CN116597988A - Intelligent hospital operation method and system based on medical information - Google Patents
Intelligent hospital operation method and system based on medical information Download PDFInfo
- Publication number
- CN116597988A CN116597988A CN202310881806.5A CN202310881806A CN116597988A CN 116597988 A CN116597988 A CN 116597988A CN 202310881806 A CN202310881806 A CN 202310881806A CN 116597988 A CN116597988 A CN 116597988A
- Authority
- CN
- China
- Prior art keywords
- image
- organ
- images
- frame difference
- disease
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 210000000056 organ Anatomy 0.000 claims abstract description 222
- 201000010099 disease Diseases 0.000 claims abstract description 137
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 137
- 238000001914 filtration Methods 0.000 claims abstract description 59
- 230000004927 fusion Effects 0.000 claims abstract description 48
- 230000007170 pathology Effects 0.000 claims abstract description 45
- 238000012216 screening Methods 0.000 claims abstract description 9
- 230000001575 pathological effect Effects 0.000 claims abstract description 7
- 230000009466 transformation Effects 0.000 claims description 24
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 11
- 238000011017 operating method Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012552 review Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 description 10
- 238000003745 diagnosis Methods 0.000 description 7
- 238000007689 inspection Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 210000004072 lung Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
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
- 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
- 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
- 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
- G06V10/40—Extraction of image or video features
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- 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
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- 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
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Radiology & Medical Imaging (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Pathology (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application relates to a medical information-based intelligent hospital operation method and system, wherein the method comprises the following steps: constructing a physiological organ reference map and a plurality of organ disease seed image sets; calculating a frame difference image of the organ disease seed image set and a physiological organ reference image to obtain an organ disease seed frame difference image set; all images in the organ disease seed frame difference image set are overlapped and then filtered to obtain a frame difference filtering overlapped image set; discrete cosine transform is carried out on the frame difference filtering superposition image set, and screening is carried out to construct an organ pathology feature map; carrying out image fusion on the organ pathology feature map to obtain an organ pathology fusion feature map; and calculating the similarity between the medical image of the patient and the pathological fusion feature map to obtain the disease probability of the target organ of the patient. The method and the device improve the accuracy of identifying the probability of various diseases of the organ of the patient through the medical image, thereby assisting in improving the treatment effect and the medical experience of the patient.
Description
Technical Field
The present application relates generally to the field of digital medical, and more particularly, to a medical information-based intelligent hospital operation method and system.
Background
With the development of technology, hospitals are increasingly introducing more medical devices to assist diagnosis, however, the existing medical image inspection system (PACS) generally only performs conventional management on the inspection image of the patient, such as electronic archiving the image, uploading the electronic medical record, simply labeling the inspection image of the patient, and the like, but does not directly diagnose the inspection image of the patient.
Many patients need to return to the doctor's office for re-diagnosis after obtaining the medical image to acquire specific diagnosis information, which leads to great workload of doctor's reading, and the working time is difficult to reasonably distribute, and meanwhile, the patients need to spend more time queuing for visiting to communicate with the doctor, which also leads to serious daily personnel load of the hospital.
In the prior art, a patient can acquire a diagnosis result while acquiring a medical image by automatically diagnosing the medical image of the patient. In the chinese patent application with publication number CN114224369a and application name of a medical image automatic diagnosis system, a medical image automatic diagnosis system is provided, which can automatically diagnose medical images, save time of patients, provide reference for doctors, and accelerate treatment progress.
However, the scheme mainly constructs text feature vectors by acquiring descriptive information keywords of diseases, and then compares X-ray films of patients with X-ray films corresponding to various diseases prestored in a system, and judges the diseases of the patients by matching with a preset threshold value. This approach does not fully exploit the image features of the medical image while not taking into account the noise carried in the large number of different medical image data, resulting in an inaccurate diagnostic result.
Disclosure of Invention
In order to solve one or more of the technical problems, the application provides an intelligent hospital operation method and system based on medical information, which can automatically diagnose medical images of patients in the patient treatment process, provide accurate and reliable diagnosis results for the patients as references and improve the patient treatment experience. To this end, the present application provides solutions in various aspects as follows.
In a first aspect, the present application provides a medical information-based intelligent hospital operation method, including: collecting a plurality of historical medical images of a target organ to construct a physiological organ reference image and a plurality of organ disease seed image sets, wherein the organ disease seed image sets are in one-to-one correspondence with disease seeds of the target organ; after preprocessing the organ disease seed image set, calculating a frame difference image of each image in the organ disease seed image set and the physiological organ reference image to obtain an organ disease seed frame difference image set; superposing all images in the organ disease seed frame difference image set, and then filtering to obtain a frame difference filtering superposition image set; performing discrete cosine transform on each image in the frame difference filtering superimposed image set in sequence to obtain discrete cosine transform coefficients, wherein the discrete cosine transform coefficients comprise direct current coefficients and alternating current coefficients, screening the alternating current coefficients based on the frame difference filtering superimposed image set to obtain effective alternating current coefficients, and constructing an organ pathological feature map according to the direct current coefficients and the effective alternating current coefficients, wherein the organ pathological feature map corresponds to the images in the frame difference filtering superimposed image set one by one; image fusion is carried out on all organ pathology feature images to obtain organ pathology fusion feature images, and all organ disease image sets are traversed to obtain pathology fusion feature images corresponding to each organ disease image set; the method comprises the steps of collecting medical images of target organs of a patient in real time, sequentially calculating the similarity between the medical images of the patient and each pathology fusion feature map to obtain the disease probability of each disease on the target organs of the patient, and displaying the disease probability on the medical images of the target organs for the patient and doctors to review.
The beneficial effects are that: according to the intelligent hospital operation method based on the medical information, provided by the embodiment of the application, the organ disease type frame difference image sets of different disease types are obtained by constructing the physiological organ reference image when the function of the target organ is normal and the organ disease type image sets of different disease types, denoising of the organ disease type frame difference image sets and screening of alternating coefficients by wavelet transformation are realized by superposing all images in the organ disease type frame difference image sets, and the accuracy of the obtained pathology fusion feature image is improved, so that the disease probability of the target organ of a patient on each disease type can be obtained more accurately according to the medical image, and the treatment effect and the medical experience of a patient in real time are improved in an auxiliary manner.
In one embodiment, the acquiring a plurality of historical medical images of the target organ to construct a physiological organ reference map and a plurality of organ disease seed image sets comprises: collecting a plurality of historical medical images of the target organ when the function of the target organ is normal and a plurality of historical medical images of the target organ under different disease types; converting all the historical medical images of the target organ when the function is normal into gray images, and calculating average gray images of all the gray images;
carrying out affine transformation on all gray level images by taking the average gray level image as a template, and carrying out image fusion on all affine transformed images to obtain a physiological organ reference image; dividing a plurality of historical medical images of a target organ under different disease types according to the disease types to obtain a plurality of organ disease type image sets, wherein the organ disease type image sets are in one-to-one correspondence with the disease types of the target organ.
The beneficial effects are that: all the historical medical images of the target organ in normal function can be identical as far as possible through affine transformation, so that the image fusion can be conveniently carried out to obtain a more accurate and universal physiological organ reference image.
In one embodiment, after the preprocessing the set of organ disease seed images, calculating a set of organ disease seed frame difference images for each image in the set of organ disease seed images and the frame difference image of the physiological organ reference map comprises: cutting the images in the organ disease image set into uniform sizes by taking the physiological organ reference image as a template, and carrying out affine transformation on each image in the organ disease image set; and sequentially calculating the frame difference images of each image subjected to affine transformation in the organ disease seed image set and the physiological organ reference image, and taking all the frame difference images as an organ disease seed frame difference image set.
The beneficial effects are that: the image concentrated by the organ disease seed image is affine transformed by taking the physiological organ reference image as a template, so that the organ disease seed image is concentrated to be closer to the physiological organ reference image, thereby obtaining a more accurate organ disease seed frame difference image, and being beneficial to more accurately obtaining the difference characteristic between the organ disease seed image and the physiological organ reference image.
In one embodiment, the step of overlaying all the images in the organ disease seed frame difference image set and then filtering to obtain a frame difference filtered overlaid image set includes: superposing all images in the organ disease seed frame difference image set to obtain a plurality of pixel gray sequences, wherein the pixel gray sequences comprise the number of pixels consistent with the number of the images in the organ disease seed frame difference image set; denoising all pixel gray sequences according to wavelet transformation, filtering pixels belonging to noise in the pixel gray sequences, and taking the organ disease seed frame difference image set after superposition and denoising as a frame difference filtering superposition image set.
The beneficial effects are that: because all images in the organ disease type frame difference image set reflect the image characteristics of the same organ under the same disease type, the whole images are similar, and the error influence caused by noise pixels can be reduced by denoising the pixel gray scale sequences at the same position.
In one embodiment, the sequentially performing discrete cosine transform on each image in the set of frame difference filtered superimposed images to obtain discrete cosine transform coefficients includes: dividing each image in the frame difference filtering superposition image set into a plurality of image blocks with the same quantity in sequence; and performing discrete cosine transform on each image block to obtain a discrete cosine transform coefficient corresponding to the image block, wherein the discrete cosine transform coefficient comprises a plurality of alternating current coefficients for representing image detail texture information.
The beneficial effects are that: the images in the frame difference filtering superimposed image set are divided into a plurality of image blocks through discrete cosine transform, so that discrete cosine transform coefficients of the image blocks are obtained, each image block can be used as a basic unit for screening image texture details in the frame difference filtering superimposed image set in the subsequent process, and important image texture features are reserved.
In one embodiment, the filtering the ac coefficient based on the frame difference filtered superimposed image set to obtain an effective ac coefficient includes: counting the total number of pixel points contained in all pixel gray sequences corresponding to a target image block as the total number of pixels of the image block sequence, wherein the target image block is any one image block in the frame difference filtering superposition image set; counting the total number of pixel points reserved after noise elimination of all pixel gray sequences corresponding to the target image block as the total number of filtering pixels of the image block; calculating the ratio of the total amount of the image block filtering pixels to the total amount of the image block sequence pixels; counting the total amount of the alternating current coefficient number corresponding to the target image block, calculating the product of the total amount of the alternating current coefficient number and the ratio, and rounding up the product to obtain a rounding reserved value; sorting the alternating current coefficients corresponding to the target image blocks according to the order from high to low, and reserving the alternating current coefficients with the same number as the rounding reserved value in the alternating current coefficients with the front sorting as effective alternating current coefficients; and traversing all image blocks in the frame difference filtering superposition image set to obtain the effective alternating current coefficient corresponding to each image block.
In one embodiment, said constructing an organ pathology feature map from said direct current coefficients and effective alternating current coefficients comprises: performing inverse discrete cosine transform on a direct current coefficient and an effective alternating current coefficient corresponding to each image block of a target image to obtain an organ pathology feature map corresponding to the target image, wherein the target image is any image in the frame difference filtering superposition image set; and traversing all images in the frame difference filtering superposition image set to obtain an organ pathology feature map corresponding to each image.
The beneficial effects are that: the alternating current coefficients of all image blocks in the frame difference filtering superimposed image set can be screened through the number of pixel points reserved by the gray level sequences of all pixels after wavelet transformation denoising, so that more accurate and reliable effective alternating current coefficients are obtained, unnecessary alternating current coefficients are filtered, and organ pathology feature images corresponding to all images in the frame difference filtering superimposed image set are reconstructed by utilizing the direct current coefficients which are obtained by combining the effective alternating current coefficients obtained by filtering all the image blocks, so that main organ pathology features in all the images are highlighted, the accuracy of the organ pathology feature images is maintained, and meanwhile, the acquisition efficiency is improved.
In one embodiment, the image fusion of all organ pathology feature maps to obtain an organ pathology fusion feature map includes: counting the number of the reserved pixels of all the image blocks at the same position in the frame difference filtering superposition image set; normalizing the number of the reserved pixels of all the image blocks at the same position to obtain fusion weights of the corresponding image blocks; and carrying out image fusion on all the image blocks at the same position based on the fusion weight to obtain an organ pathology fusion characteristic diagram.
The beneficial effects are that: the fusion weight of the corresponding image blocks can be constructed by utilizing the number of the pixels of the image blocks which are reserved at the same positions in the frame difference filtering superposition image set, so that a more accurate and effective organ pathology fusion characteristic diagram is obtained.
In one embodiment, the acquiring the medical image of the target organ of the patient in real time, and sequentially calculating the similarity between the medical image of the patient and each pathology fusion feature map to obtain the disease probability of each disease on the target organ of the patient includes: collecting a target organ medical image of a patient in real time and preprocessing the target organ medical image; and sequentially calculating the similarity of the preprocessed target organ medical image and each pathology fusion feature map according to a template matching algorithm, and taking the similarity as the disease probability of the corresponding disease on the target organ of the patient.
The beneficial effects are that: when a patient obtains medical images, the probability of the target organ of the patient to be ill for each disease can be provided for the patient at the first time, and the treatment effect and the hospitalizing experience of the patient in real time are improved in an auxiliary mode.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the application are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a flow chart of a method of intelligent hospital operation based on medical information in accordance with an embodiment of the present application;
fig. 2 is an exemplary diagram of a target organ provided in accordance with an embodiment of the present application.
Fig. 3 is a schematic diagram of a structure of a frame difference filtering superimposed image set according to an embodiment of the present application.
Fig. 4 is a schematic block diagram of a medical information-based intelligent hospital operating system according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be understood that when the terms "first," "second," and the like are used in the claims, the specification and the drawings of the present application, they are used merely for distinguishing between different objects and not for describing a particular sequential order. The terms "comprises" and "comprising" when used in the specification and claims of the present application are taken to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
According to a first aspect of the application, the application provides a medical information-based intelligent hospital operating method. Referring to fig. 1, a flowchart of an intelligent hospital operation method based on medical information according to a preferred embodiment of the present application is shown. The order of the steps in the flow diagrams may be changed, and some steps may be omitted, according to different needs.
S11, collecting a plurality of historical medical images of a target organ to construct a physiological organ reference image and a plurality of organ disease type image sets, wherein the organ disease type image sets are in one-to-one correspondence with disease types of the target organ.
In one embodiment, the lesion position of a certain part of the human body under the same disease type is generally fixed, so that a plurality of historical medical images of the target organ under normal function and a plurality of historical medical images of the target organ under different disease types can be acquired, wherein the target organ can be any organ in the human body which can be recorded by the medical images, and an example of the target organ can be a lung organ as shown in fig. 1, and the plurality of historical medical images can be 100 lung organs as shown in fig. 2, and the example of the target organ under different states is shown in the different states.
Firstly, all the historical medical images when the target organ is normal in function are converted into gray images, and average gray images corresponding to all the gray images are calculated. And then carrying out affine transformation on all other gray images in sequence by taking the average gray image as a template, so that the gray image can be aligned with the average gray image as much as possible, and then carrying out image fusion on all affine transformed images to obtain the physiological organ reference image.
Because the same target organ generally corresponds to a plurality of different disease types, image acquisition can be carried out on each typical disease type of the target organ, and the acquired historical medical images are divided into a plurality of organ disease type image sets according to different disease types, wherein the images in each organ disease type image set are medical images acquired on the same disease type of the same target organ.
Therefore, through affine transformation, all the historical medical images of the target organ in normal functions can be identical as far as possible, so that the image fusion can be conveniently carried out to obtain a more accurate and universal physiological organ reference image.
S12, after preprocessing the organ disease seed image set, calculating a frame difference image of each image in the organ disease seed image set and the physiological organ reference image to obtain an organ disease seed frame difference image set.
In one embodiment, the preprocessing is as follows: and cutting the images in the organ disease image set into uniform sizes by taking the physiological organ reference image as a template, and carrying out affine transformation on each image in the organ disease image set.
In this alternative embodiment, the frame difference map of each image of the organ disease seed image set after affine transformation and the physiological organ reference map is calculated in sequence, and all obtained frame difference maps are used as the organ disease seed frame difference image set.
Therefore, the image concentrated by the organ disease seed image is affine transformed by taking the physiological organ reference image as a template, so that the image concentrated by the organ disease seed image is more similar to the physiological organ reference image, thereby obtaining a more accurate organ disease seed frame difference image, and being beneficial to more accurately obtaining the difference characteristic between the organ disease seed image and the physiological organ reference image.
S13, overlapping all images in the organ disease seed frame difference image set, and then filtering to obtain a frame difference filtering overlapping image set.
In one embodiment, all images in the set of organ seed frame difference images are superimposed together so that at any pixel location there is a column of pixel gray sequences containing a number of pixels consistent with the number of images in the set of organ seed frame difference images.
For example, as shown in fig. 3, assuming that the number of images in the organ disease seed frame difference image set is n=100, all the superimposed images have 100 layers, that is, each column of pixel gray-scale sequences has 100 pixels, such as A1, A2, A3.
In one embodiment, all the pixel gray sequences can be denoised according to wavelet transformation, so that pixels belonging to noise in the pixel gray sequences are filtered, and the organ disease seed frame difference image set after superposition and denoising is used as a frame difference filtering superposition image set.
The method comprises the steps of firstly carrying out wavelet transformation on a pixel gray level sequence to obtain a transformation processing result, then comprehensively analyzing and setting a preset threshold value, and further eliminating the result which does not meet the threshold value in the transformation processing result through the threshold value, thereby obtaining a screening result.
For example, the noise interference factor in the pixel gray sequence data may be removed by wavelet threshold denoising, and the noise interference existing in the pixel gray sequence data may be removed by threshold denoising, so that only the peak point of the pixel gray sequence data center is reserved.
And then carrying out wavelet inverse transformation on the screening result to finally obtain a pixel gray sequence subjected to noise reduction treatment, and taking the organ disease seed frame difference image set subjected to superposition and denoising as a frame difference filtering superposition image set in the scheme after denoising all the pixel gray sequences.
For example, AN is a column of pixel gray sequences, n=100, and A1, A6, A8, A9 are filtered out as noise after wavelet transform denoising, so 96 pixels are also reserved in the column of pixel gray sequences.
Therefore, all the images in the organ disease frame difference image set reflect the image characteristics of the same organ under the same disease, so that the images are similar in whole, and the error influence caused by noise pixels can be reduced by denoising the pixel gray scale sequences at the same position.
S14, carrying out discrete cosine transform on each image in the frame difference filtering superposition image set in sequence to obtain discrete cosine transform coefficients, wherein the discrete cosine transform coefficients comprise direct current coefficients and alternating current coefficients, screening the alternating current coefficients based on the frame difference filtering superposition image set to obtain effective alternating current coefficients, and constructing an organ pathology feature map according to the direct current coefficients and the effective alternating current coefficients, wherein the organ pathology feature map corresponds to the images in the frame difference filtering superposition image set one by one.
In one embodiment, in the discrete cosine transforming step, each image in the frame difference filtered superimposed image set is first divided into a plurality of image blocks of the same number in sequence, and the size of the image blocks may be 88。
And then, performing discrete cosine transform on each image block to obtain a discrete cosine transform coefficient corresponding to each image block. Wherein the discrete cosine transform coefficients comprise a DC coefficient related to the image base tone and a plurality of AC coefficients related to the image detail texture information.
That is, the image can be converted from the spatial domain to the frequency domain by Discrete Cosine Transform (DCT) of the image, and coefficients outputted by the DCT are divided into direct current coefficients and alternating current coefficients. The direct current coefficient represents the intensity of low-frequency components in the whole image, and the alternating current coefficient represents the intensity and direction of high-frequency components, so that the direct current coefficient can be used for extracting detailed information of the image.
In one embodiment, many high frequency ac coefficients can be set to 0 directly because the information carried is not important, and in the prior art, a threshold is typically set manually to screen the high frequency ac coefficients. In the scheme, the number of pixels in a pixel gray sequence where each pixel in each image block corresponds to discrete cosine transform is combined to determine, because noise pixel points in the gray sequence are removed after wavelet transform, the remaining effective pixel points are all reserved, the more the number reserved in the same pixel gray sequence is, the more stable and effective the gray value of the current pixel is represented, and similarly, for one image block, the more the number of the reserved pixels in the pixel gray sequence where the pixel points are contained is, the less disturbance the image block is, the more important the disturbance the image block is, and the higher the confidence is.
Therefore, the total number of pixel points contained in all pixel gray sequences corresponding to the target image block can be counted as the total number of pixels of the image block sequence, wherein the target image block is any one image block in the frame difference filtering superposition image set; and simultaneously counting the total number of pixel points reserved after noise elimination of all pixel gray sequences corresponding to the target image block as the total number of filtered pixels of the image block.
And then calculating the ratio of the total quantity of the filtered pixels of the image block to the total quantity of the pixels of the sequence of the image block, counting the total quantity of the alternating current coefficients corresponding to the target image block, then calculating the product of the total quantity of the alternating current coefficients and the ratio, rounding up the product to obtain a rounding reserved value, sorting the alternating current coefficients corresponding to the target image block according to the order from high to low, reserving the alternating current coefficients with the quantity equal to the rounding reserved value in the alternating current coefficients with the front sorting as effective alternating current coefficients, and traversing all the image blocks in the frame difference filtering superposition image set to obtain the effective alternating current coefficient corresponding to each image block.
Exemplary, one 8The target image block C of 8 comprises 64 pixels, the number of the pixels in the pixel gray level sequence of each pixel is 100, so that the target image block C totally corresponds to 6400 pixels as the total number of the pixels of the image block sequence, wherein 5500 pixels in the pixel gray level sequence correspondingly remained after wavelet transformation denoising are taken as the total number of image block filtering pixels, the ratio of the total number of the image block filtering pixels to the total number of the image block sequence pixels is 5500/6400=55/64, and the total number of the alternating current coefficients corresponding to the target image block C is 93, according to the calculation formula%>80, so that the high frequency coefficients finally remain 80. Then for the 93 AC coefficientsThe ranking is performed in order of high to low, and finally only the first 80 top ranked ac coefficients are reserved as final effective ac coefficients.
Because the discrete cosine transform is a reversible transform, the forward and reverse transforms can be mutually transformed, so that the inverse discrete cosine transform can be carried out on the direct current coefficient and the effective alternating current coefficient corresponding to each image block of the target image, and the image obtained after the inverse transform is used as an organ pathological feature map corresponding to each image.
Therefore, the alternating current coefficients of all image blocks in the frame difference filtering superimposed image set can be screened according to the number of pixel points reserved in each pixel gray sequence after wavelet transformation denoising, so that more accurate and reliable effective alternating current coefficients are obtained, unnecessary alternating current coefficients are filtered, and organ pathology feature images corresponding to all images in the frame difference filtering superimposed image set are reconstructed by utilizing the direct current coefficients which are obtained by combining the effective alternating current coefficients obtained by filtering all the image blocks, so that main organ pathology features in all the images are highlighted, the accuracy of the organ pathology feature images is maintained, and meanwhile, the acquisition efficiency is improved.
S15, carrying out image fusion on all organ pathology feature images to obtain organ pathology fusion feature images, and traversing all organ disease image sets to obtain pathology fusion feature images corresponding to each organ disease image set.
In one embodiment, since the number of pixels reserved for each image block at the same position but belonging to different images is not consistent, the number of pixels reserved for all image blocks at the same position in the frame difference filtering superposition image set can be counted, then the number of pixels reserved for all image blocks at the same position is normalized to be used as a fusion weight of the corresponding image blocks, and finally, image fusion can be performed on all image blocks at the same position based on the fusion weight to obtain an organ pathology fusion feature map.
Therefore, the fusion weight of the corresponding image blocks can be constructed by utilizing the number of the pixels of the image blocks which are reserved at the same positions in the frame difference filtering superposition image set, so that a more accurate and effective organ pathology fusion characteristic diagram is obtained.
S16, acquiring medical images of target organs of a patient in real time, sequentially calculating the similarity between the medical images of the patient and each pathology fusion feature map to obtain the disease probability of each disease on the target organs of the patient, and displaying the disease probability on the medical images of the target organs for the patient and doctors to review.
In one embodiment, the medical image of the target organ of the patient can be acquired in real time and preprocessed, then the similarity between the preprocessed medical image of the target organ and each pathology fusion feature map is sequentially calculated according to a template matching algorithm, and finally the similarity is used as the disease probability of the corresponding disease on the target organ of the patient.
The template matching algorithm may be an average absolute difference algorithm (MAD), an absolute error Sum Algorithm (SAD), an error square sum algorithm (SSD), an average error square sum algorithm (MSD), a normalized product correlation algorithm (NCC), a Sequential Similarity Detection Algorithm (SSDA), a hadamard transformation algorithm (SATD), and the like.
Finally, through calculating the similarity between the medical image of the target organ and each pathological fusion feature map, the probability value of different disease types of the examination image of the real-time patient can be obtained and displayed on the medical image for the patient and doctor to review, so that the patient can master the health degree of the target organ at the first time, and the treatment effect and the hospitalizing experience of the real-time patient are improved in an auxiliary manner.
Therefore, when the patient obtains the medical image, the probability of the target organ of the patient on each disease type can be provided for the patient at the first time, and the treatment effect and the medical experience of the patient in real time are improved in an auxiliary mode.
According to the intelligent hospital operation method based on the medical information, provided by the embodiment of the application, the organ disease type frame difference image sets of different disease types are obtained by constructing the physiological organ reference image when the function of the target organ is normal and the organ disease type image sets of different disease types, denoising of the organ disease type frame difference image sets and screening of alternating coefficients by wavelet transformation are realized by superposing all images in the organ disease type frame difference image sets, and the accuracy of the obtained pathology fusion feature image is improved, so that the disease probability of the target organ of a patient on each disease type can be obtained more accurately according to the medical image, and the treatment effect and the medical experience of a patient in real time are improved in an auxiliary manner.
According to a second aspect of the present application, there is also provided a medical information-based intelligent hospital operating system comprising a memory and a processor, the memory having stored thereon computer executable instructions which, when executed by the processor, implement a medical information-based intelligent hospital operating method according to the first aspect of the present application.
Fig. 4 is a schematic frame diagram of a medical information-based intelligent hospital operation method and system according to an embodiment of the present application. The apparatus 40 comprises a processor and a memory storing computer program instructions which, when executed by the processor, implement a medical information based intelligent hospital operating method according to the first aspect of the present application. The device also includes other components, such as a communication bus and a communication interface, which are well known to those skilled in the art, and the arrangement and function of which are known in the art and therefore not described in detail herein.
In the context of this patent document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, the computer readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistance change Memory RRAM (Resistive Random Access Memory), dynamic Random Access Memory DRAM (Dynamic Random Access Memory), static Random Access Memory SRAM (Static Random-Access Memory), enhanced dynamic Random Access Memory EDRAM (Enhanced Dynamic Random Access Memory), high-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid storage cube HMC (Hybrid Memory Cube), etc., or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer storage media may be part of, or accessible by, or connectable to, the device. Any of the applications or modules described herein may be implemented using computer-readable/executable instructions that may be stored or otherwise maintained by such computer-readable media.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. An intelligent hospital operation method based on medical information is characterized in that:
collecting a plurality of historical medical images of a target organ to construct a physiological organ reference image and a plurality of organ disease seed image sets, wherein the organ disease seed image sets are in one-to-one correspondence with disease seeds of the target organ;
after preprocessing the organ disease seed image set, calculating a frame difference image of each image in the organ disease seed image set and the physiological organ reference image to obtain an organ disease seed frame difference image set;
superposing all images in the organ disease seed frame difference image set, and then filtering to obtain a frame difference filtering superposition image set;
performing discrete cosine transform on each image in the frame difference filtering superimposed image set in sequence to obtain discrete cosine transform coefficients, wherein the discrete cosine transform coefficients comprise direct current coefficients and alternating current coefficients, screening the alternating current coefficients based on the frame difference filtering superimposed image set to obtain effective alternating current coefficients, and constructing an organ pathological feature map according to the direct current coefficients and the effective alternating current coefficients, wherein the organ pathological feature map corresponds to the images in the frame difference filtering superimposed image set one by one;
image fusion is carried out on all organ pathology feature images to obtain organ pathology fusion feature images, and all organ disease image sets are traversed to obtain pathology fusion feature images corresponding to each organ disease image set;
the method comprises the steps of collecting medical images of target organs of a patient in real time, sequentially calculating the similarity between the medical images of the patient and each pathology fusion feature map to obtain the disease probability of each disease on the target organs of the patient, and displaying the disease probability on the medical images of the target organs for the patient and doctors to review.
2. The medical information-based intelligent hospital operating method according to claim 1, wherein the acquiring a plurality of historical medical images of the target organ to construct a physiological organ reference map and a plurality of organ disease image sets comprises:
collecting a plurality of historical medical images of the target organ when the function of the target organ is normal and a plurality of historical medical images of the target organ under different disease types;
converting all the historical medical images of the target organ when the function is normal into gray images, and calculating average gray images of all the gray images;
carrying out affine transformation on all gray level images by taking the average gray level image as a template, and carrying out image fusion on all affine transformed images to obtain a physiological organ reference image;
dividing a plurality of historical medical images of a target organ under different disease types according to the disease types to obtain a plurality of organ disease type image sets, wherein the organ disease type image sets are in one-to-one correspondence with the disease types of the target organ.
3. The medical information-based intelligent hospital operating method according to claim 2, wherein after preprocessing the organ disease seed image set, calculating a frame difference image of each image in the organ disease seed image set and the physiological organ reference image to obtain an organ disease seed frame difference image set comprises:
cutting the images in the organ disease image set into uniform sizes by taking the physiological organ reference image as a template, and carrying out affine transformation on each image in the organ disease image set;
and sequentially calculating the frame difference images of each image subjected to affine transformation in the organ disease seed image set and the physiological organ reference image, and taking all the frame difference images as organ disease seed frame difference images.
4. The intelligent hospital operating method based on medical information as claimed in claim 1, wherein the step of superposing all images in the organ disease seed frame difference image set and then filtering to obtain a frame difference filter superposition image set comprises the steps of:
superposing all images in the organ disease seed frame difference image set to obtain a plurality of pixel gray sequences, wherein the pixel gray sequences comprise the number of pixels consistent with the number of the images in the organ disease seed frame difference image set;
denoising all pixel gray sequences according to wavelet transformation, filtering pixels belonging to noise in the pixel gray sequences, and taking the organ disease seed frame difference image set after superposition and denoising as a frame difference filtering superposition image set.
5. The medical information-based intelligent hospital operating method according to claim 4, wherein said sequentially performing discrete cosine transform on each image in said set of frame difference filtered superimposed images to obtain discrete cosine transform coefficients comprises:
dividing each image in the frame difference filtering superposition image set into a plurality of image blocks with the same quantity in sequence;
and performing discrete cosine transform on each image block to obtain a discrete cosine transform coefficient corresponding to the image block, wherein the discrete cosine transform coefficient comprises a plurality of alternating current coefficients for representing image detail texture information.
6. The medical information-based intelligent hospital operation method according to claim 5, wherein the filtering the ac coefficients based on the frame difference filtered superimposed image set to obtain effective ac coefficients comprises:
counting the total number of pixel points contained in all pixel gray sequences corresponding to a target image block as the total number of pixels of the image block sequence, wherein the target image block is any one image block in the frame difference filtering superposition image set;
counting the total number of pixel points reserved after noise elimination of all pixel gray sequences corresponding to the target image block as the total number of filtering pixels of the image block;
calculating the ratio of the total amount of the image block filtering pixels to the total amount of the image block sequence pixels;
counting the total amount of the alternating current coefficient number corresponding to the target image block, calculating the product of the total amount of the alternating current coefficient number and the ratio, and rounding up the product to obtain a rounding reserved value;
sorting the alternating current coefficients corresponding to the target image blocks according to the order from high to low, and reserving the alternating current coefficients with the same number as the rounding reserved value in the alternating current coefficients with the front sorting as effective alternating current coefficients;
and traversing all image blocks in the frame difference filtering superposition image set to obtain the effective alternating current coefficient corresponding to each image block.
7. The medical information-based intelligent hospital operating method according to claim 1, wherein said constructing an organ pathology profile from said direct current coefficients and effective alternating current coefficients comprises:
performing inverse discrete cosine transform on a direct current coefficient and an effective alternating current coefficient corresponding to each image block of a target image to obtain an organ pathology feature map corresponding to the target image, wherein the target image is any image in the frame difference filtering superposition image set;
and traversing all images in the frame difference filtering superposition image set to obtain an organ pathology feature map corresponding to each image.
8. The medical information-based intelligent hospital operation method according to claim 1, wherein the image fusion of all organ pathology feature maps to obtain organ pathology fusion feature maps comprises:
counting the number of the reserved pixels of all the image blocks at the same position in the frame difference filtering superposition image set;
normalizing the number of the reserved pixels of all the image blocks at the same position to obtain fusion weights of the corresponding image blocks;
and carrying out image fusion on all the image blocks at the same position based on the fusion weight to obtain an organ pathology fusion characteristic diagram.
9. The medical information-based intelligent hospital operation method according to claim 1, wherein the steps of acquiring medical images of a target organ of a patient in real time, and sequentially calculating the similarity between the medical images of the patient and each pathology fusion feature map to obtain the disease probability of each disease on the target organ of the patient comprise:
collecting a target organ medical image of a patient in real time and preprocessing the target organ medical image;
and sequentially calculating the similarity of the preprocessed target organ medical image and each pathology fusion feature map according to a template matching algorithm, and taking the similarity as the disease probability of the corresponding disease on the target organ of the patient.
10. An intelligent hospital operating system based on medical information, comprising:
a processor; and
a memory storing computer instructions of a medical information based intelligent hospital operating method, which when executed by the processor, cause an apparatus to perform the medical information based intelligent hospital operating method according to any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310881806.5A CN116597988B (en) | 2023-07-18 | 2023-07-18 | Intelligent hospital operation method and system based on medical information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310881806.5A CN116597988B (en) | 2023-07-18 | 2023-07-18 | Intelligent hospital operation method and system based on medical information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116597988A true CN116597988A (en) | 2023-08-15 |
| CN116597988B CN116597988B (en) | 2023-09-19 |
Family
ID=87608517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310881806.5A Active CN116597988B (en) | 2023-07-18 | 2023-07-18 | Intelligent hospital operation method and system based on medical information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116597988B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020031247A1 (en) * | 2000-09-13 | 2002-03-14 | Tomohiko Matsuura | Image processing apparatus, image processing method, program for implementing said method, and storage medium therefor |
| US20140018676A1 (en) * | 2012-07-11 | 2014-01-16 | Samsung Electronics Co., Ltd. | Method of generating temperature map showing temperature change at predetermined part of organ by irradiating ultrasound wave on moving organs, and ultrasound system using the same |
| CN109389587A (en) * | 2018-09-26 | 2019-02-26 | 上海联影智能医疗科技有限公司 | A kind of medical image analysis system, device and storage medium |
| CN109461495A (en) * | 2018-11-01 | 2019-03-12 | 腾讯科技（深圳）有限公司 | A kind of recognition methods of medical image, model training method and server |
| CN111784593A (en) * | 2020-06-04 | 2020-10-16 | 广东省智能制造研究所 | Lung nodule CT image data enhancement method and system for deep learning |
| WO2020243583A1 (en) * | 2019-05-29 | 2020-12-03 | Leica Biosystems Imaging, Inc. | Artificial intelligence processing system and automated pre-diagnostic workflow for digital pathology |
| CN114224369A (en) * | 2021-12-21 | 2022-03-25 | 深圳市澈影医生集团有限公司 | Medical image automatic diagnosis system |
| WO2022141882A1 (en) * | 2020-12-30 | 2022-07-07 | 上海睿刀医疗科技有限公司 | Lesion recognition model construction apparatus and system based on historical pathological information |
| WO2022179083A1 (en) * | 2021-02-25 | 2022-09-01 | 上海商汤智能科技有限公司 | Image detection method and apparatus, and device, medium and program |
| CN115272647A (en) * | 2022-09-26 | 2022-11-01 | 苏州朗开医疗技术有限公司 | Lung image recognition processing method and system |
-
2023
- 2023-07-18 CN CN202310881806.5A patent/CN116597988B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020031247A1 (en) * | 2000-09-13 | 2002-03-14 | Tomohiko Matsuura | Image processing apparatus, image processing method, program for implementing said method, and storage medium therefor |
| US20140018676A1 (en) * | 2012-07-11 | 2014-01-16 | Samsung Electronics Co., Ltd. | Method of generating temperature map showing temperature change at predetermined part of organ by irradiating ultrasound wave on moving organs, and ultrasound system using the same |
| CN109389587A (en) * | 2018-09-26 | 2019-02-26 | 上海联影智能医疗科技有限公司 | A kind of medical image analysis system, device and storage medium |
| CN109461495A (en) * | 2018-11-01 | 2019-03-12 | 腾讯科技（深圳）有限公司 | A kind of recognition methods of medical image, model training method and server |
| WO2020243583A1 (en) * | 2019-05-29 | 2020-12-03 | Leica Biosystems Imaging, Inc. | Artificial intelligence processing system and automated pre-diagnostic workflow for digital pathology |
| CN111784593A (en) * | 2020-06-04 | 2020-10-16 | 广东省智能制造研究所 | Lung nodule CT image data enhancement method and system for deep learning |
| WO2022141882A1 (en) * | 2020-12-30 | 2022-07-07 | 上海睿刀医疗科技有限公司 | Lesion recognition model construction apparatus and system based on historical pathological information |
| WO2022179083A1 (en) * | 2021-02-25 | 2022-09-01 | 上海商汤智能科技有限公司 | Image detection method and apparatus, and device, medium and program |
| CN114224369A (en) * | 2021-12-21 | 2022-03-25 | 深圳市澈影医生集团有限公司 | Medical image automatic diagnosis system |
| CN115272647A (en) * | 2022-09-26 | 2022-11-01 | 苏州朗开医疗技术有限公司 | Lung image recognition processing method and system |
Non-Patent Citations (1)
| Title |
|---|
| 张昌明;: "特殊病种CT图像的挖掘方法研究与仿真", 科技通报, no. 02 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116597988B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bankman | Handbook of medical image processing and analysis | |
| US10304198B2 (en) | Automatic medical image retrieval | |
| Yang et al. | Medical image fusion via an effective wavelet-based approach | |
| Yang | Multimodal medical image fusion through a new DWT based technique | |
| US10867375B2 (en) | Forecasting images for image processing | |
| CN111640100A (en) | Tumor image processing method and device, electronic equipment and storage medium | |
| EP3749973A1 (en) | Multi-resolution quantitative susceptibility mapping with magnetic resonance imaging | |
| US11969265B2 (en) | Neural network classification of osteolysis and synovitis near metal implants | |
| CN114241077B (en) | CT image resolution optimization method and device | |
| CN112070785A (en) | Medical image analysis method based on computer vision | |
| WO2023044605A1 (en) | Three-dimensional reconstruction method and apparatus for brain structure in extreme environments, and readable storage medium | |
| CN101049242A (en) | Method for reproduciblely generating tomography contrast image data view | |
| CN111968108A (en) | CT intelligent imaging method, device and system based on intelligent scanning protocol | |
| CN101075347A (en) | Method and device for improvedly automatic detecting abnormality of medical image data | |
| CN114066798B (en) | Brain tumor nuclear magnetic resonance image data synthesis method based on deep learning | |
| CN116597988B (en) | Intelligent hospital operation method and system based on medical information | |
| CN110610527A (en) | SUV calculation method, device, equipment, system and computer storage medium | |
| Yang et al. | Fusion of CT and MR images using an improved wavelet based method | |
| CN118076296A (en) | Medical image diagnosis support device, medical image diagnosis support method, and program | |
| CN111445406B (en) | Low-dose CT picture quality improvement method, system and equipment | |
| CN112215922A (en) | FT domain medical image fusion method | |
| Sriraam et al. | Performance evaluation of computer aided diagnostic tool (CAD) for detection of ultrasonic based liver disease | |
| Kumar et al. | An Approach Based on Parallel Computing for Performance Tuning of the Denoising Filter Used in Medical Imaging | |
| CN115578285B (en) | Mammary gland molybdenum target image detail enhancement method and system | |
| CN117876241B (en) | Method, system and equipment for synthesizing FLAIR image by CT image |
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 |