CN108550136B - Blood vessel segmentation method for fundus image - Google Patents

Blood vessel segmentation method for fundus image Download PDF

Info

Publication number
CN108550136B
CN108550136B CN201810207170.5A CN201810207170A CN108550136B CN 108550136 B CN108550136 B CN 108550136B CN 201810207170 A CN201810207170 A CN 201810207170A CN 108550136 B CN108550136 B CN 108550136B
Authority
CN
China
Prior art keywords
org
blood vessel
less
vessel segmentation
image
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
Application number
CN201810207170.5A
Other languages
Chinese (zh)
Other versions
CN108550136A (en
Inventor
邵枫
杨艳
李福翠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Yunshi Information Technology Co ltd
Dragon Totem Technology Hefei Co ltd
Original Assignee
Ningbo University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ningbo University filed Critical Ningbo University
Priority to CN201810207170.5A priority Critical patent/CN108550136B/en
Publication of CN108550136A publication Critical patent/CN108550136A/en
Application granted granted Critical
Publication of CN108550136B publication Critical patent/CN108550136B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • 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
    • G06T2207/30041—Eye; Retina; Ophthalmic
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Quality & Reliability (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Eye Examination Apparatus (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a fundus image blood vessel segmentation method, which obtains a representation dictionary and a segmentation dictionary of a fundus image through dictionary training, thereby establishing a relation model between the fundus image and a blood vessel segmentation image, and can predict and obtain a preliminary blood vessel segmentation image of the fundus image to be subjected to blood vessel segmentation only through simple operation in a test stage, and the method is high in operation speed and low in calculation complexity, so that the method is suitable for practical application occasions; the enhanced image of the fundus image to be subjected to blood vessel segmentation is obtained through morphological operation, and is fused with the binary mask image of the preliminary blood vessel segmentation image of the fundus image to be subjected to blood vessel segmentation to obtain the final blood vessel segmentation image, the obtained final blood vessel segmentation image and the real blood vessel segmentation image keep high consistency, and the segmentation precision is high.

Description

Blood vessel segmentation method for fundus image
Technical Field
The invention relates to an image segmentation method, in particular to a fundus image blood vessel segmentation method.
Background
The fundus images are shot and acquired by a special fundus camera, contain main physiological structures such as retinal blood vessels, optic discs, yellow spots and the like, and are important images in medical images. The retinal blood vessels extend from the optic disc area to the inside of the whole eyeball, are distributed in a tree shape in the whole eyeground image, and are the only places where the blood vessels can be directly observed in a non-invasive way in a human body. Thus, many cardiovascular diseases, such as coronary heart disease, hypertension, arteriosclerosis and diabetic retinopathy, can be diagnosed by analyzing changes in retinal vessel caliber, angle, branch morphology.
However, at present, the vascular structure of the fundus image is mainly obtained by manually drawing marks by experts, and the whole process is time-consuming and labor-consuming. The existing fundus image blood vessel segmentation methods are mainly divided into an unsupervised blood vessel segmentation method and a supervised blood vessel segmentation method, the unsupervised blood vessel segmentation method has the advantages of high operation speed and high efficiency, but has the problem of generally low segmentation precision, and the supervised blood vessel segmentation method usually has high segmentation precision but has the problems of low operation speed, complex parameter optimization and the like. Therefore, how to accurately and quickly extract the fundus image blood vessels to assist in diagnosing various fundus diseases and cardiovascular diseases has very important significance.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a fundus image blood vessel segmentation method which is high in operation speed and high in segmentation precision.
The technical scheme adopted by the invention for solving the technical problems is as follows: a fundus image blood vessel segmentation method is characterized by comprising the following steps:
selecting N fundus images and real blood vessel segmentation images of each fundus image to form a training image set, and recording the training image set as { I }i,org,Mi,orgI is more than or equal to 1 and less than or equal to N }; wherein N is more than or equal to 1, I is more than or equal to 1 and less than or equal to N, Ii,orgRepresents { Ii,org,Mi,orgI < i > 1 < i < N >, (M)i,orgRepresents { Ii,org,Mi,orgI < 1 > I < N } of the ith fundus image, Ii,orgAnd Mi,orgAll width of (A) and all height of (B) are W and H;
step ②, for { Ii,org,Mi,orgI is more than or equal to 1 and less than or equal to N, and each fundus image and each real blood vessel segmentation image are subjected to non-overlapping subblock division processing; then, performing combined dictionary training operation on the set formed by all the sub-blocks in the N fundus images and the set formed by all the sub-blocks in the N real blood vessel segmentation images by adopting a K-SVD (singular value decomposition) method to construct and obtain { I }i,org,Mi,orgThe expression dictionary and the segmentation dictionary with |1 ≦ i ≦ N ≦ are correspondingly recorded as DRAnd DS(ii) a Wherein D isRAnd DSThe dimensions of (A) are all 64 multiplied by K, and K represents the number of the set dictionary atoms;
recording an eyeground image to be subjected to blood vessel segmentation as { I (x, y) }, wherein (x, y) represents the coordinate position of a pixel point in the { I (x, y) }, x is more than or equal to 1 and less than or equal to W ', y is more than or equal to 1 and less than or equal to H', W 'represents the width of the { I (x, y) }, H' represents the height of the { I (x, y) }, and I (x, y) represents the pixel value of the pixel point with the coordinate position of (x, y) in the { I (x, y) };
step ④, divide { I (x, y) }into
Figure BDA0001596185900000021
Sub-blocks with size of 8 × 8 and not overlapped with each other; then, the set of all sub-blocks in { I (x, y) } is recorded as { x }t',testL 1 is less than or equal to t 'is less than or equal to M'; wherein, the symbol
Figure BDA0001596185900000022
In order to round the sign of the operation down,
Figure BDA0001596185900000023
1≤t'≤M'，xt',testrepresents a column vector consisting of pixel values of all pixel points in the t' th sub-block in { I (x, y) }, xt',testFor describing the t' th sub-block, x, in { I (x, y) }t',testHas a dimension of 64 × 1;
step ⑤, obtaining D according to the structureROptimized reconstruction { xt',test1 | < t '< M' } sparse coefficient matrix of each sub-block, will { x ≦ M }t',testThe sparse coefficient matrix of the t ' sub-block in |1 ≦ t ' ≦ M ' } is recorded as at',test，at',testBy solving for min (| | a)t',test||0) Get min (| | a)t',test||0) Satisfies the conditions
Figure BDA0001596185900000024
Wherein, at',testHas dimension of Kx 1, min () is a minimum function, the symbol "| | | | luminance0"is a 0-norm symbol of matrix, symbol" | | | | | | luminance2"is the 2-norm sign of the matrix, T0Is an error coefficient;
step D obtained according to the structureSEstimating a preliminary blood vessel segmentation image of { I (x, y) }, and recording the preliminary blood vessel segmentation image as { Q (x, y) }, and recording a column vector consisting of pixel values of all pixel points in an area with a size of 8 x 8 corresponding to the t' th sub-block in { I (x, y) } in { Q (x, y) }asyt',test，yt',test＝DSat',test(ii) a Then calculate the binary mask image of { Q (x, y) }, which is marked as { Q1(x, y) }; wherein, Q (x, y) represents the pixel value of the pixel point with the coordinate position (x, y) in { Q (x, y) }, yt',testHas dimension of 64X 1, Q1(x, y) represents { Q1The coordinate position in (x, y) is the pixel value of the pixel point of (x, y);
step (c), adopting morphological operation to make enhancement treatment on { I (x, y) } so as to obtain enhanced image of { I (x, y) }, and marking it as { Q (Q) }2(x, y) }; wherein Q is2(x, y) represents { Q2The coordinate position in (x, y) is the pixel value of the pixel point of (x, y);
step ⑧ according to the { Q1(x, y) } and { Q2(x, y) }, calculating a final blood vessel segmentation image of { I (x, y) } and recording the final blood vessel segmentation image as
Figure BDA0001596185900000031
Will be provided with
Figure BDA0001596185900000032
The pixel value of the pixel point with the middle coordinate position (x, y) is recorded as
Figure BDA0001596185900000033
Figure BDA0001596185900000034
wherein the symbol "∪" denotes and operates a symbol.
the concrete process of step ② is as follows:
step 2-1 will { Ii,org,Mi,orgDividing each fundus image and each real blood vessel segmentation image in |1 ≦ i ≦ N }
Figure BDA0001596185900000035
Sub-blocks with size of 8 × 8 and not overlapped with each other; then will { Ii,org,Mi,orgThe set of subblocks in all fundus images |1 ≦ i ≦ N } is denoted as { xtL 1 is less than or equal to t is less than or equal to M, and the { I } isi,org,Mi,orgThe set formed by sub-blocks in all real blood vessel segmentation images in the I1 is less than or equal to the I is less than or equal to the N is recorded as { y ≦ N }tL 1 is not less than t is not less than M; wherein, the symbol
Figure BDA0001596185900000036
In order to round the sign of the operation down,
Figure BDA0001596185900000037
1≤t≤M，xtis represented by { Ii,org,Mi,orgI is not less than 1 and not more than N), and x is a column vector composed of pixel values of all pixel points in the t-th sub-block in all fundus imagestFor describing { Ii,org,Mi,orgI is not less than 1 but not more than NWith the t-th sub-block, x, in the fundus imagetHas a dimension of 64X 1, ytIs represented by { Ii,org,Mi,orgI is not less than 1 and not more than N), and y is a column vector formed by pixel values of all pixel points in the t-th sub-block in all real blood vessel segmentation imagestFor describing { Ii,org,Mi,orgI is not less than 1 and not more than N, y is not less than NtHas a dimension of 64 × 1;
step 2, solving by adopting a K-SVD method
Figure BDA0001596185900000041
Figure BDA0001596185900000042
Satisfies the conditions
Figure BDA0001596185900000044
The structure is obtained as { Ii,org,Mi,orgRepresentation dictionary D with I1 ≦ i ≦ N ≦RAnd a segmentation dictionary DS(ii) a Wherein min () is a minimum function with the symbol "| | | | non-woven phosphor2"is a 2-norm symbol of the matrix, X ═ X1…xt…xM]，Y＝[y1…yt…yM]The term "[ 2 ]]"is a vector representing a symbol, and the dimensions of X and Y are 64 XM, X1Is { xt1 st column vector, x, |1 ≦ t ≦ M }1Also denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N), and x is a column vector composed of pixel values of all pixel points in the 1 st sub-block in all fundus images1For describing { Ii,org,Mi,org1 st subblock, x in all fundus images |1 ≦ i ≦ N }tIs { xtT-th column vector in |1 ≦ t ≦ M |, xMIs { xtM-th column vector, x, in |1 ≦ t ≦ M |MAlso denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N), and x is a column vector composed of pixel values of all pixel points in the Mth sub-block in all fundus imagesMFor describing { Ii,org,Mi,orgMth among all fundus images |1 ≦ i ≦ N }Sub-block, y1Is { yt1 st column vector, y, |1 ≦ t ≦ M }1Also denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N) in all real blood vessel segmentation images, and y is a column vector formed by pixel values of all pixel points in the 1 st sub-block in all real blood vessel segmentation images1For describing { Ii,org,Mi,orgI is not less than 1 and not more than N, y is not less than 1 sub-block in all real blood vessel segmentation imagestIs { ytT-th column vector in |1 ≦ t ≦ M |, yMIs { ytM-th column vector in |1 ≦ t ≦ M ≦ yMAlso denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N), and y is the column vector formed by the pixel values of all pixel points in the Mth sub-block in all real blood vessel segmentation imagesMFor describing { Ii,org,Mi,orgI ≦ N ≦ 1 ≦ M subblock in all real vessel segmentation images, a representing the sparse matrix, a ═ a ≦ N ≦ M subblock in all real vessel segmentation images1…at…aM]Dimension of A is KxM, a1Is the 1 st column vector in A, atIs the t-th column vector in A, aMIs the Mth column vector in A, a1、atAnd aMThe dimension of (a) is Kx 1, the symbol | | | | | non-conducting phosphor0"is the 0-norm sign of the matrix, τ is the error coefficient.
in the step of sixthly, the step of,
Figure BDA0001596185900000043
T1is a binary threshold value.
the specific process of the step ⑦ is as follows:
⑦ _1, adopting morphological operation to perform enhancement processing on the { I (x, y) } to obtain enhancement values of each pixel point in the { I (x, y) } in different scales and different directions, and marking the enhancement values of the pixel points with the coordinate positions (x, y) in the { I (x, y) } in the scales of sigma and the directions of theta as Iθ,σ(x,y)，Iθ,σ(x,y)＝Bθ,σ(x,y)-Tθ,σ(x,y)，
Figure BDA0001596185900000051
Wherein, the symbol
Figure BDA0001596185900000052
Representing morphological dilation operation symbols
Figure BDA0001596185900000053
Representing a morphological erosion operation symbol, Sθ,σRepresenting a linear structuring element with a direction theta and a dimension sigma,
Figure BDA0001596185900000054
Figure BDA0001596185900000055
and (c) step (c 2) of combining enhancement values of each pixel point in the { I (x, y) } in different scales and different directions to obtain an enhancement value of each pixel point in the { I (x, y) }, and recording the enhancement value of the pixel point with the coordinate position (x, y) in the { I (x, y) }asQ'2(x,y)，
Figure BDA0001596185900000056
Then, an enhanced image { Q } of { I (x, y) } is acquired2(x, y) }, will { Q2The pixel value of the pixel point with the coordinate position (x, y) in (x, y) is marked as Q2(x,y)，Q2(x,y)＝Q'2(x, y) wherein the symbol ". sup.u" denotes and operates on a symbol.
Compared with the prior art, the invention has the advantages that:
1) the method obtains the representation dictionary and the segmentation dictionary of the fundus image through dictionary training, thereby establishing a relation model between the fundus image and the blood vessel segmentation image, and the preliminary blood vessel segmentation image of the fundus image to be subjected to blood vessel segmentation can be predicted and obtained only through simple operation in a test stage.
2) The method obtains the enhanced image of the fundus image to be subjected to the blood vessel segmentation through morphological operation, and obtains the final blood vessel segmentation image through fusing the enhanced image with the binary mask image of the preliminary blood vessel segmentation image of the fundus image to be subjected to the blood vessel segmentation, wherein the obtained final blood vessel segmentation image and the real blood vessel segmentation image keep higher consistency and the segmentation precision is high.
Drawings
Fig. 1 is a block diagram of the overall implementation of the method of the present invention.
Detailed Description
The invention is described in further detail below with reference to the accompanying examples.
The general implementation block diagram of the blood vessel segmentation method for the fundus image provided by the invention is shown in fig. 1, and the method comprises the following steps:
selecting N fundus images and real blood vessel segmentation images of each fundus image to form a training image set, and recording the training image set as { I }i,org,Mi,orgI is more than or equal to 1 and less than or equal to N }; where N is equal to or greater than 1, the number of fundus images to be selected in the implementation should be appropriate, and if the value of N is large, the accuracy of the dictionary table obtained through training is higher, but the computational complexity is higher, so in this embodiment, N is equal to 10, I is equal to or greater than 1 and equal to or less than N, and I is equal to or greater than Ii,orgRepresents { Ii,org,Mi,orgI < i > 1 < i < N >, (M)i,orgRepresents { Ii,org,Mi,orgI < 1 > I < N } of the ith fundus image, Ii,orgAnd Mi,orgAre all W wide and are all H high, where the symbol "{ }" is a set representing a symbol.
step ②, for { Ii,org,Mi,orgI is more than or equal to 1 and less than or equal to N, and each fundus image and each real blood vessel segmentation image are subjected to non-overlapping subblock division processing; then, performing combined dictionary training operation on the set formed by all the sub-blocks in the N fundus images and the set formed by all the sub-blocks in the N real blood vessel segmentation images by adopting a K-SVD (singular value decomposition) method to construct and obtain { I }i,org,Mi,orgThe expression dictionary and the segmentation dictionary with |1 ≦ i ≦ N ≦ are correspondingly recorded as DRAnd DS(ii) a Wherein D isRAnd DSThe number of dimensions of (a) is 64 × K, K represents the number of dictionary atoms to be set, and in this embodiment, K is 128.
in this embodiment, the specific process of step ② is:
step 2-1 will { Ii,org,Mi,orgDividing each fundus image and each real blood vessel segmentation image in |1 ≦ i ≦ N }
Figure BDA0001596185900000061
Sub-blocks with size of 8 × 8 and not overlapped with each other; then will { Ii,org,Mi,orgThe set of subblocks in all fundus images |1 ≦ i ≦ N } is denoted as { xtL 1 is less than or equal to t is less than or equal to M, and the { I } isi,org,Mi,orgThe set formed by sub-blocks in all real blood vessel segmentation images in the I1 is less than or equal to the I is less than or equal to the N is recorded as { y ≦ N }tL 1 is not less than t is not less than M; wherein, the symbol
Figure BDA0001596185900000062
In order to round the sign of the operation down,
Figure BDA0001596185900000071
1≤t≤M，xtis represented by { Ii,org,Mi,orgI is not less than 1 and not more than N), and x is a column vector composed of pixel values of all pixel points in the t-th sub-block in all fundus imagestFor describing { Ii,org,Mi,orgI is not less than 1 and not more than N, xtHas a dimension of 64X 1, ytIs represented by { Ii,org,Mi,orgI is not less than 1 and not more than N), and y is a column vector formed by pixel values of all pixel points in the t-th sub-block in all real blood vessel segmentation imagestFor describing { Ii,org,Mi,orgI is not less than 1 and not more than N, y is not less than NtHas dimension of 64 x 1.
step 2, solving by adopting a K-SVD method
Figure BDA0001596185900000072
Figure BDA0001596185900000073
Satisfies the conditions
Figure BDA0001596185900000074
The structure is obtained as { Ii,org,Mi,orgRepresentation dictionary D with I1 ≦ i ≦ N ≦RAnd a segmentation dictionary DS(ii) a Wherein min () is a minimum function with the symbol "| | | | non-woven phosphor2"is a 2-norm symbol of the matrix, X ═ X1…xt…xM]，Y＝[y1…yt…yM]The term "[ 2 ]]"is a vector representing a symbol, and the dimensions of X and Y are 64 XM, X1Is { xt1 st column vector, x, |1 ≦ t ≦ M }1Also denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N), and x is a column vector composed of pixel values of all pixel points in the 1 st sub-block in all fundus images1For describing { Ii,org,Mi,org1 st subblock, x in all fundus images |1 ≦ i ≦ N }tIs { xtT-th column vector in |1 ≦ t ≦ M |, xMIs { xtM-th column vector, x, in |1 ≦ t ≦ M |MAlso denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N), and x is a column vector composed of pixel values of all pixel points in the Mth sub-block in all fundus imagesMFor describing { Ii,org,Mi,orgI is not less than 1 and not more than N } sub-block M in all fundus images, y1Is { yt1 st column vector, y, |1 ≦ t ≦ M }1Also denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N) in all real blood vessel segmentation images, and y is a column vector formed by pixel values of all pixel points in the 1 st sub-block in all real blood vessel segmentation images1For describing { Ii,org,Mi,orgI is not less than 1 and not more than N, y is not less than 1 sub-block in all real blood vessel segmentation imagestIs { ytT-th column vector in |1 ≦ t ≦ M |, yMIs { ytM-th column vector in |1 ≦ t ≦ M ≦ yMAlso denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N), and y is the column vector formed by the pixel values of all pixel points in the Mth sub-block in all real blood vessel segmentation imagesMFor describing { Ii,org,Mi,orgI is not less than 1 and not more than N, the Mth sub-block in all the real blood vessel segmentation images,a represents a sparse matrix, and A ═ a1…at…aM]Dimension of A is KxM, a1Is the 1 st column vector in A, atIs the t-th column vector in A, aMIs the Mth column vector in A, a1、atAnd aMThe dimension of (a) is Kx 1, the symbol | | | | | non-conducting phosphor0"is a sign of 0-norm of the matrix, τ is an error coefficient, and τ is 10 in this embodiment.
recording an eyeground image to be subjected to blood vessel segmentation as { I (x, y) }, wherein (x, y) represents the coordinate position of a pixel point in the { I (x, y) }, x is more than or equal to 1 and less than or equal to W ', y is more than or equal to 1 and less than or equal to H', W 'represents the width of the { I (x, y) }, H' represents the height of the { I (x, y) }, the value of W 'and the value of W can be the same or different, the value of H' and the value of H can be the same or different, and I (x, y) represents the pixel value of the pixel point of which the coordinate position is (x, y) in the { I (x, y) }.
step ④, divide { I (x, y) }into
Figure BDA0001596185900000081
Sub-blocks with size of 8 × 8 and not overlapped with each other; then, the set of all sub-blocks in { I (x, y) } is recorded as { x }t',testL 1 is less than or equal to t 'is less than or equal to M'; wherein, the symbol
Figure BDA0001596185900000082
In order to round the sign of the operation down,
Figure BDA0001596185900000083
1≤t'≤M'，xt',testrepresents a column vector consisting of pixel values of all pixel points in the t' th sub-block in { I (x, y) }, xt',testFor describing the t' th sub-block, x, in { I (x, y) }t',testHas dimension of 64 x 1.
step ⑤, obtaining D according to the structureROptimized reconstruction { xt',test1 | < t '< M' } sparse coefficient matrix of each sub-block, will { x ≦ M }t',testThe sparse coefficient matrix of the t ' sub-block in |1 ≦ t ' ≦ M ' } is recorded as at',test，at',testBy solving for min (| | a)t',test||0) Get min (| | a)t',test||0) Satisfies the conditions
Figure BDA0001596185900000084
Wherein, at',testHas dimension of Kx 1, min () is a minimum function, the symbol "| | | | luminance0"is a 0-norm symbol of matrix, symbol" | | | | | | luminance2"is the 2-norm sign of the matrix, T0For error coefficient, take T in this example0＝6。
step D obtained according to the structureSEstimating a preliminary blood vessel segmentation image of { I (x, y) }, and recording the preliminary blood vessel segmentation image as { Q (x, y) }, and recording a column vector consisting of pixel values of all pixel points in an area with a size of 8 x 8 corresponding to the t' th sub-block in { I (x, y) } in { Q (x, y) }asyt',test，yt',test＝DSat',test(ii) a Then calculate the binary mask image of { Q (x, y) }, which is marked as { Q1(x, y) }; wherein, Q (x, y) represents the pixel value of the pixel point with the coordinate position (x, y) in { Q (x, y) }, yt',testHas dimension of 64X 1, Q1(x, y) represents { Q1And the coordinate position in the (x, y) is the pixel value of the pixel point of (x, y).
in the specific example, in the step (sixty),
Figure BDA0001596185900000091
T1for binarization of threshold, take T in this example1＝25。
step (c), adopting morphological operation to make enhancement treatment on { I (x, y) } so as to obtain enhanced image of { I (x, y) }, and marking it as { Q (Q) }2(x, y) }; wherein Q is2(x, y) represents { Q2And the coordinate position in the (x, y) is the pixel value of the pixel point of (x, y).
in this embodiment, the specific process of step (c) is as follows:
⑦ _1, adopting morphological operation to perform enhancement processing on the { I (x, y) } to obtain enhancement values of each pixel point in the { I (x, y) } in different scales and different directions, and marking the enhancement values of the pixel points with the coordinate positions (x, y) in the { I (x, y) } in the scales of sigma and the directions of theta as Iθ,σ(x,y)，Iθ,σ(x,y)＝Bθ,σ(x,y)-Tθ,σ(x,y)，
Figure BDA0001596185900000092
Wherein, the symbol
Figure BDA0001596185900000093
Representing morphological dilation operation symbols
Figure BDA0001596185900000094
Representing a morphological erosion operation symbol, Sθ,σRepresenting a linear structuring element with a direction theta and a dimension sigma,
Figure BDA0001596185900000095
Figure BDA0001596185900000096
and (c) step (c 2) of combining enhancement values of each pixel point in the { I (x, y) } in different scales and different directions to obtain an enhancement value of each pixel point in the { I (x, y) }, and recording the enhancement value of the pixel point with the coordinate position (x, y) in the { I (x, y) }asQ'2(x,y)，
Figure BDA0001596185900000097
Then, an enhanced image { Q } of { I (x, y) } is acquired2(x, y) }, will { Q2The pixel value of the pixel point with the coordinate position (x, y) in (x, y) is marked as Q2(x,y)，Q2(x,y)＝Q'2(x, y) wherein the symbol ". sup.u" denotes and operates on a symbol.
step ⑧ according to the { Q1(x, y) } and { Q2(x, y) }, calculating a final blood vessel segmentation image of { I (x, y) } and recording the final blood vessel segmentation image as
Figure BDA0001596185900000101
Will be provided with
Figure BDA0001596185900000102
The pixel value of the pixel point with the middle coordinate position (x, y) is recorded as
Figure BDA0001596185900000103
Figure BDA0001596185900000104
wherein the symbol "∪" denotes and operates a symbol.
To further illustrate the feasibility and effectiveness of the method of the present invention, the method of the present invention was tested.
In this embodiment, the method of the present invention is adopted to test three fundus image databases, namely, DRIVE, STARE, and HRF, where the DRIVE fundus image database includes 40 color fundus images and corresponding expert hand-painted blood vessel label images, the STARE fundus image database includes 20 color fundus images and corresponding expert hand-painted blood vessel label images, and the HRF fundus image database includes 45 color fundus images and corresponding expert hand-painted blood vessel label images. 3 common indexes for evaluating the classification quality, namely Sensitivity, Specificity and Accuracy (Accuracy), are utilized, and if the Sensitivity, Specificity and Accuracy are closer to 100%, the better the correlation between the blood vessel segmentation result of the method and the real blood vessel segmentation result is. Table 1 shows the correlation between the blood vessel segmentation result obtained by the method of the present invention and the real blood vessel segmentation result, and it can be seen from table 1 that the correlation between the blood vessel segmentation result of the fundus image obtained by the method of the present invention and the real blood vessel segmentation result is high enough to illustrate the effectiveness of the method of the present invention.
TABLE 1 correlation between vessel segmentation results obtained using the method of the present invention and real vessel segmentation results
Index (I) DRIVE eyeBase image database STARE fundus image database HRF fundus image database
Sensitivity of the reaction 0.710 0.679 0.712
Specificity of 0.982 0.972 0.974
Accuracy of 0.958 0.951 0.954

Claims (3)

1. A fundus image blood vessel segmentation method is characterized by comprising the following steps:
selecting N fundus images and real blood vessel segmentation images of each fundus image to form a training image set, and recording the training image set as { I }i,org,Mi,orgI is more than or equal to 1 and less than or equal to N }; wherein N is more than or equal to 1, I is more than or equal to 1 and less than or equal to N, Ii,orgRepresents { Ii,org,Mi,orgI < i > 1 < i < N >, (M)i,orgRepresents { Ii,org,Mi,orgI < 1 > I < N } of the ith fundus image, Ii,orgAnd Mi,orgAll width of (A) and all height of (B) are W and H;
step ②, for { Ii,org,Mi,orgI is more than or equal to 1 and less than or equal to N, and each fundus image and each real blood vessel segmentation image are subjected to non-overlapping subblock division processing; then all sub-blocks in the N fundus images are processed by adopting a K-SVD methodPerforming joint dictionary training operation on the formed set and the set formed by all the sub-blocks in the N real blood vessel segmentation images to obtain { I }i,org,Mi,orgThe expression dictionary and the segmentation dictionary with |1 ≦ i ≦ N ≦ are correspondingly recorded as DRAnd DS(ii) a Wherein D isRAnd DSThe dimensions of (A) are all 64 multiplied by K, and K represents the number of the set dictionary atoms;
recording an eyeground image to be subjected to blood vessel segmentation as { I (x, y) }, wherein (x, y) represents the coordinate position of a pixel point in the { I (x, y) }, x is more than or equal to 1 and less than or equal to W ', y is more than or equal to 1 and less than or equal to H', W 'represents the width of the { I (x, y) }, H' represents the height of the { I (x, y) }, and I (x, y) represents the pixel value of the pixel point with the coordinate position of (x, y) in the { I (x, y) };
step ④, divide { I (x, y) }into
Figure FDA0002330574350000011
Sub-blocks with size of 8 × 8 and not overlapped with each other; then, the set of all sub-blocks in { I (x, y) } is recorded as { x }t',testL 1 is less than or equal to t 'is less than or equal to M'; wherein, the symbol
Figure FDA0002330574350000012
In order to round the sign of the operation down,
Figure FDA0002330574350000013
1≤t'≤M'，xt',testrepresents a column vector consisting of pixel values of all pixel points in the t' th sub-block in { I (x, y) }, xt',testFor describing the t' th sub-block, x, in { I (x, y) }t',testHas a dimension of 64 × 1;
step ⑤, obtaining D according to the structureROptimized reconstruction { xt',test1 | < t '< M' } sparse coefficient matrix of each sub-block, will { x ≦ M }t',testThe sparse coefficient matrix of the t ' sub-block in |1 ≦ t ' ≦ M ' } is recorded as at',test，at',testBy solving for min (| | a)t',test||0) Get min (| | a)t',test||0) Satisfies the conditions
Figure FDA0002330574350000029
Wherein, at',testHas dimension of Kx 1, min () is a minimum function, the symbol "| | | | luminance0"is a 0-norm symbol of matrix, symbol" | | | | | | luminance2"is the 2-norm sign of the matrix, T0Is an error coefficient;
step D obtained according to the structureSEstimating a preliminary blood vessel segmentation image of { I (x, y) }, and recording the preliminary blood vessel segmentation image as { Q (x, y) }, and recording a column vector consisting of pixel values of all pixel points in an area with a size of 8 x 8 corresponding to the t' th sub-block in { I (x, y) } in { Q (x, y) }asyt',test，yt',test＝DSat',test(ii) a Then calculate the binary mask image of { Q (x, y) }, which is marked as { Q1(x, y) }; wherein, Q (x, y) represents the pixel value of the pixel point with the coordinate position (x, y) in { Q (x, y) }, yt',testHas dimension of 64X 1, Q1(x, y) represents { Q1The coordinate position in (x, y) is the pixel value of the pixel point of (x, y);
step (c), adopting morphological operation to make enhancement treatment on { I (x, y) } so as to obtain enhanced image of { I (x, y) }, and marking it as { Q (Q) }2(x, y) }; wherein Q is2(x, y) represents { Q2The coordinate position in (x, y) is the pixel value of the pixel point of (x, y);
the specific process of the step ⑦ is as follows:
⑦ _1, adopting morphological operation to perform enhancement processing on the { I (x, y) } to obtain enhancement values of each pixel point in the { I (x, y) } in different scales and different directions, and marking the enhancement values of the pixel points with the coordinate positions (x, y) in the { I (x, y) } in the scales of sigma and the directions of theta as Iθ,σ(x,y)，Iθ,σ(x,y)＝Bθ,σ(x,y)-Tθ,σ(x,y)，
Figure FDA0002330574350000021
Wherein, the symbol
Figure FDA0002330574350000022
Representing morphological dilation operation symbols
Figure FDA0002330574350000023
Representing a morphological erosion operation symbol, Sθ,σRepresenting a linear structuring element with a direction theta and a dimension sigma,
Figure FDA0002330574350000024
Figure FDA0002330574350000025
Figure FDA0002330574350000026
Figure FDA0002330574350000027
and (c) step (c 2) of combining enhancement values of each pixel point in the { I (x, y) } in different scales and different directions to obtain an enhancement value of each pixel point in the { I (x, y) }, and recording the enhancement value of the pixel point with the coordinate position (x, y) in the { I (x, y) }asQ'2(x,y)，
Figure FDA0002330574350000028
Then, an enhanced image { Q } of { I (x, y) } is acquired2(x, y) }, will { Q2The pixel value of the pixel point with the coordinate position (x, y) in (x, y) is marked as Q2(x,y)，Q2(x,y)＝Q'2(x, y), wherein the symbol "[ U ] denotes and operates a symbol;
step ⑧ according to the { Q1(x, y) } and { Q2(x, y) }, calculating a final blood vessel segmentation image of { I (x, y) } and recording the final blood vessel segmentation image as
Figure FDA0002330574350000031
Will be provided with
Figure FDA0002330574350000032
The pixel value of the pixel point with the middle coordinate position (x, y) is recorded as
Figure FDA0002330574350000033
Figure FDA0002330574350000034
wherein the symbol "∪" denotes and operates a symbol.
2. the method for segmenting blood vessels of fundus images according to claim 1, wherein the specific process of the step (II) is as follows:
step 2-1 will { Ii,org,Mi,orgDividing each fundus image and each real blood vessel segmentation image in |1 ≦ i ≦ N }
Figure FDA0002330574350000035
Sub-blocks with size of 8 × 8 and not overlapped with each other; then will { Ii,org,Mi,orgThe set of subblocks in all fundus images |1 ≦ i ≦ N } is denoted as { xtL 1 is less than or equal to t is less than or equal to M, and the { I } isi,org,Mi,orgThe set formed by sub-blocks in all real blood vessel segmentation images in the I1 is less than or equal to the I is less than or equal to the N is recorded as { y ≦ N }tL 1 is not less than t is not less than M; wherein, the symbol
Figure FDA0002330574350000036
In order to round the sign of the operation down,
Figure FDA0002330574350000037
1≤t≤M，xtis represented by { Ii,org,Mi,orgI is not less than 1 and not more than N), and x is a column vector composed of pixel values of all pixel points in the t-th sub-block in all fundus imagestFor describing { Ii,org,Mi,orgI is not less than 1 and not more than N, xtHas a dimension of 64X 1, ytIs represented by { Ii,org,Mi,orgI is not less than 1 and not more than N), and y is a column vector formed by pixel values of all pixel points in the t-th sub-block in all real blood vessel segmentation imagestFor describing { Ii,org,Mi,orgAll real blood vessel segmentation images in I1 ≦ i ≦ N ≦T-th sub-block of (1), ytHas a dimension of 64 × 1;
step 2, solving by adopting a K-SVD method
Figure FDA0002330574350000038
Figure FDA0002330574350000039
Satisfies the conditions
Figure FDA00023305743500000310
||at||0τ or less, the structure is given as { Ii,org,Mi,orgRepresentation dictionary D with I1 ≦ i ≦ N ≦RAnd a segmentation dictionary DS(ii) a Wherein min () is a minimum function with the symbol "| | | | non-woven phosphor2"is a 2-norm symbol of the matrix, X ═ X1…xt…xM]，Y＝[y1…yt…yM]The term "[ 2 ]]"is a vector representing a symbol, and the dimensions of X and Y are 64 XM, X1Is { xt1 st column vector, x, |1 ≦ t ≦ M }1Also denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N), and x is a column vector composed of pixel values of all pixel points in the 1 st sub-block in all fundus images1For describing { Ii,org,Mi,org1 st subblock, x in all fundus images |1 ≦ i ≦ N }tIs { xtT-th column vector in |1 ≦ t ≦ M |, xMIs { xtM-th column vector, x, in |1 ≦ t ≦ M |MAlso denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N), and x is a column vector composed of pixel values of all pixel points in the Mth sub-block in all fundus imagesMFor describing { Ii,org,Mi,orgI is not less than 1 and not more than N } sub-block M in all fundus images, y1Is { yt1 st column vector, y, |1 ≦ t ≦ M }1Also denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N) in all real blood vessel segmentation images, and y is a column vector formed by pixel values of all pixel points in the 1 st sub-block in all real blood vessel segmentation images1For describing aIi,org,Mi,orgI is not less than 1 and not more than N, y is not less than 1 sub-block in all real blood vessel segmentation imagestIs { ytT-th column vector in |1 ≦ t ≦ M |, yMIs { ytM-th column vector in |1 ≦ t ≦ M ≦ yMAlso denoted by { Ii,org,Mi,orgI is not less than 1 and not more than N), and y is the column vector formed by the pixel values of all pixel points in the Mth sub-block in all real blood vessel segmentation imagesMFor describing { Ii,org,Mi,orgI ≦ N ≦ 1 ≦ M subblock in all real vessel segmentation images, a representing the sparse matrix, a ═ a ≦ N ≦ M subblock in all real vessel segmentation images1…at…aM]Dimension of A is KxM, a1Is the 1 st column vector in A, atIs the t-th column vector in A, aMIs the Mth column vector in A, a1、atAnd aMThe dimension of (a) is Kx 1, the symbol | | | | | non-conducting phosphor0"is the 0-norm sign of the matrix, τ is the error coefficient.
3. the fundus image blood vessel segmentation method according to claim 1, wherein in the step (c),
Figure FDA0002330574350000041
T1is a binary threshold value.
CN201810207170.5A 2018-03-14 2018-03-14 Blood vessel segmentation method for fundus image Active CN108550136B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810207170.5A CN108550136B (en) 2018-03-14 2018-03-14 Blood vessel segmentation method for fundus image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810207170.5A CN108550136B (en) 2018-03-14 2018-03-14 Blood vessel segmentation method for fundus image

Publications (2)

Publication Number Publication Date
CN108550136A CN108550136A (en) 2018-09-18
CN108550136B true CN108550136B (en) 2020-06-02

Family

ID=63515929

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810207170.5A Active CN108550136B (en) 2018-03-14 2018-03-14 Blood vessel segmentation method for fundus image

Country Status (1)

Country Link
CN (1) CN108550136B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115409762B (en) * 2021-05-28 2023-11-24 南京博视医疗科技有限公司 Method and device for automatically detecting overlapping of planning point and blood vessel

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9092849B2 (en) * 2013-06-28 2015-07-28 International Business Machines Corporation Bidirectional blood vessel segmentation
CN104392463B (en) * 2014-12-16 2017-02-22 西安电子科技大学 Image salient region detection method based on joint sparse multi-scale fusion
CN104637056B (en) * 2015-02-02 2018-02-23 复旦大学 Medicine CT image adrenal tumor dividing method based on rarefaction representation
CN105472393B (en) * 2015-11-24 2018-04-17 宁波大学 A kind of colour and depth image post-processing approach based on joint dictionary
CN107369160B (en) * 2017-06-28 2020-04-03 苏州比格威医疗科技有限公司 Choroid neogenesis blood vessel segmentation algorithm in OCT image
CN107464246A (en) * 2017-07-14 2017-12-12 浙江大学 A kind of image partition method based on collection of illustrative plates dictionary learning
CN107657612A (en) * 2017-10-16 2018-02-02 西安交通大学 Suitable for full-automatic the retinal vessel analysis method and system of intelligent and portable equipment

Also Published As

Publication number Publication date
CN108550136A (en) 2018-09-18

Similar Documents

Publication Publication Date Title
CN109859215B (en) Automatic white matter high signal segmentation system and method based on Unet model
CN110934606B (en) Cerebral apoplexy early-stage flat-scan CT image evaluation system and method and readable storage medium
CN111772619B (en) Heart beat identification method based on deep learning, terminal equipment and storage medium
CN110619322A (en) Multi-lead electrocardio abnormal signal identification method and system based on multi-flow convolution cyclic neural network
CN111242933B (en) Retinal image artery and vein classification device, apparatus, and storage medium
CN110310280B (en) Image recognition method, system, equipment and storage medium for hepatobiliary duct and calculus
CN110934608B (en) Cerebral apoplexy early-stage CTA image evaluation system and method and readable storage medium
Diniz et al. Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network
CN112906748A (en) 12-lead ECG arrhythmia detection classification model construction method based on residual error network
CN108305241B (en) SD-OCT image GA lesion segmentation method based on depth voting model
CN112446891A (en) Medical image segmentation method based on U-Net network brain glioma
CN113012163A (en) Retina blood vessel segmentation method, equipment and storage medium based on multi-scale attention network
Guo et al. EMFN: enhanced multi-feature fusion network for hard exudate detection in fundus images
Wahid et al. A novel fuzzy-based thresholding approach for blood vessel segmentation from fundus image
CN112288749A (en) Skull image segmentation method based on depth iterative fusion depth learning model
CN115281688A (en) Cardiac hypertrophy multi-label detection system based on multi-mode deep learning
CN115294075A (en) OCTA image retinal vessel segmentation method based on attention mechanism
CN110992309B (en) Fundus image segmentation method based on deep information transfer network
CN113662664A (en) Instrument tracking-based objective and automatic evaluation method for surgical operation quality
CN112741651A (en) Method and system for processing ultrasonic image of endoscope
CN108550136B (en) Blood vessel segmentation method for fundus image
Asyhar et al. Implementation LSTM Algorithm for Cervical Cancer using Colposcopy Data
CN114492519A (en) Lung ultrasonic special sign B-line identification and classification method based on ultrasonic echo radio frequency signals
CN114332910A (en) Human body part segmentation method for similar feature calculation of far infrared image
CN111815650B (en) Brain magnetic resonance image segmentation method based on improved fuzzy C-means

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20180918

Assignee: Zhejiang Yangji Health Industry Co.,Ltd.

Assignor: Ningbo University

Contract record no.: X2022980025290

Denomination of invention: A method for segmentation of blood vessels in fundus images

Granted publication date: 20200602

License type: Common License

Record date: 20221209

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20231109

Address after: 608, 5th floor, No. 17 Madian East Road, Haidian District, Beijing, 100000

Patentee after: Beijing Yunshi Information Technology Co.,Ltd.

Address before: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province

Patentee before: Dragon totem Technology (Hefei) Co.,Ltd.

Effective date of registration: 20231109

Address after: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province

Patentee after: Dragon totem Technology (Hefei) Co.,Ltd.

Address before: 315211, Fenghua Road, Jiangbei District, Zhejiang, Ningbo 818

Patentee before: Ningbo University