CN113539471A - Auxiliary diagnosis method and system for hyperplasia of mammary glands based on conventional inspection data - Google Patents
Auxiliary diagnosis method and system for hyperplasia of mammary glands based on conventional inspection data Download PDFInfo
- Publication number
- CN113539471A CN113539471A CN202110326581.8A CN202110326581A CN113539471A CN 113539471 A CN113539471 A CN 113539471A CN 202110326581 A CN202110326581 A CN 202110326581A CN 113539471 A CN113539471 A CN 113539471A
- Authority
- CN
- China
- Prior art keywords
- data
- hyperplasia
- module
- mammary glands
- routine
- 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.)
- Pending
Links
Images
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a method for auxiliary diagnosis of hyperplasia of mammary glands by using conventional test results, belonging to the field of medical test. The overall architecture is as follows: the invention relates to a data acquisition module, a data processing module, a model construction module and an abnormality identification module, which have the beneficial effects that: compared with the prior image level inspection, the invention changes the visual angle and points to the conventional inspection data. The invention predicts the disease degree of the hyperplasia of mammary glands through routine detection of blood routine, urine test, biochemistry and the like, fully exerts the energizing effect of artificial intelligence and reduces the medical and social costs.
Description
Technical Field
The invention relates to the field of testing medicine, in particular to a mammary gland hyperplasia auxiliary diagnosis method and system based on conventional testing data.
Background
The hyperplasia of mammary glands is a common clinical disease for women and has higher morbidity. The main symptoms are hyperplasia of mammary epithelial tissue and fibrous tissue, and the problems of pain, lump in breast and the like of the breast of a patient are caused. If the treatment of hyperplasia of mammary glands is not performed in time, the lump is easy to cause and canceration appears. Therefore, clinical early diagnosis is of great significance for the treatment of diseases.
With the continuous progress and improvement of medical science and technology, the examination and diagnosis of various breast diseases has gradually formed a reasonable diagnosis procedure. At present, the diagnosis of breast diseases is mainly to photograph each level of soft tissue structure in the breast by an imaging instrument such as ultrasonic examination, diagnose various breast diseases by breast lumps, and carry out auxiliary examination by utilizing X-ray examination, ductoscopy, ductography examination, magnetic resonance of the breast and CT to qualitatively and typing the hyperplasia of the breast. For the traditional methods for examining breast diseases like infrared scanning, some limitations of poor definition and resolution exist, and in clinical practice, missed diagnosis and misdiagnosis of breast proliferative diseases are easily caused.
In order to improve the accuracy of doctor image diagnosis, computer-aided diagnosis technology has been proposed as an auxiliary means and applied to clinical diagnosis and treatment decision, and many scholars have also performed relevant research. However, most of the studies are obtained based on clinical studies of doctors, and the analysis methods are generally qualitative and have strong individual subjectivity of doctors, so that the methods cannot be effectively applied to clinical diagnosis practice.
With the continuous emergence of various novel information issuing modes and the rise of technologies such as cloud computing and the internet of things, data is continuously increasing and accumulating at an unprecedented speed. How to more rapidly and accurately mine valuable data from the big data through methods such as machine learning and data mining is a hot spot of research in academia and industry nowadays. At present, a technology for diagnosing the hyperplasia of mammary glands based on machine learning is not disclosed, but a technology for diagnosing the breast cancer by big data assistance exists. In 2019, the invention discloses a method and a system for diagnosing breast cancer based on big data and machine learning, which analyze data of an X-ray image and an ultrasonic image, construct a convolutional neural network with a high-order convolutional layer, and realize classification of benign or malignant breast cancer. In summary, the above techniques are based on the diagnosis of hyperplasia of mammary glands.
Disclosure of Invention
In order to achieve the above purposes, the invention provides a method and a system for diagnosing hyperplasia of mammary glands in an auxiliary manner by using a conventional test result, and aims to solve the problems of low disease identification efficiency and accuracy, high diagnosis cost and higher experience dependence of the existing diagnosis method for hyperplasia of mammary glands. The system comprises a physical examination data reading interface, a computer memory, a computer processor, a neural network frame and a computer display screen; the physical examination data reading interface is connected with the input of the computer processor; the computer memory is bidirectionally coupled to the computer processor; the neural network framework is bidirectionally connected with the computer processor; the computer processor is bidirectionally connected with the computer display screen.
The general architecture created by the invention is as follows: the physical examination system comprises a physical examination data acquisition module, a data processing module, a model construction module and a result identification module. The detailed steps of the sub-modules are described below.
The physical examination data acquisition module: acquiring medical routine inspection data, relating to routine inspection item values such as blood routine, urine inspection, biochemistry and the like.
A data processing module: and further processing the acquired detection data, including operations of removing special values, unifying unit dimensions, filtering outliers, normalizing data, strengthening characteristics and the like.
A model construction module: the module utilizes data after the data processing module and a Machine Learning (ML) corresponding algorithm to carry out modeling.
A result identification module: the module identifies the equipment abnormity by using the model constructed in the step and the processed data.
Compared with the prior art, the invention has the beneficial effects that: at present, the research on the diagnosis technology of the hyperplasia of mammary glands only stays at the image level of the affected area, and the invention changes the visual angle and points to the conventional inspection data. The invention predicts the disease degree of the hyperplasia of mammary glands through routine detection data such as blood routine, urine test, biochemistry and the like, fully exerts the energizing effect of artificial intelligence and reduces the medical and social costs.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application and should not be construed as unduly limiting the present application.
Fig. 1 is a schematic structural view of the present invention.
FIG. 2 is a flowchart of the prediction method of the system for predicting a mammary gland hyperplasia disease in the present invention.
Fig. 3 is a structural diagram of a neural network used in the present invention.
Fig. 4 is a schematic structural diagram of a mammary gland hyperplasia auxiliary diagnosis system based on conventional test data.
Detailed Description
Fig. 1 shows an overall structure of a method and a system for diagnosing hyperplasia of mammary glands based on conventional test data according to an embodiment of the present invention, and the following describes in detail a technical implementation method according to an embodiment of the present invention with fig. 1 as a main line.
Referring to fig. 1, the method of the present embodiment includes a physical examination data acquisition module, a data processing module, a model construction module, and a result identification module.
The data acquisition module of the embodiment is mainly the test result data of the lis system, and the data is the indexes of blood routine, urine test, biochemistry and the like of the patient who is subjected to the mammary gland hyperplasia examination. The quality of the data obtained by the above conditions is effectively guaranteed.
Preferably, the data processing module of this embodiment includes the following steps.
The special value is removed, and data containing non-numeric results such as character strings exists in the inspection result data.
The unit dimensions of the data are uniform, the data units of the items corresponding to each sample need to be ensured to be consistent when the data are analyzed, and the data analysis results have great deviation due to the inconsistent units.
Further, influence factor analysis is carried out on the test sample data, and characteristic dimension determination and extraction are achieved.
And further, filling missing values of dimensions of the test sample data.
Further, one or more classifiers suitable for intelligent identification of tuberculosis are generated based on the test sample data.
In order to enhance the generalization capability of the model, algorithms such as a full-connection neural network and the like are tried to perform supervised classification training, and a mammary gland hyperplasia classification model is established by using Q-Learning of a Tensorflow framework.
The flow chart of the method for predicting the hyperplasia of mammary glands is shown in fig. 2, wherein the training phase of the model comprises the following steps.
Firstly, the input sets are extracted one by one and provided for the neurons of the input layer, and the signals are transmitted forward layer by layer until an output result is generated. And then calculating the deviation of an output layer, reversely transmitting the deviation to a hidden layer neuron, finally adjusting the connection weight and the threshold value according to the error of the hidden layer neuron, and circularly performing the iterative process until all data sets are trained and the training error reaches a certain range.
The neural network structure is as shown in fig. 3, the number of neurons of the network input layer, the hidden layer and the output layer is respectively expressed by n, l and m, and the connection weight among the neurons is represented; an activation function for hidden neurons; being a threshold of a neuron, for a 3-layer neural network structure, the input and output relationship can be described as:。
the activation function is also called 'response function' and is used for processing the output of the neuron, and the ideal activation function is a step function of 0/1 type, but the step function has the defects of discontinuity and non-smoothness. Therefore, a Sigmoid function is commonly used as an activation function, which is smoother and can push a large range of input values into a range of (0,1) output values, and the function form is as follows:。
updating parameters by adopting a generalized perception machine learning rule in each iteration, wherein the algorithm is based on a gradient descent strategy and aims atThe negative gradient direction of (2) adjusts the parameters with the goal of minimizing the cumulative error on the training setThe actual output of the network is made as close as possible to the desired output.
The preferred process for the classifier includes: dividing test sample data into a positive data group and a negative data group according to historical test results, establishing a training set, a verification set and a test set of the positive data group and the negative data group, respectively training classifiers according to the training sets of the positive data group and the negative data group, optimizing type height parameters and structures of the classifiers through the verification set, drawing roc curves through the test set, and evaluating the classifiers according to the area auc under the roc curves so as to finish the optimization of the classifiers.
And (4) deploying the optimal classifier to a real-time hospital lis system, and receiving real-time inspection data to finish intelligent identification of the hyperplasia of mammary glands. The corresponding equipment interface is connected according to the configuration of the figure 4, and the system comprises a physical examination data reading interface, a computer memory, a computer processor, a neural network frame and a computer display screen; the physical examination data reading interface is connected with the input of the computer processor; the computer memory is bidirectionally coupled to the computer processor; the neural network framework is bidirectionally connected with the computer processor; the computer processor is bidirectionally connected with the computer display screen.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes, modifications and equivalents may be made therein without departing from the spirit and scope of the invention.
Claims (4)
1. A method for assisting in diagnosing hyperplasia of mammary glands by using conventional test results is characterized by comprising a data acquisition module, a data processing module, a model construction module and an abnormality identification module.
2. The system is characterized in that: comprises physical examination data collection equipment, a computer memory, a computer processor, a neural network framework and a computer display screen.
3. The method for identifying the equipment abnormality based on the machine learning technology as claimed in claim 1, wherein the data required to be provided by the data acquisition module are routine physical examination items of the patient, including blood routine and biochemical indicators, and the prediction accuracy is reduced due to incomplete items.
4. The method for identifying the equipment abnormality based on the machine learning technology as claimed in claim 1, wherein the outlier processing method of the data in the data processing module adopts an isolated forest model to perform outlier filtering, and the proportion of the actual filtering abnormality should be adjusted properly according to the distribution of the data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110326581.8A CN113539471A (en) | 2021-03-26 | 2021-03-26 | Auxiliary diagnosis method and system for hyperplasia of mammary glands based on conventional inspection data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110326581.8A CN113539471A (en) | 2021-03-26 | 2021-03-26 | Auxiliary diagnosis method and system for hyperplasia of mammary glands based on conventional inspection data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113539471A true CN113539471A (en) | 2021-10-22 |
Family
ID=78094498
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110326581.8A Pending CN113539471A (en) | 2021-03-26 | 2021-03-26 | Auxiliary diagnosis method and system for hyperplasia of mammary glands based on conventional inspection data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113539471A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018120942A1 (en) * | 2016-12-31 | 2018-07-05 | 西安百利信息科技有限公司 | System and method for automatically detecting lesions in medical image by means of multi-model fusion |
CN109830303A (en) * | 2019-02-01 | 2019-05-31 | 上海众恒信息产业股份有限公司 | Clinical data mining analysis and aid decision-making method based on internet integration medical platform |
CN110379509A (en) * | 2019-07-23 | 2019-10-25 | 安徽磐众信息科技有限公司 | A kind of Breast Nodules aided diagnosis method and system based on DSSD |
CN111243730A (en) * | 2020-01-17 | 2020-06-05 | 视隼智能科技(上海)有限公司 | Mammary gland focus intelligent analysis method and system based on mammary gland ultrasonic image |
CN112070125A (en) * | 2020-08-19 | 2020-12-11 | 西安理工大学 | Prediction method of unbalanced data set based on isolated forest learning |
-
2021
- 2021-03-26 CN CN202110326581.8A patent/CN113539471A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018120942A1 (en) * | 2016-12-31 | 2018-07-05 | 西安百利信息科技有限公司 | System and method for automatically detecting lesions in medical image by means of multi-model fusion |
CN109830303A (en) * | 2019-02-01 | 2019-05-31 | 上海众恒信息产业股份有限公司 | Clinical data mining analysis and aid decision-making method based on internet integration medical platform |
CN110379509A (en) * | 2019-07-23 | 2019-10-25 | 安徽磐众信息科技有限公司 | A kind of Breast Nodules aided diagnosis method and system based on DSSD |
CN111243730A (en) * | 2020-01-17 | 2020-06-05 | 视隼智能科技(上海)有限公司 | Mammary gland focus intelligent analysis method and system based on mammary gland ultrasonic image |
CN112070125A (en) * | 2020-08-19 | 2020-12-11 | 西安理工大学 | Prediction method of unbalanced data set based on isolated forest learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Shoeibi et al. | Automated detection and forecasting of covid-19 using deep learning techniques: A review | |
JP6522161B2 (en) | Medical data analysis method based on deep learning and intelligent analyzer thereof | |
CN113040715B (en) | Human brain function network classification method based on convolutional neural network | |
Sharma et al. | Deep learning applications for disease diagnosis | |
CN111626114B (en) | Electrocardiosignal arrhythmia classification system based on convolutional neural network | |
CN111429407A (en) | Chest X-ray disease detection device and method based on two-channel separation network | |
Menaouer et al. | Diabetic retinopathy classification using hybrid deep learning approach | |
Huang et al. | A structure-related fine-grained deep learning system with diversity data for universal glaucoma visual field grading | |
Zeng et al. | Automated detection of diabetic retinopathy using a binocular siamese-like convolutional network | |
Kang et al. | Automatic detection of diabetic retinopathy with statistical method and Bayesian classifier | |
CN113782184A (en) | Cerebral apoplexy auxiliary evaluation system based on facial key point and feature pre-learning | |
Das et al. | Automated classification of retinal OCT images using a deep multi-scale fusion CNN | |
Manikandan et al. | Segmentation and Detection of Pneumothorax using Deep Learning | |
Liu et al. | A cross-lesion attention network for accurate diabetic retinopathy grading with fundus images | |
Kotiyal et al. | Diabetic retinopathy binary image classification using PySpark | |
Xue et al. | CT-based COPD identification using multiple instance learning with two-stage attention | |
CN113539471A (en) | Auxiliary diagnosis method and system for hyperplasia of mammary glands based on conventional inspection data | |
Jing et al. | Optimization of Deep-learning network using Resnet50 based model for corona virus disease (COVID-19) histopathological image classification | |
Verma et al. | Methodologies, Applications, and Challenges of Pneumonia Detection of Chest X-Ray images for COVID-19 using IoT-enabled Deep Learning | |
Li et al. | DCT-Net: An effective method to diagnose retinal tears from B-scan ultrasound images | |
Taş et al. | Detection of retinal diseases from ophthalmological images based on convolutional neural network architecture. | |
Sasikumar et al. | Deep Convolutional Generative Adversarial Networks for Automated Segmentation and Detection of Lung Adenocarcinoma Using Red Deer Optimization Algorithm | |
Kikoo et al. | Using Various Convolutional Neural Network to Detect Pneumonia from Chest X-Ray Images: A Systematic Literature Review | |
Srirangam | Artificial Intelligence Based Hyper-parameter Adjustment on Deep Neural Networks: An Application of Detection and Classification of COVID-19 Diseases | |
Kavitha et al. | Classification of lung tuberculosis using non parametric and deep neural network techniques |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211022 |
|
WD01 | Invention patent application deemed withdrawn after publication |