CN116485778A - Imaging detection method, imaging detection system, computer equipment and storage medium - Google Patents
Imaging detection method, imaging detection system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116485778A CN116485778A CN202310501382.5A CN202310501382A CN116485778A CN 116485778 A CN116485778 A CN 116485778A CN 202310501382 A CN202310501382 A CN 202310501382A CN 116485778 A CN116485778 A CN 116485778A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- detection
- sample
- intelligent
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 119
- 238000003384 imaging method Methods 0.000 title claims abstract description 64
- 238000012545 processing Methods 0.000 claims abstract description 86
- 238000004458 analytical method Methods 0.000 claims abstract description 61
- 238000003745 diagnosis Methods 0.000 claims abstract description 42
- 238000007781 pre-processing Methods 0.000 claims abstract description 30
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000012360 testing method Methods 0.000 claims description 22
- 238000013507 mapping Methods 0.000 claims description 18
- 238000012706 support-vector machine Methods 0.000 claims description 15
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000003709 image segmentation Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 230000000399 orthopedic effect Effects 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 abstract description 5
- 230000011218 segmentation Effects 0.000 description 8
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 231100000915 pathological change Toxicity 0.000 description 2
- 230000036285 pathological change Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 210000000988 bone and bone Anatomy 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 210000000845 cartilage Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000004195 computer-aided diagnosis Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 210000003049 pelvic bone Anatomy 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/41—Medical
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention relates to an imaging detection technology, and discloses an imaging detection method, an imaging detection system, computer equipment and a storage medium. The method comprises the steps of receiving a target CT image sent by a CT image acquisition terminal, and preprocessing the target CT image through an intelligent processing module to obtain a target preprocessed CT image; performing three-dimensional reconstruction on the target pretreatment CT image through an intelligent reconstruction module to obtain a target three-dimensional model; and detecting and analyzing the target three-dimensional model through an intelligent detection module to obtain a target detection and analysis result, and sending the target detection and analysis result to the CT image acquisition terminal. Compared with the prior art, the method can obtain specific quantized two-dimensional medical image information and generate a visualized three-dimensional image, so that more reliable, accurate and quantized orthopedics digital information is provided for actual diagnosis, the referenceability of medical images is finally improved, and meanwhile, the diagnosis work efficiency of doctors is improved.
Description
Technical Field
The present invention relates to the field of imaging detection, and in particular, to an imaging detection method, an imaging detection system, a computer device, and a storage medium.
Background
Orthopedic diseases are various, the professional background is complex, and misdiagnosis due to missed diagnosis is very easy to occur. The diagnosis method of the orthopedic diseases depends on medical images, traditionally doctors find out pathological changes by means of two-dimensional medical images and imagine reconstructing the position, the size and the shape of the pathological changes in the brain, the method is easily influenced by factors such as image quality, doctor diagnosis experience and the like, therefore, the diagnosis lacks quantitative and quantitative indexes, three-dimensional visual information is not utilized, and finally misdiagnosis and missed diagnosis are extremely easy to occur when the orthopedic diseases with complex diagnosis and unobvious characteristics are diagnosed. Therefore, the computer-aided diagnosis system for the orthopedic diseases based on the medical image processing key technology is designed and developed, and reliable quantitative index quantification information can be provided for the diagnosis of the actual orthopedic diseases. In general, the existing method has the defect that the traditional diagnosis based on the two-dimensional medical image is easily influenced by the diagnosis experience of subjective factors of doctors and the influence of image quality, so that the misdiagnosis and missed diagnosis are serious.
Therefore, how to use computer technology to process two-dimensional medical image intelligently, to form comprehensive and reliable quantitative index information of image, to provide accurate and effective digital information for practical diagnosis, is a problem to be solved urgently.
Disclosure of Invention
The invention mainly aims to provide an imaging detection method, an imaging detection system, computer equipment and a storage medium, and aims to provide more reliable, accurate and quantized orthopaedics digital information for actual diagnosis through a computer technology, so that the referenceability of medical images is improved, and meanwhile, the diagnosis work efficiency of doctors is improved.
In order to achieve the above object, the present invention provides an imaging detection method, comprising the steps of:
a receiving step: receiving a target CT image sent by a CT image acquisition terminal, and preprocessing the target CT image through an intelligent processing module to obtain a target preprocessed CT image;
and (3) reconstruction: performing three-dimensional reconstruction on the target pretreatment CT image through an intelligent reconstruction module to obtain a target three-dimensional model;
the detection step comprises: and detecting and analyzing the target three-dimensional model through an intelligent detection module to obtain a target detection and analysis result, and sending the target detection and analysis result to the CT image acquisition terminal.
In addition, in order to achieve the above object, the present invention also proposes an imaging detection system including a memory and a processor, wherein the memory stores an imaging detection program, and the imaging detection program when executed by the processor implements the steps of:
a receiving step: receiving a target CT image sent by a CT image acquisition terminal, and preprocessing the target CT image through an intelligent processing module to obtain a target preprocessed CT image;
and (3) reconstruction: performing three-dimensional reconstruction on the target pretreatment CT image through an intelligent reconstruction module to obtain a target three-dimensional model;
the detection step comprises: and detecting and analyzing the target three-dimensional model through an intelligent detection module to obtain a target detection and analysis result, and sending the target detection and analysis result to the CT image acquisition terminal.
In addition, to achieve the above object, the present invention also proposes a computer device, including a processor and a memory;
the processor is used for processing and executing the imaging detection method;
the memory is coupled to the processor for storing the imaging detection program, which when executed by the processor, causes the system to perform the steps of the imaging detection method.
Furthermore, to achieve the above object, the present invention also proposes a computer-readable storage medium storing an imaging detection program executable by at least one processor to cause the at least one processor to perform the steps of the imaging detection method as set forth in any one of the above.
The method comprises the steps of receiving a target CT image sent by a CT image acquisition terminal, and preprocessing the target CT image by an intelligent processing module to obtain a target preprocessed CT image; performing three-dimensional reconstruction on the target pretreatment CT image through an intelligent reconstruction module to obtain a target three-dimensional model; and detecting and analyzing the target three-dimensional model through an intelligent detection module to obtain a target detection and analysis result, and sending the target detection and analysis result to the CT image acquisition terminal. Compared with the prior art, the method can obtain specific quantized two-dimensional medical image information and generate a visualized three-dimensional image, so that more reliable, accurate and quantized orthopedics digital information is provided for actual diagnosis, the referenceability of medical images is finally improved, and meanwhile, the diagnosis work efficiency of doctors is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an imaging detection method of the present invention;
FIG. 2 is a schematic flow chart of the method for detecting the CT image of the second target as the CT image of the target pretreatment;
FIG. 3 is a flow chart of storing the support vector machine in the first processing unit in the imaging detection method of the present invention;
FIG. 4 is a schematic flow chart of the texture mapping result as the target three-dimensional model in the imaging detection method of the present invention;
FIG. 5 is a flow chart of the imaging detection method according to the present invention, wherein the target detection analysis result is used as a target diagnosis reference according to the reference instruction;
FIG. 6 is a schematic diagram of an operating environment of an imaging detection program according to the present invention;
FIG. 7 is a block diagram of an imaging detection procedure according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Description of the drawings:
the device comprises an electronic device 6, an imaging detection program 60, a memory 61, a processor 62, a display 63, a receiving module 701, a reconstruction module 702 and a detection module 703.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
The invention provides an imaging detection method which is applied to an imaging detection analysis system end.
As shown in fig. 1, fig. 1 is a flow chart of the imaging detection method of the present invention.
In this embodiment, the method includes:
step S100: receiving a target CT image sent by a CT image acquisition terminal, and preprocessing the target CT image through an intelligent processing module to obtain a target preprocessed CT image;
step S200: performing three-dimensional reconstruction on the target pretreatment CT image through an intelligent reconstruction module to obtain a target three-dimensional model;
step S300: and detecting and analyzing the target three-dimensional model through an intelligent detection module to obtain a target detection and analysis result, and sending the target detection and analysis result to the CT image acquisition terminal.
Firstly, the imaging detection analysis system end receives target CT images of cartilage tissues and the like of a target user, which are acquired and transmitted by the CT image acquisition terminal. And then preprocessing the target CT image through an intelligent processing module, and correspondingly obtaining a preprocessing result, namely obtaining the target preprocessing CT image, wherein the preprocessing includes image segmentation, registration, noise reduction and the like in an image processing technology. And then, performing three-dimensional reconstruction on the target pretreatment CT image through an intelligent reconstruction module, and converting the target pretreatment CT image into a visualized three-dimensional image from two dimensions, thus obtaining a target three-dimensional model. And finally, detecting and analyzing the target three-dimensional model by an intelligent detection module, obtaining a target detection and analysis result, and further transmitting the target detection and analysis result to the CT image acquisition terminal. Exemplary three-dimensional images are displayed through an intelligent display of the CT image acquisition terminal, and meanwhile, the three-dimensional images are marked in size and the like and the intelligent analysis data of each part are displayed correspondingly.
As shown in fig. 2, in this embodiment, the receiving step includes:
processing the target CT image through a first processing unit in the intelligent processing module to obtain a first target CT image processing result;
processing the first target CT image processing result by a second processing unit in the intelligent processing module to obtain a second target CT image processing result;
taking the second target CT image processing result as the target preprocessing CT image;
the first processing unit refers to an image segmentation processing unit, and the second processing unit refers to an image registration processing unit.
The intelligent processing module is used for performing intelligent image preprocessing on a target CT image sent by the CT image acquisition terminal, and comprises a first processing unit and a second processing unit. The first processing unit is an image segmentation processing unit and is used for carrying out segmentation processing on the target CT image and correspondingly obtaining a first target CT image processing result. The second processing unit is an image registration processing unit and is used for registering the first target CT image processing result and correspondingly obtaining a second target CT image processing result. And finally, taking the second target CT image processing result as the target preprocessing CT image. The target preprocessed CT image preprocessed by the intelligent processing module provides a real and effective two-dimensional image data basis for subsequent three-dimensional reconstruction, so that the accuracy and the practicability of a subsequent three-dimensional model are improved.
In this embodiment, the processing, by the first processing unit in the above-mentioned intelligent processing module, the target CT image to obtain a first target CT image processing result includes:
acquiring a support vector machine in the first processing unit;
analyzing the target CT image through the support vector machine to obtain an image classification result, wherein the image classification result comprises a first area and a second area;
and dividing the target CT image according to the first region and the second region to obtain a processing result of the first target CT image.
As shown in fig. 3, in this embodiment, the obtaining the support vector machine in the first processing unit includes:
acquiring a target object in the target CT image;
constructing a CT image sample set of the target object based on big data, wherein the CT image sample set comprises a plurality of samples;
acquiring a first sample in the plurality of samples;
first marking is carried out on the area which belongs to the target object in the first sample, and second marking is carried out on the area which does not belong to the target object in the first sample;
constructing a first mapping relation between the first sample and the first mark and between the first sample and the second mark, and obtaining a first training data set based on the first mapping relation;
and training according to the first training data set to obtain the support vector machine, and storing the support vector machine into the first processing unit.
In this embodiment, after the first marking is performed on the area in the first sample, which belongs to the target object, and the second marking is performed on the area in the first sample, the method further includes:
based on the first sample, carrying out multi-feature acquisition on the target object to obtain first feature information;
the first characteristic information comprises a first edge characteristic, a first color characteristic and a first texture characteristic;
the method further comprises the steps of:
removing the target object in the first sample to obtain a non-target object;
based on the first sample, carrying out multi-feature acquisition on the non-target object to obtain second feature information;
the second characteristic information comprises a second edge characteristic, a second color characteristic and a second texture characteristic;
and calibrating the first mark and the second mark in sequence according to the first characteristic information and the second characteristic information respectively.
The first processing unit in the intelligent processing module firstly acquires a target object in the target CT image, such as a vertebra, a pelvic bone and the like, before processing the target CT image and correspondingly obtaining a first target CT image processing result. A CT image sample set of the target object is then constructed based on the big data, wherein the CT image sample set comprises a plurality of samples. Each of the plurality of samples includes the target object, such as CT images, digital model maps, etc., of the target object at different angles, on different individual bodies, for example. And then, any one sample in the plurality of samples is acquired and is recorded as a first sample, a first mark is carried out on the area which belongs to the target object in the first sample, a second mark is carried out on the area which does not belong to the target object in the first sample, and the distinction of different image areas on the first target CT image processing result is realized through the first mark and the second mark. Further, a first mapping relation between the first sample and the first mark and a first mapping relation between the first sample and the second mark are constructed, and a first training data set is obtained based on the first mapping relation. And finally, training according to the first training data set to obtain the support vector machine, and storing the support vector machine into the first processing unit.
And then, carrying out automatic analysis on the target CT image through the support vector machine in the first processing unit, and correspondingly obtaining an intelligent image region classification result of the target CT image, namely obtaining an image classification result. The image classification result comprises a first area and a second area. The first region and the second region refer to a region belonging to the target object and a region not belonging to the target object in the target CT image, respectively. And finally, carrying out segmentation processing on the target CT image according to the first region and the second region, and correspondingly obtaining a processing result of the first target CT image, namely a segmentation processing result of the target CT image.
In addition, multi-feature acquisition is performed on the target object based on the first sample, and first feature information is correspondingly obtained. The first characteristic information comprises a first edge characteristic, a first color characteristic and a first texture characteristic. And then, eliminating the target object in the first sample and correspondingly obtaining a non-target object. And then, carrying out multi-feature acquisition on the non-target object based on the first sample to obtain second feature information. The second characteristic information comprises a second edge characteristic, a second color characteristic and a second texture characteristic. Exemplary are whether edges are distinct, shape size dimensions, and corresponding region noise characteristic information. And finally, calibrating the first mark and the second mark in sequence according to the first characteristic information and the second characteristic information respectively so as to improve the segmentation accuracy between the target object and the non-target object. In summary, the support vector machine is used to perform preliminary segmentation on the target CT image, and then the feature point information is combined to calibrate the preliminary segmentation result, so that the defect of an effective single segmentation method is overcome, the region segmentation is more accurate, the interference object is removed by image segmentation, the region of interest is segmented, the feature with high correlation with the diagnosis result is conveniently extracted, and a more reliable and effective reference is provided for the diagnosis result of the orthopedic disease.
As shown in fig. 4, in this embodiment, the reconstructing step includes:
acquiring point cloud data of the target preprocessing CT image, and analyzing the point cloud data by the intelligent reconstruction module to acquire output information;
extracting a model parameter estimation result in the output information, and obtaining a preset point cloud model based on the model parameter estimation result;
basic characteristic parameters of the target preprocessing CT image are obtained, and texture mapping is carried out on the preset point cloud model based on the basic characteristic parameters, so that a texture mapping result is obtained;
and taking the texture mapping result as the target three-dimensional model.
In this embodiment, the obtaining the point cloud data of the target preprocessing CT image and analyzing the point cloud data by the intelligent reconstruction module to obtain the output information includes:
the intelligent reconstruction module randomly samples the point cloud data to obtain a first sample, and obtains a first parameter estimation result of a first model based on the first sample;
removing the first sample from the point cloud data to obtain a first non-sample, wherein the first non-sample comprises a plurality of non-sample point cloud data;
sequentially calculating the distances from the plurality of non-sample point cloud data to the first model, and screening the plurality of non-sample point cloud data by combining a preset distance threshold value to obtain a first consistency point set;
calculating a first data volume in the first consistency point set, and judging whether the first data volume meets a preset quantity threshold;
if the first data volume meets the preset quantity threshold value, a first overestimation instruction is obtained;
obtaining a second parameter estimation result of the first model based on the first consistency point set according to the first re-estimation instruction;
and replacing the first parameter estimation result with the second parameter estimation result to serve as the output information.
The intelligent reconstruction module is a module based on a random sampling consistency algorithm principle, and performs data information analysis on the target preprocessing CT image so as to realize conversion from a two-dimensional image to a three-dimensional model.
Firstly, point cloud data of the target preprocessing CT image are obtained, the point cloud data are used as input information analyzed by the intelligent reconstruction module, and output information is obtained through analysis by the intelligent reconstruction module. Specifically, the intelligent reconstruction module randomly samples from the point cloud data to obtain a first sample, and obtains a first parameter estimation result of a first model based on the first sample. And then removing the first sample from the point cloud data to obtain a first non-sample. Wherein the first non-sample comprises a plurality of non-sample point cloud data. And sequentially calculating the distances from the plurality of non-sample point cloud data to the first model, and screening out the non-sample point cloud data meeting a preset distance threshold value to form the first consistency point set. The preset distance threshold is a distance range set based on comprehensive feature analysis of orthopedics actual structural organization and the like, and is stored in the intelligent reconstruction module in advance. And then, calculating a first data volume in the first consistency point set, and judging whether the first data volume meets a preset quantity threshold value. When the first data quantity meets the preset quantity threshold, the system automatically obtains a first re-estimation instruction, and the first re-estimation instruction is used for carrying out parameter calculation estimation on a three-dimensional model of a target object in a target preprocessing CT image again based on the first consistency point set, and replaces the first parameter estimation result with a second parameter estimation result to serve as the output information. Otherwise, when the first data volume does not meet the preset quantity threshold, the iterative loop still needs to be continued at the moment, so that the system automatically obtains a first sampling instruction for randomly sampling point cloud data from the target preprocessing CT image again.
And extracting a model parameter estimation result in the output information of the intelligent registration fusion model, and constructing a preset point cloud model of the target object in the target preprocessing CT image based on the model parameter estimation result. And then, acquiring relevant shooting parameter characteristics of equipment for acquiring the target object in the target preprocessing CT image to obtain basic characteristic parameters, and further performing texture mapping on the preset point cloud model based on the basic characteristic parameters to obtain a texture mapping result. That is, the mutual correspondence between the three-dimensional object and the two-dimensional image thereof is solved, and the mutual correspondence is influenced by the imaging model parameters of the acquisition equipment. And finally, taking the preset point cloud model after texture mapping, namely the texture mapping result, as a three-dimensional model of a target object in the target preprocessing CT image. The corresponding relation between the target object in the target preprocessing CT image and the three-dimensional preset cloud point model is determined, so that the texture information in the two-dimensional key frame image is mapped into the three-dimensional preset cloud point model, and the three-dimensional modeling is realized. Iterative optimization is carried out on three-dimensional model construction parameters of a target object in a target pretreatment CT image through random sampling consistency, an estimation result of the model parameters is finally obtained, an accurate and effective data basis is provided for constructing a three-dimensional model of a bone structure, and the technical effects of providing three-dimensional model construction accuracy and practicality are further achieved.
In this embodiment, the imaging detection method is applied to a CT image acquisition terminal, and includes:
acquiring the target CT image, wherein the target CT image is a CT image with a target user identifier;
and sending the target CT image to the imaging detection analysis system end, and receiving the target detection analysis result of the imaging detection analysis system end.
As shown in fig. 5, in this embodiment, the sending the target CT image to the imaging detection analysis system and receiving the target detection analysis result of the imaging detection analysis system include:
constructing a test verification data set, wherein the test verification data set comprises a plurality of test CT images, and the plurality of test CT images have a plurality of test diagnosis results;
sequentially checking the plurality of test CT images serving as checking information to obtain a plurality of detection analysis results;
comparing the detection analysis results with the test diagnosis results to obtain intelligent detection evaluation results;
the intelligent detection evaluation result comprises detection accuracy and detection missed diagnosis rate;
performing reliability evaluation on the target detection analysis result according to the detection accuracy and the detection missed diagnosis rate to obtain a target reliability index;
if the target reliability index meets a preset reliability threshold, generating a reference instruction, and taking the target detection analysis result as a target diagnosis reference according to the reference instruction.
And acquiring the target CT image of a target user by a CT image acquisition terminal, transmitting the target CT image to the imaging detection analysis system end, and simultaneously receiving the target detection analysis result of the imaging detection analysis system end on the target CT image. And then, constructing a test inspection data set to analyze the effectiveness of the target detection analysis result obtained by the intelligent processing analysis of the imaging detection analysis system. The test and inspection data set comprises a plurality of test CT images, the plurality of test CT images have a plurality of test diagnosis results, and the plurality of test diagnosis results are diagnosis result data obtained by actually carrying out pathological feature analysis and diagnosis by medical staff. And then sequentially checking the plurality of test CT images serving as checking information to obtain a plurality of detection analysis results. And further comparing the detection analysis results with the test diagnosis results to obtain an intelligent detection evaluation result. The intelligent detection evaluation result comprises detection accuracy and detection missed diagnosis rate. And finally, carrying out weighted calculation analysis according to the detection accuracy and the detection missed diagnosis rate to realize specific quantification of reliability evaluation on the target detection analysis result, namely correspondingly obtaining a target reliability index. If the target reliability index meets a preset reliability threshold, the system automatically generates a reference instruction, and takes the target detection analysis result as a target diagnosis reference according to the reference instruction, so that a reference basis is provided for actual diagnosis determination, and the effect of improving diagnosis confirming efficiency is achieved.
The method comprises the steps of receiving a target CT image sent by a CT image acquisition terminal, and preprocessing the target CT image by an intelligent processing module to obtain a target preprocessed CT image; performing three-dimensional reconstruction on the target pretreatment CT image through an intelligent reconstruction module to obtain a target three-dimensional model; and detecting and analyzing the target three-dimensional model through an intelligent detection module to obtain a target detection and analysis result, and sending the target detection and analysis result to the CT image acquisition terminal. Compared with the prior art, the method can obtain specific quantized two-dimensional medical image information and generate a visualized three-dimensional image, so that more reliable, accurate and quantized orthopedics digital information is provided for actual diagnosis, the referenceability of medical images is finally improved, and meanwhile, the diagnosis work efficiency of doctors is improved.
The invention provides an imaging detection program.
Referring to FIG. 6, a schematic diagram of an operating environment of an imaging detection program 60 according to the present invention is shown.
In the present embodiment, the imaging detection program 60 is installed and run in the electronic device 6. The electronic device 6 may be a computing device such as a desktop computer, a notebook computer, a palm top computer, a server, etc. The electronic device 6 may include, but is not limited to, a memory 61, a processor 62, and a display 63. Fig. 6 shows only the electronic device 6 with components 11-13, but it is understood that not all shown components are required to be implemented, and that more or fewer components may alternatively be implemented.
The memory 61 may in some embodiments be an internal storage unit of the electronic device 6, such as a hard disk or a memory of the electronic device 6. The memory 61 may also be an external storage device of the electronic apparatus 6 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic apparatus 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the electronic apparatus 6. The memory 61 is used for storing application software installed on the electronic device 6 and various types of data, such as program codes of the imaging detection program 60. The memory 61 may also be used to temporarily store data that has been output or is to be output.
The processor 62 may in some embodiments be a central processing unit (Central Processing Unit, CPU), microprocessor or other data processing chip for executing program code or processing data stored in the memory 61, such as executing the imaging detection program 60, etc.
The display 63 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like in some embodiments. The display 63 is used for displaying information processed in the electronic device 6 and for displaying a visualized user interface. The components 11-13 of the electronic device 6 communicate with each other via a program bus.
Referring to FIG. 7, a block diagram of an imaging detection process 60 according to the present invention is shown.
In the present embodiment, the imaging detection program 60 may be divided into one or more modules, and the one or more modules are stored in the memory 61 and executed by one or more processors (the processor 62 in the present embodiment) to complete the present invention. For example, in fig. 7, the imaging detection program 60 may be divided into a receiving module 701, a reconstructing module 702, and a detecting module 703. The modules of the present invention refer to a series of computer program instruction segments capable of performing a specific function, more suitable than a program for describing the execution of the imaging detection program 60 in the electronic device 6, wherein:
the receiving module 701: receiving a target CT image sent by a CT image acquisition terminal, and preprocessing the target CT image through an intelligent processing module to obtain a target preprocessed CT image;
reconstruction module 702: performing three-dimensional reconstruction on the target pretreatment CT image through an intelligent reconstruction module to obtain a target three-dimensional model;
the detection module 703: and detecting and analyzing the target three-dimensional model through an intelligent detection module to obtain a target detection and analysis result, and sending the target detection and analysis result to the CT image acquisition terminal.
The application also provides an electronic device, which comprises a processor and a memory;
the processor configured to process the step of performing the imaging detection method according to any one of the above embodiments;
the memory is coupled to the processor for storing a program that, when executed by the processor, causes the system to perform the steps of any of the imaging detection methods described above.
Further, the present invention also proposes a computer-readable storage medium storing an imaging detection program executable by at least one processor to cause the at least one processor to execute the imaging detection method in any of the above embodiments.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structural changes made by the description of the present invention and the accompanying drawings or direct/indirect application in other related technical fields are included in the scope of the invention.
Claims (10)
1. An imaging detection method applied to an imaging detection analysis system end is characterized by comprising the following steps:
a receiving step: receiving a target CT image sent by a CT image acquisition terminal, and preprocessing the target CT image through an intelligent processing module to obtain a target preprocessed CT image;
and (3) reconstruction: performing three-dimensional reconstruction on the target pretreatment CT image through an intelligent reconstruction module to obtain a target three-dimensional model;
the detection step comprises: and detecting and analyzing the target three-dimensional model through an intelligent detection module to obtain a target detection and analysis result, and sending the target detection and analysis result to the CT image acquisition terminal.
2. The method of claim 1, wherein the receiving step comprises:
processing the target CT image through a first processing unit in the intelligent processing module to obtain a first target CT image processing result;
processing the first target CT image processing result by a second processing unit in the intelligent processing module to obtain a second target CT image processing result;
taking the second target CT image processing result as the target preprocessing CT image;
the first processing unit refers to an image segmentation processing unit, and the second processing unit refers to an image registration processing unit.
3. The method according to claim 2, wherein the processing the target CT image by the first processing unit in the intelligent processing module to obtain a first target CT image processing result includes:
acquiring a support vector machine in the first processing unit;
analyzing the target CT image through the support vector machine to obtain an image classification result, wherein the image classification result comprises a first area and a second area;
and dividing the target CT image according to the first region and the second region to obtain a processing result of the first target CT image.
4. The method of claim 3, wherein the obtaining a support vector machine in the first processing unit comprises:
acquiring a target object in the target CT image;
constructing a CT image sample set of the target object based on big data, wherein the CT image sample set comprises a plurality of samples;
acquiring a first sample in the plurality of samples;
first marking is carried out on the area which belongs to the target object in the first sample, and second marking is carried out on the area which does not belong to the target object in the first sample;
constructing a first mapping relation between the first sample and the first mark and between the first sample and the second mark, and obtaining a first training data set based on the first mapping relation;
and training according to the first training data set to obtain the support vector machine, and storing the support vector machine into the first processing unit.
5. The method of claim 4, wherein the first marking the region of the first sample that belongs to the target object and the second marking the region of the first sample that does not belong to the target object further comprises:
based on the first sample, carrying out multi-feature acquisition on the target object to obtain first feature information;
the first characteristic information comprises a first edge characteristic, a first color characteristic and a first texture characteristic;
the method further comprises the steps of:
removing the target object in the first sample to obtain a non-target object;
based on the first sample, carrying out multi-feature acquisition on the non-target object to obtain second feature information;
the second characteristic information comprises a second edge characteristic, a second color characteristic and a second texture characteristic;
and calibrating the first mark and the second mark in sequence according to the first characteristic information and the second characteristic information respectively.
6. The method of claim 1, wherein the reconstructing step comprises:
acquiring point cloud data of the target preprocessing CT image, and analyzing the point cloud data by the intelligent reconstruction module to acquire output information;
extracting a model parameter estimation result in the output information, and obtaining a preset point cloud model based on the model parameter estimation result;
basic characteristic parameters of the target preprocessing CT image are obtained, and texture mapping is carried out on the preset point cloud model based on the basic characteristic parameters, so that a texture mapping result is obtained;
and taking the texture mapping result as the target three-dimensional model.
7. The method of claim 6, wherein obtaining point cloud data of the target pre-processed CT image and analyzing by the intelligent reconstruction module to obtain output information comprises:
the intelligent reconstruction module randomly samples the point cloud data to obtain a first sample, and obtains a first parameter estimation result of a first model based on the first sample;
removing the first sample from the point cloud data to obtain a first non-sample, wherein the first non-sample comprises a plurality of non-sample point cloud data;
sequentially calculating the distances from the plurality of non-sample point cloud data to the first model, and screening the plurality of non-sample point cloud data by combining a preset distance threshold value to obtain a first consistency point set;
calculating a first data volume in the first consistency point set, and judging whether the first data volume meets a preset quantity threshold;
if the first data volume meets the preset quantity threshold value, a first overestimation instruction is obtained;
obtaining a second parameter estimation result of the first model based on the first consistency point set according to the first re-estimation instruction;
and replacing the first parameter estimation result with the second parameter estimation result to serve as the output information.
8. The method according to claim 1, applied to a CT image acquisition terminal, wherein the imaging detection method comprises:
acquiring the target CT image, wherein the target CT image is a CT image with a target user identifier;
and sending the target CT image to the imaging detection analysis system end, and receiving the target detection analysis result of the imaging detection analysis system end.
9. The method of claim 8, wherein said transmitting the target CT image to the imaging detection analysis system side and receiving the target detection analysis result of the imaging detection analysis system side comprises:
constructing a test verification data set, wherein the test verification data set comprises a plurality of test CT images, and the plurality of test CT images have a plurality of test diagnosis results;
sequentially checking the plurality of test CT images serving as checking information to obtain a plurality of detection analysis results;
comparing the detection analysis results with the test diagnosis results to obtain intelligent detection evaluation results;
the intelligent detection evaluation result comprises detection accuracy and detection missed diagnosis rate;
performing reliability evaluation on the target detection analysis result according to the detection accuracy and the detection missed diagnosis rate to obtain a target reliability index;
if the target reliability index meets a preset reliability threshold, generating a reference instruction, and taking the target detection analysis result as a target diagnosis reference according to the reference instruction.
10. An imaging detection system comprising a memory and a processor, wherein the memory has an imaging detection program stored thereon, the imaging detection program when executed by the processor performing the steps of:
a receiving step: receiving a target CT image sent by a CT image acquisition terminal, and preprocessing the target CT image through an intelligent processing module to obtain a target preprocessed CT image;
and (3) reconstruction: performing three-dimensional reconstruction on the target pretreatment CT image through an intelligent reconstruction module to obtain a target three-dimensional model;
the detection step comprises: and detecting and analyzing the target three-dimensional model through an intelligent detection module to obtain a target detection and analysis result, and sending the target detection and analysis result to the CT image acquisition terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310501382.5A CN116485778A (en) | 2023-04-27 | 2023-04-27 | Imaging detection method, imaging detection system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310501382.5A CN116485778A (en) | 2023-04-27 | 2023-04-27 | Imaging detection method, imaging detection system, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116485778A true CN116485778A (en) | 2023-07-25 |
Family
ID=87226761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310501382.5A Pending CN116485778A (en) | 2023-04-27 | 2023-04-27 | Imaging detection method, imaging detection system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116485778A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205489A (en) * | 2015-08-27 | 2015-12-30 | 华南理工大学 | License plate detection method based on color texture analyzer and machine learning |
| US20170337687A1 (en) * | 2015-11-30 | 2017-11-23 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for computer aided diagnosis |
| CN108038904A (en) * | 2017-12-20 | 2018-05-15 | 四川纵横睿影医疗技术有限公司 | Medical image three-dimensional reconstruction system |
| CN111048184A (en) * | 2019-12-24 | 2020-04-21 | 江苏大学 | CT image modeling and grading system for heart failure patients |
| CN112102234A (en) * | 2020-08-06 | 2020-12-18 | 复旦大学 | Ear sclerosis focus detection and diagnosis system based on target detection neural network |
| CN112365587A (en) * | 2020-12-01 | 2021-02-12 | 成都中创五联科技有限公司 | System and method for multi-mode three-dimensional modeling of tomographic image suitable for auxiliary diagnosis and treatment |
| CN115527657A (en) * | 2022-10-14 | 2022-12-27 | 北京帆引未来科技有限公司 | Image and image multi-mode reconstruction, imaging and labeling based on medical digital imaging and communication |
| CN115578523A (en) * | 2022-11-21 | 2023-01-06 | 慧医谷中医药科技(天津)股份有限公司 | Tongue three-dimensional modeling method and system for multi-angle image fusion |
| CN115661132A (en) * | 2022-12-05 | 2023-01-31 | 泸州职业技术学院 | Computer storage medium and device for detecting benign and malignant pulmonary nodules |
-
2023
- 2023-04-27 CN CN202310501382.5A patent/CN116485778A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205489A (en) * | 2015-08-27 | 2015-12-30 | 华南理工大学 | License plate detection method based on color texture analyzer and machine learning |
| US20170337687A1 (en) * | 2015-11-30 | 2017-11-23 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for computer aided diagnosis |
| CN108038904A (en) * | 2017-12-20 | 2018-05-15 | 四川纵横睿影医疗技术有限公司 | Medical image three-dimensional reconstruction system |
| CN111048184A (en) * | 2019-12-24 | 2020-04-21 | 江苏大学 | CT image modeling and grading system for heart failure patients |
| CN112102234A (en) * | 2020-08-06 | 2020-12-18 | 复旦大学 | Ear sclerosis focus detection and diagnosis system based on target detection neural network |
| CN112365587A (en) * | 2020-12-01 | 2021-02-12 | 成都中创五联科技有限公司 | System and method for multi-mode three-dimensional modeling of tomographic image suitable for auxiliary diagnosis and treatment |
| CN115527657A (en) * | 2022-10-14 | 2022-12-27 | 北京帆引未来科技有限公司 | Image and image multi-mode reconstruction, imaging and labeling based on medical digital imaging and communication |
| CN115578523A (en) * | 2022-11-21 | 2023-01-06 | 慧医谷中医药科技(天津)股份有限公司 | Tongue three-dimensional modeling method and system for multi-angle image fusion |
| CN115661132A (en) * | 2022-12-05 | 2023-01-31 | 泸州职业技术学院 | Computer storage medium and device for detecting benign and malignant pulmonary nodules |
Non-Patent Citations (1)
| Title |
|---|
| 叶晓健 等: "《中国生物医学工程进展 上》", 上海科学技术出版社, pages: 493 - 495 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107767376B (en) | X-ray bone age prediction method and system based on deep learning | |
| US8335359B2 (en) | Systems, apparatus and processes for automated medical image segmentation | |
| US8126242B2 (en) | Computer program products and methods for detection and tracking of rheumatoid arthritis | |
| JP6807820B2 (en) | Image search device, method and program | |
| CN103249358B (en) | Medical image-processing apparatus | |
| EP3657433B1 (en) | Medical image data | |
| KR101645292B1 (en) | System and method for automatic planning of two-dimensional views in 3d medical images | |
| US20110064289A1 (en) | Systems and Methods for Multilevel Nodule Attachment Classification in 3D CT Lung Images | |
| Yao et al. | Texture synthesis based thyroid nodule detection from medical ultrasound images: interpreting and suppressing the adversarial effect of in-place manual annotation | |
| Bagaria et al. | Bone fractures detection using support vector machine and error backpropagation neural network | |
| CN110570425A (en) | Lung nodule analysis method and device based on deep reinforcement learning algorithm | |
| CN117274278B (en) | Retina image focus part segmentation method and system based on simulated receptive field | |
| CN115661152B (en) | Target development condition analysis method based on model prediction | |
| CN112002407A (en) | Breast cancer diagnosis device and method based on ultrasonic video | |
| CN115661141B (en) | Tooth and alveolar bone segmentation method and system based on CBCT image | |
| CN116485778A (en) | Imaging detection method, imaging detection system, computer equipment and storage medium | |
| Fablet et al. | Reconstructing individual shape histories of fish otoliths: A new image-based tool for otolith growth analysis and modeling | |
| CN115564756A (en) | Medical image focus positioning display method and system | |
| WO2014106747A1 (en) | Methods and apparatus for image processing | |
| CN113177923B (en) | Medical image content identification method, electronic equipment and storage medium | |
| CN113436139A (en) | Small intestine nuclear magnetic resonance image identification and physiological information extraction system and method based on deep learning | |
| CN112801943A (en) | Medical image processing method and device | |
| CN112633405A (en) | Model training method, medical image analysis device, medical image analysis equipment and medical image analysis medium | |
| Rahmatullah et al. | Analysis of semi-automated method for femur length measurement from foetal ultrasound | |
| Fischer et al. | Bone age assessment by content-based image retrieval and case-based reasoning |
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 |