CN105225237A - Optoacoustic microvascular Iamge Segmentation and quantization method and device - Google Patents
Optoacoustic microvascular Iamge Segmentation and quantization method and device Download PDFInfo
- Publication number
- CN105225237A CN105225237A CN201510609043.4A CN201510609043A CN105225237A CN 105225237 A CN105225237 A CN 105225237A CN 201510609043 A CN201510609043 A CN 201510609043A CN 105225237 A CN105225237 A CN 105225237A
- Authority
- CN
- China
- Prior art keywords
- image
- optoacoustic
- microvascular
- segmentation
- pixel
- 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
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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The present invention discloses a kind of optoacoustic microvascular Iamge Segmentation and quantization method and device, accurately, comprehensively can quantize the blood vessel feature of optoacoustic microvascular image.Described method comprises: the optoacoustic microvascular image obtaining pending segmentation and quantification treatment, utilize multiple dimensioned Hessian wave filter to obtain the first segmentation image to described optoacoustic microvascular Image Segmentation Using, and utilize local auto-adaptive threshold method to obtain the second segmentation image to described optoacoustic microvascular Image Segmentation Using; Adopt weighted average method to carry out compound to described first segmentation image and described second segmentation image, and the image obtained is split image as the 3rd; Calculate the blood vessel characteristic parameter of described optoacoustic microvascular image based on described 3rd segmentation image, wherein, described blood vessel characteristic parameter comprises vessel radius, vessel density, length of vessel mark and fractal dimension.
Description
Technical field
The present invention relates to image processing field, be specifically related to a kind of optoacoustic microvascular Iamge Segmentation and quantization method and device.
Background technology
To the real time imagery of microcirculation in human body system, people are allowed to observe the disease progression relevant to blood vessel intuitively.Opto-acoustic microscopic imaging technology (PAM), as a kind of Dynamic Non-Destruction Measurement, can be used for obtaining the detection of biological tissue's blood-vessel image for microcirculatory disorders.Although optoacoustic microvascular image can realize the visual of blood vessel target, only blood vessel feature can be characterized qualitatively.And quantitative method can in digital form more intuitively for the diagnosis of clinical disease.
More existing quantization methods comprise measurement blood vessel diameter, the ultimate range etc. of blood flow rate and most adjacent blood vessel.But these parameters only describe the strength information of blood vessel, and the parameter describing vascular bending form is more useful, the change of such as retinal vascular morphologies can as the early stage sign of coronary heart disease and apoplexy.Thus, the quantization method finding a kind of strength information of comprehensive blood vessel and the blood vessel feature of shape information becomes a kind of problem demanding prompt solution.
Summary of the invention
The object of the invention is to, a kind of optoacoustic microvascular Iamge Segmentation and quantization method and device are provided, accurately, comprehensively can quantize the blood vessel feature of optoacoustic microvascular image.
For this purpose, on the one hand, the present invention proposes a kind of optoacoustic microvascular Iamge Segmentation and quantization method, comprising:
Obtain the optoacoustic microvascular image of pending segmentation and quantification treatment, utilize multiple dimensioned Hessian wave filter to obtain the first segmentation image to described optoacoustic microvascular Image Segmentation Using, and utilize local auto-adaptive threshold method to obtain the second segmentation image to described optoacoustic microvascular Image Segmentation Using;
Adopt weighted average method to carry out compound to described first segmentation image and described second segmentation image, and the image obtained is split image as the 3rd;
Calculate the blood vessel characteristic parameter of described optoacoustic microvascular image based on described 3rd segmentation image, wherein, described blood vessel characteristic parameter comprises vessel radius, vessel density, length of vessel mark and fractal dimension.
On the other hand, the present invention proposes a kind of optoacoustic microvascular Iamge Segmentation and quantization device, comprising:
Cutting unit, for obtaining the optoacoustic microvascular image of pending segmentation and quantification treatment, utilize multiple dimensioned Hessian wave filter to obtain the first segmentation image to described optoacoustic microvascular Image Segmentation Using, and utilize local auto-adaptive threshold method to obtain the second segmentation image to described optoacoustic microvascular Image Segmentation Using;
Recombiner unit, for adopting weighted average method to carry out compound to described first segmentation image and described second segmentation image, and splits image using the image obtained as the 3rd;
Computing unit, for calculating the blood vessel characteristic parameter of described optoacoustic microvascular image based on described 3rd segmentation image, wherein, described blood vessel characteristic parameter comprises vessel radius, vessel density, length of vessel mark and fractal dimension.
Optoacoustic microvascular Iamge Segmentation described in the embodiment of the present invention and quantization method and device, multiple dimensioned characteristic in conjunction with Hessian wave filter effectively splits the blood vessel of different size in image, and adopt self-adaptation local threshold method to improve the fuzzy of Hessian wave filter and enlarge-effect, to provide more accurate segmentation result, namely the multiple dimensioned Hessian wave filter of improvement is utilized to be partitioned into blood vessel from optoacoustic microvascular image, and quantize the vessel radius obtaining sign blood vessel feature, vessel density, length of vessel mark and fractal dimension, compared to only to the prior art that the strength information of blood vessel quantizes, the strength information of the comprehensive blood vessel of the present invention and shape information, the characteristic parameter of blood vessel is quantized, can be more accurate, the blood vessel feature of comprehensive quantification optoacoustic microvascular image, with in order to identify vascular diseases.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of optoacoustic microvascular Iamge Segmentation of the present invention and quantization method one embodiment;
Fig. 2 is an original optoacoustic microvascular image;
Fig. 3 is the skeleton image that optoacoustic microvascular Iamge Segmentation of the present invention and another embodiment of quantization method obtain;
Fig. 4 is the quantification figure of the segmentation image that obtains of optoacoustic microvascular Iamge Segmentation of the present invention and the another embodiment of quantization method and blood vessel characteristic parameter: (A) is original optoacoustic microvascular image, (B) be the first segmentation image, (C) be the second segmentation image, (D) be the 3rd segmentation image, (E) is vessel radius quantification figure;
Fig. 5 is the quantification figure of the blood vessel characteristic parameter of the subregion that optoacoustic microvascular Iamge Segmentation of the present invention and the another embodiment of quantization method obtain: (A) is length of vessel mark quantification figure, (B) for vessel density quantizes figure, (C) is fractal dimension quantification figure;
Fig. 6 is the frame structure schematic diagram of optoacoustic microvascular Iamge Segmentation of the present invention and quantization device one embodiment.
Embodiment
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
As shown in Figure 1, the present embodiment discloses a kind of optoacoustic microvascular Iamge Segmentation and quantization method, comprising:
S1, obtain the optoacoustic microvascular image (be illustrated in figure 2 original optoacoustic microvascular image) of pending segmentation and quantification treatment, utilize multiple dimensioned Hessian wave filter to obtain the first segmentation image to described optoacoustic microvascular Image Segmentation Using, and utilize local auto-adaptive threshold method to obtain the second segmentation image to described optoacoustic microvascular Image Segmentation Using;
S2, employing weighted average method carry out compound to described first segmentation image and described second segmentation image, and the image obtained is split image as the 3rd;
S3, calculate the blood vessel characteristic parameter of described optoacoustic microvascular image based on described 3rd segmentation image, wherein, described blood vessel characteristic parameter comprises vessel radius, vessel density, length of vessel mark and fractal dimension.
Optoacoustic microvascular Iamge Segmentation described in the embodiment of the present invention and quantization method, multiple dimensioned characteristic in conjunction with Hessian wave filter effectively splits the blood vessel of different size in image, and adopt self-adaptation local threshold method to improve the fuzzy of Hessian wave filter and enlarge-effect, to provide more accurate segmentation result, namely the multiple dimensioned Hessian wave filter of improvement is utilized to be partitioned into blood vessel from optoacoustic microvascular image, and quantize the vessel radius obtaining sign blood vessel feature, vessel density, length of vessel mark and fractal dimension, compared to only to the prior art that the strength information of blood vessel quantizes, the strength information of the comprehensive blood vessel of the present invention and shape information, the characteristic parameter of blood vessel is quantized, can be more accurate, the blood vessel feature of comprehensive quantification optoacoustic microvascular image, with in order to identify vascular diseases.
Alternatively, in another embodiment of optoacoustic microvascular Iamge Segmentation of the present invention and quantization method, describedly utilize multiple dimensioned Hessian wave filter to obtain the first segmentation image to described optoacoustic microvascular Image Segmentation Using, comprising:
Range scale [the s of described multiple dimensioned Hessian wave filter is determined according to described optoacoustic microvascular image I
min, s
max] and yardstick interval delta s, wherein, I ∈ R
m × n, m ∈ N
+, n ∈ N
+;
For each yardstick s, under calculating this yardstick s in described optoacoustic microvascular image I each x place, pixel position Hessian matrix H (I)
sx, and to H (I)
sxcarry out Eigenvalues Decomposition, obtain D eigenvalue λ
xl, λ
x2..., λ
xD, computing formula is
wherein, s=s
min+ k* Δ s, k are integer, and s ∈ [s
min, s
max], γ is regularization parameter, and I (x) is set to the intensity of the pixel of x for described optoacoustic microvascular image I meta, and D is the dimension of described optoacoustic microvascular image I, | λ
x1|>=| λ
x2|>=| λ
x3|>=...>=| λ
xD|;
For each yardstick s, the blood vessel functional value v at each x place, pixel position in described optoacoustic microvascular image I under calculating this yardstick s
sx (), computing formula is
Wherein,
α, β and θ are constant;
Calculate described first segmentation image I
hin the intensity I of each pixel
hx (), computing formula is
Wherein, x is the position of pixel, and T is threshold parameter;
According to described first segmentation image I
hin the intensity I of each pixel
hx () generates described first segmentation image I
h.
Alternatively, in another embodiment of optoacoustic microvascular Iamge Segmentation of the present invention and quantization method, the described local auto-adaptive threshold method that utilizes obtains the second segmentation image to described optoacoustic microvascular Image Segmentation Using, comprising:
For each pixel in described optoacoustic microvascular image I, calculate the threshold parameter T at this x place, pixel position
x, computing formula is
wherein, I (v) is set to the intensity of the pixel of v, W for described optoacoustic microvascular image I meta
xfor by position be x pixel centered by the region of threshold window W in described optoacoustic microvascular image I, W ∈ R
m × M, M is odd number;
Calculate the intensity I of each pixel in described second segmentation image
tx (), computing formula is
Wherein, I (x) is set to the intensity of the pixel of x for described optoacoustic microvascular image I meta;
According to the intensity I of each pixel in described second segmentation image
tx () generates described second segmentation image I
t.
Alternatively, in another embodiment of optoacoustic microvascular Iamge Segmentation of the present invention and quantization method, described employing weighted average method carries out compound to described first segmentation image and described second segmentation image, and the image obtained is split image as the 3rd, comprising:
Calculate the intensity I of each pixel in described 3rd segmentation image
outx (), computing formula is I
out(x)=α × I
t(x)+(1-α) × I
hx (), wherein, α is weight, I
hx () is set to the intensity of the pixel of x, I for described first segmentation image meta
tx () is set to the intensity of the pixel of x for described second segmentation image meta;
According to the intensity I of each pixel in described 3rd segmentation image
outx () generates described 3rd segmentation image I
out.
In the embodiment of the present invention, adopt average weighted method to carry out compound to described first segmentation image and described second segmentation image, thus more accurate vessel segmentation can be obtained.
Alternatively, in another embodiment of optoacoustic microvascular Iamge Segmentation of the present invention and quantization method, the described blood vessel characteristic parameter calculating described optoacoustic microvascular image based on described 3rd segmentation image, comprising:
Based on described 3rd segmentation image, distance transformation method is adopted to calculate the vessel radius of described optoacoustic microvascular image I;
Based on described 3rd segmentation image, calculate the vessel density VD of described optoacoustic microvascular image I, computing formula is
wherein, I
outx () is described 3rd segmentation image I
outmeta is set to the intensity of the pixel of x, I
out∈ R
m × n, m ∈ N
+, n ∈ N
+;
Skeletonization method is adopted to calculate described 3rd segmentation image I
outskeleton image I
skel, and based on described skeleton image I
skel, calculate the length of vessel mark VLF of described optoacoustic microvascular image I, computing formula is
wherein, I
skely () is described skeleton image I
skelmeta is set to the intensity of the pixel of y;
Utilize described skeleton image I
skel, adopt box-counting method to calculate the fractal dimension V of described optoacoustic microvascular image I
fD.
Alternatively, in another embodiment of optoacoustic microvascular Iamge Segmentation of the present invention and quantization method, also comprise:
The blood vessel characteristic parameter calculating described optoacoustic microvascular image every bit generates the quantification figure of corresponding blood vessel characteristic parameter.
As shown in Figure 4, (A) be original optoacoustic microvascular image, (B) be the first segmentation image, (C) be the second segmentation image, (D) be the 3rd segmentation image, (E) for vessel radius quantizes figure, can comparatively clearly see vessel radius information from Fig. 3, contribute to the diagnosis of microcirculatory vascular class disease.
Alternatively, in another embodiment of optoacoustic microvascular Iamge Segmentation of the present invention and quantization method, the blood vessel characteristic parameter of described calculating described optoacoustic microvascular image every bit, and generate corresponding blood vessel characteristic parameter quantification figure, comprising:
The quantification figure of vessel radius is generated according to the vessel radius of described optoacoustic microvascular image;
For each pixel in described optoacoustic microvascular image I, calculate vessel density VD (x) at this x place, pixel position, and generate the quantification figure of vessel density according to VD (x), computing formula is
wherein, I
outz () is described 3rd segmentation image I
outmeta is set to the intensity of the pixel of z, W
xfor by position be x pixel centered by local window N
1for odd number;
For each pixel in described optoacoustic microvascular image I, calculate length of vessel mark VLF (x) at this x place, pixel position, and generate length of vessel mark quantification figure according to VLF (x), computing formula is
wherein, I
skelu () is described skeleton image I
skelmeta is set to the intensity of the pixel of u;
For each pixel in described optoacoustic microvascular image I, the pixel value I of the position x of this pixel in the skeleton image corresponding to utilization
skelx (), adopts box-counting method to calculate the fractal dimension V of the every bit in described optoacoustic microvascular image I
fD(x), and according to V
fDx () generates fractal dimension and quantizes figure.
In the embodiment of the present invention, can directly obtain from the result of calculation of the vessel radius of optoacoustic microvascular image when calculating the vessel radius at each position place in optoacoustic microvascular image, and the length of vessel mark at each position place, vessel density is roughly identical with the computing method of the corresponding blood vessel characteristic parameter of optoacoustic microvascular image with in the computing method principle of fractal dimension information, uniquely unlike, because relate to a certain position, need to find the sub regions on the 3rd segmentation image for carrying out blood vessel calculation of characteristic parameters, the 3rd blood vessel characteristic parameter splitting the subregion of optoacoustic microvascular image corresponding to subregion on image found then can be calculated according to the method that the computing method of the corresponding blood vessel characteristic parameter with optoacoustic microvascular image are identical, and using the value that the calculates blood vessel characteristic parameter as some positions.
Alternatively, in another embodiment of optoacoustic microvascular Iamge Segmentation of the present invention and quantization method, also comprise:
Calculate the quantization parameter of the subregion image of described optoacoustic microvascular image I.
Alternatively, in another embodiment of optoacoustic microvascular Iamge Segmentation of the present invention and quantization method, the quantization parameter of the subregion image of described calculating described optoacoustic microvascular image I, also comprises:
For the vessel radius quantization parameter of described subregion R, quantize figure based on vessel radius, the vessel radius of pixel positions all in described subregion R is averaging, obtains the vessel radius quantization parameter value of described subregion R;
For the vessel density quantization parameter of described subregion R, quantize figure based on vessel density, the vessel density of pixel positions all in described subregion R is averaging, obtains the vessel density quantization parameter value of described subregion R;
For the length of vessel mark quantization parameter of described subregion R, quantize figure based on length of vessel mark, the length of vessel mark of pixel positions all in described subregion R is averaging, obtains the length of vessel mark quantization parameter value of described subregion R;
For the blood vessel fractal dimension quantization parameter of described subregion R, quantize figure based on blood vessel fractal dimension, the blood vessel fractal dimension of pixel positions all in described subregion R is averaging, obtains the blood vessel fractal dimension quantization parameter value of described subregion R.
The quantification figure of the blood vessel characteristic parameter of zonule as shown in Figure 5, (A) for length of vessel mark quantizes figure, (B) for vessel density quantizes figure, (C) for fractal dimension quantizes figure, comparatively clearly can see the length of vessel mark of subregion, vessel density and fractal dimension information from Fig. 5, contribute to the observation to local vascular situation.
As shown in Figure 6, the present embodiment discloses a kind of optoacoustic microvascular Iamge Segmentation and quantization device, comprising:
Cutting unit 1, for obtaining the optoacoustic microvascular image of pending segmentation and quantification treatment, utilize multiple dimensioned Hessian wave filter to obtain the first segmentation image to described optoacoustic microvascular Image Segmentation Using, and utilize local auto-adaptive threshold method to obtain the second segmentation image to described optoacoustic microvascular Image Segmentation Using;
Recombiner unit 2, for adopting weighted average method to carry out compound to described first segmentation image and described second segmentation image, and splits image using the image obtained as the 3rd;
Computing unit 3, for calculating the blood vessel characteristic parameter of described optoacoustic microvascular image based on described 3rd segmentation image, wherein, described blood vessel characteristic parameter comprises vessel radius, vessel density, length of vessel mark and fractal dimension.
Optoacoustic microvascular Iamge Segmentation described in the embodiment of the present invention and quantization device, multiple dimensioned characteristic in conjunction with Hessian wave filter effectively splits the blood vessel of different size in image, and adopt self-adaptation local threshold method to improve the fuzzy of Hessian wave filter and enlarge-effect, to provide more accurate segmentation result, namely the multiple dimensioned Hessian wave filter of improvement is utilized to be partitioned into blood vessel from optoacoustic microvascular image, and quantize the vessel radius obtaining sign blood vessel feature, vessel density, length of vessel mark and fractal dimension, compared to only to the prior art that the strength information of blood vessel quantizes, the strength information of the comprehensive blood vessel of the present invention and shape information, the characteristic parameter of blood vessel is quantized, can be more accurate, the blood vessel feature of comprehensive quantification optoacoustic microvascular image, with in order to identify vascular diseases.
Although describe embodiments of the present invention by reference to the accompanying drawings, but those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, such amendment and modification all fall into by within claims limited range.
Claims (10)
1. optoacoustic microvascular Iamge Segmentation and a quantization method, is characterized in that, comprising:
Obtain the optoacoustic microvascular image of pending segmentation and quantification treatment, utilize multiple dimensioned Hessian wave filter to obtain the first segmentation image to described optoacoustic microvascular Image Segmentation Using, and utilize local auto-adaptive threshold method to obtain the second segmentation image to described optoacoustic microvascular Image Segmentation Using;
Adopt weighted average method to carry out compound to described first segmentation image and described second segmentation image, and the image obtained is split image as the 3rd;
Calculate the blood vessel characteristic parameter of described optoacoustic microvascular image based on described 3rd segmentation image, wherein, described blood vessel characteristic parameter comprises vessel radius, vessel density, length of vessel mark and fractal dimension.
2. optoacoustic microvascular Iamge Segmentation according to claim 1 and quantization method, is characterized in that, describedly utilizes multiple dimensioned Hessian wave filter to obtain the first segmentation image to described optoacoustic microvascular Image Segmentation Using, comprising:
Range scale [the s of described multiple dimensioned Hessian wave filter is determined according to described optoacoustic microvascular image I
min, s
max] and yardstick interval delta s, wherein, I ∈ R
m × n, m ∈ N
+, n ∈ N
+;
For each yardstick s, under calculating this yardstick s in described optoacoustic microvascular image I each x place, pixel position Hessian matrix H (I)
sx, and to H (I)
sxcarry out Eigenvalues Decomposition, obtain D eigenvalue λ
xl, λ
x2..., λ
xD, computing formula is
wherein, s=s
min+ k* Δ s, k are integer, and s ∈ [s
min, s
max], γ is regularization parameter, and I (x) is set to the intensity of the pixel of x for described optoacoustic microvascular image I meta, and D is the dimension of described optoacoustic microvascular image I, | λ
x1|>=| λ
x2|>=| λ
x3|>=...>=| λ
xD|;
For each yardstick s, the blood vessel functional value v at each x place, pixel position in described optoacoustic microvascular image I under calculating this yardstick s
sx (), computing formula is
Wherein,
α, β and θ are constant;
Calculate described first segmentation image I
hin the intensity I of each pixel
hx (), computing formula is
Wherein, x is the position of pixel, and T is threshold parameter;
According to described first segmentation image I
hin the intensity I of each pixel
hx () generates described first segmentation image I
h.
3. optoacoustic microvascular Iamge Segmentation according to claim 1 and quantization method, is characterized in that, the described local auto-adaptive threshold method that utilizes obtains the second segmentation image to described optoacoustic microvascular Image Segmentation Using, comprising:
For each pixel in described optoacoustic microvascular image I, calculate the threshold parameter T at this x place, pixel position
x, computing formula is
wherein, I (v) is set to for described optoacoustic microvascular image I meta
vthe intensity of pixel, W
xfor with position being
xpixel centered by the region of threshold window W in described optoacoustic microvascular image I, W ∈ R
m × M, M is odd number;
Calculate the intensity I of each pixel in described second segmentation image
tx (), computing formula is
Wherein, I (x) is set to the intensity of the pixel of x for described optoacoustic microvascular image I meta;
According to the intensity I of each pixel in described second segmentation image
tx () generates described second segmentation image I
t.
4. optoacoustic microvascular Iamge Segmentation according to claim 1 and quantization method, it is characterized in that, described employing weighted average method carries out compound to described first segmentation image and described second segmentation image, and the image obtained is split image as the 3rd, comprising:
Calculate the intensity I of each pixel in described 3rd segmentation image
outx (), computing formula is I
out(x)=α × I
t(x)+(1-α) × I
hx (), wherein, α is weight, I
hx () is set to the intensity of the pixel of x, I for described first segmentation image meta
tx () is set to for described second segmentation image meta
xthe intensity of pixel;
According to the intensity I of each pixel in described 3rd segmentation image
outx () generates described 3rd segmentation image I
out.
5. optoacoustic microvascular Iamge Segmentation according to claim 1 and quantization method, is characterized in that, the described blood vessel characteristic parameter calculating described optoacoustic microvascular image based on described 3rd segmentation image, comprising:
Based on described 3rd segmentation image, distance transformation method is adopted to calculate the vessel radius of described optoacoustic microvascular image I;
Based on described 3rd segmentation image, calculate the vessel density VD of described optoacoustic microvascular image I, computing formula is
wherein, I
outx () is described 3rd segmentation image I
outmeta is set to the intensity of the pixel of x, I
out∈ R
m × n, m ∈ N
+, n ∈ N
+;
Skeletonization method is adopted to calculate described 3rd segmentation image I
outskeleton image I
skel, and based on described skeleton image I
skel, calculate the length of vessel mark VLF of described optoacoustic microvascular image I, computing formula is
wherein, I
skely () is described skeleton image I
skelmeta is set to the intensity of the pixel of y;
Utilize described skeleton image I
skel, adopt box-counting method to calculate the fractal dimension V of described optoacoustic microvascular image I
fD.
6. optoacoustic microvascular Iamge Segmentation according to claim 5 and quantization method, is characterized in that, also comprise:
The blood vessel characteristic parameter calculating described optoacoustic microvascular image every bit generates the quantification figure of corresponding blood vessel characteristic parameter.
7. optoacoustic microvascular Iamge Segmentation according to claim 6 and quantization method, is characterized in that, the blood vessel characteristic parameter of described calculating described optoacoustic microvascular image every bit, and generate corresponding blood vessel characteristic parameter quantification figure, comprising:
The quantification figure of vessel radius is generated according to the vessel radius of described optoacoustic microvascular image;
For each pixel in described optoacoustic microvascular image I, calculate vessel density VD (x) at this x place, pixel position, and generate the quantification figure of vessel density according to VD (x), computing formula is
wherein, I
outz () is described 3rd segmentation image I
outmeta is set to
zthe intensity of pixel, W
xfor by position be x pixel centered by local window, N
1for odd number;
For each pixel in described optoacoustic microvascular image I, calculate length of vessel mark VLF (x) at this x place, pixel position, and generate length of vessel mark quantification figure according to VLF (x), computing formula is
wherein, I
skelu () is described skeleton image I
skelmeta is set to the intensity of the pixel of u;
For each pixel in described optoacoustic microvascular image I, the pixel value I of the position x of this pixel in the skeleton image corresponding to utilization
skelx (), adopts box-counting method to calculate the fractal dimension V of the every bit in described optoacoustic microvascular image I
fD(x), and according to V
fDx () generates fractal dimension and quantizes figure.
8. optoacoustic microvascular Iamge Segmentation according to claim 1 and quantization method, is characterized in that, also comprise:
Calculate the quantization parameter of the subregion image of described optoacoustic microvascular image I.
9. optoacoustic microvascular Iamge Segmentation according to claim 8 and quantization method, is characterized in that, the quantization parameter of the subregion image of described calculating described optoacoustic microvascular image I, also comprises:
For the vessel radius quantization parameter of described subregion R, quantize figure based on vessel radius, the vessel radius of pixel positions all in described subregion R is averaging, obtains the vessel radius quantization parameter value of described subregion R;
For the vessel density quantization parameter of described subregion R, quantize figure based on vessel density, the vessel density of pixel positions all in described subregion R is averaging, obtains the vessel density quantization parameter value of described subregion R;
For the length of vessel mark quantization parameter of described subregion R, quantize figure based on length of vessel mark, the length of vessel mark of pixel positions all in described subregion R is averaging, obtains the length of vessel mark quantization parameter value of described subregion R;
For the blood vessel fractal dimension quantization parameter of described subregion R, quantize figure based on blood vessel fractal dimension, the blood vessel fractal dimension of pixel positions all in described subregion R is averaging, obtains the blood vessel fractal dimension quantization parameter value of described subregion R.
10. optoacoustic microvascular Iamge Segmentation and a quantization device, is characterized in that, comprising:
Cutting unit, for obtaining the optoacoustic microvascular image of pending segmentation and quantification treatment, utilize multiple dimensioned Hessian wave filter to obtain the first segmentation image to described optoacoustic microvascular Image Segmentation Using, and utilize local auto-adaptive threshold method to obtain the second segmentation image to described optoacoustic microvascular Image Segmentation Using;
Recombiner unit, for adopting weighted average method to carry out compound to described first segmentation image and described second segmentation image, and splits image using the image obtained as the 3rd;
Computing unit, for calculating the blood vessel characteristic parameter of described optoacoustic microvascular image based on described 3rd segmentation image, wherein, described blood vessel characteristic parameter comprises vessel radius, vessel density, length of vessel mark and fractal dimension.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510609043.4A CN105225237B (en) | 2015-09-22 | 2015-09-22 | Optoacoustic microvascular image splits and quantization method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510609043.4A CN105225237B (en) | 2015-09-22 | 2015-09-22 | Optoacoustic microvascular image splits and quantization method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105225237A true CN105225237A (en) | 2016-01-06 |
CN105225237B CN105225237B (en) | 2018-04-20 |
Family
ID=54994186
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510609043.4A Active CN105225237B (en) | 2015-09-22 | 2015-09-22 | Optoacoustic microvascular image splits and quantization method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105225237B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111798432A (en) * | 2020-07-07 | 2020-10-20 | 刘军 | Dynamic video image processing method for angiography |
CN112869768A (en) * | 2021-01-12 | 2021-06-01 | 哈尔滨工业大学(威海) | Multi-modality imaging-based body function multi-parameter quantification method and device |
CN113393425A (en) * | 2021-05-19 | 2021-09-14 | 武汉大学 | Microvessel distribution symmetry quantification method for gastric mucosa staining amplification imaging |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005048190A1 (en) * | 2003-11-13 | 2005-05-26 | Centre Hospitalier De L'universite De Montreal (Chum) | Automatic multi-dimensional intravascular ultrasound image segmentation method |
CN102467741A (en) * | 2010-11-18 | 2012-05-23 | 索尼公司 | Method and device for detecting spot area in image |
CN103218797A (en) * | 2012-01-19 | 2013-07-24 | 中国科学院上海生命科学研究院 | Method and system for processing and analyzing blood vessel image |
-
2015
- 2015-09-22 CN CN201510609043.4A patent/CN105225237B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005048190A1 (en) * | 2003-11-13 | 2005-05-26 | Centre Hospitalier De L'universite De Montreal (Chum) | Automatic multi-dimensional intravascular ultrasound image segmentation method |
CN102467741A (en) * | 2010-11-18 | 2012-05-23 | 索尼公司 | Method and device for detecting spot area in image |
CN103218797A (en) * | 2012-01-19 | 2013-07-24 | 中国科学院上海生命科学研究院 | Method and system for processing and analyzing blood vessel image |
Non-Patent Citations (3)
Title |
---|
周璐璐 等: "基于边缘检测与分裂合并的多区域分割研究", 《应用科技》 * |
朱坤 等: "微循环图像指标量化的提取研究", 《数理医药学杂志》 * |
游嘉: "眼底图像融合的研究及系统实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111798432A (en) * | 2020-07-07 | 2020-10-20 | 刘军 | Dynamic video image processing method for angiography |
CN112869768A (en) * | 2021-01-12 | 2021-06-01 | 哈尔滨工业大学(威海) | Multi-modality imaging-based body function multi-parameter quantification method and device |
CN113393425A (en) * | 2021-05-19 | 2021-09-14 | 武汉大学 | Microvessel distribution symmetry quantification method for gastric mucosa staining amplification imaging |
CN113393425B (en) * | 2021-05-19 | 2022-04-26 | 武汉大学 | Microvessel distribution symmetry quantification method for gastric mucosa staining amplification imaging |
Also Published As
Publication number | Publication date |
---|---|
CN105225237B (en) | 2018-04-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9679375B2 (en) | Ovarian follicle segmentation in ultrasound images | |
CN107072637B (en) | Apparatus and method for automated pneumothorax detection | |
Ikhsan et al. | An analysis of x-ray image enhancement methods for vertebral bone segmentation | |
US9585636B2 (en) | Ultrasonic diagnostic apparatus, medical image processing apparatus, and medical image processing method | |
DE102013001230B4 (en) | Axis-related characterization of shear waves with ultrasound | |
CN102999905A (en) | Automatic eye fundus image vessel detecting method based on PCNN (pulse coupled neural network) | |
Gastounioti et al. | Carotid artery wall motion analysis from B-mode ultrasound using adaptive block matching: in silico evaluation and in vivo application | |
US10470744B2 (en) | Ultrasound diagnosis apparatus, ultrasound diagnosis method performed by the ultrasound diagnosis apparatus, and computer-readable storage medium having the ultrasound diagnosis method recorded thereon | |
EP2189117B1 (en) | Region setting for intima media thickness measurement in an ultrasound system | |
DE102015201984B4 (en) | Method and device for analyzing and displaying blood flow information | |
CN114931396A (en) | Ultrasound elastography system and method | |
Samiappan et al. | Classification of carotid artery abnormalities in ultrasound images using an artificial neural classifier. | |
CN105225237A (en) | Optoacoustic microvascular Iamge Segmentation and quantization method and device | |
CN104732520A (en) | Cardio-thoracic ratio measuring algorithm and system for chest digital image | |
FI113835B (en) | Cardiac analysis method for monitoring atrial arrhythmias, involves focusing cardiac analysis to dynamic changes of configuration of P-wave of ECG signal, and comparing every detected P-wave to reference P-wave in defined time period | |
CN105266849B (en) | Real-time ultrasound elastograph imaging method and system | |
CN104182984A (en) | Method and system for rapidly and automatically collecting blood vessel edge forms in dynamic ultrasonic image | |
JP6191328B2 (en) | Ultrasonic diagnostic apparatus, ultrasonic image analysis method, and program | |
JP2019106202A (en) | Health state evaluation support system and capillary vessel data acquisition method | |
CN104546000A (en) | Shape feature-based ultrasonic image bladder volume measuring method and device | |
CN108182680B (en) | IVOCT image-based angle automatic identification method for bifurcated vessels | |
CN104077780B (en) | A kind of medical image non-rigid registration algorithm method of evaluating performance based on segmentation | |
CN110840484B (en) | Ultrasonic imaging method and device for adaptively matching optimal sound velocity and ultrasonic equipment | |
CN112674791A (en) | Optimization method and system for ultrasonic elastography of muscles | |
KR101492254B1 (en) | Ultrasound diagnostic apparatus and method for quality control |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20200617 Address after: 264209 No. 2, Wenhua West Road, Shandong, Weihai Co-patentee after: Shandong chenjing Photoelectric Technology Co.,Ltd. Patentee after: HARBIN INSTITUTE OF TECHNOLOGY (WEIHAI) Address before: 264209, No. 2, Wenhua West Road, Huancui District, Shandong, Weihai Patentee before: HARBIN INSTITUTE OF TECHNOLOGY (WEIHAI) |
|
TR01 | Transfer of patent right |