CN108230387B - Fiber interval characteristic quantification method and device - Google Patents
Fiber interval characteristic quantification method and device Download PDFInfo
- Publication number
- CN108230387B CN108230387B CN201711476772.2A CN201711476772A CN108230387B CN 108230387 B CN108230387 B CN 108230387B CN 201711476772 A CN201711476772 A CN 201711476772A CN 108230387 B CN108230387 B CN 108230387B
- Authority
- CN
- China
- Prior art keywords
- fiber
- fiber interval
- interval
- image
- skeleton
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000000835 fiber Substances 0.000 title claims abstract description 350
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000011002 quantification Methods 0.000 title claims description 8
- 102000008186 Collagen Human genes 0.000 claims abstract description 91
- 108010035532 Collagen Proteins 0.000 claims abstract description 91
- 229920001436 collagen Polymers 0.000 claims abstract description 91
- 230000003176 fibrotic effect Effects 0.000 claims abstract description 18
- 102000004169 proteins and genes Human genes 0.000 claims description 59
- 108090000623 proteins and genes Proteins 0.000 claims description 59
- 206010016654 Fibrosis Diseases 0.000 claims description 35
- 230000004761 fibrosis Effects 0.000 claims description 35
- 238000012545 processing Methods 0.000 claims description 19
- 230000009466 transformation Effects 0.000 claims description 16
- 239000008280 blood Substances 0.000 claims description 12
- 210000004369 blood Anatomy 0.000 claims description 12
- 238000009499 grossing Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012512 characterization method Methods 0.000 claims 1
- 210000001519 tissue Anatomy 0.000 description 58
- 210000000056 organ Anatomy 0.000 description 5
- 101000834948 Homo sapiens Tomoregulin-2 Proteins 0.000 description 3
- 102100026160 Tomoregulin-2 Human genes 0.000 description 3
- 208000019425 cirrhosis of liver Diseases 0.000 description 3
- 230000017074 necrotic cell death Effects 0.000 description 3
- 210000004738 parenchymal cell Anatomy 0.000 description 3
- 102000010834 Extracellular Matrix Proteins Human genes 0.000 description 2
- 108010037362 Extracellular Matrix Proteins Proteins 0.000 description 2
- 238000004132 cross linking Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 210000002744 extracellular matrix Anatomy 0.000 description 2
- 210000004185 liver Anatomy 0.000 description 2
- 210000005228 liver tissue Anatomy 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 206010008909 Chronic Hepatitis Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 208000037273 Pathologic Processes Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000002440 hepatic effect Effects 0.000 description 1
- 230000010224 hepatic metabolism Effects 0.000 description 1
- 208000006454 hepatitis Diseases 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 201000007270 liver cancer Diseases 0.000 description 1
- 208000014018 liver neoplasm Diseases 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000009054 pathological process Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—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
- G06T2207/30056—Liver; Hepatic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Investigating Or Analysing Biological Materials (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a method and a device for quantifying fiber interval characteristics, which are used for acquiring a fiber interval binary image of a tissue sample, wherein the fiber interval binary image is used for representing the position distribution of fiber intervals in the tissue sample; identifying each connected domain in the fiber interval binary image, and generating a characteristic binary image of each fiber interval; and obtaining a characteristic value of each fiber interval according to the characteristic binary image of the fiber interval, wherein the characteristics of the fiber interval comprise one or more of area, length and width. In the embodiments of the present invention, there are provided not only a method for obtaining a characteristic value of a fibrous interval but also a method for obtaining a characteristic value of a collagen bundle in a fibrous interval, and further, a method for obtaining a characteristic value of a non-fibrotic region in a fibrous interval. Therefore, the characteristics of the fiber intervals are quantized, and a more intuitive data basis is provided for the doctor seeing.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to a method and a device for quantifying fiber interval characteristics.
Background
Fibrosis of a biological tissue refers to a pathological process in which necrosis of parenchymal cells of a biological organ occurs due to inflammation, and Extracellular Matrix (ECM) is abnormally increased and excessively accumulated in the biological tissue. Fibrosis of biological tissue causes structural destruction of tissue in a biological organ, resulting in a decrease in function of the biological organ, and finally hardening of the biological organ.
Fibrosis of biological tissues may occur in various biological organs, for example, liver, chronic hepatitis may cause necrosis of parenchymal cells in liver tissues, and fibrosis degree of liver tissues is increased along with necrosis of parenchymal cells, so that liver metabolism is abnormal, and finally liver cirrhosis and even liver cancer are caused.
As the degree of liver fibrosis increases, there is a fibrous separation between the hepatic Tract regions (PT) and between PT and the Central venous region (CV). After determining the fiber interval in the tissue sample, how to quantify the characteristics of the fiber interval is a problem to be solved urgently at present.
Disclosure of Invention
The invention aims to provide a method and a device for quantifying fiber interval characteristics, thereby providing a method for quantifying the fiber interval characteristics and providing a more intuitive data basis for medical treatment.
Therefore, the technical scheme for solving the technical problem is as follows:
a method of fiber spacing feature quantification, the method comprising:
acquiring a fiber interval binary image of a tissue sample, wherein the fiber interval binary image is used for representing the position distribution of fiber intervals in the tissue sample;
identifying each connected domain in the fiber interval binary image, and generating a characteristic binary image of each fiber interval;
and obtaining a characteristic value of each fiber interval according to the characteristic binary image of the fiber interval, wherein the characteristics of the fiber interval comprise one or more of area, length and width.
Optionally, the obtaining the length of the fiber interval according to one binary image of the fiber interval feature includes:
determining a skeleton of the fiber interval according to the characteristic binary image of the fiber interval;
and acquiring the length of the framework between the end points of the two edges with the farthest distance on the framework with the fiber interval as the length of the fiber interval.
Optionally, the obtaining, as the length of the fiber interval, the length of the skeleton between two edge endpoints that are farthest from each other on the skeleton of the fiber interval includes:
searching two edge endpoints which are farthest away on the framework with the fiber interval;
segmenting according to the cross points on the fiber-spaced framework to obtain framework branches;
when the number of the skeleton branches is not more than 2, determining the length of the fiber interval as the length of the skeleton of the fiber interval;
and when the number of the skeleton branches is more than 2, deleting the skeleton branches on the trunk line of the skeleton not belonging to the fiber interval, and determining the length of the fiber interval as the length of the trunk line of the skeleton of the fiber interval.
Optionally, identifying whether one of the skeleton branches belongs to a trunk line of the fiber-spaced skeleton comprises:
deleting the backbone branches from the fiber-spaced backbone;
when two skeleton sections are obtained and each skeleton section respectively comprises one edge endpoint, the skeleton branches belong to the trunk lines of the fiber-spaced skeletons;
when a carcass section is obtained and comprises two of said edge end points, said carcass branch does not belong to the backbone of said fibre-spaced carcass.
Optionally, the obtaining the width of the fiber space according to one binary image of the fiber space characteristic includes:
processing the characteristic binary image of the fiber interval by adopting a distance transformation algorithm to obtain the half-width length of each pixel point on the skeleton of the fiber interval;
and determining the width of the fiber interval according to the half-width length of each pixel point on the framework of the fiber interval.
Optionally, the method further includes:
acquiring a collagen binary image and an image of the tissue sample, wherein the collagen binary image is used for representing the position distribution of collagen in the tissue sample, and the image of the tissue sample is an image obtained by acquiring a second harmonic signal of the tissue sample;
performing AND operation on the characteristic binary image of each fiber interval and the collagen image to obtain a first protein image of each fiber interval;
extracting pixel points with pixel values larger than a preset pixel threshold value in the image of the tissue sample from the first protein image of each fiber interval to obtain a second protein image of each fiber interval;
determining collagen bundles in each of the fibrous intervals from the second protein image of each of the fibrous intervals.
Optionally, said determining collagen bundles in the fibrous space based on a second protein image of the fibrous space comprises:
denoising and smoothing the second protein image of the fiber interval;
obtaining a skeleton of collagen in the fibrous interval from the processed second protein image of the fibrous interval by adopting a distance transformation algorithm;
and deleting the cross points in the collagen skeletons in the fibrous intervals according to the collagen skeletons in the fibrous intervals to obtain collagen bundles in the fibrous intervals.
Optionally, the method further includes:
determining a characteristic value of each collagen bundle in the fibrous interval, the characteristic value of the collagen bundle including one or more of a length and a width.
Optionally, the method further includes:
deleting the first protein image and the blood vessel-like image of each fiber interval from the characteristic binary image of each fiber interval to obtain a non-fibrosis binary image of each fiber interval, wherein the blood vessel-like image of each fiber interval is used for representing the position distribution of blood vessel-like structures in the fiber intervals;
obtaining a characteristic value of a non-fibrotic region in each of the fibrous intervals from the non-fibrotic binary image of the fibrous interval, the characteristic of the non-fibrotic region including one or more of an area, a length, and a width.
An apparatus for fiber space characteristic quantification, the apparatus comprising:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a fiber interval binary image of a tissue sample, and the fiber interval binary image is used for representing the position distribution of a fiber interval in the tissue sample;
the identification module is used for identifying each connected domain in the fiber interval binary image and generating a characteristic binary image of each fiber interval;
and the second acquisition module is used for acquiring a characteristic value of each fiber interval according to the characteristic binary image of the fiber interval, wherein the characteristic of the fiber interval comprises one or more of area, length and width.
Optionally, the second obtaining module includes:
the first determining unit is used for determining the skeleton of the fiber interval according to the characteristic binary image of the fiber interval;
and the first acquisition unit is used for acquiring the length of the framework between the end points of the two edges which are farthest away on the framework with the fiber interval as the length of the fiber interval.
Optionally, the obtaining unit includes:
the searching subunit is used for searching two edge endpoints which are farthest away on the framework with the fiber interval;
the dividing subunit is used for dividing according to the intersection points on the fiber interval framework to obtain framework branches;
the determining subunit is used for determining the length of the fiber interval as the length of the skeleton of the fiber interval when the number of the skeleton branches is not more than 2;
and the deleting subunit is used for deleting the skeleton branches on the trunk line of the skeleton not belonging to the fiber interval when the number of the skeleton branches is greater than 2, and determining the length of the fiber interval as the length of the trunk line of the skeleton of the fiber interval.
Alternatively to this, the first and second parts may,
the deleting subunit is further configured to delete the skeleton branch from the skeleton of the fiber interval; when two skeleton sections are obtained and each skeleton section respectively comprises one edge endpoint, the skeleton branches belong to the trunk lines of the fiber-spaced skeletons; when a carcass section is obtained and comprises two of said edge end points, said carcass branch does not belong to the backbone of said fibre-spaced carcass.
Optionally, the second obtaining module includes:
the first processing unit is used for processing the characteristic binary image of the fiber interval by adopting a distance transformation algorithm to obtain the half-width length of each pixel point on the skeleton of the fiber interval;
and the second determining unit is used for determining the width of the fiber interval according to the half-width length of each pixel point on the framework of the fiber interval.
Optionally, the apparatus further comprises:
a third obtaining module, configured to obtain a collagen binary image and an image of the tissue sample, where the collagen binary image is used to characterize a position distribution of collagen in the tissue sample, and the image of the tissue sample is an image obtained by acquiring a second harmonic signal of the tissue sample;
the operation module is used for performing AND operation on the characteristic binary image of each fiber interval and the collagen image to obtain a first protein image of each fiber interval;
the extraction module is used for extracting pixel points with pixel values larger than a preset pixel threshold value in the image of the tissue sample from the first protein image of each fiber interval to obtain a second protein image of each fiber interval;
a determining module for determining collagen bundles in each of the fibrous intervals according to the second protein image of each of the fibrous intervals.
Optionally, the determining module includes:
the second processing unit is used for carrying out denoising processing and smoothing processing on the second protein image of the fiber interval;
the second acquisition unit is used for acquiring a skeleton of collagen in the fibrous interval from the processed second protein image of the fibrous interval by adopting a distance transformation algorithm;
and the deleting unit is used for deleting the cross points in the collagen skeletons in the fibrous intervals according to the collagen skeletons in the fibrous intervals to obtain the collagen bundles in the fibrous intervals.
Optionally, the apparatus further comprises:
a third determining unit, configured to determine a characteristic value of each collagen bundle in the fiber interval, where the characteristic value of the collagen bundle includes one or more of a length and a width.
Optionally, the apparatus further comprises:
a deleting module, configured to delete the first protein image and the blood-like vessel image of each fiber interval from the feature binary image of each fiber interval, to obtain a non-fibrosis binary image of each fiber interval, and a blood-like vessel image of each fiber interval, configured to characterize a position distribution of a blood-like vessel structure in the fiber interval;
and the fourth acquisition module is used for acquiring the characteristic value of a non-fibrosis area in each fiber interval according to the non-fibrosis binary image of the fiber interval, wherein the characteristics of the non-fibrosis area comprise one or more of area, length and width.
According to the technical scheme, the invention has the following beneficial effects:
acquiring a fiber interval binary image of the tissue sample, wherein the fiber interval binary image is used for representing the position distribution of fiber intervals in the tissue sample; identifying each connected domain in the fiber interval binary image, and generating a characteristic binary image of each fiber interval; and obtaining a characteristic value of each fiber interval according to the characteristic binary image of the fiber interval, wherein the characteristics of the fiber interval comprise one or more of area, length and width. In the embodiments of the present invention, there are provided not only a method for obtaining a characteristic value of a fibrous interval but also a method for obtaining a characteristic value of a collagen bundle in a fibrous interval, and further, a method for obtaining a characteristic value of a non-fibrotic region in a fibrous interval. Therefore, the characteristics of the fiber intervals are quantized, and a more intuitive data basis is provided for the doctor seeing.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for fiber spacing characteristic quantification provided by an embodiment of the present invention;
FIG. 2 is a schematic representation of a skeleton of a fiber space provided by an embodiment of the present invention;
FIG. 3 is a schematic representation of a backbone of a fiber-spaced framework provided by an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an apparatus for quantifying fiber spacing characteristics according to an embodiment of the present invention.
Detailed Description
In order to provide an implementation scheme for quantifying the characteristics of the fiber interval connecting PT and CV, the embodiment of the invention provides a characteristic quantification method and a characteristic quantification device, and the preferred embodiment of the invention is described in the following with reference to the attached drawings of the specification.
Currently, as the degree of liver fibrosis increases, fibrous spaces occur between PTs, and between PT and CV. Currently, the degree of fibrosis in the liver is analysed by pathologists by determining the fibrous intervals present in tissue samples. However, the fiber interval obtained by the pathologist is generally represented by qualitative image information, and each feature value of the fiber interval can only be roughly determined by the pathologist based on experience. How to quantify the characteristics of the fiber intervals and provide doctors with more intuitive data basis is a problem to be solved urgently at present.
In the embodiment of the invention, a fiber interval binary image of a tissue sample is obtained, and the fiber interval binary image is used for representing the position distribution of a fiber interval in the tissue sample; identifying each connected domain in the fiber interval binary image, and generating a characteristic binary image of each fiber interval; and obtaining a characteristic value of each fiber interval according to the characteristic binary image of the fiber interval, wherein the characteristics of the fiber interval comprise one or more of area, length and width. In the embodiments of the present invention, there are provided not only a method for obtaining a characteristic value of a fibrous interval but also a method for obtaining a characteristic value of a collagen bundle in a fibrous interval, and further, a method for obtaining a characteristic value of a non-fibrotic region in a fibrous interval. Therefore, the characteristics of the fiber intervals are quantized, and a more intuitive data basis is provided for the doctor seeing.
The following describes embodiments of the present invention in detail.
Fig. 1 is a method for quantifying fiber space characteristics according to an embodiment of the present invention, which is a method for quantifying fiber space characteristics in a tissue sample, and includes:
101: and acquiring a fiber interval binary image of the tissue sample, wherein the fiber interval binary image is used for representing the position distribution of the fiber interval in the tissue sample.
The fiber interval binary image refers to a binary image used for representing the position distribution of the fiber interval in the tissue sample. The binary image is an image composed of pixel points with pixel values of 0 and 1.
Obtaining a fiber interval binary image, there are several implementation ways:
in a first implementation, a nonlinear optical fiber imaging system is used to image a tissue sample, obtain a Second Harmonic Generation (SHG) signal of the tissue sample, and obtain an SHG image showing morphological features of collagen in the tissue sample according to the SHG signal; two-photon autofluorescence (TPEF) signals of the tissue sample are also obtained, from which TPEF images showing morphological features of tissue cells in the tissue sample are obtained. Obtaining a binary image of the tissue sample according to the SHG image and the TPEF image of the tissue sample, and manually marking the fiber interval in the tissue sample from the binary image of the tissue sample by a pathologist to obtain the binary image of the fiber interval.
In a second implementation manner, referring to another invention patent of my own, entitled "a method and an apparatus for identifying a fiber interval", a preset decision tree is used to obtain a fiber interval in a tissue sample, where the preset decision tree is used to represent a correspondence between feature information of a collagen block in the tissue sample and a type of the collagen block, so as to obtain a binary image of the fiber interval.
In a third implementation manner, reference may also be made to another invention patent of my own, entitled "a method and an apparatus for identifying a fiber interval connecting PT and CV", in which a fiber interval connecting PT and CV is determined according to a position distribution of PT and CV in a tissue sample, and a fiber interval binary image is obtained.
And in a fourth implementation mode, the second implementation mode and the third implementation mode are comprehensively adopted, the fiber interval in the tissue sample is determined, and a fiber interval binary image is obtained.
Of course, obtaining the binary image of the fiber interval is a precondition for implementing the present invention, and in practical applications, the method is not limited to the four implementation manners described above, and the binary image of the fiber interval may be obtained in other manners, which is not described herein again.
102: and identifying each connected domain in the fiber interval binary image, and generating a characteristic binary image of each fiber interval.
103: and obtaining a characteristic value of each fiber interval according to the characteristic binary image of the fiber interval, wherein the characteristics of the fiber interval comprise one or more of area, length and width.
In the fiber interval binary image, each connected domain can be regarded as one fiber interval. And extracting each connected domain from the fiber interval binary image to generate a feature binary image of the fiber interval. And the characteristic binary image of one fiber interval only comprises one connected domain in the fiber interval binary image.
And analyzing the characteristic value of each fiber interval according to the characteristic binary image of each fiber interval, namely analyzing one or more of the area, the length and the width of each fiber interval. The characteristic value of each fiber interval is provided for a pathological doctor, so that the characteristic of the fiber interval is quantized, and a more intuitive data basis is provided for the doctor.
The following describes a method for obtaining a feature value of a fiber interval according to a feature binary image of any fiber interval.
First, the characteristic values are the area of the fiber spacing:
and obtaining the area of the fiber interval according to the characteristic binary image of the fiber interval. And counting the sum of the areas of all pixel points in the connected domain representing the fiber interval in the characteristic binary image of the fiber interval to obtain the area of the fiber interval.
Secondly, the characteristic value is the length of the fiber interval:
determining a skeleton of the fiber interval according to the feature binary image of the fiber interval;
and acquiring the length of the framework between the end points of the two edges which are farthest away from the framework with the fiber interval as the length of the fiber interval.
When obtaining the skeleton of the fiber interval, in one example, the characteristic binary image of the fiber interval is processed by adopting a distance transformation algorithm, and then the skeleton of the fiber interval is obtained by adopting an image thinning algorithm; in another example, the fibrous septal binary image is and-operated with a marker image to obtain a skeleton of the fibrous septal, wherein the marker image comprises a position distribution of branches and intersection points in the tissue sample for characterizing all connected domains with larger areas and composed of collagen and blood vessel-like structures. The resulting framework of fiber spacing is shown in fig. 2.
And finding two edge end points with the largest distance from the skeletons of the fiber intervals, and determining the length of the skeletons between the two edge end points as the length of the fiber intervals. Specifically, when the length of the framework between the two edge endpoints is determined, the fiber interval is segmented according to the intersection points on the framework of the fiber interval to obtain a plurality of framework branches. If the resulting backbone branch is not greater than 2, there is no crossover point or only one crossover point on the backbone of the fiber spacing, in which case there is only one trunk line on the backbone of the fiber spacing, and the length of the fiber spacing is the length of the backbone of the fiber spacing. If the obtained backbone branch is greater than 2, it is necessary to find the backbone line on the backbone at the fiber interval and take the length of the backbone line at the fiber interval as the length of the fiber interval.
The main trunk line is searched from the fiber-spaced framework, and actually, the framework branch on the main trunk line belonging to the fiber-spaced framework is searched. The searching method comprises the following steps: for a skeleton branch, after the skeleton branch is deleted from a skeleton of a fiber, if two skeleton sections are obtained and each skeleton section only comprises one edge endpoint, the skeleton branch belongs to a trunk line of the skeleton spaced by the fiber; after deletion, if only one skeleton segment is obtained and the skeleton segment simultaneously comprises two edge end points, the skeleton branch does not belong to the main trunk line of the skeleton with the fiber interval. After analyzing each skeleton branch in the skeleton of the fiber interval one by one, all skeleton branches belonging to the trunk line in the skeleton of the fiber interval can be obtained, and thus, the trunk line of the skeleton of the fiber interval is obtained, as shown in fig. 3.
Thirdly, the characteristic value is the width of the fiber interval:
after the characteristic binary image of the fiber interval is processed by adopting a distance transformation algorithm, the distance from any pixel point to the nearest edge point in the characteristic binary image of the fiber interval can be obtained, and thus the half-width length of each pixel point on the skeleton of the fiber interval can be obtained. From the obtained half-width length, twice the maximum half-width length can be selected as the width of the fiber interval; the average of the half-width lengths of all the pixel points can also be calculated, and twice the average is taken as the width of the fiber interval.
In one example, in addition to being able to obtain characteristic values for the fiber spacing, characteristic values for collagen in the fiber spacing may also be obtained, including:
acquiring a collagen binary image and an image of a tissue sample, wherein the collagen binary image is used for representing the position distribution of collagen in the tissue sample, and the image of the tissue sample is an image obtained by acquiring a second harmonic signal of the tissue sample;
performing AND operation on the characteristic binary image of each fiber interval and the collagen image to obtain a first protein image of each fiber interval;
extracting pixel points with pixel values larger than a preset pixel threshold value in the image of the tissue sample from the first protein image of each fiber interval to obtain a second protein image of each fiber interval;
from the second protein image of each fibrous interval, collagen bundles in each fibrous interval are determined.
In order to obtain an image representing the position distribution of collagen in a fibrous interval, a characteristic binary image of the fibrous interval may be and-operated with the collagen image, thereby obtaining a first protein image of the fibrous interval and representing the position distribution of collagen in the fibrous interval.
For a fiber interval, after a first protein image of the fiber interval is obtained, a pixel point representing the fiber interval in the first protein image is determined, and the pixel value is in the image of the tissue sample. And extracting pixel points with pixel values larger than a pixel threshold value in the image of the tissue sample from the first protein image of the fiber interval to serve as a second protein image of the fiber interval. The second protein image was used to characterize the location distribution of significant collagen at this fibrous interval. And deleting the second protein image from the first protein image to obtain a third protein image, wherein the third protein image is used for representing the position distribution of dim collagen at the fiber interval.
From the second protein image of a fibrous interval, the collagen bundles of that fibrous interval are determined. The concrete implementation is as follows: and deleting the area with the area smaller than the area threshold value in the second protein image of the fiber interval, namely denoising the second protein image of the fiber interval. And performing opening and closing operation on the second protein image of the fiber interval, namely performing edge smoothing on the second protein image of the fiber interval. And then, obtaining the skeleton of the collagen in the fiber interval by adopting a distance transformation algorithm on the second protein image of the processed fiber interval. In the skeleton of the collagen, each cross point is a cross-linking point, and the collagen connected with the cross-linking point is an aggregated collagen bundle; in addition to the aggregated collagen bundles, other collagens are dispersed collagen bundles.
Alternatively, the length of each collagen bundle, that is, the length of the skeleton from which the collagen bundle is obtained, may be further determined as the length of the collagen bundle.
Optionally, the width of each collagen bundle may be further determined, that is, the half-width length of each pixel point on the skeleton of the collagen bundle may be obtained by processing each collagen bundle by using a distance transformation algorithm. Selecting twice the maximum half width length from the obtained half width lengths as the width of the collagen bundle; the average value of the half width and the half length of all the pixel points can also be calculated, and the width of the collagen bundle is taken as twice of the average value.
In another example, characteristic values of non-fibrotic regions in the fibrous space may be further determined, including:
deleting the first protein image and the blood vessel-like image of each fiber interval from the characteristic binary image of each fiber interval to obtain a non-fibrosis binary image of each fiber interval and a blood vessel-like image of each fiber interval, wherein the blood vessel-like image of each fiber interval is used for representing the position distribution of a blood vessel-like structure in the fiber interval;
from the non-fibrotic binary image of each fibrous interval, values of characteristics of non-fibrotic regions in the fibrous interval are obtained, the characteristics of the non-fibrotic regions including one or more of area, length, and width.
For a fiber interval, deleting the first protein image of the fiber interval and the blood vessel-like image from the characteristic binary image of the fiber interval, and obtaining a non-fibrosis binary image of the fiber interval, wherein the non-fibrosis binary image is used for representing the position distribution of a non-fibrosis region in the fiber interval.
Determining the characteristic value of the non-fibrosis area of the fiber interval, and concretely realizing the following steps:
first, the eigenvalues are the area of the non-fibrotic region:
the area of the non-fibrotic region in the fibrous space is obtained from a non-fibrotic binary image of the fibrous space. And counting the sum of the areas of all pixel points in the connected domain of the non-fibrosis region in the non-fibrosis binary image of the fiber interval to obtain the area of the non-fibrosis region in the fiber interval.
Second, the eigenvalues are the length of the non-fibrotic regions:
processing the non-fibrosis binary image of the fiber interval by adopting a distance transformation algorithm, obtaining the skeleton of the non-fibrosis region in the fiber interval according to an image thinning algorithm, and determining the main line on the skeleton of the non-fibrosis region in the fiber interval according to the mode of determining the main line on the skeleton of the fiber interval. The length of the trunk line on the skeleton of the nonfibrillating region was defined as the length of the nonfibrillating region.
Thirdly, the characteristic value is the width of the non-fibrosis area:
after the non-fibrosis binary image of the fiber interval is processed by adopting a distance transformation algorithm, the distance from any pixel point to the nearest edge point in the non-fibrosis binary image of the fiber interval can be obtained, and thus the half-width length of each pixel point on the framework of the non-fibrosis area of the fiber interval can be obtained. From the resulting half-width lengths, twice the maximum half-width length can be selected as the width of the non-fibrotic region of the fibrous interval; or calculating the average value of the half width length of all the pixel points, and taking twice of the average value as the width of the non-fibrosis area of the fiber interval.
Fig. 4 is a schematic structural diagram of an apparatus for quantifying fiber spacing characteristics according to an embodiment of the present invention, including:
a first obtaining module 401, configured to obtain a fiber spacing binary image of a tissue sample, where the fiber spacing binary image is used to characterize a position distribution of a fiber spacing in the tissue sample.
An identifying module 402, configured to identify each connected domain in the fiber interval binary image, and generate a feature binary image of each fiber interval.
A second obtaining module 403, configured to obtain a feature value of each fiber interval according to the feature binary image of the fiber interval, where the feature of the fiber interval includes one or more of an area, a length, and a width.
Optionally, the second obtaining module includes:
the first determining unit is used for determining the skeleton of the fiber interval according to the characteristic binary image of the fiber interval;
and the first acquisition unit is used for acquiring the length of the framework between the end points of the two edges which are farthest away on the framework with the fiber interval as the length of the fiber interval.
Optionally, the obtaining unit includes:
the searching subunit is used for searching two edge endpoints which are farthest away on the framework with the fiber interval;
the dividing subunit is used for dividing according to the intersection points on the fiber interval framework to obtain framework branches;
the determining subunit is used for determining the length of the fiber interval as the length of the skeleton of the fiber interval when the number of the skeleton branches is not more than 2;
and the deleting subunit is used for deleting the skeleton branches on the trunk line of the skeleton not belonging to the fiber interval when the number of the skeleton branches is greater than 2, and determining the length of the fiber interval as the length of the trunk line of the skeleton of the fiber interval.
Alternatively to this, the first and second parts may,
the deleting subunit is further configured to delete the skeleton branch from the skeleton of the fiber interval; when two skeleton sections are obtained and each skeleton section respectively comprises one edge endpoint, the skeleton branches belong to the trunk lines of the fiber-spaced skeletons; when a carcass section is obtained and comprises two of said edge end points, said carcass branch does not belong to the backbone of said fibre-spaced carcass.
Optionally, the second obtaining module includes:
the first processing unit is used for processing the characteristic binary image of the fiber interval by adopting a distance transformation algorithm to obtain the half-width length of each pixel point on the skeleton of the fiber interval;
and the second determining unit is used for determining the width of the fiber interval according to the half-width length of each pixel point on the framework of the fiber interval.
Optionally, the apparatus further comprises:
a third obtaining module, configured to obtain a collagen binary image and an image of the tissue sample, where the collagen binary image is used to characterize a position distribution of collagen in the tissue sample, and the image of the tissue sample is an image obtained by acquiring a second harmonic signal of the tissue sample;
the operation module is used for performing AND operation on the characteristic binary image of each fiber interval and the collagen image to obtain a first protein image of each fiber interval;
the extraction module is used for extracting pixel points with pixel values larger than a preset pixel threshold value in the image of the tissue sample from the first protein image of each fiber interval to obtain a second protein image of each fiber interval;
a determining module for determining collagen bundles in each of the fibrous intervals according to the second protein image of each of the fibrous intervals.
Optionally, the determining module includes:
the second processing unit is used for carrying out denoising processing and smoothing processing on the second protein image of the fiber interval;
the second acquisition unit is used for acquiring a skeleton of collagen in the fibrous interval from the processed second protein image of the fibrous interval by adopting a distance transformation algorithm;
and the deleting unit is used for deleting the cross points in the collagen skeletons in the fibrous intervals according to the collagen skeletons in the fibrous intervals to obtain the collagen bundles in the fibrous intervals.
Optionally, the apparatus further comprises:
a third determining unit, configured to determine a characteristic value of each collagen bundle in the fiber interval, where the characteristic value of the collagen bundle includes one or more of a length and a width.
Optionally, the apparatus further comprises:
a deleting module, configured to delete the first protein image and the blood-like vessel image of each fiber interval from the feature binary image of each fiber interval, to obtain a non-fibrosis binary image of each fiber interval, and a blood-like vessel image of each fiber interval, configured to characterize a position distribution of a blood-like vessel structure in the fiber interval;
and the fourth acquisition module is used for acquiring the characteristic value of a non-fibrosis area in each fiber interval according to the non-fibrosis binary image of the fiber interval, wherein the characteristics of the non-fibrosis area comprise one or more of area, length and width.
The apparatus shown in fig. 4 is a device corresponding to the method shown in fig. 1, and the specific implementation manner is similar, and reference is made to the description of the method shown in fig. 1, which is not repeated here.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be construed as the protection scope of the present invention.
Claims (12)
1. A method of fiber space characterization, the method comprising:
acquiring a fiber interval binary image of a tissue sample, wherein the fiber interval binary image is used for representing the position distribution of fiber intervals in the tissue sample;
identifying each connected domain in the fiber interval binary image, and generating a characteristic binary image of each fiber interval;
obtaining a characteristic value of each fiber interval according to the characteristic binary image of the fiber interval, wherein the characteristics of the fiber interval comprise one or more of area, length and width;
the obtaining the length of the fiber interval according to one binary image of the fiber interval characteristic comprises:
determining a skeleton of the fiber interval according to the characteristic binary image of the fiber interval;
acquiring the length of a framework between two edge endpoints with the farthest distance on the framework with the fiber interval as the length of the fiber interval;
obtaining a skeleton length between two edge endpoints with the farthest distance on the skeleton with the fiber interval as the length of the fiber interval comprises:
searching two edge endpoints which are farthest away on the framework with the fiber interval;
segmenting according to the cross points on the fiber-spaced framework to obtain framework branches;
when the number of the skeleton branches is not more than 2, determining the length of the fiber interval as the length of the skeleton of the fiber interval;
when the number of the skeleton branches is more than 2, deleting the skeleton branches on the trunk line of the skeleton which does not belong to the fiber interval, and determining the length of the fiber interval as the length of the trunk line of the skeleton of the fiber interval;
wherein identifying whether one of the skeletal branches belongs to a trunk of the fiber-spaced skeletal framework comprises:
deleting the backbone branches from the fiber-spaced backbone;
when two skeleton sections are obtained and each skeleton section respectively comprises one edge endpoint, the skeleton branches belong to the trunk lines of the fiber-spaced skeletons;
when a carcass section is obtained and comprises two of said edge end points, said carcass branch does not belong to the backbone of said fibre-spaced carcass.
2. The method of claim 1, wherein obtaining the width of the fiber space from a binary image of the fiber space characteristic comprises:
processing the characteristic binary image of the fiber interval by adopting a distance transformation algorithm to obtain the half-width length of each pixel point on the skeleton of the fiber interval;
and determining the width of the fiber interval according to the half-width length of each pixel point on the framework of the fiber interval.
3. The method of claim 1, further comprising:
acquiring a collagen binary image and an image of the tissue sample, wherein the collagen binary image is used for representing the position distribution of collagen in the tissue sample, and the image of the tissue sample is an image obtained by acquiring a second harmonic signal of the tissue sample;
performing AND operation on the characteristic binary image of each fiber interval and the collagen image to obtain a first protein image of each fiber interval;
extracting pixel points with pixel values larger than a preset pixel threshold value in the image of the tissue sample from the first protein image of each fiber interval to obtain a second protein image of each fiber interval;
determining collagen bundles in each of the fibrous intervals from the second protein image of each of the fibrous intervals.
4. The method of claim 3, wherein determining collagen bundles in the fibrous space based on a second protein image of the fibrous space comprises:
denoising and smoothing the second protein image of the fiber interval;
obtaining a skeleton of collagen in the fibrous interval from the processed second protein image of the fibrous interval by adopting a distance transformation algorithm;
and deleting the cross points in the collagen skeletons in the fibrous intervals according to the collagen skeletons in the fibrous intervals to obtain collagen bundles in the fibrous intervals.
5. The method of claim 4, further comprising:
determining a characteristic value of each collagen bundle in the fibrous interval, the characteristic value of the collagen bundle including one or more of a length and a width.
6. The method according to any one of claims 1-5, further comprising:
deleting the first protein image and the blood vessel-like image of each fiber interval from the characteristic binary image of each fiber interval to obtain a non-fibrosis binary image of each fiber interval, wherein the blood vessel-like image of each fiber interval is used for representing the position distribution of blood vessel-like structures in the fiber intervals;
obtaining a characteristic value of a non-fibrotic region in each of the fibrous intervals from the non-fibrotic binary image of the fibrous interval, the characteristic of the non-fibrotic region including one or more of an area, a length, and a width.
7. An apparatus for fiber space characteristic quantification, the apparatus comprising:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a fiber interval binary image of a tissue sample, and the fiber interval binary image is used for representing the position distribution of a fiber interval in the tissue sample;
the identification module is used for identifying each connected domain in the fiber interval binary image and generating a characteristic binary image of each fiber interval;
the second acquisition module is used for acquiring a characteristic value of each fiber interval according to the characteristic binary image of the fiber interval, wherein the characteristic of the fiber interval comprises one or more of area, length and width;
the second acquisition module includes:
the first determining unit is used for determining the skeleton of the fiber interval according to the characteristic binary image of the fiber interval;
the first acquisition unit is used for acquiring the length of a framework between two edge endpoints which are farthest away on the framework of the fiber interval as the length of the fiber interval;
the acquisition unit includes:
the searching subunit is used for searching two edge endpoints which are farthest away on the framework with the fiber interval;
the dividing subunit is used for dividing according to the intersection points on the fiber interval framework to obtain framework branches;
the determining subunit is used for determining the length of the fiber interval as the length of the skeleton of the fiber interval when the number of the skeleton branches is not more than 2;
a deleting subunit, configured to delete, when the number of the skeleton branches is greater than 2, a skeleton branch on a trunk line of the skeleton not belonging to the fiber interval, and determine that the length of the fiber interval is the length of the trunk line of the skeleton at the fiber interval;
the deleting subunit is further configured to delete the skeleton branch from the skeleton of the fiber interval; when two skeleton sections are obtained and each skeleton section respectively comprises one edge endpoint, the skeleton branches belong to the trunk lines of the fiber-spaced skeletons; when a carcass section is obtained and comprises two of said edge end points, said carcass branch does not belong to the backbone of said fibre-spaced carcass.
8. The apparatus of claim 7, wherein the second obtaining module comprises:
the first processing unit is used for processing the characteristic binary image of the fiber interval by adopting a distance transformation algorithm to obtain the half-width length of each pixel point on the skeleton of the fiber interval;
and the second determining unit is used for determining the width of the fiber interval according to the half-width length of each pixel point on the framework of the fiber interval.
9. The apparatus of claim 7, further comprising:
a third obtaining module, configured to obtain a collagen binary image and an image of the tissue sample, where the collagen binary image is used to characterize a position distribution of collagen in the tissue sample, and the image of the tissue sample is an image obtained by acquiring a second harmonic signal of the tissue sample;
the operation module is used for performing AND operation on the characteristic binary image of each fiber interval and the collagen image to obtain a first protein image of each fiber interval;
the extraction module is used for extracting pixel points with pixel values larger than a preset pixel threshold value in the image of the tissue sample from the first protein image of each fiber interval to obtain a second protein image of each fiber interval;
a determining module for determining collagen bundles in each of the fibrous intervals according to the second protein image of each of the fibrous intervals.
10. The apparatus of claim 9, wherein the determining module comprises:
the second processing unit is used for carrying out denoising processing and smoothing processing on the second protein image of the fiber interval;
the second acquisition unit is used for acquiring a skeleton of collagen in the fibrous interval from the processed second protein image of the fibrous interval by adopting a distance transformation algorithm;
and the deleting unit is used for deleting the cross points in the collagen skeletons in the fibrous intervals according to the collagen skeletons in the fibrous intervals to obtain the collagen bundles in the fibrous intervals.
11. The apparatus of claim 10, further comprising:
a third determining unit, configured to determine a characteristic value of each collagen bundle in the fiber interval, where the characteristic value of the collagen bundle includes one or more of a length and a width.
12. The apparatus of any one of claims 7-11, further comprising:
a deleting module, configured to delete the first protein image and the blood-like vessel image of each fiber interval from the feature binary image of each fiber interval, to obtain a non-fibrosis binary image of each fiber interval, and a blood-like vessel image of each fiber interval, configured to characterize a position distribution of a blood-like vessel structure in the fiber interval;
and the fourth acquisition module is used for acquiring the characteristic value of a non-fibrosis area in each fiber interval according to the non-fibrosis binary image of the fiber interval, wherein the characteristics of the non-fibrosis area comprise one or more of area, length and width.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711476772.2A CN108230387B (en) | 2017-12-29 | 2017-12-29 | Fiber interval characteristic quantification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711476772.2A CN108230387B (en) | 2017-12-29 | 2017-12-29 | Fiber interval characteristic quantification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108230387A CN108230387A (en) | 2018-06-29 |
| CN108230387B true CN108230387B (en) | 2020-10-27 |
Family
ID=62647050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711476772.2A Active CN108230387B (en) | 2017-12-29 | 2017-12-29 | Fiber interval characteristic quantification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108230387B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020027732A1 (en) * | 2018-07-30 | 2020-02-06 | Agency For Science, Technology And Research | Method and system for assessing fibrosis in a tissue sample |
| CN109543531B (en) * | 2018-10-19 | 2023-01-03 | 兰波(苏州)智能科技有限公司 | Method for extracting fibers and correcting fiber vision |
| WO2021051335A1 (en) * | 2019-09-19 | 2021-03-25 | 北京大学人民医院(北京大学第二临床医学院) | Hepatitis c liver fibrosis feature information extraction method and apparatus |
| CN111667482B (en) * | 2020-06-30 | 2023-08-22 | 杭州筹图科技有限公司 | Region dividing method and related equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105009174A (en) * | 2013-01-08 | 2015-10-28 | 新加坡科技研究局 | Method and system for assessing fibrosis in tissue |
| CN106127256A (en) * | 2016-06-30 | 2016-11-16 | 张云超 | A kind of hepatic fibrosis detection method and device |
| CN107463913A (en) * | 2017-08-11 | 2017-12-12 | 苏炯龙 | Image collagenous fibres identification computing system and method based on Lab |
-
2017
- 2017-12-29 CN CN201711476772.2A patent/CN108230387B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105009174A (en) * | 2013-01-08 | 2015-10-28 | 新加坡科技研究局 | Method and system for assessing fibrosis in tissue |
| CN106127256A (en) * | 2016-06-30 | 2016-11-16 | 张云超 | A kind of hepatic fibrosis detection method and device |
| CN107463913A (en) * | 2017-08-11 | 2017-12-12 | 苏炯龙 | Image collagenous fibres identification computing system and method based on Lab |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108230387A (en) | 2018-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108230387B (en) | Fiber interval characteristic quantification method and device | |
| Liu et al. | Fibrillar collagen quantification with curvelet transform based computational methods | |
| Zhi et al. | AdipoCount: a new software for automatic adipocyte counting | |
| Bai et al. | Automatic segmentation of cervical region in colposcopic images using K-means | |
| JP6745874B2 (en) | Method and apparatus for tissue recognition | |
| CN110136161A (en) | Image characteristics extraction analysis method, system and device | |
| JP2018529103A (en) | Method and apparatus for tissue recognition | |
| CN112419295A (en) | Medical image processing method, apparatus, computer device and storage medium | |
| CN108198170B (en) | Fiber interval identification method and device | |
| CN115359066B (en) | Focus detection method and device for endoscope, electronic device and storage medium | |
| CN108185990B (en) | Identification method and device for fiber interval connecting PT and CV | |
| Matalka et al. | A novel approach for quantitative assessment of mucosal damage in inflammatory bowel disease | |
| CN113160153A (en) | Lung nodule screening method and system based on deep learning technology | |
| CN115861227A (en) | Unsupervised industrial surface defect detection method and unsupervised industrial surface defect detection device based on image semantic reconstruction | |
| JP6819445B2 (en) | Information processing equipment, control methods, and programs | |
| Tse et al. | A combined watershed and level set method for segmentation of brightfield cell images | |
| CN108765399B (en) | Lesion site recognition device, computer device, and readable storage medium | |
| CN116645390B (en) | Fluorescent image cell rapid segmentation method and system | |
| JP6246978B2 (en) | Method for detecting and quantifying fibrosis | |
| CN109859218B (en) | Pathological graph key area determination method and device, electronic equipment and storage medium | |
| Su et al. | A novel method for dendritic spines detection based on directional morphological filter and shortest path | |
| CN116128774A (en) | Stomach spiral CT data enhancement processing method | |
| WO2022000220A1 (en) | Area division method and related device | |
| KR102187712B1 (en) | A Method For Merging Veins In A X-ray/CT Image And An Apparatus Thereof | |
| CN111667482B (en) | Region dividing method and related equipment |
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 |