CN114332043A - Collateral circulation measuring method, device, equipment and medium based on CT perfusion image - Google Patents
Collateral circulation measuring method, device, equipment and medium based on CT perfusion image Download PDFInfo
- Publication number
- CN114332043A CN114332043A CN202111664078.XA CN202111664078A CN114332043A CN 114332043 A CN114332043 A CN 114332043A CN 202111664078 A CN202111664078 A CN 202111664078A CN 114332043 A CN114332043 A CN 114332043A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- perfusion
- ischemic
- arterial
- brain
- 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.)
- Granted
Links
Images
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The method comprises the steps of firstly obtaining a Tmax map based on a CTP image, then determining an ischemic region according to the Tmax map, determining an arterial blood vessel mask region according to the signal intensity which is corresponding to a voxel and changes along with time, dividing a brain region based on the tMIP map to obtain a brain region division result, determining the brain region where the ischemic region is located based on the brain region division result, calculating the difference degree of arterial blood vessel volumes of the ischemic brain region and the contralateral brain region and the difference degree of the perfusion peak reaching time, and evaluating and measuring the collateral circulation based on the difference degree of the arterial blood vessel volumes and the difference degree of the perfusion peak reaching time. The method can obtain the evaluation result without depending on the experience of a doctor, and is objective and accurate. In addition, a measuring device, equipment and a storage medium for cerebral ischemia area collateral circulation based on CT perfusion images are also provided.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for collateral circulation measurement based on CT perfusion images.
Background
Ischemic stroke is a common disease which harms the health of people in China. In ischemic cerebrovascular disease, arterial occlusion results in a decrease in perfusion in the area of the occluded vessel supplying blood. If the blood flow perfusion is < 10ml/(100 g.min), the nerve cells will be irreversibly damaged within a few minutes. If only a fraction of Cerebral Blood Flow (CBF) is reduced, nerve cells will cease to function, but remain structurally intact, a potential tissue that is considered to be salvageable (ischemic penumbra), making them the target of thrombolytic therapy. The collateral circulation of brain refers to the condition that when the blood supply artery of brain is severely narrowed or blocked, blood bypasses the blocked part through other branch blood vessels and is sent to the far-side distribution area to reach the ischemic tissue, so that the ischemic area obtains different degrees of blood perfusion compensation.
CT perfusion imaging is different from dynamic scanning, continuous CT scanning is carried out on the layer of an interested region when a contrast agent is injected into a vein rapidly in a bolus mode, so that an interested region time-density curve is obtained, various perfusion parameter values are calculated by using different mathematical models, and therefore the change of local tissue blood flow perfusion volume can be reflected more effectively and quantitatively.
With the emergence of new acute revascularization techniques (particularly intravascular treatment techniques), there is an urgent need to establish individualized evaluation methods to guide clinical decisions and improve efficacy. In earlier studies it was known that good collateral circulation may increase the benefit of acute revascularization and reduce the risk of hemorrhagic transformation. Therefore, the comprehensive and accurate evaluation of the structure and function of the collateral circulation of the brain is one of the important preconditions and bases for the establishment of the personalized treatment scheme for the stroke, and therefore, the evaluation of the collateral circulation state of the patient is of great significance.
Disclosure of Invention
Based on this, the application provides a method, a device, a computer device and a storage medium for evaluating and measuring the collateral circulation accurately and quantitatively.
In order to achieve the above object, a first aspect of the present application provides a method for measuring collateral circulation based on CT perfusion images, comprising:
acquiring an actual CTP image, and calculating to obtain a perfusion parameter map according to the actual CTP image, wherein the perfusion parameter map comprises: tmax plot;
determining an arterial blood vessel mask according to the signal intensity which is corresponding to each voxel in the CTP image and changes along with time;
performing threshold segmentation on the Tmax map to determine an ischemic region;
dividing the brain area based on a tMIP map to obtain a brain area division result, wherein the tMIP map is obtained by projecting based on the CTP image;
determining an ischemic brain area according to the ischemic area and the brain area partition result;
calculating the arterial blood vessel volume of the ischemic brain area and the arterial blood vessel volume of a contralateral brain area, wherein the contralateral brain area refers to a healthy brain area which is in a symmetrical position with the ischemic brain area;
calculating the peak perfusion time of the ischemic brain region and the peak perfusion time of the contralateral brain region;
and evaluating and measuring the collateral circulation according to the difference degree of the arterial blood vessel volume of the ischemic brain area and the contralateral brain area and the difference degree of the peak perfusion time.
In order to achieve the above object, a second aspect of the present application provides a device for measuring collateral circulation of cerebral ischemic region based on CT perfusion image, comprising:
an obtaining module, configured to obtain an actual CTP image, and obtain a perfusion parameter map by calculation according to the actual CTP image, where the perfusion parameter map includes: tmax plot;
the blood vessel determining module is used for determining an arterial blood vessel mask according to the signal intensity which is changed along with the time and corresponds to each voxel in the CTP image;
an ischemia determining module, configured to perform threshold segmentation on the Tmax map to determine an ischemic region;
the brain area dividing module is used for dividing a brain area based on a tMIP (partial projection image) map to obtain a brain area dividing result, and the tMIP map is obtained by projecting based on the CTP image;
the brain area determining module is used for determining an ischemic brain area according to the ischemic area and the brain area partition result;
the first calculation module is used for calculating the arterial blood vessel volume of the ischemic brain area and the arterial blood vessel volume of a contralateral brain area, wherein the contralateral brain area is a healthy brain area which is in a symmetrical position with the ischemic brain area;
a second calculation module for calculating a peak perfusion time of the ischemic brain region and a peak perfusion time of the contralateral brain region;
and the evaluation module is used for evaluating and measuring the collateral circulation according to the difference degree of the arterial blood vessel volumes of the ischemic brain area and the contralateral brain area and the difference degree of the peak perfusion time.
In order to achieve the above object, a third aspect of the present application provides a device for measuring collateral circulation of cerebral ischemic regions based on CT perfusion images, comprising a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to execute the following steps:
acquiring an actual CTP image, and calculating to obtain a perfusion parameter map according to the actual CTP image, wherein the perfusion parameter map comprises: tmax plot;
determining an arterial blood vessel mask according to the signal intensity which is corresponding to each voxel in the CTP image and changes along with time;
performing threshold segmentation on the Tmax map to determine an ischemic region;
dividing the brain area based on a tMIP map to obtain a brain area division result, wherein the tMIP map is obtained by projecting based on the CTP image;
determining an ischemic brain area according to the ischemic area and the brain area partition result;
calculating the arterial blood vessel volume of the ischemic brain area and the arterial blood vessel volume of a contralateral brain area, wherein the contralateral brain area refers to a healthy brain area which is in a symmetrical position with the ischemic brain area;
calculating the peak perfusion time of the ischemic brain region and the peak perfusion time of the contralateral brain region;
and evaluating and measuring the collateral circulation according to the difference degree of the arterial blood vessel volume of the ischemic brain area and the contralateral brain area and the difference degree of the peak perfusion time.
To achieve the above object, a fourth aspect of the present application provides a computer-readable storage medium comprising: a computer program is stored which, when executed by a processor, causes the processor to perform the steps of:
acquiring an actual CTP image, and calculating to obtain a perfusion parameter map according to the actual CTP image, wherein the perfusion parameter map comprises: tmax plot;
determining an arterial blood vessel mask according to the signal intensity which is corresponding to each voxel in the CTP image and changes along with time;
performing threshold segmentation on the Tmax map to determine an ischemic region;
dividing the brain area based on a tMIP map to obtain a brain area division result, wherein the tMIP map is obtained by projecting based on the CTP image;
determining an ischemic brain area according to the ischemic area and the brain area partition result;
calculating the arterial blood vessel volume of the ischemic brain area and the arterial blood vessel volume of a contralateral brain area, wherein the contralateral brain area refers to a healthy brain area which is in a symmetrical position with the ischemic brain area;
calculating the peak perfusion time of the ischemic brain region and the peak perfusion time of the contralateral brain region;
and evaluating and measuring the collateral circulation according to the difference degree of the arterial blood vessel volume of the ischemic brain area and the contralateral brain area and the difference degree of the peak perfusion time.
According to the method, the device, the equipment and the storage medium for measuring the collateral circulation based on the CT perfusion image, firstly, a perfusion parameter map is obtained through calculation based on a CTP image, then, blood vessels are identified, arterial blood vessels are identified, then, an ischemic region is determined based on a Tmax map, then, a brain region where the ischemic region is located is determined, namely, an ischemic brain region is determined, further, the arterial blood vessel volume in the ischemic brain region, the arterial blood vessel volume in the contralateral brain region, the perfusion peak reaching time of the ischemic brain region and the contralateral brain region are calculated, and finally, the collateral circulation is evaluated and measured according to the difference degree of the arterial blood vessel volumes of the ischemic brain region and the contralateral brain region and the difference degree of the perfusion peak reaching time. According to the scheme, a reliable mode capable of accurately and quantitatively calculating the collateral circulation of the ischemic brain region is provided by evaluating and measuring the collateral circulation of the ischemic brain region according to the difference degree of the volumes of arterial blood vessels in the ischemic brain region and the contralateral brain region and the difference degree of the peak time of perfusion, the mode can obtain an evaluation result without depending on the experience of a doctor, and the method is objective and accurate.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
FIG. 1 is a flow chart of a method for measuring collateral circulation based on CT perfusion images in one embodiment;
FIG. 2 is a flow diagram of a method for arterial revascularization in one embodiment;
FIG. 3 is a flow diagram of a method for classifying a arteriole vessel in one embodiment;
FIG. 4 is a schematic diagram of a process for imaging a brain in one embodiment;
FIG. 5 is a block diagram of a measurement device for collateral circulation based on CT perfusion images according to an embodiment;
FIG. 6 is a block diagram of a measurement apparatus for collateral circulation based on CT perfusion images according to another embodiment;
FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It is noted that the terms "comprises," "comprising," and "having" and any variations thereof in the description and claims of this application and the drawings described above are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. In the claims, the description and the drawings of the specification of the present application, relational terms such as "first" and "second", and the like, may be used solely to distinguish one entity/action/object from another entity/action/object without necessarily requiring or implying any actual such relationship or order between such entities/actions/objects.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
As shown in fig. 1, a method for measuring collateral circulation based on CT perfusion image is proposed, which specifically includes the following steps:
102, acquiring an actual CTP image, and calculating to obtain a perfusion parameter map according to the actual CTP image, wherein the perfusion parameter map comprises: tmax plot.
The actual CTP image is CT perfusion scan image obtained by actual shooting, continuous CT scan is carried out when a contrast agent is rapidly injected into veins, and then the CT image is obtained by computer reconstruction. The perfusion parameter map includes: tmax plot, rCBF plot, rCBV plot and MTT plot, where Tmax represents peak time, rCBF represents relative cerebral blood flow, rCBV represents relative cerebral blood volume, and MTT represents mean transit time.
And step 104, determining an arterial blood vessel mask according to the signal intensity which is corresponding to each voxel in the CTP image and changes along with time.
Where a voxel is conceptually similar to a pixel, the difference is that a pixel is an element on a two-dimensional image, and a voxel is an element on a three-dimensional image. The CTP image is obtained by performing continuous CT scanning, so that the signal intensity corresponding to each voxel can be obtained along with time, and the blood vessel portion has a relatively high signal intensity due to the contrast agent inside, so that the position of the blood vessel can be determined by counting the magnitude of the signal intensity, and the blood vessel mask region can be determined. The blood vessel mask region is a detected blood vessel region. The peak arrival time of each voxel signal is obtained by counting the signal intensity of the voxels changing along with the time, a peak arrival time histogram is obtained, and then the blood vessels are divided into arterial blood vessels and venous blood vessels according to the peak arrival time distribution.
In step 106, the Tmax chart is subjected to threshold segmentation to determine an ischemic region.
The Tmax map is a peak reaching time map, a preset threshold is set, and when Tmax corresponding to a pixel in the Tmax map is greater than the preset threshold (for example, 6), the area is determined as an ischemic area, so as to obtain an ischemic area mask.
In one embodiment, a region of the Tmax graph with the peak reaching time larger than a preset threshold value is obtained, and an initial ischemic region mask is determined according to the region with the peak reaching time larger than the preset threshold value; and performing morphological operation on the initial ischemic area mask, and removing the area smaller than the preset volume to obtain a smooth ischemic area mask.
Specifically, Tmax is subjected to threshold segmentation (ischemic region definition Tmax >6), and an initial ischemic region mask is obtained. The initial mask is then morphologically manipulated to obtain a relatively smooth surface of the ischemic body, and finally the suspected ischemic focus is removed in a volume less than a predetermined volume (e.g., 3 ml).
In an embodiment, since different persons have different physical qualities, the corresponding peak-to-peak times are different, and in order to make the setting of the preset threshold more accurate, when determining the ischemic region, the preset threshold is set according to individual conditions, specifically, the peak-to-peak time (for example, the top 15%) of a voxel with a statistical ranking top may be determined, and the preset threshold corresponding to the ischemic region is determined according to the peak-to-peak time of the voxel with the ranking top.
And 108, dividing the brain area based on the tMIP map to obtain a brain area division result, wherein the tMIP map is obtained by projection based on the CTP image.
And the tMIP graph represents an instantaneous maximum density projection graph, the obtained tMIP graph is converted into a standard template, the standard template is used for dividing the brain area based on an ASPECTS rule, and then the brain area where each part in the tMIP graph is located after the tMIP graph is converted into the standard template is determined. When the tMIP is converted to the standard template, a mapping equation of the conversion is determined.
And step 110, determining an ischemic brain area according to the ischemic area and the brain area partition result.
And according to the obtained mapping equation, applying the mapping equation to the Tmax map to obtain the brain area of the ischemic area.
And step 112, calculating the arterial blood vessel volume of the ischemic brain area and the arterial blood vessel volume of the contralateral brain area, wherein the contralateral brain area is a healthy brain area which is in a symmetrical position with the ischemic brain area.
Wherein, under the condition of known arterial blood vessel mask, the arterial blood vessel volume in the ischemic brain area and the arterial blood vessel volume in the contralateral brain area are respectively determined, and the collateral circulation is evaluated according to the difference between the two.
Under the condition that an arterial blood vessel mask is known, the perfusion peak time of an ischemic brain area is calculated respectively, strictly speaking, the average perfusion peak time is calculated, the brain area comprises a plurality of voxels, each voxel should have the perfusion peak time, and the counting of the perfusion peak time corresponding to the brain area is equivalent to the counting of the average perfusion peak time of the voxels.
And step 116, evaluating and measuring the collateral circulation according to the difference degree of the arterial blood vessel volumes of the ischemic brain area and the contralateral brain area and the difference degree of the peak perfusion time.
Specifically, the difference degree of the arterial vessel volume of the contralateral brain region and the ischemic brain region and the difference degree of the perfusion peak time are calculated, and the contralateral circulation is quantitatively evaluated according to the difference degrees of the contralateral brain region and the ischemic brain region. Specifically, the difference degree R of the arterial blood vessel volume is calculated by the following formula: r ═ Vc-Vp)/VcWherein V iscRepresenting the arterial vessel volume of the contralateral cerebral region, VpThe arterial vessel volume representing the ischemic region. Calculating the difference degree I of the peak reaching time by adopting the following formula: i ═ Tc-Tp)/TcWherein, TcRepresents the time to peak of perfusion, T, in the contralateral brain regionpIndicating the time to peak perfusion in the ischemic brain region. And presetting a scoring rule, setting a basic score according to the difference degree of the arterial vessel volume, and determining a final collateral circulation score according to the difference degree of the perfusion peak reaching time and the basic score. For example, assuming that the degree of difference in arterial vessel volume is within 10%, the base score is set to 8 points, and the smaller the degree of difference in perfusion peak time, the more the additional score, for example, when the degree of difference in perfusion peak time is also within 10%, the additional score is 1 point, and the base score is added to 8 points, and the final score is 9 points. When the difference in time to peak perfusion is not within 10%, the additional score is negative, and the greater the difference, the more the score is subtracted, e.g., -0.5 when the difference in time to peak perfusion is between 10% and 15%, and-1 when the difference in time to peak perfusion is between 15% and 20%, and so on. In addition, the larger the degree of difference in arterial blood vessel volume, the lower the basal score.
The method for measuring collateral circulation based on the CT perfusion image comprises the steps of firstly obtaining a perfusion parameter map based on CTP image calculation, then identifying blood vessels, identifying arterial blood vessels, then determining an ischemic region based on a Tmax map, then determining a brain region where the ischemic region is located, namely determining an ischemic brain region, further calculating arterial blood vessel volume in the ischemic brain region, arterial blood vessel volume in the contralateral brain region and perfusion peak reaching time of the ischemic brain region and the contralateral brain region, and finally evaluating and measuring collateral circulation according to the difference degree of the arterial blood vessel volume and the perfusion peak reaching time of the ischemic brain region and the contralateral brain region. According to the scheme, a reliable mode capable of accurately and quantitatively calculating the collateral circulation of the ischemic brain region is provided by evaluating and measuring the collateral circulation of the ischemic brain region according to the difference degree of the volumes of arterial blood vessels in the ischemic brain region and the contralateral brain region and the difference degree of the peak time of perfusion, the mode can obtain an evaluation result without depending on the experience of a doctor, and the method is objective and accurate.
In one embodiment, after determining the arterial blood vessel mask according to the corresponding time-varying signal intensity of each voxel in the CTP image, the method further comprises: and (4) reconstructing arterial blood vessels.
As shown in fig. 2, the reconstruction of the arterial vessel comprises the following steps:
and 105A, acquiring a signal intensity change curve corresponding to each target voxel in the arterial blood vessel mask.
The artery blood vessel mask determines the region where the artery blood vessel is located, and in order to further accurately calculate the volume of the artery blood vessel, the artery blood vessel needs to be reconstructed, and then volume calculation is performed based on the reconstructed artery blood vessel.
And 105B, generating a voxel characteristic vector corresponding to each target voxel based on the signal intensity change curve corresponding to each target voxel.
The signal intensity change curve of each target voxel is vectorized to generate a voxel characteristic vector of each target voxel.
And 105C, clustering the target voxels based on the voxel characteristic vectors to obtain a plurality of cluster clusters.
The clustering adopts unsupervised learning clustering, namely, the computer equipment automatically performs feature learning, and clusters voxels with similar features to obtain a plurality of clusters obtained by learning, and obtain feature information of each cluster.
And 105D, screening out target cluster clusters meeting artery characteristic conditions from the plurality of cluster clusters.
And respectively matching the characteristic information of each cluster with a preset artery characteristic condition, and if the characteristic information of each cluster is matched with the preset artery characteristic condition, indicating that the cluster is a cluster of artery vessels.
Wherein, the object cluster is composed of object artery voxels.
The target artery voxel is determined and then the artery vessel is reconstructed, so that more comprehensive artery vessel information can be acquired, and more accurate artery vessel volume can be calculated.
Calculating the arterial blood vessel volume of the ischemic brain area and the arterial blood vessel volume of the contralateral brain area, wherein the contralateral brain area refers to a healthy brain area which is in a symmetrical position with the ischemic brain area, and the method comprises the following steps: arterial vessel volume of the ischemic brain region and arterial vessel volume of the contralateral brain region were calculated based on the reconstructed arterial vessels.
In the embodiment, in order to calculate the arterial vessel volume for collateral circulation evaluation more accurately, after the arterial vessel region is segmented, a method for arterial vessel reconstruction based on the segmented arterial vessel is innovatively provided, specifically, a voxel characteristic vector corresponding to each target voxel is generated based on a signal intensity change curve, then clustering is performed to obtain a plurality of clustering clusters, a target clustering cluster meeting arterial vessel characteristics is selected from the plurality of clustering clusters, the target arterial voxel contained in the target clustering cluster is an accurate arterial voxel, and vessel reconstruction is performed based on the target arterial voxel, so that the accuracy of arterial vessel reconstruction is improved, the accuracy of subsequent arterial vessel volume calculation is improved, and the accuracy of collateral circulation evaluation is improved.
As shown in fig. 3, in one embodiment, the step 105F of reconstructing an arterial vessel based on the target arterial voxel further includes: and classifying the arteriolar vessels.
Classifying the arteriolar vessels comprises the steps of:
in step 302, the central axis of each arteriolar vessel is extracted from the reconstructed arterial vessel.
At step 304, the intersection of the central axes of the individual arteriolar vessels is determined.
Step 306, registering the reconstructed artery vessel to a standard artery vessel template based on the intersection point to obtain a standard classification corresponding to each arteriole vessel.
The artery blood vessels are subdivided for further accurately calculating the artery blood vessel volume, each arteriolar blood vessel is determined, after the arteriolar blood vessel is determined, the arteriolar blood vessels are required to be accurately classified, and the classification mode adopts an innovative and simple mode, and is favorable for more quickly and accurately classifying the arteriolar blood vessels by utilizing the characteristic of the intersection point of the central axes of the arteriolar blood vessels. Specifically, intersection points of all central axes are determined, a special shape is formed by a plurality of intersection points, the special shape is matched with a preset shape formed by all the intersection points on a standard artery blood vessel template based on the special shape, the special shape is registered on the standard artery blood vessel template, and standard classification of each arteriole blood vessel is obtained based on the registration result. By the method, each arteriolar vessel can be quickly and accurately registered, and the efficiency and the accuracy of arteriolar vessel classification are improved.
The calculating arterial vessel volume of the ischemic brain region and arterial vessel volume of a contralateral brain region based on the reconstructed arterial vessel comprises: respectively calculating each sub-artery blood vessel volume of the ischemic brain area and each sub-artery blood vessel volume of the contralateral brain area based on the standard classification corresponding to each sub-artery blood vessel; and acquiring preset weight of the volume of each sub-artery blood vessel, and respectively calculating the volume of the artery blood vessel of the ischemic brain area and the volume of the artery blood vessel of the contralateral brain area based on the preset weight.
In order to further accurately calculate the volume of the artery blood vessel, calculation is performed based on the classified artery blood vessels, the importance degrees of different artery blood vessels are different, corresponding weights are different, and the final artery blood vessel volume is calculated based on the preset weights, so that the evaluation of collateral circulation is more accurate.
As shown in fig. 4, a schematic process image in the embodiment of the present application includes: acquiring a CTP image, obtaining a perfusion parameter map based on the CTP image, segmenting and reconstructing blood vessels, determining an ischemic region, dividing a brain region, and finally performing collateral circulation evaluation.
In one embodiment, said determining an arterial vessel mask from the corresponding time-varying signal intensity of each voxel in said CTP image comprises: determining a blood vessel mask area according to the signal intensity which changes along with time and corresponds to each voxel; counting the signal peak reaching time corresponding to the target voxel in the blood vessel mask area to obtain a peak reaching time histogram; and dividing the blood vessel into an artery blood vessel and a vein blood vessel according to the peak-to-time histogram, and determining an artery blood vessel mask corresponding to the artery blood vessel.
Acquiring the time-varying signal intensity corresponding to each voxel, and integrating the time-varying signal intensity to obtain a signal intensity integral value corresponding to each voxel; determining a target voxel which accords with a preset rule according to the signal intensity integral value; determining the vessel mask region from the target voxel. The preset rule can set the 15% of the signal intensity integral value ranking as the target voxel, integrate the signal intensity of each voxel position, reserve the part 15% of the integral value, obtain the corresponding blood vessel mask, further count the peak arrival time of the partial voxel signal, obtain the peak arrival time histogram, and then divide the blood vessel into the artery blood vessel and the vein blood vessel according to the peak arrival time division.
In one embodiment, said obtaining an actual CTP image, calculating a perfusion parameter map from said actual CTP image comprises: inputting the perfusion parameter map obtained by calculation into a CTP image generation model to obtain a simulated CTP image output by the CTP image generation model; and comparing the actual CTP image with the simulated CTP image, and adjusting the perfusion parameter map when the comparison result exceeds a preset range to obtain the adjusted perfusion parameter map.
In order to enable the perfusion parameter map obtained through calculation to be more accurate, the perfusion parameter map obtained through initial calculation is used as a CTP image generation model, wherein the CTP image generation model is used for generating a simulated CTP image according to perfusion parameter simulation, and the CTP image generation model is obtained through deep neural network model training. Comparing the actual CTP image with the simulated CTP image, determining the similarity of the actual CTP image and the simulated CTP image, considering that the perfusion parameter map obtained by calculation is accurate when the similarity is more than 99%, and when the similarity is less than 99%, indicating that the perfusion parameter map obtained by calculation is not accurate enough, finely adjusting the perfusion parameter map based on the comparison result to obtain an adjusted perfusion parameter map, continuously using the adjusted perfusion parameter map as the input of a CTP image generation model until the obtained simulated CTP image meets the condition, and taking the final perfusion parameter map as the accurate perfusion parameter map.
In one embodiment, the evaluation of the collateral circulation based on the degree of difference in arterial vessel volume and the degree of difference in time to peak perfusion for the ischemic brain region and the contralateral brain region comprises: calculating the difference in arterial vessel volumes of the contralateral brain region and the ischemic brain region; calculating a difference in peak perfusion time between the contralateral brain region and the ischemic brain region; and calculating to obtain a score corresponding to collateral circulation according to the arterial blood vessel volume difference and the perfusion peak-to-peak time difference.
In one embodiment, the segmenting the brain region based on the tmap map to obtain the brain region segmentation result, the tmap map is projected based on the CTP image, and includes: projecting the CTP image to obtain a tMIP (partial projection maximum intensity projection) image, wherein the tMIP image is a maximum projection image along time; extracting a brain contour line based on the tMIP, and determining a longitude center line and a latitude center line based on the brain contour line; and registering the tMIP to a standard brain area template based on the intersection point of the longitude central line and the latitude central line to obtain the brain area division result.
Wherein, the CT perfusion image is divided into brain areas (referring to the brain areas according to the ASPECTS score). In order to more accurately divide the brain area, the method comprises the steps of extracting a brain contour line based on the tMIP, determining a longitude center line and a latitude center line according to the brain contour line, then determining the intersection point of the longitude center line and the latitude center line, and registering the tMIP to a standard brain area template based on the longitude center line, the latitude center line and the intersection point.
In one embodiment, acquiring an actual CTP image comprises: acquiring an original CT perfusion image, wherein the CT perfusion image is a dynamic image obtained by continuously and repeatedly performing layer scanning; respectively taking each image frame obtained by scanning for multiple times at the same position in an original CT perfusion image as a target frame, and determining the local scanning time difference between the target frame and a time adjacent frame corresponding to the same position aiming at each target frame; the time adjacent frame refers to an image frame obtained by scanning the same position at the adjacent scanning time of the target frame; according to the local scanning time difference, adaptively determining a time filtering convolution kernel parameter corresponding to the target frame; and performing smooth filtering processing on the target frame based on the time filtering convolution kernel parameters to obtain a processed CT perfusion image, and calculating a perfusion parameter map based on the processed CT perfusion image.
The temporally adjacent frames are image frames obtained by scanning the same position at scanning times adjacent to the scanning time of the target frame. The adjacent scan time, which refers to a scan time adjacent to the scan time of the target frame, may include a previous adjacent scan time (i.e., a scan time previous to the scan time of the target frame) and a next adjacent scan time (i.e., a scan time next to the scan time of the target frame). The time-adjacent frames are three-dimensional image frames scanned at the adjacent scanning time. The time adjacent frame of the target frame and the target frame belong to image frames obtained by scanning the same position at different times. It should be understood that all the "image frames" mentioned in the embodiments of the present application are three-dimensional image frames.
The local scanning time difference is the time difference between the scanning time of the target frame and the adjacent scanning time. The computer device can adaptively determine the time filtering convolution kernel parameter corresponding to the target frame according to the local scanning time difference. It can be understood that the temporal filtering convolution kernel parameter corresponding to the target frame is used to indicate the filtering weights corresponding to the temporally adjacent frames of the target frame, so that the magnitude of the local scanning time difference is inversely related to the filtering weights, that is, the larger the local scanning time difference between the temporally adjacent frame and the target frame is, the smaller the filtering influence is, and thus the filtering weight of the temporally adjacent frame is smaller, whereas the smaller the local scanning time difference is, the larger the filtering influence is, the larger the filtering weight of the temporally adjacent frame is. Therefore, the computer device can perform smoothing filtering processing on the target frame in the time dimension based on the time filtering convolution kernel parameters to obtain the CT perfusion image. It is to be understood that the smoothing filter process may be a gaussian filter process. In the above embodiment, the original CT perfusion image is subjected to a series of processing, so that the obtained CT perfusion image is more accurate, thereby facilitating the accuracy of subsequent collateral circulation evaluation.
In one embodiment, said obtaining an actual CTP image, calculating a perfusion parameter map from said CTP image, said perfusion parameter map comprising: a Tmax plot comprising: preprocessing an actual CTP image, wherein the preprocessing comprises the following steps: head motion correction, smooth denoising, skull removing operation and non-craniocerebral removing operation; and (4) performing deconvolution on the preprocessed CTP image to obtain the perfusion parameter map.
The perfusion parameter map corresponding to the brain CTP image is obtained, and the original image needs to be preprocessed, wherein the preprocessing comprises the operations of head motion correction, smooth denoising, skull removal and the like. Specifically, the cranial motion is first evaluated in the temporal direction, and the time frame with significant head motion is corrected to be in the same position as the other frames. The CTP signal is smoothly denoised by KMGB filtering (a filtering method suitable for CT perfusion images). Secondly, projecting images along a time axis to obtain tMIP (maximum projection image along time), removing skull and extracranial tissues on the basis of the tMIP to obtain a binary brain mask, and then performing Boolean operation on each frame of image by using the obtained mask to remove non-craniocerebral parts. Finally, each perfusion parameter map (Tmax, rCBF, rCBV, MTT) was calculated using deconvolution.
As shown in fig. 5, in one embodiment, a collateral circulation measuring apparatus based on CT perfusion image is provided, which includes:
an obtaining module 502, configured to obtain an actual CTP image, and obtain a perfusion parameter map by calculation according to the actual CTP image, where the perfusion parameter map includes: tmax plot;
a blood vessel determining module 504, configured to determine an arterial blood vessel mask according to the time-varying signal intensity corresponding to each voxel in the CTP image;
an ischemia determination module 506, configured to perform threshold segmentation on the Tmax map to determine an ischemic region;
a brain region dividing module 508, configured to divide a brain region based on a mip map obtained by projecting based on the CTP image to obtain a brain region dividing result;
a brain region determining module 510, configured to determine an ischemic brain region according to the ischemic region and the brain region partition result;
a first calculating module 512, configured to calculate an arterial blood vessel volume of the ischemic brain region and an arterial blood vessel volume of a contralateral brain region, where the contralateral brain region is a healthy brain region located symmetrically to the ischemic brain region;
a second calculation module 514 for calculating a time to peak perfusion for the ischemic brain region and a time to peak perfusion for the contralateral brain region;
and the evaluation module 516 is used for carrying out evaluation measurement on collateral circulation according to the difference degree of the arterial blood vessel volumes of the ischemic brain area and the contralateral brain area and the difference degree of the peak perfusion time.
As shown in fig. 6, in one embodiment, the apparatus further comprises:
a vessel reconstruction module 505, configured to obtain a signal intensity variation curve corresponding to each target voxel in an arterial vessel mask; generating a voxel characteristic vector corresponding to each target voxel based on the signal intensity change curve corresponding to each target voxel; clustering the target voxels based on the voxel characteristic vectors to obtain a plurality of clustering clusters; screening out a target cluster meeting an artery characteristic condition from the plurality of clusters; determining a target artery voxel from the target cluster; reconstructing an arterial vessel based on the target arterial voxel.
The first calculation module is further configured to calculate an arterial blood vessel volume of the ischemic brain region and an arterial blood vessel volume of a contralateral brain region based on the reconstructed arterial blood vessel.
In one embodiment, the vessel reconstruction module is further configured to extract a central axis of each arteriolar vessel from the reconstructed arterial vessel; determining the intersection point of the central axes of the sub-artery blood vessels; and registering the reconstructed artery vessel to a standard artery vessel template based on the intersection point to obtain a standard classification corresponding to each arteriole vessel.
The first calculation module is further used for calculating each arteriolar blood vessel volume of the ischemic brain region and each arteriolar blood vessel volume of the contralateral brain region respectively based on the standard classification corresponding to each arteriolar blood vessel; and acquiring preset weight of the volume of each sub-artery blood vessel, and respectively calculating the volume of the artery blood vessel of the ischemic brain area and the volume of the artery blood vessel of the contralateral brain area based on the preset weight.
In one embodiment, the vessel determining module is further configured to determine a vessel mask region according to the time-varying signal intensity corresponding to each voxel; counting the signal peak reaching time corresponding to the target voxel in the blood vessel mask area to obtain a peak reaching time histogram; and dividing the blood vessel into an artery blood vessel and a vein blood vessel according to the peak-to-time histogram, and determining an artery blood vessel mask corresponding to the artery blood vessel.
In one embodiment, the obtaining module is further configured to input the computed perfusion parameter map into a CTP image generation model, so as to obtain a simulated CTP image output by the CTP image generation model; and comparing the actual CTP image with the simulated CTP image, and adjusting the perfusion parameter map when the comparison result exceeds a preset range to obtain the adjusted perfusion parameter map.
In one embodiment, the evaluation module is further configured to calculate an arterial vessel volumetric difference between the contralateral brain region and the ischemic brain region; calculating a difference in peak perfusion time between the contralateral brain region and the ischemic brain region; and calculating to obtain a score corresponding to collateral circulation according to the arterial blood vessel volume difference and the perfusion peak-to-peak time difference.
In one embodiment, the dividing module is further configured to project the CTP image to obtain a tmap map, where the tmap map is a maximum projection map along time; extracting a brain contour line based on the tMIP, and determining a longitude center line and a latitude center line based on the brain contour line; determining an intersection of the longitude and latitude centerlines; and registering the tMIP to a standard brain area template based on the longitude central line, the latitude central line and the intersection point to obtain the brain area division result.
FIG. 7 is a diagram illustrating an internal structure of a computer device in one embodiment. The computer device may specifically be a server or a terminal. As shown in fig. 7, the computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the measuring device for the collateral circulation of the cerebral ischemic region based on the CT perfusion image is provided with a storage operating system and can also be provided with a storage computer program, and when the computer program is executed by a processor, the processor can realize the measuring method for the collateral circulation based on the CT perfusion image. The internal memory may also store a computer program that, when executed by the processor, causes the processor to perform the method for measuring collateral circulation based on CT perfusion images. Those skilled in the art will appreciate that the configuration shown in fig. 7 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation on the devices to which the present application may be applied, and that a particular device may include more or less components than those shown, or may combine certain 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 thereon a computer program which, when executed by the processor, causes the processor to carry out the steps of the above-described method for measuring a collateral circulation based on CT perfusion images.
In one embodiment, a computer-readable storage medium is provided, having a stored computer program which, when executed by a processor, causes the processor to perform the steps of the above-described method for measuring a collateral circulation based on CT perfusion images.
It is understood that the method and the apparatus for measuring collateral circulation based on CT perfusion images, the apparatus for measuring collateral circulation of cerebral ischemic region based on CT perfusion images, and the computer readable storage medium are all included in a general inventive concept, and the embodiments are applicable to each other.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile 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), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A collateral circulation measuring method based on CT perfusion images is characterized by comprising the following steps:
acquiring an actual CTP image, and calculating to obtain a perfusion parameter map according to the actual CTP image, wherein the perfusion parameter map comprises: tmax plot;
determining an arterial blood vessel mask according to the signal intensity which is corresponding to each voxel in the CTP image and changes along with time;
performing threshold segmentation on the Tmax map to determine an ischemic region;
dividing the brain area based on a tMIP map to obtain a brain area division result, wherein the tMIP map is obtained by projecting based on the CTP image;
determining an ischemic brain area according to the ischemic area and the brain area partition result;
calculating the arterial blood vessel volume of the ischemic brain area and the arterial blood vessel volume of a contralateral brain area, wherein the contralateral brain area refers to a healthy brain area which is in a symmetrical position with the ischemic brain area;
calculating the peak perfusion time of the ischemic brain region and the peak perfusion time of the contralateral brain region;
and evaluating and measuring the collateral circulation according to the difference degree of the arterial blood vessel volume of the ischemic brain area and the contralateral brain area and the difference degree of the peak perfusion time.
2. The method of claim 1, further comprising, after said determining an arterial vessel mask from the corresponding time-varying signal intensity of each voxel in said CTP image:
acquiring a signal intensity change curve corresponding to each target voxel in an arterial blood vessel mask;
generating a voxel characteristic vector corresponding to each target voxel based on the signal intensity change curve corresponding to each target voxel;
clustering the target voxels based on the voxel characteristic vectors to obtain a plurality of clustering clusters;
screening out a target cluster meeting an artery characteristic condition from the plurality of clusters;
determining a target artery voxel from the target cluster;
reconstructing an arterial vessel based on the target arterial voxel;
the calculating of the arterial blood vessel volume of the ischemic brain region and the arterial blood vessel volume of the contralateral brain region, wherein the contralateral brain region refers to a healthy brain region which is in a symmetrical position with the ischemic brain region, includes:
arterial vessel volume of the ischemic brain region and arterial vessel volume of the contralateral brain region are calculated based on the reconstructed arterial vessels.
3. The method of claim 2, wherein the reconstructing of the arterial vessel based on the target arterial voxel comprises:
extracting central axes of each arteriolar vessel from the reconstructed arterial vessel;
determining the intersection point of the central axes of the sub-artery blood vessels;
registering the reconstructed artery vessel to a standard artery vessel template based on the intersection point to obtain a standard classification corresponding to each arteriole vessel;
the calculating arterial vessel volume of the ischemic brain region and arterial vessel volume of a contralateral brain region based on the reconstructed arterial vessel comprises:
respectively calculating each sub-artery blood vessel volume of the ischemic brain area and each sub-artery blood vessel volume of the contralateral brain area based on the standard classification corresponding to each sub-artery blood vessel;
and acquiring preset weight of the volume of each sub-artery blood vessel, and respectively calculating the volume of the artery blood vessel of the ischemic brain area and the volume of the artery blood vessel of the contralateral brain area based on the preset weight.
4. The method of claim 1, wherein determining an arterial vessel mask region from the corresponding time-varying signal intensity for each voxel comprises:
determining a blood vessel mask area according to the signal intensity which changes along with time and corresponds to each voxel;
counting the signal peak reaching time corresponding to the target voxel in the blood vessel mask area to obtain a peak reaching time histogram;
and dividing the blood vessel into an artery blood vessel and a vein blood vessel according to the peak-to-time histogram, and determining an artery blood vessel mask corresponding to the artery blood vessel.
5. The method of claim 1, wherein said obtaining an actual CTP image from which a perfusion parameter map is calculated comprises:
inputting the perfusion parameter map obtained by calculation into a CTP image generation model to obtain a simulated CTP image output by the CTP image generation model;
and comparing the actual CTP image with the simulated CTP image, and adjusting the perfusion parameter map when the comparison result exceeds a preset range to obtain the adjusted perfusion parameter map.
6. The method of claim 1, wherein said assessing a measure of collateral circulation based on a degree of difference in arterial vessel volume and a degree of difference in time to peak perfusion for said ischemic brain region and contralateral brain region comprises:
calculating the difference in arterial vessel volumes of the contralateral brain region and the ischemic brain region;
calculating a difference in peak perfusion time between the contralateral brain region and the ischemic brain region;
and calculating to obtain a score corresponding to collateral circulation according to the arterial blood vessel volume difference and the perfusion peak-to-peak time difference.
7. The method according to claim 1, wherein said segmenting the brain area based on the tMIP map, which is projected based on the CTP image, to obtain the brain area segmentation result comprises:
projecting the CTP image to obtain a tMIP (partial projection maximum intensity projection) image, wherein the tMIP image is a maximum projection image along time;
extracting a brain contour line based on the tMIP, and determining a longitude center line and a latitude center line based on the brain contour line;
determining an intersection of the longitude and latitude centerlines;
and registering the tMIP to a standard brain area template based on the longitude central line, the latitude central line and the intersection point to obtain the brain area division result.
8. A collateral circulation measuring device based on CT perfusion image, characterized by that includes:
an obtaining module, configured to obtain an actual CTP image, and obtain a perfusion parameter map by calculation according to the actual CTP image, where the perfusion parameter map includes: tmax plot;
the blood vessel determining module is used for determining an arterial blood vessel mask according to the signal intensity which is changed along with the time and corresponds to each voxel in the CTP image;
an ischemia determining module, configured to perform threshold segmentation on the Tmax map to determine an ischemic region;
the brain area dividing module is used for dividing a brain area based on a tMIP (partial projection image) map to obtain a brain area dividing result, and the tMIP map is obtained by projecting based on the CTP image;
the brain area determining module is used for determining an ischemic brain area according to the ischemic area and the brain area partition result;
the first calculation module is used for calculating the arterial blood vessel volume of the ischemic brain area and the arterial blood vessel volume of a contralateral brain area, wherein the contralateral brain area is a healthy brain area which is in a symmetrical position with the ischemic brain area;
a second calculation module for calculating a peak perfusion time of the ischemic brain region and a peak perfusion time of the contralateral brain region;
and the evaluation module is used for evaluating and measuring the collateral circulation according to the difference degree of the arterial blood vessel volumes of the ischemic brain area and the contralateral brain area and the difference degree of the peak perfusion time.
9. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method of measuring a collateral circulation based on a CT perfusion image of any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, causes the processor to carry out the steps of the method of measuring a collateral circulation based on a CT perfusion image as set forth in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111664078.XA CN114332043B (en) | 2021-12-31 | 2021-12-31 | CT perfusion image-based collateral circulation measurement method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111664078.XA CN114332043B (en) | 2021-12-31 | 2021-12-31 | CT perfusion image-based collateral circulation measurement method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114332043A true CN114332043A (en) | 2022-04-12 |
| CN114332043B CN114332043B (en) | 2022-12-13 |
Family
ID=81020237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111664078.XA Active CN114332043B (en) | 2021-12-31 | 2021-12-31 | CT perfusion image-based collateral circulation measurement method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114332043B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982314A (en) * | 2012-11-05 | 2013-03-20 | 深圳市恩普电子技术有限公司 | Method of identifying, tracing and measuring external and internal membranes of vessel |
| CN108874516A (en) * | 2018-01-08 | 2018-11-23 | 深圳市铱硙医疗科技有限公司 | The method and device of csv file is generated based on MRI image |
| CN108852308A (en) * | 2018-06-22 | 2018-11-23 | 苏州高新区人民医院 | A kind of super time window AIS clinic Reperfu- sion method based on multi-parameter image technology optimizing detection system |
| CN109907758A (en) * | 2019-03-15 | 2019-06-21 | 脑玺(上海)智能科技有限公司 | The image mask method and system of intracranial vessel blood flow delay |
| CN111797901A (en) * | 2020-06-09 | 2020-10-20 | 中国科学院宁波工业技术研究院慈溪生物医学工程研究所 | Retinal artery and vein classification method and device based on topological structure estimation |
| CN112053413A (en) * | 2020-08-31 | 2020-12-08 | 杭州脉流科技有限公司 | Method and device for acquiring parameter map of brain CT perfusion imaging, computer equipment and storage medium |
| US20210085273A1 (en) * | 2018-02-01 | 2021-03-25 | Koninklijke Philips N.V. | Low radiation dose computed tomography perfusion (ctp) with improved quantitative analysis |
| CN112907563A (en) * | 2021-03-17 | 2021-06-04 | 复旦大学附属华山医院 | CTA full-automatic collateral circulation scoring method and system based on deep learning |
| CN113222974A (en) * | 2021-05-31 | 2021-08-06 | 沈阳先进医疗设备技术孵化中心有限公司 | Automatic evaluation method and device for collateral circulation |
| CN113256646A (en) * | 2021-04-13 | 2021-08-13 | 浙江工业大学 | Cerebrovascular image segmentation method based on semi-supervised learning |
| CN113256748A (en) * | 2020-02-13 | 2021-08-13 | 脑玺(上海)智能科技有限公司 | Image processing method and image processing device based on cerebrovascular CT (computed tomography) image |
| CN113450426A (en) * | 2021-06-09 | 2021-09-28 | 深圳市铱硙医疗科技有限公司 | Magnetic resonance cerebral perfusion imaging data processing system, method, terminal and medium |
| CN113610800A (en) * | 2021-08-05 | 2021-11-05 | 西门子数字医疗科技(上海)有限公司 | Device for assessing collateral circulation, non-diagnostic method and electronic apparatus |
-
2021
- 2021-12-31 CN CN202111664078.XA patent/CN114332043B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982314A (en) * | 2012-11-05 | 2013-03-20 | 深圳市恩普电子技术有限公司 | Method of identifying, tracing and measuring external and internal membranes of vessel |
| CN108874516A (en) * | 2018-01-08 | 2018-11-23 | 深圳市铱硙医疗科技有限公司 | The method and device of csv file is generated based on MRI image |
| US20210085273A1 (en) * | 2018-02-01 | 2021-03-25 | Koninklijke Philips N.V. | Low radiation dose computed tomography perfusion (ctp) with improved quantitative analysis |
| CN108852308A (en) * | 2018-06-22 | 2018-11-23 | 苏州高新区人民医院 | A kind of super time window AIS clinic Reperfu- sion method based on multi-parameter image technology optimizing detection system |
| CN109907758A (en) * | 2019-03-15 | 2019-06-21 | 脑玺(上海)智能科技有限公司 | The image mask method and system of intracranial vessel blood flow delay |
| CN113256748A (en) * | 2020-02-13 | 2021-08-13 | 脑玺(上海)智能科技有限公司 | Image processing method and image processing device based on cerebrovascular CT (computed tomography) image |
| CN111797901A (en) * | 2020-06-09 | 2020-10-20 | 中国科学院宁波工业技术研究院慈溪生物医学工程研究所 | Retinal artery and vein classification method and device based on topological structure estimation |
| CN112053413A (en) * | 2020-08-31 | 2020-12-08 | 杭州脉流科技有限公司 | Method and device for acquiring parameter map of brain CT perfusion imaging, computer equipment and storage medium |
| CN112907563A (en) * | 2021-03-17 | 2021-06-04 | 复旦大学附属华山医院 | CTA full-automatic collateral circulation scoring method and system based on deep learning |
| CN113256646A (en) * | 2021-04-13 | 2021-08-13 | 浙江工业大学 | Cerebrovascular image segmentation method based on semi-supervised learning |
| CN113222974A (en) * | 2021-05-31 | 2021-08-06 | 沈阳先进医疗设备技术孵化中心有限公司 | Automatic evaluation method and device for collateral circulation |
| CN113450426A (en) * | 2021-06-09 | 2021-09-28 | 深圳市铱硙医疗科技有限公司 | Magnetic resonance cerebral perfusion imaging data processing system, method, terminal and medium |
| CN113610800A (en) * | 2021-08-05 | 2021-11-05 | 西门子数字医疗科技(上海)有限公司 | Device for assessing collateral circulation, non-diagnostic method and electronic apparatus |
Non-Patent Citations (3)
| Title |
|---|
| F. O"SULLIVAN: "Kinetic Quantitation of Cerebral PET-FDG Studies Without Concurrent Blood Sampling: Statistical Recovery of the Arterial Input Function", 《IEEE TRANSACTIONS ON MEDICAL IMAGING》 * |
| 余翔: "多时相CT血管成像评估急性缺血性脑卒中机械取栓后的风险与获益", 《临床放射学杂志》 * |
| 颜立群: "3D pCASL及Rapid灌注分析对脑动脉搭桥术后脑血流灌注的评价", 《河北医科大学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114332043B (en) | 2022-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7486485B2 (en) | Apparatus for identifying regions in brain images | |
| EP3352135B1 (en) | Method and apparatus for segmentation of blood vessels | |
| Sun et al. | Intracranial hemorrhage detection by 3D voxel segmentation on brain CT images | |
| CN112907563A (en) | CTA full-automatic collateral circulation scoring method and system based on deep learning | |
| CN115880159A (en) | Method and computer readable storage medium for CT perfusion image parameter map correction | |
| US20220301177A1 (en) | Updating boundary segmentations | |
| CN115880261A (en) | Full-automatic post-processing method for brain CT perfusion image | |
| CN113724203B (en) | Model training method and device applied to target feature segmentation in OCT image | |
| CN113298800B (en) | CT angiography CTA source image processing method, device and equipment | |
| CN114332043B (en) | CT perfusion image-based collateral circulation measurement method, device, equipment and medium | |
| EP3977400A1 (en) | A computer based method for classifying a mass of an organ as a cyst | |
| Shinde et al. | Brain tumor identification using MRI images | |
| CN115937196A (en) | Medical image analysis system, analysis method and computer-readable storage medium | |
| CN115841472A (en) | Method, device, equipment and storage medium for identifying high-density characteristics of middle cerebral artery | |
| Lee et al. | Vessel segmentation model using automated threshold algorithm from lower leg MRI | |
| Hemmati et al. | Segmentation of carotid arteries in computed tomography angiography images using fast marching and graph cut methods | |
| Kulathilake et al. | A segmentation method for extraction of main arteries from coronary cine-angiograms | |
| CN117078711A (en) | Medical image segmentation method, system, electronic device and storage medium | |
| Wang et al. | Fully automatic diameter measurement method based on retinal vessel segmentation | |
| Kim et al. | Development of automated 3D knee bone segmentation with inhomogeneity correction for deformable approach in magnetic resonance imaging | |
| Pérez et al. | Spontaneous intracerebral hemorrhage image analysis methods: A survey | |
| BE1029246B1 (en) | Computer-implemented method for estimating an input function of a blood vein based on a sequence of three-dimensional volumetric scan images, a data processing device, a computer program product, and a computer-readable storage medium therefor | |
| Lemieux | Automatic, accurate, and reproducible segmentation of the brain and cerebro-spinal fluid in T1-weighted volume MRI scans and its application to serial cerebral and intracranial volumetry | |
| Krishnan et al. | A novel method for measurement of fetal volume from US images using segmentation techniques | |
| Castro et al. | Vessel detection in carotid ultrasound images using artificial neural networks |
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 |