CN110930399A - TKA preoperative clinical staging intelligent evaluation method based on support vector machine - Google Patents
TKA preoperative clinical staging intelligent evaluation method based on support vector machine Download PDFInfo
- Publication number
- CN110930399A CN110930399A CN201911255366.2A CN201911255366A CN110930399A CN 110930399 A CN110930399 A CN 110930399A CN 201911255366 A CN201911255366 A CN 201911255366A CN 110930399 A CN110930399 A CN 110930399A
- Authority
- CN
- China
- Prior art keywords
- data
- support vector
- vector machine
- tka
- clinical
- 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
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 39
- 238000011156 evaluation Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000003384 imaging method Methods 0.000 claims abstract description 15
- 210000000629 knee joint Anatomy 0.000 claims abstract description 13
- 210000000845 cartilage Anatomy 0.000 claims abstract description 6
- 230000037182 bone density Effects 0.000 claims abstract description 4
- 210000003141 lower extremity Anatomy 0.000 claims abstract description 4
- 238000012216 screening Methods 0.000 claims abstract description 4
- 210000001519 tissue Anatomy 0.000 claims abstract description 4
- 239000013598 vector Substances 0.000 claims description 8
- 101001023733 Homo sapiens Neurotrypsin Proteins 0.000 claims description 2
- 102100035484 Neurotrypsin Human genes 0.000 claims description 2
- 238000002591 computed tomography Methods 0.000 abstract description 7
- 238000002059 diagnostic imaging Methods 0.000 abstract description 4
- 238000013135 deep learning Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 abstract description 2
- 238000002372 labelling Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 22
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 208000014674 injury Diseases 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 208000025978 Athletic injury Diseases 0.000 description 1
- 206010007710 Cartilage injury Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 206010041738 Sports injury Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 201000008482 osteoarthritis Diseases 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000005065 subchondral bone plate Anatomy 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011883 total knee arthroplasty Methods 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of total knee joint replacement, in particular to a TKA preoperative clinical staging intelligent evaluation method based on a support vector machine. The method comprises the following steps: collecting OA (knee joint) imaging data, collecting X-ray full-length sheet data, and performing screening and data labeling of clinical staged training samples by matching with data such as lower limb full-length CT (computed tomography) volume scanning image data, bone density data, MR T1/T2/3D-FS-SPGR cartilage imaging sequence data, tissue samples, patient general data and the like; using the X-ray imaging data marked with clinical stages; and (5) adopting a support vector machine to carry out classification output. According to the TKA preoperative clinical staging intelligent evaluation method based on the support vector machine, a support vector machine-based supervised deep learning algorithm is adopted in the TKA preoperative clinical intelligent staging, doctors are liberated from a large amount of medical imaging data, level difference among the doctors is reduced, and the process from judgment of a preceding auxiliary doctor to independent decision making after maturity is realized.
Description
Technical Field
The invention relates to the technical field of total knee joint replacement, in particular to a TKA preoperative clinical staging intelligent evaluation method based on a support vector machine.
Background
With the increase of high-energy injuries such as accelerated aging of population, sports injury, traffic accidents and the like in China, the incidence of injuries and/or defects of cartilage and subchondral bone is obviously increased. According to statistics, the cartilage injury reaches 10 million people after the trauma in China every year, the total number of patients with osteoarthritis is higher by 1.2 hundred million, and the incidence rate is about 9.6 percent of the population. Despite the intensive research on cartilage repair techniques, total knee arthroplasty remains the most reliable treatment currently for severe OA of the knee. In recent years, the annual growth rate of artificial joint replacement in China reaches 13%, and currently 20 ten thousand cases per year.
Clinical manifestations and physical signs of the OA of the knee joint are different, and clinical staging evaluation of the OA of the knee joint is particularly important for improving diagnosis and treatment effects. The severity of the patient's condition is accurately judged, so that a clinician is guided to perform TKA operation on the patient. In the traditional clinical staging evaluation, before the TKA operation, doctors evaluate by using X-rays and combining CT or MRI medical imaging data timely according to experience and knowledge, and the evaluation accuracy is different according to different doctors. With the continuous development of artificial intelligence technology, the intelligent stage assessment by utilizing the imaging data becomes possible, the accuracy of the stage assessment can exceed that of an experienced doctor in the future, independent decision making from judgment of a forepart doctor to maturity is realized, the doctor is liberated from a large amount of medical imaging data, and the level difference among doctors is reduced.
Disclosure of Invention
The invention aims to provide a TKA preoperative clinical staging intelligent evaluation method based on a support vector machine, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides a TKA preoperative clinical staging intelligent evaluation method based on a support vector machine, which comprises the following steps:
s1, collecting OA (knee joint) imaging data of the knee joint, collecting X-ray full-length data, and performing screening and data annotation of a clinical staged training sample by matching with data such as lower limb full-length CT (computed tomography) volume scanning image data, bone density data, MR (magnetic resonance) T1/T2/3D-FS-SPGR cartilage imaging sequence data, a tissue sample, patient general data and the like;
s2, defining staging grades by using the X-ray imaging data labeled with clinical staging, and training support vector machines of different linear kernels, polynomial kernels, Gaussian kernels and the like;
and S3, adopting a support vector machine to perform classification output.
Preferably, in S2, the method for training a support vector machine includes the following steps:
s2.1, inputting two types of training sample vectors (X)i,Yi)(i=1,2,…,N,X∈RnY belongs to-1, 1), and the class numbers are w respectively1,w2If X isi∈w1Then Y isi=-1,;Xi∈w2Then Y isi=1;
S2.2, specifying a kernel function type;
s2.3, solving the optimal solution of the daily function expression by utilizing a quadratic programming method to obtain the optimal Lagrange multiplier a*;
S2.4, using a support vector X in the sample libraryiAnd obtaining a deviation value b.
Preferably, the specified kernel function type is a polynomial kernel, and the formula is as follows:
k(x,x')=(<x,x'>+d)p,p∈N,d≥0……(1)。
preferably, the objective function of the quadratic programming method for solving the objective function formula is as follows:
preferably, in S3, the method for the support vector machine to output the classified data includes the following steps:
s3.1, solving an optimal solution by adopting quadratic programming;
s3.2, solving the quadratic programming problem by adopting a Lagrange multiplier method;
and S3.3, constructing the SVM with soft decision output in the multi-classification.
Preferably, the formula for solving the optimal solution by quadratic programming is as follows:
w denotes the coefficient of the classification hyperplane and b is a constant.
Preferably, the formula of the lagrange multiplier method is as follows:
αi[yi(<w·xi>+b)-1]=0,i=1,…N……(4);
αifor lagrange multipliers of samples, assume the optimal solution of α is α*Substituting the optimal solution into a hyperplane equation to obtain a decision function:
preferably, the decision output of the SVM is mapped between 0 and 1 by Sigmoid function, and a mathematical expression of probability output is constructed, which is simplified as follows:
f(x)=∑αiyiK(xi,x)+b……(6);
wherein, K (x)i,x)=〈xiX > is the kernel function of the construct.
Compared with the prior art, the invention has the beneficial effects that: according to the TKA preoperative clinical staging intelligent evaluation method based on the support vector machine, a support vector machine-based supervised deep learning algorithm is adopted in the TKA preoperative clinical intelligent staging, doctors are liberated from a large amount of medical imaging data, level difference among the doctors is reduced, and the process from judgment of a preceding auxiliary doctor to independent decision making after maturity is realized.
Drawings
FIG. 1 is an overall flow diagram of the present invention;
FIG. 2 is a flowchart of a method for training a support vector machine according to the present invention;
FIG. 3 is a flowchart of a method for classified output by the SVM of the present invention;
FIG. 4 is a block diagram of the data collection of OA iconography of knee joints of people in China according to the present invention;
FIG. 5 is a block diagram of the deep learning platform of the present invention;
FIG. 6 is a block diagram of the preliminary TKA pre-operative intelligent clinical staging based on a support vector machine of the present invention;
FIG. 7 is a flowchart of the support vector machine four-classification of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-7, the present invention provides a technical solution:
the invention provides a TKA preoperative clinical staging intelligent evaluation method based on a support vector machine, which comprises the following steps:
s1, collecting OA (knee joint) imaging data, collecting X-ray full-length data, and performing screening and data annotation of clinical staged training samples by matching with data such as lower limb full-length CT (computed tomography) volume scanning image data, bone density data, MRT1/T2/3D-FS-SPGR cartilage imaging sequence data, tissue samples, patient general data and the like;
s2, defining staging grades by using the X-ray imaging data labeled with clinical staging, and training support vector machines of different linear kernels, polynomial kernels, Gaussian kernels and the like;
and S3, adopting a support vector machine to perform classification output.
In the embodiment, the training is based on constructing a distributed multi-GPU training platform, and the training effects of different-depth learning frames, such as TensorFlow, Caffe, Theano and the like, are evaluated in the aspects of distributed operation support, execution efficiency and the like; aiming at the characteristics of knee joint image data, a mainstream deep learning model at home and abroad is screened at present, and evaluation is carried out on three aspects of convergence speed, stability and generation effect; aiming at the characteristics of knee joint image data, optimization is carried out on the aspects of loss function design, convergence algorithm, momentum optimization algorithm and the like.
Furthermore, the method utilizes X-ray imaging data marked with clinical stages to define stage grades, trains Support Vector Machines (SVM) of different linear kernels, polynomial kernels, Gaussian kernels and the like, evaluates convergence speed, stability and classification effect, tests the effect of the support vector machines under different loss functions such as change loss, index loss and contrast loss, and optimizes the loss function, convergence algorithm and momentum optimization algorithm. The relevant characteristic extraction algorithm of the X-ray imaging data is researched, the data volume of a single sample is reduced, and the training efficiency is improved.
Specifically, in S2, the method for training the support vector machine includes the following steps:
s2.1, inputting two types of training sample vectors (X)i,Yi)(i=1,2,…,N,X∈RnY belongs to-1, 1), and the class numbers are w respectively1,w2If X isi∈w1Then Y isi=-1,;Xi∈w2Then Y isi=1;
S2.2, specifying a kernel function type;
s2.3, solving the optimal solution of the daily function expression by utilizing a quadratic programming method to obtain the optimal Lagrange multiplier a*;
S2.4, using a support vector X in the sample libraryiAnd obtaining a deviation value b.
The specified kernel function type adopts a polynomial kernel, and the formula is as follows:
k(x,x')=(<x,x'>+d)p,p∈N,d≥0……(1)。
wherein, the specified kernel function type can also adopt an RBF kernel, a B-spline kernel and a Fourier kernel: the function formula of the RBF kernel is as follows:
the functional formula of the B-spline kernel is as follows:
k(x,x')=B2N+1(||x-x'||)……(1-2);
the functional formula of the Fourier kernel is as follows:
specifically, the objective function of the quadratic programming method for solving the daily function equation is as follows:
in this embodiment, in S3, the method for supporting the vector machine to output the classified data includes the following steps:
s3.1, solving an optimal solution by adopting quadratic programming;
s3.2, solving the quadratic programming problem by adopting a Lagrange multiplier method;
and S3.3, constructing the SVM with soft decision output in the multi-classification.
The formula for solving the optimal solution by adopting quadratic programming is as follows:
w denotes the coefficient of the classification hyperplane and b is a constant.
The formula of the Lagrange multiplier method is as follows:
αi[yi(〈w·xi〉+b)-1]=0,i=1,…N……(4);
αifor lagrange multipliers of samples, assume the optimal solution of α is α*Substituting the optimal solution into a hyperplane equation to obtain a decision function:
the decision output of the SVM is mapped between 0 and 1 through a Sigmoid function, and a mathematical expression of probability output is constructed, wherein the simplified form is as follows:
f(x)=∑αiyiK(xi,x)+b……(6);
wherein, K (x)i,x)=<xiX > is the kernel function of the construct.
It is worth to be noted that, in the present invention, the knee joint clinical stage is divided into 4 stages, i, ii, iii and iv stages, respectively, the support vector machine principle can only perform two classifications, and in order to realize four classifications, the using method is as follows:
constructing N (N-1)/2 two-class classifiers according to the classification number required to be classified, namely constructing 6 two-class classifiers in the invention, judging a sample by adopting a voting mode, inputting the sample into any two-class classifiers which are constructed, classifying the sample by the classifiers, and determining which class the sample belongs to if the number of the class is the maximum, specifically constructing a decision function of the N (N-1)/2 two-class classifiers, namely, constructing a "voting method" decision max ((w) decision max) of the N (N-1)/2 two-class classifiers as shown in figure 7AB)TΦ(xA)+bAB) If the ticket number belongs to the category A, the ticket number of the category A is increased by one, otherwise, the ticket number of the category B is increased by one, and the category with the most tickets is counted, namely the category.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. The TKA preoperative clinical staging intelligent evaluation method based on the support vector machine is characterized by comprising the following steps: the method comprises the following steps:
s1, collecting knee joint 0A imaging data, collecting X-ray full-length data, and matching with data such as lower limb full-length CT volume scanning image data, bone density data, MRT1/T2/3D-FS-SPGR cartilage imaging sequence data, tissue samples, patient general data and the like, screening and carrying out data annotation of clinical staged training samples;
s2, defining staging grades by using the X-ray imaging data labeled with clinical staging, and training support vector machines of different linear kernels, polynomial kernels, Gaussian kernels and the like;
and S3, adopting a support vector machine to perform classification output.
2. The method for intelligently evaluating pre-operative clinical stages of TKA based on a support vector machine as claimed in claim 1, wherein: in S2, the method for training a support vector machine includes the following steps:
s2.1, inputting two types of training sample vectors (X)i,Yi)(i=1,2,...,N,X∈RnY belongs to-1, 1), and the class numbers are w respectively1,w2If X isi∈w1Then Y isi=-1,;Xi∈w2Then Y isi=1;
S2.2, specifying a kernel function type;
s2.3, solving the optimal solution of the daily function expression by utilizing a quadratic programming method to obtain the optimal Lagrange multiplier a*;
S2.4, using a support vector X in the sample libraryiAnd obtaining a deviation value b.
3. The method for intelligently evaluating pre-operative clinical stages of TKA based on a support vector machine as claimed in claim 2, wherein: the specified kernel function type adopts a polynomial kernel, and the formula is as follows:
k(x,x′)=(<x,x′>+d)p,p∈N,d≥0......(1)。
5. the method for intelligently evaluating pre-operative clinical stages of TKA based on a support vector machine as claimed in claim 1, wherein: in S3, the method for supporting the vector machine to output the classified data includes the following steps:
s3.1, solving an optimal solution by adopting quadratic programming;
s3.2, solving the quadratic programming problem by adopting a Lagrange multiplier method;
and S3.3, constructing the SVM with soft decision output in the multi-classification.
7. The method of claim 5, wherein the method comprises the following steps: the formula of the lagrange multiplier method is as follows:
αi[yi(<w·xi>+b)-1]=0,i=1,…N……(4);
αifor lagrange multipliers of samples, assume the optimal solution of α is α*Substituting the optimal solution into a hyperplane equation to obtain a decision function:
8. the method of claim 5, wherein the method comprises the following steps: the decision output of the SVM is mapped between 0 and 1 through a Sigmoid function, and a mathematical expression of probability output is constructed, wherein the simplified form is as follows:
f(x)=∑αiyiK(xi,x)+b……(6);
wherein, K (x)i,x)=<xi·x>Is a constructed kernel function.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911255366.2A CN110930399A (en) | 2019-12-10 | 2019-12-10 | TKA preoperative clinical staging intelligent evaluation method based on support vector machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911255366.2A CN110930399A (en) | 2019-12-10 | 2019-12-10 | TKA preoperative clinical staging intelligent evaluation method based on support vector machine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110930399A true CN110930399A (en) | 2020-03-27 |
Family
ID=69858046
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911255366.2A Pending CN110930399A (en) | 2019-12-10 | 2019-12-10 | TKA preoperative clinical staging intelligent evaluation method based on support vector machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110930399A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111476300A (en) * | 2020-04-07 | 2020-07-31 | 屈璠 | Throat reflux recognition model establishing method, index obtaining method and electronic system |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101373519A (en) * | 2007-08-20 | 2009-02-25 | 富士通株式会社 | Device and method for recognizing character |
US20130137962A1 (en) * | 2011-11-30 | 2013-05-30 | Kenneth L. Urish | Method for Detecting Arthritis and Cartilage Damage Using Magnetic Resonance Sequences |
CN104112143A (en) * | 2014-07-23 | 2014-10-22 | 大连民族学院 | Weighted hyper-sphere support vector machine algorithm based image classification method |
CN106372671A (en) * | 2016-09-06 | 2017-02-01 | 东南大学 | Increment learning method for continuous attribute measurement selection under C4.5 decision tree algorithm |
CN106483490A (en) * | 2016-10-20 | 2017-03-08 | 天津大学 | Wireless location method based on support vector cassification |
US20170202520A1 (en) * | 2011-11-30 | 2017-07-20 | Kenneth L. Urish | Method for predicting the development of arthritis in individuals prior to radiographic or symptomatic presentation |
CN107610114A (en) * | 2017-09-15 | 2018-01-19 | 武汉大学 | Optical satellite remote sensing image cloud snow mist detection method based on SVMs |
CN108538388A (en) * | 2018-03-06 | 2018-09-14 | 上海逸动医学科技有限公司 | A kind of motion of knee joint obstacle function evaluation method |
CN110232397A (en) * | 2019-04-22 | 2019-09-13 | 广东工业大学 | A kind of multi-tag classification method of combination supporting vector machine and projection matrix |
CN110243823A (en) * | 2019-05-08 | 2019-09-17 | 华中科技大学 | The automatic screening apparatus of Rickets and its application method based on support vector machines |
CN110309302A (en) * | 2019-05-17 | 2019-10-08 | 江苏大学 | A kind of uneven file classification method and system of combination SVM and semi-supervised clustering |
CN110472678A (en) * | 2019-08-06 | 2019-11-19 | 国家电网有限公司 | Optimization method based on the information system for power enterprise abnormality detection scheme for improving SVM |
-
2019
- 2019-12-10 CN CN201911255366.2A patent/CN110930399A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101373519A (en) * | 2007-08-20 | 2009-02-25 | 富士通株式会社 | Device and method for recognizing character |
US20130137962A1 (en) * | 2011-11-30 | 2013-05-30 | Kenneth L. Urish | Method for Detecting Arthritis and Cartilage Damage Using Magnetic Resonance Sequences |
US20170202520A1 (en) * | 2011-11-30 | 2017-07-20 | Kenneth L. Urish | Method for predicting the development of arthritis in individuals prior to radiographic or symptomatic presentation |
CN104112143A (en) * | 2014-07-23 | 2014-10-22 | 大连民族学院 | Weighted hyper-sphere support vector machine algorithm based image classification method |
CN106372671A (en) * | 2016-09-06 | 2017-02-01 | 东南大学 | Increment learning method for continuous attribute measurement selection under C4.5 decision tree algorithm |
CN106483490A (en) * | 2016-10-20 | 2017-03-08 | 天津大学 | Wireless location method based on support vector cassification |
CN107610114A (en) * | 2017-09-15 | 2018-01-19 | 武汉大学 | Optical satellite remote sensing image cloud snow mist detection method based on SVMs |
CN108538388A (en) * | 2018-03-06 | 2018-09-14 | 上海逸动医学科技有限公司 | A kind of motion of knee joint obstacle function evaluation method |
CN110232397A (en) * | 2019-04-22 | 2019-09-13 | 广东工业大学 | A kind of multi-tag classification method of combination supporting vector machine and projection matrix |
CN110243823A (en) * | 2019-05-08 | 2019-09-17 | 华中科技大学 | The automatic screening apparatus of Rickets and its application method based on support vector machines |
CN110309302A (en) * | 2019-05-17 | 2019-10-08 | 江苏大学 | A kind of uneven file classification method and system of combination SVM and semi-supervised clustering |
CN110472678A (en) * | 2019-08-06 | 2019-11-19 | 国家电网有限公司 | Optimization method based on the information system for power enterprise abnormality detection scheme for improving SVM |
Non-Patent Citations (1)
Title |
---|
陈鹏展: "《个体行为的机器识别与决策协同》", 31 July 2018 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111476300A (en) * | 2020-04-07 | 2020-07-31 | 屈璠 | Throat reflux recognition model establishing method, index obtaining method and electronic system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Xie et al. | A survey on incorporating domain knowledge into deep learning for medical image analysis | |
Wang et al. | Prior-attention residual learning for more discriminative COVID-19 screening in CT images | |
CN108364006B (en) | Medical image classification device based on multi-mode deep learning and construction method thereof | |
Joshi et al. | A survey of fracture detection techniques in bone X-ray images | |
CN109522973A (en) | Medical big data classification method and system based on production confrontation network and semi-supervised learning | |
WO2022198761A1 (en) | Asthma diagnosis system based on decision tree and improved smote algorithms | |
CN112598661B (en) | Ankle fracture and ligament injury diagnosis method based on machine learning | |
CN110084803A (en) | Eye fundus image method for evaluating quality based on human visual system | |
CN102737379A (en) | Captive test (CT) image partitioning method based on adaptive learning | |
CN109934824B (en) | Method and system for detecting cervical vertebra and spinal cord height signals | |
CN106980815A (en) | Facial paralysis objective evaluation method under being supervised based on H B rank scores | |
Verma | Novel network architecture and learning algorithm for the classification of mass abnormalities in digitized mammograms | |
CN111584046A (en) | AI (Artificial intelligence) processing method for medical image data | |
Wang et al. | Learning from highly confident samples for automatic knee osteoarthritis severity assessment: data from the osteoarthritis initiative | |
CN114795258A (en) | Child hip joint dysplasia diagnosis system | |
CN113269799A (en) | Cervical cell segmentation method based on deep learning | |
CN114693961A (en) | Fundus photo classification method, fundus image processing method and system | |
Cui et al. | Improving the prediction of benign or malignant breast masses using a combination of image biomarkers and clinical parameters | |
CN110930399A (en) | TKA preoperative clinical staging intelligent evaluation method based on support vector machine | |
Mangrulkar et al. | Automated skull damage detection from assembled skull model using computer vision and machine learning | |
CN113408603B (en) | Coronary artery stenosis degree identification method based on multi-classifier fusion | |
Karthik et al. | MSDNet: A deep neural ensemble model for abnormality detection and classification of plain radiographs | |
Al-Haija et al. | Development of breast cancer detection model using transfer learning of residual neural network (resnet-50) | |
CN117557840A (en) | Fundus lesion grading method based on small sample learning | |
Chaugule et al. | Knee Osteoarthritis Grading Using DenseNet and Radiographic Images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200327 |
|
RJ01 | Rejection of invention patent application after publication |