CN110852384A - Medical image quality detection method, device and storage medium - Google Patents
Medical image quality detection method, device and storage medium Download PDFInfo
- Publication number
- CN110852384A CN110852384A CN201911101597.8A CN201911101597A CN110852384A CN 110852384 A CN110852384 A CN 110852384A CN 201911101597 A CN201911101597 A CN 201911101597A CN 110852384 A CN110852384 A CN 110852384A
- Authority
- CN
- China
- Prior art keywords
- medical image
- data
- image data
- abnormal
- free
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application relates to a medical image quality detection method, a medical image quality detection device and a storage medium. The method comprises the following steps: acquiring original medical image data; screening abnormal data in the original medical image data to obtain abnormal-free medical image data; removing data with correlation coefficient not meeting the requirement from the abnormal medical image data to obtain medical image data to be detected; and carrying out quality classification on the medical image data to be detected by using a preset classification model, and determining the medical image meeting the quality requirement. The method can reduce the labor cost.
Description
Technical Field
The present application relates to the field of medical data processing technologies, and in particular, to a method, an apparatus, and a storage medium for detecting medical image quality.
Background
With the development of medical technology, the variety of medical devices is becoming more and more popular. Different scanning technologies of different medical devices are also various, and different medical images can be obtained by different scanning technologies and imaging modes, so that massive image data is generated. Meanwhile, in the case of image diagnosis, the quality is the sum of the properties inherent to the image itself or the examination, which determine whether or not the clinical diagnosis object can be satisfied, as the evaluation object. The quality of the image affects the diagnostic value of the doctor. Therefore, it is a problem to be solved to acquire a high-quality image from a large amount of image data.
However, the conventional low-quality or damaged image is usually discovered by the user only when being called for reading, and then the examinee is notified to re-scan and then re-read, which results in an increase in labor cost.
Disclosure of Invention
In view of the above, it is desirable to provide a medical image quality detection method, apparatus and storage medium capable of reducing labor cost.
A method of medical image quality detection, the method comprising:
acquiring original medical image data;
screening abnormal data in the original medical image data to obtain abnormal-free medical image data;
removing data with correlation coefficients which do not meet requirements from the abnormal medical image data to obtain medical image data to be detected;
and carrying out quality classification on the medical image data to be detected by using a preset classification model, and determining the medical image meeting the quality requirement.
In one embodiment, the screening abnormal data in the original medical image data to obtain abnormal-free medical image data includes:
and performing cluster analysis on the original medical image data, and screening abnormal data according to an analysis result to obtain abnormal-free medical image data.
In one embodiment, the performing cluster analysis on the original medical image data and screening abnormal data according to an analysis result to obtain abnormal-free medical image data includes:
acquiring the number of clusters, and selecting data with the same number as the number of the clusters from the original medical image data as a cluster center;
determining abnormal data according to the data volume of each distributed cluster center, and deleting the abnormal data to obtain abnormal-free medical image data;
or
Acquiring a minimum neighborhood point number and a neighborhood radius, traversing the original medical image data, and determining core data according to the minimum neighborhood point number and the neighborhood radius;
and performing data distribution based on the core data and the neighborhood radius, and screening out the original medical image data which is not distributed to obtain abnormal-free medical image data.
In one embodiment, the screening abnormal data in the original medical image data to obtain abnormal-free medical image data includes:
performing outlier factor detection on the original medical image data to obtain an outlier factor corresponding to each original medical image data;
and screening abnormal data according to each outlier factor to obtain abnormal-free medical image data.
In one embodiment, the removing data whose correlation coefficient does not meet the requirement from the non-abnormal medical image data to obtain the medical image data to be detected includes:
forming a data pair by any two abnormal medical image data;
calculating the correlation coefficient of the two abnormal-free medical image data in any data pair;
and when the correlation coefficient is used for determining that the two abnormal-free medical image data in the data pair have the correlation, deleting any one data in the data pair to obtain the medical image data to be detected.
In one embodiment, the deleting any one of the data in the data pair includes:
and when any at least two groups of data pairs have correlation and contain the same abnormal-free medical image data, deleting the same abnormal-free medical image data.
In one embodiment, the method further comprises:
acquiring training sample data, wherein the training sample data comprises negative sample data and positive sample data;
adding a negative sample label to the negative sample data and adding a positive sample label to the positive sample data;
and mixing the negative sample added with the negative sample label and the positive sample added with the positive sample label, inputting the mixture into a preset classification model, and training the classification model.
In one embodiment, the predetermined classification model includes, but is not limited to, any one or more of a decision tree model, a logistic regression model, a neural network model, and a support vector machine model.
A medical image quality detection apparatus, the apparatus comprising:
the acquisition module is used for acquiring original medical image data;
the abnormality analysis module is used for screening abnormal data in the original medical image data to obtain abnormal-free medical image data;
the correlation analysis module is used for removing data with correlation coefficients which do not meet requirements from the abnormal-free medical image data to obtain medical image data to be detected;
and the detection module is used for performing quality classification on the medical image data to be detected by using a preset detection model and determining the medical image meeting the quality requirement.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the medical image quality detection method according to any one of the above.
According to the medical image quality detection method, the medical image quality detection device and the storage medium, after the original medical image data are obtained, abnormal data are screened out, data with correlation coefficients which do not meet requirements are removed, data which can be detected are obtained, and then the data to be detected are subjected to quality classification by using the preset detection model. The method prevents noise data from influencing the detection quality by removing abnormal data and data which do not meet requirements, reduces the burden of subsequent detection work, further realizes automatic screening of high-quality images from original medical image data by combining medical image data with data analysis, and reduces labor cost.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of a medical image quality inspection method;
FIG. 2 is a flow chart illustrating a method for medical image quality inspection according to an embodiment;
FIG. 3 is a flowchart illustrating the steps of removing data with correlation coefficients not meeting the requirements from the abnormal medical image data to obtain the medical image data to be detected according to an embodiment;
FIG. 4 is a block diagram of an embodiment of an apparatus for medical image quality inspection;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The medical image quality detection method provided by the application can be applied to the application environment shown in fig. 1. The application environment involves a terminal 102 and a server 104, the terminal 102 communicating with the server 104 over a network. After the terminal 102 acquires the original medical image data, the medical image quality detection method can be implemented by the terminal 102 alone. The terminal 102 may send the original medical image data to the server 104, and the server 104 may implement the medical image quality detection method. Specifically, taking the terminal 102 as an example, after the terminal 102 acquires the original medical image data, abnormal data in the original medical image data is screened out to obtain abnormal-free medical image data; the terminal 102 removes data with correlation coefficients not meeting requirements from the abnormal medical image data to obtain medical image data to be detected; the terminal 102 performs quality classification on the medical image data to be detected by using a preset classification model, and determines the medical image meeting the quality requirement. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a medical image quality detection method is provided, which is described by taking the example that the method is applied to the terminal in fig. 1, and includes the following steps:
step S202, acquiring original medical image data.
The original medical image data refers to medical image data that has not undergone medical image quality detection, and may be medical image data acquired by a terminal from a PACS (Picture Archiving and Communication Systems) system, or medical image data generated by a terminal receiving medical equipment in real time, or medical image data uploaded by a user in real time. The medical image data in the PACS system is data stored in a digitalized manner through various interfaces for various medical images generated daily. For example, medical images generated by medical equipment such as nuclear magnetic resonance, CT (computed tomography), ultrasound, various X-ray machines, various infrared machines, and microscopes are stored digitally through corresponding interfaces to obtain data.
And S204, screening abnormal data in the original medical image data to obtain abnormal-free medical image data.
The abnormal data refers to noise data, that is, data that deviates from an expected value or differs greatly from most of the original medical image data. The abnormal-free medical image number is the original medical image data left after the abnormal data is removed.
Specifically, after the original medical image data is acquired, the terminal performs cluster analysis on the original medical image data, and determines abnormal data according to a cluster analysis result. Then, the determined abnormal data is removed from the original medical image data, and abnormal-free medical image data is obtained. The cluster analysis refers to a process of classifying data into different classes or clusters, objects classified into the same cluster have great similarity, and objects in different clusters have great dissimilarity. Therefore, in the present embodiment, the apparent abnormal data can be determined by cluster analysis. For example, data that is not allocated or data in a certain cluster is far smaller than data in other clusters, it can be determined as abnormal data.
And S206, removing the data with the correlation coefficient not meeting the requirement from the abnormal medical image data to obtain the medical image data to be detected.
The correlation coefficient is a value obtained by performing correlation analysis based on statistics, and is used for representing the correlation between two objects. The medical image data to be detected is the residual abnormal-free medical image data after the data with the correlation coefficient not meeting the requirement is removed.
Specifically, after the abnormal-free medical image data is obtained, the correlation detection is performed on the abnormal-free medical image data through the pearson correlation detection. And then determining data with stronger correlation according to the correlation coefficient obtained by correlation detection, and removing abnormal-free medical image data with stronger correlation to obtain the medical image data to be detected. Determining whether the correlation is strong may be performed by comparing the correlation coefficient with a coefficient threshold. For example, a correlation coefficient greater than a coefficient threshold indicates that the correlation is strong, and the coefficient threshold and the specific comparison method may be set according to actual conditions.
And S208, performing quality classification on the medical image data to be detected by using a preset classification model, and determining the medical image meeting the quality requirement.
The classification model is obtained by utilizing a large number of medical image data samples to train in advance, and the trained classification model is used for carrying out quality classification on the medical image data. The classification model includes, but is not limited to, any one or more of a decision tree model, a logistic regression model, a neural network model, and a support vector machine model.
Specifically, after medical image data to be detected is obtained, a classification model trained in advance is called. And inputting the medical image data to be detected into the called classification model, and performing quality classification on the medical image data to be detected through the classification model. And then, determining whether the quality of the medical image data to be detected input into the classification model meets the requirements or not according to the classification result output by the classification model. When the classification result is that the quality of the medical image data to be detected does not meet the requirement, the user can be further informed to perform scanning again.
According to the medical image quality detection method, after the original medical image data are obtained, abnormal data are screened out, data with correlation coefficients which do not meet requirements are removed, data which can be detected are obtained, and then the data to be detected are subjected to quality classification by means of the preset detection model. The method prevents noise data from influencing the detection quality by removing abnormal data and data which do not meet requirements, reduces the burden of subsequent detection work, further realizes automatic screening of high-quality images from original medical image data by combining medical image data with data analysis, and reduces labor cost.
In one embodiment, the clustering analysis of the original medical image data, and the screening of abnormal data according to the analysis result to obtain abnormal-free medical image data specifically includes: acquiring the number of clusters, and selecting data with the same number as the number of clusters from the original medical image data as a cluster center; performing data distribution based on the distance between each clustering center and the rest original medical image data; and determining abnormal data according to the data volume of each distributed clustering center, and deleting the abnormal data to obtain abnormal-free medical image data.
The number of clusters is a value preset to determine the number of clusters, for example, when the number of clusters is 4, the clusters are clustered into 4 clusters. A cluster center may be understood to be representative of a randomly selected class of data.
Specifically, when performing cluster analysis, the cluster number is first acquired. And then randomly selecting data with the same quantity as the clustering number from the original medical image data, wherein the selected data is the clustering center. For example, when the number of clusters is 4, 4 data are randomly selected from the original medical image data as cluster centers. Then, with the cluster center as a standard, the Euclidean distance between the cluster center and other remaining original medical image data is calculated. And distributing the residual original medical image data to a clustering center with the minimum Euclidean distance based on the Euclidean distance, and expressing the data distributed to the same clustering center as a type of data. For example, if the euclidean distance between the data a and the first cluster center is the smallest, the data a is assigned to the first cluster center. Finally, after the data allocation is completed, a cluster of data with the minimum data size can be directly deleted as abnormal data. The abnormal data can also be determined according to the difference between the data amounts of various types, for example, when the data amount of one cluster of data is excessively different from the data amount of other clusters, the data with the excessively large difference can be directly determined. And when the difference in the amount of data between the clusters is not large, it is determined that there is no abnormal data. Wherein whether the difference is too large may be determined by comparing the difference in the data amount of each cluster with a difference threshold.
In addition, when the data amount difference between the clusters is not large, the data amount can be increased progressively based on the number of the existing clusters. And re-clustering based on the number of clusters after increasing, and determining abnormal data according to a new round of clustering results until the abnormal data can be determined. For example, the number of clusters of originals is incremented from 4 to 5, 5 to 6, and so on. And then, randomly determining a clustering center from the original medical image data again according to the new clustering number for data distribution. If abnormal data with large data quantity difference cannot be obtained through multiple times of incremental reclustering, the fact that the abnormal data do not exist can be determined. In the embodiment, the apparent noise abnormal data is removed through clustering analysis, so that the quality of the data is improved.
In another embodiment, the clustering analysis of the original medical image data, and the screening of abnormal data according to the analysis result to obtain abnormal-free medical image data specifically includes: acquiring minimum neighborhood points and neighborhood radii, traversing original medical image data, and determining core data according to the minimum neighborhood points and the neighborhood radii; and performing data distribution based on the core data and the neighborhood radius, and screening out undistributed original medical image data to obtain abnormal-free medical image data.
The clustering analysis used in this embodiment is a DBSCAN algorithm (Density-Based clustering of Applications with Noise). The DBSCAN algorithm is a clustering method that defines clusters as the maximum set of density-connected points, can divide an area having a sufficiently high density into clusters, and can find an arbitrary shape in noisy data. The minimum field point number and the neighborhood radius are parameters in the DBSCAN algorithm, the neighborhood radius refers to a neighborhood distance threshold of a certain sample, and the minimum field point number is a threshold for describing the number of samples in a neighborhood with the certain sample distance as the field radius. Since the DBSCAN algorithm describes the closeness of a sample set based on a set of neighborhoods, the parameters of the DBSCAN algorithm are the minimum neighborhood point number and the neighborhood radius, which are used to describe the closeness of the distribution of samples in the neighborhood. Therefore, by giving the parameters of the minimum neighborhood point number and the neighborhood radius, the DBSCAN algorithm can perform cluster analysis based on the minimum neighborhood point number and the neighborhood radius.
Specifically, a preset minimum neighborhood point number and a preset minimum neighborhood radius are obtained, and each original medical image data is traversed. When the original medical image data at least containing the minimum field point number in the field radius of a certain original medical image data is determined, the original medical image data is determined as core data and a cluster is established for the core data. Then, all objects in the neighborhood radius of the core data are placed into a candidate set, and original medical image data which do not belong to other clusters in the candidate set are placed into the established clusters. In this process, the data judged in the candidate set can be regarded as the traversed data, and the data amount of the original medical image data in the neighborhood radius of the data needs to be further checked. And when the data volume is at least the minimum neighborhood point number, putting the original medical image data in the neighborhood radius of the data into the candidate set. And continuing to put the data in the candidate set into the cluster until the data in the candidate set are traversed, thereby obtaining a complete cluster.
If the next cluster needs to be obtained through clustering, the core data can be randomly determined again in the rest data, and the operations are repeated, and the principle is the same and is not repeated herein until all the original medical image data are traversed. And finally, determining the original medical image data which is free from the cluster as abnormal data, and deleting the abnormal data to obtain the abnormal-free original medical image data. In this embodiment, since the existence of the noise data generally reduces the accuracy of the model classification, the medical image data is subjected to data cleaning through cluster analysis, so that obvious abnormal medical image data can be removed, and the quality of the medical image data is improved. Moreover, the medical image data can be cleaned to provide clean data for subsequent correlation analysis, and the accuracy of the correlation analysis is improved, so that the accuracy of the model for classifying the medical image data is further improved.
In one embodiment, screening abnormal data in the original medical image data to obtain abnormal-free medical image data comprises: performing outlier factor detection on the original medical image data to obtain outlier factors corresponding to the original medical image data; and screening abnormal data according to each outlier factor to obtain abnormal-free medical image data.
Specifically, the original medical image data is detected by an Outlier Factor detection algorithm LOF (Local Outlier Factor algorithm), so as to obtain an Outlier Factor, which is the abnormal original medical image data. And then deleting the original medical image data represented by the outlier factor to obtain abnormal-free medical image data.
In addition, in one embodiment, when abnormal data in the original medical image data is screened out to obtain abnormal-free medical image data, a cluster analysis method may be used to determine the abnormal data. And when the clustering analysis determines that the original medical image data has no abnormal data or the clustering analysis carries out clustering by increasing the clustering number for multiple times, the clustering analysis can not determine the abnormal data, and then the LOF algorithm is used for carrying out outlier factor detection to obtain the abnormal data. In this embodiment, when the cluster analysis algorithm cannot clearly remove the abnormal data, the outlier detection algorithm is further used to detect and remove the abnormal data, so that the abnormal data can be accurately and effectively removed when various types of medical image data are confronted.
In one embodiment, as shown in fig. 3, removing data with correlation coefficient not meeting the requirement from the abnormal medical image data to obtain the medical image data to be detected includes the following steps:
step S302, any two abnormal medical image data are combined into a data pair.
Wherein, the data pair refers to a set comprising two different abnormal-free medical image data. Since the correlation coefficient between the abnormal medical image data needs to be calculated, all the abnormal medical image data need to form a data pair between each two abnormal medical image data. Therefore, the number of pairs of data obtained is determined by the number of abnormal-free medical image data.
Specifically, after the abnormal-free medical image data is obtained, traversing and combining the abnormal-free medical image data to obtain a corresponding data pair. For example, if there are 4 abnormal-free medical image data a, B, C and D, the data pairs obtained after the traversal combination have (a, B) (a, C) (a, D) (B, C) (B, D) (C, D).
Step S304, calculating the correlation coefficient of two abnormal medical image data in any data pair.
Specifically, after the data pair is obtained, the correlation coefficient between two pieces of abnormal medical image data in the data pair is calculated by using a calculation formula of the pearson correlation coefficient. For example, if there are 6 data pairs such as (a, B) (a, C) (a, D) (B, C) (B, D) (C, D), the abnormal medical image data in the 6 data pairs is calculated to obtain 6 corresponding correlation coefficients.
And S306, when the two abnormal medical image data in the data pair are determined to have the correlation according to the correlation coefficient, deleting any one data in the data pair to obtain the medical image data to be detected.
Specifically, the correlation coefficient of the data pair is compared with a coefficient threshold value, and the data pair having correlation is determined. For example, when the coefficient threshold is 0.8, it may be determined that two abnormal-free medical image data in the data pair having a correlation coefficient of 0.8 or more have a correlation. When the coefficient threshold is 0.6, it is determined that two non-abnormal medical image data having a correlation coefficient of 0.6 or more have a correlation coefficient. It should be understood that the setting of the coefficient threshold may be set according to actual conditions, and is not limited herein. Then, when it is determined that the two abnormal-free medical image data in the data pair have correlation according to the coefficient threshold, any abnormal-free medical image data in the data pair can be deleted, and the other abnormal-free medical image data is reserved. And finally, the preserved abnormal-free medical image data is the medical image data to be detected. For example, data B is removed from data pair (a, B), and data a is retained. In the present embodiment, since the medical image is usually saved in PACS (Picture Imaging and Communications System) in the form of DICOM (Digital Imaging and Communications in Medicine) image standard, the DOICM file identifies unique medical image data and maintains an association between various medical image data by means of various tag values (tag). Therefore, in the presence of various tags, if the medical image data is directly classified, the classification efficiency of the model is reduced. Therefore, before classifying the medical image data, the data with high relevance is deleted by performing relevance analysis on the data, so that the data with redundant attributes is reduced, the load of model classification is reduced, and the classification accuracy is improved.
In addition, in one embodiment, when any at least two sets of data pairs have correlation and contain the same abnormal-free medical image data, the same abnormal-free medical image data is deleted.
Specifically, when two sets of data pairs have correlation and contain the same abnormal-free medical image data, and the other two different sets of data have no correlation, the same abnormal-free medical image data is deleted. For example, assume that data pair (a, B) and data pair (a, C) both have a correlation and contain data a, while data B and data C have no correlation. In order to ensure the diversity of data, data a may be deleted. However, when data B and data C have correlation at the same time, after data a is removed, one data deletion should be arbitrarily selected between B and C. Similarly, when the data pair (a, B), the data pair (a, C), and the data pair (a, D) all have correlation, and there is no correlation between the data B, C and D, the deletion of the data a is selected. And the data BCD are deleted according to the condition of the correlation coefficient between every two data BCD. In this embodiment, when two or more sets of data pairs have correlations and include the same medical image data, the same medical image data is directly removed, so that not only can the data with redundant attributes be reduced to reduce the classification burden of the model, but also the diversity of the data can be further ensured on the basis of removing the redundant data.
In one embodiment, the medical image quality detection further comprises a step of training a classification model, wherein the training of the classification model should be completed before the quality classification is performed by using the classification model. For example, the classification model may be trained prior to acquiring the raw medical image data.
The training classification model specifically comprises: acquiring training sample data, wherein the training sample data comprises negative sample data and positive sample data; adding a negative sample label to the negative sample data and adding a positive sample label to the positive sample data; and mixing the negative sample added with the negative sample label and the positive sample added with the positive sample label, inputting the mixture into a preset classification model, and training the classification model.
Specifically, when training the classification model, historical medical image data, which is real medical image data obtained by shooting historically, is first obtained. The positive sample data is obtained by deleting abnormal data and data with high correlation in the historical medical image data. The negative sample data is invalid medical image data uploaded by a user, and the negative sample data is data manually generated by a person and is not real data acquired by shooting. Positive sample data may be regarded as high-quality medical image data, and negative sample data may be regarded as low-quality medical image data.
The type of the sample data is marked by adding a corresponding label to the sample data. That is, adding a positive sample tag to positive sample data identifies the sample data as high quality sample data, and adding a negative sample tag to negative sample data identifies the sample data as low quality sample data. The positive and negative exemplar labels may be represented by adding labels of boolean attributes to the sample data. For example, data with an attribute value of 1 is added as high-quality positive sample data, and data with an attribute value of 0 is added as low-quality negative sample data. And after the label is added, mixing the positive sample data and the negative sample data according to a certain proportion. The data may be represented by the positive sample data 10 by simulating invalid unbalanced data: the negative sample data 1 is mixed in proportion. Finally, a certain proportion of data, for example, 70% of data, is selected from the mixed data and is input into the classification model as training data, and the classification model is trained, so that the model has the capability of distinguishing high-quality medical image data from low-quality medical image data. And the rest 30% of data can be used for testing the classification effect of the classification model after the training of the classification model is finished, and the parameters of the classification model are further adjusted according to the tested classification result, so that the accuracy of the classification model is improved.
It should be understood that although the various steps in the flow charts of fig. 2-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 4, there is provided a medical image quality detection apparatus including: an acquisition module 402, an anomaly analysis module 404, a correlation analysis module 406, and a detection module 408, wherein:
an acquisition module 402 for acquiring raw medical image data.
The anomaly analysis module 404 is configured to screen out abnormal data in the original medical image data to obtain abnormal-free medical image data.
And the correlation analysis module 406 is configured to remove data with correlation coefficients that do not meet the requirements from the abnormal-free medical image data to obtain medical image data to be detected.
The detection module 408 is configured to perform quality classification on the medical image data to be detected by using a preset classification model, and determine a medical image meeting the quality requirement.
In one embodiment, the anomaly analysis module 404 is further configured to perform cluster analysis on the original medical image data, and screen out abnormal data according to the analysis result, so as to obtain abnormal-free medical image data.
In one embodiment, the anomaly analysis module 404 is further configured to obtain the number of clusters, and select data with the same number as the number of clusters from the original medical image data as a cluster center; determining abnormal data according to the data volume of each distributed clustering center, and deleting the abnormal data to obtain abnormal-free medical image data; or
Acquiring minimum neighborhood points and neighborhood radii, traversing original medical image data, and determining core data according to the minimum neighborhood points and the neighborhood radii; and performing data distribution based on the core data and the neighborhood radius, and screening out undistributed original medical image data to obtain abnormal-free medical image data.
In one embodiment, the anomaly analysis module 404 is further configured to perform outlier factor detection on the original medical image data, so as to obtain an outlier factor corresponding to each original medical image data; and screening abnormal data according to each outlier factor to obtain abnormal-free medical image data.
In one embodiment, the correlation analysis module 406 is further configured to combine any two non-abnormal medical image data into a data pair; calculating the correlation coefficient of two abnormal medical image data in any data pair; and when the two abnormal medical image data in the data pair are determined to have correlation according to the correlation coefficient, deleting any one data in the data pair to obtain the medical image data to be detected.
In one embodiment, the correlation analysis module 406 is further configured to delete the same abnormal-free medical image data when any two sets of data pairs have correlation and contain the same abnormal-free medical image data.
In one embodiment, the medical image quality detection apparatus further includes a training module, configured to acquire training sample data, where the training sample data includes negative sample data and positive sample data; adding a negative sample label to the negative sample data and adding a positive sample label to the positive sample data; and mixing the negative sample added with the negative sample label and the positive sample added with the positive sample label, inputting the mixture into a preset classification model, and training the classification model.
For specific limitations of the medical image quality detection apparatus, reference may be made to the above limitations of the medical image quality detection method, which are not described herein again. The modules in the medical image quality detection device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the original medical image data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a medical image quality detection method.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring original medical image data;
screening abnormal data in the original medical image data to obtain abnormal-free medical image data;
removing data with correlation coefficient not meeting the requirement from the abnormal medical image data to obtain medical image data to be detected;
and performing quality classification on the medical image data to be detected by using a preset classification model, and determining the medical image meeting the quality requirement.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and performing cluster analysis on the original medical image data, and screening abnormal data according to the analysis result to obtain abnormal-free medical image data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring the number of clusters, and selecting data with the same number as the number of clusters from the original medical image data as a cluster center; determining abnormal data according to the data volume of each distributed clustering center, and deleting the abnormal data to obtain abnormal-free medical image data; or
Acquiring minimum neighborhood points and neighborhood radii, traversing original medical image data, and determining core data according to the minimum neighborhood points and the neighborhood radii; and performing data distribution based on the core data and the neighborhood radius, and screening out undistributed original medical image data to obtain abnormal-free medical image data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
performing outlier factor detection on the original medical image data to obtain outlier factors corresponding to the original medical image data; and screening abnormal data according to each outlier factor to obtain abnormal-free medical image data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
forming a data pair by any two abnormal medical image data; calculating the correlation coefficient of two abnormal medical image data in any data pair; and when the two abnormal medical image data in the data pair are determined to have correlation according to the correlation coefficient, deleting any one data in the data pair to obtain the medical image data to be detected.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and deleting the same abnormal-free medical image data when any at least two groups of data pairs have correlation and contain the same abnormal-free medical image data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring training sample data, wherein the training sample data comprises negative sample data and positive sample data; adding a negative sample label to the negative sample data and adding a positive sample label to the positive sample data; and mixing the negative sample added with the negative sample label and the positive sample added with the positive sample label, inputting the mixture into a preset classification model, and training the classification model.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring original medical image data;
screening abnormal data in the original medical image data to obtain abnormal-free medical image data;
removing data with correlation coefficient not meeting the requirement from the abnormal medical image data to obtain medical image data to be detected;
and performing quality classification on the medical image data to be detected by using a preset classification model, and determining the medical image meeting the quality requirement.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and performing cluster analysis on the original medical image data, and screening abnormal data according to the analysis result to obtain abnormal-free medical image data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring the number of clusters, and selecting data with the same number as the number of clusters from the original medical image data as a cluster center; determining abnormal data according to the data volume of each distributed clustering center, and deleting the abnormal data to obtain abnormal-free medical image data; or
Acquiring minimum neighborhood points and neighborhood radii, traversing original medical image data, and determining core data according to the minimum neighborhood points and the neighborhood radii; and performing data distribution based on the core data and the neighborhood radius, and screening out undistributed original medical image data to obtain abnormal-free medical image data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing outlier factor detection on the original medical image data to obtain outlier factors corresponding to the original medical image data; and screening abnormal data according to each outlier factor to obtain abnormal-free medical image data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
forming a data pair by any two abnormal medical image data; calculating the correlation coefficient of two abnormal medical image data in any data pair; and when the two abnormal medical image data in the data pair are determined to have correlation according to the correlation coefficient, deleting any one data in the data pair to obtain the medical image data to be detected.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and deleting the same abnormal-free medical image data when any at least two groups of data pairs have correlation and contain the same abnormal-free medical image data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring training sample data, wherein the training sample data comprises negative sample data and positive sample data; adding a negative sample label to the negative sample data and adding a positive sample label to the positive sample data; and mixing the negative sample added with the negative sample label and the positive sample added with the positive sample label, inputting the mixture into a preset classification model, and training the classification model.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of medical image quality detection, the method comprising:
acquiring original medical image data;
screening abnormal data in the original medical image data to obtain abnormal-free medical image data;
removing data with correlation coefficients which do not meet requirements from the abnormal medical image data to obtain medical image data to be detected;
and carrying out quality classification on the medical image data to be detected by using a preset classification model, and determining the medical image meeting the quality requirement.
2. The method of claim 1, wherein the screening abnormal data from the original medical image data to obtain abnormal-free medical image data comprises:
and performing cluster analysis on the original medical image data, and screening abnormal data according to an analysis result to obtain abnormal-free medical image data.
3. The method according to claim 2, wherein the clustering analysis of the original medical image data and the screening of abnormal data according to the analysis result to obtain abnormal-free medical image data comprises:
acquiring the number of clusters, and selecting data with the same number as the number of the clusters from the original medical image data as a cluster center;
performing data distribution based on the distance between each cluster center and the rest of the original medical image data;
determining abnormal data according to the data volume of each distributed cluster center, and deleting the abnormal data to obtain abnormal-free medical image data;
or
Acquiring a minimum neighborhood point number and a neighborhood radius, traversing the original medical image data, and determining core data according to the minimum neighborhood point number and the neighborhood radius;
and performing data distribution based on the core data and the neighborhood radius, and screening out the original medical image data which is not distributed to obtain abnormal-free medical image data.
4. The method of claim 1, wherein the screening abnormal data from the original medical image data to obtain abnormal-free medical image data comprises:
performing outlier factor detection on the original medical image data to obtain an outlier factor corresponding to each original medical image data;
and screening abnormal data according to each outlier factor to obtain abnormal-free medical image data.
5. The method according to claim 1, wherein the removing the data with correlation coefficient not meeting the requirement from the non-abnormal medical image data to obtain the medical image data to be detected comprises:
forming a data pair by any two abnormal medical image data;
calculating the correlation coefficient of the two abnormal-free medical image data in any data pair;
and when the correlation coefficient is used for determining that the two abnormal-free medical image data in the data pair have the correlation, deleting any one data in the data pair to obtain the medical image data to be detected.
6. The method of claim 5, wherein the deleting any one of the pair of data comprises:
and when any at least two groups of data pairs have correlation and contain the same abnormal-free medical image data, deleting the same abnormal-free medical image data.
7. The method of claim 1, further comprising:
acquiring training sample data, wherein the training sample data comprises negative sample data and positive sample data;
adding a negative sample label to the negative sample data and adding a positive sample label to the positive sample data;
and mixing the negative sample added with the negative sample label and the positive sample added with the positive sample label, inputting the mixture into a preset classification model, and training the classification model.
8. The method according to claim 1 or 7, wherein the preset classification model comprises any one or more of but not limited to a decision tree model, a logistic regression model, a neural network model, and a support vector machine model.
9. A medical image quality detection apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring original medical image data;
the abnormality analysis module is used for screening abnormal data in the original medical image data to obtain abnormal-free medical image data;
the correlation analysis module is used for removing data with correlation coefficients which do not meet requirements from the abnormal-free medical image data to obtain medical image data to be detected;
and the detection module is used for performing quality classification on the medical image data to be detected by using a preset detection model and determining the medical image meeting the quality requirement.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911101597.8A CN110852384B (en) | 2019-11-12 | 2019-11-12 | Medical image quality detection method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911101597.8A CN110852384B (en) | 2019-11-12 | 2019-11-12 | Medical image quality detection method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110852384A true CN110852384A (en) | 2020-02-28 |
| CN110852384B CN110852384B (en) | 2023-06-27 |
Family
ID=69600543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911101597.8A Active CN110852384B (en) | 2019-11-12 | 2019-11-12 | Medical image quality detection method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110852384B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114343719A (en) * | 2022-03-17 | 2022-04-15 | 深圳华声医疗技术股份有限公司 | Ultrasonic imaging control method, ultrasonic imaging terminal, ultrasonic imaging apparatus, and medium |
| CN115860579A (en) * | 2023-02-27 | 2023-03-28 | 山东金利康面粉有限公司 | Production quality monitoring system for flour processing |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012013920A1 (en) * | 2010-07-26 | 2012-02-02 | Ucl Business Plc | Method and system for anomaly detection in data sets |
| CN109146705A (en) * | 2018-07-02 | 2019-01-04 | 昆明理工大学 | A kind of method of electricity consumption characteristic index dimensionality reduction and the progress stealing detection of extreme learning machine algorithm |
| CN109740694A (en) * | 2019-01-24 | 2019-05-10 | 燕山大学 | A kind of smart grid inartful loss detection method based on unsupervised learning |
| CN109753991A (en) * | 2018-12-06 | 2019-05-14 | 中科恒运股份有限公司 | Abnormal deviation data examination method and device |
| CN109949268A (en) * | 2019-01-24 | 2019-06-28 | 郑州大学第一附属医院 | A kind of hepatocellular carcinoma level of differentiation stage division based on machine learning |
| US20190228547A1 (en) * | 2018-01-24 | 2019-07-25 | New York University | Systems and methods for diagnostic oriented image quality assessment |
| CN110232719A (en) * | 2019-06-21 | 2019-09-13 | 腾讯科技（深圳）有限公司 | A kind of classification method of medical image, model training method and server |
-
2019
- 2019-11-12 CN CN201911101597.8A patent/CN110852384B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012013920A1 (en) * | 2010-07-26 | 2012-02-02 | Ucl Business Plc | Method and system for anomaly detection in data sets |
| US20190228547A1 (en) * | 2018-01-24 | 2019-07-25 | New York University | Systems and methods for diagnostic oriented image quality assessment |
| CN109146705A (en) * | 2018-07-02 | 2019-01-04 | 昆明理工大学 | A kind of method of electricity consumption characteristic index dimensionality reduction and the progress stealing detection of extreme learning machine algorithm |
| CN109753991A (en) * | 2018-12-06 | 2019-05-14 | 中科恒运股份有限公司 | Abnormal deviation data examination method and device |
| CN109740694A (en) * | 2019-01-24 | 2019-05-10 | 燕山大学 | A kind of smart grid inartful loss detection method based on unsupervised learning |
| CN109949268A (en) * | 2019-01-24 | 2019-06-28 | 郑州大学第一附属医院 | A kind of hepatocellular carcinoma level of differentiation stage division based on machine learning |
| CN110232719A (en) * | 2019-06-21 | 2019-09-13 | 腾讯科技（深圳）有限公司 | A kind of classification method of medical image, model training method and server |
Non-Patent Citations (2)
| Title |
|---|
| MA, DONGLING: "Precise Processing of Point Cloud Data in Omni-Directional Scanning Based on Three-Dimensional Laser Sensor", 《JOURNAL OF NANOELECTRONICS AND OPTOELECTRONICS》 * |
| 李永丽 等: "基于数据模式聚类算法的离群点检测", 《吉林大学学报(理学版)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114343719A (en) * | 2022-03-17 | 2022-04-15 | 深圳华声医疗技术股份有限公司 | Ultrasonic imaging control method, ultrasonic imaging terminal, ultrasonic imaging apparatus, and medium |
| CN114343719B (en) * | 2022-03-17 | 2022-05-31 | 深圳华声医疗技术股份有限公司 | Ultrasonic imaging control method, ultrasonic imaging terminal, ultrasonic imaging apparatus, and medium |
| CN115860579A (en) * | 2023-02-27 | 2023-03-28 | 山东金利康面粉有限公司 | Production quality monitoring system for flour processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110852384B (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6402265B2 (en) | Method, computer device and storage device for building a decision model | |
| US10810735B2 (en) | Method and apparatus for analyzing medical image | |
| CN114072879B (en) | System and method for processing images to classify processed images for digital pathology | |
| RU2533500C2 (en) | System and method for combining clinical signs and image signs for computer-aided diagnostics | |
| CN111524137B (en) | Cell identification counting method and device based on image identification and computer equipment | |
| CN110796656A (en) | Image detection method, image detection device, computer equipment and storage medium | |
| JP2021166062A (en) | Focal point weighting machine learning classifier error prediction for microscope slide image | |
| US9117009B2 (en) | Report creation support apparatus, creation support method thereof and program | |
| CN109308488B (en) | Mammary gland ultrasonic image processing device, method, computer equipment and storage medium | |
| JP2015087903A (en) | Apparatus and method for information processing | |
| WO2016057960A1 (en) | Apparatus, system and method for cloud based diagnostics and image archiving and retrieval | |
| CN110335248B (en) | Medical image focus detection method, device, computer equipment and storage medium | |
| CN109146891B (en) | Hippocampus segmentation method and device applied to MRI and electronic equipment | |
| CN108241853A (en) | A kind of video frequency monitoring method, system and terminal device | |
| WO2020056968A1 (en) | Data denoising method and apparatus, computer device, and storage medium | |
| US9070203B2 (en) | Identification and quantification of microtextured regions in materials with ordered crystal structure | |
| CN110852384B (en) | Medical image quality detection method, device and storage medium | |
| KR20220115627A (en) | Systems and methods for analyzing electronic images for quality control | |
| CN113160199B (en) | Image recognition method and device, computer equipment and storage medium | |
| CN117809124B (en) | Medical image association calling method and system based on multi-feature fusion | |
| CN112102235A (en) | Human body part recognition method, computer device, and storage medium | |
| CN109978849B (en) | Baseline cell determination method, device and readable medium based on digital pathology image | |
| CN111128348A (en) | Medical image processing method, device, storage medium and computer equipment | |
| CN111292298A (en) | Breast cancer pathological typing determination method, device and storage medium | |
| US10467258B2 (en) | Data categorizing system, method, program software and recording medium therein |
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 |