CN108596887A - A kind of abdominal CT sequence image liver neoplasm automatic division method - Google Patents
A kind of abdominal CT sequence image liver neoplasm automatic division method Download PDFInfo
- Publication number
- CN108596887A CN108596887A CN201810341254.8A CN201810341254A CN108596887A CN 108596887 A CN108596887 A CN 108596887A CN 201810341254 A CN201810341254 A CN 201810341254A CN 108596887 A CN108596887 A CN 108596887A
- Authority
- CN
- China
- Prior art keywords
- liver
- image
- abdominal
- pixel
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 208000014018 liver neoplasm Diseases 0.000 title claims abstract description 41
- 206010019695 Hepatic neoplasm Diseases 0.000 title claims abstract description 38
- 230000003187 abdominal effect Effects 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 23
- 210000004185 liver Anatomy 0.000 claims abstract description 55
- 230000011218 segmentation Effects 0.000 claims abstract description 33
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 18
- 230000002708 enhancing effect Effects 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000005457 optimization Methods 0.000 claims abstract description 3
- 238000004364 calculation method Methods 0.000 claims description 5
- 210000003484 anatomy Anatomy 0.000 claims description 2
- 238000004195 computer-aided diagnosis Methods 0.000 abstract description 4
- 230000002440 hepatic effect Effects 0.000 abstract description 2
- 208000019423 liver disease Diseases 0.000 abstract description 2
- 238000012805 post-processing Methods 0.000 abstract 1
- 238000002203 pretreatment Methods 0.000 abstract 1
- 210000001519 tissue Anatomy 0.000 description 10
- 230000001225 therapeutic effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 201000007270 liver cancer Diseases 0.000 description 3
- 210000001015 abdomen Anatomy 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000002246 antineoplastic agent Substances 0.000 description 1
- 229940041181 antineoplastic drug Drugs 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000002386 leaching Methods 0.000 description 1
- 210000005228 liver tissue Anatomy 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—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
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30056—Liver; Hepatic
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of abdominal CT sequence image liver neoplasm automatic division methods.Include the following steps：Pre-treatment step pre-processes abdominal CT sequence image, obtains liver area therein；Hepatic contrast step improves the contrast of normal liver parenchyma and tumor tissues using piecewise nonlinear enhancing and iterative convolution operation according to liver area gray-scale watermark；Automatic segmentation step, using enhancing as a result, in conjunction with image boundary information, the figure for building Segmentation of Multi-target cuts energy function, minimizes energy function using optimization algorithm, obtains liver neoplasm preliminary automatic segmentation result；Post-processing step is opened operation using 3-d mathematics morphology and is optimized to primary segmentation result, removes accidentally cut zone therein, improve segmentation precision.The present invention contributes to dept. of radiology expert and surgeon timely and effectively to obtain the Global Information and Three-dimensional Display of liver neoplasm, and technical support is provided for liver diseases computer-aided diagnosis and treatment.
Description
Technical field
The invention belongs to technical field of image processing, the Target Segmentation being related in medical image, more particularly to abdominal CT sequence
The automatic segmentation of row image liver neoplasm tissue can be used for medical image auxiliary diagnosis and treatment.
Background technology
The new hair and dead liver cancer patient in 50% or more the whole world are happened at China, and annual China about 300,000 people are because suffering from
Suffer from PLC mortality.Since the symptom of early liver cancer is not obvious, about 60% patient just goes to go to a doctor when uncomfortable, this
When often enter middle and advanced stage, lose the chance of radical treatment.Statistical data shows the existence in later period of hepatocarcinoma patient 5 years
Rate only has 7% or so.
Liver neoplasm load Analysis is commonly used in the disease development situation of monitoring liver cancer patient, formulation therapeutic scheme, progress
Comparison, prediction between different therapeutic schemes and the validity etc. assessed therapeutic effect, assess anticancer drug.Abdomen computer is disconnected
The segmentation of layer scanning (computed tomography, CT) sequence image liver neoplasm tissue is liver neoplasm load Analysis
The important foundation that important prerequisite and liver diseases computer-aided diagnosis and operation plan are formulated.Clinician can be according to abdomen
The segmentation result of portion CT sequence image liver neoplasm tissues obtains the quantity of lesion, size, shape, position, lesion degree, leaching
The information such as whether moistening depth, shift, diagnose disease, formulate therapeutic scheme appropriate.Since CT is imaged the image used
Number of sections is larger, and (if thickness is 1.5mm, complete abdominal CT sequence comprising patient's liver is cut there are about 120 or so
Piece), each slice heavy workload of artificial segmentation, time-consuming and the accuracy of segmentation result and validity depend critically upon radiation
Experience, skill and the subjective judgement of section expert.Therefore, exploitation designs a kind of automatic robust of abdominal CT sequence image liver neoplasm point
Segmentation method is of great significance to the precision for improving liver neoplasm load Analysis and computer-aided diagnosis with efficiency.
Invention content
The purpose of the present invention is to provide a kind of abdominal CT sequence image liver neoplasm automatic division methods, it is intended to solve CT
Liver neoplasm obscurity boundary in image, liver caused by the reasons such as low with normal structure contrast, complicated, gray scale is various are swollen
Tumor divides inaccurate problem automatically, improves the precision and efficiency of computer-aided diagnosis.
A kind of abdominal CT sequence image liver neoplasm automatic division method, includes the following steps：
(1) abdominal CT sequence image f is pre-processed using the prior art, obtains liver area therein；
(2) grey level histogram for using entire liver area in Gaussian function fitting sequence, according to the probability of Gaussian Profile
Theoretical and anatomy priori, obtains the substantially tonal range [I of normal liver tissuemin,Imax], wherein IminIndicate ash
Spend minimum value, ImaxIndicate gray scale maximum value；
(3) gray value I is utilizedminAnd Imax, piecewise nonlinear enhancing is carried out to liver area, improves tumour and normal liver
The contrast of tissue, enhancing result are denoted as ζ.
(4) in order to remove noise, the smoothed image in enhancing result, use size for the convolution kernel of (2s+1) × (2s+1)
N is carried out to enhancing result ζiterSecondary iterative convolution operation, obtains result ζconv, wherein s, NiterIt is the natural number more than 0, it is excellent
It is 1~5 natural number, N to select siterFor 30~130 natural number；
(5) using enhancing as a result, in conjunction with image boundary information, the figure for building Segmentation of Multi-target cuts energy function：
Wherein, P indicates all pixels collection in image f, fpAnd fqThe pixel p and q in image f, N are indicated respectivelypIt indicates
The neighborhood territory pixel collection of pixel p, R (fp) and B (fp,fq) it is respectively gray scale and boundary penalty term, respectively by enhancing result and image
Gradient is calculated, and is respectively used to label distribution and segmentation that figure cuts background in algorithm, normal liver parenchyma and tumor tissues
The smoothness of zone boundary controls, and weight α is for adjusting gray scale penalty term R (fp) and boundary penalty term B (fp,fq) in figure cut calculation
Shared proportion in method, value range are 0~1, the normal number that preferably α is 0.5~1；
(6) it uses optimization algorithm to minimize energy function E (f), obtains liver neoplasm primary segmentation result；
(7) it opens operation using 3-d mathematics morphology to post-process primary segmentation result, removes accidentally segmentation therein
Region obtains accurate liver neoplasm tissue.
In described (3) step, it is as follows that piecewise nonlinear enhances formula：
Wherein, I is image pixel gray level,It is respectively to adjust normal liver region and tumor region to enhance punishing for degree with θ
Penalty factor,It is normal number with θ values, when image pixel gray level I is fallen in section [Imin,Imax] on when, show the pixel
The probability for belonging to normal liver is larger, the penalty factor enhanced itBe arranged it is relatively small, and when gray scale I be less than IminOr
More than ImaxWhen, show the pixel belong to liver neoplasm probability it is larger, penalty factor θ values be then arranged it is relatively large, preferably
For 0.1~1 normal number, the normal number that θ is 1~3.
In described (5) step, figure cuts the gray scale penalty term R (f of energy functionp) be related to image slices vegetarian refreshments and be belonging respectively to
The gray scale of background, normal liver parenchyma and tumor tissues punishes that specific formula for calculation is as follows：
Wherein, fpAnd fqThe pixel p and q in image f, I are indicated respectivelypAnd IqIndicate the gray value of pixel p and q, mask
For the liver mask pre-processed to abdominal CT sequence image using the prior art, belong to the element marking of liver area
It is 1, the pixel for belonging to background is labeled as 0, i.e.,Boundary penalty term B (fp,fq) to adjacent
Pixel grey scale is inconsistent to be punished, calculation formula is as follows：
Wherein
D (p, q) indicates the Euclidean distance of pixel p and q, TPIndicate the sum of all pixels of the set of pixels P of image f.
In described (7) step, preferably radius is that the spherical structure of r opens the structural element of operation as three dimensional morphology,
The natural number of wherein r preferably 2~25.
Description of the drawings
The 4 width original images selected at random in a certain abdominal CT sequences of Fig. 1
The liver area segmentation result example of Fig. 2 embodiment of the present invention
The liver area grey level histogram Gaussian fitting result example of Fig. 3 embodiment of the present invention
The convolution kernel of Fig. 4 embodiment of the present invention
The liver area of Fig. 5 embodiment of the present invention enhances result example
The figure based on Segmentation of Multi-target of Fig. 6 embodiment of the present invention cuts algorithm basic principle figure
Background area, normal liver parenchyma and the liver neoplasm classification results example of Fig. 7 embodiment of the present invention
The liver neoplasm segmentation result two dimension of Fig. 8 embodiment of the present invention is shown
The liver neoplasm segmentation result Three-dimensional Display of Fig. 9 embodiment of the present invention
Specific implementation mode
Embodiment 1
In order to obtain the liver area in abdominal CT sequence image, using document " A hierarchical local
region-based sparse shape composition for liver segmentationin CT scans”
Abdominal CT sequence liver automatic division method is to original CT disclosed in (pattern recognition, pp.88-106,2016.)
Sequence image is pre-processed, and the liver area in sequence is obtained.Fig. 1 (a)-(d) is 4 selected at random from a certain CT sequences
Width original image, Fig. 2 (a)-(d) are the liver segmentation results obtained using the present embodiment method, i.e. liver area mask.
Embodiment 2
A kind of abdominal CT sequence image liver area Enhancement Method, steps are as follows for specific implementation：
(1) embodiment 1 is used to obtain the liver area in abdominal CT sequence image f；
(2) in order to obtain the intensity profile range of liver area, using entire liver area in Gaussian function fitting sequence
Grey level histogram：
Wherein, c is the peak value of Gaussian Profile, and μ and σ are respectively center and the standard deviation of Gaussian Profile.Fig. 3 is to Fig. 1 institute
Show that the grey level histogram of sequence image liver area carries out Gaussian fitting result, it can be seen that liver intensity can preferably meet
Gaussian Profile.According to the probability theory of Gaussian Profile, the tonal range of [μ-σ, μ+σ], [+2 σ of μ -2 σ, μ] and [+3 σ of μ -3 σ, μ]
Occupy the pixel of liver area 68%, 95%, 99% respectively.In view of the noise and tumor group being likely to occur in liver area
It knits, the gray scale minimum and maximum value of the preferred normal liver parenchyma of the present embodiment is respectively Imin=μ -0.8 σ and Imax+ 0.8 σ of=μ.
(3) gray value I is utilizedminAnd Imax, piecewise nonlinear enhancing is carried out to liver area, improves tumour and normal liver
The contrast of tissue.It is as follows that piecewise nonlinear enhances formula：
Wherein, I is image pixel gray level,It is respectively to adjust normal liver region and tumor region to enhance punishing for degree with θ
Penalty factor,It is normal number with θ values, when image pixel gray level I is fallen in section [Imin,Imax] on when, show the pixel
The probability for belonging to normal liver is larger, the penalty factor enhanced itBe arranged it is relatively small, and when gray scale I be less than Imin
Or it is more than ImaxWhen, show the pixel belong to liver neoplasm probability it is larger, relatively large, this reality is then arranged in penalty factor θ values
It is preferred to apply exampleθ=2.
(4) convolution operation is iterated to enhanced result ζ, obtains result ζconv, the preferred size of the present embodiment be 3 ×
3 convolution kernels as shown in Figure 4, and preferably iterations are 60.The convolution operation can effectively remove noise, smoothed image, simultaneously
Retain image boundary information.
Fig. 5 (a)-(d) be using the present embodiment to the liver area in Fig. 1 (a)-(d) enhanced as a result, can see
It is significantly improved to the contrast between normal liver parenchyma and tumor tissues.
Embodiment 3
Hepatic contrast is obtained as a result, in conjunction with image boundary information using embodiment 2, the figure for building Segmentation of Multi-target cuts energy
Function：
Wherein, the normal number that α is 0~1, P indicate all pixels collection in abdominal CT sequence image f, NpIndicate pixel p
Neighborhood territory pixel collection, R (fp) and B (fp,fq) it is respectively gray scale and boundary penalty term, and following formula is respectively adopted and obtains：
Wherein
fpAnd fqThe pixel p and q in image f, I are indicated respectivelypAnd IqIndicate that the gray value of pixel p and q, d (p, q) indicate
The Euclidean distance of pixel p and q, TPIndicate the sum of all pixels of the set of pixels P of image f, mask is that the liver obtained using embodiment 1 is covered
Mould, the pixel for belonging to liver area are labeled as 1, and the pixel for belonging to background is labeled as 0, i.e.,
Fig. 6 is that the figure of Segmentation of Multi-target cuts algorithm basic principle figure.In the figure based on Segmentation of Multi-target cuts algorithm, gray scale penalty term R
(fp) it is used for the label distribution of background, normal liver parenchyma and tumor tissues, correspond to the t connections in Fig. 6, when pixel belongs to a certain
The probability of classification is bigger, punishes it smaller, and corresponding t connection values will be bigger, i.e., corresponding side is thicker in non-directed graph, on the contrary
It is as the same.Boundary penalty term B (fp,fq) it is then used for the smoothness control on cut zone boundary, correspond to the n connections in Fig. 6, works as phase
Gray scale is closer between adjacent pixel, punishes it smaller, and corresponding n connection values will be bigger, i.e., corresponding side is got in non-directed graph
Slightly, vice versa.Weight α is for adjusting gray scale penalty term R (fp) and boundary penalty term B (fp,fq) shared in figure cuts algorithm
Proportion, value range are 0~1, preferred α=0.6 of the present embodiment.Using max-flow min-cut algorithmic minimizing energy function E
(f), CT images can be divided into background, normal liver tissue and tumour three classes, as shown in Fig. 7 (a)-(d), extraction wherein belongs to swollen
That one kind of tumor can obtain liver neoplasm primary segmentation result.
Embodiment 4
After obtaining liver neoplasm primary segmentation result using embodiment 3, it is carried out three dimensional morphology open operation removal its
In the noise that is likely to occur and accidentally cut zone, obtain final liver neoplasm segmentation result, the preferred radius of the present embodiment is 8
Spherical structure opens the structural element of operation as morphology.Fig. 8 (a)-(d) is the liver neoplasm obtained using the present embodiment method
Segmentation result two dimension shows that tumor region therein is by complete effective Ground Split.Fig. 9 is the three-dimensional of liver neoplasm segmentation result
Display, it can be seen that the method for the present invention can effectively divide size in abdominal CT sequence image, different liver neoplasm.
Claims (7)
1. a kind of abdominal CT sequence image liver neoplasm automatic division method, which is characterized in that this method includes：
(1) abdominal CT sequence image f is pre-processed using the prior art, obtains liver area therein；
(2) grey level histogram for using entire liver area in Gaussian function fitting sequence, according to the probability theory of Gaussian Profile
And anatomy priori, obtain the substantially tonal range [I of normal liver tissuemin,Imax], wherein IminIndicate gray scale most
Small value, ImaxIndicate gray scale maximum value；
(3) gray value I is utilizedminAnd Imax, piecewise nonlinear enhancing is carried out to liver area, improves tumour and normal liver parenchyma
Contrast, enhancing result are denoted as ζ.
(4) in order to remove enhancing result in noise, smoothed image, use size be the convolution kernel of (2s+1) × (2s+1) to increasing
Strong result ζ carries out NiterSecondary iterative convolution operation, obtains result ζconv, wherein s, NiterIt is the natural number more than 0；
(5) using enhancing as a result, in conjunction with image boundary information, the figure for building Segmentation of Multi-target cuts energy function：
Wherein, P indicates all pixels collection in image f, fpAnd fqThe pixel p and q in image f, N are indicated respectivelypIndicate pixel
The neighborhood territory pixel collection of point p, R (fp) and B (fp,fq) it is respectively gray scale and boundary penalty term, respectively by enhancing result and image gradient
It is calculated, and is respectively used to label distribution and cut zone that figure cuts background in algorithm, normal liver parenchyma and tumor tissues
The smoothness on boundary controls, and weight α is for adjusting gray scale penalty term R (fp) and boundary penalty term B (fp,fq) in figure cuts algorithm
Shared proportion, value range are 0~1.
(6) it uses optimization algorithm to minimize energy function E (f), obtains liver neoplasm primary segmentation result；
(7) it opens operation using 3-d mathematics morphology to post-process primary segmentation result, removes accidentally cut zone therein,
Obtain accurate liver neoplasm tissue.
2. abdominal CT sequence image liver neoplasm automatic division method as described in claim 1, it is characterised in that：The s is excellent
Select 1~5 natural number, NiterIt is preferred that 30~130 natural number, the normal number of α preferably 0.5~1.
3. abdominal CT sequence image liver neoplasm automatic division method as described in claim 1, it is characterised in that：
In described (3) step, it is as follows that piecewise nonlinear enhances formula：
Wherein, I is image pixel gray level,With θ be respectively adjust normal liver region and tumor region enhance the punishment of degree because
Son,It is normal number with θ values, when image pixel gray level I is fallen in section [Imin,Imax] on when, show that the pixel belongs to
The probability of normal liver is larger, the penalty factor enhanced itBe arranged it is relatively small, and when gray scale I be less than IminOr it is big
In ImaxWhen, show the pixel belong to liver neoplasm probability it is larger, penalty factor θ values are then arranged relatively large.
4. abdominal CT sequence image liver neoplasm automatic division method as claimed in claim 3, it is characterised in that：It is describedIt is excellent
Select 0.1~1 normal number, the normal number of θ preferably 1~3.
5. abdominal CT sequence image liver neoplasm automatic division method as described in claim 1, it is characterised in that：Described
In (5) step, figure cuts the gray scale penalty term R (f of energy functionp) be related to image slices vegetarian refreshments and be belonging respectively to background, normal liver parenchyma
Punish that specific formula for calculation is as follows with the gray scale of tumor tissues：
Wherein, fpAnd fqThe pixel p and q in image f, I are indicated respectivelypAnd IqIndicate that the gray value of pixel p and q, mask are to adopt
The liver mask pre-processed to abdominal CT sequence image with the prior art, the pixel for belonging to liver area are labeled as 1,
The pixel for belonging to background is labeled as 0, i.e.,Boundary penalty term B (fp,fq) then to adjacent picture
Plain gray scale is inconsistent to be punished, calculation formula is as follows：
Wherein
D (p, q) indicates the Euclidean distance of pixel p and q, TPIndicate the sum of all pixels of the set of pixels P of image f.
6. abdominal CT sequence image liver neoplasm automatic division method as described in claim 1, it is characterised in that：Described
In (7) step, preferably radius is that the spherical structure of r opens the structural element of operation as three dimensional morphology.
7. abdominal CT sequence image liver neoplasm automatic division method as claimed in claim 6, it is characterised in that：The r is excellent
Select 2~25 natural number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810341254.8A CN108596887B (en) | 2018-04-17 | 2018-04-17 | Automatic segmentation method for liver tumor region image in abdominal CT sequence image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810341254.8A CN108596887B (en) | 2018-04-17 | 2018-04-17 | Automatic segmentation method for liver tumor region image in abdominal CT sequence image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108596887A true CN108596887A (en) | 2018-09-28 |
| CN108596887B CN108596887B (en) | 2020-06-02 |
Family
ID=63622730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810341254.8A Active CN108596887B (en) | 2018-04-17 | 2018-04-17 | Automatic segmentation method for liver tumor region image in abdominal CT sequence image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596887B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109493351A (en) * | 2018-11-12 | 2019-03-19 | 哈尔滨理工大学 | The system that liver segmentation is carried out using probability map and level set to CT image |
| CN109741359A (en) * | 2019-01-13 | 2019-05-10 | 中南大学 | A kind of abdominal CT sequence image pathologic liver dividing method |
| CN109753997A (en) * | 2018-12-19 | 2019-05-14 | 湖南科技大学 | A kind of liver neoplasm automatic and accurate Robust Segmentation method in CT image |
| CN109934235A (en) * | 2019-03-20 | 2019-06-25 | 中南大学 | A kind of unsupervised abdominal CT sequence image multiple organ automatic division method simultaneously |
| CN109961449A (en) * | 2019-04-15 | 2019-07-02 | 上海电气集团股份有限公司 | The method and apparatus of image segmentation, the method for reconstructing of 3-D image and system |
| CN110223289A (en) * | 2019-06-17 | 2019-09-10 | 上海联影医疗科技有限公司 | A kind of image processing method and system |
| CN110276407A (en) * | 2019-06-26 | 2019-09-24 | 哈尔滨理工大学 | A kind of Hepatic CT staging system and classification method |
| CN110473196A (en) * | 2019-08-14 | 2019-11-19 | 中南大学 | A kind of abdominal CT images target organ method for registering based on deep learning |
| CN110610491A (en) * | 2019-09-17 | 2019-12-24 | 湖南科技大学 | Liver tumor region segmentation method of abdominal CT image |
| CN111047567A (en) * | 2019-12-05 | 2020-04-21 | 电子科技大学 | Kidney tumor picture determination method and related device |
| CN111161256A (en) * | 2019-12-31 | 2020-05-15 | 北京推想科技有限公司 | Image segmentation method, image segmentation device, storage medium, and electronic apparatus |
| CN111476881A (en) * | 2020-03-18 | 2020-07-31 | 创业慧康科技股份有限公司 | Human tissue organ three-dimensional reconstruction method based on structural similarity level set algorithm |
| CN111489434A (en) * | 2020-03-18 | 2020-08-04 | 创业慧康科技股份有限公司 | Medical image three-dimensional reconstruction method based on three-dimensional graph cut |
| CN112308082A (en) * | 2020-11-05 | 2021-02-02 | 湖南科技大学 | Dynamic video image segmentation method based on dual-channel convolution kernel and multi-frame feature fusion |
| CN112734790A (en) * | 2020-12-30 | 2021-04-30 | 武汉联影生命科学仪器有限公司 | Tumor region labeling method, system, device and readable storage medium |
| CN114820663A (en) * | 2022-06-28 | 2022-07-29 | 日照天一生物医疗科技有限公司 | Assistant positioning method for determining radio frequency ablation therapy |
| CN115294122A (en) * | 2022-10-08 | 2022-11-04 | 江苏诺阳家居科技有限公司 | Lung tumor feature extraction method and system based on CT image |
| CN116993764A (en) * | 2023-09-26 | 2023-11-03 | 江南大学附属医院 | Stomach CT intelligent segmentation extraction method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385751A (en) * | 2011-07-19 | 2012-03-21 | 中国科学院自动化研究所 | Liver tumor region segmentation method based on watershed transform and classification through support vector machine |
| CN105139377A (en) * | 2015-07-24 | 2015-12-09 | 中南大学 | Rapid robustness auto-partitioning method for abdomen computed tomography (CT) sequence image of liver |
| US20170148156A1 (en) * | 2015-11-25 | 2017-05-25 | Zebra Medical Vision Ltd. | Systems and methods for detecting a fatty liver from a computed tomography (ct) scan |
-
2018
- 2018-04-17 CN CN201810341254.8A patent/CN108596887B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385751A (en) * | 2011-07-19 | 2012-03-21 | 中国科学院自动化研究所 | Liver tumor region segmentation method based on watershed transform and classification through support vector machine |
| CN105139377A (en) * | 2015-07-24 | 2015-12-09 | 中南大学 | Rapid robustness auto-partitioning method for abdomen computed tomography (CT) sequence image of liver |
| US20170148156A1 (en) * | 2015-11-25 | 2017-05-25 | Zebra Medical Vision Ltd. | Systems and methods for detecting a fatty liver from a computed tomography (ct) scan |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109493351A (en) * | 2018-11-12 | 2019-03-19 | 哈尔滨理工大学 | The system that liver segmentation is carried out using probability map and level set to CT image |
| CN109753997A (en) * | 2018-12-19 | 2019-05-14 | 湖南科技大学 | A kind of liver neoplasm automatic and accurate Robust Segmentation method in CT image |
| CN109753997B (en) * | 2018-12-19 | 2022-11-22 | 湖南科技大学 | Automatic accurate robust segmentation method for liver tumor in CT image |
| CN109741359A (en) * | 2019-01-13 | 2019-05-10 | 中南大学 | A kind of abdominal CT sequence image pathologic liver dividing method |
| CN109741359B (en) * | 2019-01-13 | 2022-05-31 | 中南大学 | Method for segmenting lesion liver of abdominal CT sequence image |
| CN109934235A (en) * | 2019-03-20 | 2019-06-25 | 中南大学 | A kind of unsupervised abdominal CT sequence image multiple organ automatic division method simultaneously |
| CN109961449B (en) * | 2019-04-15 | 2023-06-02 | 上海电气集团股份有限公司 | Image segmentation method and device, and three-dimensional image reconstruction method and system |
| CN109961449A (en) * | 2019-04-15 | 2019-07-02 | 上海电气集团股份有限公司 | The method and apparatus of image segmentation, the method for reconstructing of 3-D image and system |
| CN110223289A (en) * | 2019-06-17 | 2019-09-10 | 上海联影医疗科技有限公司 | A kind of image processing method and system |
| CN110276407A (en) * | 2019-06-26 | 2019-09-24 | 哈尔滨理工大学 | A kind of Hepatic CT staging system and classification method |
| CN110473196A (en) * | 2019-08-14 | 2019-11-19 | 中南大学 | A kind of abdominal CT images target organ method for registering based on deep learning |
| CN110473196B (en) * | 2019-08-14 | 2021-06-04 | 中南大学 | Abdomen CT image target organ registration method based on deep learning |
| CN110610491A (en) * | 2019-09-17 | 2019-12-24 | 湖南科技大学 | Liver tumor region segmentation method of abdominal CT image |
| CN111047567A (en) * | 2019-12-05 | 2020-04-21 | 电子科技大学 | Kidney tumor picture determination method and related device |
| CN111161256A (en) * | 2019-12-31 | 2020-05-15 | 北京推想科技有限公司 | Image segmentation method, image segmentation device, storage medium, and electronic apparatus |
| CN111489434A (en) * | 2020-03-18 | 2020-08-04 | 创业慧康科技股份有限公司 | Medical image three-dimensional reconstruction method based on three-dimensional graph cut |
| CN111476881A (en) * | 2020-03-18 | 2020-07-31 | 创业慧康科技股份有限公司 | Human tissue organ three-dimensional reconstruction method based on structural similarity level set algorithm |
| CN112308082A (en) * | 2020-11-05 | 2021-02-02 | 湖南科技大学 | Dynamic video image segmentation method based on dual-channel convolution kernel and multi-frame feature fusion |
| CN112734790A (en) * | 2020-12-30 | 2021-04-30 | 武汉联影生命科学仪器有限公司 | Tumor region labeling method, system, device and readable storage medium |
| CN112734790B (en) * | 2020-12-30 | 2023-07-11 | 武汉联影生命科学仪器有限公司 | Tumor region labeling method, system, device and readable storage medium |
| CN114820663A (en) * | 2022-06-28 | 2022-07-29 | 日照天一生物医疗科技有限公司 | Assistant positioning method for determining radio frequency ablation therapy |
| CN115294122A (en) * | 2022-10-08 | 2022-11-04 | 江苏诺阳家居科技有限公司 | Lung tumor feature extraction method and system based on CT image |
| CN116993764A (en) * | 2023-09-26 | 2023-11-03 | 江南大学附属医院 | Stomach CT intelligent segmentation extraction method |
| CN116993764B (en) * | 2023-09-26 | 2023-12-08 | 江南大学附属医院 | Stomach CT intelligent segmentation extraction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108596887B (en) | 2020-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596887A (en) | A kind of abdominal CT sequence image liver neoplasm automatic division method | |
| Gonçalves et al. | Hessian based approaches for 3D lung nodule segmentation | |
| Chung et al. | Automated segmentation of muscle and adipose tissue on CT images for human body composition analysis | |
| Liu et al. | Automatic organ segmentation for CT scans based on super-pixel and convolutional neural networks | |
| CN108335304B (en) | Aortic aneurysm segmentation method of abdominal CT scanning sequence image | |
| CN100573581C (en) | Semi-automatic partition method of lung CT image focus | |
| Abd-Elaziz et al. | Liver tumors segmentation from abdominal CT images using region growing and morphological processing | |
| Anand | Segmentation coupled textural feature classification for lung tumor prediction | |
| CN109753997B (en) | Automatic accurate robust segmentation method for liver tumor in CT image | |
| US20050207630A1 (en) | Lung nodule detection and classification | |
| Chen et al. | Pathological lung segmentation in chest CT images based on improved random walker | |
| CN106780518A (en) | A kind of MR image three-dimensional interactive segmentation methods of the movable contour model cut based on random walk and figure | |
| CN105139377A (en) | Rapid robustness auto-partitioning method for abdomen computed tomography (CT) sequence image of liver | |
| CN112767407B (en) | CT image kidney tumor segmentation method based on cascade gating 3DUnet model | |
| CN108268897A (en) | A kind of multi-modal multi-level computer aided diagnosing method of ultrasound of tumor of breast | |
| Jimenez-Carretero et al. | Optimal multiresolution 3D level-set method for liver segmentation incorporating local curvature constraints | |
| CN110678934A (en) | Quantitative aspects of lesions in medical images | |
| Hamad et al. | Segmentation and measurement of lung pathological changes for COVID-19 diagnosis based on computed tomography | |
| Alirr et al. | Automatic liver segmentation from ct scans using intensity analysis and level-set active contours | |
| CN117427286A (en) | Tumor radiotherapy target area identification method, system and equipment based on energy spectrum CT | |
| CN101295400B (en) | Medical image partitioning method for radiation therapy planning system | |
| CN110533667A (en) | Lung tumors CT images 3D dividing method based on image pyramid fusion | |
| Fu et al. | Segmentation of spinal canal region in CT images using 3D region growing technique | |
| Yao et al. | Computer aided detection of lytic bone metastases in the spine using routine CT images | |
| Timp | Analysis of Temporal Mammogram Pairs to Detect and Characterise Mass Lesions. |
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 |