CN106204587B - Multiple organ dividing method based on depth convolutional neural networks and region-competitive model - Google Patents
Multiple organ dividing method based on depth convolutional neural networks and region-competitive model Download PDFInfo
- Publication number
- CN106204587B CN106204587B CN201610539736.5A CN201610539736A CN106204587B CN 106204587 B CN106204587 B CN 106204587B CN 201610539736 A CN201610539736 A CN 201610539736A CN 106204587 B CN106204587 B CN 106204587B
- Authority
- CN
- China
- Prior art keywords
- region
- image
- neural networks
- convolutional neural
- kidney
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Abstract
The present invention relates to Medical Image Processings, it is desirable to provide the multiple organ dividing method based on depth convolutional neural networks and region-competitive model.The multiple organ dividing method based on depth convolutional neural networks and region-competitive model includes process: training Three dimensional convolution neural network；Using in trained Three dimensional convolution neural network learning CTA volume data liver, spleen, kidney and background prior probability image；The initial segmentation region of each tissue is determined by the prior probability image of various organization；Determine that each pixel is belonging respectively to four kinds of probability organized in image；Establish the multi_region model based on region-competitive；With convex optimization method solving model；It is post-processed, obtains the profile of each organ.The present invention quickly detects the position of abdomen liver, spleen and kidney using convolutional neural networks automatically, obtains the prior probability image of each organ, recycles region-competitive model, can accurately be partitioned into the profile of liver, spleen and kidney simultaneously.
Description
Technical field
The present invention relates to field of medical image processing, in particular to are based on depth convolutional neural networks and region-competitive mould
The multiple organ dividing method of type.
Background technique
The segmentation of abdomen organ has important research significance and clinical value.Clinically, doctor is usually by means of CT machine,
That is computed tomography scanner, to obtain a series of plane gray scale faultage images of human abdomen, and by continuously checking this
A little images are come size, position, the correlation etc. of sentencing each organ.Fast automaticly coming out organ segmentation from CT image is
Carry out the visual first step.Than visualization importantly, determine organ of interest position and region in radiotherapy operation by
Important meaning.Only according to the spatial geometric shape of organ and volume, accurate Radiation treatment plans and radiotherapeutic agents can be just made
Amount.
Traditional abdominal organ segmentation method can be divided into the method based on image and the method based on model.Based on image
Method include threshold segmentation method, region growing method, deformation model etc..These methods generally require artificial initialization or
Interaction, and be easy to be influenced by gray value, there is a situation where less divided or over-segmentation occurs.In method based on model, allusion quotation
Type algorithm has probability atlas calculation and statistical shape model.But these two types of algorithms are influenced big, algorithm by prior shape initialization
Process is complicated, and prior shape is difficult to portray the organ shape of Different Individual.On the one hand due to the shape of abdomen organ, position and
Size difference in different crowd is huge, on the other hand due to the presence of different tissues organ adhesion and pathological tissues, so that device
Edge blurry, the contrast of official is low, is difficult to detect.These problems all bring challenge to existing abdominal organ segmentation method.
Have in newest algorithm through convolutional neural networks and detect the multiple organs of abdomen, but does not obtain accurate segmentation result.
It is therefore proposed that one kind can detect abdominal multivisceral organ position automatically, and being capable of each organ of quick Accurate Segmentation
Algorithm it is clinically very necessary and need.
Summary of the invention
It is a primary object of the present invention to overcome deficiency in the prior art, a kind of automatic detection multiple organs of abdomen are provided
Position, and be able to solve the joint dividing method of multiple organ in the medical image of speed and precision problem.It is above-mentioned to solve
Technical problem, solution of the invention is:
The multiple organ dividing method based on depth convolutional neural networks and region-competitive model is provided, for abdominal CT A
(Computed Tomography Angiography, CT angiography) three-dimensional data, i.e. computed tomography blood vessel
Liver, spleen, left kidney, right kidney in contrastographic picture carry out while dividing, described competing based on depth convolutional neural networks and region
The multiple organ dividing method for striving model includes following processes:
One, training Three dimensional convolution neural network；
Two, liver, spleen, kidney and the background in trained Three dimensional convolution neural network learning CTA volume data are utilized
Prior probability image；
Three, the initial segmentation region of each tissue is determined by the prior probability image of various organization；
Four, determine that each pixel is belonging respectively to four kinds of probability organized in image；
Five, the multi_region model based on region-competitive is established；
Six, with convex optimization method solving model；
Seven, it is post-processed, obtains the profile of each organ；
The process one specifically include the following steps:
Step A: prepare training set: collecting size and be the abdomen Hepatic CT A volume data of 512 × 512 × n, and make these
The Standard Segmentation of the livers of data, spleen and kidney is as a result, wherein n is the number of plies of volume data；
Step B: designing the structure of convolutional neural networks, and input picture block size is 496 × 496 × 279, and output image is
The image block that four sizes are 496 × 496 × 256, respectively corresponds each pixel and belongs to background, liver, spleen and kidney
Probability value；
Step C: using the various parameters in training set training convolutional neural networks, by training set ready in step A
It is put into designed convolutional neural networks in step B to be trained, obtains the various parameters in convolutional neural networks, trained
At；
The process two specifically refers to:
If the image for needing to carry out organ segmentation is three-dimensional data I (x), image definition domain isPixel is x=
(x1, x2, x3)；
By in the trained convolutional neural networks of image input process one to be tested, make each pixel quilt of image I (x)
The probability value for belonging to four kinds of tissues is assigned, it is respectively L that note, which belongs to the probability value of background, liver, spleen and kidney,0(x), L1(x),
L2(x) and L3(x), the size of x ∈ Ω, this four probability graphs are identical as original image size；
Wherein, symbolExpression is contained in, and symbol ∈ expression belongs to set；
The process three specifically refers to:
Respectively to probability graph Li(x), i=0,1,2,3 each pixel point value takes threshold value 0.5, greater than the pixel of threshold value
Belong to the histioid prime area Si, i=0,1,2,3；
The process four specifically refers to:
To the every bit pixel x in the original image I (x) of input, for the original area of background, liver, spleen and kidney
Domain Si, i=0,1,2,3, count the grey level histogram H in each regioni, i=0,1,2,3；Then according to the gray scale of pixel x
Value, by this gray value in grey level histogram HiIn shared ratio belong to the probability of i class as this pixel, be denoted as pi
(x)；
The process five specifically include the following steps:
Step D: the label function for defining background, liver, spleen and kidney is respectively as follows:
For x ∈ Ω and satisfaction
ui(x) value is equal to 1 expression pixel x and belongs to the i-th class loading；
Wherein, symbol :=indicate to be defined as；Ω indicates image-region；Region Ωi, i=0,1,2,3 respectively represent background,
Liver, spleen and kidney region；Symbol ∪ indicates union of sets；∑ is summation symbol；
Step E: to original image I (x), it is as follows to calculate frontier probe function g (x):
Wherein, β is positive number (value 0.2), and symbol :=expression is defined as；SymbolIndicate gradient operator；Symbol | |
Indicate L2 norm；
Step F: the region-competitive model based on prior probability image and regional statistical information is established:
And calculate Ci(x) :=[α1(-log pi(x))+α2(-log Li(x))] g (x), i=0,1,2,3；
Wherein, g (x) is the frontier probe function that step E is defined；Symbol :=indicate to be defined as；Ω indicates image-region；
∫ΩIndicate the integral in the Ω of region；Dx indicates domain integral member；∑ is summation symbol；pi(x) pixel calculated for process four
Point x belongs to the probability of class i；Li(x) the pixel x to be obtained by process two belongs to the prior probability of class i；Log is indicated with 10
Seek logarithm in bottom；Symbol | | indicate L1Norm；α1, α2For normal number, for adjusting every weight, value section [20,
50] in；Indicate gradient operator；The λ refers to regularization parameter, and for adjusting every weight, value is between [0,20]；
(C in the first item of above-mentioned energy functional (1)i(x) it is the item based on region, utilizes the prime area of each tissue
Grey-level statistics pi(x) and prior probability image Li(x), it estimates each pixel x and belongs to the i-th histioid cost function Ci
(x)；Section 2 is the item based on boundary, can capture boundary information well, guarantees the slickness of liver profile being partitioned into；
Area item and border item pass through a frontier probe function g (x) and weight α1, α2, λ adaptive adjusting specific gravity, so that close
The place on boundary, model depend on boundary information, the smooth region in liver, and model depends on area information；It is optimal
SolutionIt is available by the above-mentioned energy functional of minimization)
The process six includes the following steps:
Step G: convex relaxation is carried out to the model (1) in process five, is obtained:
And meet
Step H: the problem of solving above-mentioned belt restraining with Augmented Lagrange method (2) obtains optimal solution
Step I: the cut zone of each tissue is determined according to the value of each region label function, can specifically be indicated are as follows:
Ωi=x ∈ Ω | ui(x)=max (u0(x), u1(x), u2(x), u3(x)) }, respectively for i=0,1,2,3；
The process seven specifically refers to:
For the tissue binary segmentation result that process six obtains, the processing of hole operator successively is filled out with two dimension to get arriving finally
Corresponding tissue regions are realized and are divided to liver, spleen, the kidney in computed tomography angiography image.
In the present invention, the convolutional neural networks in the step B specifically:
Convolutional neural networks share 10 layers of convolutional layer: the 1st layer is convolutional layer, is inputted as the original of 496 × 496 × 279 sizes
Beginning image, export be for 96 sizes 248 × 248 × 136 sizes characteristic pattern, convolution kernel size be 7 × 7 × 9, step-length 2；
2nd convolutional layer inputs the characteristic pattern that 96 sizes are 124 × 124 × 68, exports the feature that 512 sizes are 62 × 62 × 64
Figure, convolution kernel size are 5 × 5 × 5, step-length 2；3rd layer to the 7th layer convolutional layer is distributed in operation on 4 GPU, on each GPU
The characteristic pattern that 512 sizes are 31 × 31 × 32 is all inputted, the characteristic pattern that 512 sizes are 31 × 31 × 32, convolution kernel are exported
Size is 3 × 3 × 3, step-length 1；512 characteristic patterns being distributed on 4 GPU are summed it up in the 7th layer of convolutional layer；8th convolution
Layer inputs the characteristic pattern that 64 sizes are 62 × 62 × 64, exports the characteristic pattern that 512 sizes are 62 × 62 × 64, and convolution kernel is big
Small is 3 × 3 × 3, step-length 1；The characteristic pattern that 9th convolutional layer input size is 124 × 124 × 128, exports 128 sizes
For 124 × 124 × 128 characteristic pattern；The characteristic pattern that 10th convolutional layer input is 16 248 × 248 × 256, exports 4
248 × 248 × 256 characteristic pattern, convolution kernel size are 3 × 3 × 3, step-length 1；Then a softmax function output is acted on
4 248 × 248 × 256 image blocks；Finally, the image block of output is upsampled to 496 × 496 × 256 sizes, obtain most
4 whole probability graphs；
Wherein, average pond layer is acted on after the 1st, 2 convolutional layer, local domain size is 2 × 2 × 2；In the 7th, 8,9
Double size output layer is reset in effect respectively after a convolutional layer, and 8 channels of input are become 2 × 2 × 2, i.e. double size, and 1/
8 port numbers；And the scale for exporting and inputting after 3 rearrangements is consistent.
In the present invention, in the process seven, two dimension is filled out the processing of hole operator and is specifically referred to:
To every tomographic image of volume data, the hole in tissue regions is detected, it is believed that also belonged to by the hole that the tissue surrounds
In the tissue, the value of its corresponding binary segmentation result is set as 1 to get the tissue regions for arriving final complete and accurate.
Compared with prior art, the beneficial effects of the present invention are:
The present invention can quickly detect the position of abdomen liver, spleen and kidney using convolutional neural networks automatically, and
And study obtains the prior probability image of accurate each organ, it then, can simultaneously accurately using region-competitive model
It is partitioned into the profile of liver, spleen and kidney.The present invention does not need man-machine interactively, and algorithm speed is fast, and segmentation result is accurate.
Detailed description of the invention
Fig. 1 is operational flowchart of the invention.
Fig. 2 is the 118th layer of original image of three-dimensional data.
Fig. 3 is intermediate effect figure of the 118th layer data after Three dimensional convolution Processing with Neural Network.
Fig. 4 is the 118th layer data through the technology of the present invention treated final effect figure.
Fig. 5 is the 189th layer of original image of three-dimensional data.
Fig. 6 is intermediate effect of the 189th layer data after Three dimensional convolution Processing with Neural Network.
Fig. 7 is the 189th layer data through the technology of the present invention treated final effect figure.
Specific embodiment
Present invention is further described in detail with specific embodiment with reference to the accompanying drawing:
The following examples can make the professional technician of this profession that the present invention be more fully understood, but not with any side
The formula limitation present invention.
As shown in Figure 1, using the multiple organ dividing method based on convolutional neural networks and region-competitive model, to computer
Liver, spleen and kidney in Tomography Angiography image carry out while dividing, specific steps are as follows:
The process one specifically include the following steps:
Step A: 140 sizes are collected and are the abdomen Hepatic CT A volume data of 512 × 512 × N, and these are provided by doctor
The liver segmentation standard results of data, wherein N is the number of plies of volume data.For the data of N > 286, delete in data without liver
The number of plies of dirty tissue, so that the data number of plies is reduced to 286 layers；For the data of N < 286, increase in its last layer several
Layer without liver organization, so that the data number of plies increases to 286 layers.
Step B, C: selecting size with machine frame from 512 × 512 × 286 image is the image of 496 × 496 × 279 sizes
Block inputs in network.Random initializtion network parameter, the probability graph then exported using propagated forward.According to what is obtained
Cost function between probability graph and the label of Standard Segmentation, backpropagation update network parameter.After 90 step of iteration, stop network
Training.
The process two specifically: input three dimensional CT A sweep image I size is 512 × 512 × 245, adjusts window width and window level
So that liver intensity range is between 0 to 255.Image is tested in trained convolutional neural networks, obtains four
With original image with the probability graph L of sizei, i=0,1,2,3.Probability graph given image every belongs to the probability L of class ii(x), value
Range is in [0.1,0.9].
The process three specifically: selected threshold value is 0.5, to probability graph L1Take truncation, it is believed that probability is greater than 0.5 point category
In liver；To probability graph L2Take truncation, it is believed that point of the probability greater than 0.5 belongs to spleen；To probability graph L3Take truncation, it is believed that probability
Point greater than 0.5 belongs to kidney；To probability graph L0Take truncation, it is believed that point of the probability greater than 0.5 belongs to background.In this way given four
Histioid initial segmentation result.
The process four specifically: to the every bit pixel x in the original image I (x) of input, for background, liver, spleen
Dirty and kidney prime area Si, i=0,1,2,3, count the grey level histogram H in each regioni, i=0,1,2,3.Then root
According to the gray value of pixel x, by this gray value in grey level histogram HiIn shared ratio belong to i class as this pixel
Probability, be denoted as pi(x)。
The process five specifically: image is calculated in each pixel according to the formula that five step B, C of process provides in explanation
The C of pointi(x) and the value of g (x).In this example, it takes and determines parameter alpha1=40, α2=24, λ=12.
The process six specifically: utilize convex relaxation and that primal-dual interior pointmethod, introduce variable ps, pt, p, by energy functional
Conversion are as follows:
s.t.pi(x)≤Ci(x), qi(x)≤λg(x)；I=0,1,2,3
To solve above-mentioned new model, using the technology of staggeredly iteration, respectively to i=0,1,2,3, iteratively calculate following formula
Son:
1, fixed variableOptimization Solution
This step can use Chambolle
Projection algorithm solves；
2, fixed variable updates
3, fixed variableIt updates
4, fixed variableIt updates
Iterative steps k=k+1 repeats the above 1-4 iteration until stopping after convergence.
Wherein, c is the step-length in iteration, is set as 0.35 in this example.G is that this illustrates that boundary defined in step 4 is visited
It surveys function g (x).After finally solving above-mentioned model, optimum segmentation label function
5, to obtained label functionTwo-value words, obtain final segmentation result, specifically,
Ωi=x ∈ Ω | ui(x)=max (u0(x), u1(x), u2(x), u3(x)) }, respectively for i=0,1,2,3.
In above-mentioned symbol, s.t. indicates " constrained in "；Max indicates maximizing, and min expression is minimized；K and k+1
Indicate iteration kth step and+1 step of kth；The subscript k of equal symbols indicates iteration kth step；Arg max expression, which is asked, to be made
Obtain the maximum variate-value of energy function；|| ||∞Indicate Infinite Norm；Div indicates divergence operator；:=indicate " being defined as "；∫Ω
Indicate the integral in the Ω of region；Dx indicates domain integral member；Set omega0, Ω1, Ω2, Ω3Respectively correspond background, liver, spleen
Dirty and kidney region.
The process seven specifically: to the binary segmentation result that process seven obtains, fill out the processing of hole operator with two dimension.Specifically
, to every tomographic image of volume data, detect the hole in liver area, it is believed that liver is also belonged to by the hole that liver surrounds,
The value of its corresponding binary segmentation result is set as 1.Similarly, same processing is also done to spleen, kidney region.
The the 118th, 189 layer of the respectively exemplary three-dimensional volume data of Fig. 2,5.Fig. 3,6 is by Three dimensional convolution Processing with Neural Network
Initial segmentation afterwards, Fig. 4,7 are the technology of the present invention treated final segmentation result.As can be seen that Three dimensional convolution network can be with
The position of liver, kidney and spleen is accurately navigated to, but segmentation result is inaccurate；By point of region-competitive model
It cuts, available each accurate segmentation result of organ.
Finally it should be noted that the above enumerated are only specific embodiments of the present invention.It is clear that the invention is not restricted to
Above embodiments can also have many variations.Those skilled in the art can directly lead from present disclosure
Out or all deformations for associating, it is considered as protection scope of the present invention.
Claims (3)
1. the multiple organ dividing method based on depth convolutional neural networks and region-competitive model, for abdominal CT A said three-dimensional body
Data, i.e., liver, spleen, left kidney, right kidney in computed tomography angiography image carry out while dividing, and feature exists
In the multiple organ dividing method based on depth convolutional neural networks and region-competitive model includes following processes:
One, training Three dimensional convolution neural network；
Two, the elder generation of liver, spleen, kidney and background in trained Three dimensional convolution neural network learning CTA volume data is utilized
Test probability graph；
Three, the initial segmentation region of each tissue is determined by the prior probability image of various organization；
Four, determine that each pixel is belonging respectively to four kinds of probability organized in image；
Five, the multi_region model based on region-competitive is established；
Six, with convex optimization method solving model；
Seven, it is post-processed, obtains the profile of each organ；
The process one specifically include the following steps:
Step A: prepare training set: collecting size and be the abdomen Hepatic CT A volume data of 512 × 512 × n, and make these data
Liver, spleen and kidney Standard Segmentation as a result, wherein n is the number of plies of volume data；
Step B: designing the structure of convolutional neural networks, and input picture block size is 496 × 496 × 279, and output image is four
The image block that size is 496 × 496 × 256, respectively corresponds the probability that each pixel belongs to background, liver, spleen and kidney
Value；
Step C: using the various parameters in training set training convolutional neural networks, training set ready in step A is put into
Designed convolutional neural networks are trained in step B, obtain the various parameters in convolutional neural networks, and training is completed；
The process two specifically refers to:
If the image for needing to carry out organ segmentation is three-dimensional data I (x), image definition domain isPixel is x=(x1,
x2, x3)；
By in the trained convolutional neural networks of image input process one to be tested, it is endowed each pixel of image I (x)
Belong to the probability value of four kinds of tissues, it is respectively L that note, which belongs to the probability value of background, liver, spleen and kidney,0(x), L1(x), L2
(x) and L3(x), the size of x ∈ Ω, this four probability graphs are identical as original image size；
Wherein, symbolExpression is contained in, and symbol ∈ expression belongs to set；
The process three specifically refers to:
Respectively to probability graph Li(x), i=0,1,2,3 each pixel point value take threshold value 0.5, and the pixel greater than threshold value belongs to this
Histioid prime area Si, i=0,1,2,3；
The process four specifically refers to:
To the every bit pixel x in the original image I (x) of input, for the prime area S of background, liver, spleen and kidneyi, i
=0,1,2,3, count the grey level histogram H in each regioni, i=0,1,2,3；It then, will according to the gray value of pixel x
This gray value is in grey level histogram HiIn shared ratio belong to the probability of i class as this pixel, be denoted as pi(x)；
The process five specifically include the following steps:
Step D: the label function for defining background, liver, spleen and kidney is respectively as follows:
For x ∈ Ω and satisfaction
ui(x) value is equal to 1 expression pixel x and belongs to the i-th class loading；
Wherein, symbol :=indicate to be defined as；Ω indicates image-region；Region Ωi, i=0,1,2,3 respectively represent background, liver,
Spleen and kidney region；∑ is summation symbol；
Step E: to original image I (x), it is as follows to calculate frontier probe function g (x):
Wherein, β is positive number, and symbol :=expression is defined as；SymbolIndicate gradient operator；Symbol | |2Indicate L2 norm；
Step F: the region-competitive model based on prior probability image and regional statistical information is established:
And calculate Ci(x) :=[α1(-log pi(x))+α2(-log Li(x))] g (x), i=0,1,2,3；
Wherein, g (x) is the frontier probe function that step E is defined；Symbol :=indicate to be defined as；Ω indicates image-region；∫ΩTable
Show the integral in the Ω of region；Dx indicates domain integral member；∑ is summation symbol；pi(x) belong to for the pixel x that process four calculates
In the probability of class i；Li(x) the pixel x to be obtained by process two belongs to the prior probability of class i；Log indicates to ask pair with 10 the bottom of for
Number；Symbol | | indicate L1Norm；α1, α2For normal number, for adjusting every weight, value is in section [20,50]；Indicate gradient operator；The λ refers to regularization parameter, and for adjusting every weight, value is between [0,20]；
The process six includes the following steps:
Step G: convex relaxation is carried out to the model (1) in process five, is obtained:
And meet
Step H: the problem of solving above-mentioned belt restraining with Augmented Lagrange method (2) obtains optimal solution
Step I: the cut zone of each tissue is determined according to the value of each region label function, can specifically be indicated are as follows:
Ωi=x ∈ Ω | ui(x)=max (u0(x), u1(x), u2(x), u3(x)) }, respectively for i=0,1,2,3；
The process seven specifically refers to:
For the tissue binary segmentation result that process six obtains, the processing of hole operator successively is filled out with two dimension to get final correspondence is arrived
Tissue regions are realized and are divided to liver, spleen, the kidney in computed tomography angiography image.
2. the multiple organ dividing method according to claim 1 based on depth convolutional neural networks and region-competitive model,
It is characterized in that, the convolutional neural networks in the step B specifically:
Convolutional neural networks share 10 layers of convolutional layer: the 1st layer is convolutional layer, is inputted as the original graph of 496 × 496 × 279 sizes
Picture, export be for 96 sizes 248 × 248 × 136 sizes characteristic pattern, convolution kernel size be 7 × 7 × 9, step-length 2；2nd
A convolutional layer inputs the characteristic pattern that 96 sizes are 124 × 124 × 68, exports the characteristic pattern that 512 sizes are 62 × 62 × 64,
Convolution kernel size is 5 × 5 × 5, step-length 2；3rd layer to the 7th layer convolutional layer is distributed in operation on 4 GPU, on each GPU
The characteristic pattern that 512 sizes are 31 × 31 × 32 is inputted, the characteristic pattern that 512 sizes are 31 × 31 × 32 is exported, convolution kernel is big
Small is 3 × 3 × 3, step-length 1；512 characteristic patterns being distributed on 4 GPU are summed it up in the 7th layer of convolutional layer；8th convolutional layer
The characteristic pattern that 64 sizes are 62 × 62 × 64 is inputted, the characteristic pattern that 512 sizes are 62 × 62 × 64, convolution kernel size are exported
It is 3 × 3 × 3, step-length 1；The characteristic pattern that 9th convolutional layer input size is 124 × 124 × 128, exporting 128 sizes is
124 × 124 × 128 characteristic pattern；The characteristic pattern that 10th convolutional layer input is 16 248 × 248 × 256, exports 4 248
× 248 × 256 characteristic pattern, convolution kernel size are 3 × 3 × 3, step-length 1；Then it acts on a softmax function and exports 4
248 × 248 × 256 image block；Finally, the image block of output is upsampled to 496 × 496 × 256 sizes, obtain final
4 probability graphs；
Wherein, average pond layer is acted on after the 1st, 2 convolutional layer, local domain size is 2 × 2 × 2；It is rolled up at the 7th, 8,9
Double size output layer is reset in effect respectively after lamination, 8 channels of input is become 2 × 2 × 2, i.e. double size, 1/8 is logical
Road number；And the scale for exporting and inputting after 3 rearrangements is consistent.
3. the multiple organ dividing method according to claim 1 based on depth convolutional neural networks and region-competitive model,
It is characterized in that, two dimension is filled out the processing of hole operator and is specifically referred in the process seven:
To every tomographic image of volume data, the hole in tissue regions is detected, it is believed that this is also belonged to by the hole that the tissue surrounds
The value of its corresponding binary segmentation result is set as 1 to get the tissue regions for arriving final complete and accurate by tissue.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2016103697030 | 2016-05-27 | ||
| CN201610369703 | 2016-05-27 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106204587A CN106204587A (en) | 2016-12-07 |
| CN106204587B true CN106204587B (en) | 2019-01-08 |
Family
ID=57473272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610539736.5A Active CN106204587B (en) | 2016-05-27 | 2016-07-05 | Multiple organ dividing method based on depth convolutional neural networks and region-competitive model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106204587B (en) |
Families Citing this family (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018112137A1 (en) * | 2016-12-15 | 2018-06-21 | General Electric Company | System and method for image segmentation using a joint deep learning model |
| WO2018112783A1 (en) * | 2016-12-21 | 2018-06-28 | 深圳前海达闼云端智能科技有限公司 | Image recognition method and device |
| CN106650662B (en) * | 2016-12-21 | 2021-03-23 | 北京旷视科技有限公司 | Target object shielding detection method and device |
| GB201705876D0 (en) | 2017-04-11 | 2017-05-24 | Kheiron Medical Tech Ltd | Recist |
| GB201705911D0 (en) | 2017-04-12 | 2017-05-24 | Kheiron Medical Tech Ltd | Abstracts |
| CN106886801B (en) * | 2017-04-14 | 2021-12-17 | 北京图森智途科技有限公司 | Image semantic segmentation method and device |
| CN107358600A (en) * | 2017-06-14 | 2017-11-17 | 北京全域医疗技术有限公司 | Automatic hook Target process, device and electronic equipment in radiotherapy planning |
| CN109325385A (en) * | 2017-07-31 | 2019-02-12 | 株式会社理光 | Target detection and region segmentation method, device and computer readable storage medium |
| CN107451565B (en) * | 2017-08-01 | 2020-12-11 | 重庆大学 | Semi-supervised small sample deep learning image mode classification and identification method |
| CN107705305A (en) * | 2017-10-20 | 2018-02-16 | 上海联影医疗科技有限公司 | A kind of method and device of Medical Image Processing |
| CN108062543A (en) * | 2018-01-16 | 2018-05-22 | 中车工业研究院有限公司 | A kind of face recognition method and device |
| CN110276762A (en) * | 2018-03-15 | 2019-09-24 | 北京大学 | A kind of full-automatic bearing calibration of respiratory movement of the diffusion-weighted Abdominal MRI imaging of more b values |
| CN110390660A (en) * | 2018-04-16 | 2019-10-29 | 北京连心医疗科技有限公司 | A kind of medical image jeopardizes organ automatic classification method, equipment and storage medium |
| CN108765369B (en) * | 2018-04-20 | 2023-05-02 | 平安科技（深圳）有限公司 | Method, apparatus, computer device and storage medium for detecting lung nodule |
| CN109255757B (en) * | 2018-04-25 | 2022-01-11 | 江苏大学 | Method for segmenting fruit stem region of grape bunch naturally placed by machine vision |
| CN109166107A (en) * | 2018-04-28 | 2019-01-08 | 北京市商汤科技开发有限公司 | A kind of medical image cutting method and device, electronic equipment and storage medium |
| AU2019285393B2 (en) | 2018-06-14 | 2022-12-08 | Kheiron Medical Technologies Ltd | Second reader |
| US20210290096A1 (en) * | 2018-07-31 | 2021-09-23 | Washington University | Methods and systems for segmenting organs in images using a cnn-based correction network |
| CN109242865B (en) * | 2018-09-26 | 2020-09-25 | 上海联影智能医疗科技有限公司 | Medical image automatic partitioning system, method, device and storage medium based on multiple maps |
| US11227390B2 (en) | 2018-09-26 | 2022-01-18 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for image processing |
| CN109544550B (en) * | 2018-12-05 | 2021-10-22 | 易必祥 | CT image-based intelligent detection and identification method and system |
| CN110097557B (en) * | 2019-01-31 | 2021-02-12 | 卫宁健康科技集团股份有限公司 | Medical image automatic segmentation method and system based on 3D-UNet |
| CN110223300A (en) * | 2019-06-13 | 2019-09-10 | 北京理工大学 | CT image abdominal multivisceral organ dividing method and device |
| CN110232383B (en) * | 2019-06-18 | 2021-07-02 | 湖南省华芯医疗器械有限公司 | Focus image recognition method and focus image recognition system based on deep learning model |
| CN110705555B (en) * | 2019-09-17 | 2022-06-14 | 中山大学 | Abdomen multi-organ nuclear magnetic resonance image segmentation method, system and medium based on FCN |
| EP3863022A1 (en) * | 2020-02-06 | 2021-08-11 | Siemens Healthcare GmbH | Method and system for automatically characterizing liver tissue of a patient, computer program and electronically readable storage medium |
| CN111507381B (en) * | 2020-03-31 | 2024-04-02 | 上海商汤智能科技有限公司 | Image recognition method, related device and equipment |
| CN111798463B (en) * | 2020-06-30 | 2023-03-17 | 电子科技大学 | Method for automatically segmenting multiple organs in head and neck CT image |
| CN111882527B (en) * | 2020-07-14 | 2021-12-21 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN112561860B (en) * | 2020-11-23 | 2022-05-03 | 重庆邮电大学 | BCA-UNet liver segmentation method based on prior shape constraint |
| CN113034522B (en) * | 2021-04-01 | 2022-11-01 | 上海市第一人民医院 | CT image segmentation method based on artificial neural network |
| CN113436173B (en) * | 2021-06-30 | 2023-06-27 | 陕西大智慧医疗科技股份有限公司 | Abdominal multi-organ segmentation modeling and segmentation method and system based on edge perception |
| CN114693830B (en) * | 2022-05-27 | 2022-11-15 | 阿里巴巴达摩院(杭州)科技有限公司 | Multi-organ segmentation and model training method, equipment and medium for medical image |
| CN116389705B (en) * | 2023-03-23 | 2023-10-13 | 北京至格科技有限公司 | Three-dimensional scene realization method and system for augmented reality |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609913A (en) * | 2012-01-17 | 2012-07-25 | 浙江大学 | Method for enhancing liver blood vessel and simultaneously dividing liver from blood vessel in CTA (computed tomography imaging) image |
| CN104573688A (en) * | 2015-01-19 | 2015-04-29 | 电子科技大学 | Mobile platform tobacco laser code intelligent identification method and device based on deep learning |
| CN104751457A (en) * | 2015-03-19 | 2015-07-01 | 浙江德尚韵兴图像科技有限公司 | Novel variational energy based liver partition method |
| CN104850836A (en) * | 2015-05-15 | 2015-08-19 | 浙江大学 | Automatic insect image identification method based on depth convolutional neural network |
| CN104992430A (en) * | 2015-04-14 | 2015-10-21 | 杭州奥视图像技术有限公司 | Fully-automatic three-dimensional liver segmentation method based on convolution nerve network |
| CN105574859A (en) * | 2015-12-14 | 2016-05-11 | 中国科学院深圳先进技术研究院 | Liver tumor segmentation method and device based on CT (Computed Tomography) image |
-
2016
- 2016-07-05 CN CN201610539736.5A patent/CN106204587B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609913A (en) * | 2012-01-17 | 2012-07-25 | 浙江大学 | Method for enhancing liver blood vessel and simultaneously dividing liver from blood vessel in CTA (computed tomography imaging) image |
| CN104573688A (en) * | 2015-01-19 | 2015-04-29 | 电子科技大学 | Mobile platform tobacco laser code intelligent identification method and device based on deep learning |
| CN104751457A (en) * | 2015-03-19 | 2015-07-01 | 浙江德尚韵兴图像科技有限公司 | Novel variational energy based liver partition method |
| CN104992430A (en) * | 2015-04-14 | 2015-10-21 | 杭州奥视图像技术有限公司 | Fully-automatic three-dimensional liver segmentation method based on convolution nerve network |
| CN104850836A (en) * | 2015-05-15 | 2015-08-19 | 浙江大学 | Automatic insect image identification method based on depth convolutional neural network |
| CN105574859A (en) * | 2015-12-14 | 2016-05-11 | 中国科学院深圳先进技术研究院 | Liver tumor segmentation method and device based on CT (Computed Tomography) image |
Non-Patent Citations (3)
| Title |
|---|
| Deep convolutional neural networks for multi-modality isointense infant brain image segmentation;Wenlu Zhang 等;《NeuroImage 》;20150103;214-224 |
| DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation;Holger R. Roth 等;《MICCAI》;20150622;1-12 |
| 基于多模态3D-CNNs特征提取的MＲI 脑肿瘤分割方法;罗蔓 等;《科学技术与工程》;20141108;第14卷(第31期);78-83 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106204587A (en) | 2016-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106204587B (en) | Multiple organ dividing method based on depth convolutional neural networks and region-competitive model | |
| CN104599270B (en) | A kind of Ultrasound Image of Breast Tumor dividing method based on improvement level set algorithm | |
| CN106056596B (en) | Full-automatic three-dimensional liver segmentation method based on local prior information and convex optimization | |
| CN106780518B (en) | A kind of MR image three-dimensional interactive segmentation method of the movable contour model cut based on random walk and figure | |
| Jeyavathana et al. | A survey: analysis on pre-processing and segmentation techniques for medical images | |
| Zhuge et al. | An abdominal aortic aneurysm segmentation method: Level set with region and statistical information | |
| CN107563983A (en) | Image processing method and medical imaging devices | |
| CN107403201A (en) | Tumour radiotherapy target area and jeopardize that organ is intelligent, automation delineation method | |
| Zhang et al. | Review of breast cancer pathologigcal image processing | |
| CN104809723A (en) | Three-dimensional liver CT (computed tomography) image automatically segmenting method based on hyper voxels and graph cut algorithm | |
| CN104899926A (en) | Medical image segmentation method and device | |
| CN109102506A (en) | A kind of automatic division method carrying out abdominal CT hepatic disease image based on three-stage cascade network | |
| CN102663416A (en) | Segmentation method of viscera and internal blood vessels thereof in surgical planning system | |
| CN103035009A (en) | Pulmonary nodule edge rebuilding and partitioning method based on computed tomography (CT) image | |
| CN108765385A (en) | A kind of double source CT coronary artery extraction method | |
| CN111784701A (en) | Ultrasonic image segmentation method and system combining boundary feature enhancement and multi-scale information | |
| CN112132808A (en) | Breast X-ray image lesion detection method and device based on normal model learning | |
| Tan et al. | An approach for pulmonary vascular extraction from chest CT images | |
| Peng et al. | H-ProMed: Ultrasound image segmentation based on the evolutionary neural network and an improved principal curve | |
| Hao et al. | Juxta-vascular pulmonary nodule segmentation in PET-CT imaging based on an LBF active contour model with information entropy and joint vector | |
| Biswas et al. | Chest X-ray enhancement to interpret pneumonia malformation based on fuzzy soft set and Dempster–Shafer theory of evidence | |
| CN107564023A (en) | A kind of CBCT teeth segmentation and modeling algorithm | |
| CN110197206A (en) | The method and device of image procossing | |
| Soomro et al. | Automatic segmentation of colorectal cancer in 3D MRI by combining deep learning and 3D level-set algorithm-a preliminary study | |
| CN110458842B (en) | Brain tumor segmentation method based on two-channel three-dimensional dense connection network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180110 Address after: 310012 7 floors, 7 floors, East 709 and 710, Hangzhou, Xihu District, Xihu District, Zhejiang Applicant after: ZHEJIANG DESHANG YUNXING IMAGE SCIENCE & TECHNOLOGY CO., LTD. Address before: 310012 East 801/802, Hangzhou, Hangzhou, Zhejiang, East Software Park, No. 6 building, No. 6 building, room 8, East 801/802 Applicant before: Kong Dexing |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Room 801/802, 8-storey East Science and Technology Building, Building 6, East Software Park, No. 90 Wensan Road, Hangzhou City, Zhejiang Province Patentee after: Zhejiang Deshang Yunxing Medical Technology Co., Ltd. Address before: 310012 Room 709, 710, 7-storey East Building, No. 90 Wensan Road, Xihu District, Hangzhou City, Zhejiang Province Patentee before: ZHEJIANG DESHANG YUNXING IMAGE SCIENCE & TECHNOLOGY CO., LTD. |