CN107292889B - Tumor segmentation method, system and readable medium - Google Patents
Tumor segmentation method, system and readable medium Download PDFInfo
- Publication number
- CN107292889B CN107292889B CN201710449209.XA CN201710449209A CN107292889B CN 107292889 B CN107292889 B CN 107292889B CN 201710449209 A CN201710449209 A CN 201710449209A CN 107292889 B CN107292889 B CN 107292889B
- Authority
- CN
- China
- Prior art keywords
- region
- interest
- preset condition
- image
- determining
- 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
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
- G06T7/11—Region-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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a method, a system and a readable medium for segmenting a region of interest in a medical image. The system may include: at least one storage medium and at least one processor. The storage medium may include a series of instructions for image segmentation. The processor is configured to communicate with the at least one storage medium. The at least one processor, when executing the series of instructions, may be configured to: receiving a medical image containing region-of-interest information; determining a first preset condition; identifying a first region of interest of the regions of interest in the image based on the first preset condition; segmenting the first region of interest; determining a second preset condition based on the first region of interest; identifying a second region of interest in the image based on the second preset condition; segmenting the second region of interest. The invention solves the problem of how to set the characteristics of a personalized tumor region. Compared with the traditional full-automatic whole-body tumor segmentation, the segmentation effect of the system is more accurate and faster, the advantage of the speed is more obvious compared with the speed manually identified by human eyes, and the efficiency is improved.
Description
Technical Field
The present invention relates to image processing systems, and more particularly to methods of tumor segmentation.
Background
In medical image post-processing, a tumor needs to be segmented. The traditional tumor segmentation modes include a full-automatic segmentation mode and a manual auxiliary segmentation mode.
The full-automatic segmentation mode is to preset a group of tumor feature sets, and the computer automatically identifies the tumor features of the full image and determines the region which meets the tumor feature sets in the image so as to segment the tumor. The manual auxiliary segmentation mode is to determine a tumor reference area by using judgment of a person and setting a mouse suspension point, an anchor point, a reference line and the like through a mouse. The computer identifies the reference region and the nearby region based on the full set or the subset of the tumor feature set, so that the tumor of the reference region can be segmented quickly and accurately.
The problems of the prior art are that the speed of a full-automatic segmentation mode is low, and because of the complex particularity of biological tissues and the inconsistency of different tumors of different patients, a tumor feature set which is universal for each tumor of each patient is difficult to define and perfect, and the tumor identification error is often large; the manner of manually assisted segmentation does not allow for segmentation and identification of tumors (e.g., metastatic tumors) in non-reference regions.
Disclosure of Invention
Aiming at the problems that the full-automatic segmentation mode is slow in speed and large in tumor identification error, and the manual auxiliary segmentation mode cannot segment and identify tumors (such as metastatic tumors) in a non-reference region, the invention aims to solve the problem of setting the characteristics of personalized tumor regions and rapidly and accurately segment tumors (such as metastatic tumors) of the whole body.
In order to achieve the purpose of the invention, the technical scheme provided by the invention is as follows:
a method of segmentation of a region of interest in a medical image, the method may comprise: receiving a medical image containing region-of-interest information; determining a first preset condition; identifying a first region of interest of the regions of interest in the image based on the first preset condition; segmenting the first region of interest; determining a second preset condition based on the first region of interest; identifying a second region of interest in the image based on the second preset condition; segmenting the second region of interest.
In the present invention, the region of interest may comprise a tumor, cyst, organ or tissue.
In the present invention, the determining the second preset condition based on the first region of interest may include: acquiring data of the first region of interest; performing statistical analysis on the data of the first region of interest to determine the second preset condition.
In the present invention, the first preset condition and the second preset condition may be determined by a parameter related to an image, a first threshold value related to the parameter, or a numerical range.
In the present invention, the parameter related to the image may include a pixel value, a voxel value, distribution uniformity, or a distribution region area.
In the present invention, determining the distribution area may include: obtaining a pixel point; determining the pixel value of the pixel point; determining pixel values of surrounding pixels of the pixel points; acquiring a second threshold; determining a region of the pixel point where the difference between the pixel value and the pixel values of the surrounding pixel points is less than the second threshold; determining the distribution region area based on the region.
In the present invention, the identifying the first region of interest of the regions of interest in the image based on the first preset condition may include: determining a value of the parameter in the first region of interest in the image; determining a first preset area of the image, wherein the value of the parameter meets the first preset condition; identifying the first one of the regions of interest in the image based on the first preset region.
In the present invention, the identifying the second region of interest in the image based on the second preset condition may include: determining a value of the parameter in the image; determining a second preset area of the image, wherein the value of the parameter meets the second preset condition; identifying the second region of interest in the image based on the second preset region.
A system segments a region of interest in a medical image. The system may include: at least one storage medium and at least one processor. The storage medium may include a series of instructions for image segmentation. The processor is configured to communicate with the at least one storage medium. The at least one processor, when executing the series of instructions, may be configured to: receiving a medical image containing region-of-interest information; determining a first preset condition; identifying a first region of interest of the regions of interest in the image based on the first preset condition; segmenting the first region of interest; determining a second preset condition based on the first region of interest; identifying a second region of interest in the image based on the second preset condition; segmenting the second region of interest.
A non-transitory computer readable medium comprising executable instructions. The instructions, when executed by at least one processor, cause the at least one processor to implement a method. The method may include: receiving a medical image containing region-of-interest information; determining a first preset condition; identifying a first region of interest of the regions of interest in the image based on the first preset condition; segmenting the first region of interest; determining a second preset condition based on the first region of interest; identifying a second region of interest in the image based on the second preset condition; segmenting the second region of interest.
Compared with the prior art, the invention has the following beneficial effects:
firstly, one or more pieces of local tumor data which are obtained by manual auxiliary segmentation or other modes and are accurately segmented are subjected to statistical analysis to obtain a group of corrected tumor feature sets, wherein the tumor feature sets are more accurate than full-automatic preset tumor feature sets;
and secondly, by utilizing the corrected tumor characteristic data, the computer automatically identifies the tumor characteristics of the whole image, segments the tumor and can segment the metastatic tumor of the whole body more quickly and accurately.
Drawings
FIG. 1 is a schematic structural diagram of a tumor segmentation system according to the present invention;
FIG. 2 is an exemplary flow chart of a tumor segmentation system of the present invention;
FIG. 3 is a flow chart of one embodiment of determining preset conditions according to the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures and examples are described in detail below.
For a complete understanding of the present invention, reference is made to FIG. 1, which is a block diagram illustrating a tumor segmentation system according to a preferred embodiment of the present invention. The tumor segmentation system comprises, but is not limited to, a data acquisition device 102, a reconstruction unit 104, a receiving unit 106, a determination unit 108, an identification unit 110 and a segmentation unit 112.
The data acquisition device 102 may scan a target object and acquire corresponding scan data. The data acquisition device 102 may be one or a combination of Positron Emission Tomography (PET), Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Single Photon Emission Computed Tomography (SPECT), Thermal Tomography (TTM), Medical Electronic Endoscope (MEE), and the like. In some embodiments, the data acquisition device 102 may transmit its acquired scan data to the reconstruction unit 104 over a network.
The reconstruction unit 104 may reconstruct an image based on the scan data. The scan data may be scan data acquired by the data acquisition device 102. Methods of reconstructing the image may include an Expectation Maximization (EM), an Ordered Subset Expectation Maximization (OSEM), a conjugate gradient (conjugate gradient), a maximum a posteriori (maximum a posteriori), an AML, an iterative, and the like. In some embodiments, the image may be a full image. A full image may refer to an image of multiple slices of the target object being scanned.
The receiving unit 106 may receive an image. The receiving unit 106 may receive the image reconstructed by the reconstruction unit 104 through a network.
The determination unit 108 may determine a preset condition. The determination unit 108 may determine the preset condition based on the image. The determination unit 108 may determine a region of interest in the image. The determination unit 108 may receive or determine a first preset condition. The determination unit 108 may identify and segment a first tumor in the region of interest and its vicinity in the image based on a first preset condition. The determination unit 108 may perform a statistical analysis on the data of the first lesion. The determination unit 108 may determine the second preset condition based on the statistical analysis result. The determination unit 108 may designate the second preset condition as the preset condition. The preset condition may be a relationship between a value of a parameter (e.g., pixel value, voxel value, distribution uniformity, distribution area) related to the image and a threshold value or within a range of values. For example, the determining unit 108 may count the pixel values of the first region to obtain a minimum pixel value corresponding to the tumor. The determination unit 108 may determine that the second preset condition is that the pixel value is greater than the minimum pixel value. For another example, the determining unit 108 may count the pixel values of the first region to obtain a maximum pixel value corresponding to the tumor. The determination unit 108 may determine that the second preset condition is that the pixel value is smaller than the maximum pixel value. For another example, the determining unit 108 may count the pixel values of the first region to obtain a value range of the pixel values corresponding to the tumor. The determination unit 108 may determine that the second preset condition is that the pixel value is located in the numerical range.
The recognition unit 110 may recognize a tumor in the image based on a preset condition. The recognition unit 110 may recognize the full image. In some embodiments, the identification unit 110 may identify a metastatic tumor in the image. A metastatic tumor is a tumor that has metastasized from an initial growth site to another site through lymphatic channels, blood vessels, or body cavities, etc., and continues to grow.
The recognition unit 110 may determine a value of each parameter associated with the image. The recognition unit 110 may determine whether the value of each parameter or the value of a part of the parameters satisfies a preset condition. The identifying unit 110 may identify a tumor in the image based on the value of each parameter or the value of a part of the parameters satisfying a preset condition. The recognition result may be stored in the recognition unit 110 or in another storage unit of the system.
The segmentation unit 112 may receive the recognition result from the recognition unit 110 or other storage unit and then segment the tumor in the image based on the recognition result.
Fig. 2 is an exemplary flow chart of a tumor segmentation system of the present invention.
In step 202, the reconstruction unit 104 may reconstruct an image based on the data acquired by the data acquisition device 102. The reconstruction unit 104 may also reconstruct images based on pre-stored data of the tumor segmentation system. In some embodiments, the image may be a full image. A full image may refer to an image of multiple slices of the target object being scanned.
In step 204, the receiving unit 106 may receive the image. The image may be an image reconstructed by the reconstruction unit 104 or an image pre-stored by the tumor segmentation system. The image may include tumor data.
In step 206, the determination unit 108 may determine the preset condition based on the image. The image may be an image received by the receiving unit 106. The preset condition may be decided based on a parameter related to the image. In some embodiments, the image-related parameters may include a combination of one or more of pixel values (or voxel values), distribution uniformity, distribution area, and the like.
The pixel values (or voxel values) may include, but are not limited to, Standard Uptake Value (SUV), CT values, and the like. The distribution uniformity may include, but is not limited to, gradients, variances, entropies, etc. of pixel or voxel values.
The distribution region area may include, but is not limited to, the area of a region that differs from surrounding pixel or voxel values by less than a threshold. To determine the area of the distribution region, the determination unit 108 may determine pixel values of a plurality of pixel points. The determination unit 108 may determine pixel values of pixel points around each of the pixel points. The determination unit 108 may determine a distribution area of the pixel points where a difference between the pixel value and the pixel values of the surrounding pixel points is less than a threshold. The determination unit 108 may determine the distribution region area based on the distribution region.
The preset condition may be that each parameter or part of the parameters is less than, greater than or equal to a threshold value, respectively. For another example, the preset condition may be that each parameter or a part of the parameters are within a preset range.
In some embodiments, the determination unit 108 may determine the preset condition through a manual-assisted segmentation manner or other manners. The determination unit 108 may determine a region of interest in the image. The region of interest may comprise a tumor, cyst, organ or tissue. The determination unit 108 may receive or determine a first preset condition. The determination unit 108 may segment the first tumor in the region of interest and its vicinity in the image based on a first preset condition. The determination unit 108 may perform a statistical analysis on the data of the first lesion to determine a second preset condition. The determination unit 108 may designate the second preset condition as the preset condition.
In step 208, the identification unit 110 may identify a tumor in the image. In some embodiments, the identification unit 110 may identify a metastatic tumor in the image based on a preset condition. A metastatic tumor is a tumor that has metastasized from an initial growth site to another site through lymphatic channels, blood vessels, or body cavities, etc., and continues to grow.
The recognition unit 110 may recognize a feature of the image. Identifying a feature of an image may be determining a value of a parameter associated with the image. The parameters may include a combination of one or more of pixel values (or voxel values), distribution uniformity, distribution area, and the like. The content of the image-related parameter is visible to the relevant content of step 206. The recognition unit 110 may determine an area where a value of a parameter related to the image meets a preset condition. The identification unit 110 may identify a tumor in the image based on the region. For example, the identification unit 110 may determine that a tumor is located in the region.
In step 210, the segmentation unit 112 may segment the tumor in the image based on the recognition result.
FIG. 3 is a flow chart of one embodiment of determining preset conditions according to the present invention.
Step 206 in fig. 2 may be performed by the flow shown in fig. 3.
In step 302, the determination unit 108 may determine a region of interest in the image. The region of interest may be a tissue, an organ or any other medical region of interest. For example, the region of interest may be a lesion (e.g., a tumor) in the image. The determination unit 108 may determine the region of interest in the image in various ways. For example, the determination unit 108 may select a region of interest. The selection may be manual. The determination unit 108 may determine the region of interest by setting a hover point, an anchor point, a reference line, and the like through a mouse based on a manual-assisted segmentation manner using human judgment. The selection may also be automatic. For example, the determination unit 108 may select the region of interest using a computer-aided diagnosis algorithm or an automatic seed point selection algorithm. The selecting may further comprise the user manually selecting the region of interest from a list of regions of interest automatically suggested by the tumor segmentation system.
In step 304, the determining unit 108 may receive or determine a first preset condition. The first preset condition may be a default of the tumor segmentation system, or may be adjusted according to different situations. Similar to the preset condition, the first preset condition may be decided based on a parameter related to the image. In some embodiments, the image-related parameters may include a combination of one or more of pixel values (or voxel values), distribution uniformity, distribution area, and the like. The pixel values (or voxel values) may include, but are not limited to, SUV values for PET images, CT values for CT images, and the like. The distribution uniformity may include, but is not limited to, gradients, variances, entropies, etc. of pixel or voxel values. The distribution region area includes, but is not limited to, the area of a region that differs from surrounding pixel or voxel values by less than a threshold. The first preset condition may be that each parameter or part of the parameters is less than, greater than or equal to the first threshold value, respectively. For another example, the first preset condition may be that each parameter or a part of the parameters are respectively within a first preset range.
In some embodiments, the determination unit 108 may employ an algorithm to update the first preset condition based on the parameter value of the region of interest. The algorithm may include, but is not limited to, fitting, iteration, etc. The updating of the first preset condition may be updating the first threshold or the first preset range.
In step 306, the determination unit 108 may identify a region of interest in the image and a tumor in its vicinity. The determination unit 108 may determine the values of the parameters in the region of interest and its vicinity in the image. The parameters may include a combination of one or more of pixel values (or voxel values), distribution uniformity, distribution area, and the like. The content associated with the parameter is visible to the associated content of step 206. The determination unit 108 may determine a first region of the image where the parameter values of the region of interest and its vicinity meet a first preset condition. The determination unit 108 may identify a first tumor in the region of interest and its vicinity in the image based on the first region.
In step 308, the determination unit 108 may segment the region of interest and the first tumor in the vicinity thereof in the image based on the recognition result.
In step 310, the determination unit 108 may perform a statistical analysis on the data of the first lesion. The first tumor data may include values for each parameter or portion of parameters in the image. The determination unit 108 may determine the second preset condition based on the statistical analysis result. Similar to the first preset condition, the second preset condition corresponds to a second threshold value or a second range of values. The determination unit 108 may statistically analyze a distribution law of values of the parameter in the first lesion data. The determination unit 108 may determine a second threshold or a second range of values based on the distribution rule to determine a second preset condition. The determination unit 108 may designate the second preset condition as the preset condition in step 206.
For example, the determination unit 108 may determine that the SUV values of the pixels in the first tumor data are all greater than 20000 after counting the SUV values of the pixels. The determination unit 108 may designate the pixel SUV value greater than 20000 as a second preset condition.
In some embodiments, the determination unit 108 may determine the second preset condition according to information of the patient related to the image, which is pre-stored in the system. For example, the determination unit 108 may determine information of sex, age, height, weight, examination hospital, body part (e.g., foot, chest, etc.) corresponding to the image, image type (e.g., PET image, MR image, etc.), and the like of the patient. The determination unit 108 may determine the second preset condition based on the information.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (11)
1. A method of segmentation of a region of interest in a medical image, the method comprising:
receiving a medical image containing region-of-interest information;
determining a first preset condition;
identifying a first region of interest of the regions of interest in the image based on the first preset condition;
segmenting the first region of interest;
determining a second preset condition based on the first region of interest;
identifying a second region of interest in the image based on the second preset condition;
segmenting the second region of interest.
2. The method of claim 1, wherein the region of interest comprises a tumor.
3. The method of claim 1, wherein said determining the second preset condition based on the first region of interest comprises:
acquiring data of the first region of interest;
performing statistical analysis on the data of the first region of interest to determine the second preset condition.
4. The method of claim 1, wherein the first preset condition and the second preset condition are determined by a parameter associated with an image, a first threshold value associated with the parameter, or a range of values.
5. The method of claim 4, wherein the image-related parameter comprises a pixel value, a voxel value, a distribution uniformity, or a distribution region area.
6. The method of claim 5, wherein determining the distribution area comprises:
obtaining a pixel point;
determining the pixel value of the pixel point;
determining pixel values of surrounding pixels of the pixel points;
acquiring a second threshold;
determining a region of the pixel point where the difference between the pixel value and the pixel values of the surrounding pixel points is less than the second threshold;
determining the distribution region area based on the region.
7. The method of claim 5, wherein the identifying the first one of the regions of interest in the image based on the first preset condition comprises:
determining a value of the parameter in the first region of interest in the image;
determining a first preset area of the image, wherein the value of the parameter meets the first preset condition;
identifying the first one of the regions of interest in the image based on the first preset region.
8. The method of claim 5, wherein the identifying the second region of interest in the image based on the second preset condition comprises:
determining a value of the parameter in the image;
determining a second preset area of the image, wherein the value of the parameter meets the second preset condition;
identifying the second region of interest in the image based on the second preset region.
9. The method of claim 1, wherein the region of interest comprises an organ or tissue.
10. A system for segmenting a region of interest in a medical image, comprising:
at least one storage medium comprising a series of instructions for image segmentation; and
at least one processor configured to communicate with the at least one storage medium, wherein the at least one processor, when executing the series of instructions, is configured to:
receiving a medical image containing region-of-interest information;
determining a first preset condition;
identifying a first region of interest of the regions of interest in the image based on the first preset condition;
segmenting the first region of interest;
determining a second preset condition based on the first region of interest;
identifying a second region of interest in the image based on the second preset condition;
segmenting the second region of interest.
11. A non-transitory computer-readable medium comprising executable instructions that, when executed by at least one processor, cause the at least one processor to implement a method comprising:
receiving a medical image containing region-of-interest information;
determining a first preset condition;
identifying a first region of interest of the regions of interest in the image based on the first preset condition;
segmenting the first region of interest;
determining a second preset condition based on the first region of interest;
identifying a second region of interest in the image based on the second preset condition;
segmenting the second region of interest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710449209.XA CN107292889B (en) | 2017-06-14 | 2017-06-14 | Tumor segmentation method, system and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710449209.XA CN107292889B (en) | 2017-06-14 | 2017-06-14 | Tumor segmentation method, system and readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107292889A CN107292889A (en) | 2017-10-24 |
| CN107292889B true CN107292889B (en) | 2020-09-25 |
Family
ID=60096383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710449209.XA Active CN107292889B (en) | 2017-06-14 | 2017-06-14 | Tumor segmentation method, system and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107292889B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3646240A4 (en) | 2017-06-26 | 2021-03-17 | The Research Foundation for The State University of New York | System, method, and computer-accessible medium for virtual pancreatography |
| CN109509179B (en) * | 2018-10-24 | 2023-03-28 | 深圳市旭东数字医学影像技术有限公司 | Automatic segmentation method and system for eyeballs and crystalline lenses based on medical images |
| CN109978887B (en) * | 2018-12-10 | 2022-11-11 | 深圳市旭东数字医学影像技术有限公司 | Automatic spinal cord segmentation method and system based on medical image |
| CN110210308B (en) * | 2019-04-30 | 2023-05-02 | 南方医科大学南方医院 | Biological tissue image identification method and device |
| CN110400626B (en) * | 2019-07-08 | 2023-03-24 | 上海联影智能医疗科技有限公司 | Image detection method, image detection device, computer equipment and storage medium |
| CN110610481A (en) * | 2019-08-06 | 2019-12-24 | 深圳市旭东数字医学影像技术有限公司 | Automatic brain stem segmentation method and system based on medical image |
| WO2022193077A1 (en) * | 2021-03-15 | 2022-09-22 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for image segmentation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484871A (en) * | 2014-11-27 | 2015-04-01 | 小米科技有限责任公司 | Method and device for extracting edges |
| CN106611413A (en) * | 2016-11-30 | 2017-05-03 | 上海联影医疗科技有限公司 | Image segmentation method and system |
| CN106709929A (en) * | 2016-12-30 | 2017-05-24 | 上海联影医疗科技有限公司 | Method and device for displaying interesting region of medical image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6678413B1 (en) * | 2000-11-24 | 2004-01-13 | Yiqing Liang | System and method for object identification and behavior characterization using video analysis |
-
2017
- 2017-06-14 CN CN201710449209.XA patent/CN107292889B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484871A (en) * | 2014-11-27 | 2015-04-01 | 小米科技有限责任公司 | Method and device for extracting edges |
| CN106611413A (en) * | 2016-11-30 | 2017-05-03 | 上海联影医疗科技有限公司 | Image segmentation method and system |
| CN106709929A (en) * | 2016-12-30 | 2017-05-24 | 上海联影医疗科技有限公司 | Method and device for displaying interesting region of medical image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107292889A (en) | 2017-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107292889B (en) | Tumor segmentation method, system and readable medium | |
| CN106600609B (en) | Spine segmentation method and system in medical image | |
| CN109741284B (en) | System and method for correcting respiratory motion-induced mismatches in PET imaging | |
| CN106558045B (en) | A kind of segmentation of lung parenchyma method, apparatus, magic magiscan | |
| US8787648B2 (en) | CT surrogate by auto-segmentation of magnetic resonance images | |
| Bezrukov et al. | MR-based PET attenuation correction for PET/MR imaging | |
| CN107644421B (en) | Medical image segmentation method and system | |
| CN106133790B (en) | Method and device for generating one or more computed tomography images based on magnetic resonance images with the aid of tissue type separation | |
| JP5530446B2 (en) | Method and apparatus for generating attenuation map in PET-MR | |
| CN111008984B (en) | Automatic contour line drawing method for normal organ in medical image | |
| JP5893623B2 (en) | Anomaly detection method and system in data set | |
| US8655038B2 (en) | Method and assembly for correcting a relaxation map for medical imaging applications | |
| Vaidyanathan et al. | Monitoring brain tumor response to therapy using MRI segmentation | |
| RU2589292C2 (en) | Device and method for formation of attenuation correction map | |
| Wang et al. | Automated segmentation of CBCT image using spiral CT atlases and convex optimization | |
| JP2010517601A (en) | Identification and analysis of lesions in medical images | |
| WO2016033458A1 (en) | Restoring image quality of reduced radiotracer dose positron emission tomography (pet) images using combined pet and magnetic resonance (mr) | |
| US20160292848A1 (en) | Medical imaging data processing apparatus and method | |
| CN106709920B (en) | Blood vessel extraction method and device | |
| EP3631806A1 (en) | Quantified aspects of lesions in medical images | |
| JP2015514520A (en) | Identification of blood vessel region | |
| CN116630342A (en) | Abdominal MRI image segmentation system, method, electronic device, and storage medium | |
| CN108805947B (en) | PET data processing method and device and PET imaging system | |
| Myint et al. | Effective kidney segmentation using gradient based approach in abdominal CT images | |
| US10436867B2 (en) | Method and computer for automatic characterization of liver tissue from magnetic resonance images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Patentee after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Patentee before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |