[go: up one dir, main page]

CN119069086B - A medical data aggregation system based on heterogeneous multiple data sources - Google Patents

A medical data aggregation system based on heterogeneous multiple data sources Download PDF

Info

Publication number
CN119069086B
CN119069086B CN202411545820.9A CN202411545820A CN119069086B CN 119069086 B CN119069086 B CN 119069086B CN 202411545820 A CN202411545820 A CN 202411545820A CN 119069086 B CN119069086 B CN 119069086B
Authority
CN
China
Prior art keywords
gastrointestinal stromal
stromal tumor
module
data
tumor image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202411545820.9A
Other languages
Chinese (zh)
Other versions
CN119069086A (en
Inventor
徐娟
倪翔
张连超
司锋刚
包国峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Provincial Hospital
Inspur Software Co Ltd
Original Assignee
Shandong Provincial Hospital
Inspur Software Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shandong Provincial Hospital, Inspur Software Co Ltd filed Critical Shandong Provincial Hospital
Priority to CN202411545820.9A priority Critical patent/CN119069086B/en
Publication of CN119069086A publication Critical patent/CN119069086A/en
Application granted granted Critical
Publication of CN119069086B publication Critical patent/CN119069086B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/30—Noise filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30028—Colon; Small intestine
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30092—Stomach; Gastric
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30096—Tumor; Lesion

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Public Health (AREA)
  • Radiology & Medical Imaging (AREA)
  • Primary Health Care (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Quality & Reliability (AREA)
  • Data Mining & Analysis (AREA)
  • Pathology (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)

Abstract

The invention relates to the technical field of data processing, in particular to a medical data convergence system based on multi-data source isomerism, which comprises a time dimension fusion unit and a space dimension fusion unit in a medical source fusion module, and (3) carrying out sequence fusion and fusion under the same coordinate system on the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image which are acquired at different moments, so that blood flow image information data provided by ultrasonic contrast and anatomical structure image information data provided by computer tomography are combined to form a medical data convergence system.

Description

Medical data converging system based on multiple data sources are heterogeneous
Technical Field
The invention relates to the technical field of data processing, and particularly discloses a medical data aggregation system based on multi-data source isomerism.
Background
Gastrointestinal stromal tumors originate from gastrointestinal stromal cells and are commonly found in the stomach and small intestine, because of heterogeneity and potential malignancy tendency, it is important to accurately identify the gastrointestinal stromal tumors by imaging, ultrasonic radiography is a common imaging examination means, can provide clues for primarily finding the gastrointestinal stromal tumors, but has limited penetration, has poor imaging effect on lesions located in the deep gastrointestinal region, can provide high-resolution cross-sectional images by computed tomography, can clearly show the deep gastrointestinal structure, has poor hemodynamic evaluation capability on the gastrointestinal stromal tumors, is difficult to comprehensively reflect the blood supply characteristics of the gastrointestinal stromal tumors, can only detect the gastrointestinal stromal tumors by a single imaging method, has incompleteness in detecting the gastrointestinal stromal tumors, and provides a technical scheme for solving the problems.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a medical data converging system based on multiple data sources isomerism, which is characterized in that an endogenous acquisition module is used for acquiring ultrasonic contrast gastrointestinal stromal tumor image data and computer tomography gastrointestinal stromal tumor image data, a doctor source fusion module is used for fusing isomerism data from different data sources, a doctor research analysis module is used for identifying and segmenting a tumor area of gastrointestinal stromal tumor, and a visualization module is used for displaying analysis results and influence data to doctors in an intuitive mode so as to solve the problems in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
A medical data converging system based on multi-data source isomerism comprises an endogenous acquisition module, an iatrogenic refining module, an iatrogenic repository module, an iatrogenic fusion module, an iatrogenic research identification module, a visualization module and a safety protection module, and is characterized in that the endogenous acquisition module acquires ultrasonic contrast gastrointestinal stromal tumor image data and computer tomography gastrointestinal stromal tumor image data from ultrasonic equipment and computer tomography scanning equipment, the iatrogenic refining module performs image preprocessing on the acquired ultrasonic contrast gastrointestinal stromal tumor image data and computer tomography gastrointestinal stromal tumor image data, the iatrogenic fusion module comprises a time dimension fusion unit and a space dimension fusion unit, the time dimension fusion unit performs sequence fusion on ultrasonic contrast gastrointestinal stromal tumor images and computer tomography gastrointestinal stromal tumor images acquired in a patient examination period, builds a time sequence minimum accumulation distance model, and measures a first time sequence And a second time sequenceThe similarity between the two is calculated by the formula of a time sequence minimum accumulated distance model:
,
Wherein: for the value of the minimum cumulative distance, For the first time seriesAnd a second time sequenceAn optimal path aligned between, a first time series,For the first time seriesIs selected from the group consisting of a first element,For the first time seriesIs selected from the group consisting of a first element,For the first time seriesThe first of (3)Element, second time series,For a second time seriesIs selected from the group consisting of a first element,For a second time seriesIs selected from the group consisting of a first element,For a second time seriesThe first of (3)The number of elements to be added to the composition,For the first time seriesTime point of middleIs used for the indexing of (a),For a second time seriesTime point of middleIs used for the indexing of (a),To be from the first time seriesFrom the start point to the point of (2)And from a second time seriesFrom the start point to the point of (2)Is used for the minimum cumulative distance of (a),Is the optimal pathThrough the minimum cumulative distance value of the two time series of outputsMeasuring a first time seriesAnd a second time sequenceSimilarity between the two, if the minimum accumulated distance value is lower than the preset distance value, adopting a pixel level fusion technology to carry out first time sequenceAnd a second time sequenceThe medical research analysis module is used for identifying and dividing the gastrointestinal stromal tumor into tumor areas, and the visualization module is used for displaying the analysis result and the influence data to a doctor in an intuitive mode.
As a further scheme of the invention, the iatrogenic fusion module comprises a time dimension fusion unit and a space dimension fusion unit, wherein the space dimension fusion unit fuses an ultrasonic contrast gastrointestinal stromal tumor image and a computer tomography gastrointestinal stromal tumor image under the same space coordinate system, and the specific steps are as follows:
Step Y1, establishing a transformation model from an ultrasonic contrast gastrointestinal stromal tumor image coordinate system to a computer tomography gastrointestinal stromal tumor image coordinate system, wherein the transformation model has the formula:
,
Wherein: For ultrasound contrast of point coordinates in images of gastrointestinal stromal tumors, For the point coordinates in the corresponding ultrasound contrast gastrointestinal stromal tumor image in the computed tomography gastrointestinal stromal tumor image,For rotation of the matrix, a rotation of the ultrasound contrast gastrointestinal stromal tumor image relative to the computed tomography gastrointestinal stromal tumor image is described,Describing the translation of the ultrasound contrast gastrointestinal stromal tumor image relative to the computed tomography gastrointestinal stromal tumor image as a translation vector;
step Y2, an optimization model of optimal transformation parameters is established, and the formula of the model is as follows:
,
Wherein: for an optimal rotation matrix, For the optimal translation vector to be present,In order to measure the parameter value of the similarity between the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image, when the parameter value is in the preset parameter value range, the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image are fused;
step Y3, establishing a model after the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image are fused, wherein the model formula is as follows:
,
Wherein: In order to obtain the image after the fusion, As a result of the weighting factor(s),For ultrasound contrast of images of gastrointestinal stromal tumors,Gastrointestinal stromal tumor images were scanned for computer tomography.
As a further scheme of the invention, the endogenous acquisition module is connected with the doctor source refining module, the doctor source refining module is connected with the doctor source repository module, the doctor source repository module is connected with the doctor source fusion module, the time dimension unit and the space dimension fusion unit are respectively connected with the doctor source fusion module, the doctor source fusion module is connected with the doctor-grinding analysis module, the doctor-grinding identification module is connected with the visualization module, and the visualization module is connected with the safety protection module.
According to the invention, an internal acquisition module acquires ultrasonic contrast gastrointestinal stromal tumor image data and computer tomography gastrointestinal stromal tumor image data from ultrasonic equipment and computer tomography equipment, the internal acquisition module is connected with the ultrasonic equipment and the computer tomography equipment through interfaces, image data acquisition is carried out on the computer tomography equipment by using a special API, image data are acquired by customizing the interfaces of the ultrasonic equipment, the internal acquisition module automatically pulls gastrointestinal stromal tumor image data from the ultrasonic equipment and the computer tomography equipment according to requirements and marks patient information and inspection results, the accuracy of subsequent data management and retrieval is ensured, the gastrointestinal stromal tumor image data comprise ultrasonic contrast gastrointestinal stromal tumor image data and computer tomography gastrointestinal stromal tumor image data, the ultrasonic contrast gastrointestinal stromal tumor image data comprise dynamic image sequences and enhanced echo information, the dynamic image sequences appear in the form of dynamic image sequences, the distribution and flow conditions of microbubble contrast agents in the gastrointestinal tract of patients are displayed, the echo information is enhanced under the action of ultrasonic waves, the computed tomography gastrointestinal stromal tumor image data comprise high-volume contrast gastrointestinal stromal tumor volume data and high-resolution cross-section image data which can be used for reconstructing a three-dimensional cross-sectional image with high-dimensional cross-sectional image volume, and three-dimensional cross-sectional image data can be generated in a multi-dimensional cross-sectional image and can be reconstructed in a multi-dimensional cross-dimensional image structure.
As a further proposal of the invention, the iatrogenic refining module carries out image preprocessing on the acquired ultrasonic contrast gastrointestinal stromal tumor image data and the computed tomography gastrointestinal stromal tumor image data so as to adapt to the subsequent data fusion and analysis, image preprocessing is carried out on the acquired ultrasonic contrast gastrointestinal stromal tumor image data and the acquired computer tomography gastrointestinal stromal tumor image data, subsequent data fusion and analysis are adapted, a Gaussian check image is used for convolution, particle noise and spot noise in the computer tomography gastrointestinal stromal tumor image and the ultrasonic gastrointestinal stromal tumor image are eliminated, the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image are aligned through registration based on characteristics so as to have consistency in space, a SIFT algorithm detects key points in the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image, a characteristic vector with unchanged scale is generated for each key point, matching key point pairs in two images through feature descriptions, estimating affine transformation between the images through the matched key point pairs, resampling the ultrasound contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image to align them in the same coordinate system based on the estimated affine transformation matrix, the global contrast of the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image is enhanced through histogram equalization, the Laplacian operator is utilized to calculate the second derivative of the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image, and the edge definition in the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image is enhanced.
As a further aspect of the present invention, the doctor-source repository module stores multi-source heterogeneous data, wherein the multi-source heterogeneous data refers to ultrasound contrast gastrointestinal stromal tumor image data, computed tomography gastrointestinal stromal tumor image data, patient information and examination results, the doctor-source repository module supports large-scale data management and access, stores structured data and unstructured data, the structured data comprises patient information and examination results, the unstructured data comprises ultrasound contrast gastrointestinal stromal tumor image data and computed tomography gastrointestinal stromal tumor image data, the system adopts a hybrid storage architecture according to different requirements of data types, the relational database stores and manages structured data, and the NoSQL database stores and manages unstructured data.
As a further scheme of the invention, the medical research identification module is used for identifying and dividing the tumor area of the gastrointestinal stromal tumor, the medical research identification module is used for identifying and dividing the tumor area by using a U-Net model, the U-Net is designed to enable the tumor area to be divided and retain enough context information, the identification and division of the gastrointestinal stromal tumor of a medical image are particularly important, the boundary of the gastrointestinal stromal tumor is fuzzy and the shape is different, the U-Net can accurately divide the gastrointestinal stromal tumor area on the pixel level, and based on the identification and division result, the medical research identification module can generate quantitative analysis data of the gastrointestinal stromal tumor, such as the size, the shape and the position of the gastrointestinal stromal tumor and the relation between the gastrointestinal stromal tumor and surrounding tissues, and the generated quantitative analysis data of the gastrointestinal stromal tumor can provide abundant quantitative analysis materials for researchers during medical research.
As a further scheme of the invention, the visualization module presents analysis results and influence data to a doctor in an intuitive mode, the module uses a volume drawing method to reconstruct the fused ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image in a three-dimensional mode, displays the space form and the space position of the gastrointestinal stromal tumor, synchronously loads the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image corresponding to each time point on a time axis into a playing window, realizes interframe interpolation to smooth playing differences among different modes, synchronously plays the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image through a unified time controller in the playing process, and synchronously observes the condition of the gastrointestinal stromal tumor through the synchronous playing function of the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image.
The medical data convergence system based on multi-data source isomerism has the technical effects and advantages that:
According to the invention, the ultrasonic contrast gastrointestinal stromal tumor image data and the computer tomography gastrointestinal stromal tumor image data are acquired through the endogenous acquisition module, the acquired images are preprocessed through the doctor-source refining module, the multi-source heterogeneous data are stored through the doctor-source repository module, the heterogeneous data from different data sources are fused through the doctor-source fusion module to generate a unified patient view, the gastrointestinal stromal tumor is identified and segmented into tumor areas through the doctor-grinding analysis module, the analysis result and the influence data are displayed to a doctor in an intuitive mode through the visualization module, and the blood flow image information data provided by ultrasonic contrast and the anatomical structure image information data provided by computer tomography are combined to form a medical data convergence system, so that the accuracy rate of detecting gastrointestinal stromal tumor is improved.
Drawings
Fig. 1 is a schematic structural diagram of a medical data aggregation system based on multi-data source heterogeneous system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
The embodiment of the invention provides a medical data converging system based on multi-data source isomerism, which comprises an endogenous acquisition module, a medical source refining module, a medical source repository module, a medical source fusion module, a medical research identification module, a visualization module and a safety protection module, wherein the medical source fusion module comprises a time dimension fusion unit and a space dimension fusion unit, the endogenous acquisition module acquires ultrasonic contrast gastrointestinal stromal tumor image data and computer tomography gastrointestinal stromal tumor image data from ultrasonic equipment and computer tomography scanning equipment, the medical source refining module performs image preprocessing on the acquired ultrasonic contrast gastrointestinal stromal tumor image data and computer tomography gastrointestinal stromal tumor image data to adapt to subsequent data fusion and analysis, the medical source repository module stores multi-source isomerism data, wherein the multi-source isomerism data refers to the ultrasonic contrast gastrointestinal stromal tumor image data, the computer tomography gastrointestinal stromal tumor image data, patient information and inspection results, supports management and access of large-scale data, stores structured data and unstructured data, the medical source fusion module fuses isomerism data from different data sources, and displays the medical source image preprocessing on the acquired ultrasonic contrast gastrointestinal stromal tumor image data and the computer tomography gastrointestinal stromal tumor image data to the visual analysis module in a visual display mode.
In this embodiment, the endogenous acquisition module is connected with the iatrogenic refining module, the iatrogenic refining module is connected with the iatrogenic repository module, the iatrogenic repository module is connected with the iatrogenic fusion module, the time dimension unit and the space dimension fusion unit are respectively connected with the iatrogenic fusion module, the iatrogenic fusion module is connected with the iatrogenic analysis module, the iatrogenic identification module is connected with the visualization module, and the visualization module is connected with the safety protection module.
In this embodiment, the intrinsic acquisition module acquires ultrasound contrast gastrointestinal stromal tumor image data and computed tomography gastrointestinal stromal tumor image data from an ultrasound device and a computed tomography device, including the following specific contents:
The internal acquisition module is connected with the ultrasonic equipment and the computer tomography equipment through an interface, the computer tomography equipment uses a special API to acquire image data, the ultrasonic equipment is customized to acquire the image data, and the internal acquisition module is configured to automatically check whether the equipment has newly generated influence data after the patient is checked, and acquire gastrointestinal stromal tumor image data from the connected equipment;
the gastrointestinal stromal tumor image data comprises ultrasonic contrast gastrointestinal stromal tumor image data and computer tomography gastrointestinal stromal tumor image data, the ultrasonic contrast gastrointestinal stromal tumor image data comprises a dynamic image sequence and enhanced echo information, the dynamic image sequence appears in the form of the dynamic image sequence, the distribution and flow condition of the microbubble contrast agent in the stomach and intestine of a patient are displayed, the identification of tumor blood flow characteristics is facilitated, and the enhanced echo generates the enhanced echo information under the action of ultrasonic waves;
the gastrointestinal stromal tumor image data of the computed tomography comprises a high-resolution cross-section gastrointestinal stromal tumor image and volume parameters, the high-resolution cross-section gastrointestinal stromal tumor image is a high-resolution two-position cross-section image, the internal structure of the gastrointestinal tract can be displayed in detail, and three-dimensional volume data can be generated through multi-layer scanning and used for three-dimensional reconstruction and multi-view observation.
In this embodiment, the iatrogenic refining module performs image preprocessing on the acquired ultrasound contrast gastrointestinal stromal tumor image data and the computed tomography gastrointestinal stromal tumor image data to adapt to subsequent data fusion and analysis, including the following specific contents:
image preprocessing is carried out on the acquired ultrasonic contrast gastrointestinal stromal tumor image data and the acquired computer tomography gastrointestinal stromal tumor image data, subsequent data fusion and analysis are adapted, a Gaussian check image is used for convolution, particle noise and spot noise in the computer tomography gastrointestinal stromal tumor image and the ultrasonic gastrointestinal stromal tumor image are eliminated, the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image are aligned through registration based on characteristics, the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image are enabled to have consistency in space, a SIFT algorithm detects key points in the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image, a feature vector with unchanged scale is generated for each key point, a key point pair in the two images is matched through characteristic description, affine transformation between the images is estimated through the matched key point pair, the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image are resampled according to an estimated affine transformation matrix, the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image are enabled to be aligned under the same coordinate system, key points in the space are enabled to have consistency through histogram equalization, and the ultrasonic contrast gastrointestinal stromal tumor image and the computer tomography gastrointestinal stromal tumor image are enabled to be enhanced by means of the global contrast of the gastrointestinal stromal tumor image and the gastrointestinal stromal tumor image.
In this embodiment, the medical repository module stores multi-source heterogeneous data, where the multi-source heterogeneous data refers to ultrasound contrast gastrointestinal stromal tumor image data, computed tomography gastrointestinal stromal tumor image data, patient information, and examination results, support for large-scale data management and access, and store structured data and unstructured data includes the following specific contents:
structured data including personal information of the patient, medical history records and examination results, the data having well-defined formats and fields, unstructured data including ultrasound contrast gastrointestinal stromal tumor image data and computed tomography gastrointestinal stromal tumor image data, such data being in the form of images and videos;
In order to meet the storage requirements of different types of data, the doctor source repository module adopts a hybrid storage architecture, structured data is stored and managed through a relational database, the consistency and the integrity of the data are ensured by utilizing the strong transaction processing capability and complex query support of the structured data, unstructured data is stored and managed through a NoSQL database, and the NoSQL database can flexibly process large-scale image data, support distributed storage and parallel processing and improve the expansibility and the data access speed of the system.
In this embodiment, the medical research identification module identifies and segments the gastrointestinal stromal tumor region according to the following specific contents:
The medical research identification module is used for identifying and dividing the gastrointestinal stromal tumor area by using a trained U-Net model, the U-Net model is composed of an encoder and a decoder, jump connection is arranged between the encoder and the decoder, the U-Net is designed to enable the U-Net to be divided and retain enough context information, the medical research identification module is particularly important for identifying and dividing the gastrointestinal stromal tumor of medical images, the boundary of the gastrointestinal stromal tumor is fuzzy, the U-Net can accurately divide the gastrointestinal stromal tumor area on the pixel level, based on the identification and division results, the medical research identification module can generate quantitative analysis data of the gastrointestinal stromal tumor, such as the size, the shape and the position of the gastrointestinal stromal tumor and the relation between the gastrointestinal stromal tumor and surrounding tissues, the generated quantitative analysis data of the gastrointestinal stromal tumor can provide abundant quantitative analysis materials for researchers during medical research, the trained U-Net model weight and framework are derived to be TensorFlow and deployed in a server, the input medical image data are processed in normalized image data, and the difference between the gastrointestinal stromal tumor area and the gastrointestinal stromal tumor area is eliminated after the medical image data are scanned under different conditions.
In this embodiment, the iatrogenic fusion module fuses heterogeneous data from different data sources, and the generation of the unified patient view includes the following specific contents:
The medical source fusion module comprises two units, namely a time dimension fusion unit and a space dimension fusion unit, wherein the time dimension fusion unit carries out sequence fusion on ultrasonic contrast gastrointestinal stromal tumor images and computed tomography gastrointestinal stromal tumor images which are acquired at different moments, and the specific steps are as follows:
Step Z1, obtaining a first time sequence of ultrasound contrast gastrointestinal stromal tumor images ,For the first time seriesIs provided for the first time point of the (c),For the first time seriesIs provided in the form of a second time point of the series,For the first time seriesThe first of (3)At a time point, simultaneously acquiring a second time series of computed tomography gastrointestinal stromal tumor images,For a second time seriesIs provided for the first time point of the (c),For a second time seriesIs provided in the form of a second time point of the series,For a second time seriesThe first of (3)Time points;
Step Z2, first time series And a second time sequenceThe distance formula of the two time points is as follows: Wherein, the method comprises the steps of, wherein, For the point in timeAnd point in timeThe distance between the two plates is set to be equal,For the first time seriesThe first of (3)The time point at which the time point is the same,For a second time seriesThe first of (3)Time points;
step Z3, the accumulated distance matrix formula is:
,
Wherein: to accumulate distance matrix, representing the distance from the first time series From the start point to the point of (2)From a second time seriesFrom the start point to the point of (2)The minimum cumulative distance of the positions,For the first time seriesIs the previous point in time of (a)With a second time sequenceIs the current point in time of (2)Is used for the distance of the accumulation of (a),For the first time seriesIs the current point in time of (2)With a second time sequenceIs the previous point in time of (a)Is used for the distance of the accumulation of (a),For the first time seriesIs the previous point in time of (a)With a second time sequenceIs the previous point in time of (a)Is a cumulative distance of (2);
Step Z4, constructing a time sequence minimum accumulated distance model, and measuring a first time sequence And a second time sequenceThe similarity between the two is calculated by the formula of a time sequence minimum accumulated distance model:
,
Wherein: for the value of the minimum cumulative distance, The aligned optimal path between the two time series,For the first time seriesTime point of middleIs used for the indexing of (a),For a second time seriesTime point of middleIs used for the indexing of (a),To be from the first time seriesFrom the start point to the point of (2)And from a second time seriesFrom the start point to the point of (2)Is used for the minimum cumulative distance of (a),Is the optimal pathThrough the minimum cumulative distance value of the two time series of outputsMeasuring a first time seriesAnd a second time sequenceSimilarity between the two, if the minimum accumulated distance value is lower than the preset distance value, adopting a pixel level fusion technology to carry out first time sequenceAnd a second time sequenceFusing;
the space dimension fusion unit fuses the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image under the same space coordinate system, and the specific steps are as follows:
Step Y1, establishing a transformation model from an ultrasonic contrast gastrointestinal stromal tumor image coordinate system to a computer tomography gastrointestinal stromal tumor image coordinate system, wherein the transformation model has the formula:
,
Wherein: For ultrasound contrast of point coordinates in images of gastrointestinal stromal tumors, For the point coordinates in the corresponding ultrasound contrast gastrointestinal stromal tumor image in the computed tomography gastrointestinal stromal tumor image,For rotation of the matrix, a rotation of the ultrasound contrast gastrointestinal stromal tumor image relative to the computed tomography gastrointestinal stromal tumor image is described,Describing the translation of the ultrasound contrast gastrointestinal stromal tumor image relative to the computed tomography gastrointestinal stromal tumor image as a translation vector;
step Y2, an optimization model of optimal transformation parameters is established, and the formula of the model is as follows:
,
Wherein: for an optimal rotation matrix, For the optimal translation vector to be present,In order to measure the parameter value of the similarity between the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image, when the parameter value is in the preset parameter value range, the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image are fused;
step Y3, establishing a model after the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image are fused, wherein the model formula is as follows:
,
Wherein: In order to obtain the image after the fusion, As a result of the weighting factor(s),For ultrasound contrast of images of gastrointestinal stromal tumors,Gastrointestinal stromal tumor images were scanned for computer tomography.
In this embodiment, the visualization module presents the analysis result and the influence data to the doctor in an intuitive manner, including the following specific contents:
the visualization module is a key part and is responsible for displaying the multi-mode medical image to a doctor in a three-dimensional form, the module uses an advanced volume rendering method to carry out high-precision three-dimensional reconstruction on the fused ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image, the process can accurately present the spatial form, size and position of the gastrointestinal stromal tumor, and the difference between gastrointestinal stromal tumor tissues and surrounding tissues is highlighted through different color and transparency settings;
The visualization module supports a time-synchronous playing function, can display ultrasound contrast images and computed tomography gastrointestinal stromal tumor images acquired at different time points in the same visualization interface at the same time, in a front-end interface, a doctor can play, pause and adjust the frame rate through a playing controller to flexibly control the playing rhythm of the images, image data corresponding to each time point on a time axis can be synchronously loaded to a playing window, and the system also smoothly processes time differences among different modes through an inter-frame interpolation technology to ensure the continuity and consistency of the playing process;
In addition, the visualization module integrates a unified time controller, so that accurate synchronous playing of ultrasonic contrast and computed tomography gastrointestinal stromal tumor images is ensured. In actual operation, a doctor can obtain more comprehensive diagnosis information through the function and simultaneously observe and analyze the ultrasonic contrast and the gastrointestinal stromal tumor image by computer tomography. The visualization module also provides a multi-view observation function, and a doctor can rotate and zoom the three-dimensional reconstructed image to view the morphological and positional changes of the gastrointestinal stromal tumor in detail from different angles.
The invention collects the image data of the gastrointestinal stromal tumor from the ultrasonic equipment and the computer tomography equipment through the endogenous collection module, carries out pretreatment on the image data through the doctor source refining module so as to facilitate the subsequent analysis and fusion, manages structured and unstructured data through the doctor source repository module by using the mixed storage architecture, supports the management and access of large-scale data, fuses the heterogeneous data from different data sources in time and space dimensions through the doctor source fusion module to generate a unified patient view, recognizes and partitions the gastrointestinal stromal tumor area through the doctor source recognition module, generates quantitative analysis data, carries out three-dimensional reconstruction through the visualization module, displays the fused image data, supports the time synchronization playing function, facilitates the visual observation of analysis results by doctors, enables the doctors to efficiently manage and access the large-scale structured and unstructured data, and has the three-dimensional reconstruction and time synchronization playing function so that the doctors can intuitively observe the focus condition, and the heterogeneous data from various medical equipment are fused to generate the unified patient view.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally, the foregoing description of the preferred embodiment of the invention is provided for the purpose of illustration only, and is not intended to limit the invention to the particular form disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

Claims (3)

1. A medical data converging system based on multi-data source isomerism comprises an endogenous acquisition module, an iatrogenic refining module, an iatrogenic repository module, an iatrogenic fusion module, an iatrogenic research identification module, a visualization module and a safety protection module, and is characterized in that the endogenous acquisition module acquires ultrasonic contrast gastrointestinal stromal tumor image data and computer tomography gastrointestinal stromal tumor image data from ultrasonic equipment and computer tomography scanning equipment, the iatrogenic refining module performs image preprocessing on the acquired ultrasonic contrast gastrointestinal stromal tumor image data and computer tomography gastrointestinal stromal tumor image data, the iatrogenic fusion module comprises a time dimension fusion unit and a space dimension fusion unit, the time dimension fusion unit performs sequence fusion on ultrasonic contrast gastrointestinal stromal tumor images and computer tomography gastrointestinal stromal tumor images acquired in a patient examination period, builds a time sequence minimum accumulation distance model, and measures a first time sequenceAnd a second time sequenceThe similarity between the two is calculated by the formula of a time sequence minimum accumulated distance model:
,
Wherein: for the value of the minimum cumulative distance, For the first time seriesAnd a second time sequenceAn optimal path aligned between, a first time series,Is a time sequenceIs selected from the group consisting of a first element,For the first time seriesIs selected from the group consisting of a first element,For the first time seriesThe first of (3)Element, second time series,For a second time seriesIs selected from the group consisting of a first element,For a second time seriesIs selected from the group consisting of a first element,For a second time seriesThe first of (3)The number of elements to be added to the composition,Is a time sequenceTime point of middleIs used for the indexing of (a),Is a time sequenceTime point of middleIs used for the indexing of (a),To be from time seriesFrom the start point to the point of (2)And from a time seriesFrom the start point to the point of (2)Is used for the minimum cumulative distance of (a),Is the optimal pathThrough the minimum cumulative distance value of the two time series of outputsMeasuring a first time seriesAnd a second time sequenceSimilarity between the two, if the minimum accumulated distance value is lower than the preset distance value, adopting a pixel level fusion technology to carry out first time sequenceAnd a second time sequenceFusing;
The medical source fusion module comprises a time dimension fusion unit and a space dimension fusion unit, wherein the space dimension fusion unit fuses an ultrasonic contrast gastrointestinal stromal tumor image and a computed tomography gastrointestinal stromal tumor image under the same space coordinate system, and the specific steps are as follows:
Step Y1, establishing a transformation model from an ultrasonic contrast gastrointestinal stromal tumor image coordinate system to a computer tomography gastrointestinal stromal tumor image coordinate system, wherein the transformation model has the formula:
,
Wherein: For ultrasound contrast of point coordinates in images of gastrointestinal stromal tumors, For the point coordinates in the corresponding ultrasound contrast gastrointestinal stromal tumor image in the computed tomography gastrointestinal stromal tumor image,For rotation of the matrix, a rotation of the ultrasound contrast gastrointestinal stromal tumor image relative to the computed tomography gastrointestinal stromal tumor image is described,Describing the translation of the ultrasound contrast gastrointestinal stromal tumor image relative to the computed tomography gastrointestinal stromal tumor image as a translation vector;
Step Y2, an optimal model of optimal transformation parameters is established, and the formula of the model is as follows:
,
Wherein: for an optimal rotation matrix, For the optimal translation vector to be present,In order to measure the parameter value of the similarity between the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image, when the parameter value is in the preset parameter value range, the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image are fused;
Step Y3, establishing a model after the ultrasonic contrast gastrointestinal stromal tumor image and the computed tomography gastrointestinal stromal tumor image are fused, wherein the model formula is as follows:
,
Wherein: In order to obtain the image after the fusion, As a result of the weighting factor(s),For ultrasound contrast of images of gastrointestinal stromal tumors,Gastrointestinal stromal tumor images were scanned for computer tomography.
2. The medical data aggregation system based on multiple data sources isomerism according to claim 1, wherein the endogenous acquisition module is connected with the medical source refining module, the medical source refining module is connected with the medical source repository module, the medical source repository module is connected with the medical source fusion module, the time dimension unit and the space dimension fusion unit are respectively connected with the medical source fusion module, the medical source fusion module is connected with the medical research analysis module, the medical research identification module is connected with the visualization module, and the visualization module is connected with the safety protection module.
3. The multi-data source heterogeneous based medical data aggregation system of claim 1, wherein the medical repository module stores multi-source heterogeneous data, wherein the multi-source heterogeneous data refers to ultrasound contrast gastrointestinal stromal tumor image data, computed tomography gastrointestinal stromal tumor image data, patient information and examination results, supports management and access of large-scale data, stores structured data and unstructured data, the structured data is patient information and examination results, the unstructured data is ultrasound contrast and computed tomography gastrointestinal stromal tumor image data, and stores the structured data with relational databases and stores the unstructured data according to different data type requirements by adopting a hybrid storage architecture.
CN202411545820.9A 2024-11-01 2024-11-01 A medical data aggregation system based on heterogeneous multiple data sources Active CN119069086B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411545820.9A CN119069086B (en) 2024-11-01 2024-11-01 A medical data aggregation system based on heterogeneous multiple data sources

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411545820.9A CN119069086B (en) 2024-11-01 2024-11-01 A medical data aggregation system based on heterogeneous multiple data sources

Publications (2)

Publication Number Publication Date
CN119069086A CN119069086A (en) 2024-12-03
CN119069086B true CN119069086B (en) 2025-02-28

Family

ID=93632228

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411545820.9A Active CN119069086B (en) 2024-11-01 2024-11-01 A medical data aggregation system based on heterogeneous multiple data sources

Country Status (1)

Country Link
CN (1) CN119069086B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116778236A (en) * 2023-06-13 2023-09-19 广州市第一人民医院（广州消化疾病中心、广州医科大学附属市一人民医院、华南理工大学附属第二医院） Multi-classification method, device and storage medium for breast cancer images
CN117635616A (en) * 2024-01-26 2024-03-01 江西科技学院 Image diagnosis system for mutual recognition of medical examination results

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005111932A2 (en) * 2004-05-14 2005-11-24 Philips Intellectual Property & Standards Gmbh Information enhanced image guided interventions
US10157462B2 (en) * 2016-06-27 2018-12-18 University Of Central Florida Research Foundation, Inc. System and method for image-based quantification of white and brown adipose tissue at the whole-body, organ and body-region levels
GB201709672D0 (en) * 2017-06-16 2017-08-02 Ucl Business Plc A system and computer-implemented method for segmenting an image
US11665330B2 (en) * 2021-01-27 2023-05-30 Dell Products L.P. Dynamic-baseline imaging array with real-time spatial data capture and fusion
CN118197627A (en) * 2024-03-29 2024-06-14 天津工业大学 Gastrointestinal stromal tumor risk level prediction method based on CT (computed tomography) section attention transducer
CN118196074B (en) * 2024-04-16 2024-10-22 山东佰泰丰信息科技有限公司 Medical ultrasonic image quality control system based on multi-mode fusion
CN118629612A (en) * 2024-05-29 2024-09-10 浙江大学医学院附属邵逸夫医院 Cardiac rehabilitation equipment control method based on multi-data fusion
CN118537648A (en) * 2024-05-31 2024-08-23 北京凯普顿医药科技开发有限公司 Medical image identification method and medical image identification device
CN118691863A (en) * 2024-07-25 2024-09-24 贵州大学 An unsupervised feature extraction and clustering method for multi-view data

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116778236A (en) * 2023-06-13 2023-09-19 广州市第一人民医院（广州消化疾病中心、广州医科大学附属市一人民医院、华南理工大学附属第二医院） Multi-classification method, device and storage medium for breast cancer images
CN117635616A (en) * 2024-01-26 2024-03-01 江西科技学院 Image diagnosis system for mutual recognition of medical examination results

Also Published As

Publication number Publication date
CN119069086A (en) 2024-12-03

Similar Documents

Publication Publication Date Title
CN101336844B (en) Medical image processing apparatus and medical image diagnosis apparatus
US8150113B2 (en) Method for lung lesion location identification
KR101503940B1 (en) Tools for aiding in the diagnosis of neurodegenerative diseases
US8630467B2 (en) Diagnosis assisting system using three dimensional image data, computer readable recording medium having a related diagnosis assisting program recorded thereon, and related diagnosis assisting method
CN109830289B (en) Rib image display device
EP2059165B1 (en) Detection and localization of vascular occlusion from angiography data
CN111227864A (en) Method and apparatus for lesion detection using ultrasound image using computer vision
CN103462646B (en) Integrated IVUS (intravascular ultrasound) image and DSA (digital subtraction angiography) image integrating offline-treatment system
Giancardo et al. Textureless macula swelling detection with multiple retinal fundus images
CN106204733A (en) Liver and the three-dimensional constructing system of kidney CT image associating
CN103462590B (en) Integrated intravascular OCT (optical coherence tomography) image and DSA (digital subtraction angiography) integrating offline treatment system
CN103462696B (en) An integrated online real-time processor integrating intravascular optical coherence tomography (OCT) images and digital subtraction (DSA) images
CN109498046A (en) The myocardial infarction quantitative evaluating method merged based on nucleic image with CT coronary angiography
JP2014064824A (en) Shortest route searching device, method and program of tubular structure
CN112603368A (en) Mammary gland ultrasonic navigation and diagnosis system and method
CN116580819B (en) Method and system for automatically determining inspection results in an image sequence
Sakellarios et al. Novel methodology for 3D reconstruction of carotid arteries and plaque characterization based upon magnetic resonance imaging carotid angiography data
Dong et al. A novel end‐to‐end deep learning solution for coronary artery segmentation from CCTA
CN117132837A (en) Vascular image target detection method and device
CN111563876A (en) Medical image acquisition method and display method
CN100559397C (en) Method and system for affine registration of two-dimensional images during surgery and three-dimensional images before surgery
CN119069086B (en) A medical data aggregation system based on heterogeneous multiple data sources
CN111563877A (en) Medical image generation method and device, display method and storage medium
Fujita et al. State-of-the-art of computer-aided detection/diagnosis (CAD)
Ünay et al. Model-free automatic segmentation of the aortic valve in multislice computed tomography images

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant