CN112862793B - Rib centerline extraction method and device based on rib three-dimensional morphology and distribution - Google Patents
Rib centerline extraction method and device based on rib three-dimensional morphology and distribution Download PDFInfo
- Publication number
- CN112862793B CN112862793B CN202110195185.6A CN202110195185A CN112862793B CN 112862793 B CN112862793 B CN 112862793B CN 202110195185 A CN202110195185 A CN 202110195185A CN 112862793 B CN112862793 B CN 112862793B
- Authority
- CN
- China
- Prior art keywords
- rib
- center
- point
- dimensional
- center line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000605 extraction Methods 0.000 title abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000009499 grossing Methods 0.000 claims abstract description 10
- 238000004590 computer program Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 abstract description 6
- 208000027790 Rib fracture Diseases 0.000 abstract description 5
- 238000005452 bending Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000002591 computed tomography Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 9
- 238000003745 diagnosis Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 210000004072 lung Anatomy 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 208000010392 Bone Fractures Diseases 0.000 description 2
- 206010017076 Fracture Diseases 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013170 computed tomography imaging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 238000013316 zoning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—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
- G06T7/60—Analysis of geometric attributes
-
- 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
-
- 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
- G06T2207/30172—Centreline of tubular or elongated structure
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Respiratory Apparatuses And Protective Means (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a rib center line extraction method and device based on three-dimensional rib morphology and distribution. The method at least comprises the following steps: and carrying out region division on the rib mask according to the rib morphology priori, extracting the central point of each region, connecting the central points to serve as a rough central line, and carrying out smoothing operation on the obtained rough central line to obtain a smooth rib central line. The method does not need to carry out three-dimensional reconstruction or surface extraction, has a speed faster than that of an algorithm for extracting the surface model, well solves the problem of bending, is not limited by factors such as rib fracture and the like, ensures a smoother rib center line extraction result, and can be better beneficial to the subsequent rib tiling process.
Description
Technical Field
The invention belongs to the field of image technical processing, and particularly relates to a method and a device for rib center line extraction based on rib morphology priori.
Background
Computer Tomography (CT) is the main method for diagnosing rib fracture, and at present, the traditional rib CT diagnosis is mainly carried out by two-dimension and three-dimension image positioning is used as assistance. However, in the rib fracture diagnosis process, the conventional two-dimensional method generally needs to manually track a plurality of CT tomographic slices, and repeatedly observe the CT cross sections so as to track the dynamic change of each rib on different slices, thereby increasing the diagnosis difficulty of doctors, consuming time, having strong subjectivity and being easy to miss. Compared with two-dimensional CT, the three-dimensional CT imaging changes the original plane image into a three-dimensional image, and can observe the whole condition of the rib, but because the cage-shaped structure of the rib is easy to be shielded, some small fracture focus is easy to be missed in the diagnosis of the traditional three-dimensional method.
The three-dimensional tiling of the ribs, namely tiling the ribs from the three-dimensional cage-shaped structure to a plane, can realize the display of the morphological details of each rib on the plane, so that the rib display is more visual, the visualization of the unfolded ribs is enhanced, and the accuracy and the diagnosis efficiency of rib fracture diagnosis of doctors are greatly improved. In rib tiling, rib voxels need to be deformed depending on rib center lines, and in this process, rib center line extraction is important.
At present, the rib centerline extraction related technology is less, and the three-dimensional reconstruction with slow dependence speed is mainly concentrated or the centerline extraction is performed on the surface trend depending on the ribs. The extraction of the rib surface is easy to be influenced by fracture and other conditions, and the existing algorithm is easy to extract a central line with a large number of bends and needs to rely on post-processing calculation for smoothing.
Disclosure of Invention
In order to solve the problems, the invention provides a rib center line extraction method based on a rib three-dimensional form and distribution, which has a speed faster than that of an algorithm for extracting a surface model, well solves the problem of bending, is not limited by factors such as rib fracture, ensures a smoother rib center line extraction result, and can be better beneficial to the subsequent rib tiling process.
The rib center line extraction method provided by the invention comprises the following steps:
according to rib morphology priori, dividing the region of the rib mask;
extracting the center point of each region and connecting the center points to serve as a thick center line;
and smoothing the obtained rough center line to ensure the smoothness of the finally obtained center line.
In a preferred embodiment, three dimensions ribmask are converted to two dimensions ribslice prior to zoning the rib mask.
In a preferred embodiment, the conversion of the three dimensions ribmask to a two-dimensional ribslice is performed according to the following formula, where a rib segmentation map ribmask (rib region value 1, non-rib region value 0) of the chest CT image is obtained by using a segmentation algorithm, and for each rib individually, the size is height with depth, and the coordinates y, x, z are corresponding. Wherein, the height corresponds to the direction from the chest to the spine, the width corresponds to the left-right direction of the human body, the depth corresponds to the direction from the head to the foot, and the coordinate system takes the upper left corner of one CT scan as the origin. The patient is stacked ribmask in the axial direction in which the patient lies, converting the three-dimensional ribmask into a two-dimensional ribslice.
In a preferred embodiment, the region division of the rib mask is performed according to the following steps: the center point ribcenter of ribslice is extracted. The cartesian coordinates of the point ribpoint in each rib on ribslice, i.e., the point having a value of 1, are converted into polar coordinates centering on ribcenter to obtain the angular relationship of each point ribpoint with respect to ribcenter. From 0 to 360 degrees per n degrees, where n is any number of degrees in the range of 1-20 degrees, preferably 6, all ribpoint are divided into groups, the group located in the rib region being designated ribsegments.
The method for extracting the center point ribcenter of ribslice comprises the following steps: and respectively finding the minimum value and the maximum value on the x axis and the y axis through the coordinate relation, extracting the circumscribed rectangle of the region of the ribs of the package ribslice, and obtaining the center point ribcenter of the rectangle.
In a preferred embodiment, the specific operation of extracting the center point of each region and connecting it together as a thick center line is: the set of the means of Cartesian coordinates inside each ribsegments (the means of the x-direction and y-direction coordinates are obtained respectively) is the thick center line of the rib.
In a preferred embodiment, the smoothing operation for the coarse center line adopts a Moving Average method.
The Moving Average method comprises the following specific operations: the rib thick center line is smoothed in a sliding window manner, the step length of the sliding window is 1, and the window width is 7 continuous ribsegments center points. For each coordinate point p, the front and rear 3 coordinate points and p are taken as p smoothed center points by the average value of 7 center points.
The second aspect of the present invention also provides a computer apparatus comprising a memory, a processor and a computer program stored on the memory. The processor executes the computer program to realize the rib center line extraction method based on the rib three-dimensional morphology and distribution.
The third aspect of the present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the rib centerline extraction method described above based on a three-dimensional morphology and distribution of ribs.
The fourth aspect of the present invention also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the rib centerline extraction method described above based on rib three-dimensional morphology and distribution.
The rib center line extraction method based on rib morphology priori provided by the invention has the following outstanding technical effects:
1. The rib center line extraction method based on the three-dimensional morphology and distribution of the rib is different from the situation that the efficiency of extracting the rib center line is low due to the fact that a large number of processes such as three-dimensional reconstruction or surface extraction which are slow in dependence speed in the past are conducted, the rib center line extraction algorithm based on the three-dimensional morphology and distribution of the rib does not need to conduct three-dimensional reconstruction or surface extraction, and the rib center line can be extracted rapidly.
2. The extracted central line is smoothly adjusted based on the central line smoothing method of the sliding window, so that the situation that the extracted central line has burrs or is not smooth is avoided, and the follow-up rib tiling process is facilitated.
Drawings
FIG. 1 is an effect diagram of a crescent rib plane
FIG. 2 is an effect diagram of rib region segmentation in accordance with the method of the present invention
FIG. 3 is a graph of rib centerline effects extracted in accordance with the method of the present invention
FIG. 4 is a diagram showing the effect of rib centerline extraction
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
Unless defined otherwise hereinafter, all technical and scientific terms used herein are intended to be identical to what is commonly understood by one of ordinary skill in the art. References to techniques used herein are intended to refer to techniques commonly understood in the art, including variations of those that are obvious to those skilled in the art or alternatives to equivalent techniques. While the following terms are believed to be well understood by those skilled in the art, the following definitions are set forth to better explain the present invention.
As used herein, the terms "comprising," "including," "having," "containing," or "involving," and other variations thereof herein, are inclusive (inclusive) or open-ended and do not exclude other, unrecited elements or method steps.
The indefinite or definite article "a" or "an" when used in reference to a singular noun includes a plural of that noun.
The terms "about" and "substantially" in this invention mean the range of accuracy that one skilled in the art can understand yet still guarantee the technical effect of the features in question. The term generally means a deviation of + -10%, preferably + -5%, from the indicated value.
Furthermore, the terms first, second, third, (a), (b), (c), and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and that the embodiments of the invention described herein are capable of operation in other sequences than described or illustrated herein.
The algorithm provided by the invention extracts the central line of each rib based on the mask for rib segmentation. The ribs are relatively fixed in three dimensions, each rib wraps the lung in a crescent shape, and the ribs surround a central shaft area with the center of the lung. Based on the prior of the fixed shape, a coordinate system can be established by taking the centers of the left lung and the right lung as reference points, and the coordinates of each point of the rib mask are converted into polar coordinates. The ribs can then be split into different regions according to the angular relationship of the ribs in the converted polar coordinates. Extracting the center point of each region, and connecting the center points in series to obtain the initial center line. The centerline points are then smoothed.
The following are specific examples.
The rib center line extraction method provided by the embodiment of the invention comprises the following steps: firstly, dividing regions of a rib mask according to rib morphology priori; subsequently, the center point of each region is extracted and connected as a thick center line; and finally, smoothing the obtained rough center line to ensure the smoothness of the finally obtained center line.
Firstly, a rib segmentation map ribmask (rib region value is 1, non-rib region value is 0) of the chest CT image is obtained by using a segmentation algorithm. For each rib alone, the dimensions are height with depth, corresponding to the coordinates y, x, z. Wherein, the height corresponds to the direction from the chest to the spine, the width corresponds to the left-right direction of the human body, the depth corresponds to the direction from the head to the foot, and the coordinate system takes the upper left corner of one CT scan as the origin. The patient is stacked ribmask in the axial direction in which the patient lies, converting the three-dimensional ribmask into a two-dimensional ribslice.
The effect of the crescent rib plane is shown in figure 1.
And secondly, dividing rib areas, extracting the central point of each area and connecting the central points as thick central lines.
Centerline point extraction is performed on the ribslice map obtained in the first step, and the morphology prior of the crescent shape of ribslice is fully used. First, the center point of ribslice is extracted. And respectively finding the minimum value and the maximum value on the x axis and the y axis through the coordinate relation, extracting the circumscribed rectangle of the region of the ribs of the package ribslice, and obtaining the center point ribcenter of the rectangle. Subsequently, the cartesian coordinates of the point ribpoint in each rib on ribslice, that is, the point having a value of 1, are converted into polar coordinates centering on ribcenter, and the angular relationship of each point ribpoint with respect to ribcenter is obtained. From 0 to 360 degrees, one group per 6 degrees, all ribpoint are divided into multiple groups, namely ribsegments (the group located in the rib region is called ribsegments). The set of the means of Cartesian coordinates (the means of the x-direction and y-direction coordinates, respectively) obtained from inside each ribsegments is the rough center line of the rib. The rib region division result is shown in fig. 2, and gray lines are division lines, and regions between lines are division regions.
And thirdly, performing smoothing operation on the rough center line obtained in the second step.
The rib thick center line is smoothed in a sliding window manner, the step length of the sliding window is 1, and the window width is 7 continuous ribsegments center points. For each coordinate point p, the front and rear 3 coordinate points and p are taken as p smoothed center points by the average value of 7 center points. And finally obtaining a smooth center line extraction result by adjusting the extracted center line.
In order to obtain a smoother central line and prevent burrs from occurring during rib tiling or jumping points from occurring during rib MPR tracking, the algorithm adjusts the extracted central line by adopting a Moving Average method, and the final extraction effect of the central line is shown in a figure 3, wherein color change represents coordinate change, and no points with unsmooth change such as burr points exist on the central line in the figure, so that the algorithm can be used for subsequent MPR and rib tiling.
Fig. 4 is a view showing the effect of extracting a part of rib center line, in which a white area is a rib plan view and a black mark is an extracted rib center line. It can be seen that the rib centerline extracted by the above method is smoother.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. The figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices. Thus, the technical solution according to the embodiments of the present invention may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present invention.
It should also be understood that the foregoing detailed description of the invention, while indicating preferred embodiments of the invention, is given by way of illustration only, since various changes and modifications within the spirit and scope of the invention will become apparent to those skilled in the art from this detailed description. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. The method for extracting the rib center line based on rib morphology priori is characterized by comprising the following steps:
according to rib morphology priori, dividing the region of the rib mask;
extracting the center point of each region and connecting the center points to serve as a thick center line;
performing smoothing operation on the obtained rough center line to obtain a smooth rib center line;
Before the region division is performed on the rib mask, the method further comprises the operation of converting the three-dimensional rib mask into the two-dimensional rib slice, and the region division is performed on the rib mask according to the following steps: extracting a center point rib center of a two-dimensional rib slice, converting Cartesian coordinates of a point rib point, namely a point with a value of 1, in each rib on the rib slice into polar coordinates with the rib center as a center, obtaining an angle relation of each point rib point relative to the rib center, dividing all the rib points into a plurality of groups from 0 to 360 degrees per n degrees, wherein the groups positioned in a rib area are called rib segments, n is any degree in a range of 1-20 degrees, and the extracting method of the center point rib center of the rib slice comprises the following steps: and respectively finding the minimum value and the maximum value on the x axis and the y axis through the coordinate relation, extracting the circumscribed rectangle wrapping the rib slice region, and obtaining the center point rib center of the rectangle.
2. The method of claim 1, wherein converting the three-dimensional rib mask to the two-dimensional rib slice is performed according to the following formula: obtaining rib segmentation map rib mask of chest CT image by segmentation algorithm, wherein rib region value is 1, non-rib region value is 0, for each individual rib, its size is high, wide, deep, corresponding to coordinates y, x, z, performing rib mask stacking according to axial direction of patient lying, converting three-dimensional rib mask into a two-dimensional rib slice,
3. The method of claim 1, wherein n is 6.
4. A method according to any one of claims 1-3, characterized in that the specific operation of extracting the center point of each region and connecting it together as a thick center line is: and respectively obtaining the average value of the coordinates in the x direction and the y direction, and obtaining the average value of the Cartesian coordinates in each rib segment to obtain a set which is the thick central line of the rib.
5. A method according to any one of claims 1-3, wherein the smoothing operation of the obtained coarse center line is performed by using a Moving Average method, and the Moving Average method specifically includes: smoothing rib coarse center line in sliding window mode, sliding window step length is 1, window width is center point of 7 continuous rib segments, for each coordinate point p, front and back 3 coordinate points and p, total average value of 7 center points is used as smoothed center point of p.
6. A computer apparatus, device or system comprising a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of the method of any of claims 1-5.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1-5.
8. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, realizes the steps of the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110195185.6A CN112862793B (en) | 2021-02-20 | 2021-02-20 | Rib centerline extraction method and device based on rib three-dimensional morphology and distribution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110195185.6A CN112862793B (en) | 2021-02-20 | 2021-02-20 | Rib centerline extraction method and device based on rib three-dimensional morphology and distribution |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112862793A CN112862793A (en) | 2021-05-28 |
| CN112862793B true CN112862793B (en) | 2024-08-16 |
Family
ID=75988360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110195185.6A Active CN112862793B (en) | 2021-02-20 | 2021-02-20 | Rib centerline extraction method and device based on rib three-dimensional morphology and distribution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862793B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109124662A (en) * | 2018-07-13 | 2019-01-04 | 上海皓桦科技股份有限公司 | Rib cage center line detecting device and method |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4545807B2 (en) * | 2008-03-31 | 2010-09-15 | 富士フイルム株式会社 | Bone number recognition device and program thereof |
| US8989471B2 (en) * | 2011-09-27 | 2015-03-24 | Siemens Aktiengesellschaft | Method and system for automatic rib centerline extraction using learning based deformable template matching |
| JP6209506B2 (en) * | 2014-11-25 | 2017-10-04 | ラトックシステムエンジニアリング株式会社 | Method and program for forming mesh for fiber analysis |
| CN108845999B (en) * | 2018-04-03 | 2021-08-06 | 南昌奇眸科技有限公司 | Trademark image retrieval method based on multi-scale regional feature comparison |
| CN109785303B (en) * | 2018-12-28 | 2020-12-11 | 上海联影智能医疗科技有限公司 | Rib marking method, device and equipment and training method of image segmentation model |
| CN109925056B (en) * | 2019-04-09 | 2021-01-08 | 广州新脉科技有限公司 | Method and device for implanting intracranial aneurysm virtual support |
| CN110916707B (en) * | 2019-12-18 | 2023-06-27 | 上海皓桦科技股份有限公司 | Two-dimensional bone image acquisition method, system and device |
| CN112349391A (en) * | 2020-11-10 | 2021-02-09 | 山东大学齐鲁医院(青岛) | Optimized rib automatic labeling method |
-
2021
- 2021-02-20 CN CN202110195185.6A patent/CN112862793B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109124662A (en) * | 2018-07-13 | 2019-01-04 | 上海皓桦科技股份有限公司 | Rib cage center line detecting device and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112862793A (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022052303A1 (en) | Method, apparatus and device for registering ultrasound image and ct image | |
| CN106485695B (en) | Medical image Graph Cut dividing method based on statistical shape model | |
| CN104809723B (en) | The three-dimensional CT image for liver automatic division method of algorithm is cut based on super voxel and figure | |
| Ruskó et al. | Automatic segmentation of the liver from multi-and single-phase contrast-enhanced CT images | |
| US8842904B2 (en) | Method for tooth dissection in CBCT volume | |
| WO2022088581A1 (en) | Training method for image detection model, related apparatus, device, and storage medium | |
| CN101971213A (en) | A method and system for anatomy structure segmentation and modeling in an image | |
| CN113421226B (en) | CT-DR multi-modal esophageal image registration method and system based on mutual information | |
| Yan et al. | Improved mask R-CNN for lung nodule segmentation | |
| CN109584167A (en) | Blood vessel enhancing and dividing method and system in CT image liver based on second order feature | |
| Chen et al. | Liver segmentation from CT images based on region growing method | |
| Häme | Liver tumor segmentation using implicit surface evolution | |
| KR101831340B1 (en) | Method and apparatus for automatic segmentation of renal parenchyma using graph-cuts with shape constraint based on multi-probabilistic atlas in abdominal ct images | |
| CN112862793B (en) | Rib centerline extraction method and device based on rib three-dimensional morphology and distribution | |
| Nair et al. | Modified level cut liver segmentation from ct images | |
| Alirr et al. | Automatic liver segmentation from ct scans using intensity analysis and level-set active contours | |
| CN108154532B (en) | Method for assisting in evaluating thyroid volume of SPECT image | |
| CN114757953B (en) | Medical ultrasonic image recognition method, equipment and storage medium | |
| CN112258533A (en) | Method for segmenting earthworm cerebellum in ultrasonic image | |
| CN110136100B (en) | Automatic classification method and device for CT slice images | |
| Yanagisawa et al. | Extraction of 3D shape of a tooth from dental CT images with region growing method | |
| Chen et al. | Image segmentation and registration techniques for MR-Guided Liver Cancer Surgery | |
| CN114581476A (en) | Lung organ model automatic leaf separation method and system based on CT image | |
| CN117911445B (en) | Root canal segmentation method, root canal three-dimensional reconstruction method and device | |
| CN114693698A (en) | Neural network-based computer-aided lung airway segmentation method |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 3011, 2nd Floor, Building A, No. 1092 Jiangnan Road, Nanmingshan Street, Liandu District, Lishui City, Zhejiang Province, 323000 Applicant after: Zhejiang Yizhun Intelligent Technology Co.,Ltd. Applicant after: Guangxi Yizhun Intelligent Technology Co.,Ltd. Address before: 1106, 11 / F, Weishi building, No.39 Xueyuan Road, Haidian District, Beijing Applicant before: Beijing Yizhun Intelligent Technology Co.,Ltd. Applicant before: Guangxi Yizhun Intelligent Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |