CN111784716A - Sequence diagram image segmentation method and system based on ultrasonic CT - Google Patents
Sequence diagram image segmentation method and system based on ultrasonic CT Download PDFInfo
- Publication number
- CN111784716A CN111784716A CN202010501314.5A CN202010501314A CN111784716A CN 111784716 A CN111784716 A CN 111784716A CN 202010501314 A CN202010501314 A CN 202010501314A CN 111784716 A CN111784716 A CN 111784716A
- Authority
- CN
- China
- Prior art keywords
- sequence
- image
- segmentation
- sequence diagram
- contour
- 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
- 238000010586 diagram Methods 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000003709 image segmentation Methods 0.000 title claims abstract description 40
- 230000011218 segmentation Effects 0.000 claims abstract description 77
- 241000270295 Serpentes Species 0.000 claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 35
- 238000002604 ultrasonography Methods 0.000 claims description 32
- 210000000481 breast Anatomy 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000012010 growth Effects 0.000 abstract description 6
- 238000013461 design Methods 0.000 abstract description 2
- 238000002591 computed tomography Methods 0.000 abstract 5
- 210000005075 mammary gland Anatomy 0.000 description 10
- 230000008569 process Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000005452 bending Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001808 coupling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 230000035040 seed growth Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- 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
- G06T2207/30068—Mammography; Breast
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention belongs to the field of image segmentation, and discloses a sequence diagram image segmentation method and a sequence diagram image segmentation system based on ultrasonic CT (computed tomography), wherein the segmentation method comprises the following steps: (1) selecting a group of ultrasonic CT sequence diagrams, carrying out segmentation processing on the images by utilizing a seed region growing method aiming at a certain sequence diagram, and recording the contour obtained by the segmentation processing as a rough contour; (2) and re-segmenting the sequence diagram by using the coarse contour as an initial contour and utilizing a snake model to obtain a refined segmentation result of the image. Preferably, the segmentation result can be used as an initial contour of the next sequence diagram, and the next diagram is segmented by using a snake model. The invention improves the whole flow design, the matching working mode and the like of the segmentation method, utilizes the matching algorithm of seed region growth and snake model to carry out high-precision image segmentation on the ultrasonic CT sequence image, and can effectively solve the problem of image segmentation of the ultrasonic CT sequence image compared with the prior art.
Description
Technical Field
The invention belongs to the technical field of image segmentation, and particularly relates to a sequence diagram image segmentation method and system based on ultrasonic CT.
Background
Ultrasonic CT is a method in which, on the basis of not damaging the internal structure of an object to be studied, projection data of the object under the irradiation of ultrasonic waves are measured by an ultrasonic device, and a two-dimensional or three-dimensional ultrasonic image can be reconstructed by using the data. Ultrasonic detection has the advantages of good directivity, low price, no harm to human body, portability of equipment and the like, so that a detection technology using ultrasonic waves as an emission source instead of rays to irradiate an object has gradually become one of new targets pursued by researchers in the field of ultrasonic application.
Taking a mammary gland as an object to be detected as an example, researching the medical image segmentation method of the ultrasonic CT, designing and realizing the segmentation method of the mammary gland ultrasonic CT image and the sequence diagram thereof, segmenting the mammary gland part, avoiding the influence of the image of water providing the coupling effect, saving an unnecessary visual field area, laying a cushion for the subsequent mammary gland three-dimensional reconstruction, and displaying the mammary gland condition to a doctor more intuitively and clearly in clinic by the segmented sequence diagram, which is beneficial to finding out a focus area quickly and efficiently and making a more accurate diagnosis and treatment result.
At present, the image segmentation method of ultrasonic CT has been realized on high-end ultrasonic products of main medical image enterprises abroad, but ultrasonic enterprises and research units mastering the technology are not available at home, and the main reason is that the selection of a proper ultrasonic CT sequence diagram image segmentation algorithm to realize the image segmentation of the high-precision sequence diagram is difficult.
Disclosure of Invention
In view of the above defects or improvement needs in the prior art, an object of the present invention is to provide a sequence diagram image segmentation method and system based on ultrasound CT, wherein the whole flow design of the segmentation method, and the component arrangement and the coordination working mode of the corresponding system are improved, and the matching algorithm of seed region growing and snake model is used to perform high-precision image segmentation on an ultrasound CT sequence diagram image, so that the problem of the segmentation of the ultrasound CT image reconstruction sequence diagram image can be effectively solved compared with the prior art.
To achieve the above object, according to one aspect of the present invention, there is provided a sequence map image segmentation method based on ultrasound CT, comprising the steps of:
(1) selecting a group of ultrasonic CT sequence diagrams, carrying out segmentation processing on the images by utilizing a seed region growing method aiming at a certain sequence diagram, and recording the contour obtained by the segmentation processing as a rough contour;
(2) and (2) taking the rough contour obtained in the step (1) as an initial contour, and re-segmenting the sequence diagram by using a snake model so as to obtain a refined segmentation result of the image.
According to another aspect of the present invention, there is provided a sequence diagram image segmentation method based on ultrasound CT, comprising the following steps:
(1) selecting a group of ultrasonic CT sequence images, and aiming at the first sequence image, carrying out segmentation processing on the image by using a seed region growing method, and recording the contour obtained by the segmentation processing as a rough contour;
(2) taking the rough contour obtained in the step (1) as an initial contour, and re-segmenting the first sequence diagram by using a snake model so as to obtain a refined segmentation result of the image;
(3) for the next sequence image in the group of ultrasonic CT sequence images, regarding the sequence image, the contour corresponding to the refined segmentation result obtained from the previous sequence image is used as an initial contour, and the sequence image is segmented by using a snake model, so that the refined segmentation result of the image is obtained; in this way, the refined segmentation result of the previous sequence diagram is repeatedly processed by using a snake model as the initial contour of the next sequence diagram, and the refined segmentation of the whole sequence diagram can be completed.
As a further preferred embodiment of the present invention, the set of ultrasound CT sequence charts is a set of breast ultrasound CT sequence charts.
As a further preferred aspect of the present invention, the ultrasound CT sequence diagram is an ultrasound CT sequence diagram reconstructed based on reflection data, an ultrasound CT sound velocity sequence diagram reconstructed based on transmission data, or an attenuation coefficient sequence diagram.
According to another aspect of the present invention, there is provided an ultrasound CT-based sequence image segmentation system, comprising:
the seed region growing method processing module is used for carrying out segmentation processing on the image by using a seed region growing method aiming at a certain sequence diagram of the selected group of ultrasonic CT sequence diagrams, and recording the contour obtained by the segmentation processing as a rough contour;
and the snake model processing module is used for taking the rough contour as an initial contour and utilizing a snake model to re-segment the sequence diagram so as to obtain a refined segmentation result of the image.
According to still another aspect of the present invention, there is provided an ultrasound CT-based sequence image segmentation system, comprising:
the seed region growing method processing module is used for carrying out segmentation processing on the image by using a seed region growing method aiming at the first sequence diagram of the selected group of ultrasonic CT sequence diagrams, and recording the contour obtained by the segmentation processing as a rough contour;
a snake model processing module for:
(i) taking the rough contour as an initial contour, and utilizing a snake model to re-segment the first sequence diagram so as to obtain a refined segmentation result of the image;
and (ii) for the next sequence in the set of ultrasound CT sequence, for the next sequence, using the contour corresponding to the refined segmentation result obtained from the previous sequence as the initial contour, and segmenting the sequence by using a snake model to obtain the refined segmentation result of the image; the result of the refined segmentation of the previous sequence diagram is used as the initial contour of the next sequence diagram, and the refined segmentation of the whole sequence diagram can be completed.
As a further preferred embodiment of the present invention, the set of ultrasound CT sequence charts is a set of breast ultrasound CT sequence charts.
As a further preferred aspect of the present invention, the ultrasound CT sequence diagram is an ultrasound CT sequence diagram reconstructed based on reflection data, an ultrasound CT sound velocity sequence diagram reconstructed based on transmission data, or an attenuation coefficient sequence diagram.
Compared with the prior art, the technical scheme provided by the invention has the advantages that the image segmentation is carried out on the ultrasonic CT sequence image by utilizing the matching algorithm of seed region growth and snake model aiming at the ultrasonic CT sequence image, and the high-precision image segmentation can be realized.
When the snake model method is directly used for image segmentation, because the method is sensitive to the position of an initial contour, the method often adopts a manual point-taking method to draw the initial contour to pursue the accuracy of a segmentation result, a user firstly judges an interested region, selects a plurality of points which are close to a target, and then interpolates to obtain the initial contour, so that the position of the initial contour can be ensured to cover the target region without deviating too far. However, the manual selection method brings inconvenience to the user, and the segmentation result is also uncertain and unstable due to human factors such as judgment errors of the user. Aiming at the image types of the ultrasonic CT sequence diagram, the method provided by the invention particularly adjusts the initial contour selection step of the Snake model method, abandons the manual point-taking mode, and uses the seed region growing method to process the image firstly to obtain a more accurate initial contour as the input value of the Snake method, so that the image segmentation process is more automatic. And under the pre-participation of the seed growth method, the initial contour used by the Snake model method is more accurate, and the Snake method can play a role in further refining and segmenting to obtain a more accurate segmentation result. Meanwhile, because two adjacent images in the sequence diagram are similar, the segmentation result of the previous sequence diagram is used as the initial contour of the next sequence diagram, and the segmentation speed and the segmentation precision can be further increased.
Drawings
Figure 1 is a sequence diagram of the UCT mammary gland.
FIG. 2 is a sequence diagram of the seed region growing and Snake model combined algorithm after segmentation in the present invention.
FIG. 3 is a flowchart of the sequence diagram image segmentation method based on ultrasound CT in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention discloses a sequence image segmentation method based on ultrasonic CT, which is an ultrasonic CT sequence image segmentation method based on the combination of seed region growth and a snake model. And then the initial contour of the Snake model method is used as the initial contour of the Snake model method, the segmentation result of the first graph can be used as the initial contour of the second graph, and thus the segmentation of the whole sequence graph can be completed by using the segmentation result of the previous sequence graph as the initial contour of the next sequence graph.
The corresponding sequence image segmentation system based on the ultrasonic CT can comprise a seed region growing method processing module and a snake model processing module, wherein:
the seed region growing method processing module is used for carrying out segmentation processing on the image by using a seed region growing method aiming at the first sequence diagram of the selected group of ultrasonic CT sequence diagrams, and recording the contour obtained by the segmentation processing as a rough contour;
a snake model processing module for:
(i) taking the rough contour as an initial contour, and utilizing a snake model to re-segment the first sequence diagram so as to obtain a refined segmentation result of the image;
and (ii) for the next sequence in the set of ultrasound CT sequence, for the next sequence, using the contour corresponding to the refined segmentation result obtained from the previous sequence as the initial contour, and segmenting the sequence by using a snake model to obtain the refined segmentation result of the image; the result of the refined segmentation of the previous sequence diagram is used as the initial contour of the next sequence diagram, and the refined segmentation of the whole sequence diagram can be completed.
Taking an ultrasonic CT sequence diagram of a mammary gland as an example, the sequence diagram image segmentation method based on the ultrasonic CT can firstly segment a first sequence diagram, obtain a relatively rough mammary gland region segmentation result by adopting a seed region growing method, perform data processing on the result to obtain edge point coordinates of a rough contour, serve as an initial contour point of a Snake model method, and further refine and segment by the Snake model method.
Since the difference between two adjacent layers of the sequence diagram is relatively small, the result of the previous layer can be used for image segmentation of the next layer. Therefore, after the division of the first graph is completed, the result of the first graph is used as the initial contour of the second graph, the second graph is divided by using a snake model method, the result of the second graph is used for the third division, all sequence graphs are operated in sequence, and all division can be completed.
The seed region growing method and the Snake model method related by the invention can refer to the prior art.
For example, the sequence diagram image segmentation method based on the ultrasonic CT in the present invention can be processed according to the following processing procedures:
the first sequence diagram is first divided by means of a seed region growing method, which is based on the SRG methodIn the conventional region growing method, a pixel with a similar gray value is assumed to be a region, and a gray judgment criterion is set to achieve the purpose of segmentation (the judgment criterion can be preset according to actual requirements) starting from selecting a seed point. The SRG method first selects seed points from the graph, which are divided into n sets: a. the1，A2，A3...An. There may be a set that contains only a single point. With the seed points, the seed region growing method can segment the image into regions with the following properties: each connecting part of the region is exactly connected with AiOne point in (non-empty intersection), under this constraint, the region is selected to be as homogenous as possible.
And carrying out loop iteration in the region growing process of the seed points according to a certain rule, wherein each growing process can increase one pixel point in the set. The growth criterion is described in the case after the m-th growth. Let T be the set of all unassigned pixels adjacent to at least one region:
if x ∈ T, then N (x) is considered to intersect ai.I (x) is defined as such that i (x) ∈ {1, 2
And (x) is defined to measure the degree of difference between x and its adjoining area. (x) The simplest definition is as follows:
where g (x) represents the gray value of the image point x. If N (x) is present with a plurality of AiCrossing, then assigning to i (x) a number satisfying N (x) and AiIn this case, x may also be defined as a boundary pixel and added to the set B of known boundary pixels.then we take z ∈ T and satisfy:
add z to set ai(z)。
The above process is repeated until all pixels have been allocated. Several areas of complete growth allocated according to the initially selected seed points can be obtained. In a specific implementation, a data structure called a sequential sorting table may be used, and the sequential sorting table is a linked list of objects and is sorted according to characteristics. The algorithm for SRG is implemented as follows: firstly, marking the seed points according to the initial grouping, and entering the neighborhood of the seed points into a sequential sorting table for recording. The first point in the table is taken and the neighborhood of the point is checked for marking, if all neighborhoods that have been marked (except for the point marked as the border) have the same mark, the point is set to the same mark and the gray average of the area is recalculated and the unmarked points in the neighborhood of the point are put into the sorted list. The above steps are continuously executed until the ordered list is empty. And finally, marking the same area as the result of the segmentation.
And the set B of the boundary pixel points is the target contour obtained based on the seed growing method.
After the initial contour of the ultrasonic CT image is obtained by using a seed region growing method, in order to enable the segmentation result to be more accurate, the initial contour is used as the initial contour of a Snake model method, and the segmentation function can be further refined by using the Snake method.
The Snake model is a segmentation method taking the detection of edges by a calculated energy function as a core. The main principle is that the profile is moved to the direction of minimum energy according to the energy function of the initial profile, and when the energy function reaches the minimum, the initial profile is moved to the edge of the target area. In summary, the snake model can be regarded as a curve, and a new parameter is calculated to control the curve deformation under the target trend of minimizing energy according to the corresponding energy function, so as to fit the target area.
The deformation curve of the Snake model consists of a set of points v(s) ═ x(s), y(s) ], s ∈ [0,1], where x and y are coordinate positions describing the points, and s, which is an argument, is in the form obtained by fourier transformation. I (v) the energy function is calculated at each point for the grey values of the image.
The first term in the expression is elastic energy controlled by a parameter alpha, the second term is bending energy controlled by beta, the two terms are called internal energy of the image (alpha and beta can be constants, values of the two terms can be preset according to a segmentation object), curve characteristics of a Snake model are mainly controlled, the elastic energy is used for controlling the contour to be compressed into a circle and ensuring continuity of the contour, the bending energy is used for controlling the smoothness degree of the contour, and the third term is only related to information of the image, namely external force, namely image force. The image force is usually obtained by calculating the image gradient value of the point
The problem of searching the target contour becomes an energy functional problem in this way, and is converted into an Euler equation to be solved:
after the initial contour is selected, points on the initial contour are used as v(s), iteration is carried out by using an energy function, and the final edge contour point is obtained by solving.
By the above division method, the division result of the first graph in the sequence graph can be obtained. The relevance of the upper and lower layer pictures of the sequence diagram is large, and the shape and the size of the pictures are slightly changed. The Snake model segmentation can fully utilize the characteristic, after a first segmented image is obtained, the obtained contour coordinates of the first image are used as the initial contour of a second sequence diagram, the second diagram is continuously segmented by using a sanke model, the result of the second diagram can be used for a third diagram in the same way, and the sequence diagram can be completely segmented by continuously using the upper segmentation result as the lower initial contour.
FIG. 1 shows a sequence diagram of an initial mammary gland, and FIG. 2 shows a sequence diagram of a mammary gland after segmentation by the method of the present invention; as can be seen from FIG. 2, the segmentation result of the present invention has very clear boundary and high precision.
The physical meanings, initial settings and other details not specified above regarding the various formulae and parameters used in the seed region Growing process are referred to in the prior art, such as IEEE Transactions on Pattern Analysis and machine understanding, Vol.16, No.6,1994, by Rolf Adams et al.
The physical meanings, initial settings and other details not described in detail of the above formulas and parameters used in the Snake model processing can be found in the prior art, such as Kass, M., Witkin, A.andTerzopoulos, D.A. (Snakes: Active content Models, 1988, 321-.
The sequence image segmentation method and the sequence image segmentation system based on the ultrasonic CT are suitable for various ultrasonic CT sequence images, an ultrasonic CT system is used for collecting data of an imaging object, a reflection map, a sound velocity map and an attenuation coefficient map of the imaging object can be reconstructed, and corresponding sequence images can be obtained by moving a probe up and down; in addition, the present invention is applicable to other subjects than the breast as the detection subject as long as they are suitable for the ultrasound CT examination.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. A sequence diagram image segmentation method based on ultrasonic CT is characterized by comprising the following steps:
(1) selecting a group of ultrasonic CT sequence diagrams, carrying out segmentation processing on the images by utilizing a seed region growing method aiming at a certain sequence diagram, and recording the contour obtained by the segmentation processing as a rough contour;
(2) and (2) taking the rough contour obtained in the step (1) as an initial contour, and re-segmenting the sequence diagram by using a snake model so as to obtain a refined segmentation result of the image.
2. A sequence diagram image segmentation method based on ultrasonic CT is characterized by comprising the following steps:
(1) selecting a group of ultrasonic CT sequence images, and aiming at the first sequence image, carrying out segmentation processing on the image by using a seed region growing method, and recording the contour obtained by the segmentation processing as a rough contour;
(2) taking the rough contour obtained in the step (1) as an initial contour, and re-segmenting the first sequence diagram by using a snake model so as to obtain a refined segmentation result of the image;
(3) for the next sequence image in the group of ultrasonic CT sequence images, regarding the sequence image, the contour corresponding to the refined segmentation result obtained from the previous sequence image is used as an initial contour, and the sequence image is segmented by using a snake model, so that the refined segmentation result of the image is obtained; in this way, the refined segmentation result of the previous sequence diagram is repeatedly processed by using a snake model as the initial contour of the next sequence diagram, and the refined segmentation of the whole sequence diagram can be completed.
3. The ultrasound-CT-based sequence diagram image segmentation method according to claim 1 or 2, wherein the set of ultrasound CT sequence diagrams is a set of breast ultrasound CT sequence diagrams.
4. The sequence diagram image segmentation method based on the ultrasonic CT as set forth in claim 1 or 2, wherein the ultrasonic CT sequence diagram is an ultrasonic CT sequence diagram reconstructed based on reflection data, an ultrasonic CT sound velocity sequence diagram reconstructed based on transmission data or an attenuation coefficient sequence diagram.
5. A sequence diagram image segmentation system based on ultrasound CT, comprising:
the seed region growing method processing module is used for carrying out segmentation processing on the image by using a seed region growing method aiming at a certain sequence diagram of the selected group of ultrasonic CT sequence diagrams, and recording the contour obtained by the segmentation processing as a rough contour;
and the snake model processing module is used for taking the rough contour as an initial contour and utilizing a snake model to re-segment the sequence diagram so as to obtain a refined segmentation result of the image.
6. A sequence diagram image segmentation system based on ultrasound CT, preferably comprising:
the seed region growing method processing module is used for carrying out segmentation processing on the image by using a seed region growing method aiming at the first sequence diagram of the selected group of ultrasonic CT sequence diagrams, and recording the contour obtained by the segmentation processing as a rough contour;
a snake model processing module for:
(i) taking the rough contour as an initial contour, and utilizing a snake model to re-segment the first sequence diagram so as to obtain a refined segmentation result of the image;
and (ii) for the next sequence in the set of ultrasound CT sequence, for the next sequence, using the contour corresponding to the refined segmentation result obtained from the previous sequence as the initial contour, and segmenting the sequence by using a snake model to obtain the refined segmentation result of the image; the result of the refined segmentation of the previous sequence diagram is used as the initial contour of the next sequence diagram, and the refined segmentation of the whole sequence diagram can be completed.
7. The ultrasound-CT-based sequence diagram image segmentation system as set forth in claim 5 or 6, wherein the set of ultrasound CT sequence diagrams is a set of breast ultrasound CT sequence diagrams.
8. The ultrasound CT-based sequence chart image segmentation system as set forth in claim 5 or 6, wherein the ultrasound CT sequence chart is an ultrasound CT sequence chart reconstructed based on reflection data, an ultrasound CT sound velocity sequence chart reconstructed based on transmission data, or an attenuation coefficient sequence chart.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010501314.5A CN111784716A (en) | 2020-06-04 | 2020-06-04 | Sequence diagram image segmentation method and system based on ultrasonic CT |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010501314.5A CN111784716A (en) | 2020-06-04 | 2020-06-04 | Sequence diagram image segmentation method and system based on ultrasonic CT |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111784716A true CN111784716A (en) | 2020-10-16 |
Family
ID=72753954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010501314.5A Pending CN111784716A (en) | 2020-06-04 | 2020-06-04 | Sequence diagram image segmentation method and system based on ultrasonic CT |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111784716A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130195324A1 (en) * | 2010-03-15 | 2013-08-01 | Georgia Tech Research Corporation | Cranial suture snake algorithm |
| CN103440665A (en) * | 2013-09-13 | 2013-12-11 | 重庆大学 | Automatic segmentation method of knee joint cartilage image |
| CN104599270A (en) * | 2015-01-18 | 2015-05-06 | 北京工业大学 | Breast neoplasms ultrasonic image segmentation method based on improved level set algorithm |
| CN107481252A (en) * | 2017-08-24 | 2017-12-15 | 上海术理智能科技有限公司 | Dividing method, device, medium and the electronic equipment of medical image |
| CN109035268A (en) * | 2018-07-03 | 2018-12-18 | 南方医科大学 | A kind of self-adaptive projection method method |
-
2020
- 2020-06-04 CN CN202010501314.5A patent/CN111784716A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130195324A1 (en) * | 2010-03-15 | 2013-08-01 | Georgia Tech Research Corporation | Cranial suture snake algorithm |
| CN103440665A (en) * | 2013-09-13 | 2013-12-11 | 重庆大学 | Automatic segmentation method of knee joint cartilage image |
| CN104599270A (en) * | 2015-01-18 | 2015-05-06 | 北京工业大学 | Breast neoplasms ultrasonic image segmentation method based on improved level set algorithm |
| CN107481252A (en) * | 2017-08-24 | 2017-12-15 | 上海术理智能科技有限公司 | Dividing method, device, medium and the electronic equipment of medical image |
| CN109035268A (en) * | 2018-07-03 | 2018-12-18 | 南方医科大学 | A kind of self-adaptive projection method method |
Non-Patent Citations (2)
| Title |
|---|
| 房春兰等: "肝脏CT图像三维分割研究", 《电子科技大学学报》, vol. 38, no. 2, 31 March 2009 (2009-03-31), pages 278 - 281 * |
| 牛金海: "《超声原理及生物医学工程应用 生物医学超声学》", 上海交通大学出版社, pages: 213 - 216 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5931755B2 (en) | Increased probability of model-based segmentation | |
| US7865002B2 (en) | Methods and apparatus for computer automated diagnosis of mammogram images | |
| CN110517238B (en) | AI three-dimensional reconstruction and human-computer interaction visualization network system for CT medical image | |
| US8036436B2 (en) | System and method for segmenting a region in a medical image | |
| US7529396B2 (en) | Method, computer program product, and apparatus for designating region of interest | |
| US20070116334A1 (en) | Method and apparatus for three-dimensional interactive tools for semi-automatic segmentation and editing of image objects | |
| US8077948B2 (en) | Method for editing 3D image segmentation maps | |
| CN107590809A (en) | Lung dividing method and medical image system | |
| CN107440730A (en) | Breast image alignment method and image processing device | |
| CN107103605B (en) | Breast tissue segmentation method | |
| CN101103924A (en) | Galactophore cancer computer auxiliary diagnosis method based on galactophore X-ray radiography and system thereof | |
| CN106887000A (en) | The gridding processing method and its system of medical image | |
| CN112529834A (en) | Spatial distribution of pathological image patterns in 3D image data | |
| US9361711B2 (en) | Lesion-type specific reconstruction and display of digital breast tomosynthesis volumes | |
| Chen et al. | Real-time freehand 3D ultrasound imaging | |
| EP2353141B1 (en) | One-click correction of tumor segmentation results | |
| CN113223028A (en) | Multi-modal liver tumor segmentation method based on MR and CT | |
| Li et al. | Segmentation of human aorta using 3D nnU-net-oriented deep learning | |
| US10891776B2 (en) | Imaging system and method | |
| CN117115437A (en) | Multi-index multi-organ medical image segmentation model evaluation system based on region | |
| CN111784716A (en) | Sequence diagram image segmentation method and system based on ultrasonic CT | |
| Aydin et al. | A hybrid image processing system for X-ray images of an external fixator | |
| CN115035207A (en) | Method and device for generating fetal craniocerebral standard section and ultrasonic imaging display system | |
| Hopp et al. | Registration of 3D ultrasound computer tomography and MRI for evaluation of tissue correspondences | |
| Bornik et al. | Interactive editing of segmented volumetric datasets in a hybrid 2D/3D virtual environment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201016 |
|
| RJ01 | Rejection of invention patent application after publication |