CN112767332A - Blood vessel region judgment method and system based on CTA image - Google Patents

Blood vessel region judgment method and system based on CTA image Download PDF

Info

Publication number
CN112767332A
CN112767332A CN202110026581.6A CN202110026581A CN112767332A CN 112767332 A CN112767332 A CN 112767332A CN 202110026581 A CN202110026581 A CN 202110026581A CN 112767332 A CN112767332 A CN 112767332A
Authority
CN
China
Prior art keywords
blood vessel
circle
layer
data
bone
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110026581.6A
Other languages
Chinese (zh)
Other versions
CN112767332B (en
Inventor
王兴维
邰从越
刘慧芳
刘龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiaorui Medical Technology (Dalian) Co.,Ltd.
Original Assignee
Senyint International Digital Medical System Dalian Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Senyint International Digital Medical System Dalian Co ltd filed Critical Senyint International Digital Medical System Dalian Co ltd
Priority to CN202110026581.6A priority Critical patent/CN112767332B/en
Publication of CN112767332A publication Critical patent/CN112767332A/en
Application granted granted Critical
Publication of CN112767332B publication Critical patent/CN112767332B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30008—Bone
    • G06T2207/30012—Spine; Backbone
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30101—Blood vessel; Artery; Vein; Vascular
    • G06T2207/30104—Vascular flow; Blood flow; Perfusion

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Health & Medical Sciences (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The invention discloses a blood vessel region judgment method and system based on a CTA image, and belongs to the technical field of medical image processing. The method comprises the following steps: dividing CTA image data to obtain data to be processed; automatically selecting a seed point based on the data to be processed; extracting target data from the data to be processed, wherein the target data comprises abdominal bone and blood vessel data; performing layering processing on the abdominal bone and blood vessel data; an abdominal vascular region is obtained. The parts of the chest, the abdomen and the two lower limbs are divided, and the parts are independently processed according to the characteristics of the abdomen and the two lower limbs, so that the influence caused by the characteristic difference of different parts is avoided; two seed points are selected through the central layer, so that the time consumed by traversing each layer of a sequence is avoided, bones and blood vessels can be effectively extracted, and meanwhile, the interference of a bed board can be eliminated without bed removal; more accurate layering is carried out during abdominal segmentation, and the problems that extraction is difficult and the like caused by abdominal vascular lesions can be effectively avoided.

Description

Blood vessel region judgment method and system based on CTA image
Technical Field
The invention relates to the technical field of medical image processing, in particular to a blood vessel region judgment method and system based on a CTA image.
Background
Computed Tomography Angiography (CTA) is the injection of a contrast agent into a blood vessel and a CT scan performed to help diagnose and assess vascular disease or related conditions, such as an aneurysm or occlusion. In the medical field, the CTA image can more intuitively display the human body structure through three-dimensional reconstruction. CTA images of the chest, the abdomen and the lower limbs enhance blood vessels and highlight vascular lesions, but the three-dimensional reconstruction images of the two parts comprise a plurality of visceral organs, blood vessels and bones, and have great influence on blood vessel diagnosis.
At present, some blood vessel region acquisition mainly depends on manual operation or semi-automatic operation of doctors, and has large workload and easy generation of fatigue. There are also some automatic acquisition methods, and common methods are subtraction of non-CTA images and CTA images, model registration, threshold-based region growing, deep learning methods, and the like. Subtraction requires two CT scans, which is time consuming and increases the radiation exposure to the patient. The model registration algorithm is complex and is difficult to be applied to practice. The structure of the chest and abdomen is complex, the enhanced blood vessels and bones have similar CT values, and a single threshold is difficult to segment without a fixed threshold. The deep learning method needs standard marking data of professional doctors and is not suitable for short-term rapid development and application.
Disclosure of Invention
Aiming at the problems in the prior art, the application provides a blood vessel region judgment method and system based on a CTA image, which can be used for layering the abdomen in detail, effectively distinguishing the characteristics of each layer, achieving accurate segmentation and avoiding the problem of difficult extraction caused by abdominal blood vessel lesion; the technical scheme is as follows:
a blood vessel region judgment method based on CTA image comprises the following steps:
dividing CTA image data to obtain data to be processed;
automatically selecting a seed point based on the data to be processed;
extracting target data from the data to be processed, wherein the target data comprises abdominal bone and blood vessel data;
performing layering processing on the abdominal bone and blood vessel data;
an abdominal vascular region is obtained.
Optionally, the target data further includes double lower limb bone and blood vessel data, and the double lower limb bone and blood vessel data is subjected to bone removal processing to obtain double lower limb blood vessel regions.
Optionally, the seed points are automatically selected based on the data to be processed, specifically:
acquiring an image of a certain reference layer, wherein the image is divided into a left part and a right part from a middle column;
partitioning each part of image to obtain an average CT value of each block, and taking the block with the maximum CT value as a selection area;
comparing all the points in the selected area to obtain a point PxIs a seed point.
Optionally, a comparison operation is performed on all the points in the selected area to obtain a point PxThe method is characterized by comprising the following steps:
for any point P in the selection areaxDefinition of Vx＝min(Hpx,Hpx1,Hpx2,Hpx3,Hpx4) In which H ispxIs a point PxCT value of (1), Hpx1,Hpx2,Hpx3,Hpx4Are respectively a point PxFour neighborhood point P ofx1、Px2、Px3、Px4CT value of (1), selecting the maximum VxCorresponding point PxIs a seed point, which is selected on a bone or a blood vessel.
Optionally, the extracting target data from the data to be processed specifically includes:
acquiring a first threshold as a growth condition, and performing region growth by using two automatically selected seed points to segment bones and blood vessels into masks 1;
acquiring a second threshold, and shielding impurities to obtain a bone and blood vessel mask 2;
the intersection of the bone and blood vessel mask1 and the bone and blood vessel mask2 is taken as the segmented bone and blood vessel mask.
Optionally, the abdominal bone and blood vessel data are subjected to layering processing, specifically:
acquiring a bounding box mask _ temp of an abdominal skeleton and a blood vessel mask;
preprocessing the bounding box mask _ temp to obtain an image mask _ pre;
traversing the image mask _ pre from top to bottom to obtain a first circle, wherein the layer parameter of the first circle is a layer boundary layer 1;
traversing layer by layer from the first circle, finding the whole abdominal aorta circle, and determining a layer2 of the abdominal aorta circle branch;
and removing the external interference of the circle to the delamination boundary layer1 and the abdominal aorta circular branch layer 2.
Optionally, traversing the image mask _ pre from top to bottom to obtain a first circle, where a layer parameter of the first circle is a layer boundary layer1, specifically:
traversing the image mask _ pre from top to bottom, obtaining a first circle through Hough transformation, and obtaining an average CT value and a variance of a current layer circle;
if the average CT value of the current layer circle is larger than 0 and the variance is smaller than a set value, the acquired first circle meets the requirement of the abdominal aorta circle; storing the radius, center coordinates, average CT value and variance of the first circle;
the layer parameter of the first circle is the layer boundary layer 1.
Optionally, traversing layer by layer from the first circle, finding the entire abdominal aorta circle, and determining the abdominal aorta circle branch layer2, specifically:
traversing layer by layer from the first circle, stopping traversing if two continuous layers have no circles, and storing the number of layers of the branch layer and a circle parameter list obtained by traversing before the branch layer; if not, then,
acquiring circular parameters of two adjacent layers;
if the distance between the circle centers of the two adjacent layers is smaller than the threshold value, the parameter of the layer is continuously compared with the parameter of the next layer, the layer number, the circle center and the radius parameter of the layer are stored, and then iterative comparison is carried out;
if the distance between the circle centers of two adjacent layers is larger than a threshold value, obtaining the average CT value and the variance of the current layer, and if the average CT value is larger than 0 and the variance is smaller than a set value, judging that the current layer is a circle; otherwise, the last layer of the circle is the layer2 of the abdominal aorta circular branch.
Optionally, the circle external interference is removed from the layered boundary layer1 and the abdominal aorta circular branch layer2, specifically:
obtaining the connectivity of a skeleton mask and a blood vessel mask, and extracting a circle through the center of the circle;
shifting the circle center to the left by a certain number of pixels, and extracting a new circle according to a new circle center coordinate in the certain number of pixels;
obtaining an upper boundary bottom _ c and a lower boundary top _ c of the new circle;
and setting all the connected domains above the upper boundary bottom _ c to be 0.
Optionally, after performing layering processing on the abdominal bone and blood vessel data, extracting blood vessel features, specifically:
obtaining connectivity of the skeleton and the blood vessel mask after the layering processing, obtaining area, perimeter, centroid, boundary bbox and circularity of a connected domain, and further obtaining average CT value mean and standard deviation determination;
if the average CT value mean, the standard deviation determination and the circularity determination meet set judgment conditions, the blood vessel region is not determined;
if the area of the connected region area>πR2Perimeter>2 π R, mean CT value mean>0, if the standard deviation is greater than the set value, the blood vessel area is not; wherein R is the vessel radius;
if the centroid is not within the bounding box, it is not a vascular region.
Optionally, obtaining a double lower limb vascular region specifically comprises:
obtaining a communicating region of at least one double lower limb skeleton and a blood vessel mask, and obtaining an area, a perimeter and a boundary bbox of the communicating region;
extracting image bounding boxes meeting a judgment condition of 0<area<πR2，0<perimeter<2 pi R, wherein R is the vessel radius:
if the average CT value mean of the image bounding box is greater than 0 and the variance is smaller than a set value, the image bounding box is a double-lower-limb blood vessel;
and removing bone impurities from the double lower limb blood vessels in the z direction.
A blood vessel region determination system based on CTA image, comprising:
the segmentation module is used for segmenting the CTA image data to obtain data to be processed;
the automatic selection module is used for automatically selecting seed points based on the data to be processed;
the target data acquisition module is used for extracting target data from the data to be processed, wherein the target data comprises abdominal bone and blood vessel data;
the layering processing module is used for performing layering processing on the abdominal skeleton and blood vessel data;
and the blood vessel acquisition module is used for acquiring an abdominal blood vessel region.
According to the technical scheme, the blood vessel region judgment method and the blood vessel region judgment system based on the CTA image can automatically extract the abdominal region and the double lower limb regions, and do not need any operation of a user in the bone removing process, so that the time cost is saved. The different characteristics of each part are utilized to independently process the abdomen and the double lower limb areas, thereby being beneficial to commercialization and improving the practicability. The abdominal region is complex, and lesion blood vessels are more, so that the abdomen is layered more accurately, the structural characteristics of different parts of the abdomen can be fully utilized, and the influence on the parameters of the whole extraction process due to partial interference is avoided. The method for automatically selecting two seed points and extracting blood vessels and bones is suitable for all parts such as the abdomen, the double lower limbs and the like, and can remove the interference of a bed plate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flowchart of a blood vessel region determination method based on CTA images according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart illustrating automatic selection of a seed point based on the data to be processed according to the present application;
fig. 3 is a schematic flow chart of extracting target data from the data to be processed according to the embodiment of the present application;
FIG. 4 is a schematic flow chart illustrating a process for layering the abdominal bone and blood vessel data according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of a bone and blood vessel mask of layer1 and layer2 provided in an embodiment of the present application;
FIG. 6 is a diagram illustrating the effect of bone removal on both lower limbs according to the embodiment of the present application;
fig. 7 is a blood vessel region determination system based on CTA images according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of an electronic device for blood vessel region determination based on CTA images according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a blood vessel region determination method based on CTA image according to an embodiment of the present application, where the present embodiment is applicable to a situation where a target blood vessel needs to be extracted, and the method may be executed by a blood vessel region determination device based on CTA image, and the device may be implemented in software and/or hardware, and the device may be configured in a computer device. As shown in fig. 1, the method of this embodiment specifically includes:
s1, segmenting CTA image data to obtain data to be processed;
CTA (CT angiography) combines a CT enhancement technology with a thin-layer, large-range and rapid scanning technology, and clearly displays details of blood vessels of all parts of the whole body through reasonable post-processing. Has the characteristics of no wound and simple and convenient operation, and has important values for vascular variation, vascular diseases and displaying pathological changes and vascular relations. Therefore, CTA image data is mainly acquired using CT (Computed Tomography) scanning technology.
The CTA image data is subjected to part segmentation and divided into a chest part, an abdomen part and two lower limbs, and different parts are processed independently, so that the problem that different characteristics of each part are limited by a single algorithm is solved;
s2, automatically selecting seed points based on the data to be processed;
based on abdominal and double lower limb data of the CTA image, the blood vessels are enhanced, and the CT values of the blood vessels and bones are higher than those of skin and other organs; the automatic selection of seed points is based on the above characteristics, with selection on highlighted blood vessels and bones. Because the two lower limbs are divided into the left leg and the right leg, the two legs are not connected, two seed points are selected, the condition that tissues are selected in a missing mode is avoided, and double guarantee is provided for extraction of whole blood vessels and bones; one or two seed points may be selected for the abdominal region.
S3, extracting target data from the data to be processed, wherein the target data comprises abdominal bone and blood vessel data;
the data to be processed obtained in step S1 is three-dimensional volume data, and the target data is extracted by using a multi-threshold three-dimensional volume region growing method, and the target data includes abdominal bone and blood vessel data, and both lower limb bone and blood vessel data because the present invention extracts blood vessel regions of the abdomen and both lower limbs by using different methods.
S4, carrying out layering processing on the abdominal skeleton and blood vessel data;
the abdomen deboning adopts a layering method, so that the influence of complicated abdomen structure on the whole deboning method is avoided; the key to the abdominal stratification process is to locate the abdominal aorta circle, defining the stratification limit layer1 as the first abdominal aorta circle layer and layer2 as the abdominal aorta circle starting branch layer.
S5, obtaining an abdominal blood vessel area;
removing bones and segmenting abdominal bones and blood vessel masks, extracting blood vessel characteristics to remove bones after layering treatment, and then removing impurities in the z direction according to the blood vessel communication characteristic.
According to the blood vessel region judgment method based on the CTA image, the chest, the abdomen and the two lower limbs are subjected to region segmentation, and are independently processed according to the characteristics of the abdomen and the two lower limbs, so that the influence caused by different region characteristic differences is avoided; two seed points are selected through the central layer, so that the time consumed by traversing each layer of a sequence is avoided, bones and blood vessels can be effectively extracted, and meanwhile, the interference of a bed board can be eliminated without bed removal; more accurate layering is carried out during abdominal segmentation, and the problems that extraction is difficult and the like caused by abdominal vascular lesions can be effectively avoided.
In a possible implementation manner, bone removal processing is further performed on the double lower limb bone and blood vessel data in the target data to obtain double lower limb blood vessel regions; the blood vessel extraction range is determined through the communicated area of the three-dimensional data of the double lower limb bones and the blood vessel mask, so that the lower limb bone removing efficiency is improved; in addition, the efficiency and the accuracy of the lower limb blood vessel extraction can be further improved by combining the structural characteristics of the double lower limb blood vessels.
In a possible implementation manner, the segmenting CTA image data to obtain to-be-processed data may be: the CTA image data comprises a chest area, an abdomen area and two lower limb areas, and the chest data, the abdomen data and the two lower limb data are obtained through an automatic chest and abdomen division line searching algorithm by positioning a caudal vertebra area. The segmentation divides the deboned area into different regions and uses adaptive deboning methods for the structural features of the different regions.
In a possible implementation manner, the segmenting CTA image data to obtain to-be-processed data may further include:
performing double-threshold preprocessing on CTA image data to obtain a bone and blood vessel region;
a threshold T1 is given and can be set as-150, image binarization processing is carried out on CTA image data to obtain a human body region binarization image, a morphology opening operation is used for removing noise points, and then regions with the number of connected region pixel points being less than 10000 are removed, so that small region interference is avoided; and further obtaining a mask _ body image of the complete area of the human body.
Given a threshold T2, which may be set at 150, CTA image data is binarized to obtain the intersection with the image mask _ body, and the bone and blood vessel region mask is obtained.
Segmenting chest and abdomen data based on the bone and blood vessel regions;
and (3) carrying out processing such as denoising on the mask of the bone and blood vessel region, traversing layer by layer from top to bottom (the cross section of the CT image in the direction from the head to the feet) to obtain the communication characteristic, combining the positioned bottom boundary of the lung cavity according to the attribute of the communication region to obtain the boundary of the chest and the abdomen, and finishing the traversing layer by layer. The boundary is a relative value, an accurate value is not needed, and a plurality of layers of front and back deviation have no influence on subsequent bone removal.
Segmenting abdominal and double lower limb data based on the bone and blood vessel region positioning relative caudal vertebra region;
according to the structural characteristics of the tail vertebra on the cross section, the relative position of the tail vertebra end can be positioned to be used as a boundary line for dividing the abdomen and the double lower limbs. The boundary does not need to be accurate to a certain layer, and the front error and the rear error of a plurality of layers do not influence the abdomen segmentation and the double lower limbs segmentation.
Finding out a boundary line between the abdomen and the two lower limbs in the relative caudal vertebra region;
after the caudal vertebra region is located, the bone and blood vessel region mask (head to foot direction) is traversed from top to bottom, and if the pixels of the caudal vertebra region are all 0, the layer is determined to be the boundary layer.
And removing foot interference according to the double lower limb data according to the judgment condition.
Although the feet are also defined in the lower limbs, the cross section of the foot data is different from the leg data, and the judgment condition is set to prevent the interference of the foot data.
The CTA image generally includes chest, abdomen, and two lower limbs, and the dividing lines of each part need to be automatically divided. For abdominal bone removal, the boundary between the two lower limbs and the chest and abdomen needs to be extracted first to obtain abdominal data.
In one possible implementation, segmenting abdominal and dual lower limb data based on the bone and blood vessel region location versus the caudal vertebra region may include:
acquiring an upper boundary bottom, a lower boundary top, a left boundary left and a right boundary right of a human body region mask _ body;
obtaining an upper boundary bottom _ relative, a lower boundary top _ relative, a left boundary left _ relative and a right boundary right _ relative of the relative caudal vertebra region according to the boundary of the human body region mask _ body as follows:
bottom_relative＝bottom
top_relative＝bottom+(top-bottom)*0.4
left_relative＝(right+left)/2–(right-left)*0.1
right_relative＝(right+left)/2+(right-left)*0.1。
in one possible implementation manner, the removing of the foot interference according to the determination condition by the dual lower limb data may include:
the first determination condition: traversing CTA image data from top to bottom, and judging that the data of the two lower limbs is also a boundary when the mask _ body of a certain layer of human body area is empty;
the second determination condition: the height of the mask _ body image of a certain layer of human body area is height, the width is weight, and the offsets div _1 and div _2 are defined as follows:
div_1＝top–bottom
div_2＝right-left
the CTA image data is traversed from top to bottom, and when 0< div _1< height/2 and 0< div _2< weight/2, it is determined as the double lower limb data, which is also the boundary.
The method can find the boundary line during the division processing of the abdomen and the double lower limb parts, and the boundary line is a relative position, so that the deviation of several layers does not have any influence on the subsequent algorithm.
Fig. 2 is a schematic flow chart of automatically selecting a seed point based on the to-be-processed data according to an embodiment of the present application, and in a possible implementation manner, the automatically selecting a seed point may include:
s21, acquiring an image of a certain reference layer, wherein the image is divided into a left part and a right part from a middle column;
the seed points are selected according to a certain reference layer image, the middle layer is selected as the reference layer in the embodiment, the size of the reference layer can be 512 × 512, the middle column is divided into a left part and a right part, and the method for automatically selecting the seed points of the left part and the right part of the image is consistent.
S22, partitioning each image to obtain an average CT value of each block, and taking the block with the maximum CT value as a selection area;
determining a first number of column parting lines in the horizontal direction and a second number of line parting lines in the vertical direction of the image to be parted; according to each column parting line and each row parting line, partitioning an image to be partitioned, wherein the size of each block can be 32 x 32, obtaining the average CT value of each block, and taking the block with the maximum CT value as a selection area;
s23, comparing all the points in the selected area to obtain a point PxIs a seed point.
For any point P in the selection areaxDefinition of Vx＝min(Hpx,Hpx1,Hpx2,Hpx3,Hpx4) In which H ispxIs a point PxCT value of (1), Hpx1,Hpx2,Hpx3,Hpx4Are respectively a point PxFour neighborhood point P ofx1、Px2、Px3、Px4Selecting the maximum CT value ofVxCorresponding point PxIs a seed point, which is selected on a bone or a blood vessel.
The method uses two automatically selected seed points, can effectively extract bones and blood vessels, avoids the condition that the left leg and the right leg of the two lower limbs are not connected, directly shields the influence of a bed plate without a bed passing algorithm, is suitable for extracting the bones and the blood vessels of the whole CTA image, and is not influenced by a single part.
Fig. 3 is a schematic flow diagram of extracting target data from the data to be processed according to an embodiment of the present application, and in a possible implementation manner, the schematic flow diagram may include:
s31, acquiring a first threshold as a growth condition, and performing region growth by using two automatically selected seed points to segment bones and blood vessels into masks 1;
the CT values of the bed plate and the blood vessel are close, but the bed plate and the bone are separated by the skin, the CT value of the skin is far smaller than that of the bone and the blood vessel, and the seed point is selected on the bone or the blood vessel. The first threshold T, which may be 80, is chosen as the optimal threshold, and bone and bed plates may be separated by skin as growth conditions, using two seed points selected automatically for region growth, to segment out bone and blood vessel masks 1.
S32, acquiring a second threshold, and shielding impurities to obtain a bone and blood vessel mask 2;
the second threshold T may be 150, and all impurities with a threshold less than 150, including other organs, skin, noise, etc., are masked.
S33, taking the intersection of the bone and blood vessel mask1 and the bone and blood vessel mask2 as a segmented bone and blood vessel mask.
The obtained bone and blood vessel mask is the final segmentation result of the step, the method can quickly extract the bone and the blood vessel, and the influence of a bed plate is automatically shielded without bed passing processing. It is not only suitable for each region, but also for the extraction of the whole CTA image.
Fig. 4 is a schematic flow chart of a process for performing layering on the abdominal bone and blood vessel data according to an embodiment of the present application, and in a possible implementation manner, the process may include:
s41, acquiring a bounding box mask _ temp of an abdominal skeleton and a blood vessel mask;
the abdominal blood vessels are distributed on the left and right sides of the body region, and finding the abdominal blood vessel bounding box can reduce a part of the interference. The method comprises the steps of setting a threshold T to be-150 aiming at an original image of the abdomen, reserving a skin area according to the threshold T, further preprocessing, and removing an area with the number of pixels of a connected area being less than 10000 through morphological opening operation. Since the human body edge connected region is large enough, this number limitation does not affect the extraction of the human body region.
It should be noted that, to obtain the left and right boundaries of the human body region, the left boundary is defined as left, and the right boundary is defined as right; the center index of the abdominal blood vessel bounding box is (right + left)/2, and the left-right offset is (right-left) × 0.25, so the left and right boundaries of the abdominal blood vessel bounding box are respectively: ((right + left)/2- (right-left) × 0.25), ((right + left)/2+ (right-left) × 0.25). Bounding box mask _ temp of bone and blood vessel mask is defined according to the left and right boundaries of the bounding box, and original image data bounding box image _ temp is defined.
S42, preprocessing the bounding box mask _ temp to obtain an image mask _ pre;
and preprocessing the bounding box mask _ temp to obtain a mask _ pre, wherein the process is to fill a cavity, and the opening operation is performed to prevent the influence of the cavity when the abdominal aorta circle is subsequently positioned.
S43, traversing the image mask _ pre from top to bottom to obtain a first circle, wherein the layer parameter of the first circle is a layer boundary layer 1;
and traversing the image mask _ pre from top to bottom, finding a first circle through Hough transform, and obtaining the average CT value and the variance of the current layer circle. If the average CT value of the current layer circle is larger than 0 and the variance is smaller than 150 (which can be adjusted according to actual conditions), the acquired first circle meets the requirement of the abdominal aorta circle, and parameters such as the radius, the center coordinate, the average CT value, the variance and the layer where the first circle is located are stored, and the layer is defined as a layered boundary layer 1.
S44, traversing layer by layer from the first circle, finding the whole abdominal aorta circle, and determining a layer2 of the abdominal aorta circle branch;
the specific method comprises the following steps:
the first judgment condition: traversing layer by layer from the first circle, stopping traversing if two continuous layers have no circles, and storing the number of layers of the branch layer and a circle parameter list obtained by traversing before the branch layer;
a second judgment condition: acquiring circle parameters of two adjacent layers, judging the distance between the centers of the front layer and the rear layer, and if the distance between the centers of the two adjacent layers is less than a threshold value 5 (which can be adjusted according to actual conditions), conforming to the judgment condition of a circle; continuously comparing the layer parameter with the next layer parameter, storing the layer number, the circle center and the radius parameter of the layer, and then iteratively comparing until the fourth judgment condition is met;
the third judgment condition: if the distance between the circle centers of two adjacent layers is larger than a threshold value 5, the average CT value and the variance of the current layer are obtained, and if the average CT value is larger than 0 and the variance is smaller than 150, the circle is judged.
The fourth judgment condition: if the distance between the centers of two adjacent layers is greater than the threshold value 5, the mean value is greater than 0 and the variance is less than 150, counting is carried out, and the two adjacent layers do not meet the conditions, the last layer of the circle can be judged to be the layer2 of the abdominal aorta circular branch layer, as shown in fig. 5, the skeleton and blood vessel masks are layer1 and layer2 respectively.
S45, removing the external interference of the circle to the layered boundary layer1 and the abdominal aorta circular branch layer 2.
Acquiring connectivity and circle center parameters of the skeleton mask and the blood vessel mask, and extracting a circle through the circle center; and (3) preventing the coordinate deviation of the circle center to cause missing detection, wherein the circle center is deviated by 10 pixels (which can be adjusted according to actual conditions) to the left, and a new circle is extracted by using the new circle center coordinate in the 10 pixels. The upper boundary bottom _ c and the lower boundary top _ c of the new circle are obtained. And setting all the connected domains above the upper boundary bottom _ c to be 0 so as to remove the external interference of the circle.
In a possible implementation manner, after performing layering processing on the abdominal bone and blood vessel data, extracting blood vessel features, specifically: the treatment resulted in bone and blood vessel masks (including layer1, layer2 and all layers except). And obtaining the connectivity of the skeleton and the blood vessel mask, obtaining the area of a connected domain, the perimeter, the centroid, the boundary bbox and the circularity, and further obtaining the average CT value mean and the standard deviation determination.
Setting a judgment condition:
if the average CT value mean is more than 400 (can be adjusted according to actual conditions), the standard deviation is more than 100 (can be adjusted according to actual conditions), and the circularity is less than 0.2, the average CT value mean is not a blood vessel region;
if the area of the connected region area>πR2Perimeter>2 π R, mean CT value mean>0, standard deviation>100, then is not a vascular region; wherein R is the radius of the blood vessel which can be 15;
if the centroid is not within the bounding box, it is not a vascular region.
In one possible implementation, after the blood vessel features are extracted, the three-dimensional connectivity of the blood vessels is utilized to remove bone impurities in the z direction. Because blood vessels and bone fragments exist in the bone removing and segmenting result, impurities are removed in the z direction by utilizing the connectivity of the blood vessels; the method is based on the three-dimensional connectivity of blood vessels, and if the thickness in the z direction is less than 50, the bone impurities are obtained. The final vascular area is obtained after decontamination, at which point the abdominal deboning process is complete.
Fig. 6 is a diagram illustrating an effect of bone removal effect of two lower limbs according to an embodiment of the present application, and in a possible implementation manner, a blood vessel region of two lower limbs is obtained, specifically:
obtaining at least one communicating region of a double lower limb bone and a blood vessel mask, and obtaining the area, the perimeter and the boundary bbox of each communicating region;
extracting image bounding boxes meeting a judgment condition of 0<area<πR2，0<perimeter<2 pi R, wherein R is the radius of the blood vessel which can be 15:
if the average CT value mean of the image bounding box is greater than 0 and the variance is less than <300 (the variance can be adjusted according to actual conditions), the image bounding box is a double-lower-limb blood vessel;
and removing bone impurities from the double lower limb blood vessels in the z direction, wherein the final double lower limb blood vessel region is obtained by a method similar to the method for removing the impurities from the abdominal part in the z direction, and the double lower limb bone removal process is finished.
The invention processes each part by using a separate method, utilizes different characteristics of each part, is beneficial to commercialization and improves the practicability.
The blood vessel region determination system based on the CTA image provided by the embodiment of the present application is described below, and may be referred to in correspondence with the blood vessel region determination method based on the CTA image described above.
Fig. 7 is a blood vessel region determination system based on CTA images according to an embodiment of the present disclosure, where the system may include: a segmentation module 71, an automatic selection module 72, a target data acquisition module 73, a hierarchical processing module 74, and a blood vessel acquisition module 75; wherein:
the segmentation module 71 is configured to segment the CTA image data to obtain to-be-processed data;
an automatic selection module 72 for automatically selecting seed points based on the data to be processed;
a target data obtaining module 73, configured to extract target data from the data to be processed, where the target data includes abdominal bone and blood vessel data;
a layering processing module 74, configured to perform layering processing on the abdominal bone and blood vessel data;
a blood vessel obtaining module 75 for obtaining an abdominal blood vessel region.
According to the blood vessel region judgment system based on the CTA image, the chest, the abdomen and the two lower limbs are subjected to region segmentation, and are independently processed according to the characteristics of the abdomen and the two lower limbs, so that the influence caused by different region characteristic differences is avoided; two seed points are selected through the central layer, so that the time consumed by traversing each layer of a sequence is avoided, bones and blood vessels can be effectively extracted, and meanwhile, the interference of a bed board can be eliminated without bed removal; more accurate layering is carried out during abdominal segmentation, and the problems that extraction is difficult and the like caused by abdominal vascular lesions can be effectively avoided.
In a possible implementation manner, the target data further includes double lower limb bone and blood vessel data, and the double lower limb bone and blood vessel data is subjected to bone removal processing to obtain double lower limb blood vessel regions.
In a possible implementation manner, the CTA image data in the segmentation module 71 includes a chest region, an abdomen region, and two lower limb regions, and the chest data, the abdomen data, and the two lower limb data are obtained through an algorithm of automatically searching a thoracic-abdominal segmentation line through positioning a caudal vertebra region.
In one possible implementation, the automatic selection module 72 may include:
the device comprises a reference layer acquisition module, a reference layer acquisition module and a reference layer acquisition module, wherein the reference layer acquisition module is used for acquiring an image of a certain reference layer, and the image is divided into a left part and a right part from a middle column;
the blocking module is used for blocking each part of image to obtain the average CT value of each block, and the block with the maximum CT value is taken as a selection area;
a seed point obtaining module for comparing all points in the selected region to obtain a point PxIs a seed point.
In one possible implementation manner, the specific implementation manner in the seed point obtaining module may be:
for any point P in the selection areaxDefinition of Vx＝min(Hpx,Hpx1,Hpx2,Hpx3,Hpx4) In which H ispxIs a point PxCT value of (1), Hpx1,Hpx2,Hpx3,Hpx4Are respectively a point PxFour neighborhood point P ofx1、Px2、Px3、Px4CT value of (1), selecting the maximum VxCorresponding point PxIs a seed point, which is selected on a bone or a blood vessel.
In one possible implementation, the target data obtaining module 73 may include:
the mask1 acquisition module acquires a first threshold as a growth condition, performs region growth by using two automatically selected seed points, and segments a bone and a blood vessel mask 1;
a mask2 obtaining module for obtaining a second threshold value and shielding impurities to obtain a bone and blood vessel mask 2;
and the Mask acquisition module is used for taking the intersection of the bone and blood vessel Mask1 and the bone and blood vessel Mask2 as a segmented bone and blood vessel Mask.
In one possible implementation, the hierarchical processing module 74 is specifically:
the bounding box acquisition module is used for acquiring a bounding box mask _ temp of the abdominal skeleton and the blood vessel mask;
the bounding box preprocessing module is used for preprocessing the bounding box mask _ temp to obtain an image mask _ pre;
a layer1 obtaining module, which traverses the image mask _ pre from top to bottom to obtain a first circle, wherein a layer parameter of the first circle is a layer1 of a hierarchical boundary;
a layer2 obtaining module, which starts from the first circle to traverse layer by layer, finds the whole abdominal aorta circle and determines the layer2 of the abdominal aorta circle branch;
and the interference removal module is used for removing the interference outside the circle for the layering boundary layer1 and the abdominal aorta circular branch layer 2.
In one possible implementation, the specific implementation in the layer1 acquisition module may be:
traversing the image mask _ pre from top to bottom, obtaining a first circle through Hough transformation, and obtaining an average CT value and a variance of a current layer circle;
if the average CT value of the current layer circle is larger than 0 and the variance is smaller than a set value, the acquired first circle meets the requirement of the abdominal aorta circle; storing the radius, center coordinates, average CT value and variance of the first circle;
the layer parameter of the first circle is the layer boundary layer 1.
In one possible implementation, the specific implementation in the layer2 acquisition module may be:
traversing layer by layer from the first circle, stopping traversing if two continuous layers have no circles, and storing the number of layers of the branch layer and a circle parameter list obtained by traversing before the branch layer; if not, then,
acquiring circular parameters of two adjacent layers;
if the distance between the circle centers of the two adjacent layers is smaller than the threshold value, the parameter of the layer is continuously compared with the parameter of the next layer, the layer number, the circle center and the radius parameter of the layer are stored, and then iterative comparison is carried out;
if the distance between the circle centers of two adjacent layers is larger than a threshold value, obtaining the average CT value and the variance of the current layer, and if the average CT value is larger than 0 and the variance is smaller than a set value, judging that the current layer is a circle; otherwise, the last layer of the circle is the layer2 of the abdominal aorta circular branch.
In a possible implementation manner, the specific implementation manner of the interference removing module may be:
obtaining the connectivity of a skeleton mask and a blood vessel mask, and extracting a circle through the center of the circle;
shifting the circle center to the left by a certain number of pixels, and extracting a new circle according to a new circle center coordinate in the certain number of pixels;
obtaining an upper boundary bottom _ c and a lower boundary top _ c of the new circle;
and setting all the connected domains above the upper boundary bottom _ c to be 0.
In a possible implementation manner, the method further includes a blood vessel feature extraction module, where the blood vessel feature extraction module may include:
the parameter acquisition module is used for acquiring the connectivity of the skeleton and blood vessel mask after the layering processing to obtain the area of a connected domain, the perimeter, the centroid, the boundary bbox and the circularity, and further obtain the mean CT value mean and the standard deviation;
a judging module:
if the average CT value mean, the standard deviation determination and the circularity determination meet set judgment conditions, the blood vessel region is not determined;
if the area of the connected region area>πR2Perimeter>2 π R, averageCT value mean>0, if the standard deviation is greater than the set value, the blood vessel area is not; wherein R is the vessel radius;
if the centroid is not within the bounding box, it is not a vascular region.
In one possible implementation, the method further comprises a rogue module that removes bone impurities in the z-direction using three-dimensional connectivity of blood vessels.
In a possible implementation manner, the method further includes a dual lower limb blood vessel region acquisition module, where the dual lower limb blood vessel region acquisition module may include:
the system comprises a connected region parameter acquisition module, a parameter acquisition module and a parameter acquisition module, wherein the connected region parameter acquisition module is used for acquiring a connected region of at least one double lower limb bone and a blood vessel mask to obtain the area, the perimeter and the boundary bbox of the connected region;
a judging module for extracting image bounding boxes meeting judging conditions, wherein the judging conditions are 0<area<πR2，0<perimeter<2 pi R, wherein R is the vessel radius:
the double-lower-limb blood vessel acquisition module is used for acquiring double lower limb blood vessels if the average CT value mean of the image bounding box is greater than 0 and the variance is smaller than a set value;
and removing the bone impurity module, and removing bone impurities from the double lower limb blood vessels in the z direction.
Fig. 8 is a schematic structural diagram of an electronic device for blood vessel region determination based on CTA images according to an embodiment of the present disclosure. The electronic device may include: at least one processor 81, at least one communication interface 82, at least one memory 83 and at least one communication bus 84; the processor 81, the communication interface 82 and the memory 83 complete mutual communication through the communication bus 84;
the processor 81 may be a central processing unit CPU, or an application Specific integrated circuit asic, or one or more integrated circuits configured to implement embodiments of the present invention, or the like;
the memory 83 may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory) or the like, such as at least one disk memory;
wherein the memory stores a program and the processor can call the program stored in the memory, the program for:
dividing CTA image data to obtain data to be processed;
automatically selecting a seed point based on the data to be processed;
extracting target data from the data to be processed, wherein the target data comprises abdominal bone and blood vessel data;
performing layering processing on the abdominal bone and blood vessel data;
an abdominal vascular region is obtained.
Alternatively, the detailed function and the extended function of the program may be as described above.
An embodiment of the present application further provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the blood vessel region determination method based on the CTA image. Wherein the program stored in the readable medium, when executed by the processor, causes the processor to perform the method of:
dividing CTA image data to obtain data to be processed;
automatically selecting a seed point based on the data to be processed;
extracting target data from the data to be processed, wherein the target data comprises abdominal bone and blood vessel data;
performing layering processing on the abdominal bone and blood vessel data;
an abdominal vascular region is obtained.
The readable storage medium proposed in this embodiment is the same as the blood vessel region determination method based on the CTA image, and the technical details not described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods of the embodiments of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (12)

1. A blood vessel region judgment method based on a CTA image is characterized by comprising the following steps:
dividing CTA image data to obtain data to be processed;
automatically selecting a seed point based on the data to be processed;
extracting target data from the data to be processed, wherein the target data comprises abdominal bone and blood vessel data;
performing layering processing on the abdominal bone and blood vessel data;
an abdominal vascular region is obtained.
2. The blood vessel region determination method based on CTA image as claimed in claim 1, wherein the target data further includes double lower limb bone and blood vessel data, and the double lower limb bone and blood vessel data is subjected to bone removal processing to obtain a double lower limb blood vessel region.
3. The blood vessel region determination method based on CTA image as claimed in claim 1 or 2, wherein the seed points are automatically selected based on the data to be processed, specifically:
acquiring an image of a certain reference layer, wherein the image is divided into a left part and a right part from a middle column;
partitioning each part of image to obtain an average CT value of each block, and taking the block with the maximum CT value as a selection area;
comparing all the points in the selected area to obtain a point PxIs a seed point.
4. The method of claim 3, wherein the comparison operation is performed on all points in the selected region to obtain a point PxThe method is characterized by comprising the following steps:
for any point P in the selection areaxDefinition of Vx＝min(Hpx,Hpx1,Hpx2,Hpx3,Hpx4) In which H ispxIs a point PxCT value of (1), Hpx1,Hpx2,Hpx3,Hpx4Are respectively a point PxFour neighborhood point P ofx1、Px2、Px3、Px4CT value of (1), selecting the maximum VxCorresponding point PxIs a seed point, which is selected on a bone or a blood vessel.
5. The blood vessel region determination method based on CTA image as claimed in claim 1 or 2, wherein the target data is extracted from the data to be processed, specifically:
acquiring a first threshold as a growth condition, and performing region growth by using two automatically selected seed points to segment bones and blood vessels into masks 1;
acquiring a second threshold, and shielding impurities to obtain a bone and blood vessel mask 2;
the intersection of the bone and blood vessel mask1 and the bone and blood vessel mask2 is taken as the segmented bone and blood vessel mask.
6. The blood vessel region determination method based on CTA image as claimed in claim 1, wherein the abdominal bone and blood vessel data are processed in layers, specifically:
acquiring a bounding box mask _ temp of an abdominal skeleton and a blood vessel mask;
preprocessing the bounding box mask _ temp to obtain an image mask _ pre;
traversing the image mask _ pre from top to bottom to obtain a first circle, wherein the layer parameter of the first circle is a layer boundary layer 1;
traversing layer by layer from the first circle, finding the whole abdominal aorta circle, and determining a layer2 of the abdominal aorta circle branch;
and removing the external interference of the circle to the delamination boundary layer1 and the abdominal aorta circular branch layer 2.
7. The blood vessel region determination method based on CTA image as claimed in claim 6, wherein traversing the image mask _ pre from top to bottom obtains a first circle, and a layer parameter of the first circle is a layer boundary layer1, specifically:
traversing the image mask _ pre from top to bottom, obtaining a first circle through Hough transformation, and obtaining an average CT value and a variance of a current layer circle;
if the average CT value of the current layer circle is larger than 0 and the variance is smaller than a set value, the acquired first circle meets the requirement of the abdominal aorta circle; storing the radius, center coordinates, average CT value and variance of the first circle;
the layer parameter of the first circle is the layer boundary layer 1.
8. The method for determining a blood vessel region based on CTA image as claimed in claim 6, wherein the first circle is traversed layer by layer to find the entire circle of the abdominal aorta and determine the layer2 of the branch of the circle of the abdominal aorta, specifically:
traversing layer by layer from the first circle, stopping traversing if two continuous layers have no circles, and storing the number of layers of the branch layer and a circle parameter list obtained by traversing before the branch layer; if not, then,
acquiring circular parameters of two adjacent layers;
if the distance between the circle centers of the two adjacent layers is smaller than the threshold value, the parameter of the layer is continuously compared with the parameter of the next layer, the layer number, the circle center and the radius parameter of the layer are stored, and then iterative comparison is carried out;
if the distance between the circle centers of two adjacent layers is larger than a threshold value, obtaining the average CT value and the variance of the current layer, and if the average CT value is larger than 0 and the variance is smaller than a set value, judging that the current layer is a circle; otherwise, the last layer of the circle is the layer2 of the abdominal aorta circular branch.
9. The blood vessel region determination method based on CTA image as claimed in claim 6, wherein the circle external interference is removed from the layer boundary layer1 and the abdominal aorta circular branch layer2, specifically:
obtaining the connectivity of a skeleton mask and a blood vessel mask, and extracting a circle through the center of the circle;
shifting the circle center to the left by a certain number of pixels, and extracting a new circle according to a new circle center coordinate in the certain number of pixels;
obtaining an upper boundary bottom _ c and a lower boundary top _ c of the new circle;
and setting all the connected domains above the upper boundary bottom _ c to be 0.
10. The blood vessel region determination method based on CTA image as claimed in claim 6, wherein after the abdominal bone and blood vessel data are layered, blood vessel features are extracted, specifically:
obtaining connectivity of the skeleton and the blood vessel mask after the layering processing, obtaining area, perimeter, centroid, boundary bbox and circularity of a connected domain, and further obtaining average CT value mean and standard deviation determination;
if the average CT value mean, the standard deviation determination and the circularity determination meet set judgment conditions, the blood vessel region is not determined;
if the area of the connected region area>πR2Perimeter>2 π R, mean CT value mean>0, if the standard deviation is greater than the set value, the blood vessel area is not; wherein R is the vessel radius;
if the centroid is not within the bounding box, it is not a vascular region.
11. The blood vessel region determination method based on CTA image as claimed in claim 2, wherein the blood vessel regions of both lower limbs are obtained by:
obtaining a communicating region of at least one double lower limb bone and a blood vessel mask, and obtaining an area, a perimeter and a boundary bbox of the communicating region;
extracting image bounding boxes meeting a judgment condition of 0<area<πR2，0<perimeter<2 pi R, wherein R is the vessel radius:
if the average CT value mean of the image bounding box is greater than 0 and the variance is smaller than a set value, the image bounding box is a double-lower-limb blood vessel;
and removing bone impurities from the double lower limb blood vessels in the z direction.
12. A blood vessel region determination system based on CTA image, comprising:
the segmentation module is used for segmenting the CTA image data to obtain data to be processed;
the automatic selection module is used for automatically selecting seed points based on the data to be processed;
the target data acquisition module is used for extracting target data from the data to be processed, wherein the target data comprises abdominal bone and blood vessel data;
the layering processing module is used for performing layering processing on the abdominal skeleton and blood vessel data;
and the blood vessel acquisition module is used for acquiring an abdominal blood vessel region.
CN202110026581.6A 2021-01-08 2021-01-08 Blood vessel region judging method and system based on CTA image Active CN112767332B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110026581.6A CN112767332B (en) 2021-01-08 2021-01-08 Blood vessel region judging method and system based on CTA image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110026581.6A CN112767332B (en) 2021-01-08 2021-01-08 Blood vessel region judging method and system based on CTA image

Publications (2)

Publication Number Publication Date
CN112767332A true CN112767332A (en) 2021-05-07
CN112767332B CN112767332B (en) 2024-05-17

Family

ID=75701163

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110026581.6A Active CN112767332B (en) 2021-01-08 2021-01-08 Blood vessel region judging method and system based on CTA image

Country Status (1)

Country Link
CN (1) CN112767332B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116051566A (en) * 2023-04-03 2023-05-02 华南师范大学 Automatic blood vessel segmentation method for CT enhanced image

Citations (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1472650A (en) * 2002-07-10 2004-02-04 日本电气株式会社 Information processor
US20050228272A1 (en) * 2004-04-09 2005-10-13 Daphne Yu System and method for automatically segmenting bones in computed tomography angiography data
WO2007050437A2 (en) * 2005-10-21 2007-05-03 The General Hospital Corporation Methods and apparatus for segmentation and reconstruction for endovascular and endoluminal anatomical structures
CN102609913A (en) * 2012-01-17 2012-07-25 浙江大学 Method for enhancing liver blood vessel and simultaneously dividing liver from blood vessel in CTA (computed tomography imaging) image
US20120259406A1 (en) * 2011-04-06 2012-10-11 Stefan Schreck Method and system for treating aneurysms
US20120269407A1 (en) * 2011-04-19 2012-10-25 Microsoft Corporation Automatic organ localization
CN103310436A (en) * 2013-03-12 2013-09-18 华南师范大学 Clifford-based three-dimensional region growing method
CN104978726A (en) * 2014-04-03 2015-10-14 上海联影医疗科技有限公司 Blood vessel extraction method
CN105167798A (en) * 2015-10-21 2015-12-23 穆亚平 Method for extracting blood vessel information from coronary artery CTA (computed tomographic angiography) image
CN105427329A (en) * 2015-12-21 2016-03-23 东软集团股份有限公司 Method and system for dividing double-limb blood vessel image based on CTA image
CN105513055A (en) * 2015-11-26 2016-04-20 东软集团股份有限公司 Method and apparatus for segmenting tissue in CTA image
CN106023198A (en) * 2016-05-16 2016-10-12 天津工业大学 Hessian matrix-based method for extracting aortic dissection of human thoracoabdominal cavity CT image
CN106780477A (en) * 2016-12-30 2017-05-31 上海联影医疗科技有限公司 A kind of blood flow analysis method and system
CN107045721A (en) * 2016-10-24 2017-08-15 东北大学 One kind extracts pulmonary vascular method and device from chest CT image
CN107451406A (en) * 2017-07-28 2017-12-08 海纳医信（北京）软件科技有限责任公司 Vessels analysis method, apparatus, storage medium and processor
CN110176004A (en) * 2019-04-24 2019-08-27 艾瑞迈迪科技石家庄有限公司 A kind of liver subsection method and system
CN110648338A (en) * 2019-09-25 2020-01-03 上海微创医疗器械（集团）有限公司 Image segmentation method, readable storage medium, and image processing apparatus
CN110652312A (en) * 2019-07-19 2020-01-07 慧影医疗科技（北京）有限公司 Blood vessel CTA intelligent analysis system and application
CN110908818A (en) * 2019-11-29 2020-03-24 上海联影医疗科技有限公司 Verification method, device, equipment and storage medium
CN112132837A (en) * 2020-08-19 2020-12-25 心医国际数字医疗系统(大连)有限公司 Chest bone automatic extraction method and system, electronic equipment and storage medium

Patent Citations (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1472650A (en) * 2002-07-10 2004-02-04 日本电气株式会社 Information processor
US20050228272A1 (en) * 2004-04-09 2005-10-13 Daphne Yu System and method for automatically segmenting bones in computed tomography angiography data
WO2007050437A2 (en) * 2005-10-21 2007-05-03 The General Hospital Corporation Methods and apparatus for segmentation and reconstruction for endovascular and endoluminal anatomical structures
US20120259406A1 (en) * 2011-04-06 2012-10-11 Stefan Schreck Method and system for treating aneurysms
US20120269407A1 (en) * 2011-04-19 2012-10-25 Microsoft Corporation Automatic organ localization
CN102609913A (en) * 2012-01-17 2012-07-25 浙江大学 Method for enhancing liver blood vessel and simultaneously dividing liver from blood vessel in CTA (computed tomography imaging) image
CN103310436A (en) * 2013-03-12 2013-09-18 华南师范大学 Clifford-based three-dimensional region growing method
CN104978726A (en) * 2014-04-03 2015-10-14 上海联影医疗科技有限公司 Blood vessel extraction method
CN105167798A (en) * 2015-10-21 2015-12-23 穆亚平 Method for extracting blood vessel information from coronary artery CTA (computed tomographic angiography) image
CN105513055A (en) * 2015-11-26 2016-04-20 东软集团股份有限公司 Method and apparatus for segmenting tissue in CTA image
CN105427329A (en) * 2015-12-21 2016-03-23 东软集团股份有限公司 Method and system for dividing double-limb blood vessel image based on CTA image
CN106023198A (en) * 2016-05-16 2016-10-12 天津工业大学 Hessian matrix-based method for extracting aortic dissection of human thoracoabdominal cavity CT image
CN107045721A (en) * 2016-10-24 2017-08-15 东北大学 One kind extracts pulmonary vascular method and device from chest CT image
CN106780477A (en) * 2016-12-30 2017-05-31 上海联影医疗科技有限公司 A kind of blood flow analysis method and system
CN107451406A (en) * 2017-07-28 2017-12-08 海纳医信（北京）软件科技有限责任公司 Vessels analysis method, apparatus, storage medium and processor
CN110176004A (en) * 2019-04-24 2019-08-27 艾瑞迈迪科技石家庄有限公司 A kind of liver subsection method and system
CN110652312A (en) * 2019-07-19 2020-01-07 慧影医疗科技（北京）有限公司 Blood vessel CTA intelligent analysis system and application
CN110648338A (en) * 2019-09-25 2020-01-03 上海微创医疗器械（集团）有限公司 Image segmentation method, readable storage medium, and image processing apparatus
CN110908818A (en) * 2019-11-29 2020-03-24 上海联影医疗科技有限公司 Verification method, device, equipment and storage medium
CN112132837A (en) * 2020-08-19 2020-12-25 心医国际数字医疗系统(大连)有限公司 Chest bone automatic extraction method and system, electronic equipment and storage medium

Non-Patent Citations (8)

* Cited by examiner, † Cited by third party
Title
H. SUZUKI: "Segmentation and analysis of pulmonary blood vessel from X-ray CT images", 《PROCEEDINGS OF THE ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY》 *
JIAFA HE: "Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction", 《ARXIV》, 14 December 2020 (2020-12-14) *
张睿;吴水才;周著黄;王月;吴薇薇;: "基于增强CT图像的肝脏血管三维分割方法研究", 中国医疗设备, no. 11, 25 November 2017 (2017-11-25) *
易颂平: "基于CTA三维重建子宫内膜癌患者血管指数与MVD关系的研究", 《中国优秀硕士论文全文数据库》, 15 December 2014 (2014-12-15) *
普外时间: "灵魂画手带你读懂 CTA 影像", 《HTTPS://WWW.SOHU.COM/A/341754174_656533》, 18 September 2019 (2019-09-18) *
王光磊;史英杰;苑昊;王洪瑞;刘秀玲;: "基于置信连接的CT血管造影分层可视化研究", 河北大学学报(自然科学版), no. 03, 25 May 2016 (2016-05-25) *
王胜军: "一种自适应区域生长的CTA血管分割算法", 《中国生物医学工程学会成立30周年纪念大会暨2010中国生物医学工程学会学术大会壁报展示论文》 *
陈文宽: "320排CT血管成像在腹主动脉瘤影像诊断中的应用价值分析", 《现代医用影像学》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116051566A (en) * 2023-04-03 2023-05-02 华南师范大学 Automatic blood vessel segmentation method for CT enhanced image

Also Published As

Publication number Publication date
CN112767332B (en) 2024-05-17

Similar Documents

Publication Publication Date Title
US20210106299A1 (en) Method and system for extracting lower limb vasculature
WO2018023917A1 (en) Method and system for extracting lower limb blood vessel
WO2018120644A1 (en) Blood vessel extraction method and system
Rusko et al. Fully automatic liver segmentation for contrast-enhanced CT images
CN112767333B (en) Dual-lower limb blood vessel region judging method and system based on CTA image
CN108305255B (en) Generation device of liver surgery cutting surface
US9230331B2 (en) Systems and methods for registration of ultrasound and CT images
CN111539944A (en) Lung focus statistical attribute acquisition method and device, electronic equipment and storage medium
CN113222974B (en) Automatic evaluation method and device for side branch circulation
CN109740602B (en) Pulmonary artery stage blood vessel extraction method and system
CN112132837B (en) Chest bone automatic extraction method, system, electronic equipment and storage medium
JP2015066311A (en) Image processor, image processing method, program for controlling image processor, and recording medium
JP2004222864A (en) Diagnosis supporting system, diagnosis supporting method and diagnosis supporting program
CN117974652B (en) Ultrasonic image auxiliary positioning method based on machine vision
CN106910193B (en) Scanning image processing method
Guerroudji et al. Automatic brain tumor segmentation, and 3d reconstruction and visualization using augmented reality
CN112767332B (en) Blood vessel region judging method and system based on CTA image
CN112862850A (en) Digital silhouette angiography image processing method and device
Karim et al. Left atrium segmentation for atrial fibrillation ablation
CN108573494B (en) Tubular structure extraction method and device
Yamaguchi et al. Three-dimensional semiautomatic liver segmentation method for non-contrast computed tomography based on a correlation map of locoregional histogram and probabilistic atlas
CN116912098A (en) Medical image processing method, system, device and storage medium for interventional operation
Mokri et al. Lung segmentation in CT for thoracic PET-CT registration through visual study
Yang et al. Graph cuts based left atrium segmentation refinement and right middle pulmonary vein extraction in C-arm CT
Araujo et al. Computer aided detection of deep inferior epigastric perforators in computed tomography angiography scans

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
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20240725

Address after: No. 1012, 20th Floor, No.1 Huangpu Road, Ganjingzi District, Dalian City, Liaoning Province 116000

Patentee after: Xiaorui Medical Technology (Dalian) Co.,Ltd.

Country or region after: China

Address before: 116023 403-404A, 3, 5 East Road, software park, Dalian hi tech Industrial Park, Liaoning

Patentee before: SENYINT INTERNATIONAL DIGITAL MEDICAL SYSTEM (DALIAN) Co.,Ltd.

Country or region before: China