CN113570570A - Device for segmenting pulmonary blood vessels from pulmonary mask image - Google Patents
Device for segmenting pulmonary blood vessels from pulmonary mask image Download PDFInfo
- Publication number
- CN113570570A CN113570570A CN202110848452.5A CN202110848452A CN113570570A CN 113570570 A CN113570570 A CN 113570570A CN 202110848452 A CN202110848452 A CN 202110848452A CN 113570570 A CN113570570 A CN 113570570A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- image
- module
- unit
- blood
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 325
- 230000002685 pulmonary effect Effects 0.000 title claims abstract description 51
- 210000004072 lung Anatomy 0.000 claims abstract description 88
- 230000011218 segmentation Effects 0.000 claims abstract description 64
- 230000004927 fusion Effects 0.000 claims abstract description 50
- 238000004364 calculation method Methods 0.000 claims abstract description 43
- 238000005457 optimization Methods 0.000 claims abstract description 33
- 230000017531 blood circulation Effects 0.000 claims description 45
- 230000008859 change Effects 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 27
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000003708 edge detection Methods 0.000 claims description 7
- 238000012886 linear function Methods 0.000 claims description 7
- 230000004048 modification Effects 0.000 claims description 6
- 238000012986 modification Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000007620 mathematical function Methods 0.000 claims description 3
- 238000012887 quadratic function Methods 0.000 claims description 3
- 210000001519 tissue Anatomy 0.000 abstract description 16
- 239000008280 blood Substances 0.000 abstract description 13
- 210000004369 blood Anatomy 0.000 abstract description 13
- 210000001147 pulmonary artery Anatomy 0.000 abstract description 13
- 210000000988 bone and bone Anatomy 0.000 abstract description 8
- 230000002861 ventricular Effects 0.000 abstract description 8
- 238000003709 image segmentation Methods 0.000 description 8
- 238000000605 extraction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000000926 separation method Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000003394 haemopoietic effect Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 210000003097 mucus Anatomy 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
- 210000003437 trachea Anatomy 0.000 description 1
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
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-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
- G06T7/13—Edge detection
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30061—Lung
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a device for segmenting pulmonary vessels from a pulmonary mask image, which comprises a computing module, an image acquisition module, an image fusion module, a vessel segmentation module, a vessel position determination module and a vessel edge optimization module, wherein the computing module is used for computing the pulmonary mask image; the calculation module is in electric signal connection with the image acquisition module, the image acquisition module is used for acquiring images of lung masks, the calculation module is used for calculating the range of the sizes of blood vessels in the lung mask images, the image acquisition module is in electric signal connection with the image fusion module, and the image fusion module is used for carrying out image fusion on a plurality of lung mask images to acquire fused lung fusion images. The invention has the advantages that the gray scale of the tiny blood vessels is uniformly distributed, the gray scale of the blood vessels is obviously compared with the gray scale of surrounding tissues, the boundary with obvious gray scale difference is provided, the accuracy of extracting the pulmonary blood vessels is improved, the gray scale difference of the blood vessels and other tissues such as adjacent bones, ventricular blood and the like in the image is large, and the blood vessel segmentation image is accurate and clear.
Description
Technical Field
The invention relates to the technical field of medical instruments, in particular to a device for segmenting pulmonary vessels from a pulmonary mask image.
Background
The lung is a respiratory organ of a human body and also an important hematopoietic organ of the human body, the lung is positioned on the left side and the right side of a thoracic cavity and covers the heart, blood vessels are distributed in the lung in a complex manner, the lung comprises a plurality of blood vessel branches, the diameter of each blood vessel is within the range of 20 micrometers to 15 millimeters, in order to observe and know pathological changes of the blood vessels, the blood vessels of the lung of the human body are usually scanned by a digital image device, the scanned images are often required to be subjected to blood vessel segmentation so as to be convenient for doctors to perform further blood vessel analysis and detection, the blood vessel segmentation in medical images is mainly completed based on gray information in the images, particularly gray level difference, and accurate lung blood vessel segmentation is realized through computer-aided detection and diagnosis.
The existing pulmonary blood vessel segmentation device displays a high-density image on the whole due to the fact that the inside of a pulmonary blood vessel is filled with blood on a CT image, the gray scale distribution is not uniform, particularly, the influence of a small blood vessel part is large, the gray scale of the blood vessel is close to that of surrounding tissues, no obvious gray scale difference or boundary exists, mucus filled trachea, pulmonary nodules and high-density lesions around the pulmonary blood vessel can interfere with the accuracy of extraction of the pulmonary blood vessel, the gray scale values of the blood vessel and other tissues such as adjacent bones and ventricular blood in the image are very close, and the segmentation is not easy to perform, so that difficulty is brought to the blood vessel segmentation in a medical image, and the condition of blood vessel segmentation failure can occur.
Disclosure of Invention
The invention aims to provide a device for segmenting pulmonary blood vessels from a lung mask image, so that the gray scale of small blood vessels is uniformly distributed, the gray scale of the blood vessels is obviously compared with the gray scale of surrounding tissues, the device has an obvious gray scale difference boundary, the accuracy of pulmonary blood vessel extraction is improved, the gray scale difference of the blood vessels and other tissues such as adjacent bones, ventricular blood and the like in the image is large, and the image of blood vessel segmentation is accurate and clear.
A device for segmenting pulmonary blood vessels from a pulmonary mask image comprises a computing module, an image acquisition module, an image fusion module, a blood vessel segmentation module, a blood vessel position determination module and a blood vessel edge optimization module; the calculation module is electrically connected with the image acquisition module, the image acquisition module is used for acquiring the image of the lung mask, the calculation module is used for calculating the range of the blood vessel size in the lung mask image, the image acquisition module and the image fusion module are mutually connected by electric signals, the image fusion module is used for carrying out image fusion on a plurality of lung mask images to acquire fused lung fusion images, the image fusion module and the blood vessel segmentation module are in electric signal connection with each other, the blood vessel segmentation module is used for segmenting the position of a blood vessel in the lung fusion image to obtain a blood vessel image, the blood vessel segmentation module and the blood vessel position determination module are in electric signal connection with each other, the blood vessel position determination module is used for determining the position of the blood vessel in the blood vessel image, the blood vessel position determination module and the blood vessel edge optimization module are in electric signal connection with each other, and the blood vessel edge optimization module is used for performing optimization processing of fitting of a linear function on the edge of the blood vessel.
The pulmonary vessel segmentation device is provided with a calculation module, the calculation module is used for calculating the range of the vessel size in a pulmonary mask image, the image fusion module is used for carrying out image fusion on a plurality of pulmonary mask images, when the pulmonary vessel is filled with blood to display a high-density image on the whole, the separation of the vessel size range is carried out through the calculation module, so that the gray level of the small vessel is uniformly distributed, the gray level of the vessel is obviously compared with the gray level of surrounding tissues, an obvious gray level difference boundary is provided, the accuracy of pulmonary vessel extraction is improved, the vessel edge optimization module is used for carrying out optimization processing of linear function fitting on the edge of the vessel, the gray level difference of the vessel and other tissues such as adjacent bones, ventricular blood and the like in the image is large, and the vessel segmentation image is accurate and clear.
Furthermore, the calculation module comprises a blood vessel size calculation unit, a change rate calculation unit, a blood flow parameter calculation unit and a blood flow threshold calculation unit, the blood vessel size calculation unit calculates the range of the blood vessel size in the lung mask image through the response value of the function, and calculating response values of blood vessel similarity functions under different blood vessel sizes in the lung mask image, calculating diameter change rates of different blood vessel sizes by a change rate calculation unit, calculating change rates at different blood vessel segmentation positions, wherein the change rates are represented by a plurality of mathematical functions, calculating blood flow parameter values by a blood flow parameter calculation unit according to the sizes of the blood vessels and the change rates of the blood vessel diameters, calculating the blood flow parameter values by blood flow velocity values, calculating derivatives of the blood flow velocity value functions by a blood flow threshold calculation unit, defining blood flow thresholds by the derivatives, and obtaining a plurality of blood flow velocity thresholds by a plurality of blood vessels.
The blood flow threshold value calculation unit is used for solving a derivative of a function of the blood flow velocity value, the derivative is used for defining the blood flow threshold value, a plurality of blood vessels obtain a plurality of blood flow velocity threshold values, different blood vessels are judged by setting different blood flow velocity threshold values, the threshold values are defined for different blood vessels, and the contrast of the image is improved through the definition of the threshold values.
Further, the image acquisition module comprises an image shooting unit and an image modification unit, wherein the image shooting unit is used for acquiring images containing blood vessels in the lung mask images, the number of the lung mask images is multiple, the images of the lung masks are six-sided images, and the image modification unit is used for modifying the sizes of the lung mask images.
Further, the image fusion module comprises an image fusion unit and an image determination unit, the image fusion unit is used for fusing the lung mask images to obtain a fused lung mask image stereogram, and the image determination unit is used for determining the directions and the positions of the lung mask images.
The image fusion unit is used for fusing the lung mask images, the image determination unit is used for determining the directions and the positions of the lung mask images, the lung mask images form multi-view lung blood vessel images, the images and the depth information of the lung blood vessels at a plurality of weak different views can be obtained through image fusion in one step, the directions and the positions of the fused lung mask images are identified and determined at different views, and therefore the accuracy of lung blood vessel identification is improved.
The blood vessel segmentation module further comprises a blood vessel analysis unit and a blood vessel segmentation unit, wherein the blood vessel analysis unit analyzes and determines the lung mask image stereogram to enable blood vessels to be segmented from the image, the analysis unit determines blood vessel positions through continuity and gradient of the blood vessels and fits the blood vessels segmented in different directions and positions, and the blood vessel segmentation unit is used for segmenting and extracting structures of the blood vessels, extracting diameters of the segmented blood vessels and extracting positions of the segmented blood vessels to form a two-dimensional blood vessel image.
Furthermore, the blood vessel position determining module is provided with a continuity detecting unit, a length detecting unit, an edge detecting unit and a distance detecting unit, wherein the continuity detecting unit determines the position of the blood vessel through the continuity of the blood vessel, the length detecting unit determines the length of the blood vessel through the continuity of the diameter change of the blood vessel, the edge detecting unit determines the edge line of the blood vessel through the continuity of the equivalent diameter of the cross section of the blood vessel, and the distance detecting unit determines the distance between the blood vessels through the adjacent blood vessel positions of the two-dimensional blood vessel image.
Furthermore, the blood vessel edge optimization module comprises an edge detection unit and an edge fitting unit, wherein the edge detection unit detects the edge value of the blood vessel through the difference value of the adjacent edge distances at two sides of the blood vessel, and the edge fitting unit performs linear fitting of a quadratic function of the same blood vessel through repeated images.
Further, the blood vessel edge optimization module comprises a blood vessel contour fitting unit and a blood vessel diameter determining unit, wherein the blood vessel contour fitting unit adopts a three-dimensional blood vessel contour model to perform fitting processing on the blood vessel edge, and the blood vessel diameter determining unit calculates and determines the average diameter of the blood vessel through an average diameter value function according to the change of the blood vessel diameter.
The blood vessel edge optimization module comprises a blood vessel diameter determination unit, the blood vessel diameter determination unit calculates and determines the average diameter of the blood vessel through an average diameter value function according to the change of the blood vessel diameter, the average diameter value function is an average diameter similarity function of the blood vessel, and the blood vessel images are fused by adopting the similarity function, so that the accuracy of segmenting the pulmonary blood vessel in the pulmonary mask image is improved, and the effect of segmenting the pulmonary blood vessel in the pulmonary mask image is improved.
Furthermore, the blood vessel segmentation module comprises a first blood vessel segmentation unit and a second blood vessel segmentation unit, the first blood vessel segmentation unit primarily segments different blood vessel parts of the lung through a lung mask image, and the second blood vessel segmentation unit performs optimal processing on the image segmentation after the blood vessel is primarily segmented.
Further, the image acquisition module is provided with an image storage unit, the image storage unit comprises a hard disk drive and a solid-state memory, the solid-state memory stores images of different blood vessel parts of the lung which are segmented preliminarily by the first blood vessel segmentation unit, and the hard disk drive stores images which are segmented by the second blood vessel segmentation unit and then are subjected to optimization processing.
The invention has the advantages that: the pulmonary vessel segmentation device is provided with a calculation module, the calculation module is used for calculating the range of the vessel size in a pulmonary mask image, the image fusion module is used for carrying out image fusion on a plurality of pulmonary mask images, when the pulmonary vessel is filled with blood to display a high-density image on the whole, the separation of the vessel size range is carried out through the calculation module, so that the gray level of the small vessel is uniformly distributed, the gray level of the vessel is obviously compared with the gray level of surrounding tissues, an obvious gray level difference boundary is provided, the accuracy of pulmonary vessel extraction is improved, the vessel edge optimization module is used for carrying out optimization processing of linear function fitting on the edge of the vessel, the gray level difference of the vessel and other tissues such as adjacent bones, ventricular blood and the like in the image is large, and the vessel segmentation image is accurate and clear.
Drawings
Fig. 1 is a block diagram of a pulmonary mask image segmentation device for pulmonary blood vessels.
FIG. 2 is a block diagram of a computing module of an image segmentation pulmonary vessel device.
Fig. 3 is a schematic diagram of a unit of an image acquisition module of an image segmentation pulmonary blood vessel device.
Fig. 4 is a schematic diagram of a blood vessel edge optimization module of an image segmentation pulmonary blood vessel device.
Fig. 5 is a schematic diagram of a unit of an image fusion module of an image segmentation pulmonary vessel device.
Fig. 6 is a schematic diagram of a blood vessel position determining module of an image segmentation pulmonary blood vessel device.
Detailed Description
Aiming at the defects in the prior art, the invention provides a device for segmenting pulmonary blood vessels from a pulmonary mask image, so that the gray level of the tiny blood vessels is uniformly distributed, the gray level of the blood vessels is obviously compared with the gray level of surrounding tissues, the boundary of the obvious gray level difference is formed, the accuracy of pulmonary blood vessel extraction is improved, the gray level difference of the blood vessels and other tissues such as adjacent bones, ventricular blood and the like in the image is large, and the image segmented by the blood vessels is accurate and clear.
In order to solve the technical problems, the invention adopts the following technical scheme:
as an embodiment, as shown in fig. 1, an apparatus for segmenting a pulmonary blood vessel from a pulmonary mask image includes a computing module, an image obtaining module, an image fusion module, a blood vessel segmentation module, a blood vessel position determination module, and a blood vessel edge optimization module; the calculation module is electrically connected with the image acquisition module, the image acquisition module is used for acquiring the image of the lung mask, the calculation module is used for calculating the range of the blood vessel size in the lung mask image, the image acquisition module and the image fusion module are mutually connected by electric signals, the image fusion module is used for carrying out image fusion on a plurality of lung mask images to acquire fused lung fusion images, the image fusion module and the blood vessel segmentation module are in electric signal connection with each other, the blood vessel segmentation module is used for segmenting the position of a blood vessel in the lung fusion image to obtain a blood vessel image, the blood vessel segmentation module and the blood vessel position determination module are in electric signal connection with each other, the blood vessel position determination module is used for determining the position of the blood vessel in the blood vessel image, the blood vessel position determination module and the blood vessel edge optimization module are in electric signal connection with each other, and the blood vessel edge optimization module is used for performing optimization processing of fitting of a linear function on the edge of the blood vessel.
Preferably, the pulmonary blood vessel segmentation device is provided with a calculation module, the calculation module is used for calculating the range of the blood vessel size in the pulmonary mask images, the image fusion module is used for carrying out image fusion on a plurality of pulmonary mask images, when the pulmonary blood vessels are filled with blood to display high-density images on the whole, the blood vessel size range is separated through the calculation module, so that the gray scale of the small blood vessels is uniformly distributed, the gray scale of the blood vessels is obviously compared with the gray scale of surrounding tissues, the boundary of the obvious gray scale difference is formed, the accuracy of pulmonary blood vessel extraction is improved, the blood vessel edge optimization module is used for carrying out optimization processing of linear function fitting on the edges of the blood vessels, the gray scale difference of the blood vessels and other tissues such as adjacent bones, ventricular blood and the like in the images is large, and the blood vessel segmentation images are accurate and clear.
As an embodiment, as shown in fig. 2, the calculating module includes a blood vessel size calculating unit, a change rate calculating unit, a blood flow parameter calculating unit and a blood flow threshold calculating unit, the blood vessel size calculating unit calculates a range of blood vessel sizes in the lung mask image according to response values of the function and calculates response values of the blood vessel similarity function under a plurality of different blood vessel sizes in the lung mask image, the change rate calculating unit calculates diameter change rates of different blood vessel sizes and calculates change rates at different blood vessel segmentation positions, the change rates are expressed by a plurality of mathematical functions, the blood flow parameter calculating unit calculates a blood flow parameter value according to the change rates of the blood vessel sizes and the blood vessel diameters, the blood flow parameter value is calculated from a blood flow velocity value, the blood flow threshold calculating unit calculates a derivative of the function of the blood flow velocity value, and defines a blood flow threshold by the derivative, the plurality of blood vessels results in a plurality of blood flow velocity thresholds.
Preferably, the blood flow threshold calculation unit calculates a derivative of a function of the blood flow velocity values, defines a blood flow threshold by the derivative, obtains a plurality of blood flow velocity thresholds by a plurality of blood vessels, determines different types of blood vessels by setting different blood flow velocity thresholds, defines the thresholds for the different blood vessels, and improves the contrast of the image by defining the thresholds.
As an embodiment, as shown in fig. 3, the image obtaining module includes an image capturing unit configured to obtain an image including blood vessels in a lung mask image, the lung mask image has a plurality of lung mask images, the images of the lung masks are six-sided images, and an image modifying unit configured to modify sizes of the lung mask images.
As an embodiment, as shown in fig. 4, the blood vessel edge optimization module includes an edge detection unit and an edge fitting unit, wherein the edge detection unit detects an edge value of a blood vessel by a difference value of adjacent edge distances on two sides of the blood vessel, and the edge fitting unit performs linear fitting of a quadratic function of the same blood vessel by repeating images.
Preferably, the blood vessel edge optimization module comprises a blood vessel contour fitting unit and a blood vessel diameter determination unit, the blood vessel contour fitting unit adopts a three-dimensional blood vessel contour model to perform fitting processing on the blood vessel edge, and the blood vessel diameter determination unit performs calculation according to the change of the blood vessel diameter through a mean diameter value function to determine the mean diameter of the blood vessel.
Preferably, the blood vessel edge optimization module comprises a blood vessel diameter determination unit, the blood vessel diameter determination unit calculates and determines the average diameter of the blood vessel according to the change of the blood vessel diameter through an average diameter value function, the average diameter value function is an average diameter similarity function of the blood vessel, and the blood vessel images are fused by adopting the similarity function, so that the accuracy of segmenting the pulmonary blood vessel in the pulmonary mask image is improved, and the effect of segmenting the pulmonary blood vessel in the pulmonary mask image is improved.
As an embodiment, as shown in fig. 5, the image fusion module includes an image fusion unit and an image determination unit, the image fusion unit is configured to fuse the plurality of lung mask images to obtain a fused stereo image of the lung mask images, and the image determination unit is configured to determine directions and positions of the plurality of lung mask images.
Preferably, the image fusion unit is used for fusing the lung mask images, the image determination unit is used for determining the directions and the positions of the lung mask images, the lung mask images form multi-view lung blood vessel images, multiple weak and different view images and depth information of the lung blood vessels can be obtained through image fusion in one step, and the directions and the positions of the fused lung mask images are identified and determined through different view angles, so that the accuracy of lung blood vessel identification is improved.
Preferably, the blood vessel segmentation module comprises a blood vessel analysis unit and a blood vessel segmentation unit, the blood vessel analysis unit analyzes and determines the lung mask image stereogram to segment blood vessels from the image, the analysis unit determines the blood vessel parts according to the continuity and the gradient of the blood vessels and fits the blood vessels segmented in different directions and positions, and the blood vessel segmentation unit is used for segmenting and extracting the structure of the blood vessels, extracting the segmented diameters of the blood vessels and extracting the segmented positions of the blood vessels to form the two-dimensional blood vessel image.
As one embodiment, as shown in fig. 6, the blood vessel position determination module is provided with a continuity detection unit that determines a blood vessel position by continuity of a blood vessel, a length detection unit that determines a blood vessel length by continuity of a change in a diameter of the blood vessel, an edge detection unit that determines an edge line of the blood vessel by continuity of an equivalent diameter of a cross section of the blood vessel, and a distance detection unit that determines a distance between the blood vessels by adjacent blood vessel positions of a two-dimensional blood vessel image.
Preferably, the blood vessel segmentation module comprises a first blood vessel segmentation unit and a second blood vessel segmentation unit, the first blood vessel segmentation unit primarily segments different blood vessel parts of the lung through a lung mask image, and the second blood vessel segmentation unit performs optimization processing on image segmentation after the blood vessel is primarily segmented.
Preferably, the image acquisition module is provided with an image storage unit, the image storage unit includes a hard disk drive and a solid-state memory, the solid-state memory stores images of different blood vessel parts of the lung which are initially segmented by the first blood vessel segmentation unit, and the hard disk drive stores images which are optimally processed after segmentation by the second blood vessel segmentation unit.
The invention has the beneficial effects that: the pulmonary vessel segmentation device is provided with a calculation module, the calculation module is used for calculating the range of the vessel size in a pulmonary mask image, the image fusion module is used for carrying out image fusion on a plurality of pulmonary mask images, when the pulmonary vessel is filled with blood to display a high-density image on the whole, the separation of the vessel size range is carried out through the calculation module, so that the gray level of the small vessel is uniformly distributed, the gray level of the vessel is obviously compared with the gray level of surrounding tissues, an obvious gray level difference boundary is provided, the accuracy of pulmonary vessel extraction is improved, the vessel edge optimization module is used for carrying out optimization processing of linear function fitting on the edge of the vessel, the gray level difference of the vessel and other tissues such as adjacent bones, ventricular blood and the like in the image is large, and the vessel segmentation image is accurate and clear.
The blood vessel edge optimization module comprises a blood vessel diameter determination unit, the blood vessel diameter determination unit calculates and determines the average diameter of the blood vessel through an average diameter value function according to the change of the blood vessel diameter, the average diameter value function is an average diameter similarity function of the blood vessel, and the blood vessel images are fused by adopting the similarity function, so that the accuracy of segmenting the pulmonary blood vessel in the pulmonary mask image is improved, and the effect of segmenting the pulmonary blood vessel in the pulmonary mask image is improved.
The blood flow threshold value calculation unit is used for solving a derivative of a function of the blood flow velocity value, the derivative is used for defining the blood flow threshold value, a plurality of blood vessels obtain a plurality of blood flow velocity threshold values, different blood vessels are judged by setting different blood flow velocity threshold values, the threshold values are defined for different blood vessels, and the contrast of an image is improved by defining the threshold values; the image fusion unit is used for fusing the lung mask images, the image determination unit is used for determining the directions and the positions of the lung mask images, the lung mask images form multi-view lung blood vessel images, the images and the depth information of the lung blood vessels at a plurality of weak different views can be obtained through image fusion in one step, the directions and the positions of the fused lung mask images are identified and determined at different views, and therefore the accuracy of lung blood vessel identification is improved.
All patents and publications mentioned in the specification of the invention are indicative of the techniques disclosed in the art to which this invention pertains and are intended to be applicable. All patents and publications cited herein are hereby incorporated by reference to the same extent as if each individual publication was specifically and individually indicated to be incorporated by reference. The invention described herein may be practiced in the absence of any element or elements, limitation or limitations, which limitation or limitations is not specifically disclosed herein. For example, in each of the examples herein the terms "comprising", "consisting essentially of", and "consisting of" may be substituted for the remaining 2 terms of either. The terms and expressions which have been employed herein are used as terms of description and not of limitation, and there is no intention in the use of such terms and expressions of excluding any equivalents of the features shown and described, but it is recognized that various modifications and changes may be made within the scope of the invention and the claims which follow. It is to be understood that the embodiments described herein are preferred embodiments and features and that modifications and variations may be made by one skilled in the art in light of the teachings of this disclosure, and are to be considered within the purview and scope of this invention and the scope of the appended claims and their equivalents.
Claims (10)
1. An apparatus for segmenting pulmonary blood vessels from a mask image of a lung, comprising: the system comprises a calculation module, an image acquisition module, an image fusion module, a blood vessel segmentation module, a blood vessel position determination module and a blood vessel edge optimization module; the calculation module is electrically connected with the image acquisition module, the image acquisition module is used for acquiring the image of the lung mask, the calculation module is used for calculating the range of the blood vessel size in the lung mask image, the image acquisition module and the image fusion module are mutually connected by electric signals, the image fusion module is used for carrying out image fusion on a plurality of lung mask images to acquire fused lung fusion images, the image fusion module and the blood vessel segmentation module are in electric signal connection with each other, the blood vessel segmentation module is used for segmenting the position of a blood vessel in the lung fusion image to obtain a blood vessel image, the blood vessel segmentation module and the blood vessel position determination module are in electric signal connection with each other, the blood vessel position determination module is used for determining the position of the blood vessel in the blood vessel image, the blood vessel position determination module and the blood vessel edge optimization module are in electric signal connection with each other, and the blood vessel edge optimization module is used for performing optimization processing of fitting of a linear function on the edge of the blood vessel.
2. The apparatus of claim 1, wherein the apparatus further comprises: the calculation module comprises a blood vessel size calculation unit, a change rate calculation unit, a blood flow parameter calculation unit and a blood flow threshold calculation unit, the blood vessel size calculation unit calculates the range of the blood vessel size in the lung mask image through the response value of the function, and calculating response values of blood vessel similarity functions under different blood vessel sizes in the lung mask image, calculating diameter change rates of different blood vessel sizes by a change rate calculation unit, calculating change rates at different blood vessel segmentation positions, wherein the change rates are represented by a plurality of mathematical functions, calculating blood flow parameter values by a blood flow parameter calculation unit according to the sizes of the blood vessels and the change rates of the blood vessel diameters, calculating the blood flow parameter values by blood flow velocity values, calculating derivatives of the blood flow velocity value functions by a blood flow threshold calculation unit, defining blood flow thresholds by the derivatives, and obtaining a plurality of blood flow velocity thresholds by a plurality of blood vessels.
3. The apparatus of claim 1, wherein the apparatus further comprises: the image acquisition module comprises an image shooting unit and an image modification unit, wherein the image shooting unit is used for acquiring images containing blood vessels in lung mask images, the number of the lung mask images is multiple, the images of the lung masks are six-sided images, and the image modification unit is used for modifying the sizes of the lung mask images.
4. The apparatus of claim 1, wherein the apparatus further comprises: the image fusion module comprises an image fusion unit and an image determination unit, the image fusion unit is used for fusing the lung mask images to obtain a fused lung mask image stereogram, and the image determination unit is used for determining the directions and the positions of the lung mask images.
5. The apparatus of claim 1, wherein the apparatus further comprises: the blood vessel segmentation module comprises a blood vessel analysis unit and a blood vessel segmentation unit, wherein the blood vessel analysis unit analyzes and determines the lung mask image stereogram to enable blood vessels to be segmented from the image, the analysis unit determines the positions of the blood vessels through the continuity and the gradual change of the blood vessels and fits the blood vessels segmented in different directions and positions, and the blood vessel segmentation unit is used for segmenting and extracting the structure of the blood vessels, extracting the segmented diameters of the blood vessels and extracting the segmented positions of the blood vessels to form a two-dimensional blood vessel image.
6. The apparatus of claim 1, wherein the apparatus further comprises: the blood vessel position determining module is provided with a continuity detecting unit, a length detecting unit, an edge detecting unit and a distance detecting unit, wherein the continuity detecting unit determines the position of a blood vessel through the continuity of the blood vessel, the length detecting unit determines the length of the blood vessel through the continuity of the diameter change of the blood vessel, the edge detecting unit determines the edge line of the blood vessel through the continuity of the equivalent diameter of the cross section of the blood vessel, and the distance detecting unit determines the distance between the blood vessels through the adjacent blood vessel positions of the two-dimensional blood vessel image.
7. The apparatus of claim 1, wherein the apparatus further comprises: the blood vessel edge optimization module comprises an edge detection unit and an edge fitting unit, wherein the edge detection unit detects the edge value of a blood vessel through the difference value of the adjacent edge distances at two sides of the blood vessel, and the edge fitting unit performs linear fitting on a quadratic function of the same blood vessel through repeated images.
8. The apparatus of claim 1, wherein the apparatus further comprises: the blood vessel edge optimization module comprises a blood vessel contour fitting unit and a blood vessel diameter determining unit, wherein the blood vessel contour fitting unit adopts a three-dimensional blood vessel contour model to perform fitting processing on the blood vessel edge, and the blood vessel diameter determining unit calculates and determines the average diameter of the blood vessel through an average diameter value function according to the change of the blood vessel diameter.
9. The apparatus of claim 1, wherein the apparatus further comprises: the blood vessel segmentation module comprises a first blood vessel segmentation unit and a second blood vessel segmentation unit, the first blood vessel segmentation unit initially segments different blood vessel parts of the lung through a lung mask image, and the second blood vessel segmentation unit performs optimal processing on the image after the blood vessel is initially segmented.
10. The apparatus of claim 1, wherein the apparatus further comprises: the image acquisition module is provided with an image storage unit, the image storage unit comprises a hard disk drive and a solid-state memory, the solid-state memory stores images of different blood vessel parts of the lung which are initially segmented by the first blood vessel segmentation unit, and the hard disk drive stores images which are optimally processed after being segmented by the second blood vessel segmentation unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110848452.5A CN113570570A (en) | 2021-07-27 | 2021-07-27 | Device for segmenting pulmonary blood vessels from pulmonary mask image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110848452.5A CN113570570A (en) | 2021-07-27 | 2021-07-27 | Device for segmenting pulmonary blood vessels from pulmonary mask image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113570570A true CN113570570A (en) | 2021-10-29 |
Family
ID=78167750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110848452.5A Pending CN113570570A (en) | 2021-07-27 | 2021-07-27 | Device for segmenting pulmonary blood vessels from pulmonary mask image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113570570A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116071355A (en) * | 2023-03-06 | 2023-05-05 | 山东第一医科大学第二附属医院 | Auxiliary segmentation system and method for peripheral blood vessel image |
-
2021
- 2021-07-27 CN CN202110848452.5A patent/CN113570570A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116071355A (en) * | 2023-03-06 | 2023-05-05 | 山东第一医科大学第二附属医院 | Auxiliary segmentation system and method for peripheral blood vessel image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11783498B2 (en) | Feature-based registration method | |
| CN107563998B (en) | Method for processing heart image in medical image | |
| CN110338840B (en) | Three-dimensional imaging data display processing method and three-dimensional ultrasonic imaging method and system | |
| US11986252B2 (en) | ENT image registration | |
| KR101967357B1 (en) | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery | |
| EP2827301B1 (en) | Image generation device, method, and program | |
| CA2986590C (en) | Surface modeling of a segmented echogenic structure for detection and measurement of anatomical anomalies | |
| US7480401B2 (en) | Method for local surface smoothing with application to chest wall nodule segmentation in lung CT data | |
| CN111374712B (en) | Ultrasonic imaging method and ultrasonic imaging equipment | |
| KR20090098839A (en) | Medical imaging system | |
| CN111311626A (en) | Skull fracture automatic detection method based on CT image and electronic medium | |
| EP3047455B1 (en) | Method and system for spine position detection | |
| KR101251822B1 (en) | System and method for analysising perfusion in dynamic contrast-enhanced lung computed tomography images | |
| CN113570570A (en) | Device for segmenting pulmonary blood vessels from pulmonary mask image | |
| CN111369537A (en) | Automatic segmentation system and method for pulmonary milled glass nodules | |
| CN107961023B (en) | ENT image registration | |
| CN110533667B (en) | Lung tumor CT image 3D segmentation method based on image pyramid fusion | |
| JP4681358B2 (en) | Ultrasonic diagnostic apparatus and volume data processing method | |
| EP3624058A1 (en) | Method and system of analyzing symmetry from image data | |
| US20200305837A1 (en) | System and method for guided ultrasound imaging | |
| Schwing et al. | Reliable extraction of the mid-sagittal plane in 3D brain MRI via hierarchical landmark detection | |
| CN111862014A (en) | ALVI automatic measurement method and device based on left and right ventricle segmentation | |
| Ng et al. | Salient features useful for the accurate segmentation of masticatory muscles from minimum slices subsets of magnetic resonance images | |
| WO2019245506A2 (en) | A method and an algorithm to conduct a safe biopsy on lung airways | |
| CN113222886B (en) | Jugular fossa and sigmoid sinus groove positioning method and intelligent temporal bone image processing system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211029 |