CN111539917B - Blood vessel segmentation method, system, terminal and storage medium based on coarse-fine granularity fusion - Google Patents
Blood vessel segmentation method, system, terminal and storage medium based on coarse-fine granularity fusion Download PDFInfo
- Publication number
- CN111539917B CN111539917B CN202010272913.4A CN202010272913A CN111539917B CN 111539917 B CN111539917 B CN 111539917B CN 202010272913 A CN202010272913 A CN 202010272913A CN 111539917 B CN111539917 B CN 111539917B
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- region
- segmentation result
- fine
- vessel segmentation
- 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
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
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The application provides a blood vessel segmentation method, a system, a terminal and a storage medium based on coarse-fine granularity fusion, wherein the method comprises the following steps: acquiring a medical image, and performing blood vessel coarse-fine granularity segmentation to obtain a rough blood vessel segmentation result and a fine blood vessel segmentation result; determining a potential vessel fracture region according to the rough vessel segmentation result and the fine vessel segmentation result; determining a non-vascular rupture zone of the potential vascular rupture zones and removing the non-vascular rupture zone from the potential vascular rupture zone to yield a preserved vascular rupture zone; fusing the reserved blood vessel fracture area with the fine blood vessel segmentation result to repair the blood vessel fracture area in the fine blood vessel segmentation result, and obtaining a final blood vessel segmentation result; the application fuses the coarse and fine granularity segmentation results, repairs the blood vessel fracture region in the fine blood vessel segmentation by using the coarse blood vessel segmentation result, simultaneously avoids introducing redundant noise in the coarse blood vessel segmentation result, improves the blood vessel segmentation effect and ensures the blood vessel connectivity.
Description
Technical Field
The application belongs to the technical field of medical images and computer assistance, and particularly relates to a blood vessel segmentation method, a blood vessel segmentation system, a blood vessel segmentation terminal and a blood vessel segmentation storage medium based on coarse-fine granularity fusion.
Background
Cerebral stroke, also known as cerebrovascular accident, is a disease of impaired cerebral blood circulation, with mortality inferior to heart-like diseases and higher than that of cancer. At present, the incidence and death rate of cerebral apoplexy in China still have an ascending trend, and the death rate of the elderly suffering from cerebral apoplexy is doubled compared with that of the young people. Cerebral stroke is also classified into ischemic and hemorrhagic cerebral stroke, with ischemic cerebral stroke accounting for about 80%. One of the main causes of ischemic stroke is that the vulnerable plaque of head and neck atherosclerosis causes lumen stenosis and hemodynamic changes, and the carotid artery, which is the upstream blood vessel of the intracranial artery, is the main blood supply artery of the brain circulation. Therefore, head and neck vessel segmentation by head and neck arterial angiography (CTA) has important implications for timely risk discovery.
In modern medical image analysis, segmentation of blood vessels from raw medical image images is an important basis for various pathological analyses. The method for segmenting the blood vessel based on the deep learning model is a current mainstream method, and compared with the traditional blood vessel segmentation method, the method is good in effect and robust in performance. However, the existing blood vessel segmentation methods generally have the condition of blood vessel segmentation fracture, and the blood vessel segmentation fracture seriously affects the post-treatment effect and pathological analysis.
Therefore, there is a need for a blood vessel segmentation method, system, terminal and storage medium based on coarse-fine granularity fusion, which can effectively reduce the blood vessel segmentation fracture condition and improve the blood vessel segmentation effect.
Disclosure of Invention
Aiming at the defects of the prior art, the application provides a blood vessel segmentation method, a blood vessel segmentation system, a blood vessel segmentation terminal and a blood vessel storage medium based on coarse-fine granularity fusion, which solve the problems that the blood vessel segmentation is broken in the blood vessel segmentation method in the prior art, and the post-treatment effect and pathological analysis are seriously influenced.
In order to solve the above technical problems, in a first aspect, the present application provides a blood vessel segmentation method based on coarse-fine granularity fusion, including:
acquiring a medical image, and performing blood vessel coarse-fine granularity segmentation to obtain a rough blood vessel segmentation result and a fine blood vessel segmentation result;
determining a potential vessel fracture region according to the rough vessel segmentation result and the fine vessel segmentation result;
determining a non-vascular rupture zone of the potential vascular rupture zones and removing the non-vascular rupture zone from the potential vascular rupture zone to yield a preserved vascular rupture zone;
and fusing the reserved blood vessel fracture area with the fine blood vessel segmentation result to repair the blood vessel fracture area in the fine blood vessel segmentation result, so as to obtain a final blood vessel segmentation result.
Optionally, the obtaining the medical image map, and performing the coarse-fine granularity segmentation on the medical image map to obtain a coarse blood vessel segmentation result and a fine blood vessel segmentation result, includes:
acquiring a medical image;
and performing blood vessel segmentation on the same medical image by training two deep learning models with different segmentation precision or adopting different segmentation thresholds, and obtaining a rough blood vessel segmentation result and a fine blood vessel segmentation result of the medical image.
Optionally, the determining the potential vascular fracture region according to the rough vascular segmentation result and the fine vascular segmentation result includes:
making a difference between the rough blood vessel segmentation result and the fine blood vessel segmentation result, and setting voxels with the difference less than zero to be zero to obtain redundant blood vessel parts in the rough blood vessel segmentation result;
and (3) carrying out connected domain analysis on redundant blood vessel parts in the rough blood vessel segmentation result, and dividing voxel points which are mutually connected into the same region to form a plurality of potential blood vessel fracture regions.
Optionally, the determining a non-vascular rupture zone of the potential vascular rupture zone and removing the non-vascular rupture zone from the potential vascular rupture zone results in a reserved vascular rupture zone, comprising:
determining a non-vascular rupture zone of the potential vascular rupture zones;
removing the non-vascular rupture zone from the potential vascular rupture zone to yield a preserved vascular rupture zone;
wherein the non-vascular rupture zone comprises: small area vascular noise, vascular wall area, distal redundant branch vascular area, and adherent vascular branches.
Optionally, the method for determining the vascular noise in the small area includes:
acquiring the number of voxels of each region of the potential vessel fracture region;
and judging whether the number of voxels of the region is smaller than a preset number, if so, judging that the region is small-region vascular noise.
Optionally, the method for determining a wall area of a blood vessel includes:
acquiring the total number of voxel points of each region of the potential blood vessel fracture region;
judging whether each voxel point in each region of the blood vessel fracture region has adjacent blood vessel voxels in the fine blood vessel segmentation result, if so, acquiring the number of voxel points with adjacent blood vessel voxels in the region;
calculating the ratio of the number of voxel points with adjacent blood vessel voxels in the region to the total number of voxel points in the region;
judging whether the voxel point duty ratio of the region exceeds a preset threshold value, if so, judging that the region is a blood vessel wall region.
Optionally, the method for determining the redundant branch vessel area at the tail end includes:
acquiring voxel points with adjacent vessel voxels in each of the vessel fracture regions;
and judging whether the voxel points of the region belong to the same connected region or not, if so, judging that the connected region is the only adjacent surface of the branch of the end blood vessel and the fine blood vessel, and judging that the region is the redundant branch blood vessel region of the end.
Optionally, the method for determining the adhered vascular branches comprises the following steps:
acquiring voxel points with adjacent vessel voxels in each of the vessel fracture regions;
acquiring a blood vessel voxel point adjacent to a voxel point in a blood vessel fracture region in a fine blood vessel segmentation result;
and judging whether voxel points in the fine blood vessel segmentation result only belong to the same connected region, if so, judging that the blood vessel branch is connected with the mutually connected region in the fine blood vessel segmentation, namely, two ends of a U-shaped blood vessel or a plurality of adjacent blood vessels, and judging that the region is the adhered blood vessel branch.
Optionally, the fusing the reserved vascular fracture region with the fine vascular segmentation result to repair the vascular fracture region in the fine vascular segmentation result to obtain a final vascular segmentation result includes:
and merging the fine blood vessel segmentation result with the reserved blood vessel fracture region to obtain a final blood vessel segmentation result.
In a second aspect, the present application also provides a vessel segmentation system based on coarse-fine granularity fusion, including:
a segmentation unit configured to acquire a medical image, and segment the medical image in a blood vessel coarse-fine granularity to obtain a rough blood vessel segmentation result and a fine blood vessel segmentation result;
a determination unit configured to determine a potential vessel-rupture region from the rough vessel-segmentation result and the fine vessel-segmentation result;
a removal unit configured to determine a non-vascular rupture zone of the potential vascular rupture zones and remove the non-vascular rupture zone from the potential vascular rupture zone resulting in a reserved vascular rupture zone;
and the fusion unit is configured to fuse the reserved blood vessel fracture region with the fine blood vessel segmentation result to repair the blood vessel fracture region in the fine blood vessel segmentation result, so as to obtain a final blood vessel segmentation result.
Optionally, the acquiring unit is specifically configured to:
acquiring a medical image;
and performing blood vessel segmentation on the same medical image by training two deep learning models with different segmentation precision or adopting different segmentation thresholds, and obtaining a rough blood vessel segmentation result and a fine blood vessel segmentation result of the medical image.
Optionally, the determining unit is specifically configured to:
making a difference between the rough blood vessel segmentation result and the fine blood vessel segmentation result, and setting voxels with the difference less than zero to be zero to obtain redundant blood vessel parts in the rough blood vessel segmentation result;
and (3) carrying out connected domain analysis on redundant blood vessel parts in the rough blood vessel segmentation result, and dividing voxel points which are mutually connected into the same region to form a plurality of potential blood vessel fracture regions.
Optionally, the removing unit is specifically configured to:
determining a non-vascular rupture zone of the potential vascular rupture zones;
removing the non-vascular rupture zone from the potential vascular rupture zone to yield a preserved vascular rupture zone;
wherein the non-vascular rupture zone comprises: small area vascular noise, vascular wall area, distal redundant branch vascular area, and adherent vascular branches.
Optionally, the fusion unit is specifically configured to:
and merging the fine blood vessel segmentation result with the reserved blood vessel fracture region to obtain a final blood vessel segmentation result.
In a third aspect, the present application provides a terminal comprising:
a processor, a memory, wherein,
the memory is used for storing a computer program,
the processor is configured to call and run the computer program from the memory, so that the terminal performs the method of the terminal as described above.
In a fourth aspect, the present application provides a computer storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the method of the above aspects.
Compared with the prior art, the application has the following beneficial effects:
the application fuses the rough and fine granularity segmentation results, repairs the blood vessel fracture region in the fine blood vessel segmentation by using the rough blood vessel segmentation result, avoids introducing redundant noise in the rough blood vessel segmentation result, improves the blood vessel segmentation effect and ensures the connectivity of blood vessels.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a blood vessel segmentation method based on coarse-fine granularity fusion according to an embodiment of the present application;
FIG. 2 is a flow chart of a blood vessel coarse-fine granularity segmentation provided by an embodiment of the present application;
FIG. 3 is a flow chart of determining potential vascular rupture zones provided by an embodiment of the present application;
FIG. 4 is a flow chart of removing non-vascular rupture zones from potential vascular rupture zones provided by an embodiment of the present application;
FIG. 5 is a flow chart of the fusion of a region of a vessel-reserved fracture with a result of a fine vessel segmentation according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a blood vessel segmentation system based on coarse-fine granularity fusion according to another embodiment of the present application;
fig. 7 is a schematic structural diagram of a terminal system according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, fig. 1 is a flowchart of a blood vessel segmentation method based on coarse-fine granularity fusion according to an embodiment of the present application, and the method 100 includes:
s101: acquiring a medical image, and performing blood vessel coarse-fine granularity segmentation to obtain a rough blood vessel segmentation result and a fine blood vessel segmentation result;
s102: determining a potential vessel fracture region according to the rough vessel segmentation result and the fine vessel segmentation result;
s103: determining a non-vascular rupture zone of the potential vascular rupture zones and removing the non-vascular rupture zone from the potential vascular rupture zone to yield a preserved vascular rupture zone;
s104: and fusing the reserved blood vessel fracture area with the fine blood vessel segmentation result to repair the blood vessel fracture area in the fine blood vessel segmentation result, so as to obtain a final blood vessel segmentation result.
It should be noted that, in the conventional blood vessel segmentation method based on a single deep learning model or segmentation threshold, it is difficult to balance the blood vessel segmentation accuracy and the connectivity of the blood vessel, and the segmentation result is often not ideal. Although the fine blood vessel segmentation results are generally excellent in segmentation accuracy, there are cases where the blood vessel is likely to be broken. The rough blood vessel segmentation result has better blood vessel connectivity, but contains more extra noise such as end blood vessel branches, adhesion blood vessel branches and the like. Therefore, the application fuses the coarse and fine granularity segmentation results, repairs the blood vessel fracture region in the fine blood vessel segmentation by using the coarse blood vessel segmentation result, simultaneously avoids introducing redundant noise in the coarse blood vessel segmentation result, improves the blood vessel segmentation effect and ensures the connectivity of blood vessels.
Based on the foregoing embodiments, as an optional embodiment, the step S101 of obtaining a medical image and performing coarse-fine granularity segmentation on the medical image to obtain a coarse blood vessel segmentation result and a fine blood vessel segmentation result includes:
acquiring a medical image;
and performing blood vessel segmentation on the same medical image by training two deep learning models with different segmentation precision or adopting different segmentation thresholds, and obtaining a rough blood vessel segmentation result and a fine blood vessel segmentation result of the medical image.
Specifically, as shown in fig. 2, fig. 2 is a flowchart of blood vessel thickness granularity segmentation according to an embodiment of the present application. After the medical image is acquired, the same medical image can be subjected to blood vessel segmentation by training two deep learning models with different segmentation precision, namely a high-precision segmentation model and a low-precision segmentation model, so as to respectively obtain a fine blood vessel segmentation result and a rough blood vessel segmentation result. After the medical image is acquired, the same medical image can be subjected to blood vessel segmentation by setting different segmentation thresholds and respectively adopting a high segmentation threshold and a low segmentation threshold to obtain a fine blood vessel segmentation result and a rough blood vessel segmentation result.
Based on the above embodiment, as an optional embodiment, the determining, at S102, a potential blood vessel fracture region according to the rough blood vessel segmentation result and the fine blood vessel segmentation result includes:
making a difference between the rough blood vessel segmentation result and the fine blood vessel segmentation result, and setting voxels with the difference less than zero to be zero to obtain redundant blood vessel parts in the rough blood vessel segmentation result;
and (3) carrying out connected domain analysis on redundant blood vessel parts in the rough blood vessel segmentation result, and dividing voxel points which are mutually connected into the same region to form a plurality of potential blood vessel fracture regions.
Specifically, as shown in fig. 3, fig. 3 is a flowchart for determining a potential vascular rupture zone according to an embodiment of the present application. The application regards the blood vessel regions which only appear in the rough blood vessel segmentation result but not in the fine blood vessel segmentation result as the potential blood vessel fracture regions, can obtain the redundant blood vessel parts in the rough blood vessel segmentation result by differencing the rough blood vessel segmentation result and the fine blood vessel segmentation result, carries out connected domain analysis on the redundant blood vessel parts in the rough blood vessel segmentation result, divides the voxel points which are mutually connected into the same region, and can form a plurality of potential blood vessel fracture regions.
Based on the above embodiment, as an alternative embodiment, the step S103 of determining a non-vascular rupture zone of the potential vascular rupture zones and removing the non-vascular rupture zone from the potential vascular rupture zone to obtain a reserved vascular rupture zone includes:
determining a non-vascular rupture zone of the potential vascular rupture zones;
removing the non-vascular rupture zone from the potential vascular rupture zone to yield a preserved vascular rupture zone;
wherein the non-vascular rupture zone comprises: small area vascular noise, vascular wall area, distal redundant branch vascular area, and adherent vascular branches.
Specifically, as shown in fig. 4, fig. 4 is a flowchart illustrating removal of a non-vascular rupture zone from a potential vascular rupture zone according to an embodiment of the present application. Since the non-vascular rupture zone includes: and after the small-area vascular noise, the vascular wall area, the end redundant branch vascular area, the adhered vascular branches and the like are judged, the small-area vascular noise, the vascular wall area, the end redundant branch vascular area and the adhered vascular branches are removed from the potential vascular fracture area respectively, so that the reserved vascular fracture area can be obtained. The method for judging the vascular noise in the small region, the vascular wall region, the redundant branch vascular region at the tail end and the adhered vascular branch comprises the following steps:
small area vascular noise determination: because of the potential vascular fracture area obtained directly by the differential method, more scattered noise is obtained, namely small-area vascular noise. The method utilizes all the obtained potential blood vessel fracture areas to obtain the number of voxels of each area of the potential blood vessel fracture areas; and judging whether the number of voxels of the region is smaller than a preset number, if so, judging that the region is small-region vascular noise.
Determination of a vascular wall region: the blood vessels in the rough blood vessel segmentation result are usually thicker than those in the fine blood vessel segmentation result, so that more hollow blood vessel areas exist after the difference, namely blood vessel wall areas. The method utilizes all the obtained potential blood vessel fracture areas to obtain the total number of voxel points of each area of the potential blood vessel fracture areas; judging whether each voxel point in each region of the blood vessel fracture region has adjacent blood vessel voxels in the fine blood vessel segmentation result, if so, acquiring the number of voxel points with adjacent blood vessel voxels in the region; calculating the ratio of the number of voxel points with adjacent blood vessel voxels in the region to the total number of voxel points in the region; judging whether the voxel point duty ratio of the region exceeds a preset threshold value, if so, judging that the region is a blood vessel wall region.
Judging the region of the redundant branch blood vessel at the tail end: compared to the fine vessel segmentation result, the vessel in the rough vessel segmentation result typically has a number of redundant elongated branches introduced at its vessel end, i.e. the end redundant branch vessel. The method utilizes all the obtained potential blood vessel fracture areas to obtain voxel points with adjacent blood vessel voxels in each of the blood vessel fracture areas; and judging whether the voxel points of the region belong to the same connected region or not, if so, judging that the connected region is the only adjacent surface of the branch of the end blood vessel and the fine blood vessel, and judging that the region is the redundant branch blood vessel region of the end.
And (3) judging the vascular branching of adhesion: there is also a special class of vessel branches in the rough vessel segmentation result that just connect the two ends of the "U" shaped vessel or multiple adjacent vessels in the fine vessel segmentation result. The special structure is that a plurality of adjacent surfaces are just arranged with the fine blood vessel, and the special blood vessel branch is the adhesion blood vessel branch. The method utilizes all the obtained potential blood vessel fracture areas to obtain voxel points with adjacent blood vessel voxels in each of the blood vessel fracture areas; acquiring a blood vessel voxel point adjacent to a voxel point in a blood vessel fracture region in a fine blood vessel segmentation result; and judging whether voxel points in the fine blood vessel segmentation result only belong to the same connected region, if so, judging that the blood vessel branch is connected with the mutually connected region in the fine blood vessel segmentation, namely, two ends of a U-shaped blood vessel or a plurality of adjacent blood vessels, and judging that the region is the adhered blood vessel branch.
Based on the above embodiment, as an optional embodiment, the step S104 of fusing the reserved blood vessel fracture region with the fine blood vessel segmentation result to repair the blood vessel fracture region in the fine blood vessel segmentation result, to obtain a final blood vessel segmentation result, includes:
and merging the fine blood vessel segmentation result with the reserved blood vessel fracture region to obtain a final blood vessel segmentation result.
Specifically, as shown in fig. 5, fig. 5 is a flowchart of fusion of a reserved vascular fracture region and a fine vascular segmentation result according to an embodiment of the present application. And merging the fine blood vessel segmentation result with all the reserved blood vessel segmentation areas, namely directly fusing the reserved blood vessel segmentation areas with the fine blood vessel segmentation result to repair the blood vessel segmentation areas in the fine blood vessel segmentation, so as to obtain a final blood vessel segmentation result, and ensuring the connectivity of the final blood vessel segmentation result.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a blood vessel segmentation system based on coarse-fine granularity fusion according to an embodiment of the present application, the system 600 includes:
a segmentation unit 601 configured to acquire a medical image map, and perform a blood vessel coarse-fine granularity segmentation on the medical image map to obtain a coarse blood vessel segmentation result and a fine blood vessel segmentation result;
a determining unit 602 configured to determine a potential vessel-rupture region from the rough vessel-segmentation result and the fine vessel-segmentation result;
a removal unit 603 configured to determine a non-vascular rupture zone of the potential vascular rupture zones and remove the non-vascular rupture zone from the potential vascular rupture zone resulting in a reserved vascular rupture zone;
and a fusion unit 604 configured to fuse the reserved vascular fracture region with the fine vascular segmentation result to repair the vascular fracture region in the fine vascular segmentation result, and obtain a final vascular segmentation result.
Based on the above embodiments, as an optional embodiment, the obtaining unit 601 is specifically configured to:
acquiring a medical image;
and performing blood vessel segmentation on the same medical image by training two deep learning models with different segmentation precision or adopting different segmentation thresholds, and obtaining a rough blood vessel segmentation result and a fine blood vessel segmentation result of the medical image.
Based on the above embodiments, as an optional embodiment, the determining unit 602 is specifically configured to:
making a difference between the rough blood vessel segmentation result and the fine blood vessel segmentation result, and setting voxels with the difference less than zero to be zero to obtain redundant blood vessel parts in the rough blood vessel segmentation result;
and (3) carrying out connected domain analysis on redundant blood vessel parts in the rough blood vessel segmentation result, and dividing voxel points which are mutually connected into the same region to form a plurality of potential blood vessel fracture regions.
Based on the above embodiments, as an optional embodiment, the removing unit 603 is specifically configured to:
determining a non-vascular rupture zone of the potential vascular rupture zones;
removing the non-vascular rupture zone from the potential vascular rupture zone to yield a preserved vascular rupture zone;
wherein the non-vascular rupture zone comprises: small area vascular noise, vascular wall area, distal redundant branch vascular area, and adherent vascular branches.
Based on the above embodiments, as an optional embodiment, the fusion unit 604 is specifically configured to:
and merging the fine blood vessel segmentation result with the reserved blood vessel fracture region to obtain a final blood vessel segmentation result.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a terminal system 700 according to an embodiment of the present application, and the terminal system 700 may be used to execute the method for displaying multiple languages and switching input synchronization according to the embodiment of the present application.
The terminal system 700 may include: a processor 701, a memory 702 and a communication unit 703. The components may communicate via one or more buses, and it will be appreciated by those skilled in the art that the configuration of the server as shown in the drawings is not limiting of the application, as it may be a bus-like structure, a star-like structure, or include more or fewer components than shown, or may be a combination of certain components or a different arrangement of components.
The memory 702 may be used to store instructions for execution by the processor 701, and the memory 702 may be implemented by any type of volatile or non-volatile memory terminal or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. The execution of the instructions in memory 702, when executed by processor 701, enables terminal system 700 to perform some or all of the steps in the method embodiments described below.
The processor 701 is a control center of the storage terminal, connects various parts of the entire electronic terminal using various interfaces and lines, and performs various functions of the electronic terminal and/or processes data by running or executing software programs and/or modules stored in the memory 702, and invoking data stored in the memory. The processor may be comprised of an integrated circuit (Integrated Circuit, simply referred to as an IC), for example, a single packaged IC, or may be comprised of a plurality of packaged ICs connected to the same function or different functions. For example, the processor 701 may include only a central processing unit (Central Processing Unit, simply CPU). In the embodiment of the application, the CPU can be a single operation core or can comprise multiple operation cores.
A communication unit 703 for establishing a communication channel so that the storage terminal can communicate with other terminals. Receiving user data sent by other terminals or sending the user data to other terminals.
The present application also provides a computer storage medium in which a program may be stored, which program may include some or all of the steps in the embodiments provided by the present application when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random-access memory (random access memory, RAM), or the like.
According to the application, by fusing the coarse and fine granularity segmentation results, the blood vessel fracture region in the fine blood vessel segmentation is repaired by utilizing the coarse blood vessel segmentation result, meanwhile, redundant noise in the coarse blood vessel segmentation result is avoided being introduced, the blood vessel segmentation effect is improved, and the connectivity of blood vessels is ensured.
In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. The system provided by the embodiment is relatively simple to describe as it corresponds to the method provided by the embodiment, and the relevant points are referred to in the description of the method section.
The principles and embodiments of the present application have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present application and its core ideas. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the application can be made without departing from the principles of the application and these modifications and adaptations are intended to be within the scope of the application as defined in the following claims.
It should also be noted that in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. A blood vessel segmentation method based on coarse-fine granularity fusion is characterized by comprising the following steps:
acquiring a medical image, and performing blood vessel coarse-fine granularity segmentation to obtain a rough blood vessel segmentation result and a fine blood vessel segmentation result;
making a difference between the rough blood vessel segmentation result and the fine blood vessel segmentation result, and setting voxels with the difference less than zero to be zero to obtain redundant blood vessel parts in the rough blood vessel segmentation result;
carrying out connected domain analysis on redundant blood vessel parts in rough blood vessel segmentation results, dividing mutually connected voxel points into the same region, and forming a plurality of potential blood vessel fracture regions
Determining a non-vascular rupture zone of the potential vascular rupture zones and removing the non-vascular rupture zone from the potential vascular rupture zone to yield a preserved vascular rupture zone;
and merging the reserved blood vessel fracture area with the fine blood vessel segmentation result to repair the blood vessel fracture area in the fine blood vessel segmentation result, so as to obtain a final blood vessel segmentation result.
2. The method for segmenting blood vessels based on coarse-fine granularity fusion according to claim 1, wherein the step of obtaining a medical image and segmenting the medical image into coarse blood vessels and fine blood vessels comprises the steps of:
acquiring a medical image;
and performing blood vessel segmentation on the same medical image by training two deep learning models with different segmentation precision or adopting different segmentation thresholds, and obtaining a rough blood vessel segmentation result and a fine blood vessel segmentation result of the medical image.
3. The coarse-fine granularity fusion-based vessel segmentation method as set forth in claim 1, wherein the determining a non-vessel-fractured region of the potential vessel-fractured regions and removing the non-vessel-fractured region from the potential vessel-fractured region results in a preserved vessel-fractured region comprises:
determining a non-vascular rupture zone of the potential vascular rupture zones;
removing the non-vascular rupture zone from the potential vascular rupture zone to yield a preserved vascular rupture zone;
wherein the non-vascular rupture zone comprises: small area vascular noise, vascular wall area, distal redundant branch vascular area, and adherent vascular branches.
4. The blood vessel segmentation method based on coarse-fine granularity fusion according to claim 3, wherein the small-area blood vessel noise determination method comprises the following steps:
acquiring the number of voxels of each region of the potential vessel fracture region;
and judging whether the number of voxels of the region is smaller than a preset number, if so, judging that the region is small-region vascular noise.
5. A blood vessel segmentation method based on coarse-fine granularity fusion according to claim 3, wherein the determination method of the blood vessel wall region comprises:
acquiring the total number of voxel points of each region of the potential blood vessel fracture region;
judging whether each voxel point in each region of the potential blood vessel fracture region has adjacent blood vessel voxels in the fine blood vessel segmentation result, if so, acquiring the number of voxel points with adjacent blood vessel voxels in the region;
calculating the ratio of the number of voxel points with adjacent blood vessel voxels in the region to the total number of voxel points in the region;
judging whether the voxel point duty ratio of the region exceeds a preset threshold value, if so, judging that the region is a blood vessel wall region.
6. The blood vessel segmentation method based on coarse-fine granularity fusion according to claim 3, wherein the determination method of the terminal redundant branch blood vessel region comprises the following steps:
acquiring voxel points with adjacent vessel voxels in each region of the potential vessel fracture region;
and judging whether the voxel points of the region belong to the same connected region or not, if so, judging that the connected region is the only adjacent surface of the branch of the end blood vessel and the fine blood vessel, and judging that the region is the redundant branch blood vessel region of the end.
7. The blood vessel segmentation method based on coarse-fine granularity fusion according to claim 3, wherein the method for judging the adhered blood vessel branches comprises the following steps:
acquiring voxel points with adjacent vessel voxels in each region of the potential vessel fracture region;
acquiring a blood vessel voxel point adjacent to a voxel point in a potential blood vessel fracture region in a fine blood vessel segmentation result;
and judging whether voxel points in the fine blood vessel segmentation result only belong to the same connected region, if so, judging that the blood vessel branch is connected with the mutually connected region in the fine blood vessel segmentation, namely, two ends of a U-shaped blood vessel or a plurality of adjacent blood vessels, and judging that the region is the adhered blood vessel branch.
8. A vessel segmentation system based on coarse-fine granularity fusion, comprising:
a segmentation unit configured to acquire a medical image, and segment the medical image in a blood vessel coarse-fine granularity to obtain a rough blood vessel segmentation result and a fine blood vessel segmentation result;
a determining unit configured to make a difference between the rough blood vessel segmentation result and the fine blood vessel segmentation result and set a voxel with a difference less than zero to zero, so as to obtain an unnecessary blood vessel part in the rough blood vessel segmentation result; carrying out connected domain analysis on redundant blood vessel parts in the rough blood vessel segmentation result, dividing voxel points which are mutually communicated into the same region, and forming a plurality of potential blood vessel fracture regions;
a removal unit configured to determine a non-vascular rupture zone of the potential vascular rupture zones and remove the non-vascular rupture zone from the potential vascular rupture zone resulting in a reserved vascular rupture zone;
and the fusion unit is configured to merge and collect the reserved blood vessel fracture area with the fine blood vessel segmentation result to repair the blood vessel fracture area in the fine blood vessel segmentation result, so as to obtain a final blood vessel segmentation result.
9. A terminal, comprising:
a processor;
a memory for storing execution instructions of the processor;
wherein the processor is configured to perform the method of any of claims 1-7.
10. A computer readable storage medium storing a computer program, which when executed by a processor implements the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010272913.4A CN111539917B (en) | 2020-04-09 | 2020-04-09 | Blood vessel segmentation method, system, terminal and storage medium based on coarse-fine granularity fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010272913.4A CN111539917B (en) | 2020-04-09 | 2020-04-09 | Blood vessel segmentation method, system, terminal and storage medium based on coarse-fine granularity fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111539917A CN111539917A (en) | 2020-08-14 |
| CN111539917B true CN111539917B (en) | 2023-08-25 |
Family
ID=71977152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010272913.4A Active CN111539917B (en) | 2020-04-09 | 2020-04-09 | Blood vessel segmentation method, system, terminal and storage medium based on coarse-fine granularity fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111539917B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005998A (en) * | 2015-08-05 | 2015-10-28 | 大连理工大学 | Cerebrovascular image segmentation method based on multi-angle serialized image space feature point set |
| CN106097378A (en) * | 2016-07-24 | 2016-11-09 | 江西理工大学 | A kind of level set retinal vascular images dividing method merging shape prior |
| CN106875375A (en) * | 2016-12-28 | 2017-06-20 | 浙江工业大学 | Three-dimensional blood vessel axis detection method based on tubulose feature enhancing filtering and ridge line tracking |
| CN108109159A (en) * | 2017-12-21 | 2018-06-01 | 东北大学 | It is a kind of to increase the retinal vessel segmenting system being combined based on hessian matrixes and region |
| CN108198184A (en) * | 2018-01-09 | 2018-06-22 | 北京理工大学 | The method and system of contrastographic picture medium vessels segmentation |
| CN108428210A (en) * | 2017-02-15 | 2018-08-21 | 浙江京新术派医疗科技有限公司 | Blood-vessel image method for reconstructing and reconstructing device |
| CN108537802A (en) * | 2018-03-30 | 2018-09-14 | 北京灵医灵科技有限公司 | A kind of blood vessel segmentation method and device |
| CN108986106A (en) * | 2017-12-15 | 2018-12-11 | 浙江中医药大学 | Retinal vessel automatic division method towards glaucoma clinical diagnosis |
| CN109584223A (en) * | 2018-11-20 | 2019-04-05 | 北京中科研究院 | Pulmonary vascular dividing method in CT image |
| CN109886982A (en) * | 2019-04-24 | 2019-06-14 | 数坤（北京）网络科技有限公司 | A kind of blood-vessel image dividing method, device and computer memory device |
| CN109903298A (en) * | 2019-03-12 | 2019-06-18 | 数坤（北京）网络科技有限公司 | Restorative procedure, system and the computer storage medium of blood vessel segmentation image fracture |
| CN110827283A (en) * | 2019-10-28 | 2020-02-21 | 北京深睿博联科技有限责任公司 | Head and neck blood vessel segmentation method and device based on convolutional neural network |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030099390A1 (en) * | 2001-11-23 | 2003-05-29 | Xiaolan Zeng | Lung field segmentation from CT thoracic images |
| US9092849B2 (en) * | 2013-06-28 | 2015-07-28 | International Business Machines Corporation | Bidirectional blood vessel segmentation |
| US10869644B2 (en) * | 2016-07-30 | 2020-12-22 | Shanghai United Imaging Healthcare Co., Ltd. | Method and system for extracting lower limb vasculature |
-
2020
- 2020-04-09 CN CN202010272913.4A patent/CN111539917B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005998A (en) * | 2015-08-05 | 2015-10-28 | 大连理工大学 | Cerebrovascular image segmentation method based on multi-angle serialized image space feature point set |
| CN106097378A (en) * | 2016-07-24 | 2016-11-09 | 江西理工大学 | A kind of level set retinal vascular images dividing method merging shape prior |
| CN106875375A (en) * | 2016-12-28 | 2017-06-20 | 浙江工业大学 | Three-dimensional blood vessel axis detection method based on tubulose feature enhancing filtering and ridge line tracking |
| CN108428210A (en) * | 2017-02-15 | 2018-08-21 | 浙江京新术派医疗科技有限公司 | Blood-vessel image method for reconstructing and reconstructing device |
| CN108986106A (en) * | 2017-12-15 | 2018-12-11 | 浙江中医药大学 | Retinal vessel automatic division method towards glaucoma clinical diagnosis |
| CN108109159A (en) * | 2017-12-21 | 2018-06-01 | 东北大学 | It is a kind of to increase the retinal vessel segmenting system being combined based on hessian matrixes and region |
| CN108198184A (en) * | 2018-01-09 | 2018-06-22 | 北京理工大学 | The method and system of contrastographic picture medium vessels segmentation |
| CN108537802A (en) * | 2018-03-30 | 2018-09-14 | 北京灵医灵科技有限公司 | A kind of blood vessel segmentation method and device |
| CN109584223A (en) * | 2018-11-20 | 2019-04-05 | 北京中科研究院 | Pulmonary vascular dividing method in CT image |
| CN109903298A (en) * | 2019-03-12 | 2019-06-18 | 数坤（北京）网络科技有限公司 | Restorative procedure, system and the computer storage medium of blood vessel segmentation image fracture |
| CN109886982A (en) * | 2019-04-24 | 2019-06-14 | 数坤（北京）网络科技有限公司 | A kind of blood-vessel image dividing method, device and computer memory device |
| CN110827283A (en) * | 2019-10-28 | 2020-02-21 | 北京深睿博联科技有限责任公司 | Head and neck blood vessel segmentation method and device based on convolutional neural network |
Non-Patent Citations (1)
| Title |
|---|
| 张也 ; 张勇德 ; 沙宪政 ; .基于多尺度匹配滤波法的视网膜血管分割.中国医疗器械杂志.2020,(02),第17-21,44页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111539917A (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mouridsen et al. | Automatic selection of arterial input function using cluster analysis | |
| Verfaillie et al. | A more randomly organized grey matter network is associated with deteriorating language and global cognition in individuals with subjective cognitive decline | |
| El‐Bouri et al. | A statistical model of the penetrating arterioles and venules in the human cerebral cortex | |
| Colebank et al. | Influence of image segmentation on one-dimensional fluid dynamics predictions in the mouse pulmonary arteries | |
| CN111539917B (en) | Blood vessel segmentation method, system, terminal and storage medium based on coarse-fine granularity fusion | |
| Greene et al. | Finding maximally disconnected subnetworks with shortest path tractography | |
| Sundaresan et al. | Automated detection of candidate subjects with cerebral microbleeds using machine learning | |
| Shi et al. | Relationships between quantitative retinal microvascular characteristics and cognitive function based on automated artificial intelligence measurements | |
| CN114648514B (en) | Cerebral artery positioning and extracting method and device, electronic equipment and storage medium | |
| CN113450329B (en) | Microcirculation image blood vessel branch erythrocyte flow rate calculation method and system | |
| CN111383766A (en) | Computer data processing method, device, medium and electronic equipment | |
| CN115910360A (en) | Smog disease risk prediction model construction method | |
| Drabo et al. | Prospects of graduation for least developed countries: What structural change? | |
| CN116077048A (en) | Brain age prediction system, device and storage medium | |
| Cheng et al. | Association between morphologic features of intracranial distal arteries and brain atrophy indexes in cerebral small vessel disease: a voxel-based morphometry study | |
| CN113763403B (en) | Coronary artery blood vessel segmentation method and device | |
| CN117495951B (en) | Intracranial aneurysm positioning method, device, computer equipment and storage medium | |
| Hagemejer | Productivity spillovers in the GVC | |
| Li et al. | Associations of hypertensive disorders of pregnancy with cognition, dementia, and brain structure: a Mendelian randomization study | |
| CN117541728A (en) | Blood vessel midline straightening method and device, electronic equipment and storage medium | |
| CN114332202B (en) | Vascular model processing method and device and computer readable storage medium | |
| Lau et al. | Use of fractional flow reserve in different anatomical subsets | |
| Chapuis et al. | Morphologic and neuropsychological patterns in patients suffering from Alzheimer’s disease | |
| Hernández-Díaz et al. | Asymptomatic cerebral small vessel disease in adults with low cardiovascular risk | |
| Greco et al. | Relationship between chronic kidney disease and cerebral white matter hyperintensities: a systematic review |
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 |