CN117752357A - Leg blood vessel construction system and method based on patient ct - Google Patents
Leg blood vessel construction system and method based on patient ct Download PDFInfo
- Publication number
- CN117752357A CN117752357A CN202311597543.1A CN202311597543A CN117752357A CN 117752357 A CN117752357 A CN 117752357A CN 202311597543 A CN202311597543 A CN 202311597543A CN 117752357 A CN117752357 A CN 117752357A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- blood vessel
- leg
- vascular
- 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
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 103
- 238000010276 construction Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 38
- 238000007781 pre-processing Methods 0.000 claims abstract description 33
- 238000003745 diagnosis Methods 0.000 claims abstract description 30
- 230000003287 optical effect Effects 0.000 claims abstract description 27
- 238000003709 image segmentation Methods 0.000 claims abstract description 26
- 238000003325 tomography Methods 0.000 claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 210000003205 muscle Anatomy 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000005516 engineering process Methods 0.000 claims abstract description 16
- 210000001519 tissue Anatomy 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 5
- 230000002792 vascular Effects 0.000 claims description 75
- 238000005259 measurement Methods 0.000 claims description 38
- 238000002591 computed tomography Methods 0.000 claims description 21
- 230000000007 visual effect Effects 0.000 claims description 17
- 230000011218 segmentation Effects 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 11
- 238000013135 deep learning Methods 0.000 claims description 10
- 230000002708 enhancing effect Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000003672 processing method Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 201000010099 disease Diseases 0.000 claims description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 4
- 230000036541 health Effects 0.000 claims description 4
- 230000004069 differentiation Effects 0.000 claims description 3
- 238000002224 dissection Methods 0.000 claims description 3
- 238000002583 angiography Methods 0.000 abstract description 5
- 210000003462 vein Anatomy 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 244000309466 calf Species 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a leg blood vessel construction system and method based on patient ct, comprising the following steps: the frequency domain optical correlation tomography (SD-OCT) scanning system is used for acquiring, processing and analyzing images; the image preprocessing module is used for preprocessing the acquired image and highlighting distinguishing features between blood vessels and muscle tissues in the image; the image reconstruction module is used for providing accurate information according to the data acquired by the frequency domain optical correlation tomography (SD-OCT) scanning system; the image segmentation module is used for distinguishing blood vessel areas in the image from other tissues; the blood vessel bifurcation detection module is used for detecting the distribution and trend of blood vessels; the blood vessel diameter measuring module can better observe and analyze the blood vessel condition, finally improves the accuracy of diagnosis and treatment analysis of a doctor on a patient, improves the cure rate, greatly avoids the probability of misdiagnosis, and compared with the traditional angiography technology, the scheme has no pain and no burden, and greatly relieves the pain of the patient in the process of treatment.
Description
Technical Field
The invention relates to the technical field of blood vessel construction, in particular to a leg blood vessel construction system and method based on patient ct.
Background
Computed tomography (Computerized Tomography, CT), also known as computed tomography (Computed Tomography), is a medical imaging technique that uses X-rays and computer techniques to generate images of a body structure having a cross-section.
For scanned images, the images can be associated to body surface marks in software, the imaging definition far exceeds the angiography technology, the distribution of blood vessels is more visual and better observed, the traditional angiography technology is difficult to show the communication between the vein blood vessels of the legs and the muscles and other blood vessels of the lower legs of a patient, the contrast measurement value is less, the diagnosis and analysis of a later doctor are not facilitated, and at present, the function of computed tomography is less applied to the scheme of the leg blood vessel construction system of the patient.
In summary, the present invention proposes a leg blood vessel construction system and method based on patient ct to solve the above-mentioned problems of the background art.
Disclosure of Invention
The invention aims to provide a leg blood vessel construction system and method based on patient ct, which are used for solving the problems that the traditional angiography technology proposed in the background technology is difficult to present the communication between the leg vein blood vessel and the calf muscle and other blood vessels, and the contrast measurement value is less, so that the diagnosis and analysis of a later doctor are not facilitated.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a patient ct-based leg vascular construction system comprising:
the frequency domain optical correlation tomography (SD-OCT) scanning system is used for acquiring, processing and analyzing images;
the image preprocessing module is used for preprocessing the acquired image and highlighting distinguishing features between blood vessels and muscle tissues in the image;
the image reconstruction module is used for providing accurate information according to the data acquired by the frequency domain optical correlation tomography (SD-OCT) scanning system;
the image segmentation module is used for distinguishing blood vessel areas in the image from other tissues;
the blood vessel bifurcation detection module is used for detecting the distribution and trend of blood vessels;
the blood vessel diameter measurement module is used for carrying out accurate diameter measurement on each target blood vessel segment of the leg and acquiring detailed blood vessel structure information;
the three-dimensional reconstruction module is used for converting the segmented vascular structure into a three-dimensional model;
the AI learning module is used for improving the accuracy and efficiency of automatic analysis, and can more accurately identify and process the blood vessel characteristics in the image after a large amount of training data and repeated iterative optimization;
medical image viewing software for viewing and viewing CT leg blood vessel images;
the display module is used for visually displaying the three-dimensional leg vascular system model constructed by the modules together;
the frequency domain optical correlation tomography SD-OCT scanning system, the image preprocessing module, the image reconstruction module, the image segmentation module, the blood vessel bifurcation detection module, the blood vessel diameter measurement module, the three-dimensional reconstruction module, the AI learning module, the medical image viewing software and the display module are in communication connection.
As a preferable technical scheme of the leg blood vessel construction system based on patient ct, the image preprocessing module carries out specific denoising and enhancement operation of preprocessing, improves the quality and definition of images, and adopts the processing methods of filtering, sharpening and contrast adjustment.
As a preferable technical scheme of the leg blood vessel construction system based on patient ct, the AI learning model related to the AI learning module is specifically a Convolutional Neural Network (CNN).
As a preferable technical scheme of the leg blood vessel construction system based on patient ct, the image segmentation module adopts a comparison principle of threshold segmentation and region growth when the image segmentation module is used for differentiation.
As a preferable technical scheme of the leg blood vessel construction system based on patient ct, the invention further comprises:
and the database is used for storing the constructed display models of the leg blood vessels of different patients and the data thereof.
The leg blood vessel construction method based on patient ct comprises the following steps:
s1, CT scanning and shooting operation: the frequency domain optical correlation tomographic SD-OCT scanning system is used to align the leg of the patient, adjust parameters to scan, and generate CT images as CT scan rays penetrate the leg tissue of the patient.
Software/device: and the frequency domain optical correlation tomography (SD-OCT) scanning system is used for acquiring, processing and analyzing images.
S2, an image preprocessing module: the image preprocessing module is used for preprocessing an original image obtained by CT scanning, and comprises denoising and enhancing operations, the quality and the definition of the image are improved, and the processing method also comprises filtering, sharpening and contrast adjustment, so that distinguishing features between blood vessels and muscle tissues in the highlighted image are performed, and a basis is provided for processing and analysis.
S3, image reconstruction: and reconstructing a tomographic image obtained by CT scanning through a reconstruction algorithm of an image reconstruction module to generate three-dimensional voxel data, so that the data comprehensively shows the form and structure of the leg vascular system of the patient and provides accurate information.
S4, image segmentation: the vascular structure is extracted from the image through a segmentation algorithm of the image segmentation module, which comprises threshold segmentation and region growth, so that the vascular region in the image is distinguished from other tissues, and an accurate basis is provided for subsequent measurement and analysis.
S5, detecting bifurcation points: and detecting and marking bifurcation points in the vascular system through a vascular bifurcation detection module so as to construct a complete vascular network, wherein the detection result comprises the distribution and trend of blood vessels, and reference information is provided for diagnosis and treatment.
S6, diameter measurement: accurate diameter measurement is carried out on each target vessel segment of the leg through a vessel diameter measurement module, detailed vessel structure information is obtained, and the data are measured through a frequency domain optical correlation tomography (SD-OCT) scanning system to provide more accurate diagnosis basis and help to judge the health condition and the disease degree of the vessel.
S7, three-dimensional reconstruction: the segmented vascular structure is converted into a three-dimensional model through a three-dimensional reconstruction module, and the shape and distribution of the leg vascular system with high sense of realism and intuitiveness are constructed and presented.
S8, AI model learning and optimization: the model training is performed by using the convolutional neural network CNN by using the AI model deep learning technology, the model training is performed by using the deep learning technology aiming at tasks such as image segmentation, bifurcation point detection and diameter measurement, the accuracy and the efficiency of automatic analysis are improved, and after a large amount of training data and repeated iterative optimization, the vascular characteristics in the image can be more accurately identified and processed, and the accuracy and the efficiency of diagnosis are improved.
S9, medical image viewing and computer operation: using medical image viewing software, a physician can conveniently view and view CT leg vessel images, which typically has various functions and tools such as zoom, rotation, measurement, etc., to support more detailed analysis and diagnosis by the physician, while medical image processing software can also provide a segmentation and dissection function of muscles and vessels for analysis and processing as a preferred solution for a patient CT-based leg vessel construction system of the present invention.
S10, result display: the three-dimensional leg vascular system model is visually presented by the result display module, so that doctors or researchers can analyze and diagnose the leg vascular system based on patient ct by using the preferable technical scheme of the leg vascular system, the morphology, structure and spatial relationship of the blood vessel can be clearly displayed, more visual diagnosis basis is provided for doctors, and meanwhile, the doctors can adjust the visual angle, color and other attributes of the model as required, so that the vascular condition can be observed and analyzed better.
As a technical scheme of the leg blood vessel construction method based on patient ct, the medical image viewing software in the step S9 is specifically Osirix medical image viewing software.
Compared with the prior art, the invention has the beneficial effects that: the system of the invention can provide high-resolution images by using a frequency domain optical correlation tomography (SD-OCT) scanning system, so that details of a vascular system can be more clearly displayed, an image preprocessing module adopts operations such as denoising, enhancing and the like, the quality and the definition of the images are improved, distinguishing characteristics of blood vessels and muscle tissues are facilitated to be highlighted, the system can reconstruct two-dimensional images obtained by CT scanning into three-dimensional voxel data by an algorithm of the image reconstruction module, comprehensively display the morphology and the structure of the vascular system of a leg of a patient, provide accurate information, extract the vascular structure from the images, provide accurate basis for subsequent measurement and analysis, detect and mark bifurcation points in the vascular system, and a vascular diameter measurement module provides a function of accurately measuring the diameter of each target vascular segment of the leg, the method has the advantages that detailed vascular structure information is acquired, the accuracy and efficiency of automatic analysis are improved through a deep learning technology, vascular features in images can be more accurately identified and processed, a doctor can conveniently browse and view CT leg vascular images by using Osirix medical image viewing software, multiple functions and tools are provided, a doctor is supported to perform more detailed analysis and diagnosis, finally, a three-dimensional leg vascular system model constructed through a result display module is presented in a visual mode, a more visual diagnosis basis is provided for the doctor, an option for adjusting model attributes is provided, vascular conditions can be better observed and analyzed, the accuracy of the doctor on diagnosis and analysis of patients is finally improved, the cure rate is improved, the probability of misdiagnosis is greatly avoided, compared with the traditional angiography technology, the scheme is painless and non-burdened, the pain of the patient in the treatment is greatly relieved.
Drawings
Fig. 1 is a flowchart of a method for constructing a leg blood vessel based on patient ct according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
Referring to fig. 1, the present invention provides a technical solution:
a patient ct-based leg vascular construction system comprising:
the frequency domain optical correlation tomography (SD-OCT) scanning system is used for acquiring, processing and analyzing images;
the image preprocessing module is used for preprocessing the acquired image and highlighting distinguishing features between blood vessels and muscle tissues in the image;
the image reconstruction module is used for providing accurate information according to the data acquired by the frequency domain optical correlation tomography (SD-OCT) scanning system;
the image segmentation module is used for distinguishing blood vessel areas in the image from other tissues;
the blood vessel bifurcation detection module is used for detecting the distribution and trend of blood vessels;
the blood vessel diameter measurement module is used for carrying out accurate diameter measurement on each target blood vessel segment of the leg and acquiring detailed blood vessel structure information;
the three-dimensional reconstruction module is used for converting the segmented vascular structure into a three-dimensional model;
the AI learning module is used for improving the accuracy and efficiency of automatic analysis, and can more accurately identify and process the blood vessel characteristics in the image after a large amount of training data and repeated iterative optimization;
medical image viewing software for viewing and viewing CT leg blood vessel images;
the display module is used for visually displaying the three-dimensional leg vascular system model constructed by the modules together;
the system comprises a frequency domain optical correlation tomography (SD-OCT) scanning system, an image preprocessing module, an image reconstruction module, an image segmentation module, a blood vessel bifurcation detection module, a blood vessel diameter measurement module, a three-dimensional reconstruction module, an AI learning module, medical image viewing software and a display module which are in communication connection.
The image preprocessing module carries out the specific denoising and enhancing operation of preprocessing, improves the quality and definition of the image, and adopts the processing methods of filtering, sharpening and contrast adjustment.
The AI learning model referred to by the AI learning module is specifically a Convolutional Neural Network (CNN).
The image segmentation module adopts a comparison principle of threshold segmentation and region growth when the image segmentation module performs differentiation.
Further comprises:
and the database is used for storing the constructed display models of the leg blood vessels of different patients and the data thereof.
The leg blood vessel construction method based on patient ct comprises the following steps:
s1, CT scanning and shooting operation: the frequency domain optical correlation tomographic SD-OCT scanning system is used to align the leg of the patient, adjust parameters to scan, and generate CT images as CT scan rays penetrate the leg tissue of the patient.
Software/device: and the frequency domain optical correlation tomography (SD-OCT) scanning system is used for acquiring, processing and analyzing images.
S2, an image preprocessing module: the image preprocessing module is used for preprocessing an original image obtained by CT scanning, and comprises denoising and enhancing operations, the quality and the definition of the image are improved, and the processing method also comprises filtering, sharpening and contrast adjustment, so that distinguishing features between blood vessels and muscle tissues in the highlighted image are performed, and a basis is provided for processing and analysis.
S3, image reconstruction: and reconstructing a tomographic image obtained by CT scanning through a reconstruction algorithm of an image reconstruction module to generate three-dimensional voxel data, so that the data comprehensively shows the form and structure of the leg vascular system of the patient and provides accurate information.
S4, image segmentation: the vascular structure is extracted from the image through a segmentation algorithm of the image segmentation module, which comprises threshold segmentation and region growth, so that the vascular region in the image is distinguished from other tissues, and an accurate basis is provided for subsequent measurement and analysis.
S5, detecting bifurcation points: and detecting and marking bifurcation points in the vascular system through a vascular bifurcation detection module so as to construct a complete vascular network, wherein the detection result comprises the distribution and trend of blood vessels, and reference information is provided for diagnosis and treatment.
S6, diameter measurement: accurate diameter measurement is carried out on each target vessel segment of the leg through a vessel diameter measurement module, detailed vessel structure information is obtained, and the data are measured through a frequency domain optical correlation tomography (SD-OCT) scanning system to provide more accurate diagnosis basis and help to judge the health condition and the disease degree of the vessel.
S7, three-dimensional reconstruction: the segmented vascular structure is converted into a three-dimensional model through a three-dimensional reconstruction module, and the shape and distribution of the leg vascular system with high sense of realism and intuitiveness are constructed and presented.
S8, AI model learning and optimization: the model training is performed by using an AI model deep learning technology and a Convolutional Neural Network (CNN), and the model training is performed by using the deep learning technology aiming at tasks such as image segmentation, bifurcation point detection and diameter measurement, so that the accuracy and the efficiency of automatic analysis are improved, and after a large amount of training data and repeated iterative optimization, the blood vessel characteristics in the image can be more accurately identified and processed, and the accuracy and the efficiency of diagnosis are improved.
S9, medical image viewing and computer operation: using medical image viewing software, a physician can conveniently view and view CT leg blood vessel images, which typically have a variety of functions and tools, such as zoom, rotate, measure, etc., to support more detailed analysis and diagnosis by the physician, while medical image processing software can also provide a segmentation and dissection function of muscles and blood vessels for further analysis and processing.
S10, result display: the three-dimensional leg vascular system model constructed by the result display module is displayed in a visual mode for further analysis and diagnosis by doctors or researchers, so that the morphology, structure and spatial relationship of the blood vessel can be clearly displayed, more visual diagnosis basis is provided for the doctors, and meanwhile, the doctors can adjust the visual angle, color and other attributes of the model according to the needs, so that the conditions of the blood vessel can be observed and analyzed better.
The medical image viewing software in step S9 is specifically Osirix medical image viewing software.
Examples
The leg blood vessel construction system and the leg blood vessel construction method based on patient ct concretely comprise the following steps:
firstly, establishing a frequency domain optical correlation tomography (SD-OCT) scanning system for acquiring, processing and analyzing images; an image preprocessing module is established and used for preprocessing the acquired image and highlighting distinguishing features between blood vessels and muscle tissues in the image; an image reconstruction module is established and used for providing accurate information according to the data acquired by the frequency domain optical correlation tomography (SD-OCT) scanning system; an image segmentation module is established and used for distinguishing blood vessel areas in the image from other tissues; establishing a blood vessel bifurcation detection module for detecting the distribution and trend of blood vessels; establishing a blood vessel diameter measurement module for accurately measuring the diameter of each target blood vessel segment of the leg to acquire detailed blood vessel structure information; a three-dimensional reconstruction module is established and used for converting the segmented vascular structure into a three-dimensional model; the AI learning module is selected for improving the accuracy and efficiency of automatic analysis, and the blood vessel characteristics in the image can be more accurately identified and processed after a large amount of training data and repeated iterative optimization; selecting medical image viewing software for browsing and viewing CT leg blood vessel images; the method comprises the steps of establishing a display module, wherein the display module is used for visually displaying the three-dimensional leg vascular system model jointly constructed by the modules; the method comprises the steps that a frequency spectrum optical correlation tomographic SD-OCT scanning system, an image preprocessing module, an image reconstruction module, an image segmentation module, a blood vessel bifurcation detection module, a blood vessel diameter measurement module, a three-dimensional reconstruction module, an AI learning module, medical image viewing software and a display module are in communication connection with each other in a leg blood vessel construction system based on patient ct;
then, using a frequency domain optical correlation tomography (SD-OCT) scanning system to align the leg of the patient, adjusting parameters to scan, and generating a CT image when CT scanning rays penetrate leg tissues of the patient;
the image preprocessing module is used for preprocessing an original image obtained by CT scanning, including denoising and enhancing operations, improving the quality and definition of the image, and the processing method also includes filtering, sharpening and contrast adjustment, is used for highlighting distinguishing features between blood vessels and muscle tissues in the image, and provides a basis for processing and analysis;
reconstructing a tomographic image obtained by CT scanning through a reconstruction algorithm of an image reconstruction module to generate three-dimensional voxel data, so that the data comprehensively show the form and structure of the leg vascular system of a patient and are used for providing accurate information;
extracting the vascular structure from the image through a segmentation algorithm of the image segmentation module, wherein the segmentation algorithm comprises threshold segmentation and region growth, and distinguishing the vascular region from other tissues in the image, so as to provide an accurate basis for subsequent measurement and analysis;
detecting and marking bifurcation points in a vascular system through a vascular bifurcation detection module so as to construct a complete vascular network, wherein a detection result comprises the distribution and trend of blood vessels, and providing reference information for diagnosis and treatment;
accurate diameter measurement is carried out on each target vessel segment of the leg part through a vessel diameter measurement module, detailed vessel structure information is obtained, and the data are measured through a frequency domain optical correlation tomography (SD-OCT) scanning system and are used for providing more accurate diagnosis basis and helping to judge the health condition and the disease degree of the vessel;
converting the segmented vascular structure into a three-dimensional model through a three-dimensional reconstruction module, and constructing and presenting the shape and distribution of the leg vascular system with high sense of realism and intuitiveness;
the method comprises the steps of performing model training by using an AI model deep learning technology and a Convolutional Neural Network (CNN), aiming at tasks such as image segmentation, bifurcation point detection and diameter measurement, performing model training by using the deep learning technology, so as to improve the accuracy and efficiency of automatic analysis, and after a large amount of training data and repeated iterative optimization, identifying and processing vascular features in images more accurately, and improving the accuracy and efficiency of diagnosis;
using Osirix medical image viewing software, doctors can conveniently view and view CT leg blood vessel images, and these software usually have various functions and tools such as scaling, rotation, measurement, etc. to support doctors to perform more detailed analysis and diagnosis, and at the same time, medical image processing software can also provide a segmentation and peeling function of muscles and blood vessels for further analysis and processing;
finally, carrying out result display:
the three-dimensional leg vascular system model constructed by the result display module is displayed in a visual mode for further analysis and diagnosis by doctors or researchers, so that the morphology, structure and spatial relationship of the blood vessel can be clearly displayed, more visual diagnosis basis is provided for the doctors, and meanwhile, the doctors can adjust the visual angle, color and other attributes of the model according to the needs, so that the conditions of the blood vessel can be observed and analyzed better.
In summary, in the system, the frequency domain optical correlation tomographic SD-OCT scanning system is used to provide high resolution images, so that details of the vascular system can be clearly displayed, and meanwhile, the image preprocessing module adopts operations such as denoising and enhancement, so that the quality and the definition of the images are improved, distinguishing features of blood vessels and muscle tissues are facilitated to be highlighted, through an algorithm of the image reconstruction module, the system can reconstruct two-dimensional images obtained by CT scanning into three-dimensional voxel data, comprehensively display morphology and structure of the vascular system of a patient, provide accurate information, extract vascular structures from the images, provide accurate basis for subsequent measurement and analysis, detect and mark bifurcation points in the vascular system, and provide accurate diameter measurement functions for each target vascular segment of the leg, acquire detailed vascular structure information, improve accuracy and efficiency of automated analysis through a deep learning technology, more accurately identify and process vascular features in the images, use of Osir medical imaging software to view and view blood vessel images of the legs, provide various diagnostic tools and support detailed analysis tools, and display visual and display a three-dimensional analysis model for visual analysis, and finally, provide visual and adjust the diagnosis model for the vascular system.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. A patient ct-based leg vascular construction system, comprising:
the frequency domain optical correlation tomography (SD-OCT) scanning system is used for acquiring, processing and analyzing images;
the image preprocessing module is used for preprocessing the acquired image and highlighting distinguishing features between blood vessels and muscle tissues in the image;
the image reconstruction module is used for providing accurate information according to the data acquired by the frequency domain optical correlation tomography (SD-OCT) scanning system;
the image segmentation module is used for distinguishing blood vessel areas in the image from other tissues;
the blood vessel bifurcation detection module is used for detecting the distribution and trend of blood vessels;
the blood vessel diameter measurement module is used for carrying out accurate diameter measurement on each target blood vessel segment of the leg and acquiring detailed blood vessel structure information;
the three-dimensional reconstruction module is used for converting the segmented vascular structure into a three-dimensional model;
the AI learning module is used for improving the accuracy and efficiency of automatic analysis, and can more accurately identify and process the blood vessel characteristics in the image after a large amount of training data and repeated iterative optimization;
medical image viewing software for viewing and viewing CT leg blood vessel images;
the display module is used for visually displaying the three-dimensional leg vascular system model constructed by the modules together;
the frequency domain optical correlation tomography SD-OCT scanning system, the image preprocessing module, the image reconstruction module, the image segmentation module, the blood vessel bifurcation detection module, the blood vessel diameter measurement module, the three-dimensional reconstruction module, the AI learning module, the medical image viewing software and the display module are in communication connection.
2. The patient ct-based leg vascular construction system of claim 1, wherein: the image preprocessing module performs preprocessing specifically by denoising and enhancing operations, improves the quality and definition of an image, and adopts filtering, sharpening and contrast adjustment as processing methods.
3. The patient ct-based leg vascular construction system of claim 2, wherein: the AI learning model referred to by the AI learning module is specifically a Convolutional Neural Network (CNN).
4. A patient ct-based leg vascular construction system according to claim 3, wherein: and the image segmentation module adopts a comparison principle of threshold segmentation and region growth when the image segmentation module performs differentiation.
5. The patient ct-based leg vascular construction system of claim 4, further comprising:
and the database is used for storing the constructed display models of the leg blood vessels of different patients and the data thereof.
6. The patient ct-based leg blood vessel construction method according to any one of claims 1 to 5, comprising the steps of:
s1, CT scanning and shooting operation: the frequency domain optical correlation tomographic SD-OCT scanning system is used to align the leg of the patient, adjust parameters to scan, and generate CT images as CT scan rays penetrate the leg tissue of the patient.
Software/device: and the frequency domain optical correlation tomography (SD-OCT) scanning system is used for acquiring, processing and analyzing images.
S2, an image preprocessing module: the image preprocessing module is used for preprocessing an original image obtained by CT scanning, and comprises denoising and enhancing operations, the quality and the definition of the image are improved, and the processing method also comprises filtering, sharpening and contrast adjustment, so that distinguishing features between blood vessels and muscle tissues in the highlighted image are performed, and a basis is provided for processing and analysis.
S3, image reconstruction: and reconstructing a tomographic image obtained by CT scanning through a reconstruction algorithm of an image reconstruction module to generate three-dimensional voxel data, so that the data comprehensively shows the form and structure of the leg vascular system of the patient and provides accurate information.
S4, image segmentation: the vascular structure is extracted from the image through a segmentation algorithm of the image segmentation module, which comprises threshold segmentation and region growth, so that the vascular region in the image is distinguished from other tissues, and an accurate basis is provided for subsequent measurement and analysis.
S5, detecting bifurcation points: and detecting and marking bifurcation points in the vascular system through a vascular bifurcation detection module so as to construct a complete vascular network, wherein the detection result comprises the distribution and trend of blood vessels, and reference information is provided for diagnosis and treatment.
S6, diameter measurement: accurate diameter measurement is carried out on each target vessel segment of the leg through a vessel diameter measurement module, detailed vessel structure information is obtained, and the data are measured through a frequency domain optical correlation tomography (SD-OCT) scanning system to provide more accurate diagnosis basis and help to judge the health condition and the disease degree of the vessel.
S7, three-dimensional reconstruction: the segmented vascular structure is converted into a three-dimensional model through a three-dimensional reconstruction module, and the shape and distribution of the leg vascular system with high sense of realism and intuitiveness are constructed and presented.
S8, AI model learning and optimization: the model training is performed by using an AI model deep learning technology and a Convolutional Neural Network (CNN), and the model training is performed by using the deep learning technology aiming at tasks such as image segmentation, bifurcation point detection and diameter measurement, so that the accuracy and the efficiency of automatic analysis are improved, and after a large amount of training data and repeated iterative optimization, the blood vessel characteristics in the image can be more accurately identified and processed, and the accuracy and the efficiency of diagnosis are improved.
S9, medical image viewing and computer operation: using medical image viewing software, a physician can conveniently view and view CT leg blood vessel images, which typically have a variety of functions and tools, such as zoom, rotate, measure, etc., to support more detailed analysis and diagnosis by the physician, while medical image processing software can also provide a segmentation and dissection function of muscles and blood vessels for further analysis and processing.
S10, result display: the three-dimensional leg vascular system model constructed by the result display module is displayed in a visual mode for further analysis and diagnosis by doctors or researchers, so that the morphology, structure and spatial relationship of the blood vessel can be clearly displayed, more visual diagnosis basis is provided for the doctors, and meanwhile, the doctors can adjust the visual angle, color and other attributes of the model according to the needs, so that the conditions of the blood vessel can be observed and analyzed better.
7. The patient ct-based leg blood vessel construction method according to claim 6, wherein: the medical image viewing software in the step S9 is specifically Osirix medical image viewing software.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311597543.1A CN117752357A (en) | 2023-11-28 | 2023-11-28 | Leg blood vessel construction system and method based on patient ct |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311597543.1A CN117752357A (en) | 2023-11-28 | 2023-11-28 | Leg blood vessel construction system and method based on patient ct |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117752357A true CN117752357A (en) | 2024-03-26 |
Family
ID=90313588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311597543.1A Pending CN117752357A (en) | 2023-11-28 | 2023-11-28 | Leg blood vessel construction system and method based on patient ct |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117752357A (en) |
-
2023
- 2023-11-28 CN CN202311597543.1A patent/CN117752357A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI750583B (en) | Medical image dividing method, device, and system, and image dividing method | |
| CN105719278B (en) | A kind of medical image cutting method based on statistics deformation model | |
| CN113781439B (en) | Ultrasonic video focus segmentation method and device | |
| CN107563998B (en) | Method for processing heart image in medical image | |
| IL158566A (en) | Method and apparatus for medical intervention procedure planning | |
| CN109770943A (en) | A kind of ultrasonic automatic optimization method positioned using computer vision | |
| Giancardo et al. | Textureless macula swelling detection with multiple retinal fundus images | |
| CN101658428A (en) | Method and system for processing bitmap in perfusion imaging technology | |
| CN110264559B (en) | Bone tomographic image reconstruction method and system | |
| CN108618749A (en) | Retinal vessel three-dimensional rebuilding method based on portable digital fundus camera | |
| Cheng et al. | Airway segmentation and measurement in CT images | |
| CN109377481A (en) | Image quality evaluating method, device, computer equipment and storage medium | |
| JP2006102353A (en) | Apparatus, method and program for analyzing joint motion | |
| CN111062979B (en) | Visualization method and visualization system for acquiring physical characteristic parameters of thrombus based on medical image | |
| CN111466952B (en) | Real-time conversion method and system for ultrasonic endoscope and CT three-dimensional image | |
| CN116580033B (en) | Multi-mode medical image registration method based on image block similarity matching | |
| CN117752357A (en) | Leg blood vessel construction system and method based on patient ct | |
| CN110858412B (en) | Heart coronary artery CTA model building method based on image registration | |
| CN117455931A (en) | Segmentation and quantitative measurement method based on deep learning MR body adipose tissue | |
| CN116402954A (en) | Spine three-dimensional structure reconstruction method based on deep learning | |
| CN111583219B (en) | Analysis method and device for craniomaxillofacial soft and hard tissues and electronic equipment | |
| CN115690045A (en) | Quantitative assessment method for bone increment before and after periodontitis treatment based on curved surface fault slice | |
| CN112991478A (en) | Method for analyzing multi-temporal abnormal characteristic region parameters based on deep learning image | |
| CN117934651B (en) | Coronary artery CTA projection transformation method for lesion coronary artery detection | |
| CN111035403A (en) | Scanning opportunity determination method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |