Method, apparatus, device and storage medium for extracting a cardiovascular vessel from a CTA image

Abstract

A method, an apparatus, a device, and a storage medium for extracting a cardiovascular vessel from a CTA image, the method including the steps of: performing erosion operation and dilation operation on image data successively via a preset structural element to obtain a structure mask; performing a slice-by-slice transformation on the plane of section images of the structural mask to acquire the first ascending aortic structure in the structural mask, and acquiring an aortic center position and an aortic radius in the last slice of the plane of section image of the said structural mask; establishing a binarized sphere structure according to the aortic center position and the aortic radius, and synthesizing a second ascending aorta structure by combining the first ascending aorta structure with the structure mask and the binarized sphere structure.

Claims

1. A method for extracting a cardiovascular vessel from a CTA image, comprising the steps of: performing a first erosion operation and dilation operation on an image data I successively via a preset structural element Kr to obtain a structure mask I′, said image data I is a coronary angiography image after down-sampling processing targeted at large-size original CTA data; in order to quickly extract a large-size ascending aortic structure without affecting the precision of the structure extraction; and said structural mask I′ is a structure excluding lung region, wherein a sphere of which the radius is controlled at a preset volume element is selected, and the number of the above preset volume elements is 6±2, the sphere of which the radius is controlled at the preset volume element is used as a preset structural element Kr, the erosion operation is performed on the image data I firstly via the preset structural element Kr, and then the dilation operation is performed via the preset structural element Kr to obtain the structure mask I′ with a calculation formula expressed as: I′=I∘K.sub.r=(I⊖K.sub.r)⊕K.sub.r; performing a slice-by-slice transformation on the plane of section images of the structural mask I′ to acquire the first ascending aortic structure in the structural mask, and acquiring an aortic center position and an aortic radius in the last slice of the plane of section image of said structural mask I′, wherein, during the slice-by-slice transformation, the aortic center positions Co(n) and the aortic radius Ro(n), n=1,2, . . . , N, of the current plane of section image are transformed slice by slice, a preset deviation value is set, and the preset deviation value is ε=6±2, when a distance between the aorta center positions of the current plane of section image and the preceding plane of section image is greater than a preset deviation value, the detection is stopped, and the current plane of section image is determined as the last slice of plane of section image, and the aorta center position Co(n) and the aortic radius Ro(n) in the last slice of plane of section image are acquired; establishing a binarized sphere structure according to the aortic center position and the aortic radius by taking the aortic radius as the radius of the binarized sphere structure, and synthesizing a second ascending aorta structure by combining the first ascending aorta structure with the structure mask and the binarized sphere structure, wherein at the aortic center position Co(n), a binarized sphere structure Sphx is established by taking the aortic radius Ro(n) as the radius, and a seconding ascending aortic structure A.sub.S is synthesized by combining the first ascending aortic structure A.sub.n with the structural mask B and the binarized sphere structure Sph.sub.X, and the calculation formula is:
A.sub.S=(A.sub.N∪Sph.sub.X)∩B where A.sub.S is the second ascending aortic structure, A.sub.N is the first ascending aortic structure, Sph.sub.X is the binarized sphere structure and B is the structural mask, and erosion is performed via a morphological opening operation, so as to obtain a supplementary area of an ascending aorta root, and the second ascending aortic structure A.sub.S is the complete ascending aortic structure of an aortic sinus; wherein in order to enhance blood vessels of the heart, prevent the contrast of blood vessels in the heart region from being very low and prevent the blood vessel information from being suppressed, a contrast equalization filtering is performed on the image data according to the shape of the blood vessel and the strength of the blood vessel signal to enhance the coronary arteries; F.sub.A and F.sub.B are blood vessel shape measures, and F.sub.C is a blood vessel signal strength measure, which is used to improve the signal-to-noise ratio of blood vessels in the heart region, wherein: $F_{A} = e^{- \frac{{(1 - R_{A})}^{2}}{2 a^{2}}}, F_{B} = e^{- \frac{R_{B}^{2}}{2 β^{2}}}, F_{C} = {\begin{matrix} γ_{C} .Math. e^{- \frac{{(z_{σ} - R_{C})}^{2}}{2 C^{2}}} \\ γ_{C} + (1 - γ_{C}) .Math. \frac{Z_{σ} - R_{C}}{(1 - r_{h}) .Math. c} \end{matrix} \begin{matrix} Z_{σ} \leq c \\ Z_{σ} > c \end{matrix},$ wherein, R.sub.A and R.sub.B are two measurement functions based on the characteristics values of Hessian Matrix, R.sub.A is used to distinguish between a sheet structure and a linear structure, R.sub.B is used to distinguish between a point structure and a linear structure, α, β, and C function as thresholds for controlling the sensitivity of R.sub.A, R.sub.B, and R.sub.C, and γ.sub.C∈(0,1) is a response expectation constant which generally ranges from 0.5 to 0.8; under a certain scale σ, spatial Hessian matrix norm ∥H.sub.σ∥=√{square root over (Σj.sub.j≤Dλ.sub.j.sup.2)} exhibits a higher response in the lung region with a larger blood vessel contrast, but exhibits a smaller response in the heart region; ∥H.sub.σ∥ mean value and maximum value in the lung region and the peripheral region both trend to monotonously increase; when Z.sub.o0 be a zero matrix, the maximum norm value under each scale is recorded as:
Z.sub.σn(x) custom character max.sub.x{Z.sub.σn−1(x),∥H.sub.σn(x)∥}, n=1, . . . ,N a dynamic threshold c is found to distinguish between the lung region and other tissues according to Z.sub.σ≤c and Z.sub.σ>c in measurement F.sub.C; the non-lung region is defined as θ.sub.h, the maximum norm is calculated in θ.sub.h and the full space Θ respectively via r.sub.h=∥H.sub.σ.sub.n(x)∥.sub.max/∥H.sub.σ.sub.n(Θ)∥.sub.max, r.sub.h∈(0.65,1) is calculated by experimental statistics, and then the parameter c=r.sub.h.Math.max(Z.sub.σ) is obtained; let R.sub.C=c, and a blood vessel characteristic graph V(x, σ) after contrast enhancement is finally obtained, $𝒱 (x, σ) \overset{△}{=} {\begin{matrix} 0 & if λ_{2} > 0 or λ_{3} > 0 \\ F_{A} .Math. F_{B} .Math. F_{C} & else \end{matrix},$ where λ.sub.2 and λ.sub.3 are the second characteristic value and the third characteristic value of the spatial Hessian matrix respectively.

2. A device for extracting a cardiovascular vessel from a CTA image, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the method of claim 1 are implemented when the computer program is executed by the processor.

3. An apparatus for extracting a cardiovascular vessel from a CTA image, wherein the apparatus comprises: a structure mask acquiring unit, configured for performing erosion operation and dilation operation on image data I successively via a preset structural element Kr to obtain a structure mask, the image data I is a coronary angiography image after down-sampling processing and the structural mask I′ is a structure excluding lung region, wherein a sphere of which the radius is controlled at a preset volume element is selected, and the number of the above preset volume elements is 6±2, the sphere of which the radius is controlled at the preset volume element is used as a preset structural element Kr, the erosion operation is performed on the image data I firstly via the preset structural element Kr, and then the dilation operation is performed via the preset structural element Kr to obtain the structure mask I′ with a calculation formula expressed as: I′=I∘K.sub.r=(I⊖K.sub.r)⊕K.sub.r; a slice-by-slice transformation unit, configured for performing a slice-by-slice transformation on plane of section images of the structural mask I′ to acquire the first ascending aortic structure in the structural mask, and acquiring an aortic center position and an aortic radius in the last slice of the plane of section image of the structural mask I′, wherein, during the slice-by-slice transformation, the aortic center positions Co(n) and the aortic radius Ro(n), n=1,2, . . . , N, of the current plane of section image are transformed slice by slice, a preset deviation value is set, and the preset deviation value is ε=6±2, when a distance between the aorta center positions of the current plane of section image and the preceding plane of section image is greater than a preset deviation value, the detection is stopped, and the current plane of section image is determined as the last slice of plane of section image, and the aorta center position Co(n) and the aortic radius Ro(n) in the last slice of plane of section image are acquired; and a synthesizing unit, configured for establishing a binarized sphere structure according to the aortic center position and the aortic radius by taking the aortic radius as the radius of the binarized sphere structure, and synthesizing a second ascending aorta structure by combining the first ascending aorta structure with the structure mask and the binarized sphere structure, wherein at the aortic center position Co(n), a binarized sphere structure Sphx is established by taking the aortic radius Ro(n) as the radius, and a seconding ascending aortic structure A.sub.S is synthesized by combining the first ascending aortic structure A.sub.n with the structural mask B and the binarized sphere structure Sph.sub.X, and the calculation formula is:
A.sub.S=(A.sub.N∪Sph.sub.X)∩B where A.sub.S is the second ascending aortic structure, A.sub.N is the first ascending aortic structure, Sph.sub.X is the binarized sphere structure and B is the structural mask, and erosion is performed via a morphological opening operation, so as to obtain a supplementary area of an ascending aorta root, and the second ascending aortic structure A.sub.S is the complete ascending aortic structure of an aortic sinus; wherein in order to enhance blood vessels of the heart, prevent the contrast of blood vessels in the heart region from being very low and prevent the blood vessel information from being suppressed, a contrast equalization filtering is performed on the image data according to the shape of the blood vessel and the strength of the blood vessel signal to enhance the coronary arteries; F.sub.A and F.sub.B are blood vessel shape measures, and F.sub.C is a blood vessel signal strength measure, which is used to improve the signal-to-noise ratio of blood vessels in the heart region, wherein: $F_{A} = e^{- \frac{{(1 - R_{A})}^{2}}{2 a^{2}}}, F_{B} = e^{- \frac{R_{B}^{2}}{2 β^{2}}}, F_{C} = {\begin{matrix} γ_{C} .Math. e^{- \frac{{(z_{σ} - R_{C})}^{2}}{2 C^{2}}} \\ γ_{C} + (1 - γ_{C}) .Math. \frac{Z_{σ} - R_{C}}{(1 - r_{h}) .Math. c} \end{matrix} \begin{matrix} Z_{σ} \leq c \\ Z_{σ} > c \end{matrix},$ wherein, R.sub.A and R.sub.B are two measurement functions based on the characteristics values of Hessian Matrix, R.sub.A is used to distinguish between a sheet structure and a linear structure, R.sub.B is used to distinguish between a point structure and a linear structure, α, β, and C function as thresholds for controlling the sensitivity of R.sub.A, R.sub.B, and R.sub.C, and γ.sub.C∈(0,1) is a response expectation constant which generally ranges from 0.5 to 0.8; under a certain scale σ, spatial Hessian matrix norm ∥H.sub.σ∥=√{square root over (Σj.sub.j≤Dλ.sub.j.sup.2)} exhibits a higher response in the lung region with a larger blood vessel contrast, but exhibits a smaller response in the heart region; ∥H.sub.σ∥ mean value and maximum value in the lung region and the peripheral region both trend to monotonously increase; when Z.sub.o0 be a zero matrix, the maximum norm value under each scale is recorded as:
Z.sub.σn(x) custom character max.sub.x{Z.sub.σn−1(x),∥H.sub.σn(x)∥}, n=1, . . . ,N a dynamic threshold c is found to distinguish between the lung region and other tissues according to Z.sub.σ≤c and Z.sub.σ>c in measurement F.sub.C; the non-lung region is defined as θ.sub.h, the maximum norm is calculated in θ.sub.h and the full space Θ respectively via r.sub.h=∥H.sub.σ.sub.n(x)∥.sub.max/∥H.sub.σ.sub.n(Θ)∥.sub.max,r.sub.h∈(0.65,1) is calculated by experimental statistics, and then the parameter c=r.sub.h.Math.max(Z.sub.σ) is obtained; let R.sub.C=c, and a blood vessel characteristic graph V(x, σ) after contrast enhancement is finally obtained, $𝒱 (x, σ) \overset{△}{=} {\begin{matrix} 0 & if λ_{2} > 0 or λ_{3} > 0 \\ F_{A} .Math. F_{B} .Math. F_{C} & else \end{matrix},$ where λ.sub.2 and λ.sub.3 are the second characteristic value and the third characteristic value of the spatial Hessian matrix respectively.

4. The apparatus of claim 3, wherein the apparatus further comprises: a processor, and a computer-readable storage medium storing a computer program, the computer program can be executed by the processor to realize the functions of the structure mask acquiring unit, the slice-by-slice transformation unit, and the synthesizing unit.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

(1) FIG. 1 is an implementation flowchart of a method for extracting a cardiovascular vessel from a CTA image provided in Embodiment 1 of the present invention;

(2) FIG. 2 is an implementation flowchart of a method for extracting a cardiovascular vessel from a CTA image provided in Embodiment 2 of the present invention;

(3) FIG. 3 is a comparison diagram of axial projection effects;

(4) FIG. 4 is a structural representation of an apparatus for extracting a cardiovascular vessel from a CTA image provided in Embodiment 3 of the present invention;

(5) FIG. 5 is a structural representation of a device for extracting a cardiovascular vessel from a CTA image provided in Embodiment 4 of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT

(6) In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be further illustrated in detail below in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

(7) The specific implementation of the present invention will be described in detail below in conjunction with the specific embodiments:

Embodiment 1

(8) FIG. 1 shows an implementation process of a method for extracting a cardiovascular vessel from a CTA image provided in Embodiment 1 of the present invention, for the convenience of illustration, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

(9) In step S101, erosion operation and dilation operation are performed on image data successively via a preset structural element to obtain a structure mask.

(10) In an embodiment of the present invention, the above image data is a coronary angiography image after down-sampling processing targeted at large-size original CTA data, in order to quickly extract a large-size ascending aortic structure without affecting the precision of the structure extraction. The image size may be down-sampled to half of the original size; some noise in the above image data and some structures that are not related to the aorta are suppressed or attenuated. Erosion operation is performed on image data firstly, then dilation operation is performed to obtain the structure mask B, and the above structural mask is a structure excluding the lung region.

(11) Further, a sphere of which the radius is controlled at a preset volume element is taken as the preset structural element, erosion operation is performed firstly on the image data via a preset structural element, and then dilation operation is performed on image data via a preset structural element to obtain a structure mask which includes: an ascending aorta, partial ventricle and atrium and a descending aorta, of which the partial ventricle and atrium and the descending aorta coexist in a spatial communication area, and the descending aorta is not spatially connected with the ascending aorta and partial ventricle and atrium.

(12) Specifically, a sphere of which the radius is controlled at a preset volume element is selected, and the number of the above preset volume elements is 6±2, the sphere of which the radius is controlled at the preset volume element is used as a preset structural element K.sub.r, erosion operation is performed on the image data I firstly via the preset structural element Kr, and then dilation operation I is performed via the preset structural element Kr to obtain the structure mask I′, and the above calculation formula is expressed as: I′=I∘K.sub.r=(⊖K.sub.r)⊕K.sub.r.

(13) In step S102, a slice-by-slice transformation is performed on plane of section images of the structural mask to acquire the first ascending aortic structure in the structural mask, and an aortic center position and an aortic radius are acquired in the last slice of the plane of section image of the structural mask.

(14) In the embodiment of the present invention, a Hough Transform is performed on the plane of section image of the structural mask, that is, on an axial position plane of the structural mask (i.e., a heart horizontal plane of section), a circular area corresponding to the aorta is selected in each plane of section image, and then, in the circular area segmentation and morphological opening operation are performed to obtain the first ascending aortic structure A.sub.N, and an aortic center position C.sub.oN and an aortic radius R.sub.oN are acquired in the last slice of the plane of section image of the structural mask.

(15) Further, during the slice-by-slice transformation, the current plane of section image will be determined as the last slice of plane of section image if the distance between the aorta center positions of the current plane of section image and the preceding plane of section image is greater than a preset deviation value, and the aorta center position and the aortic radius in the last slice of plane of section image will be acquired.

(16) Specifically, during the slice-by-slice transformation, the aortic center positions (n) and the aortic radius (n), n=1,2, . . . , N, of the current plane of section image are transformed slice by slice. A preset deviation value is set, and the preset deviation value is ε=6±2. When the distance between the aorta center positions of two adjacent slices Dn>ε, the detection would be stopped, and the current plane of section image is determined as the last slice of plane of section image, and the aorta center position C(n) and the aortic radius Ro(n) in the last slice of plane of section image are acquired.

(17) In step S103, a binarized sphere structure is established according to the aortic center position and the aortic radius, and a second ascending aortic structure is synthesized by combining the first ascending aortic structure with the structural mask and the binarized sphere structure.

(18) In the embodiment of the present invention, at the aortic center position C.sub.oN, a binarized sphere structure Sph.sub.X is established by taking the aortic radius R.sub.oN as the radius, and a second ascending aortic structure A.sub.S is synthesized by combining the first ascending aortic structure A.sub.N with the structural mask B and the binarized sphere structure Sph.sub.X, and the calculation formula is:
A.sub.S=(A.sub.N∪Sph.sub.X)∩B

(19) Where A.sub.S is the second ascending aortic structure, A.sub.N is the first ascending aortic structure, Sph.sub.X is the binarized sphere structure and B is the structural mask, and erosion is performed via a morphological opening operation, so as to obtain the supplementary area of the ascending aorta root, i.e., an aortic sinus area, and the second ascending aortic structure A.sub.S is the complete ascending aortic structure of the aortic sinus.

(20) In the embodiment of the present invention, erosion operation and dilation operation are performed on image data to erode the irrelevant structures of the lungs and retain the heart and aortic structures, the first ascending aortic structure is acquired via the slice-by-slice transformation and combined with a binarized sphere structure to synthesize a second ascending aortic structure, and erosion is performed via a morphological opening operation, so that the supplementary area of the ascending aorta root is obtained, thereby extracting the shapes of ascending aorta and root aortic sinus to accurately visualize the aortic structure and morphology, thus providing an important reference for automatic centerline extraction, segmentation and computer-assisted intelligent intervention to greatly improve the level and ability of medical imaging researches to solve clinical issues.

Embodiment 2

(21) FIG. 2 shows an implementation process of a method for extracting a cardiovascular vessel from a CTA image provided in Embodiment 2 of the present invention, for the convenience of illustration, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

(22) In step S201, erosion operation and dilation operation are performed on image data successively via a preset structural element to obtain a structure mask.

(23) In step S202, a slice-by-slice transformation is performed on plane of section images of the structural mask to acquire the first ascending aortic structure in the structural mask, and an aortic center position and an aortic radius are acquired in the last slice of the plane of section image of the structural mask.

(24) In step S203, a binarized sphere structure is established according to the aortic center position and the aortic radius, and a second ascending aortic structure is synthesized by combining the first ascending aortic structure with the structural mask and the binarized sphere structure.

(25) In step S204, a contrast equalization filtering is performed on the image data according to the shape of the blood vessel and the strength of the blood vessel signal to enhance the coronary arteries, and a coronary artery starting position is determined according to the maximum response filtering in the second ascending aorta structure.

(26) In the embodiment of the present invention, in order to enhance the blood vessels of the heart, prevent the contrast of blood vessels in the heart region from being very low and prevent the blood vessel information from being suppressed, a contrast equalization filtering is performed on the image data according to the shape of the blood vessel and the strength of the blood vessel signal to enhance the coronary arteries. F.sub.A and F.sub.B are blood vessel shape measures, and F.sub.C is a blood vessel signal strength measure, which can be used to improve the signal-to-noise ratio of blood vessels in the heart region, wherein:

(27) $F_{A} = e^{- \frac{{(1 - R_{A})}^{2}}{2 a^{2}}}, F_{B} = e^{- \frac{R_{B}^{2}}{2 β^{2}}}, F_{C} = {\begin{matrix} γ_{c} .Math. e^{- \frac{{(Z_{σ} - R_{C})}^{2}}{2 C^{2}}} & Z_{σ} \leq c \\ γ_{c} + (1 - γ_{c}) .Math. \frac{Z_{σ} - R_{C}}{(1 - r_{h}) .Math. c} & Z_{σ} > c \end{matrix},$
wherein, R.sub.A and R.sub.B are two measurement functions based on the characteristic values of the Hessian Matrix, R.sub.A is used to distinguish between a sheet structure and a linear structure, R.sub.B is used to distinguish between a point structure and a linear structure, α, β and c function as thresholds for controlling the sensitivity of R.sub.A, R.sub.B and R.sub.c, and γ.sub.C∈(0,1) is a response expectation constant which generally ranges from 0.5 to 0.8. Under a certain scale σ, the spatial Hessian matrix norm ∥H.sub.σ∥=√{square root over (Σj.sub.j≤Dλ.sub.j.sup.2)} exhibits a higher response in the lung region with a larger blood vessel contrast, but exhibits a smaller response in the heart region. ∥H.sub.σ∥ mean value and maximum value in the lung region and the peripheral region both trend to monotonously increase. Therefore, let Z.sub.σ0 be a zero matrix, and the maximum norm value under each scale is recorded as:
Z.sub.σn(x) custom character max.sub.x{(Z.sub.σn−1(x),∥H.sub.σn(x)∥)}, n=1, . . . ,N

(28) Then a dynamic threshold c is found, and it may distinguish between the lung region and other tissues according to Zσ≤c and Zσ>c in measurement F.sub.C. The non-lung region is defined as θ.sub.h, the maximum norm is calculated in θ.sub.h and the full space Θ respectively via r.sub.h=∥H.sub.σ.sub.n(x)∥.sub.max/∥H.sub.σ.sub.n(Θ)∥.sub.max, r.sub.h∈(0.65,1) is calculated by experimental statistics, and then the parameter c=r.sub.h.Math.max (Zσ) is obtained. Let R.sub.C=c, and a blood vessel characteristic graph V(x, σ) after contrast enhancement is finally obtained,

(29) $𝒱 (x, σ) \overset{Δ}{=} {\begin{matrix} 0 & if λ_{2} > 0 or λ_{3} > 0 \\ F_{A} .Math. F_{B} .Math. F_{C} & else \end{matrix},$
where λ.sub.2 and λ.sub.3 are the second characteristic value and the third characteristic value of the spatial Hessian matrix respectively.

(30) As shown in FIG. 3, a1-a5 are the axial projection effects of the CTA data, b1-b5 are the axial projection effects after multi-scale filtering, c1-c5 are the axial projection effects after contrast equalization filtering, and d1-d5 are the axial projection effects in the non-lung region θ.sub.h in the present invention. It can be seen from the contrast among d1-d5, b1-b5 and c1-c5 that: b1-b5 clearly show that traditional multi-scale filtering can only enhance the lung blood vessels but cannot enhance the cardiovascular vessels in the heart region, c1-c5 clearly show that the blood vessels in the heart region are significantly enhanced, and d1-d5 clearly show that the blood vessels in the lung region are largely shielded.

Embodiment 3

(31) FIG. 4 shows a structural representation of an apparatus for extracting a cardiovascular vessel from a CTA image provided in Embodiment 3 of the present invention, for the convenience of illustration, only the parts related to the embodiment of the present invention are shown, and the apparatus for extracting a cardiovascular vessel from a CTA image comprises:

(32) A structure mask acquiring unit 41, configured for performing erosion operation and dilation operation on image data successively via a preset structural element to obtain a structure mask. The image data is a coronary angiography image after down-sampling processing, and the structural mask is a structure excluding the lung region.

(33) In an embodiment of the present invention, the above image data is a coronary angiography image after down-sampling processing targeted at large-size original CTA data, in order to quickly extract a large-size ascending aortic structure without affecting the precision of the structure extraction. The image size may be down-sampled to half of the original size; some noise in the above image data and some structures that are not related to the aorta are suppressed or attenuated. Erosion operation is performed on image data firstly, then dilation operation is performed to obtain the structure mask B, and the above structural mask is a structure excluding the lung region.

(34) Further, a structure mask acquiring unit comprises:

(35) a structure mask acquiring subunit used to take a sphere of which the radius is controlled at a preset volume element as the preset structural element. Erosion operation is performed firstly on the image data via a preset structural element, and then dilation operation is performed on image data via a preset structural element to obtain a structure mask which includes: an ascending aorta, partial ventricle and atrium and a descending aorta, of which the partial ventricle and atrium and the descending aorta coexist in a spatial communication area, and the descending aorta is not spatially connected with the ascending aorta and partial ventricle and atrium.

(36) Specifically, a sphere of which the radius is controlled at a preset volume element is selected, and the number of the above preset volume elements is 6±2, the sphere of which the radius is controlled at the preset volume element is used as a preset structural element K.sub.r, erosion operation is performed on the image data I firstly via the preset structural element Kr, and then dilation operation I is performed via the preset structural element Kr to obtain the structure mask I′, and the above calculation formula is expressed as: I′=∘K.sub.r=(⊖K.sub.r)⊕K.sub.r.

(37) A slice-by-slice transformation subunit 42, used to perform a slice-by-slice transformation on plane of section images of the structural mask to acquire the first ascending aortic structure in the structural mask, and an aortic center position and an aortic radius are acquired in the last slice of the plane of section image of the structural mask.

(38) In the embodiment of the present invention, a Hough Transform is performed on the plane of section image of the structural mask, that is, on an axial position plane of the structural mask (i.e., a heart horizontal plane of section), a circular area corresponding to the aorta is selected in each plane of section image, and then, in the circular area segmentation and morphological opening operation are performed to obtain the first ascending aortic structure A.sub.N, and an aortic center position C.sub.oN and an aortic radius R.sub.oN are acquired in the last slice of the plane of section image of the structural mask.

(39) Further, a slice-by-slice transformation comprises:

(40) a slice-by-slice transformation subunit, used in slice-by-slice transformation, where the current plane of section image will be determined as the last slice of plane of section image if the distance between the aorta center positions of the current plane of section image and the preceding plane of section image is greater than a preset deviation value, and the aorta center position and the aortic radius in the last slice of plane of section image will be acquired.

(41) Specifically, during the slice-by-slice transformation, the aortic center positions (n) and the aortic radius (n), n=1, 2, . . . , N, of the current plane of section image are transformed slice by slice. A preset deviation value is set, and the preset deviation value is ε=6±2. When the distance between the aorta center positions of two adjacent slices Dn>ε, the detection would be stopped, and the current plane of section image is determined as the last slice of plane of section image, and the aorta center position C(n) and the aortic radius Ro(n) in the last slice of plane of section image are acquired.

(42) A synthesizing unit 43, configured for establishing a binarized sphere structure according to the aortic center position and the aortic radius, and a second ascending aortic structure is synthesized by combining the first ascending aortic structure with the structural mask and the binarized sphere structure.

(43) In the embodiment of the present invention, at the aortic center position C.sub.oN, a binarized sphere structure Sph.sub.X is established by taking the aortic radius R.sub.oN as the radius, and a second ascending aortic structure A.sub.S is synthesized by combining the first ascending aortic structure A.sub.N with the structural mask B and the binarized sphere structure Sph.sub.X, and the calculation formula is:
A.sub.S=(A.sub.N∪Sph.sub.X)∩B

(44) Where A.sub.S is the second ascending aortic structure, A.sub.N is the first ascending aortic structure, Sph.sub.X is the binarized sphere structure and B is the structural mask, and erosion is performed via a morphological opening operation, so as to obtain the supplementary area of the ascending aorta root, i.e., an aortic sinus area, and the second ascending aortic structure A.sub.S is the complete ascending aortic structure of the aortic sinus.

(45) In the embodiment of the present invention, erosion operation and dilation operation are performed on image data to erode the irrelevant structures of the lungs and retain the heart and aortic structures, the first ascending aortic structure is acquired via the slice-by-slice transformation and combined with a binarized sphere structure to synthesize a second ascending aortic structure, and erosion is performed via a morphological opening operation, so that the supplementary area of the ascending aorta root is obtained, thereby extracting the shapes of ascending aorta and root aortic sinus to accurately visualize the aortic structure and morphology, thus providing an important reference for automatic centerline extraction, segmentation and computer-assisted intelligent intervention to greatly improve the level and ability of medical imaging researches to solve clinical issues.

(46) In the embodiment of the present invention, each unit of the apparatus for extracting a cardiovascular vessel from a CTA image may be implemented by corresponding hardware or software unit; each unit may be an independent software or hardware unit, or may be integrated into one software and hardware unit, and it is not intended to limit the invention here.

Embodiment 4

(47) FIG. 5 shows a structural representation of a device for extracting a cardiovascular vessel from a CTA image provided in Embodiment 4 of the present invention, for the convenience of illustration, only the parts related to the embodiment of the present invention are shown

(48) The device 5 for extracting a cardiovascular vessel from a CTA image according to the embodiment of the present invention comprises a processor 50, a memory 51 and a computer program 52 stored in memory 51 and executable on processor 50. The steps of the method in the above embodiments for extracting a cardiovascular vessel from a CTA image, such as the steps S101 to S103 shown in FIG. 1, are implemented when the computer program 52 is executed by the processor 50. Alternatively, the function of each module/unit in the above apparatus embodiments, such as the functions of modules 41 to 43 shown in FIG. 4, are implemented when the computer program 52 is executed by the processor 50.

(49) In the embodiment of the present invention, erosion operation and dilation operation are performed on image data to erode the irrelevant structures of the lungs and retain the heart and aortic structures, the first ascending aortic structure is acquired via the slice-by-slice transformation and combined with a binarized sphere structure to synthesize a second ascending aortic structure, and erosion is performed via a morphological opening operation, so that the supplementary area of the ascending aorta root is obtained, thereby extracting the shapes of ascending aorta and root aortic sinus to accurately visualize the aortic structure and morphology, thus providing an important reference for automatic centerline extraction, segmentation and computer-assisted intelligent intervention to greatly improve the level and ability of medical imaging researches to solve clinical issues.

Embodiment 5

(50) In the embodiment of the present invention, a computer-readable storage medium storing a computer program is provided, and the steps of the above methods for extracting a cardiovascular vessel from a CTA image, such as the steps S101 to S103 shown in FIG. 1, are implemented when the computer program is executed by the processor. Alternatively, the function of each module/unit in the above apparatus embodiments, such as the functions of modules 41 to 43 shown in FIG. 4, are implemented when the computer program is executed by the processor.

(51) Erosion operation and dilation operation are performed on image data to erode the irrelevant structures of the lungs and retain the heart and aortic structures, the first ascending aortic structure is acquired via the slice-by-slice transformation and combined with a binarized sphere structure to synthesize a second ascending aortic structure, and erosion is performed via a morphological opening operation, so that the supplementary area of the ascending aorta root is obtained, thereby extracting the shapes of ascending aorta and root aortic sinus to accurately visualize the aortic structure and morphology, thus providing an important reference for automatic centerline extraction, segmentation and computer-assisted intelligent intervention to greatly improve the level and ability of medical imaging researches to solve clinical issues.

(52) The computer-readable storage medium according to the embodiment of the present invention may include any entity or device and recording medium capable of carrying a computer program code, for example, a memory such as ROM/RAM, magnetic disk, optical disk, and flash memory.

(53) The above description is only the preferred embodiments of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement and improvement within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Method, apparatus, device and storage medium for extracting a cardiovascular vessel from a CTA image

Assignee

Inventors

Cpc classification

Classification Explorer

G06T2207/30172

PHYSICS

Classification Explorer

G06T2207/20024

PHYSICS

Classification Explorer

G06T7/262

PHYSICS

Classification Explorer

G06T2211/404

PHYSICS

Classification Explorer

G06T7/155

PHYSICS

Classification Explorer

G06T2207/10081

PHYSICS

Classification Explorer

G06T5/30

PHYSICS

Classification Explorer

G06T7/174

PHYSICS

Classification Explorer

G06T7/11

PHYSICS

Classification Explorer

G06T2207/30048

PHYSICS

Classification Explorer

G06T2207/20016

PHYSICS

Classification Explorer

G06T7/0012

PHYSICS

Classification Explorer

G06T2207/30104

PHYSICS

Classification Explorer

G06V10/34

PHYSICS

Classification Explorer

G06T2207/30101

PHYSICS

Classification Explorer

G06V2201/03

PHYSICS

International classification

Classification Explorer

G06T7/11

PHYSICS

Classification Explorer

G06T5/30

PHYSICS

Classification Explorer

G06T7/00

PHYSICS

Classification Explorer

G06T7/262

PHYSICS

Classification Explorer

G06V10/34

PHYSICS

Abstract

Claims

Description