CN113191998B - AIF curve extraction system, method, device and medium based on artery segmentation - Google Patents
AIF curve extraction system, method, device and medium based on artery segmentation Download PDFInfo
- Publication number
- CN113191998B CN113191998B CN202110055510.9A CN202110055510A CN113191998B CN 113191998 B CN113191998 B CN 113191998B CN 202110055510 A CN202110055510 A CN 202110055510A CN 113191998 B CN113191998 B CN 113191998B
- Authority
- CN
- China
- Prior art keywords
- curve
- voxel
- artery
- blood vessel
- peak
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/30104—Vascular flow; Blood flow; Perfusion
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses an AIF curve extraction system based on artery segmentation, which comprises: the blood vessel segmentation module preprocesses the original time density curve, calculates a contrast agent time density curve and a contrast agent peak value curve of each blood vessel voxel, obtains a blood vessel template by utilizing threshold segmentation, and extracts the contrast agent time density curve corresponding to the blood vessel voxel; the aorta positioning module calculates the peak arrival time of each blood vessel voxel through a blood vessel template, acquires the histogram distribution of the peak arrival time, selects the voxel before the cumulative histogram density is a set value as an artery rough segmentation result, removes tiny blood vessels to obtain an artery template, and selects an aorta and a blood vessel center part from the artery template; the artery input curve selection module extracts a contrast agent time density curve of a voxel corresponding to the central part of the blood vessel, calculates the density curve characteristic of each voxel, calculates the conformity of each voxel, and analyzes the conformity to obtain an artery input curve. The system can obtain the AIF curve efficiently and stably.
Description
Technical Field
The invention relates to the technical field of post-processing of dynamic perfusion images, in particular to an AIF curve extraction system, method, device and medium based on artery segmentation.
Background
In recent years, ischemic stroke has become a major health problem worldwide. The incidence of stroke in China is increasing year by year, and stroke becomes a main cause of death. The key to stroke therapy is the use of advanced imaging techniques (e.g., CT/MR perfusion imaging) to save ischemic penumbra. CT/MR perfusion imaging can be used to assess perfusion parameters by monitoring the time-density curve (TDC) of the tracer in the capillary bed for non-invasive diagnosis of stroke. In the course of the post-processing, it is first necessary to determine the Arterial Input Function (AIF), i.e. the change in the contrast agent concentration in the arteries supplying the brain with time. The tissue TDC can be considered as a convolution of the response function with the AIF. To analyze ischemic tissue, the response function must be calculated by deconvolution using AIF. We deconvolute the TDC at each voxel to obtain a hemodynamic map containing Cerebral Blood Flow (CBF), cerebral Blood Volume (CBV), time to maximum tissue residual function (Tmax) and Mean Transit Time (MTT). It is generally accepted that the characteristic TDC of voxels in aortic vessels (such as the basilar or internal carotid arteries) is AIF. The AIF is a key reference curve for obtaining quantitative CBF, CBV, tmax and MTT parameter maps in a deconvolution model, and has great influence on the result of deconvolution operation. Clinically, the selection of AIF depends on the expertise, experience and skill of the medical professional, and high time consumption and low reproducibility are the biggest drawbacks of manual selection of AIF. Visualization of the location and extent of the salvageable tissue can effectively help the physician determine who would benefit from thrombolysis or other treatment. Since treatment with thrombolytic drugs must be initiated quickly, a perfusion map is provided immediately after scanning for clinical decision-making. While establishing various perfusion maps requires determining the Arterial Input Function (AIF), which describes the intravascular tracer delivery to the tissue. If the process is performed manually, the results are completely dependent on the experience and subjective judgment of the operator, and the whole process is tedious, error-prone and non-repeatable.
The AIF curve has the characteristics of high maximum concentration, small half-peak width and early maximum concentration occurrence time. Traditional AIF extraction methods require the operator to map regions of interest, such as the Middle Cerebral Artery (MCA) and the internal carotid artery, on the aorta that passes through the imaging slice. However, since the manual operation is performed based on the experience and subjective judgment of the operator, the operation is time-consuming and not repeatable, and may adversely affect the calculation of the hemodynamic parameters. Therefore, the automatic detection model of AIF has important significance, and it can achieve high efficiency, low user dependence, and high repeatability. Currently, some methods for automatically selecting an AIF curve have been developed, mainly including a threshold method, a weight method, a clustering method, and the like. Based on the shape characteristics of the AIF curve, carroll T J et al propose a thresholding method to pre-select voxels of interest and detect AIF therefrom. However, these fixed thresholds have poor generalization ability. Lorenz C et al create a local AIF for each voxel in the brain by searching for voxels with minimal delay and dispersion, and then interpolating and spatially smoothing them for continuity. An automatic AIF extraction method based on kmeans classification proposed by Kim Mouridsen et al. Since K-means is highly sensitive to randomly selected initial cluster centers, the repeatability of AIF is reduced. Straka M selects the best AIF by weighted summation of the peak height, peak width, and arrival time of the time density curve using weight method. But fixed parameters are difficult to adapt to different patients. Peruzzo et al propose a new Middle Cerebral Artery (MCA) AIF automatic detection method, which combines the prior knowledge of the anatomical position and signal form of AIF on the basis of the Hier method, and improves the reliability of AIF detection. However, this method requires a predefined voxel extraction mask, which limits the flexibility and robustness of Hier.
Disclosure of Invention
Aiming at the defects in the prior art, the AIF curve extraction system, the method, the device and the medium based on the artery segmentation can stably and efficiently obtain the artery input function curve.
In a first aspect, an AIF curve extraction system based on artery segmentation provided in an embodiment of the present invention includes: a blood vessel segmentation module, an aorta positioning module and an artery input curve selection module,
the vessel segmentation module is used for preprocessing the original time density curve, calculating a contrast agent time density curve and a contrast agent peak value curve of each vessel voxel, obtaining a vessel template by utilizing threshold segmentation, and extracting the contrast agent time density curve corresponding to the vessel voxel;
the aorta positioning module is used for calculating the peak value arrival time of each blood vessel voxel through a blood vessel template, obtaining the histogram distribution of the peak value arrival time, selecting the voxel before the accumulated histogram density is a set value as an artery rough segmentation result, removing tiny blood vessels to obtain an artery template, and selecting a main artery and a blood vessel center part from the artery template;
the artery input curve selection module is used for extracting a contrast agent time density curve of a voxel corresponding to the central part of a blood vessel, calculating the density curve characteristic of each voxel, calculating the conformity of each voxel, and analyzing the conformity to obtain an artery input curve.
In a second aspect, an AIF curve extraction method based on artery segmentation provided in an embodiment of the present invention includes the following steps:
preprocessing the original time density curve, calculating a contrast agent time density curve and a contrast agent peak value curve of each vessel voxel, obtaining a vessel template by utilizing threshold segmentation, and extracting the contrast agent time density curve corresponding to the vessel voxel;
calculating the peak arrival time of each blood vessel voxel through a blood vessel template, acquiring the histogram distribution of the peak arrival time, selecting the voxel before the accumulated histogram density is a set value as an artery rough segmentation result, removing tiny blood vessels to obtain an artery template, and selecting a central part of a main artery and a blood vessel from the artery template;
extracting a contrast agent time density curve of a voxel corresponding to the central part of the blood vessel, calculating the density curve characteristic of each voxel, calculating the conformity of each voxel, and analyzing the conformity to obtain an artery input curve.
In a third aspect, an embodiment of the present invention provides an AIF curve extraction apparatus, including a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method steps described in the foregoing embodiment.
In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium storing a computer program, the computer program comprising program instructions that, when executed by a processor, cause the processor to perform the method steps described in the above embodiments.
The invention has the beneficial effects that:
the AIF curve extraction system, method, device and medium based on artery segmentation provided by the embodiment of the invention can be used for preprocessing raw data, removing most non-AIF volume data, directly removing non-vascular voxels, segmenting a middle cerebral artery region by using the characteristics of an artery curve, extracting the time density curve characteristics of each voxel, weighting to obtain an optimal AIF curve, efficiently and stably obtaining the AIF curve, and avoiding the problem of poor repeatability caused by kmeans or FCM algorithm. Meanwhile, the generalization capability is strong, and the condition that a threshold segmentation algorithm needs to debug corresponding parameters on different data sets is avoided.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings used in the detailed description or the prior art description will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 is a schematic structural diagram illustrating an AIF curve extraction system based on artery segmentation according to a first embodiment of the present invention;
FIG. 2 shows a time density curve obtained after a pretreatment in a first embodiment of the present invention;
FIG. 3 shows a contrast agent time density curve in a first embodiment of the present invention;
FIG. 4 shows a voxel peak map in a first embodiment of the invention;
FIG. 5 shows a diagram of a vascular template in a first embodiment of the present invention;
FIG. 6 is a diagram showing the result of the histogram segmentation of peak arrival times according to the first embodiment of the present invention;
FIG. 7 is a diagram illustrating a blood vessel classification result according to a first embodiment of the present invention;
FIG. 8 is a diagram showing the result after removal of small blood vessels in the first embodiment of the present invention;
FIG. 9 is a diagram showing the result of the aorta positioning in the first embodiment of the present invention;
FIG. 10 is a schematic view showing the central part of the aorta in the first embodiment of the present invention;
FIG. 11 shows the resulting AIF plot in a first embodiment of the present invention;
fig. 12 is a flowchart of an AIF curve extraction method based on artery segmentation according to a second embodiment of the present invention;
fig. 13 is a schematic structural diagram of an AIF curve extraction apparatus according to a third embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. 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 invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
Example 1
Fig. 1 shows a schematic structural diagram of an AIF curve extraction system based on artery segmentation according to a first embodiment of the present invention, where the system includes: the system comprises a vessel segmentation module, an aorta positioning module and an artery input curve selection module, wherein the vessel segmentation module is used for preprocessing an original time density curve, calculating a contrast agent time density curve and a contrast agent peak value curve of each vessel voxel, obtaining a vessel template by utilizing threshold segmentation, and extracting a contrast agent time density curve corresponding to the vessel voxel; the aorta positioning module is used for calculating the peak value arrival time of each blood vessel voxel through a blood vessel template, obtaining the histogram distribution of the peak value arrival time, selecting the voxel before the accumulated histogram density is a set value as an artery rough segmentation result, removing tiny blood vessels to obtain an artery template, and selecting a main artery and a blood vessel center part from the artery template; the artery input curve selection module is used for extracting a contrast agent time density curve of a voxel corresponding to the central part of a blood vessel, calculating the density curve characteristic of each voxel, calculating the conformity of each voxel, and analyzing the conformity to obtain an artery input curve.
The vessel segmentation module performs smoothing filtering and data denoising on the original time density curve to obtain the TDC, as shown in fig. 2. Calculating the mean value of the first few moments of the TDC curve 0 As a voxel eigenvalue, the contrast agent time density curve CTDC = TDC-TDC 0 As shown in fig. 3, a contrast agent time density plot is shown; calculating contrast agent peak CTDC for each voxel max = max { CTDC }, resulting in a voxel peak map, as shown in fig. 4; selecting a proper threshold value to carry out segmentation to obtain blood vesselsTemplate MASK vessel Obtaining a blood vessel template map, as shown in fig. 5, selecting a threshold value of 64Hu for segmentation in this embodiment; extracting contrast agent time density curve CTDC corresponding to vessel voxel vessel The subsequent operations are performed on the voxels corresponding to the blood vessel template.
The aorta positioning module is used for calculating the peak arrival time T = maxarg { CTDC (computed tomography) of each vessel voxel vessel }; acquiring histogram distribution of peak arrival time T, selecting an early part as an artery rough segmentation result, and selecting a voxel with cumulative histogram density of 40% in the embodiment, wherein the obtained segmentation results are shown in fig. 6 and 7, fig. 6 shows a histogram segmentation result schematic diagram of peak arrival time T, and fig. 7 shows a blood vessel classification result schematic diagram; removing fine blood vessels by using morphological closure operation to obtain artery template MASK artery As shown in the red area of fig. 8, a schematic diagram of the result after the removal of the small blood vessels is shown, and a diagram of the result after the removal of the small blood vessels is shown; calculating the radius of the central axis of the blood vessel and the corresponding position, and selecting the part with large radius and small curvature as the aorta, as shown in the green part in fig. 9, showing a schematic diagram of the aorta positioning result; obtaining target blood vessel middle part MASK by using morphological erosion algorithm obj As shown in the colored part of fig. 10, a schematic diagram of the central part of the aorta is shown, and subsequent operations are performed only on the central part of the voxels of the blood vessel.
The artery input curve selection module extracts a contrast agent time density curve CTDC of a target area obj (ii) a Extracting the density curve characteristics of each voxel, wherein the curve characteristics comprise curve peak height, peak arrival time and half-peak width, and calculating the conformity of each voxel according to the formula
Wherein k is i Is weight, i is integer, h, a, w are curve peak height, peak arrival time, half peak width respectively,
the obtained conformity degrees are sorted according to a descending order, N conformity degrees which are ranked in the front are selected, N is a natural number, and the average value of the N conformity degrees is calculated to obtain a final AIF curve, as shown in FIG. 11. In the present embodiment, k 1 ＝1，k 2 ＝-3.5，k 3 And (4) keeping the number of pixels to be selected at full range by = 5,N =10, and if the number of pixels in the target region is less than N.
The AIF curve extraction system based on artery segmentation provided by the embodiment of the invention has the advantages that the preprocessing operation is carried out on the original data, most of non-AIF volume data can be removed, non-vascular voxels are directly removed, the middle cerebral artery area is segmented by utilizing the artery curve characteristics, the time density curve characteristics of each voxel are extracted, the optimal AIF curve is obtained through weighting, the AIF curve can be efficiently and stably obtained through the system, and the problem of poor repeatability caused by kmeans or FCM algorithm is avoided. Meanwhile, the generalization capability is strong, and the condition that a threshold segmentation algorithm needs to debug corresponding parameters on different data sets is avoided.
In the first embodiment described above, an AIF curve extraction system based on artery segmentation is provided, and correspondingly, the present application also provides an AIF curve extraction method based on artery segmentation. Please refer to fig. 12, which is a flowchart illustrating an AIF curve extraction method based on artery segmentation according to a second embodiment of the present invention. Since the method embodiments are substantially similar to the apparatus embodiments, they are described in a relatively simple manner, and reference may be made to the apparatus embodiments for some of their relevant descriptions. The method embodiments described below are merely illustrative.
Example 2
As shown in fig. 12, a flowchart of an AIF curve extraction method based on artery segmentation according to a second embodiment of the present invention is shown, and the method includes the following steps:
s1: preprocessing the original time density curve, calculating a contrast agent time density curve and a contrast agent peak value curve of each vessel voxel, obtaining a vessel template by utilizing threshold segmentation, and extracting the contrast agent time density curve corresponding to the vessel voxel.
Specifically, the original time density curve is subjected to smoothing filtering and data noise reduction processing.
S2: calculating the peak arrival time of each blood vessel voxel through a blood vessel template, acquiring the histogram distribution of the peak arrival time, selecting the voxel before the cumulative histogram density is a set value as an artery rough segmentation result, removing tiny blood vessels to obtain an artery template, and selecting a main artery and a blood vessel center part from the artery template.
S3: extracting a contrast agent time density curve of a voxel corresponding to the central part of the blood vessel, calculating the density curve characteristic of each voxel, calculating the conformity of each voxel, and analyzing the conformity to obtain an artery input curve.
Specifically, a contrast agent time density curve CTDC of the target region is extracted obj (ii) a Extracting the density curve characteristics of each voxel, wherein the curve characteristics comprise curve peak height, peak arrival time and half-peak width, and calculating the conformity of each voxel according to the formula
Wherein k is i Is weight, i is integer, h, a, w are curve peak height, peak arrival time, half peak width respectively,
respectively are the mean values of curve peak height, peak value arrival time and half peak width, the obtained conformity degrees are sorted according to a descending order, N conformity degrees which are ranked at the front are selected, N is a natural number, the mean value of the N conformity degrees is calculated, and a final AIF curve is obtained. In the present embodiment, k 1 ＝1，k 2 ＝-3.5，k 3 And (4) = -5,N =10, and if the target area is less than N voxels, the selection is carried out.
According to the AIF curve extraction method based on artery segmentation provided by the embodiment of the invention, the preprocessing operation is carried out on the original data, most of non-AIF volume data can be removed, non-vascular voxels are directly removed, the middle cerebral artery region is segmented by using the characteristics of the artery curve, the time density curve characteristics of each voxel are extracted, and the optimal AIF curve is obtained by weighting. Meanwhile, the generalization capability is strong, and the condition that a threshold segmentation algorithm needs to debug corresponding parameters on different data sets is avoided.
Example 3
As shown in fig. 13, a schematic structural diagram of an AIF curve extraction apparatus provided in a third embodiment of the present invention is shown, where the apparatus includes a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, the memory is used for storing a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method steps described in the foregoing embodiments.
It should be understood that in the embodiments of the present invention, the Processor may be a Central Processing Unit (CPU), and the Processor may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device may include a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of the fingerprint), a microphone, etc., and the output device may include a display (LCD, etc.), a speaker, etc.
The memory may include both read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
In a specific implementation, the processor, the input device, and the output device described in the embodiments of the present invention may execute the implementation described in the method embodiments provided in the embodiments of the present invention, and may also execute the implementation described in the system embodiments in the embodiments of the present invention, which is not described herein again.
An embodiment of a computer-readable storage medium is also provided in the present invention, which computer-readable storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to carry out the method steps described in the above embodiment.
The computer readable storage medium may be an internal storage unit of the terminal according to the foregoing embodiment, for example, a hard disk or a memory of the terminal. The computer readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the terminal. The computer-readable storage medium is used for storing the computer program and other programs and data required by the terminal. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the terminal and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed terminal and method can be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electrical, mechanical or other form of connection.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being covered by the appended claims and their equivalents.
Claims (7)
1. An AIF curve extraction system based on artery segmentation, comprising: a blood vessel segmentation module, an aorta positioning module and an artery input curve selection module,
the vessel segmentation module is used for preprocessing the original time density curve, calculating a contrast agent time density curve and a contrast agent peak value curve of each vessel voxel, obtaining a vessel template by utilizing threshold segmentation, and extracting a contrast agent time density curve corresponding to the vessel voxel;
the aorta positioning module is used for calculating the peak value arrival time of each blood vessel voxel through a blood vessel template, obtaining the histogram distribution of the peak value arrival time, selecting the voxel before the accumulated histogram density is a set value as an artery rough segmentation result, removing tiny blood vessels to obtain an artery template, and selecting a main artery and a blood vessel center part from the artery template;
the artery input curve selection module is used for extracting a contrast agent time density curve of a voxel corresponding to the central part of a blood vessel, calculating the density curve characteristic of each voxel, calculating the conformity of each voxel, and analyzing the conformity to obtain an artery input curve;
the artery input curve selection module comprises a voxel density curve extraction unit and an analysis unit, wherein the voxel density curve extraction unit is used for extracting a contrast agent time density curve of a voxel corresponding to the central part of a blood vessel;
the analysis unit is used for calculating the density curve characteristics of each voxel, the curve characteristics comprise curve peak height, peak arrival time and half-peak width, the conformity of each voxel is calculated, and the calculation formula is
2. The system according to claim 1, wherein the blood vessel segmentation module comprises a preprocessing unit, a first calculating unit, a segmentation unit and an extracting unit, wherein the preprocessing unit is configured to perform smoothing filtering and data denoising on an original time density curve to obtain a processed time density curve;
the first calculating unit is used for calculating a contrast agent time density curve and a contrast agent peak value curve of each blood vessel voxel according to the processed time density curve;
the segmentation unit is used for obtaining a blood vessel template by utilizing set threshold segmentation;
the extraction unit is used for extracting a contrast agent time density curve corresponding to the vessel voxel.
3. The system according to claim 2, wherein the aorta localization module comprises a second computing unit, an artery coarse segmentation unit, a small blood vessel removal unit and a selection unit, wherein the second computing unit computes the peak arrival time of each blood vessel voxel through a blood vessel template;
the artery rough segmentation unit acquires histogram distribution of peak arrival time, and selects a voxel before the accumulated histogram density is a set value as an artery rough segmentation result;
the small blood vessel removing unit is used for removing small blood vessels through morphological closure operation to obtain an artery template;
the selecting unit is used for calculating the radius of the central axis of the blood vessel and the radius of the corresponding position from the artery template, selecting the part of the blood vessel with the radius larger than the radius threshold value and the curvature smaller than the curvature threshold value as an aorta, and obtaining the central part of the target blood vessel by utilizing a morphological corrosion algorithm.
4. An AIF curve extraction method based on artery segmentation is characterized by comprising the following steps:
preprocessing the original time density curve, calculating a contrast agent time density curve and a contrast agent peak value curve of each vessel voxel, obtaining a vessel template by utilizing threshold segmentation, and extracting the contrast agent time density curve corresponding to the vessel voxel;
calculating the peak arrival time of each blood vessel voxel through a blood vessel template, acquiring the histogram distribution of the peak arrival time, selecting the voxel before the accumulated histogram density is a set value as an artery rough segmentation result, removing tiny blood vessels to obtain an artery template, and selecting a main artery and a blood vessel center part from the artery template;
extracting a contrast agent time density curve of voxels corresponding to the central part of the blood vessel, calculating the density curve characteristics of each voxel, calculating the conformity of each voxel, and analyzing the conformity to obtain an artery input curve;
the calculating the density curve characteristic of each voxel, calculating the conformity of each voxel, and analyzing the conformity to obtain the artery input curve specifically comprises:
calculating the density curve characteristics of each voxel, wherein the curve characteristics comprise curve peak height, peak arrival time and half-peak width, and calculating the conformity of each voxel according to the formula
Wherein k is i Is weight, i is integer, h, a, w are curve peak height, peak arrival time, half peak width respectively,
and respectively averaging the peak height of the curve, the arrival time of the peak value and the half-peak width, sorting the obtained conformity according to a descending order, selecting N conformity degrees which are ranked at the front, wherein N is a natural number, and calculating the average value of the N conformity degrees to obtain the artery input curve.
5. The method according to claim 4, wherein the preprocessing the raw time density curve specifically comprises: and carrying out smooth filtering and data noise reduction processing on the original time density curve.
6. An AIF curve extraction apparatus comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, the memory being adapted to store a computer program comprising program instructions, characterized in that the processor is configured to invoke the program instructions to perform the method of any of claims 4 to 5.
7. A computer-readable storage medium, characterized in that the computer storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to carry out the method according to any one of claims 4-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110055510.9A CN113191998B (en) | 2021-01-15 | 2021-01-15 | AIF curve extraction system, method, device and medium based on artery segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110055510.9A CN113191998B (en) | 2021-01-15 | 2021-01-15 | AIF curve extraction system, method, device and medium based on artery segmentation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113191998A CN113191998A (en) | 2021-07-30 |
| CN113191998B true CN113191998B (en) | 2023-01-13 |
Family
ID=76972944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110055510.9A Active CN113191998B (en) | 2021-01-15 | 2021-01-15 | AIF curve extraction system, method, device and medium based on artery segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191998B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109431531A (en) * | 2018-12-25 | 2019-03-08 | 上海联影医疗科技有限公司 | Blood vessel segmentation method and device and computer installation based on Perfusion Imaging |
| CN109461138A (en) * | 2018-09-29 | 2019-03-12 | 深圳睿心智能医疗科技有限公司 | Calculation method of parameters, system, readable storage medium storing program for executing and computer equipment |
| CN110236544A (en) * | 2019-05-29 | 2019-09-17 | 中国科学院重庆绿色智能技术研究院 | Apoplexy Perfusion Imaging lesion region detection system and method based on related coefficient |
| CN110301900A (en) * | 2019-07-01 | 2019-10-08 | 脑玺(上海)智能科技有限公司 | The quantitative analysis method and system of dynamic perfusion image processing |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8837800B1 (en) * | 2011-10-28 | 2014-09-16 | The Board Of Trustees Of The Leland Stanford Junior University | Automated detection of arterial input function and/or venous output function voxels in medical imaging |
| US20130322718A1 (en) * | 2012-06-01 | 2013-12-05 | Yi-Hsuan Kao | Method and apparatus for measurements of the brain perfusion in dynamic contrast-enhanced computed tomography images |
| TW201408262A (en) * | 2012-08-30 | 2014-03-01 | Univ Chang Gung | Method of extracting arterial input function and its application for dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) |
| US20140163403A1 (en) * | 2012-12-12 | 2014-06-12 | The Texas A&M University System | Automated determination of arterial input function areas in perfusion analysis |
-
2021
- 2021-01-15 CN CN202110055510.9A patent/CN113191998B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109461138A (en) * | 2018-09-29 | 2019-03-12 | 深圳睿心智能医疗科技有限公司 | Calculation method of parameters, system, readable storage medium storing program for executing and computer equipment |
| CN109431531A (en) * | 2018-12-25 | 2019-03-08 | 上海联影医疗科技有限公司 | Blood vessel segmentation method and device and computer installation based on Perfusion Imaging |
| CN110236544A (en) * | 2019-05-29 | 2019-09-17 | 中国科学院重庆绿色智能技术研究院 | Apoplexy Perfusion Imaging lesion region detection system and method based on related coefficient |
| CN110301900A (en) * | 2019-07-01 | 2019-10-08 | 脑玺(上海)智能科技有限公司 | The quantitative analysis method and system of dynamic perfusion image processing |
Non-Patent Citations (2)
| Title |
|---|
| Kinetic Quantitation of Cerebral PET-FDG Studies;F. O’Sullivan et al;《IEEE》;20100331;第29卷(第3期);第610-624页 * |
| 肺部CT图像病变区域检测方法;韩光辉 等;《自动化学报》;20171231;第43卷(第12期);第2071-2090页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113191998A (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190690B (en) | Method for detecting and identifying cerebral microhemorrhage points based on SWI image of machine learning | |
| WO2022063198A1 (en) | Lung image processing method, apparatus and device | |
| US10229488B2 (en) | Method and system for determining a stage of fibrosis in a liver | |
| CN107292835B (en) | Method and device for automatically vectorizing retinal blood vessels of fundus image | |
| Yang et al. | Renal compartment segmentation in DCE-MRI images | |
| CN111415321B (en) | Aneurysm rupture risk detection device and equipment | |
| Lian et al. | Automatic gallbladder and gallstone regions segmentation in ultrasound image | |
| Nisha et al. | A computer-aided diagnosis system for plus disease in retinopathy of prematurity with structure adaptive segmentation and vessel based features | |
| CN112734828B (en) | Method, device, medium and equipment for determining center line of fundus blood vessel | |
| CN112233789A (en) | Regional feature fusion type hypertensive retinopathy classification method | |
| WO2014107402A1 (en) | Classification of biological tissue by multi-mode data registration, segmentation and characterization | |
| Lamy et al. | A benchmark framework for multiregion analysis of vesselness filters | |
| CN113191998B (en) | AIF curve extraction system, method, device and medium based on artery segmentation | |
| WO2022006917A1 (en) | Artificial intelligence-based lung magnetic resonance image recognition apparatus and method | |
| Ali et al. | Segmenting retinal blood vessels with Gabor filter and automatic binarization | |
| CN114077863A (en) | System and method for measuring artery input function in dynamic perfusion image post-processing | |
| Hanuman et al. | Brain tumor segmentation and volume estimation from T1-contrasted and T2 MRIs | |
| CN113269756A (en) | Retina blood vessel segmentation method and device based on multi-scale matched filtering and particle swarm optimization | |
| Luo et al. | Extraction of brain vessels from magnetic resonance angiographic images: Concise literature review, challenges, and proposals | |
| CN112102188A (en) | GPU-based distributed computing multi-scale vascular enhancement filtering method | |
| Napier et al. | A CAD system for brain haemorrhage detection in head CT scans | |
| Luo et al. | Recent progresses on cerebral vasculature segmentation for 3D quantification and visualization of MRA | |
| Fu et al. | A new automatic segmentation algorithm for carotid artery ultrasound images | |
| KR102555996B1 (en) | Apparatus and method for diagnosing disease of target part based on medicial image | |
| Nery et al. | An algorithm for the pulmonary border extraction in PET images |
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 |