CN110610502A - Automatic aortic arch region positioning and segmentation method based on CT image - Google Patents
Automatic aortic arch region positioning and segmentation method based on CT image Download PDFInfo
- Publication number
- CN110610502A CN110610502A CN201910884138.5A CN201910884138A CN110610502A CN 110610502 A CN110610502 A CN 110610502A CN 201910884138 A CN201910884138 A CN 201910884138A CN 110610502 A CN110610502 A CN 110610502A
- Authority
- CN
- China
- Prior art keywords
- aortic arch
- image
- region
- model
- aortic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000002376 aorta thoracic Anatomy 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000011218 segmentation Effects 0.000 title claims abstract description 38
- 210000004072 lung Anatomy 0.000 claims abstract description 19
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 210000000709 aorta Anatomy 0.000 claims description 27
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 210000000115 thoracic cavity Anatomy 0.000 claims description 8
- 210000000683 abdominal cavity Anatomy 0.000 claims description 7
- 210000001367 artery Anatomy 0.000 claims description 2
- 230000001788 irregular Effects 0.000 claims description 2
- 210000004888 thoracic abdominal cavity Anatomy 0.000 claims description 2
- 208000002251 Dissecting Aneurysm Diseases 0.000 abstract description 5
- 206010002895 aortic dissection Diseases 0.000 abstract description 5
- 210000000056 organ Anatomy 0.000 abstract description 5
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 238000002591 computed tomography Methods 0.000 description 40
- 230000001174 ascending effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 206010020772 Hypertension Diseases 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 239000010410 layer Substances 0.000 description 2
- 210000001835 viscera Anatomy 0.000 description 2
- 201000001320 Atherosclerosis Diseases 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 208000034693 Laceration Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000000702 aorta abdominal Anatomy 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000002224 dissection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000011229 interlayer Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 208000019553 vascular disease Diseases 0.000 description 1
Classifications
-
- 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
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/149—Segmentation; Edge detection involving deformable models, e.g. active contour models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an aortic arch region automatic positioning segmentation method based on a CT image, which can rapidly determine the position of the aortic arch in the CT image according to the position relation of the aortic arch and the pleuroperitoneal cavity and the elliptical characteristic of the aortic arch and completely segment the aortic arch region; the principle is that an elliptical model with adjustable size and angle is set by positioning the initial position of the right lung region in a CT image and the center point of the whole CT image, the elliptical model is moved on the connecting line of the image center point and the center of the right lung region, the aortic arch part is positioned by counting the maximum ratio of a gray histogram, and then the whole segmentation and extraction of the aortic region are completed by utilizing spatial continuity; the method eliminates the interference of other organ tissues on the extraction process of the aortic region through shape constraint, has strong robustness, and can be used for providing medical auxiliary diagnosis for aortic dissection cases.
Description
Technical Field
The invention relates to an automatic positioning and segmentation method for an aortic arch region in a Computed Tomography (CT) image of the thoracic and abdominal cavities, which is not influenced by the contrast of the CT image and other interfering organs, can accurately perform automatic positioning and segmentation extraction on the arch region of an aorta in the thoracic and abdominal cavities, belongs to the technical field of image processing, and can be used for providing medical auxiliary diagnosis for aortic dissection cases.
Background
In recent years, various vascular diseases caused by hypertension have great threat to human health, wherein aortic dissection caused by atherosclerosis due to long-term hypertension is the most dangerous cardiovascular disease, the main diagnosis method is thoracic and abdominal cavity CT scanning, and a doctor mainly analyzes the aortic region in each CT image to diagnose the disease condition, so that the aorta positioning and segmentation algorithm based on the CT image is designed to play a vital role in analyzing the disease condition and accurately performing the operation for the doctor.
Because the internal structure of the human pleuroperitoneal cavity where the aorta is located is relatively complex, a plurality of visceral organs tissues are relatively close to the aorta at spatial positions, even parts of the visceral organs are directly connected together, the aorta is not in a completely vertical state in the pleuroperitoneal cavity, and the spatial positions and the shapes of the aorta in the same group of CT image sequences are constantly changed, which is mainly divided into: ascending aorta, aortic arch and descending aorta. The aortic dissection is frequently performed in the aortic arch region, so that the longitudinal dissection of the whole aortic wall is caused, and therefore, the accurate positioning of the aortic arch region and the segmentation and extraction of the aortic arch region from the pleuroperitoneal cavity CT image set containing various other organ interferences are a problem to be solved urgently at present.
At present, a positioning segmentation algorithm for a CT image mainly comprises a method based on regions, boundaries and a specific theory, the principle based on the region method is simple and has high speed, but for images with unobvious gray level difference among different target regions, the segmentation and extraction effect needs to be improved; the method based on the boundary is suitable for the image with obvious edge and small noise, and has the defects of sensitivity to noise and easy obtaining of false edge or discontinuous edge for the image with complex edge; the segmentation method based on a specific theory mainly applies knowledge in the mathematical field to the image segmentation field, such as neural network, active shape model and the like, because two sample sets of an aortic arch and a descending aorta need to be established and trained into two models, and when a target segmentation part area is greatly different from the trained models, certain errors exist in segmentation and extraction.
The invention designs an aortic arch region automatic positioning segmentation algorithm based on a CT image, which can rapidly determine the position of an aortic arch part in a CT sequence image according to the position relation of the aortic arch part and the center of the pleuroperitoneal cavity and the elliptic shape characteristics of the aortic arch part, and completely segment and extract the aortic arch region; the method utilizes the continuity of the human thoracic and abdominal aorta and the shape characteristics of the ascending and descending aorta, eliminates the interference of other nearby organ tissues on the aorta extraction process through shape constraint, is not influenced by the contrast of the CT image, and has strong robustness.
Disclosure of Invention
The invention aims to overcome the defects of the existing aortic arch region positioning and segmenting method, and provides an aortic arch region automatic positioning and segmenting method based on a human body thoracic and abdominal cavity CT image. Therefore, the invention adopts the following technical scheme.
An aortic arch region automatic positioning segmentation method based on CT images comprises the following steps:
(1) firstly, defining the initial position of the right lung region in a CT image;
(2) then defining the central point of the whole CT image, and setting an elliptical region model with adjustable size, angle and position;
(3) moving the set elliptical model on a connecting line between the center point of the whole CT image and the center of the right lung, and calculating the real-time histogram distribution of the pixel gray value in the elliptical model;
(4) positioning and judging the aortic arch part by counting the ratio of the maximum value of the gray level histogram in the area of the elliptic model when the elliptic model is at different positions, wherein the position of the maximum ratio is the position of the aortic arch part; the number of layers in the CT sequence is the CT image layer to be cut;
(5) the method comprises the steps of roughly extracting the target boundary of the aortic arch part by using the space continuity of the aorta and a self-adaptive threshold value method, and finally realizing the accurate segmentation and extraction of the aortic arch part in the whole CT image sequence by using a level set segmentation algorithm;
in step 2, the center position of the thoracic abdominal cavity CT image is the center of the spine part of the human body, an elliptical model with the size consistent with the shape of the aortic arch region obtained through statistics is arranged, and the size and the position of the model can be freely changed;
in step 3, moving the elliptic model constructed in the step 2 on a connecting line between the center point of the CT image of the thoracic cavity and the abdominal cavity and the center point of the lung region defined in the step 1, simultaneously changing the size of the elliptic model, and then calculating gray level histograms of all pixels in the elliptic model;
in step 4, because the aortic arch region is in an irregular elliptical shape, when the model constructed in step 2 is approximately overlapped with the real aortic arch in the actual CT image, the maximum value in the corresponding gray level histogram takes the maximum proportion;
step 5, after the aortic arch part is automatically positioned, aortic segmentation is carried out along two directions; one direction is to divide the complete aortic arch part upwards, and the other direction is to divide the aortic arch part downwards to the aortic end; the starting points in the two directions, namely the upward direction and the downward direction, are the same, firstly, the threshold value is used for rough segmentation, and the automatic segmentation and extraction of the main artery region in all the CT images can be realized by using the space continuity and the level set of the aorta and taking the segmentation result of the previous time as the initial contour of the next time.
Compared with the prior art, the invention has the following advantages:
1. the method is simple and easy to realize. The invention finds that the position of the interlayer film laceration of a large number of aortic dissection cases starts from the aortic arch part through analysis, makes full use of the relationship characteristics of the aortic arch part and the spine and the right lung and the characteristics that the CT value is gentler, and realizes the accurate positioning of the aortic arch part area by carrying out pixel gray level histogram statistics in the connecting area between the CT image center (spine position) and the right lung center.
2. The accuracy is high. The invention fully utilizes the continuity of the aorta in the three-dimensional space, on the basis of accurately positioning the aortic arch step region, the aorta is segmented and extracted from two directions, one direction is upwards to segment the aortic arch part, the other direction is downwards to segment the aortic arch part to the tail end, the aorta is roughly segmented through a threshold value, and then the aorta segmentation and extraction of the whole CT image sequence are realized by utilizing the methods of the spatial continuity and the level set of the aorta, thereby better solving the problems that other methods are sensitive to noise, the target region is greatly different from a training sample, and the like and easily causes errors.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a CT scan of the thoracic and abdominal cavities of a human body, wherein the white frame shows the aortic arch region;
FIG. 3 is a histogram of gray values of pixels in the elliptical model at two different positions obtained by automatically moving the elliptical model on a connecting line between the center point of FIG. 1 and the center of the right lung, wherein (a) is the histogram with the highest ratio and (b) is the histogram at other positions;
fig. 4 is an image of the aortic arch region of fig. 2 after segmentation and extraction by the method of the present invention.
Detailed Description
The algorithm flow of the invention is shown in figure 1, the method comprises the steps of firstly positioning the initial position of a lung region in a CT image, then defining the central point of the whole CT image, setting an elliptical region model with adjustable size and angle, then moving the elliptical model on a connecting line of the central point of the image and the center of the right lung, calculating a gray histogram in the model, and positioning and distinguishing the aortic arch part by counting the ratio of the maximum value of the gray histogram; and finally, the aorta is integrally segmented by utilizing the spatial continuity of the aorta and through a self-adaptive threshold method and a level set segmentation algorithm. The following describes a specific implementation process of the technical solution of the present invention with reference to the accompanying drawings.
1. Defining a lung region in a CT image, and setting an elliptical region model with adjustable size and angle;
as shown in fig. 2, the aortic arch is positioned depending on the position of the aortic arch in the thoracic cavity of the human body, and the arch takes the shape of an ellipse and the pixel value. The aortic arch is positioned between the two lungs, is positioned at the upper right of the spine and the left side of the right lung, the spine is generally positioned at the center of the CT image, and because the change of the CT value in the aortic arch is stable, the aortic arch and the nearby tissues and organs are positioned and distinguished by utilizing the characteristics; the lung region in the CT image is positioned by a manual setting method, as the marking in fig. 2, and an elliptical region model with adjustable size and angle is set by combining the shape characteristics of the aortic arch part.
2. Moving the elliptical model on a connecting line between the image center point and the right lung center, and calculating a gray level histogram in the model;
calculating a central point (spine position) of the image, drawing an ellipse with adjustable angle positions at the aortic arch part according to the relation between the central point, the right lung and the aortic arch part, automatically moving an ellipse model on a connecting line of the center and the right lung center, and calculating a pixel gray distribution histogram in the ellipse, namely a gray histogram for short, wherein the numerical value of a gray pixel is related to a CT value;
the gray histogram is a function of the gray level of the pixel, describing the number of pixels in the image at that gray level. Namely: the abscissa represents the pixel gray level and the ordinate represents the number of occurrences of the pixel gray level in the image. The essence is a statistical map obtained by counting the number of gray pixels of each level, and a series of gray features can be obtained through a gray histogram. The gray histogram is defined as
Where i denotes the grey level, L denotes the grey value level, miIndicating the number of pixels with a gray level i and M indicating the total number of pixels in the total image.
3. Carrying out positioning judgment on the aortic arch part by counting the ratio of the maximum value of the gray histogram;
according to the relation between the position of the aortic arch part, the spine and the right lung part and the CT value, when the position, the size and the angle of the area of the aortic arch part and the elliptical model are consistent, most of the pixel gray histogram data in the elliptical model are concentrated on one numerical value, as shown in figure 3, therefore, whether the position of the elliptical frame is the aortic arch part or not can be judged according to the ratio of the maximum value of the histogram, and the positioning judgment of the aortic arch part area is realized.
4. The aorta is wholly segmented by using the aorta 3D space continuity and through an adaptive threshold method and a level set segmentation algorithm
According to the two-dimensional features of the aorta and the spatial continuity of the aorta, a certain aortic arch part is selected as a starting point of full-automatic segmentation, the ascending and descending aorta is searched downwards and segmented, the ascending and descending aorta is upwards till the top end of the aortic arch part, the two-direction segmentation and reconstruction are carried out, and the automatic segmentation and reconstruction work of the aorta is completed. The energy functional obtained by the level set method is generally not convex, and the segmentation result is sensitive to the initial contour and is easy to fall into a local threshold. The result is more accurate when the initial contour is closer to the target contour. Therefore, the Method of adaptive threshold is used for crude extraction of the target boundary, a Level Set Method is used for segmentation on the premise of ensuring that the initial contour is as close to the real contour as possible, a Level Set algorithm (LSM) is used for model calculation based on the geometric parameters of a curve, and the curve model evolution process is as follows:
let define a level set function φ (x, y, t) containing three variables in a continuous space: r2-R-→ R is a closed curve C (p, t) on the two-dimensional plane: 0 ≦ p ≦ 1 at time t, at which time the two-dimensional curve C (p, t) is described as a defined zero-level set of φ (x, y, t), so that the inward unit normal vector N is:
according to the curve evolution theory, in the process of applying the LSM to process the plane closed curve and aiming at continuously evolving and updating phi, the LSM can always process the curve evolution under the condition of high one-dimension, and the curve phi [ C (t), t and t in the two-dimensional plane corresponding to the zero level set]0, according to the nature of curve evolution theory, the curve calculation process should satisfy
As can be seen from the combination of the level set algorithm and the definition of the curve evolution theory, the variation of the defined phi along the evolution direction (i.e. unit normal vector) of the curve C is zero, i.e. the unit normal vectorCsWhere s is the arc length parameter of the planar curve C. At this time, a parameter indicating a change in phiTangent C to plane curve CsVertical, parametricIn the same direction as the normal to curve C. And (3) sorting the curve evolution theoretical formula and the calculation derivation formula to obtain:
when defining an arbitrary level set function phi0(x，y)：φ0(C0) When the value is equal to 0, the zero level set of phi (x, y, t) can satisfy the curve evolution theory in the evolution process according to the formula (3), that is, the zero level set of phi (x, y, t) is always kept as the target contour line C (p, t). At this time, the expression of the curvature of the curve C (p, t), derived by calculation, can be expressed as a level set function:
after the velocity field of the level set function is defined, an effective numerical method can be used for solving to obtain the contour of the target area. By the above method, segmentation and extraction of the aortic arch region are realized, and the extraction result is shown in fig. 4.
5. Summary of the invention
The invention designs a positioning and segmenting method of an aortic arch part based on a medical CT image, which fully utilizes the position relation among a spine, a right lung and the aortic arch part in the CT image, combines the gentle change characteristic of a CT value in an aortic region, constructs a movable elliptical model, utilizes the maximum ratio of a gray histogram in a statistical elliptical model to realize the accurate positioning of the aortic arch part region, and designs a method for combining an automatic threshold value with a level set.
Claims (1)
1. An aortic arch region automatic positioning segmentation method based on CT images comprises the following steps:
(1) firstly, defining the initial position of the right lung region in a CT image;
(2) then defining the central point of the whole CT image, and setting an elliptical region model with adjustable size, angle and position;
(3) moving the set elliptical model on a connecting line between the center point of the whole CT image and the center of the right lung, and calculating the real-time histogram distribution of the pixel gray value in the elliptical model;
(4) positioning and judging the aortic arch part by counting the ratio of the maximum value of the gray level histogram in the area of the elliptic model when the elliptic model is at different positions, wherein the position of the maximum ratio is the position of the aortic arch part; the number of layers in the CT sequence is the CT image layer to be cut;
(5) the method comprises the steps of roughly extracting the target boundary of the aortic arch part by using the space continuity of the aorta and a self-adaptive threshold value method, and finally realizing the accurate segmentation and extraction of the aortic arch part in the whole CT image sequence by using a level set segmentation algorithm;
in step 2, the center position of the thoracic abdominal cavity CT image is the center of the spine part of the human body, an elliptical model with the size consistent with the shape of the aortic arch region obtained through statistics is arranged, and the size and the position of the model can be freely changed;
in step 3, moving the elliptic model constructed in the step 2 on a connecting line between the center point of the CT image of the thoracic cavity and the abdominal cavity and the center point of the lung region defined in the step 1, simultaneously changing the size of the elliptic model, and then calculating gray level histograms of all pixels in the elliptic model;
in step 4, because the aortic arch region is in an irregular elliptical shape, when the model constructed in step 2 is approximately overlapped with the real aortic arch in the actual CT image, the maximum value in the corresponding gray level histogram takes the maximum proportion;
step 5, after the aortic arch part is automatically positioned, aortic segmentation is carried out along two directions; one direction is to divide the complete aortic arch part upwards, and the other direction is to divide the aortic arch part downwards to the aortic end; the starting points in the two directions, namely the upward direction and the downward direction, are the same, firstly, the threshold value is used for rough segmentation, and the automatic segmentation and extraction of the main artery region in all the CT images can be realized by using the space continuity and the level set of the aorta and taking the segmentation result of the previous time as the initial contour of the next time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910884138.5A CN110610502A (en) | 2019-09-18 | 2019-09-18 | Automatic aortic arch region positioning and segmentation method based on CT image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910884138.5A CN110610502A (en) | 2019-09-18 | 2019-09-18 | Automatic aortic arch region positioning and segmentation method based on CT image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110610502A true CN110610502A (en) | 2019-12-24 |
Family
ID=68892117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910884138.5A Pending CN110610502A (en) | 2019-09-18 | 2019-09-18 | Automatic aortic arch region positioning and segmentation method based on CT image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110610502A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112330708A (en) * | 2020-11-24 | 2021-02-05 | 沈阳东软智能医疗科技研究院有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN112561871A (en) * | 2020-12-08 | 2021-03-26 | 中国医学科学院北京协和医院 | Aortic dissection method and device based on flat scanning CT image |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020009215A1 (en) * | 2000-01-18 | 2002-01-24 | Arch Development Corporation | Automated method and system for the segmentation of lung regions in computed tomography scans |
| US20110206257A1 (en) * | 2008-04-16 | 2011-08-25 | Universite De Lausanne | Automatic detection and accurate segmentation of abdominal aortic aneurysm |
| 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 |
| CN109003278A (en) * | 2018-03-26 | 2018-12-14 | 天津工业大学 | A kind of improved CT image aorta segmentation method based on active shape model |
| CN109003283A (en) * | 2018-03-26 | 2018-12-14 | 天津工业大学 | A kind of aorta outline segmentation based on active shape model |
-
2019
- 2019-09-18 CN CN201910884138.5A patent/CN110610502A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020009215A1 (en) * | 2000-01-18 | 2002-01-24 | Arch Development Corporation | Automated method and system for the segmentation of lung regions in computed tomography scans |
| US20110206257A1 (en) * | 2008-04-16 | 2011-08-25 | Universite De Lausanne | Automatic detection and accurate segmentation of abdominal aortic aneurysm |
| 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 |
| CN109003278A (en) * | 2018-03-26 | 2018-12-14 | 天津工业大学 | A kind of improved CT image aorta segmentation method based on active shape model |
| CN109003283A (en) * | 2018-03-26 | 2018-12-14 | 天津工业大学 | A kind of aorta outline segmentation based on active shape model |
Non-Patent Citations (1)
| Title |
|---|
| XIAOJIE DUAN: "Automatic 3D Aorta Segmentation in CT Images" * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112330708A (en) * | 2020-11-24 | 2021-02-05 | 沈阳东软智能医疗科技研究院有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN112330708B (en) * | 2020-11-24 | 2024-04-23 | 沈阳东软智能医疗科技研究院有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN112561871A (en) * | 2020-12-08 | 2021-03-26 | 中国医学科学院北京协和医院 | Aortic dissection method and device based on flat scanning CT image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110136157B (en) | Three-dimensional carotid artery ultrasound image vessel wall segmentation method based on deep learning | |
| CN106204587B (en) | Multiple organ dividing method based on depth convolutional neural networks and region-competitive model | |
| CN109166124B (en) | Retinal blood vessel morphology quantification method based on connected region | |
| CN105913432B (en) | Aorta extracting method and device based on CT sequence images | |
| CN109858540B (en) | Medical image recognition system and method based on multi-mode fusion | |
| CN103310457B (en) | A kind of pulmonary parenchyma dividing method based on para-curve correction convex closure | |
| CN107862694A (en) | A kind of hand-foot-and-mouth disease detecting system based on deep learning | |
| CN107369160A (en) | A kind of OCT image median nexus film new vessels partitioning algorithm | |
| CN107203999A (en) | A kind of skin lens image automatic division method based on full convolutional neural networks | |
| CN104809723A (en) | Three-dimensional liver CT (computed tomography) image automatically segmenting method based on hyper voxels and graph cut algorithm | |
| CN104766316B (en) | New lip partitioning algorithm in tcm inspection | |
| CN108615239B (en) | Tongue image segmentation method based on threshold technology and gray level projection | |
| CN109753997B (en) | Automatic accurate robust segmentation method for liver tumor in CT image | |
| CN108230301A (en) | A kind of spine CT image automatic positioning dividing method based on active contour model | |
| CN116236150A (en) | Arteriovenous blood vessel image segmentation method based on fundus image | |
| CN108830856B (en) | GA automatic segmentation method based on time series SD-OCT retina image | |
| CN110796670A (en) | Dissection method and device for dissecting artery | |
| CN106570856A (en) | Common carotid artery intima-media thickness measuring device and method combining level set segmentation and dynamic programming | |
| CN110610502A (en) | Automatic aortic arch region positioning and segmentation method based on CT image | |
| CN112288794B (en) | Method and device for measuring blood vessel diameter of fundus image | |
| CN109583331A (en) | Human wrist arteries and veins mouth position precise positioning method based on deep learning | |
| CN112270667A (en) | TI-RADS-based integrated deep learning multi-tag identification method | |
| CN109919216B (en) | Counterlearning method for computer-aided diagnosis of prostate cancer | |
| CN109636864A (en) | A kind of tongue dividing method and system based on color correction Yu depth convolutional neural networks | |
| CN112712540B (en) | Lung bronchus extraction method based on CT image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191224 |