CN116485800B - Automatic acquisition method, device, equipment and storage medium for morphological parameters of aneurysms - Google Patents
Automatic acquisition method, device, equipment and storage medium for morphological parameters of aneurysms Download PDFInfo
- Publication number
- CN116485800B CN116485800B CN202310752810.1A CN202310752810A CN116485800B CN 116485800 B CN116485800 B CN 116485800B CN 202310752810 A CN202310752810 A CN 202310752810A CN 116485800 B CN116485800 B CN 116485800B
- Authority
- CN
- China
- Prior art keywords
- aneurysm
- point
- blood vessel
- model
- central line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 206010002329 Aneurysm Diseases 0.000 title claims abstract description 196
- 230000000877 morphologic effect Effects 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 39
- 239000013598 vector Substances 0.000 claims abstract description 65
- 230000003902 lesion Effects 0.000 claims abstract description 52
- 230000002792 vascular Effects 0.000 claims abstract description 26
- 210000004204 blood vessel Anatomy 0.000 claims description 147
- 206010028980 Neoplasm Diseases 0.000 claims description 127
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 abstract description 8
- 230000000875 corresponding effect Effects 0.000 description 47
- 238000010586 diagram Methods 0.000 description 9
- 238000005259 measurement Methods 0.000 description 9
- 238000011156 evaluation Methods 0.000 description 4
- 201000008450 Intracranial aneurysm Diseases 0.000 description 2
- 238000002583 angiography Methods 0.000 description 2
- 238000010968 computed tomography angiography Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000032851 Subarachnoid Hemorrhage Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000000004 hemodynamic effect Effects 0.000 description 1
- 238000007917 intracranial administration Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/02007—Evaluating blood vessel condition, e.g. elasticity, compliance
- A61B5/02014—Determining aneurysm
-
- 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
- G06T7/0002—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
- 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
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Vascular Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Radiology & Medical Imaging (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Physiology (AREA)
- Cardiology (AREA)
- Neurosurgery (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The application relates to an automatic acquisition method, a device, equipment and a storage medium for aneurysm morphological parameters, which are characterized in that a three-dimensional vascular model is constructed according to vascular images, a corresponding first dimension norgram is obtained, a healthy vascular model without an aneurysm is reconstructed in the three-dimensional vascular model by determining lesion vascular segments, a first aneurysm cavity model of a target aneurysm is constructed according to the healthy vascular model, a direction axis of the aneurysm is obtained by calculating according to the first aneurysm cavity model and the central line of the healthy vascular model, the aneurysm neck plane of the aneurysm is determined by a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes, the first aneurysm cavity model is cut by the aneurysm neck plane to obtain a second aneurysm cavity model, and finally the aneurysm morphological parameters are obtained by calculating according to the second aneurysm cavity model and the aneurysm neck plane. The method improves the repeatability of morphological parameter calculation and improves the accuracy and efficiency of obtaining the morphological parameters of the aneurysm.
Description
Technical Field
The application relates to the technical field of medical image processing, in particular to an automatic acquisition method, device and equipment for morphological parameters of aneurysms and a storage medium.
Background
Intracranial aneurysms refer to abnormal bulging of the intracranial arterial wall, with an overall prevalence of about 3% -5%. Although most intracranial aneurysms do not rupture for life, once ruptured, they cause subarachnoid hemorrhage, with mortality rates up to 40%. Thus, it is particularly important to screen and evaluate the risk of rupture of an aneurysm in a timely manner. The risk of rupture of an aneurysm is often strongly correlated with the clinical characteristics of the patient, the morphological characteristics of the aneurysm, and the hemodynamic characteristics. Wherein morphological assessment is an important clinical means of predicting the risk of rupture of an aneurysm.
Morphological evaluation in the current clinical scenario is mainly based on manual measurement of two-dimensional images, and the measurement result deviates from the true three-dimensional geometry of the aneurysm. In addition, the selection of the visual angle of the image and the selection of the measuring position are different among different evaluators. Therefore, the manual measurement means have the problems of low accuracy and low repeatability.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an automatic acquisition method, apparatus, device, and storage medium for morphological parameters of an aneurysm that can avoid manual measurement and improve accuracy.
A method for automatically obtaining morphological parameters of an aneurysm, the method comprising:
acquiring a blood vessel image related to a target aneurysm, and constructing a corresponding blood vessel three-dimensional model according to the blood vessel image;
generating a first dimension norgram according to the blood vessel three-dimensional model, and determining a lesion blood vessel segment part in the blood vessel three-dimensional model through a blood vessel central line;
reconstructing an aneurysm-free healthy vessel model in the vessel three-dimensional model from the diseased vessel segment portion;
processing the first dimension norgram according to the healthy vessel model, extracting a second dimension norgram representing the cavity of the target aneurysm, and constructing a first tumor cavity model of the target aneurysm according to the second dimension norgram;
calculating according to the central lines of the first tumor cavity model and the healthy blood vessel model to obtain a direction axis of the aneurysm, and determining a tumor neck plane of the aneurysm through a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes;
cutting the first tumor cavity model by utilizing the tumor neck plane, and extracting the maximum connected domain as a second tumor cavity model;
and calculating the morphological parameters of the aneurysm according to the second tumor cavity model and the tumor neck plane so as to obtain the morphological parameters of the target aneurysm.
In one embodiment, the determining the lesion vessel segment portion through the vessel centerline in the three-dimensional model of the vessel comprises:
acquiring a first central line connecting a blood vessel inlet and a blood vessel outlet, a second central line connecting the blood vessel inlet and the aneurysm top and a third central line connecting the blood vessel outlet and the aneurysm top from the blood vessel three-dimensional model;
acquiring a maximum inscribed sphere radius sequence along a blood vessel line by taking each point on each central line as a central point, wherein the maximum inscribed sphere radius sequence is a first radius sequence, a second radius sequence and a third radius sequence respectively;
calculating the distance between each point on the second central line and the third central line and the nearest point on the first central line respectively so as to determine a first bifurcation point and a second bifurcation point on the first central line;
respectively taking the first bifurcation point and the second bifurcation point as starting points, and moving a preset distance on the first central line towards the direction of the blood vessel inlet and the direction of the blood vessel outlet to obtain a first lesion blood vessel segment end point and a second lesion blood vessel segment end point;
the lesion vessel segment part is a part between a first lesion vessel segment end point and a second lesion vessel segment end point in the vessel three-dimensional model.
In one embodiment, the calculating the distance between each point on the second center line and the third center line and the closest point on the first center line to determine the first branch point and the second branch point on the first center line includes:
traversing from the vascular inlet to calculate the distance between each point on the first central line and the nearest point on the second central line, and when the distance is larger than a preset threshold value, taking the corresponding point as the first bifurcation point;
and traversing from the vascular outlet to calculate the distance between each point on the first central line and the nearest point on the third central line, and when the distance is larger than a preset threshold value, taking the corresponding point as the second bifurcation point.
In one embodiment, reconstructing an aneurysmal-free healthy vessel model from the diseased vessel segment portion in the three-dimensional model of the vessel comprises:
removing the part between the first lesion blood vessel segment end point and the second lesion blood vessel segment end point on the first central line, and interpolating and complementing the removed part by using a spline curve to obtain a fourth central line;
removing data between the endpoints of the corresponding first lesion vessel segment and the endpoint of the second lesion vessel segment in the first radius sequence, and interpolating and complementing the removed part to obtain a fourth radius sequence;
And reconstructing according to the fourth central line and the fourth radius sequence to obtain the healthy blood vessel model without the aneurysm, wherein the fourth central line is the central line of the healthy blood vessel model.
In one embodiment, the processing the first dimension of the norgram according to the healthy vessel model, extracting a second dimension of the norgram representing the lumen of the target aneurysm, includes:
the first dimension Nor graph comprises a Thiessen polygon vertex set corresponding to the blood vessel three-dimensional model, and the radius of an inscribed sphere to which each vertex belongs;
and judging each Thiessen polygon vertex in the first dimension North chart according to the healthy blood vessel by using a ray method, and constructing the second dimension North chart according to Thiessen polygons to which all vertices positioned outside the healthy blood vessel model belong.
In one embodiment, the calculating according to the center lines of the first tumor cavity model and the healthy blood vessel model, to obtain the direction axis of the aneurysm includes:
calculating the distance between each point on the first tumor cavity model and a fourth central line, and classifying the points on the first tumor cavity model into multiple classes according to the obtained distance;
connecting each type of points by utilizing a shortest path algorithm, and correspondingly forming a plurality of circles of equidistant lines on the tumor cavity wall on the first tumor cavity model;
Calculating the geometric center coordinates of each circle of equidistant lines, and interpolating all the geometric center coordinates by using a cubic spline curve to obtain the direction axis of the aneurysm.
In one embodiment, the determining the neck plane of the aneurysm by generating a plurality of planes according to points on the direction axis and normal vectors corresponding to the planes includes:
taking an end point, which is close to the fourth central line, on the direction axis as a proximal end point, and taking an end point, which is far away from the fourth central line, as a distal end point;
taking the near end point as a first point of a direction axis, and simultaneously marking other points on the direction axis as a second point of the direction axis and a third point of the direction axis in sequence according to the distance from the near end to the first point of the direction axis until reaching the far end point;
generating a first plane by using the first point of the direction axis and a tangential vector corresponding to the first point, wherein the first plane passes through the first point of the direction axis and takes the tangential vector corresponding to the first point as a first normal vector;
deflecting the first normal vector by a preset angle in any direction to obtain a second normal vector, passing through a first point of the direction axis, and taking the second normal vector as a plane normal to obtain a second plane;
Until the first point rotates around the direction axis for one circle, a plurality of planes and normal vectors corresponding to the planes are obtained, the intersection line of each plane and the first tumor cavity model is calculated, and if a closed curve exists in the plurality of intersection lines, the plane corresponding to the curve with the smallest surrounding area in the closed curve is selected as the tumor neck plane of the aneurysm;
if no closed curve exists in the intersecting lines, selecting the second point of the direction axis to generate a plurality of planes and normal vectors corresponding to the planes until the aneurysm neck plane of the aneurysm is obtained.
An apparatus for automatically acquiring morphological parameters of an aneurysm, the apparatus comprising:
the blood vessel three-dimensional model construction module is used for acquiring a blood vessel image related to the target aneurysm and constructing a corresponding blood vessel three-dimensional model according to the blood vessel image;
the lesion blood vessel segment part determining module is used for generating a first dimension norgram according to the blood vessel three-dimensional model, and determining a lesion blood vessel segment part through a blood vessel central line in the blood vessel three-dimensional model;
a healthy vessel model construction module for reconstructing an aneurysm-free healthy vessel model in the vessel three-dimensional model from the diseased vessel segment portion;
the first tumor cavity model construction module is used for processing the first dimension norgram according to the healthy blood vessel model, extracting a second dimension norgram representing the target aneurysm cavity, and constructing a first tumor cavity model of the target aneurysm according to the second dimension norgram;
The aneurysm neck plane obtaining module is used for obtaining a direction axis of the aneurysm according to the central lines of the first tumor cavity model and the healthy blood vessel model, and determining a tumor neck plane of the aneurysm through a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes;
the second tumor cavity model obtaining module is used for cutting the first tumor cavity model by utilizing the tumor neck plane and extracting the maximum connected domain as a second tumor cavity model;
and the morphological parameter automatic acquisition module is used for calculating the morphological parameters of the aneurysm according to the second tumor cavity model and the tumor neck plane so as to acquire the morphological parameters of the target aneurysm.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring a blood vessel image related to a target aneurysm, and constructing a corresponding blood vessel three-dimensional model according to the blood vessel image;
generating a first dimension norgram according to the blood vessel three-dimensional model, and determining a lesion blood vessel segment part in the blood vessel three-dimensional model through a blood vessel central line;
Reconstructing an aneurysm-free healthy vessel model in the vessel three-dimensional model from the diseased vessel segment portion;
processing the first dimension norgram according to the healthy vessel model, extracting a second dimension norgram representing the cavity of the target aneurysm, and constructing a first tumor cavity model of the target aneurysm according to the second dimension norgram;
calculating according to the central lines of the first tumor cavity model and the healthy blood vessel model to obtain a direction axis of the aneurysm, and determining a tumor neck plane of the aneurysm through a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes;
cutting the first tumor cavity model by utilizing the tumor neck plane, and extracting the maximum connected domain as a second tumor cavity model;
and calculating the morphological parameters of the aneurysm according to the second tumor cavity model and the tumor neck plane so as to obtain the morphological parameters of the target aneurysm.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring a blood vessel image related to a target aneurysm, and constructing a corresponding blood vessel three-dimensional model according to the blood vessel image;
Generating a first dimension norgram according to the blood vessel three-dimensional model, and determining a lesion blood vessel segment part in the blood vessel three-dimensional model through a blood vessel central line;
reconstructing an aneurysm-free healthy vessel model in the vessel three-dimensional model from the diseased vessel segment portion;
processing the first dimension norgram according to the healthy vessel model, extracting a second dimension norgram representing the cavity of the target aneurysm, and constructing a first tumor cavity model of the target aneurysm according to the second dimension norgram;
calculating according to the central lines of the first tumor cavity model and the healthy blood vessel model to obtain a direction axis of the aneurysm, and determining a tumor neck plane of the aneurysm through a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes;
cutting the first tumor cavity model by utilizing the tumor neck plane, and extracting the maximum connected domain as a second tumor cavity model;
and calculating the morphological parameters of the aneurysm according to the second tumor cavity model and the tumor neck plane so as to obtain the morphological parameters of the target aneurysm.
According to the method, the device, the equipment and the storage medium for automatically acquiring the aneurysm morphology parameters, the corresponding vascular three-dimensional model is constructed according to the acquired vascular images, the corresponding first dimension norgram is generated, the healthy vascular model without the aneurysm is partially reconstructed in the vascular three-dimensional model through determining the lesion vascular segment, the second dimension norgram representing the target aneurysm cavity is extracted from the first dimension norgram according to the healthy vascular model, the first aneurysm cavity model of the target aneurysm is constructed, the calculation is carried out according to the first aneurysm cavity model and the central line of the healthy vascular model, the direction axis of the aneurysm is obtained, the aneurysm neck plane of the aneurysm is determined according to the planes generated on the direction axis and normal vectors corresponding to the planes, the first aneurysm cavity model is cut by the aneurysm neck plane to obtain the second aneurysm cavity model, and finally the calculation of the aneurysm morphology parameters is carried out according to the second aneurysm cavity model and the aneurysm neck plane, so that the morphology parameters of the target aneurysm are acquired. By adopting the method, on one hand, the repeatability of morphological parameter calculation is improved, and on the other hand, the accuracy and efficiency of obtaining the morphological parameters of the aneurysm are improved.
Drawings
FIG. 1 is a flow chart of an automatic acquisition method of morphological parameters of an aneurysm in one embodiment;
FIG. 2 is a schematic diagram of a first dimension of a North graph and a three-dimensional model of a blood vessel in one embodiment;
FIG. 3 is a schematic illustration of various centerlines, bifurcation points, and lesion vessel segment endpoints in a three-dimensional model of a vessel in one embodiment;
FIG. 4 is a schematic diagram of a healthy blood vessel model, a second dimension of the norgram, and a first tumor cavity model according to one embodiment, wherein FIG. (a) is a schematic diagram of the healthy blood vessel model and the second dimension of the norgram, and FIG. (b) is a schematic diagram of the first tumor cavity model;
FIG. 5 is a schematic illustration of the first tumor cavity model with the axes of orientation and the equidistant lines in one embodiment;
FIG. 6 is a schematic illustration of the effect of dividing the neck of an aneurysm in one embodiment;
FIG. 7 is a block diagram of an apparatus for automatically acquiring morphological parameters of an aneurysm according to one embodiment;
fig. 8 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Aiming at the problems that in the prior art, the morphological evaluation of the aneurysm is mainly based on manual measurement of two-dimensional images, the measurement results often have errors, and when different people perform measurement, the measurement results also have differences, so that the manual measurement means have low accuracy and low repeatability, as shown in fig. 1, the automatic acquisition method of the morphological parameters of the aneurysm is provided, and comprises the following steps:
step S100, acquiring a blood vessel image related to a target aneurysm, and constructing a corresponding blood vessel three-dimensional model according to the blood vessel image;
step S110, generating a first dimension norgram according to the three-dimensional vascular model, and determining a lesion vascular segment part in the first dimension norgram through a vascular central line;
step S120, reconstructing a healthy blood vessel model without an aneurysm in the first dimension norgram according to the lesion blood vessel segment part;
step S130, processing the first dimension norgram according to the healthy vessel model, extracting a second dimension norgram representing the cavity of the target aneurysm, and constructing a first tumor cavity model of the target aneurysm according to the second dimension norgram;
step S140, calculating according to the central lines of the first tumor cavity model and the healthy blood vessel model to obtain a direction axis of the aneurysm, and determining a tumor neck plane of the aneurysm through a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes;
Step S150, cutting the first tumor cavity model by utilizing a tumor neck plane, and extracting a maximum connected domain as a second tumor cavity model;
step S160, calculating the morphological parameters of the aneurysm according to the second tumor cavity model and the tumor neck plane so as to obtain the morphological parameters of the target aneurysm.
In this embodiment, an aneurysm model is reconstructed based on the medical image, then a tumor neck plane is automatically determined in the aneurysm model, and finally morphological parameters of the aneurysm are automatically obtained by using an algorithm. The method further improves the automation degree of the whole process of obtaining the morphological parameters of the aneurysm, improves the accuracy and efficiency of obtaining the morphological parameters, and improves the repeatability of morphological evaluation of the aneurysm.
In step S100, a vessel image associated with the target aneurysm is acquired as a three-dimensional image sequence including, but not limited to, DSA (digital subtraction angiography), CTA (CT angiography), and MRA (magnetic resonance angiography). When a three-dimensional model (blood vessel model) of the blood vessel is constructed according to the blood vessel image, a threshold method, a level set method or an artificial intelligence technology segmentation model (such as 3D UNet) can be adopted to segment the three-dimensional image sequence, and then a cube algorithm is adopted to reconstruct the surface of the blood vessel in a memory manner, so that the three-dimensional model of the blood vessel is obtained. Wherein the vessel model includes a portion of the target aneurysm.
Further, in step S110, a corresponding voronoi diagram is calculated from the three-dimensional model of blood vessels and is denoted as a first dimensional noro (voronoi) diagram, as shown in fig. 2. The first dimension northbound chart comprises a Thiessen polygon vertex set corresponding to the blood vessel model and radius data of inscribed spheres to which each vertex belongs.
In this embodiment, determining a lesion vessel segment portion by a vessel centerline in a three-dimensional model of a vessel includes: a first centerline connecting the vessel inlet and the vessel outlet, a second centerline connecting the vessel inlet and the apex of the aneurysm, and a third centerline connecting the vessel outlet and the apex of the aneurysm are obtained in a three-dimensional model of the vessel, as shown in fig. 3. Meanwhile, a maximum inscribed sphere radius sequence of the blood vessel along the line taking each point on each central line as a central point is obtained and is respectively a first radius sequence, a second radius sequence and a third radius sequence. The distances between each point on the second center line and the third center line and the nearest point on the first center line are calculated to determine a first branch point B1 and a second branch point B2 on the first center line. And then respectively taking the first bifurcation point B1 and the second bifurcation point B2 as starting points, and moving a preset distance on the first central line towards the direction of the blood vessel inlet and the direction of the blood vessel outlet to obtain a first lesion blood vessel segment end point L1 and a second lesion blood vessel segment end point L2. The diseased vessel segment portion is a portion between the first diseased vessel segment end point L1 and the second diseased vessel segment end point L2 in the vessel three-dimensional model.
Specifically, before each central line of the three-dimensional model of the blood vessel is acquired, the position of the blood vessel inlet, the position of the blood vessel outlet and the position of the aneurysm vertex on the three-dimensional model of the blood vessel are needed to be determined by means or calculated by adopting a related algorithm.
Next, the bifurcation point is determined by calculating the distance between the first centerline and the corresponding point between the second centerline and the third centerline, respectively, and the distance between each point on the first centerline and the nearest point on the second centerline is calculated by traversing the vascular three-dimensional model from the vascular inlet, and when the distance is greater than the preset threshold, the corresponding point is the first bifurcation point B1. And simultaneously, traversing from the vascular outlet to calculate the distance between each point on the first central line and the nearest point on the third central line, and when the distance is larger than a preset threshold value, taking the corresponding point as a second bifurcation point B2.
In the present embodiment, the threshold value for judging the bifurcation point may be set to 0.01mm.
In another embodiment, another method of determining the bifurcation point is used. The points between the first central line and the second central line from the vascular inlet to the bifurcation point are coincident, the points on the first central line and the second central line are traversed from the vascular inlet at the same time, two three-dimensional coordinates can be obtained each time, the distance between the two three-dimensional coordinates is calculated, and when the distance is larger than a preset threshold value, the corresponding point is the first bifurcation point B1. Likewise, a point on the first centerline and the third centerline is traversed simultaneously from the vessel outlet, resulting in a second bifurcation point B2.
Further, the maximum inscribed sphere radii R1, R2 at the first branch point B1 and the second branch point B2 are extracted. At the first branch point B1, the linear distance D1 is moved in the inlet direction along the first center line, obtaining a first lesion vessel segment end point L1. Wherein D1 is equal to n1 times R1. Similarly, at the second branch point B2, the linear distance D2 is moved along the first center line toward the outlet direction, obtaining the second lesion vessel segment end point L2. Wherein D2 is equal to n2 times R2.
In this embodiment, n1 and n2 are natural numbers greater than 0, and in one embodiment, n1 and n2 are equal to 1.
In step S120, after determining a diseased vessel segment, i.e., a target aneurysm vessel segment, on the vessel model by the first and second diseased vessel segment endpoints, reconstructing an aneurysm-free healthy vessel model in the vessel three-dimensional model from the portion, comprising: and removing the part between the first lesion vessel segment end point L1 and the second lesion vessel segment end point L2 on the first central line, and interpolating and complementing the removed part by using a spline curve to obtain a fourth central line. And simultaneously removing data between the endpoints of the corresponding first lesion blood vessel segment and the endpoint of the second lesion blood vessel segment in the first radius sequence, and interpolating and complementing the removed part to obtain a fourth radius sequence. And finally, reconstructing according to a fourth central line and a fourth radius sequence to obtain the healthy blood vessel model without the aneurysm, wherein the fourth central line is the central line of the healthy blood vessel model.
In step S130, the first dimension of the norgram is processed according to the healthy vessel model, and a second dimension of the norgram representing the lumen of the target aneurysm is extracted, as shown in fig. 4 (a), comprising: the first dimension northlasso polygon vertex set corresponding to the three-dimensional blood vessel model and the radius of the inscribed sphere to which each vertex belongs are adopted, each Thlasso polygon vertex in the first dimension northlasso polygon is judged according to the healthy blood vessel model by utilizing a ray method, and a second dimension northlasso polygon is constructed according to the Thlasso polygons to which all vertices positioned outside the healthy blood vessel model are judged to belong.
Further, the vertex in the second dimension of the nuo-graph and the corresponding inscribed sphere radius are then reconstructed to obtain a first tumor cavity model representing the target aneurysm, as shown in fig. 4 (b).
Then, in the prior art, the tumor neck plane needs to be defined by a manual scribing method, and the definition method still has deviation among different operators, so that the image is used for evaluating the rupture risk of the aneurysm.
Specifically, in step S140, a direction axis of the aneurysm is obtained by performing calculation according to the center lines of the first tumor cavity model and the healthy blood vessel model, and then a tumor neck plane of the aneurysm is determined by a plurality of planes generated by points on the direction axis and normal vectors corresponding to the planes.
The process of obtaining the direction axis of the aneurysm specifically comprises the following steps: and calculating the distance between each point on the first tumor cavity model and the fourth central line, and classifying the points on the first tumor cavity model into multiple classes according to the obtained distance. And then, connecting each class of points by using a shortest path algorithm, correspondingly forming a plurality of circles of equidistant lines on the tumor cavity wall on the first tumor cavity model, calculating the geometric center coordinates of each circle of equidistant lines, and interpolating all geometric center coordinates by using a cubic spline curve to obtain the direction axis of the aneurysm, as shown in fig. 5.
In particular, the closer to the tumor neck the tumor cavity wall is, the smaller the distance between the equidistant lines is, and conversely, the larger is. The distance spacing of the equidistant lines is a natural number greater than 0, in this example the spacing of the equidistant lines is 0.1mm.
Next, determining a neck plane of the aneurysm from the plurality of planes generated at points on the direction axis and normal vectors corresponding to the planes, specifically including: the end point on the direction axis near the fourth center line is taken as a proximal end point, and the end point far from the fourth center line is taken as a distal end point. And the near end point is taken as a first point of the direction axis, and meanwhile, other points on the direction axis are sequentially marked as a second point of the direction axis and a third point of the direction axis according to the distance from the first point of the direction axis until the far end point is reached, namely, the points on the direction axis are ordered according to the distance from the near end point.
And generating a first plane by using a first point of the direction axis and a tangential vector corresponding to the first point, wherein the first plane passes through the first point of the direction axis, and the tangential vector corresponding to the first point is taken as a plane normal vector, and the plane normal vector is taken as a first normal vector. And then, deflecting the first normal vector by a preset angle in any direction to obtain a second normal vector, passing through a first point of the direction axis, and taking the second normal vector as a plane normal to obtain a second plane. And rotating the second normal vector around the first normal vector by a certain angle to obtain a third normal vector and a third plane.
And continuing to rotate the third normal vector around the first normal vector, and so on until the third normal vector rotates for one circle, finally obtaining N normal vectors and N planes, and obtaining a plurality of planes and normal vectors corresponding to the planes. Each time the normal vectors are deflected, the deflection angle is not uniform, for example, the deflection angle of the first normal vector in any direction can be 30 degrees, and the deflection angle of the second normal vector in a certain angle around the first normal vector can be 10 degrees.
And then, calculating the intersection line of each plane and the first tumor cavity model, and if a closed curve exists in a plurality of intersection lines, selecting the plane corresponding to the smallest curve surrounding area in the closed curve as the tumor neck plane of the aneurysm.
If the closed curve does not exist in the intersecting lines, selecting a second point of the direction axis, repeating the steps to generate a plurality of planes and normal vectors corresponding to the planes, and similarly calculating the intersecting lines of each plane and the first tumor cavity model until the closed curve is obtained and the plane corresponding to the smallest surrounding area is taken as the tumor neck plane.
In step S140, the first tumor cavity is cut by using the tumor neck plane, and the maximum connected domain is extracted as the second tumor cavity, as shown in fig. 6.
In step S150, finally, using the tumor neck plane and the second tumor cavity, the aneurysm morphology parameters are calculated, including: aneurysm inflow angle, aneurysm inclination angle, vessel angle, aneurysm maximum height, aneurysm middle diameter, aneurysm neck diameter, parent artery diameter, aneurysm vertical height, aneurysm surface area, aneurysm volume, size ratio, aspect ratio, patent-neg ratio, ellipse index, aspheric index, aneurysm morphology irregularity index, etc.
In the method for automatically acquiring the morphological parameters of the aneurysm, the calculation graphics algorithm is utilized to automatically divide the tumor neck plane, so that the repeatability of the morphological parameter calculation is improved. Meanwhile, the learning threshold and the workload of the morphological evaluation of the aneurysm are reduced. By adopting the method, the obtained aneurysm morphological parameters are more accurate, so that the subsequent judgment result is more reliable, and the risk of aneurysm rupture and the risk of excessive intervention are reduced to a certain extent.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of other steps or sub-steps of other steps.
In one embodiment, as shown in fig. 7, there is provided an apparatus for automatically acquiring morphological parameters of an aneurysm, comprising: a blood vessel three-dimensional model construction module 200, a lesion blood vessel segment part determination module 210, a healthy blood vessel model construction module 220, a first tumor cavity model construction module 230, a tumor neck plane obtaining module 240, a second tumor cavity model obtaining module 250 and a morphological parameter automatic obtaining module 260, wherein:
The blood vessel three-dimensional model construction module 200 is used for acquiring a blood vessel image related to the target aneurysm and constructing a corresponding blood vessel three-dimensional model according to the blood vessel image;
a lesion vessel segment part determination module 210 for generating a first dimension norgram from the vessel three-dimensional model in which a lesion vessel segment part is determined by a vessel centerline;
a healthy vessel model construction module 220 for reconstructing an aneurysm-free healthy vessel model in the vessel three-dimensional model from the diseased vessel segment portion;
a first tumor cavity model building module 230, configured to process a first dimension of the norgram according to the healthy vessel model, extract a second dimension of the norgram representing the target aneurysm cavity, and build a first tumor cavity model of the target aneurysm according to the second dimension of the norgram;
the tumor neck plane obtaining module 240 is configured to obtain a direction axis of the aneurysm according to the first tumor cavity model and the center line of the healthy blood vessel model, and determine a tumor neck plane of the aneurysm by using a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes;
the second tumor cavity model obtaining module 250 is configured to cut the first tumor cavity model by using the tumor neck plane, and extract the maximum connected domain as the second tumor cavity model;
The automatic morphological parameter obtaining module 260 is configured to perform calculation of morphological parameters of the aneurysm according to the second tumor cavity model and the tumor neck plane, so as to obtain morphological parameters of the target aneurysm.
For specific limitations on the automatic obtaining device for the morphological parameters of the aneurysm, reference may be made to the above limitation on the automatic obtaining method for the morphological parameters of the aneurysm, and no further description is given here. The modules in the automatic aneurysm morphology parameter acquisition device can be all or partially realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method for automatically acquiring morphological parameters of an aneurysm. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 8 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring a blood vessel image related to a target aneurysm, and constructing a corresponding blood vessel three-dimensional model according to the blood vessel image;
generating a first dimension norgram according to the blood vessel three-dimensional model, and determining a lesion blood vessel segment part in the blood vessel three-dimensional model through a blood vessel central line;
reconstructing an aneurysm-free healthy vessel model in the vessel three-dimensional model from the diseased vessel segment portion;
processing the first dimension norgram according to the healthy vessel model, extracting a second dimension norgram representing the cavity of the target aneurysm, and constructing a first tumor cavity model of the target aneurysm according to the second dimension norgram;
Calculating according to the central lines of the first tumor cavity model and the healthy blood vessel model to obtain a direction axis of the aneurysm, and determining a tumor neck plane of the aneurysm through a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes;
cutting the first tumor cavity model by utilizing the tumor neck plane, and extracting the maximum connected domain as a second tumor cavity model;
and calculating the morphological parameters of the aneurysm according to the second tumor cavity model and the tumor neck plane so as to obtain the morphological parameters of the target aneurysm.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a blood vessel image related to a target aneurysm, and constructing a corresponding blood vessel three-dimensional model according to the blood vessel image;
generating a first dimension norgram according to the blood vessel three-dimensional model, and determining a lesion blood vessel segment part in the blood vessel three-dimensional model through a blood vessel central line;
reconstructing an aneurysm-free healthy vessel model in the vessel three-dimensional model from the diseased vessel segment portion;
processing the first dimension norgram according to the healthy vessel model, extracting a second dimension norgram representing the cavity of the target aneurysm, and constructing a first tumor cavity model of the target aneurysm according to the second dimension norgram;
Calculating according to the central lines of the first tumor cavity model and the healthy blood vessel model to obtain a direction axis of the aneurysm, and determining a tumor neck plane of the aneurysm through a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes;
cutting the first tumor cavity model by utilizing the tumor neck plane, and extracting the maximum connected domain as a second tumor cavity model;
and calculating the morphological parameters of the aneurysm according to the second tumor cavity model and the tumor neck plane so as to obtain the morphological parameters of the target aneurysm.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (8)
1. An automatic acquisition method for morphological parameters of an aneurysm, comprising:
acquiring a blood vessel image related to a target aneurysm, and constructing a corresponding blood vessel three-dimensional model according to the blood vessel image;
generating a first dimension norgram from the three-dimensional model of the vessel, determining a lesion vessel segment portion in the three-dimensional model of the vessel through a vessel centerline, comprising: acquiring a first central line connecting a blood vessel inlet and a blood vessel outlet, a second central line connecting the blood vessel inlet and the top of the aneurysm, and a third central line connecting the blood vessel outlet and the top of the aneurysm from the three-dimensional model of the blood vessel, determining a first bifurcation point and a second bifurcation point on the first central line by calculating the distance between each point on the second central line and the third central line and the nearest point on the first central line respectively, taking the first bifurcation point and the second bifurcation point as starting points respectively, moving preset distances on the first central line towards the blood vessel inlet direction and the blood vessel outlet direction, obtaining a first lesion blood vessel segment end point and a second lesion blood vessel segment end point, and determining the lesion blood vessel segment part according to the part between the two lesion blood vessel segment end points;
Reconstructing an aneurysm-free healthy vessel model in the vessel three-dimensional model from the diseased vessel segment portion, comprising: removing the lesion vessel segment part on the first central line, interpolating and complementing the removed part by using a spline curve to obtain a fourth central line, removing data between a corresponding first lesion vessel segment end point and a corresponding second lesion vessel segment end point in a first radius sequence corresponding to the first central line, interpolating and complementing the removed part to obtain a fourth radius sequence, and reconstructing according to the fourth central line and the fourth radius sequence to obtain the healthy vessel model without aneurysm;
processing the first dimension norgram according to the healthy vessel model, extracting a second dimension norgram representing the cavity of the target aneurysm, and constructing a first tumor cavity model of the target aneurysm according to the second dimension norgram;
calculating according to the central lines of the first tumor cavity model and the healthy blood vessel model to obtain a direction axis of the aneurysm, and determining a tumor neck plane of the aneurysm through a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes, wherein the method comprises the following steps: taking an endpoint, which is close to the fourth central line, on the direction axis as a near endpoint, taking an endpoint, which is far away from the fourth central line, as a far endpoint, taking the near endpoint as a direction axis first point, simultaneously, taking other points on the direction axis as a direction axis second point and a direction axis third point according to the near and far distances from the direction axis first point in sequence, until the far endpoint, generating a first plane by taking the direction axis first point and a tangential vector corresponding to the point, taking the tangential vector corresponding to the point as a first normal vector, carrying out deflection of any direction preset angle on the first normal vector to obtain a second normal vector, taking the second normal vector as a plane normal to obtain a second plane, and rotating the second normal vector by one circle around the direction axis first point to obtain a plurality of planes and normal vectors corresponding to each plane, calculating intersection lines of each plane and a first aneurysm cavity model, if a closed curve exists in the plurality of intersection lines, selecting a plane corresponding to a small-area enclosing the closed curve as a first normal vector, selecting a plurality of planes not corresponding to the neck aneurysm, and generating a plurality of normal vectors until the neck aneurysm exists in the closed curve;
Cutting the first tumor cavity model by utilizing the tumor neck plane, and extracting the maximum connected domain as a second tumor cavity model;
and calculating the morphological parameters of the aneurysm according to the second tumor cavity model and the tumor neck plane so as to obtain the morphological parameters of the target aneurysm.
2. The method of claim 1, wherein determining a lesion vessel segment portion through a vessel centerline in the three-dimensional model of the vessel further comprises:
the method comprises the steps of obtaining a maximum inscribed sphere radius sequence along a blood vessel line by taking each point on each central line as a central point, wherein the maximum inscribed sphere radius sequence is a first radius sequence, a second radius sequence and a third radius sequence respectively.
3. The method of claim 2, wherein calculating the distance between each of the second and third centerlines and a closest point on the first centerline to determine the first and second bifurcation points on the first centerline comprises:
traversing from the vascular inlet to calculate the distance between each point on the first central line and the nearest point on the second central line, and when the distance is larger than a preset threshold value, taking the corresponding point as the first bifurcation point;
And traversing from the vascular outlet to calculate the distance between each point on the first central line and the nearest point on the third central line, and when the distance is larger than a preset threshold value, taking the corresponding point as the second bifurcation point.
4. The method of claim 3, wherein the processing the first dimension of the norgram according to the healthy vessel model to extract a second dimension of the norgram representing the lumen of the target aneurysm comprises:
the first dimension Nor graph comprises a Thiessen polygon vertex set corresponding to the blood vessel three-dimensional model, and the radius of an inscribed sphere to which each vertex belongs;
and judging each Thiessen polygon vertex in the first dimension North chart according to the healthy blood vessel by using a ray method, and constructing the second dimension North chart according to Thiessen polygons to which all vertices positioned outside the healthy blood vessel model belong.
5. The method according to claim 4, wherein calculating the direction axis of the aneurysm according to the center lines of the first tumor cavity model and the healthy blood vessel model comprises:
calculating the distance between each point on the first tumor cavity model and a fourth central line, and classifying the points on the first tumor cavity model into multiple classes according to the obtained distance;
Connecting each type of points by utilizing a shortest path algorithm, and correspondingly forming a plurality of circles of equidistant lines on the tumor cavity wall on the first tumor cavity model;
calculating the geometric center coordinates of each circle of equidistant lines, and interpolating all the geometric center coordinates by using a cubic spline curve to obtain the direction axis of the aneurysm.
6. An apparatus for automatically acquiring morphological parameters of an aneurysm, the apparatus comprising:
the blood vessel three-dimensional model construction module is used for acquiring a blood vessel image related to the target aneurysm and constructing a corresponding blood vessel three-dimensional model according to the blood vessel image;
a lesion vessel segment portion determining module for generating a first dimension norgram from the vessel three-dimensional model in which a lesion vessel segment portion is determined by a vessel centerline, comprising: acquiring a first central line connecting a blood vessel inlet and a blood vessel outlet, a second central line connecting the blood vessel inlet and the top of the aneurysm, and a third central line connecting the blood vessel outlet and the top of the aneurysm from the three-dimensional model of the blood vessel, determining a first bifurcation point and a second bifurcation point on the first central line by calculating the distance between each point on the second central line and the third central line and the nearest point on the first central line respectively, taking the first bifurcation point and the second bifurcation point as starting points respectively, moving preset distances on the first central line towards the blood vessel inlet direction and the blood vessel outlet direction, obtaining a first lesion blood vessel segment end point and a second lesion blood vessel segment end point, and determining the lesion blood vessel segment part according to the part between the two lesion blood vessel segment end points;
A healthy vessel model construction module for reconstructing an aneurysmal-free healthy vessel model in the vessel three-dimensional model from the diseased vessel segment portion, comprising: removing the lesion vessel segment part on the first central line, interpolating and complementing the removed part by using a spline curve to obtain a fourth central line, removing data between a corresponding first lesion vessel segment end point and a corresponding second lesion vessel segment end point in a first radius sequence corresponding to the first central line, interpolating and complementing the removed part to obtain a fourth radius sequence, and reconstructing according to the fourth central line and the fourth radius sequence to obtain the healthy vessel model without aneurysm;
the first tumor cavity model construction module is used for processing the first dimension norgram according to the healthy blood vessel model, extracting a second dimension norgram representing the target aneurysm cavity, and constructing a first tumor cavity model of the target aneurysm according to the second dimension norgram;
the tumor neck plane obtaining module is configured to obtain a direction axis of the aneurysm according to the first tumor cavity model and a center line of the healthy blood vessel model, and determine a tumor neck plane of the aneurysm by using a plurality of planes generated according to points on the direction axis and normal vectors corresponding to the planes, where the normal vectors include: taking an endpoint, which is close to the fourth central line, on the direction axis as a near endpoint, taking an endpoint, which is far away from the fourth central line, as a far endpoint, taking the near endpoint as a direction axis first point, simultaneously, taking other points on the direction axis as a direction axis second point and a direction axis third point according to the near and far distances from the direction axis first point in sequence, until the far endpoint, generating a first plane by taking the direction axis first point and a tangential vector corresponding to the point, taking the tangential vector corresponding to the point as a first normal vector, carrying out deflection of any direction preset angle on the first normal vector to obtain a second normal vector, taking the second normal vector as a plane normal to obtain a second plane, and rotating the second normal vector by one circle around the direction axis first point to obtain a plurality of planes and normal vectors corresponding to each plane, calculating intersection lines of each plane and a first aneurysm cavity model, if a closed curve exists in the plurality of intersection lines, selecting a plane corresponding to a small-area enclosing the closed curve as a first normal vector, selecting a plurality of planes not corresponding to the neck aneurysm, and generating a plurality of normal vectors until the neck aneurysm exists in the closed curve;
The second tumor cavity model obtaining module is used for cutting the first tumor cavity model by utilizing the tumor neck plane and extracting the maximum connected domain as a second tumor cavity model;
and the morphological parameter automatic acquisition module is used for calculating the morphological parameters of the aneurysm according to the second tumor cavity model and the tumor neck plane so as to acquire the morphological parameters of the target aneurysm.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310752810.1A CN116485800B (en) | 2023-06-26 | 2023-06-26 | Automatic acquisition method, device, equipment and storage medium for morphological parameters of aneurysms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310752810.1A CN116485800B (en) | 2023-06-26 | 2023-06-26 | Automatic acquisition method, device, equipment and storage medium for morphological parameters of aneurysms |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116485800A CN116485800A (en) | 2023-07-25 |
| CN116485800B true CN116485800B (en) | 2023-09-08 |
Family
ID=87218185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310752810.1A Active CN116485800B (en) | 2023-06-26 | 2023-06-26 | Automatic acquisition method, device, equipment and storage medium for morphological parameters of aneurysms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116485800B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109907732A (en) * | 2019-04-09 | 2019-06-21 | 广州新脉科技有限公司 | A kind of appraisal procedure and system of rupture of intracranial aneurysm risk |
| CN115600053A (en) * | 2021-06-28 | 2023-01-13 | 华为技术有限公司（Cn） | Navigation method and related equipment |
| CN116309673A (en) * | 2022-12-30 | 2023-06-23 | 杭州脉流科技有限公司 | Method, computer device and readable storage medium for obtaining saccular aneurysm morphological parameters based on tumor neck curved surface |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060184066A1 (en) * | 2005-02-15 | 2006-08-17 | Baylor College Of Medicine | Method for aiding stent-assisted coiling of intracranial aneurysms by virtual parent artery reconstruction |
-
2023
- 2023-06-26 CN CN202310752810.1A patent/CN116485800B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109907732A (en) * | 2019-04-09 | 2019-06-21 | 广州新脉科技有限公司 | A kind of appraisal procedure and system of rupture of intracranial aneurysm risk |
| CN115600053A (en) * | 2021-06-28 | 2023-01-13 | 华为技术有限公司（Cn） | Navigation method and related equipment |
| CN116309673A (en) * | 2022-12-30 | 2023-06-23 | 杭州脉流科技有限公司 | Method, computer device and readable storage medium for obtaining saccular aneurysm morphological parameters based on tumor neck curved surface |
Non-Patent Citations (1)
| Title |
|---|
| 颈内-后交通动脉瘤破裂危险的形态学与血流动力学分析;吕楠;江澈;瞿米睿;Ajay K.Wakhloo;徐瑾瑜;于瀛;刘建民;黄清海;;第二军医大学学报(04);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116485800A (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200320697A1 (en) | Method, system, and device for lung lobe segmentation, model training, model construction and segmentation | |
| CN109493348B (en) | Method and system for measuring morphological parameters of intracranial aneurysm image | |
| Heckel et al. | Interactive 3D medical image segmentation with energy-minimizing implicit functions | |
| WO2020083374A1 (en) | Method and system for measuring morphological parameters of an intracranial aneurysm image | |
| US20150104090A1 (en) | Modification of a hollow organ representation | |
| CN116503395B (en) | Method, device and equipment for automatically obtaining morphological parameters aiming at wide-neck aneurysm | |
| CN112446866A (en) | Blood flow parameter calculation method, device, equipment and storage medium | |
| Gharleghi et al. | Deep learning for time averaged wall shear stress prediction in left main coronary bifurcations | |
| CN115965750B (en) | Vascular reconstruction method, vascular reconstruction device, vascular reconstruction computer device, and vascular reconstruction program | |
| US20210020304A1 (en) | Systems and methods for generating classifying and quantitative analysis reports of aneurysms from medical image data | |
| JP4411075B2 (en) | Branch selection method for probe alignment | |
| CN113180824B (en) | Shaping needle form simulation method and device for microcatheter shaping, computer equipment and storage medium | |
| CN116485800B (en) | Automatic acquisition method, device, equipment and storage medium for morphological parameters of aneurysms | |
| CN117036530B (en) | Cross-modal data-based coronary artery fractional flow reserve prediction method and device | |
| CN115953457B (en) | Method and computer device for recommending first spring ring | |
| US9135697B2 (en) | Method and system for determining a boundary surface network | |
| CN116524003B (en) | Method and device for obtaining morphological parameters of bifurcation aneurysm | |
| CN115760813A (en) | Screw channel generation method, device, equipment, medium and program product | |
| CN112001893B (en) | Calculation method, device and equipment of vascular parameters and storage medium | |
| CN114974596A (en) | Simulation method and device for intra-aneurysm turbulent flow device | |
| CN116503436B (en) | Method and device for automatically dividing aneurysm neck based on control points | |
| CN117438092B (en) | Intracranial aneurysm rupture risk prediction device, computer device, and storage medium | |
| CN116485803B (en) | Method and device for obtaining morphological parameters of aneurysms with complex shapes | |
| CN115546089A (en) | Medical image segmentation method, pathological image processing method, device and equipment | |
| CN115944389B (en) | Method and computer device for simulated implantation of spring coil |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |