CN118553397B - Cone beam X-ray data calibration processing method based on linear regression - Google Patents
Cone beam X-ray data calibration processing method based on linear regression Download PDFInfo
- Publication number
- CN118553397B CN118553397B CN202411026163.7A CN202411026163A CN118553397B CN 118553397 B CN118553397 B CN 118553397B CN 202411026163 A CN202411026163 A CN 202411026163A CN 118553397 B CN118553397 B CN 118553397B
- Authority
- CN
- China
- Prior art keywords
- data
- cone beam
- ray
- cone
- verification
- 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.)
- Active
Links
- 238000012417 linear regression Methods 0.000 title claims abstract description 29
- 238000003672 processing method Methods 0.000 title claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 123
- 230000002159 abnormal effect Effects 0.000 claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 100
- 238000005259 measurement Methods 0.000 claims description 87
- 238000012795 verification Methods 0.000 claims description 52
- 238000013524 data verification Methods 0.000 claims description 48
- 238000012216 screening Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims 2
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/40—Arrangements for generating radiation specially adapted for radiation diagnosis
- A61B6/4064—Arrangements for generating radiation specially adapted for radiation diagnosis specially adapted for producing a particular type of beam
- A61B6/4085—Cone-beams
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/58—Testing, adjusting or calibrating thereof
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/58—Testing, adjusting or calibrating thereof
- A61B6/582—Calibration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01T—MEASUREMENT OF NUCLEAR OR X-RADIATION
- G01T7/00—Details of radiation-measuring instruments
- G01T7/005—Details of radiation-measuring instruments calibration techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- High Energy & Nuclear Physics (AREA)
- Molecular Biology (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Optics & Photonics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Radiology & Medical Imaging (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention relates to the field of cone beam X-ray comprehensive calibration, in particular to a cone beam X-ray data calibration processing method based on linear regression, which comprises the following steps: utilizing the cone beam X-rays to establish comprehensive operation data of the cone beam X-rays; utilizing the comprehensive operation data of the cone beam X rays to establish an operation data deviation identification model of the cone beam X rays based on linear regression; acquiring an operation data deviation recognition result according to the cone beam X-rays and the operation data deviation recognition model of the cone beam X-rays; and the calibration processing result of the cone beam X-ray data is obtained by utilizing the deviation recognition result of the operation data, so that the accurate and efficient analysis processing of the cone beam X-ray calibration data is improved, the related hardware of the cone beam X-ray is combined, the implementation self-optimization in the scheme and the abnormal output of the scheme are synchronously carried out, and under the conditions of abnormal states and the like, the stable output of the calibration data is ensured, and meanwhile, the implementation scene of the scheme is adapted to the rapid self-adjustment.
Description
Technical Field
The invention relates to the field of cone beam X-ray comprehensive calibration, in particular to a cone beam X-ray data calibration processing method based on linear regression.
Background
In recent years, with the continuous development of medical technology, radiation diagnosis and treatment equipment is continuously refined, three-dimensional stereoscopic images are obtained after three-dimensional cone beam X-rays are rotated and scanned around a human body, and all-dimensional observation of a human body scanning position can be realized, but after the equipment is newly installed or used for a long time, the scanning accuracy of the cone beam X-rays needs to be recalibrated or detected on time so as to ensure the safety of the cone beam X-rays and the accuracy of image quality, but the traditional method lacks the uniformity of data output by relying on the relative pose verification among hardware, and meanwhile, certain errors are caused on calibration test results by considering directions only depending on geometric parameters comprehensively.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a conical beam X-ray data calibration processing method based on linear regression, which combines the historical data with the corresponding firmware state by referencing a large amount of historical data and performs calibration compensation processing based on linear regression analysis errors.
In order to achieve the above object, the present invention provides a method for calibrating and processing cone beam X-ray data based on linear regression, comprising:
S1, utilizing cone beam X rays to establish comprehensive operation data of the cone beam X rays;
s2, utilizing the comprehensive operation data of the cone beam X rays to establish an operation data deviation identification model of the cone beam X rays based on linear regression;
s3, acquiring an operation data deviation recognition result according to the cone beam X-rays and the operation data deviation recognition model of the cone beam X-rays;
s4, obtaining a cone beam X-ray data calibration processing result by using the operation data deviation identification result.
Preferably, the establishing the integrated operation data of the cone beam X-rays by using the cone beam X-rays includes:
s1-1, acquiring cone beam X-rays and basic operation parameter data of the cone beam X-rays;
S1-2, acquiring a corresponding historical cone beam X-ray measurement data set according to the basic operation parameter data of the cone beam X-rays;
S1-3, screening the historical cone beam X-ray measurement data set by utilizing the basic operation parameter data to obtain a screening result of the historical cone beam X-ray measurement data set;
S1-4, using the screening processing result as comprehensive operation data of the cone beam X-rays;
The basic operation parameter data are the cone angle and the ray frequency of cone beam X rays.
Further, the screening processing of the historical cone beam X-ray measurement data set by using the basic operation parameter data to obtain a screening processing result of the historical cone beam X-ray measurement data set includes:
S1-3-1, acquiring basic operation parameter data of historical cone beam X-ray measurement data according to the historical cone beam X-ray measurement data set;
S1-3-2, sequentially judging whether the basic operation parameter data corresponding to each subset in the historical cone beam X-ray measurement data set is consistent with the basic operation parameter data of the cone beam X-rays, if so, acquiring the corresponding subset of the historical cone beam X-ray measurement data set to establish a consistent data set, otherwise, establishing a non-consistent data set by using the non-corresponding subset of the historical cone beam X-ray measurement data set;
s1-3-3, using the consistency data set and the non-consistency data set as screening processing results of the historical cone beam X-ray measurement data set.
Further, establishing the cone beam X-ray operation data deviation recognition model based on linear regression by utilizing the comprehensive cone beam X-ray operation data comprises:
S2-1, dividing a forward data training set and a forward data verification set by utilizing a consistency data set corresponding to comprehensive operation data of the cone beam X-rays;
s2-2, respectively establishing a forward basic operation parameter data training set and a forward basic operation parameter data verification set by utilizing the forward data training set and the forward data verification set;
S2-3, using the forward data training set and the forward basic operation parameter data training set as input and using the normal state as output, wherein the forward basic operation parameter data training set corresponds to basic operation parameter data types to establish model gradients, and training is performed based on linear regression to obtain a basic forward output model;
S2-4, inputting a basic forward output model by using the forward data verification set and the forward basic operation parameter data verification set to obtain a verification result of the basic forward output model;
S2-5, judging whether all verification results of the basic forward output model are normal, if so, reserving the current basic forward output model, otherwise, acquiring a forward data verification set and a forward basic operation parameter data verification set, of which the verification results are not normal, respectively adding a forward data training set and a forward basic operation parameter data training set, and returning to S2-3;
S2-6, dividing a negative data training set and a negative data verification set by utilizing the non-consistency data set corresponding to the comprehensive operation data of the cone beam X rays;
s2-7, respectively establishing a negative basic operation parameter data training set and a negative basic operation parameter data verification set by utilizing the negative data training set and the negative data verification set;
S2-8, using the negative data training set and the negative basic operation parameter data training set as input and using state abnormality as output, wherein the negative basic operation parameter data training set establishes model gradients corresponding to basic operation parameter data types, and training is performed based on linear regression to obtain a basic negative output model;
S2-9, inputting a basic negative output model by using the negative data verification set and the negative basic operation parameter data verification set to obtain a verification result of the basic negative output model;
S2-10, judging whether verification results of the basic negative output model are all abnormal, if so, reserving the current basic negative output model, otherwise, acquiring a negative data verification set and a negative basic operation parameter data verification set, of which the verification results are not abnormal, respectively adding the negative data training set and the negative basic operation parameter data training set, and returning to S2-8;
s2-11, combining the basic positive output model and the basic negative output model to serve as a cone beam X-ray operation data deviation identification model;
The positive data training set is 80% subset of the consistency data set, the positive data verification set is 20% subset of the consistency data set, the negative data training set is 80% subset of the non-consistency data set, and the negative data verification set is 20% subset of the non-consistency data set.
Further, obtaining the operation data deviation recognition result according to the operation data deviation recognition model of the cone beam X-rays and the cone beam X-rays comprises:
s3-1, utilizing the operation data deviation recognition model of the cone beam X-ray input cone beam X-ray to obtain an operation data deviation recognition result of the cone beam X-ray;
S3-2, performing feature comparison processing on the cone beam X rays by utilizing the deviation recognition result of the operation data of the cone beam X rays to obtain feature comparison processing results of the cone beam X rays;
S3-3, performing fitting verification processing on the conical beam X-ray operation data deviation recognition model by using the conical beam X-ray operation data deviation recognition result to obtain an overfitting verification processing result of the conical beam X-ray operation data deviation recognition model;
s3-4, using the feature comparison processing result and the over-fitting verification processing result as operation data deviation recognition results.
Further, the feature comparison processing of the cone beam X-rays by using the deviation recognition result of the operation data of the cone beam X-rays includes:
Acquiring basic operation parameter data of the cone beam X-rays;
Establishing a historical cone beam X-ray measurement data set of the same basic operation parameter data according to the basic operation parameter data;
Judging whether all the corresponding states of all the subsets in the historical cone beam X-ray measurement data sets of the same basic operation parameter data are consistent, if so, using the corresponding states of all the subsets in the historical cone beam X-ray measurement data sets of the same basic operation parameter data as relative comparison states, otherwise, acquiring the relatively high proportion type of the corresponding states of all the subsets in the historical cone beam X-ray measurement data sets of the same basic operation parameter data as the relative comparison states;
Judging whether the relative comparison state is consistent with the running data deviation recognition result of the cone beam X rays, if so, outputting the running data deviation recognition result of the current cone beam X rays as a characteristic comparison processing result of the cone beam X rays, otherwise, adding the cone beam X rays corresponding to the relative comparison state into a corresponding training set, and returning to S2-1;
Wherein the relative comparison state includes a normal operation state and an abnormal operation state of the cone beam X-ray.
Further, performing fitting verification processing on the cone beam X-ray operation data deviation recognition model by using the cone beam X-ray operation data deviation recognition result to obtain a fitting verification processing result of the cone beam X-ray operation data deviation recognition model includes:
s3-3-1, judging whether the repeated training times of the running data deviation recognition model of the cone beam X rays are larger than the data type number of the basic running parameter data corresponding to the cone beam X rays, if so, performing over-fitting verification processing on the running data deviation recognition model of the cone beam X rays to obtain over-fitting, otherwise, executing S3-3-2;
S3-3-2, judging whether the relative ratio of the number of subsets of the positive data training set to the number of subsets of the negative data training set corresponding to the deviation recognition result of the operation data of the cone beam X rays is larger than 1.5, if yes, performing over-fitting verification on the operation data of the cone beam X rays from the recognition model, and if not, performing over-fitting verification on the operation data of the cone beam X rays from the recognition model.
Further, the step of obtaining the cone beam X-ray data calibration processing result by using the operation data deviation recognition result comprises the following steps:
S4-1, performing cone beam X-ray measurement data adjustment processing on the processing result according to the characteristic comparison of the deviation recognition result of the operation data to obtain a cone beam X-ray measurement data adjustment processing result;
s4-2, performing cone beam X-ray measurement data compensation processing according to the overfitting verification processing result of the running data deviation recognition result to obtain cone beam X-ray measurement data compensation processing result;
S4-3, using the cone beam X-ray measurement data adjustment processing result and the cone beam X-ray measurement data compensation processing result as cone beam X-ray data calibration processing results.
Further, performing cone beam X-ray measurement data adjustment processing on the processing result according to the feature comparison of the deviation recognition result of the operation data to obtain a cone beam X-ray measurement data adjustment processing result includes:
s4-1-1, judging whether the characteristic comparison processing result of the deviation recognition result of the running data is normal, if so, enabling the cone beam X-ray measurement data adjustment processing result to pass, correspondingly outputting the cone beam X-ray measurement data adjustment processing result to be empty, reserving the characteristic comparison processing result of the deviation recognition result of the current running data, and otherwise, executing S4-1-2;
S4-1-2, judging whether the characteristic comparison processing result of the current operation data deviating from the identification result corresponds to the cone beam X-ray and the basic operation parameter data of the cone beam X-ray, if so, the cone beam X-ray measurement data fails to be adjusted, outputting the basic operation parameter data of the current cone beam X-ray and the cone beam X-ray, otherwise, returning to S1-3-1.
Further, performing cone beam X-ray measurement data compensation processing according to the over-fitting verification processing result of the deviation recognition result of the operation data to obtain a cone beam X-ray measurement data compensation processing result includes:
S4-2-1, judging whether an overfitting verification processing result of the running data deviation recognition result is overfitting or not, if yes, acquiring a training set with relatively lower subset number of positive data training sets and negative data training sets corresponding to the running data deviation recognition result of the cone beam X-rays as an optimization basic template, and executing S4-2-2, otherwise, the cone beam X-ray measurement data compensation processing result passes, reserving the overfitting verification processing result of the current running data deviation recognition result, and the cone beam X-ray measurement data compensation processing result is null;
S4-2-2, acquiring positive data training sets and negative data training sets with the same subset number according to the optimized basic template;
S4-2-3, using the current positive data training set and the negative data training set as updated positive data training set and negative data training set, and returning to S2.
Compared with the closest prior art, the invention has the following beneficial effects:
The method improves the accurate and efficient analysis processing of the cone beam X-ray calibration data, relates to the correlation of hardware in combination with X-rays, establishes a normal and abnormal corresponding mechanism for large-range multi-source measurement data based on linear regression, and synchronously performs implementation self-optimization and abnormal output of the scheme in the scheme, ensures stable output of the calibration data under abnormal conditions and the like, and simultaneously rapidly self-adjusts to adapt to scheme implementation scenes.
Drawings
FIG. 1 is a flow chart of a method for calibrating cone beam X-ray data based on linear regression.
Detailed Description
The following describes the embodiments of the present invention in further detail with reference to the drawings.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1:
The invention provides a conical beam X-ray data calibration processing method based on linear regression, which is shown in figure 1 and comprises the following steps:
S1, utilizing cone beam X rays to establish comprehensive operation data of the cone beam X rays;
s2, utilizing the comprehensive operation data of the cone beam X rays to establish an operation data deviation identification model of the cone beam X rays based on linear regression;
s3, acquiring an operation data deviation recognition result according to the cone beam X-rays and the operation data deviation recognition model of the cone beam X-rays;
s4, obtaining a cone beam X-ray data calibration processing result by using the operation data deviation identification result.
S1 specifically comprises:
s1-1, acquiring cone beam X-rays and basic operation parameter data of the cone beam X-rays;
S1-2, acquiring a corresponding historical cone beam X-ray measurement data set according to the basic operation parameter data of the cone beam X-rays;
S1-3, screening the historical cone beam X-ray measurement data set by utilizing the basic operation parameter data to obtain a screening result of the historical cone beam X-ray measurement data set;
S1-4, using the screening processing result as comprehensive operation data of the cone beam X-rays;
The basic operation parameter data are the cone angle and the ray frequency of cone beam X rays.
S1-3 specifically comprises:
S1-3-1, acquiring basic operation parameter data of historical cone beam X-ray measurement data according to the historical cone beam X-ray measurement data set;
S1-3-2, sequentially judging whether the basic operation parameter data corresponding to each subset in the historical cone beam X-ray measurement data set is consistent with the basic operation parameter data of the cone beam X-rays, if so, acquiring the corresponding subset of the historical cone beam X-ray measurement data set to establish a consistent data set, otherwise, establishing a non-consistent data set by using the non-corresponding subset of the historical cone beam X-ray measurement data set;
s1-3-3, using the consistency data set and the non-consistency data set as screening processing results of the historical cone beam X-ray measurement data set.
In this embodiment, in the cone beam X-ray data calibration processing method based on linear regression, since a large amount of historical data is used as a basis for processing in S1-3-3, after the screening is sequentially determined in S1-3-2, two corresponding cases of data still exist, and at this time, the step of S1-3-2 is only the screening step and is not used as a fixed direction of a certain case.
S2 specifically comprises:
S2-1, dividing a forward data training set and a forward data verification set by utilizing a consistency data set corresponding to comprehensive operation data of the cone beam X-rays;
s2-2, respectively establishing a forward basic operation parameter data training set and a forward basic operation parameter data verification set by utilizing the forward data training set and the forward data verification set;
S2-3, using the forward data training set and the forward basic operation parameter data training set as input and using the normal state as output, wherein the forward basic operation parameter data training set corresponds to basic operation parameter data types to establish model gradients, and training is performed based on linear regression to obtain a basic forward output model;
S2-4, inputting a basic forward output model by using the forward data verification set and the forward basic operation parameter data verification set to obtain a verification result of the basic forward output model;
S2-5, judging whether all verification results of the basic forward output model are normal, if so, reserving the current basic forward output model, otherwise, acquiring a forward data verification set and a forward basic operation parameter data verification set, of which the verification results are not normal, respectively adding a forward data training set and a forward basic operation parameter data training set, and returning to S2-3;
S2-6, dividing a negative data training set and a negative data verification set by utilizing the non-consistency data set corresponding to the comprehensive operation data of the cone beam X rays;
s2-7, respectively establishing a negative basic operation parameter data training set and a negative basic operation parameter data verification set by utilizing the negative data training set and the negative data verification set;
S2-8, using the negative data training set and the negative basic operation parameter data training set as input and using state abnormality as output, wherein the negative basic operation parameter data training set establishes model gradients corresponding to basic operation parameter data types, and training is performed based on linear regression to obtain a basic negative output model;
S2-9, inputting a basic negative output model by using the negative data verification set and the negative basic operation parameter data verification set to obtain a verification result of the basic negative output model;
S2-10, judging whether verification results of the basic negative output model are all abnormal, if so, reserving the current basic negative output model, otherwise, acquiring a negative data verification set and a negative basic operation parameter data verification set, of which the verification results are not abnormal, respectively adding the negative data training set and the negative basic operation parameter data training set, and returning to S2-8;
s2-11, combining the basic positive output model and the basic negative output model to serve as a cone beam X-ray operation data deviation identification model;
The positive data training set is 80% subset of the consistency data set, the positive data verification set is 20% subset of the consistency data set, the negative data training set is 80% subset of the non-consistency data set, and the negative data verification set is 20% subset of the non-consistency data set.
S3 specifically comprises:
s3-1, utilizing the operation data deviation recognition model of the cone beam X-ray input cone beam X-ray to obtain an operation data deviation recognition result of the cone beam X-ray;
S3-2, performing feature comparison processing on the cone beam X rays by utilizing the deviation recognition result of the operation data of the cone beam X rays to obtain feature comparison processing results of the cone beam X rays;
S3-3, performing fitting verification processing on the conical beam X-ray operation data deviation recognition model by using the conical beam X-ray operation data deviation recognition result to obtain an overfitting verification processing result of the conical beam X-ray operation data deviation recognition model;
s3-4, using the feature comparison processing result and the over-fitting verification processing result as operation data deviation recognition results.
S3-2 specifically comprises:
S3-2-1, acquiring basic operation parameter data of the cone beam X-rays;
S3-2-2, establishing a historical cone beam X-ray measurement data set of the same basic operation parameter data according to the basic operation parameter data;
S3-2-3, judging whether all the corresponding states of all the subsets in the historical cone beam X-ray measurement data sets of the same basic operation parameter data are consistent, if so, using the corresponding states of all the subsets in the historical cone beam X-ray measurement data sets of the same basic operation parameter data as relative comparison states, otherwise, acquiring the relatively high proportion type of the corresponding states of all the subsets in the historical cone beam X-ray measurement data sets of the same basic operation parameter data as the relative comparison states;
S3-2-4, judging whether the relative comparison state is consistent with the running data deviation recognition result of the cone beam X rays, if so, outputting the running data deviation recognition result of the current cone beam X rays as a characteristic comparison processing result of the cone beam X rays, otherwise, adding the cone beam X rays corresponding to the relative comparison state into a corresponding training set, and returning to S2-1;
Wherein the relative comparison state includes a normal operation state and an abnormal operation state of the cone beam X-ray.
S3-3 specifically comprises:
s3-3-1, judging whether the repeated training times of the running data deviation recognition model of the cone beam X rays are larger than the data type number of the basic running parameter data corresponding to the cone beam X rays, if so, performing over-fitting verification processing on the running data deviation recognition model of the cone beam X rays to obtain over-fitting, otherwise, executing S3-3-2;
S3-3-2, judging whether the relative ratio of the number of subsets of the positive data training set to the number of subsets of the negative data training set corresponding to the deviation recognition result of the operation data of the cone beam X rays is larger than 1.5, if yes, performing over-fitting verification on the operation data of the cone beam X rays from the recognition model, and if not, performing over-fitting verification on the operation data of the cone beam X rays from the recognition model.
In this embodiment, in the cone beam X-ray data calibration processing method based on linear regression, the S3-3-2 determines that the screening criterion is 1.5, which can be equivalently understood as that the relative ratio of the two output results is 150%, and the abnormal situation can be defined in the training process or the result ratio.
S4 specifically comprises the following steps:
S4-1, performing cone beam X-ray measurement data adjustment processing on the processing result according to the characteristic comparison of the deviation recognition result of the operation data to obtain a cone beam X-ray measurement data adjustment processing result;
s4-2, performing cone beam X-ray measurement data compensation processing according to the overfitting verification processing result of the running data deviation recognition result to obtain cone beam X-ray measurement data compensation processing result;
S4-3, using the cone beam X-ray measurement data adjustment processing result and the cone beam X-ray measurement data compensation processing result as cone beam X-ray data calibration processing results.
S4-1 specifically comprises:
s4-1-1, judging whether the characteristic comparison processing result of the deviation recognition result of the running data is normal, if so, enabling the cone beam X-ray measurement data adjustment processing result to pass, correspondingly outputting the cone beam X-ray measurement data adjustment processing result to be empty, reserving the characteristic comparison processing result of the deviation recognition result of the current running data, and otherwise, executing S4-1-2;
S4-1-2, judging whether the characteristic comparison processing result of the current operation data deviating from the identification result corresponds to the cone beam X-ray and the basic operation parameter data of the cone beam X-ray, if so, the cone beam X-ray measurement data fails to be adjusted, outputting the basic operation parameter data of the current cone beam X-ray and the cone beam X-ray, otherwise, returning to S1-3-1.
S4-2 specifically comprises:
S4-2-1, judging whether an overfitting verification processing result of the running data deviation recognition result is overfitting or not, if yes, acquiring a training set with relatively lower subset number of positive data training sets and negative data training sets corresponding to the running data deviation recognition result of the cone beam X-rays as an optimization basic template, and executing S4-2-2, otherwise, the cone beam X-ray measurement data compensation processing result passes, reserving the overfitting verification processing result of the current running data deviation recognition result, and the cone beam X-ray measurement data compensation processing result is null;
S4-2-2, acquiring positive data training sets and negative data training sets with the same subset number according to the optimized basic template;
S4-2-3, using the current positive data training set and the negative data training set as updated positive data training set and negative data training set, and returning to S2.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
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.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411026163.7A CN118553397B (en) | 2024-07-30 | 2024-07-30 | Cone beam X-ray data calibration processing method based on linear regression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411026163.7A CN118553397B (en) | 2024-07-30 | 2024-07-30 | Cone beam X-ray data calibration processing method based on linear regression |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118553397A CN118553397A (en) | 2024-08-27 |
| CN118553397B true CN118553397B (en) | 2024-11-22 |
Family
ID=92453533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411026163.7A Active CN118553397B (en) | 2024-07-30 | 2024-07-30 | Cone beam X-ray data calibration processing method based on linear regression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118553397B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110236583A (en) * | 2019-06-19 | 2019-09-17 | 新里程医用加速器(无锡)有限公司 | Rotating platform cone-beam CT-systems, calibration die body and scaling method |
| CN115049753A (en) * | 2022-05-13 | 2022-09-13 | 沈阳铸造研究所有限公司 | Cone beam CT artifact correction method based on unsupervised deep learning |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10605933B2 (en) * | 2016-10-21 | 2020-03-31 | Carestream Health, Inc. | X-ray spectral calibration technique for cone-beam CT |
| RU2736160C1 (en) * | 2019-09-11 | 2020-11-12 | Акционерное общество "Научно-исследовательская производственная компания "Электрон" (АО "НИПК "Электрон") | Method of medical image forming |
-
2024
- 2024-07-30 CN CN202411026163.7A patent/CN118553397B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110236583A (en) * | 2019-06-19 | 2019-09-17 | 新里程医用加速器(无锡)有限公司 | Rotating platform cone-beam CT-systems, calibration die body and scaling method |
| CN115049753A (en) * | 2022-05-13 | 2022-09-13 | 沈阳铸造研究所有限公司 | Cone beam CT artifact correction method based on unsupervised deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118553397A (en) | 2024-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111667417B (en) | Method for determining a corrected recording geometry of a projection image | |
| JP2023021266A (en) | MEDICAL IMAGE PROCESSING APPARATUS, MEDICAL IMAGE PROCESSING METHOD AND X-RAY CT APPARATUS | |
| CN110298447B (en) | Method for processing parameters of machine learning method and reconstruction method | |
| CN111599432B (en) | Three-dimensional craniofacial image feature point marking analysis system and method | |
| CN111292378A (en) | CT scanning auxiliary method, device and computer readable storage medium | |
| CN111157539B (en) | Weld morphology monitoring method, system and device and readable storage medium | |
| CN107796834B (en) | Orthogonal electronic linear scanning CL imaging system and method | |
| CN110811663A (en) | Multi-region scanning method, device, equipment and storage medium | |
| EP4506884A1 (en) | Training method and apparatus for artifact removal model, and device, medium and program product | |
| CN110335325A (en) | A kind of CT image rebuilding method and its system | |
| CN110349234A (en) | A kind of CT cone beam images method for reconstructing and its system | |
| CN109964249A (en) | The device delineated for the adaptive profile to body part | |
| JP2022528818A (en) | How to calibrate X-ray projection geometry in X-ray cone beam computer tomography | |
| CN113205457A (en) | Microscopic image splicing method and system | |
| JP6466617B1 (en) | Abnormal sign diagnosis system and abnormality sign diagnosis method | |
| CN112734917B (en) | Three-dimensional curved surface reconstruction and optimization method, system and storage medium of medical data | |
| CN112001979B (en) | Motion artifact processing method, system, readable storage medium and apparatus | |
| CN118553397B (en) | Cone beam X-ray data calibration processing method based on linear regression | |
| CN119180759B (en) | Three-dimensional live-action medical image and path diagram fusion method and system | |
| CN110270017B (en) | Quality assurance method for hospital bed, radiotherapy system and storage medium | |
| CN118177867B (en) | Ultrasonic image acquisition system and method based on coordinate positioning and marking | |
| CN110060314B (en) | CT iterative reconstruction acceleration method and system based on artificial intelligence | |
| Heryan et al. | Validation framework for analyzing complex anatomical structures: application of L-system models | |
| CN113316779A (en) | Successive approximation calculation method, successive approximation calculation device, and program | |
| CN119359847B (en) | A method for reconstructing visual field images based on convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |