is the area, and C y , C x is the centroid coordinate.

[0054] A grayscale histogram feature matrix for statistical calculation based on the detail magnified image; the grayscale histogram feature matrix includes mean, median, standard deviation, skewness, kurtosis, maximum, minimum, entropy, energy, range, mean absolute deviation and root mean square;

[0055] An adjusted image is obtained by grayscale adjustment based on the detail magnified image, and the grayscale co-occurrence matrix of the adjusted image is calculated. Shear wave transform features are calculated by shear wave exchange algorithm based on the adjusted image. The morphological features, the grayscale histogram feature matrix, the grayscale co-occurrence matrix, and the shear wave transform features are spliced ​​to obtain a feature matrix. Tumor classification data is obtained by calculation through a classifier based on the feature matrix. The time series uterine tumor morphology data is constructed based on the tumor classification data, the tumor detail features, and the morphological features.

[0056] Specifically, the key features of the gray-level co-occurrence matrix include second-order moment, moment of inertia, entropy, correlation, dissimilarity, and inverse difference moment;

[0057] The second-order moment calculation formula is:

[0058]

[0059] Among them, A is the second-order moment, and P(i, j) is the value of the i-th row and j-th column in the gray-level co-occurrence matrix.

[0060] The formula for calculating the moment of inertia is:

[0061]

[0062] Where I is the moment of inertia, and P(i, j) is the value of the i-th row and j-th column in the gray-level co-occurrence matrix.

[0063] The entropy calculation formula is:

[0064]

[0065] Where E is the entropy and P(i, j) is the value of the i-th row and j-th column in the gray-level co-occurrence matrix.

[0066] The correlation calculation formula is:

[0067]

[0068] Where corr is the correlation, P(i, j) is the value of the i-th row and j-th column in the gray-level co-occurrence matrix, and U x , U y is the mean value in the x and y directions, Z x , Z y is the standard deviation in the x and y directions.

[0069] The similarity calculation formula is:

[0070]

[0071] Where D is the dissimilarity and P(i, j) is the value of the i-th row and j-th column in the gray-level co-occurrence matrix.

[0072] In this embodiment, a data management system based on comprehensive diagnosis and treatment of tumors uses data collection, diagnosis, treatment, and prognosis as the digital main line to manage the data of the entire disease cycle of cervical cancer.

[0073] A data management system based on comprehensive diagnosis and treatment of tumors using the data management method based on comprehensive diagnosis and treatment of tumors, comprising: a data acquisition module, a data processing module, a data storage module, and a data transfer module;

[0074] The data acquisition module is used to acquire the patient's uterine imaging data and clinical data, add timestamps to the uterine imaging data and clinical data to obtain time-series imaging data and time-series clinical data, and calculate the time-series uterine tumor morphology data through a tumor recognition model based on the time-series imaging data;

[0075] The data processing module is used to construct admission record data according to the time-series uterine tumor morphology data and the time-series clinical data, obtain medical course data, surgical record data, and system log data, and add timestamps according to the admission record data, the medical course data, the surgical record data, and the system log data to obtain time-series admission record data, time-series medical course data, time-series surgical record data, and time-series system log data;

[0076] The data storage module is used to perform data statistics based on the time series system log data to obtain the number of file retrievals and the most recent file retrieval time, and store the time series admission record data, the time series disease course data, and the time series surgical record data into an integrated storage space through a classification storage model based on the number of file retrievals and the most recent file retrieval time;

[0077] The data transfer module is used to obtain discharge record data, access the discharge record data to obtain discharged patient information, search the integrated storage space according to the discharged patient information data to obtain discharged patient admission record data, discharged patient chronological course data, and discharged patient surgical record data, and transfer the discharged patient admission record data, the discharged patient chronological course data, and the discharged patient surgical record data to a cloud storage server.

[0078] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the data management method based on comprehensive diagnosis and treatment of tumors as described above is implemented.

[0079] A storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute the data management method based on comprehensive tumor diagnosis and treatment as described above.

[0080] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0081] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0082] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0083] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A data management method based on comprehensive diagnosis and treatment of tumors, characterized in that: include: Acquire the patient's uterine imaging data and clinical data, add timestamps to the uterine imaging data and clinical data to obtain time-series imaging data and time-series clinical data, and calculate the time-series uterine tumor morphology data through a tumor recognition model based on the time-series imaging data; Construct admission record data according to the time-series uterine tumor morphology data and the time-series clinical data, obtain medical course data, surgical record data, and system log data, and add timestamps to the admission record data, the medical course data, the surgical record data, and the system log data to obtain time-series admission record data, time-series medical course data, time-series surgical record data, and time-series system log data; Perform data statistics based on the time series system log data to obtain the number of file retrievals and the most recent file retrieval time, and store the time series admission record data, the time series disease course data, and the time series surgical record data into an integrated storage space through a classification storage model based on the number of file retrievals and the most recent file retrieval time; Obtain discharge record data, access the discharge record data to obtain discharged patient information, search the integrated storage space according to the discharged patient information data to obtain discharged patient admission record data, discharged patient chronological course data, and discharged patient surgical record data, and transfer the discharged patient admission record data, the discharged patient chronological course data, and the discharged patient surgical record data to a cloud storage server.

2. The data management method based on comprehensive diagnosis and treatment of tumors according to claim 1, characterized in that: The clinical data include marker examination data, clinical manifestation data, gynecological examination data, and diagnostic report data.

3. The data management method based on comprehensive diagnosis and treatment of tumors according to claim 1, characterized in that: The integrated storage space includes a fast access storage layer and a secondary storage layer.

4. The data management method based on comprehensive diagnosis and treatment of tumors according to claim 1, characterized in that: The classification storage model includes firstly sorting the time-series admission record data, the time-series medical course data, and the time-series surgical record data according to the number of file retrieval times to obtain primary sorting data, sorting the primary sorting data according to the most recent retrieval time of the file to obtain ultimate sorting data, dividing the ultimate sorting data according to the storage size of the fast access layer to obtain the frequently accessed data and the infrequently accessed data, storing the frequently accessed data in the fast access storage layer, and storing the infrequently accessed data in the secondary storage layer.

5. The data management method based on comprehensive diagnosis and treatment of tumors according to claim 1, characterized in that: The constructing of admission record data according to the time series uterine tumor morphology data and the time series clinical data comprises: Decomposing the time series clinical data to obtain the patient information data and disease data; An admission record template is obtained, and the patient information data, the disease data, and the time-series uterine tumor morphology data are parallelly spliced ​​according to the admission record template to obtain the admission record data.

6. The data management method based on comprehensive diagnosis and treatment of tumors according to claim 1, characterized in that: The specific calculation steps of the tumor recognition model are: Preprocessing the time-series image data to obtain preprocessed image data, acquiring a tumor region of interest template image, and convolving the preprocessed image data with the tumor region of interest template image to obtain a tumor lesion region image; The tumor lesion region image is intercepted according to the minimum circumscribed rectangle to obtain a lesion image, a detail magnified image is calculated according to the lesion image by using a histogram equalization algorithm, tumor detail features are obtained according to the detail magnified image by using a morphology-based edge feature extraction technology, and morphological features are calculated according to the tumor detail features; Performing statistical calculations on the detailed magnified image to obtain a grayscale histogram feature matrix; An adjusted image is obtained by grayscale adjustment based on the detail magnified image, and the grayscale co-occurrence matrix of the adjusted image is calculated. Shear wave transformation features are calculated by shear wave exchange algorithm based on the adjusted image. The morphological features, the grayscale histogram feature matrix, the grayscale co-occurrence matrix, and the shear wave transformation features are spliced ​​to obtain a feature matrix. Tumor classification data is obtained by calculating a classifier based on the feature matrix. The time series uterine tumor morphology data is constructed based on the tumor classification data, the tumor detail features, and the morphological features.

7. The data management method based on comprehensive diagnosis and treatment of tumors according to claim 1, characterized in that: The key features of the gray level co-occurrence matrix include second-order moment, moment of inertia, entropy, correlation, dissimilarity, and inverse difference moment.

8. A data management system based on comprehensive diagnosis and treatment of tumors using the data management method based on comprehensive diagnosis and treatment of tumors, characterized in that: include: Data acquisition module, data processing module, data storage module, data transfer module; The data acquisition module is used to acquire the patient's uterine imaging data and clinical data, add timestamps to the uterine imaging data and clinical data to obtain time-series imaging data and time-series clinical data, and calculate the time-series uterine tumor morphology data through a tumor recognition model based on the time-series imaging data; The data processing module is used to construct admission record data according to the time-series uterine tumor morphology data and the time-series clinical data, obtain medical course data, surgical record data, and system log data, and add timestamps according to the admission record data, the medical course data, the surgical record data, and the system log data to obtain time-series admission record data, time-series medical course data, time-series surgical record data, and time-series system log data; The data storage module is used to perform data statistics based on the time series system log data to obtain the number of file retrievals and the most recent file retrieval time, and store the time series admission record data, the time series disease course data, and the time series surgical record data into an integrated storage space through a classification storage model based on the number of file retrievals and the most recent file retrieval time; The data transfer module is used to obtain discharge record data, access the discharge record data to obtain discharged patient information, search the integrated storage space according to the discharged patient information data to obtain discharged patient admission record data, discharged patient chronological course data, and discharged patient surgical record data, and transfer the discharged patient admission record data, the discharged patient chronological course data, and the discharged patient surgical record data to a cloud storage server.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the data management method based on comprehensive diagnosis and treatment of tumors as described in any one of claims 1-7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the data management method based on comprehensive diagnosis and treatment of tumors as described in any one of claims 1-7.

Images