CN113345558A - Auxiliary system and method for improving orthopedic diagnosis decision-making efficiency - Google Patents
Auxiliary system and method for improving orthopedic diagnosis decision-making efficiency Download PDFInfo
- Publication number
- CN113345558A CN113345558A CN202110734554.4A CN202110734554A CN113345558A CN 113345558 A CN113345558 A CN 113345558A CN 202110734554 A CN202110734554 A CN 202110734554A CN 113345558 A CN113345558 A CN 113345558A
- Authority
- CN
- China
- Prior art keywords
- information set
- information
- disease
- obtaining unit
- key point
- 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.)
- Withdrawn
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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides an auxiliary system and a method for improving the decision-making efficiency of orthopedic diagnosis, wherein the method comprises the following steps: acquiring disease condition information of a first patient, wherein the disease condition information comprises examination image information, and acquiring a first disease characteristic information set, and the first disease characteristic information set comprises a first key point information set and a second key point information set; constructing a first structure three-dimensional model diagram according to the first disease information set; obtaining a first correction parameter according to the first structure three-dimensional model diagram; correcting the first key point information set and the second key point information set according to the first correction parameter to obtain a third key point information set and a fourth key point information set; the third key point information set and the fourth key point information set are input into an orthopedic diagnosis evaluation model, a first evaluation result is obtained and sent to an expert platform, and a second evaluation result is obtained according to expert opinions, so that the technical problem that in the prior art, the application range is small due to the fact that only auxiliary diagnosis of orthopedic diseases with obvious characteristic points can be performed is solved.
Description
Technical Field
The invention relates to the technical field related to artificial intelligence, in particular to an auxiliary system and method for improving the decision-making efficiency of orthopedic diagnosis.
Background
Since orthopedics diagnosis needs to rely on the reading of medical images, the application of Al in orthopedics has mainly focused on the deep learning of these images. The deep learning can autonomously analyze the medical images, thereby improving the accuracy and speed of diagnosis, preferentially marking emergency patients, reducing human errors caused by fatigue and/or inexperience, reducing the burden and pressure of workers, and improving the diagnosis and treatment of orthopedics to a certain extent. In addition, the deep learning method training is carried out according to the professional knowledge of experienced doctors, the experiences can be shared in smaller medical institutions and more remote areas, and the application and research of the AI in the orthopedic diagnosis have good development prospects.
At present, the main problems in the orthopedics department image data include fracture, spinal degeneration, deformity, joint diseases and the like, the consistency of the diseases is that the characteristic information of the orthopedics department is obvious, and the identification is easy to carry out deep learning.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
in the prior art, the technical problem of small application range is caused only by aiming at the auxiliary diagnosis of the orthopedic diseases with obvious characteristic points.
Disclosure of Invention
The embodiment of the application provides an intelligent management method and system for orthopedic implants, and solves the technical problem that in the prior art, the application range is small due to the fact that only orthopedic diseases with obvious characteristic points can be diagnosed in an auxiliary mode. The method has the advantages that the basic information of the state of an illness of the patient is combined, on the basis of carrying out feature recognition on the image of the patient, three-dimensional modeling is carried out again to extract feature information, more comprehensive feature data is obtained, and then the state of an illness of the orthopedic patient is evaluated through intelligent model analysis.
In view of the above problems, the embodiments of the present application provide an auxiliary system and method for improving the decision efficiency of orthopedic diagnosis.
In a first aspect, an auxiliary system for improving the decision efficiency of orthopedic diagnosis is provided in an embodiment of the present application, the system includes: the first obtaining unit is used for obtaining disease condition information of a first patient, and the disease condition information comprises examination image information; a second obtaining unit, configured to obtain a first disease feature information set according to the examination image information, where the first disease feature information set includes a first key point information set and a second key point information set; a first construction unit for constructing a first structural three-dimensional model map from the first disease information set; a third obtaining unit, configured to obtain a first correction parameter according to the first structural three-dimensional model map; a fourth obtaining unit, configured to correct the first keypoint information set and the second keypoint information set according to the first correction parameter, and obtain a third keypoint information set and a fourth keypoint information set; a fifth obtaining unit, configured to input the third keypoint information set and the fourth keypoint information set into an orthopedic diagnosis evaluation model to obtain a first evaluation result; and the sixth obtaining unit is used for sending the first evaluation result to an expert platform and obtaining a second evaluation result according to the reference opinions of the experts.
In another aspect, an embodiment of the present application provides an auxiliary method for improving the decision efficiency of orthopedic diagnosis, where the method includes: acquiring disease condition information of a first patient, wherein the disease condition information comprises examination image information; acquiring a first disease characteristic information set according to the inspection image information, wherein the first disease characteristic information set comprises a first key point information set and a second key point information set; constructing a first structure three-dimensional model map according to the first disease information set; obtaining a first correction parameter according to the first structure three-dimensional model diagram; correcting the first key point information set and the second key point information set according to the first correction parameter to obtain a third key point information set and a fourth key point information set; inputting the third key point information set and the fourth key point information set into an orthopedic diagnosis evaluation model to obtain a first evaluation result; and sending the first evaluation result to an expert platform, and obtaining a second evaluation result according to the reference opinions of the experts.
In a third aspect, the present application provides an assistance system for improving the efficiency of orthopedic diagnostic decision making, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the system according to any one of the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
acquiring disease condition information of a first patient, wherein the disease condition information comprises examination image information; acquiring a first disease characteristic information set according to the inspection image information, wherein the first disease characteristic information set comprises a first key point information set and a second key point information set; constructing a first structure three-dimensional model map according to the first disease information set; obtaining a first correction parameter according to the first structure three-dimensional model diagram; correcting the first key point information set and the second key point information set according to the first correction parameter to obtain a third key point information set and a fourth key point information set; inputting the third key point information set and the fourth key point information set into an orthopedic diagnosis evaluation model to obtain a first evaluation result; the technical scheme that the first evaluation result is sent to an expert platform, and the second evaluation result is obtained according to reference opinions of experts is achieved, so that basic information of the state of an illness of a patient is combined, three-dimensional modeling is carried out on the basis of carrying out feature recognition on an image of the patient, feature information is extracted, more comprehensive feature data is obtained, then the state of the illness of the orthopedic patient is evaluated through intelligent model analysis, the features can be extracted more comprehensively due to multiple times of feature extraction, and in addition, the intelligent model is analyzed, so that decision-making efficiency is improved, and the technical effect of an auxiliary technology which has a wide applicability range and improves decision-making efficiency of orthopedic diagnosis is achieved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
FIG. 1 is a schematic flow chart illustrating an auxiliary method for improving decision efficiency of orthopedic diagnosis according to an embodiment of the present application;
fig. 2 is a flowchart illustrating a method for obtaining a first disease characteristic information set based on the inspection image information, where the first disease characteristic information set includes a first key point information set and a second key point information set according to the embodiment of the present application;
FIG. 3 is a flowchart illustrating a method for constructing a three-dimensional model map of a first structure according to the first disease characteristic information set according to an embodiment of the present application;
FIG. 4 is a schematic flow chart illustrating another method for improving decision efficiency of orthopedic diagnosis according to an embodiment of the present application;
FIG. 5 is a schematic structural diagram of an auxiliary system for improving decision-making efficiency of orthopedic diagnosis according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a first constructing unit 13, a third obtaining unit 14, a fourth obtaining unit 15, a fifth obtaining unit 16, a sixth obtaining unit 17, an electronic device 300, a memory 301, a processor 302, a communication interface 303, and a bus architecture 304.
Detailed Description
The embodiment of the application provides an intelligent management method and system for orthopedic implants, and solves the technical problem that in the prior art, the application range is small due to the fact that only orthopedic diseases with obvious characteristic points can be diagnosed in an auxiliary mode. The method has the advantages that the basic information of the state of an illness of the patient is combined, on the basis of carrying out feature recognition on the image of the patient, three-dimensional modeling is carried out again to extract feature information, more comprehensive feature data is obtained, and then the state of an illness of the orthopedic patient is evaluated through intelligent model analysis.
Summary of the application
Since orthopedics diagnosis needs to rely on the reading of medical images, the application of Al in orthopedics has mainly focused on the deep learning of these images. The deep learning can autonomously analyze the medical images, thereby improving the accuracy and speed of diagnosis, preferentially marking emergency patients, reducing human errors caused by fatigue and/or inexperience, reducing the burden and pressure of workers, and improving the diagnosis and treatment of orthopedics to a certain extent. In addition, the deep learning method training according to the professional knowledge of experienced doctors can share the experience to smaller medical institutions and remote areas, the application and research of AI in orthopedic diagnosis has good development prospect, the problems mainly aiming at orthopedic image data at present include fracture, spinal degeneration, deformity, joint diseases and the like, the consistency of the diseases is that the characteristic information of orthopedic disease sites is obvious, and the deep learning is easy to identify. However, in the prior art, the technical problem of small application range exists because only the auxiliary diagnosis of orthopedic diseases with obvious characteristic points can be performed.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides an auxiliary method for improving the decision-making efficiency of orthopedic diagnosis, which comprises the following steps: acquiring disease condition information of a first patient, wherein the disease condition information comprises examination image information; acquiring a first disease characteristic information set according to the inspection image information, wherein the first disease characteristic information set comprises a first key point information set and a second key point information set; constructing a first structure three-dimensional model map according to the first disease information set; obtaining a first correction parameter according to the first structure three-dimensional model diagram; correcting the first key point information set and the second key point information set according to the first correction parameter to obtain a third key point information set and a fourth key point information set; inputting the third key point information set and the fourth key point information set into an orthopedic diagnosis evaluation model to obtain a first evaluation result; and sending the first evaluation result to an expert platform, and obtaining a second evaluation result according to the reference opinions of the experts.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides an auxiliary method for improving the decision efficiency of orthopedic diagnosis, the method including:
s100: acquiring disease condition information of a first patient, wherein the disease condition information comprises examination image information;
specifically, the condition information of the first patient refers to the condition of the patient with orthopedic diseases, wherein the diseases of the first patient include orthopedic diseases with obvious characteristics such as fracture, spinal degeneration, deformity and joint diseases, and also include orthopedic diseases with unobvious characteristics such as lumbar vertebra injury and tendon injury. The disease condition information comprises data such as the age, the sex, the related past medical history, the past examination image information, the examination image information and the like of the patient. Through the onset part of the orthopedic disease of the first patient, the corresponding disease information can be classified and stored, for example, the disease information is classified into two categories of arthrosis and spine disease, and is preferably stored in a cloud database, wherein the cloud database is a virtual database which is a stable, reliable and elastically telescopic online database. And providing an information basis for subsequent diagnosis by calling and storing the illness state information of the first patient.
S200: acquiring a first disease characteristic information set according to the inspection image information, wherein the first disease characteristic information set comprises a first key point information set and a second key point information set;
specifically, the first disease feature information set is to perform image recognition on the examination image information of the first patient to extract feature information of a diseased part, and a preferred implementation mode may perform feature extraction through a feature extraction model trained based on a convolutional neural network, where convolution may be used as a feature extractor in machine learning, so that the extracted feature information has concentration and representativeness, and further convolution features of the examination image information are obtained, and the convolutional neural network is one of neural networks and has an excellent recognition function for feature extraction, particularly, image feature extraction. The first key point information set is information of the inside of an abnormal region such as the position and shape of the first patient-onset abnormal region, and the second key point information set is information of abnormality of a region in the vicinity of the first patient-onset abnormal region. More significant characteristic information of the orthopaedic disease of the first patient may be preliminarily characterized by the first disease characteristic information set.
S300: constructing a first structure three-dimensional model map according to the first disease characteristic information set;
s400: obtaining a first correction parameter according to the first structure three-dimensional model diagram;
specifically, the first structural three-dimensional model map is a three-dimensional model map obtained by combining the first disease characteristic information set with the actual scene of the internal environment of the first patient, and the first structural three-dimensional model map is obtained by constructing a general three-dimensional frame from the first disease characteristic information and then restoring the general three-dimensional frame according to the scene of the first patient, and can reflect the state of illness of the first patient more realistically. In addition, when the first patient performs an operation, the first structure three-dimensional model can be printed, so that the success rate of the operation is improved.
Further, the first correction parameter refers to more detailed characteristic information related to the orthopedic disease of the first patient obtained by performing feature extraction again on the first structural three-dimensional model map. The first correction parameter represents the feature information which is not contained in the first disease feature information set, and the feature information which is not obvious can be extracted in vitro through the first structural three-dimensional model diagram, so that the technical effect of extracting the feature information more comprehensively is achieved.
S500: correcting the first key point information set and the second key point information set according to the first correction parameter to obtain a third key point information set and a fourth key point information set;
specifically, the first keypoint information set is corrected to obtain the third keypoint information set based on feature extraction of the first correction parameter for more details of information inside the abnormal region, such as the position and the shape of the first patient disease abnormal region; and correcting the second key point information set to obtain the fourth key point information set based on the feature extraction of the first correction parameter for more details of the abnormal information of the area near the first patient abnormal disease occurrence area. The third key point information set and the fourth key point information set comprehensively represent the orthopedic disease condition information of the first patient.
S600: inputting the third key point information set and the fourth key point information set into an orthopedic diagnosis evaluation model to obtain a first evaluation result;
specifically, the first evaluation result information is a diagnosis result of the orthopedic disease of the first patient obtained by inputting the third keypoint information set and the fourth keypoint information set into the orthopedic diagnosis evaluation model for intelligent analysis, the orthopedic diagnosis evaluation model is built on the basis of a neural network model, and has characteristics of a neural network model, wherein the artificial neural network is an abstract mathematical model which is proposed and developed on the basis of modern neuroscience and is intended to reflect the structure and function of the human brain, the neural network is an operation model and is formed by connecting a large number of nodes (or called neurons) with each other, each node represents a specific output function called an excitation function, the connection between every two nodes represents a weighted value for signals passing through the connection, called a weight, which is equivalent to the memory of the artificial neural network, the output of the network is the expression of a logic strategy according to the connection mode of the network, and the orthopedic diagnosis evaluation model established based on the neural network model can output accurate first evaluation result information, so that the method has stronger analysis and calculation capacity and achieves the accurate and efficient technical effect.
S700: and sending the first evaluation result to an expert platform, and obtaining a second evaluation result according to the reference opinions of the experts.
Specifically, the first evaluation result is an intelligent evaluation result obtained by the orthopedic diagnosis evaluation model. Further, the first evaluation result is sent to an expert platform, and an expert mainly based on a doctor who is mainly attending the first patient evaluates and corrects the first evaluation result, so that an orthopedic disease diagnosis result of the first patient, namely the second evaluation result, is obtained. The first evaluation result is given by the orthopedic diagnosis evaluation model, the efficiency is high, and the main doctor of the first patient can obtain the second evaluation result only by confirming and slightly modifying the first evaluation result, so that the technical effect of improving the orthopedic diagnosis decision-making efficiency of the first patient is achieved.
Further, based on the examination image information, a first disease feature information set is obtained, where the first disease feature information set includes a first key point information set and a second key point information set, as shown in fig. 2, and the method step S200 further includes:
s210: constructing a first examination image database according to the examination image information to obtain a first image set;
s220: obtaining a target convolution characteristic based on the first inspection image database;
s230: performing traversal convolution operation on the first image set according to the target convolution characteristic to obtain a first convolution result;
s240: obtaining the first disease characteristic information set according to the first convolution result, wherein the first disease characteristic information set and the first image set have a first mapping relation;
s250: and obtaining the first key point information set and the second key point information set according to the first disease characteristic information set and the first image set based on the first mapping relation.
Specifically, the first examination image database refers to a database constructed by storing the examination image information of the first patient in a sorted manner, preferably in a sorted manner with a time element as a first priority and a position element as a second priority. Wherein the examination image information comprises historical examination image information and current examination image information of the orthopedic diseases of the first patient. The first image set refers to the image set of the first patient retrieved from the first examination image database according to classification, and for example, the first image set is sequentially retrieved from top to bottom by position elements, and the obtained information is easier to manage and calculate.
Further, the target convolution feature refers to a result obtained by performing convolution feature extraction on the inspection image in the first inspection image database, and as described above, the convolution feature can be extracted by using a convolution feature extraction model based on convolutional neural network training, so that the target convolution feature information is obtained more accurately.
Furthermore, the first image set is subjected to traversal convolution operation based on the target convolution feature, the distribution probability of the target convolution feature in each image information of the first image set is calculated, and when the distribution probability of the target convolution feature reaches a preset threshold value, the target convolution feature can be used as the first convolution result corresponding to the first image set. The threshold is set according to the actual situation, and is not limited herein.
Further, storing the first influence set and the corresponding first volume result to obtain the first disease characteristic information set; the first mapping relation refers to a feature mapping chart of the first disease feature information set and the first image set, and is preferably obtained by multiplying a feature matrix formed by the first image set and the first disease feature information set, and the first mapping relation can represent all the first disease feature information sets corresponding to the regions of the first image set. Furthermore, the first disease characteristic information sets are sorted based on the first mapping relationship to obtain the first key point information set representing information inside abnormal regions such as positions and shapes of the abnormal regions of the first patient and the second key point information set representing abnormal information of the regions near the abnormal regions of the first patient. The examination image information is classified, stored and managed by constructing the first examination image database, feature extraction is carried out by utilizing convolution operation, the dimension of the examination image information is reduced, and meanwhile, the first key point information set and the second key point information set are classified to represent the orthopedic disease condition of the first patient, so that the information is disordered and redundant, and the technical effect of improving the decision efficiency is achieved.
Further, based on the constructing a first three-dimensional model map of the structure according to the first disease characteristic information set, as shown in fig. 3, the method S300 further includes:
s310: constructing an image three-dimensional modeling system;
s320: obtaining a first sparse matrix according to the first disease characteristic information set;
s330: obtaining a first sparse point set according to the first sparse matrix;
s340: inputting the first sparse point set into the image three-dimensional modeling system to obtain a first approximate three-dimensional model;
s350: generating a first initial point cloud according to the inspection image information;
s360: performing point cloud diffusion on the first initial point cloud to obtain a first diffusion result;
s370: obtaining a first dense point set according to the first diffusion result;
s380: and inputting the first dense point set and the first approximate three-dimensional model into the image three-dimensional modeling system to obtain the first structure three-dimensional model diagram.
Specifically, the image three-dimensional modeling system refers to an intelligent model capable of performing full-automatic three-dimensional modeling based on images, and obtains the first sparse matrix capable of generally representing disease information of the first patient at the disease onset position by detecting feature points in the first disease feature information set and matching the feature points. Further, the first sparse point set is extracted from the first sparse matrix based on the position information and the size information of each feature point, and the first sparse point set represents that each feature point is subjected to sparse decomposition to obtain sparse vectors with the same basic size unit and different results. Furthermore, based on the first sparse point set, the first sparse point set is input into the image three-dimensional modeling system, and sparse vectors are rebuilt according to results to form the first approximate three-dimensional model capable of representing each feature point.
Furthermore, the first initial point cloud is obtained by comparing the appearance of the similar human body based on the inspection image information, preferably in combination with the orthopedic disease condition of the first patient and the appearance of the orthopedic disease diseased part, and obtaining a set of inference image feature points which are more in line with the actual condition of the first patient through inference and evolution, wherein the set of inference image feature points is characterized by obtaining position information and size information of the feature points through inference. The point cloud diffusion refers to gradually increasing the point cloud based on the first initial point cloud by combining with the orthopedic disease condition of the first patient until the appearance information of the disease onset position of the first patient can be represented, and the result is the first diffusion result. The first dense point set refers to point cloud information covering a whole area after diffusion. And inputting the first dense point set and the first approximate three-dimensional model into the image three-dimensional modeling system to obtain the first structure three-dimensional model diagram. The first approximate three-dimensional model constructed based on the first disease characteristic information set can represent more obvious characteristic information of the first patient, the first structure three-dimensional model diagram constructed by combining the first initial point cloud and the first approximate three-dimensional model is obtained through reasoning, more obvious and less obvious characteristic information of the first patient can be represented, and the orthopedic assistant decision making application range is wider.
Further, based on the generating of the first initial point cloud according to the inspection image information, the method step S350 further includes:
s351: obtaining a first noise set according to the inspection image information set;
s352: performing cluster analysis on the first noise set to obtain a first classification result;
s353: constructing a first function according to the first classification result, wherein the first function reflects the correlation between the inspection image information and the first noise set;
s354: constructing a first image denoising model;
s355: inputting the first inspection image information set and the first function into the first image denoising model to obtain a first denoising image set;
s356: and generating the first initial point cloud according to the first denoising image set.
Specifically, the original inspection image information is redundant and has too much interference information, so that in order to ensure the high efficiency and accuracy of information processing, the original inspection image information needs to be denoised, the image quality can be effectively improved through a denoising technology, the signal-to-noise ratio is increased, and the information carried by the original image is better embodied. The first noise set refers to a factor information set which can prevent the received source information from being understood, such as the required brightness distribution f for observing a certain position of orthopedic diseases of the first patient
The distribution of brightness which causes the abnormal observation is T
Then T is
It is noise. Furthermore, because different image noise removing methods are different, the first noise set needs to be clustered, and the first noise set is classified into quantization noise (difference between a digital image and an original image), multiplicative noise (error caused when an image is scanned), and transformation error noise (image noise) without limitationSuch as errors caused by image transformation), and the obtained result is the first classification result. Further, according to the relevance of the inspection image information of each type of noise in the first classification result, for example, the relationship between the scanning times and time in multiplicative noise and the missing degree of the inspection image information. And counting to obtain a result by recording a plurality of groups of data, and constructing the first function. The first image denoising model is a model for denoising the first examination image information set based on the first function, and can be used for training the denoising model suitable for the first patient according to an algorithm, or selecting an existing model if the information is not enough. The first denoising image set refers to a higher-quality image set subjected to denoising processing, and can represent orthopedic disease information of the first patient, almost has no noise interference of other images, and is more beneficial to feature extraction.
Further, as shown in fig. 4, the method further includes step S800:
s810: constructing a first similar historical disease information database based on big data according to the disease information of the first patient;
s820: obtaining a second disease characteristic information set according to the first similar historical disease information database;
s830: obtaining a first historical diagnosis result according to the second disease characteristic information set;
s840: and adjusting the second evaluation result according to the first historical diagnosis result to obtain a third evaluation result.
Specifically, the first similar historical disease information database is used for screening and storing and managing disease information similar to or identical to the disease information of the first patient in big data by taking the disease information of the first patient as an index; the second disease characteristic information set refers to examination image information of a patient based on the history in the first similar historical disease information database, and a disease characteristic information set evaluated at that time is obtained. Further, the corresponding first historical diagnosis result is obtained according to the second disease characteristic information set. The third evaluation result refers to a result obtained by appropriately adjusting the second evaluation result based on the first historical diagnosis result information. In an implementation manner, as an example without limitation, a region to be adjusted is preset, and if the first historical diagnosis result is within the region, the adjustment is performed, and if the first historical diagnosis result is outside the region, the adjustment is not performed. On the basis of a second evaluation result obtained based on two times of feature extraction, the data of historical patients are introduced, so that the diagnosis accuracy is improved, the generalization of the feature information of the first patient is facilitated, and a more accurate evaluation result is obtained.
Further, based on the obtaining a first historical diagnosis result according to the second disease characteristic information set, the method step S830 further includes:
s831: obtaining a first characteristic information preset threshold;
s832: comparing the first disease characteristic information set with the second disease characteristic information set to obtain a first comparison result, wherein the first comparison result comprises the quantity of similar characteristic information;
s833: judging whether the quantity of the similar characteristic information is within a preset threshold value of the first characteristic information;
s834: and if the quantity of the similar characteristic information is within the first characteristic information preset threshold value, obtaining the corresponding first historical diagnosis result.
Specifically, the preset threshold of the first feature information refers to a set threshold for the first disease feature information, for example, a feature quantity threshold is set, the first disease feature information set and the second disease feature information set are compared, an initial value k =0 of a counter is set, when the first disease feature information set and the second disease feature information set have a same feature, an operation of adding one to k is performed, when the comparison of each group of the first disease feature information and the second disease feature information is finished, counting is stopped, the counting and the corresponding second disease feature information are stored in a one-to-one correspondence manner, after the storage is finished, k =0 is set, and the next group is compared until the comparison of the first disease feature information set and the second disease feature information set is finished. Furthermore, the k value of each group is compared with the first characteristic information preset threshold, the second disease characteristic information set which meets the first characteristic information preset threshold is left, the corresponding first historical diagnosis result is obtained, and the rest are deleted. Through screening of the second disease characteristic information, the data redundancy is reduced, and meanwhile, the accuracy of an evaluation result is improved.
Further, based on the inputting the third key point information set and the fourth key point information set into the orthopedic diagnosis evaluation model, a first evaluation result is obtained, and step S600 further includes:
s610: inputting the third key point information set and the fourth key point information set into the orthopedic diagnosis and evaluation model, wherein the orthopedic diagnosis and evaluation model is obtained by training multiple sets of training data, and each set of training data in the multiple sets of training data comprises: the third set of keypoint information, the fourth set of keypoint information, and identification information used to identify the first evaluation result;
s620: obtaining a first output of the orthopedic diagnostic evaluation model, wherein the first output is the first evaluation of disease information for the first patient.
In particular, the orthopedic diagnosis and evaluation model is also a neural network model, namely a neural network model in machine learning, which reflects many basic characteristics of human brain functions and is a highly complex nonlinear dynamical learning system. Wherein, it can carry out continuous self-training study according to training data, each group of training data in the multiunit all includes: the third set of keypoint information, the fourth set of keypoint information, and identification information to identify the first evaluation result. And continuously self-correcting the orthopedic diagnosis and evaluation model, and finishing the supervised learning process when the output information of the orthopedic diagnosis and evaluation model reaches a preset accuracy rate/convergence state. By carrying out data training on the orthopedic diagnosis and evaluation model, the orthopedic diagnosis and evaluation model can process input data more accurately, so that the output first evaluation result information is more accurate, the data information can be accurately obtained, and the intelligent technical effect of the evaluation result can be improved.
In summary, the auxiliary system and method for improving the decision efficiency of orthopedic diagnosis provided by the embodiments of the present application have the following technical effects:
1. the method has the advantages that the basic information of the state of an illness of the patient is combined, on the basis of carrying out feature recognition on the image of the patient, three-dimensional modeling is carried out again to extract feature information, more comprehensive feature data is obtained, and then the state of an illness of the orthopedic patient is evaluated through intelligent model analysis.
2. On the basis of a second evaluation result obtained based on two times of feature extraction, the data of historical patients are introduced, so that the diagnosis accuracy is improved, the generalization of the feature information of the first patient is facilitated, and a more accurate evaluation result is obtained.
3. The first approximate three-dimensional model constructed based on the first disease characteristic information set can represent more obvious characteristic information of the first patient, the first structure three-dimensional model diagram constructed by combining the first initial point cloud and the first approximate three-dimensional model is obtained through reasoning, more obvious and less obvious characteristic information of the first patient can be represented, and the orthopedic assistant decision making application range is wider.
Example two
Based on the same inventive concept as the method for assisting in improving the efficiency of an orthopedic diagnosis decision in the foregoing embodiments, as shown in fig. 5, an embodiment of the present application provides an assisting system for improving the efficiency of an orthopedic diagnosis decision, where the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain disease condition information of a first patient, where the disease condition information includes examination image information;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain a first disease feature information set according to the examination image information, where the first disease feature information set includes a first key point information set and a second key point information set;
a first constructing unit 13, wherein the first constructing unit 13 is configured to construct a first structural three-dimensional model map according to the first disease characteristic information set;
a third obtaining unit 14, where the third obtaining unit 14 is configured to obtain a first correction parameter according to the first structural three-dimensional model map;
a fourth obtaining unit 15, where the fourth obtaining unit 15 is configured to modify the first keypoint information set and the second keypoint information set according to the first modification parameter, and obtain a third keypoint information set and a fourth keypoint information set;
a fifth obtaining unit 16, wherein the fifth obtaining unit 16 is configured to input the third keypoint information set and the fourth keypoint information set into an orthopedic diagnosis evaluation model to obtain a first evaluation result;
a sixth obtaining unit 17, where the sixth obtaining unit 17 is configured to send the first evaluation result to an expert platform, and obtain a second evaluation result according to the reference opinion of the expert.
Further, the system further comprises:
a seventh obtaining unit, configured to construct a first examination image database according to the examination image information, and obtain a first image set;
an eighth obtaining unit, configured to obtain a target convolution feature based on the first inspection image database;
a ninth obtaining unit, configured to perform traversal convolution operation on the first image set according to the target convolution feature to obtain a first convolution result;
a tenth obtaining unit, configured to obtain the first disease characteristic information set according to the first convolution result, where the first disease characteristic information set and the first image set have a first mapping relationship;
an eleventh obtaining unit, configured to obtain the first keypoint information set and the second keypoint information set according to the first disease feature information set and the first image set based on the first mapping relationship.
Further, the system further comprises:
the second construction unit is used for constructing an image three-dimensional modeling system;
a twelfth obtaining unit, configured to obtain a first sparse matrix according to the first disease feature information set;
a thirteenth obtaining unit, configured to obtain a first sparse point set according to the first sparse matrix;
a fourteenth obtaining unit, configured to input the first sparse point set into the image three-dimensional modeling system, and obtain a first approximate three-dimensional model;
the first generating unit is used for generating a first initial point cloud according to the inspection image information;
a fifteenth obtaining unit, configured to perform point cloud diffusion on the first initial point cloud to obtain a first diffusion result;
a sixteenth obtaining unit configured to obtain a first dense point set according to the first diffusion result;
a seventeenth obtaining unit, configured to input the first dense point set and the first approximate three-dimensional model into the image three-dimensional modeling system, and obtain the first structural three-dimensional model map.
Further, the system further comprises:
an eighteenth obtaining unit, configured to obtain a first noise set according to the first inspection image information set;
a nineteenth obtaining unit, configured to perform cluster analysis on the first noise set to obtain a first classification result;
a third constructing unit, configured to construct a first function according to the first classification result, where the first function reflects a correlation between the first inspection image information and the first noise set;
the fourth construction unit is used for constructing the first image denoising model;
a twentieth obtaining unit, configured to input the first inspection image information set and the first function into the first image denoising model, and obtain a first denoising image set;
a second generating unit, configured to generate the first initial point cloud according to the first denoised image set.
Further, the system further comprises:
a fifth construction unit for constructing a first similar historical disease information database based on big data according to the disease information of the first patient;
a twenty-first obtaining unit, configured to obtain a second disease feature information set according to the first similar historical disease information database;
a twenty-second obtaining unit for obtaining a first historical diagnosis result according to the second disease characteristic information set;
a twenty-third obtaining unit that adjusts the second evaluation result according to the first historical diagnosis result to obtain a third evaluation result.
Further, the system further comprises:
a twenty-fourth obtaining unit, configured to obtain a first feature information preset threshold;
the first comparison unit is used for comparing the first disease characteristic information set with the second disease characteristic information set to obtain a first comparison result, and the first comparison result comprises the quantity of similar characteristic information;
a first judging unit, configured to judge whether the quantity of the similar feature information is within a preset threshold of the first feature information;
a twenty-fifth obtaining unit, configured to obtain a corresponding first historical diagnosis result if the number of the similar feature information is within a preset threshold of the first feature information.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to figure 6,
based on the same inventive concept as the auxiliary method for improving the decision efficiency of the orthopedic diagnosis in the foregoing embodiments, the present application embodiment further provides an auxiliary system for improving the decision efficiency of the orthopedic diagnosis, which includes: a processor coupled to a memory, the memory for storing a program that, when executed by the processor, causes a system to perform the method of any of the first aspects.
The electronic device 300 includes: processor 302, communication interface 303, memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. Wherein, the communication interface 303, the processor 302 and the memory 301 may be connected to each other through a bus architecture 304; the bus architecture 304 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 3, but this does not mean only one bus or one type of bus.
The communication interface 303 may be any device, such as a transceiver, for communicating with other devices or communication networks, such as an ethernet, a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), a wired access network, and the like.
The memory 301 may be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, an electrically erasable Programmable read-only memory (EEPROM), a compact disc read-only memory (compact disc)
read-only memory, CD-ROM) or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory may be self-contained and coupled to the processor through a bus architecture 304. The memory may also be integral to the processor.
The memory 301 is used for storing computer-executable instructions for executing the present application, and is controlled by the processor 302 to execute. The processor 302 is used for executing computer-executable instructions stored in the memory 301, so as to implement an auxiliary system and method for improving the efficiency of orthopedic diagnosis decision provided by the above embodiments of the present application.
Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application program codes, which are not specifically limited in the embodiments of the present application.
2. The embodiment of the application provides an auxiliary method for improving the decision-making efficiency of orthopedic diagnosis, which comprises the following steps: acquiring disease condition information of a first patient, wherein the disease condition information comprises examination image information; acquiring a first disease characteristic information set according to the inspection image information, wherein the first disease characteristic information set comprises a first key point information set and a second key point information set; constructing a first structure three-dimensional model map according to the first disease information set; obtaining a first correction parameter according to the first structure three-dimensional model diagram; correcting the first key point information set and the second key point information set according to the first correction parameter to obtain a third key point information set and a fourth key point information set; inputting the third key point information set and the fourth key point information set into an orthopedic diagnosis evaluation model to obtain a first evaluation result; and sending the first evaluation result to an expert platform, and obtaining a second evaluation result according to the reference opinions of the experts. The method has the advantages that the basic information of the state of an illness of the patient is combined, on the basis of carrying out feature recognition on the image of the patient, three-dimensional modeling is carried out again to extract feature information, more comprehensive feature data is obtained, and then the state of an illness of the orthopedic patient is evaluated through intelligent model analysis.
Those of ordinary skill in the art will understand that: the various numbers of the first, second, etc. mentioned in this application are only used for the convenience of description and are not used to limit the scope of the embodiments of this application, nor to indicate the order of precedence. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one" means one or more. At least two means two or more. "at least one," "any," or similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one (one ) of a, b, or c, may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or multiple.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer finger
The instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, where the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device including one or more available media integrated servers, data centers, and the like. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The various illustrative logical units and circuits described in this application may be implemented or operated upon by design of a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
The steps of a method or algorithm described in the embodiments herein may be embodied directly in hardware, in a software element executed by a processor, or in a combination of the two. The software cells may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. For example, a storage medium may be coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may be disposed in a terminal. In the alternative, the processor and the storage medium may reside in different components within the terminal. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary of the present application as defined in the appended claims and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations.
Claims (9)
1. An assistance system for improving the efficiency of orthopaedic diagnostic decision making, wherein the system comprises:
the first obtaining unit is used for obtaining disease condition information of a first patient, and the disease condition information comprises examination image information;
a second obtaining unit, configured to obtain a first disease feature information set according to the examination image information, where the first disease feature information set includes a first key point information set and a second key point information set;
a first construction unit, configured to construct a first structural three-dimensional model map according to the first disease feature information set;
a third obtaining unit, configured to obtain a first correction parameter according to the first structural three-dimensional model map;
a fourth obtaining unit, configured to correct the first keypoint information set and the second keypoint information set according to the first correction parameter, and obtain a third keypoint information set and a fourth keypoint information set;
a fifth obtaining unit, configured to input the third keypoint information set and the fourth keypoint information set into an orthopedic diagnosis evaluation model to obtain a first evaluation result;
and the sixth obtaining unit is used for sending the first evaluation result to an expert platform and obtaining a second evaluation result according to the reference opinions of the experts.
2. The system of claim 1, wherein the first disease feature information set is obtained based on the examination image information, the first disease feature information set comprises a first key point information set and a second key point information set, and the system further comprises:
a seventh obtaining unit, configured to construct a first examination image database according to the examination image information, and obtain a first image set;
an eighth obtaining unit, configured to obtain a target convolution feature based on the first inspection image database;
a ninth obtaining unit, configured to perform traversal convolution operation on the first image set according to the target convolution feature to obtain a first convolution result;
a tenth obtaining unit, configured to obtain the first disease characteristic information set according to the first convolution result, where the first disease characteristic information set and the first image set have a first mapping relationship;
an eleventh obtaining unit, configured to obtain the first keypoint information set and the second keypoint information set according to the first disease feature information set and the first image set based on the first mapping relationship.
3. The system of claim 1, wherein said constructing a first three-dimensional model map of the structure based on said first disease information set further comprises:
the second construction unit is used for constructing an image three-dimensional modeling system;
a twelfth obtaining unit, configured to obtain a first sparse matrix according to the first disease feature information set;
a thirteenth obtaining unit, configured to obtain a first sparse point set according to the first sparse matrix;
a fourteenth obtaining unit, configured to input the first sparse point set into the image three-dimensional modeling system, and obtain a first approximate three-dimensional model;
the first generating unit is used for generating a first initial point cloud according to the inspection image information;
a fifteenth obtaining unit, configured to perform point cloud diffusion on the first initial point cloud to obtain a first diffusion result;
a sixteenth obtaining unit configured to obtain a first dense point set according to the first diffusion result;
a seventeenth obtaining unit, configured to input the first dense point set and the first approximate three-dimensional model into the image three-dimensional modeling system, and obtain the first structural three-dimensional model map.
4. The system of claim 3, wherein the generating a first initial point cloud based on the inspection image information further comprises:
an eighteenth obtaining unit, configured to obtain a first noise set according to the first inspection image information set;
a nineteenth obtaining unit, configured to perform cluster analysis on the first noise set to obtain a first classification result;
a third constructing unit, configured to construct a first function according to the first classification result, where the first function reflects a correlation between the first inspection image information and the first noise set;
the fourth construction unit is used for constructing the first image denoising model;
a twentieth obtaining unit, configured to input the first inspection image information set and the first function into the first image denoising model, and obtain a first denoising image set;
a second generating unit, configured to generate the first initial point cloud according to the first denoised image set.
5. The system of claim 1, wherein the system further comprises:
a fifth construction unit for constructing a first similar historical disease information database based on big data according to the disease information of the first patient;
a twenty-first obtaining unit, configured to obtain a second disease feature information set according to the first similar historical disease information database;
a twenty-second obtaining unit for obtaining a first historical diagnosis result according to the second disease characteristic information set;
a twenty-third obtaining unit that adjusts the second evaluation result according to the first historical diagnosis result to obtain a third evaluation result.
6. The system of claim 5, wherein said obtaining a first historical diagnosis is based on said second disease characteristic information set, said system further comprising:
a twenty-fourth obtaining unit, configured to obtain a first feature information preset threshold;
the first comparison unit is used for comparing the first disease characteristic information set with the second disease characteristic information set to obtain a first comparison result, and the first comparison result comprises the quantity of similar characteristic information;
a first judging unit, configured to judge whether the quantity of the similar feature information is within a preset threshold of the first feature information;
a twenty-fifth obtaining unit, configured to obtain a corresponding first historical diagnosis result if the number of the similar feature information is within a preset threshold of the first feature information.
7. The system of claim 1, wherein the third set of keypoint information and the fourth set of keypoint information are input into an orthopedic diagnostic evaluation model to obtain a first evaluation result, the system further comprising:
a first training unit, configured to input the third keypoint information set and the fourth keypoint information set into the orthopedic diagnosis and evaluation model, where the orthopedic diagnosis and evaluation model is obtained by training multiple sets of training data, and each set of training data in the multiple sets of training data includes: the third set of keypoint information, the fourth set of keypoint information, and identification information used to identify the first evaluation result;
a first output unit for obtaining a first output result of the orthopaedic diagnostic evaluation model, wherein the first output result is the first evaluation result of disease information for the first patient.
8. An auxiliary method for improving the decision making efficiency of orthopedic diagnosis, wherein the method comprises the following steps:
acquiring disease condition information of a first patient, wherein the disease condition information comprises examination image information;
acquiring a first disease characteristic information set according to the inspection image information, wherein the first disease characteristic information set comprises a first key point information set and a second key point information set;
constructing a first structure three-dimensional model map according to the first disease characteristic information set;
obtaining a first correction parameter according to the first structure three-dimensional model diagram;
correcting the first key point information set and the second key point information set according to the first correction parameter to obtain a third key point information set and a fourth key point information set;
inputting the third key point information set and the fourth key point information set into an orthopedic diagnosis evaluation model to obtain a first evaluation result;
and sending the first evaluation result to an expert platform, and obtaining a second evaluation result according to the reference opinions of the experts.
9. An assistance system for improving the efficiency of orthopaedic diagnostic decisions comprising: a processor coupled to a memory for storing a program that, when executed by the processor, causes a system to operate as the system of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110734554.4A CN113345558A (en) | 2021-06-30 | 2021-06-30 | Auxiliary system and method for improving orthopedic diagnosis decision-making efficiency |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110734554.4A CN113345558A (en) | 2021-06-30 | 2021-06-30 | Auxiliary system and method for improving orthopedic diagnosis decision-making efficiency |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113345558A true CN113345558A (en) | 2021-09-03 |
Family
ID=77481692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110734554.4A Withdrawn CN113345558A (en) | 2021-06-30 | 2021-06-30 | Auxiliary system and method for improving orthopedic diagnosis decision-making efficiency |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113345558A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114510767A (en) * | 2022-02-22 | 2022-05-17 | 中交四公局第一工程有限公司 | Steel structure assembly effect evaluation method and system based on three-dimensional modeling |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111243106A (en) * | 2020-01-21 | 2020-06-05 | 杭州微洱网络科技有限公司 | Method for correcting three-dimensional human body model based on 2D human body image |
| CN111539912A (en) * | 2020-03-23 | 2020-08-14 | 中国科学院自动化研究所 | Health index evaluation method and equipment based on face structure positioning and storage medium |
| CN112734746A (en) * | 2021-01-21 | 2021-04-30 | 常德海 | Orthopedic injury spectrum matching system and method based on image recognition |
-
2021
- 2021-06-30 CN CN202110734554.4A patent/CN113345558A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111243106A (en) * | 2020-01-21 | 2020-06-05 | 杭州微洱网络科技有限公司 | Method for correcting three-dimensional human body model based on 2D human body image |
| CN111539912A (en) * | 2020-03-23 | 2020-08-14 | 中国科学院自动化研究所 | Health index evaluation method and equipment based on face structure positioning and storage medium |
| CN112734746A (en) * | 2021-01-21 | 2021-04-30 | 常德海 | Orthopedic injury spectrum matching system and method based on image recognition |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114510767A (en) * | 2022-02-22 | 2022-05-17 | 中交四公局第一工程有限公司 | Steel structure assembly effect evaluation method and system based on three-dimensional modeling |
| CN114510767B (en) * | 2022-02-22 | 2022-09-02 | 中交第四公路工程局有限公司 | Steel structure assembly effect evaluation method and system based on three-dimensional modeling |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020181805A1 (en) | Diabetes prediction method and apparatus, storage medium, and computer device | |
| JP5926728B2 (en) | Visualization adapted for direct use by physicians | |
| CN110111886A (en) | A kind of intelligent interrogation system and method based on XGBoost disease forecasting | |
| CN108511057A (en) | Transfusion volume model foundation and prediction technique, device, equipment and its storage medium | |
| CN110859624A (en) | Brain age deep learning prediction system based on structural magnetic resonance image | |
| CN116453706B (en) | Hemodialysis scheme making method and system based on reinforcement learning | |
| CN113345558A (en) | Auxiliary system and method for improving orthopedic diagnosis decision-making efficiency | |
| KR20240019263A (en) | A hierarchical workflow for generating annotated training data for machine learning-assisted image segmentation. | |
| CN111403029A (en) | Information processing method and device for improving evaluation quality | |
| CN113851218A (en) | Tuberculosis treatment scheme matching method and system based on image information | |
| CN116935009B (en) | Operation navigation system for prediction based on historical data analysis | |
| Souza et al. | End-to-end bone age assessment with residual learning | |
| CN112101438B (en) | Left-right eye classification method, device, server and storage medium | |
| CN114255855A (en) | Medical grading diagnosis and treatment registration management method and system based on artificial intelligence | |
| CN111275059A (en) | Image processing method and device and computer readable storage medium | |
| WO2024108483A1 (en) | Multimodal neural biological signal processing method and apparatus, and server and storage medium | |
| WO2023134087A1 (en) | Method and apparatus for generating inquiry template, electronic device, and storage medium | |
| CN116205915A (en) | Brain age assessment method and system based on mask and electronic equipment | |
| CN112233126B (en) | Windowing method and device for medical image | |
| CN113554641A (en) | Pediatric pharyngeal image acquisition method and device | |
| CN109816632B (en) | Brain image processing method and device, readable storage medium and electronic equipment | |
| WO2022050078A1 (en) | Training data creation device, method, and program, machine learning device and method, learning model, and image processing device | |
| CN113380391A (en) | Intelligent management method and system for orthopedic implant | |
| CN117710373B (en) | Anti-interference OCTA retinal vessel extraction method and device | |
| CN118299070B (en) | Treatment effect estimation method, system, equipment and medium based on inverse fact prediction |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210903 |