CN117974528B - Kidney biopsy slice image optimization enhancement method - Google Patents
Kidney biopsy slice image optimization enhancement method Download PDFInfo
- Publication number
- CN117974528B CN117974528B CN202410391207.XA CN202410391207A CN117974528B CN 117974528 B CN117974528 B CN 117974528B CN 202410391207 A CN202410391207 A CN 202410391207A CN 117974528 B CN117974528 B CN 117974528B
- Authority
- CN
- China
- Prior art keywords
- kidney biopsy
- gray
- initial cell
- image
- slice
- 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
- 238000011862 kidney biopsy Methods 0.000 title claims abstract description 190
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000005457 optimization Methods 0.000 title abstract description 8
- 230000002708 enhancing effect Effects 0.000 claims abstract description 16
- 230000008859 change Effects 0.000 claims abstract description 7
- 238000003708 edge detection Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 7
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 3
- 210000004027 cell Anatomy 0.000 description 123
- 210000003904 glomerular cell Anatomy 0.000 description 14
- 230000002452 interceptive effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 210000001039 kidney glomerulus Anatomy 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001434 glomerular Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000663 muscle cell Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30084—Kidney; Renal
Landscapes
- Image Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a kidney biopsy slice image optimization enhancement method, which comprises the following steps: collecting a plurality of kidney biopsy slice gray level images; dividing the region of the gray level image of the kidney biopsy slice according to the change condition of the gray level value of the pixel point in the gray level image of the kidney biopsy slice to obtain a plurality of initial cell regions; obtaining a kidney biopsy characteristic coefficient of each initial cell region according to the overall gray level difference condition of different regions in the gray level map of the kidney biopsy slice, the shape arrangement difference condition on different edges in the same region and the region size difference condition; and adjusting a gray scale interval according to the kidney biopsy characteristic coefficient, and optimizing and enhancing the gray scale image of each kidney biopsy slice. The invention improves the enhancement effect of the kidney biopsy slice image and improves the detection efficiency of the kidney biopsy slice.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a kidney biopsy slice image optimization enhancement method.
Background
In the process of kidney biopsy section image analysis, the analysis is mainly carried out according to the image information of glomerulus tissue; however, the image of the kidney biopsy slice also contains a large amount of image information of other interfering objects, which interfere with the image expression of glomerular tissues, so that the image enhancement of the image of the kidney biopsy slice is required.
The traditional method generally utilizes a piecewise linear gray level transformation algorithm to enhance the kidney biopsy slice image, but other cells in the kidney biopsy slice image have similar colors and sizes with the kidney glomerulus cells, so that the traditional piecewise linear gray level transformation algorithm cannot effectively identify the kidney glomerulus cells and enhance pertinently according to a mode of manually presetting a gray level threshold, the enhancement effect of the image is poor, and the detection efficiency of kidney biopsy is reduced.
Disclosure of Invention
The invention provides a kidney biopsy slice image optimization enhancement method, which aims to solve the existing problems: other cells in the image of the kidney biopsy section are similar to the glomerular cells in color and size, and the traditional piecewise linear gray level conversion algorithm cannot effectively identify the glomerular cells and perform targeted enhancement in a gray level conversion mode according to an artificial preset gray level threshold.
The invention relates to a kidney biopsy slice image optimization enhancement method which adopts the following technical scheme:
The method comprises the following steps:
Collecting a plurality of kidney biopsy slice gray level images;
Dividing the region of the gray level image of the kidney biopsy slice according to the change condition of the gray level value of the pixel point in the gray level image of the kidney biopsy slice to obtain a plurality of initial cell regions; obtaining a kidney biopsy characteristic coefficient of each initial cell region according to the overall gray level difference condition of different regions in the gray level map of the kidney biopsy slice, the shape arrangement difference condition on different edges in the same region and the region size difference condition;
and adjusting a gray scale interval according to the kidney biopsy characteristic coefficient, and optimizing and enhancing the gray scale image of each kidney biopsy slice.
Preferably, the method for dividing the region of the gray level map of the kidney biopsy slice according to the change condition of the gray level value of the pixel point in the gray level map of the kidney biopsy slice to obtain a plurality of initial cell regions comprises the following specific steps:
Inputting the grey level image of the kidney biopsy slice into a Canny edge detection algorithm to obtain an edge detection image of the kidney biopsy slice for any grey level image of the kidney biopsy slice; marking all pixels with gray values different from 0 in the kidney biopsy edge detection diagram as initial edge pixels; each closed region surrounded by all the initial edge pixel points in the kidney biopsy edge detection map is marked as an edge cell region, and the region with the same position as the edge cell region in the kidney biopsy slice gray scale map is marked as an initial cell region.
Preferably, the obtaining the characteristic coefficient of the kidney biopsy of each initial cell area according to the overall gray scale difference condition of different areas in the gray scale map of the kidney biopsy slice, the shape arrangement difference condition on different edges in the same area and the area size difference condition comprises the following specific methods:
for any initial cell area, obtaining the area gray consistency of the initial cell area according to the distribution difference condition of gray values in the initial cell area;
Obtaining the edge smoothness of the initial cell area according to the distribution condition of the pixel points on the edge of the initial cell area;
Obtaining the cell area difference degree of the initial cell area according to the difference between the area size of the initial cell area and the ideal situation;
And (3) marking the product of the region gray level consistency of the initial cell region, the edge smoothness of the initial cell region and the edge smoothness of the initial cell region as a kidney biopsy characteristic coefficient of the initial cell region.
Preferably, the obtaining the regional gray scale consistency of the initial cell region according to the distribution difference condition of the gray scale values in the initial cell region comprises the following specific methods:
In the method, in the process of the invention, A region gray scale uniformity representing an initial cell region; /(I)Representing the average value of gray values of all pixel points in the initial cell area; /(I)Representing the number of all pixel points in the initial cell area; /(I)Represents the/>, in the initial cell regionGray values of the individual pixels; /(I)An exponential function based on a natural constant is represented.
Preferably, the obtaining the edge smoothness of the initial cell area according to the distribution of the pixel points on the edge of the initial cell area includes the following specific steps:
Marking each pixel point on the edge of the initial cell area as an edge pixel point; acquiring a normal vector of each edge pixel point, and acquiring a Euclidean distance between each edge pixel point and a centroid in an initial cell area; according to the normal vector of each edge pixel point and the Euclidean distance between each edge pixel point and the mass center in the initial cell area, the edge smoothness of the initial cell area is obtained, and the specific formula is as follows:
In the method, in the process of the invention, Edge smoothness representing the initial cell area; /(I)Representing the number of all edge pixels in the initial cell area; /(I)Represents the/>, within the initial cell regionNormal vector of each edge pixel point; /(I)Represents the/>, within the initial cell regionThe Euclidean distance between each edge pixel point and the mass center in the initial cell area; /(I)Represents the/>, within the initial cell regionNormal vector of each edge pixel point; /(I)Represents the/>, within the initial cell regionThe Euclidean distance between each edge pixel point and the mass center in the initial cell area; /(I)An exponential function based on a natural constant is represented.
Preferably, the obtaining the cell area difference degree of the initial cell area according to the size difference condition of the area size of the initial cell area and the ideal condition comprises the following specific methods:
Presetting a reference cell area ; Area of initial cell region and/>The absolute value of the difference of (2) is denoted as the area difference value, and the inverse proportion normalization value of the area difference value is denoted as the cell area difference degree of the initial cell region.
Preferably, the gray scale interval is adjusted according to the characteristic coefficient of the kidney biopsy, and the gray scale image of each kidney biopsy slice is optimized and enhanced, which comprises the following specific steps:
for any one of the grey-scale images of the kidney biopsy slices, presetting a threshold value of the kidney biopsy characteristic coefficient ; According to the threshold value/>, of the characteristic coefficient of renal biopsyScreening all initial cell areas in the gray level diagram of the kidney biopsy slice to obtain a plurality of target kidney biopsy cell areas;
the minimum gray value is marked as the minimum kidney biopsy gray value and the maximum gray value is marked as the maximum kidney biopsy gray value in the gray values of all pixel points in all target kidney biopsy cell areas; obtaining a kidney biopsy core gray scale interval, a first gray scale interval and a second gray scale interval according to the minimum kidney biopsy gray scale value and the maximum kidney biopsy gray scale value;
And carrying out gray level transformation according to the gray level interval, the first gray level interval and the second gray level interval of the kidney biopsy core to obtain an optimized enhanced image of the gray level image of the kidney biopsy slice.
Preferably, the threshold value is based on the characteristic coefficient of the kidney biopsyScreening all initial cell areas in a grey level chart of the kidney biopsy slice to obtain a plurality of target kidney biopsy cell areas, wherein the specific method comprises the following steps:
The characteristic coefficient of the kidney biopsy is greater than a plurality Is designated as the target kidney biopsy cell area.
Preferably, the method for obtaining the kidney biopsy core gray scale interval, the first gray scale interval and the second gray scale interval according to the minimum kidney biopsy gray scale value and the maximum kidney biopsy gray scale value comprises the following specific steps:
the gray value interval formed by the minimum kidney biopsy gray value and the maximum kidney biopsy gray value is marked as a kidney biopsy core gray value interval, the interval formed by all gray values before the kidney biopsy core gray value is marked as a first gray value interval, and the interval formed by all gray values after the kidney biopsy core gray value is marked as a second gray value interval.
Preferably, the method for obtaining the optimized enhanced image of the gray level map of the kidney biopsy slice by performing gray level transformation according to the gray level interval, the first gray level interval and the second gray level interval of the kidney biopsy core comprises the following specific steps:
taking the first gray scale interval as a gray scale value range [0, a ], taking the kidney biopsy core gray scale interval as a gray scale value range [ a, b ], and taking the second gray scale interval as a gray scale value range [ b, e ]; compressing the gray value range [0, a ] and the gray value range [ b, e ], linearly expanding the gray value range [ a, b ] to obtain an image after gray conversion, and marking the image as an optimized enhanced image of the gray image of the kidney biopsy slice.
The technical scheme of the invention has the beneficial effects that: the method comprises the steps of obtaining a kidney biopsy characteristic coefficient of each initial cell region by analyzing the overall gray level difference condition and the region size difference condition of different regions in a gray level map of a kidney biopsy slice and combining the shape arrangement difference conditions on different edges in the same region, and adaptively adjusting a gray level threshold value so as to adjust a gray level interval; dividing the grey level image of the kidney biopsy slice into a plurality of initial cell areas according to the change condition of grey level values of pixel points in the grey level image of the kidney biopsy slice, wherein the initial cell areas are used for reflecting areas possibly containing glomerular cells, and eliminating other impurities and interference of partial background; then, the difference of gray scales of different areas and the difference of shape arrangement on the edges are used for obtaining the kidney biopsy characteristic coefficient of the initial cell area, wherein the kidney biopsy characteristic coefficient is used for reflecting the probability that the initial cell area belongs to glomerular cells and further eliminating the interference of other irrelevant areas such as muscle cells, cell fluid and the like; according to the invention, through analyzing the overall gray level difference, shape difference and region size difference conditions of different regions in the gray level map of the kidney biopsy slice, the kidney biopsy characteristic coefficient is comprehensively obtained, the gray level threshold value is adaptively adjusted, the gray level interval is further adjusted, the image optimization enhancement is completed, the influence of other interference cells on the glomerular cell distinction is reduced, the precision of identifying the glomerular cells is improved, the gray level threshold value is more accurate, the enhancement effect of the kidney biopsy slice image is improved, and the detection efficiency of the kidney biopsy slice is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for optimizing and enhancing images of a kidney biopsy according to the present invention;
FIG. 2 is a schematic representation of a gray scale map of a kidney biopsy slice of the present invention;
fig. 3 is a flow chart of features of a method for optimizing and enhancing images of a kidney biopsy according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following description refers to the specific implementation, structure, characteristics and effects of the method for optimizing and enhancing the image of the kidney biopsy slice according to the invention by combining the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the kidney biopsy slice image optimization enhancement method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps in a method for optimizing and enhancing a renal biopsy slice image according to an embodiment of the present invention is shown, the method comprises the following steps:
step S001: several kidney biopsy slice gray-scale images are acquired.
It should be noted that, in the existing method, the image of the kidney biopsy slice is usually enhanced by using a piecewise linear gray level conversion algorithm, but other cells exist in the image of the kidney biopsy slice and have similar colors and sizes with the glomerulus cells, so that the traditional piecewise linear gray level conversion algorithm cannot effectively identify the glomerulus cells and enhance pertinently in a manner of manually presetting a gray level threshold, so that the enhancement effect of the image is poor, and the detection efficiency of the kidney biopsy is reduced.
Specifically, firstly, a gray level image of a kidney biopsy slice needs to be acquired, and the specific process is as follows: and acquiring a near-day kidney biopsy slice image in the kidney biopsy slice image library, and carrying out grey-scale treatment on each kidney biopsy slice image to obtain a plurality of kidney biopsy slice grey-scale images. The graying process is a known technique, and the description of this embodiment is omitted. Referring to fig. 2, a schematic representation of a gray scale map of a kidney biopsy slice is shown.
To this end, a grey-scale map of the kidney biopsy slice was obtained by the method described above.
Step S002: dividing the region of the gray level image of the kidney biopsy slice according to the change condition of the gray level value of the pixel point in the gray level image of the kidney biopsy slice to obtain a plurality of initial cell regions; and obtaining the kidney biopsy characteristic coefficient of each initial cell region according to the overall gray level difference condition of different regions in the gray level map of the kidney biopsy slice, the shape arrangement difference condition on different edges in the same region and the region size difference condition.
In the actual grey level image of the kidney biopsy section, the interference of some other cells such as capillaries and muscle tissues usually causes similar grey level characteristics of some interfering cells and glomerular cells, and the corresponding whole grey level is deeper, so that the interference of some glomerular cells cannot be observed obviously. For glomerular cells, the glomerular cells are elliptical, the internal gray level distribution is more consistent, the cell appearance is smoother, the glomerular cells have more obvious edge parts, and the whole glomerular cells are closed; for other interfering cells, such as muscle tissues, the shape of the interfering cells is like a long strip, the internal gray level distribution is more consistent, the cell appearance is more tortuous, the cell has more obvious edge parts, and the whole body is in a closed shape; like capillary, it is like a long column, the inner gray level distribution is more dispersed, the cell surface is smoother, the edge part is more blurred, and the whole is open. And there will also be some amount of translucent cellular fluid in the kidney biopsy, which is randomly distributed and the area formed is usually not a complete occlusion area. In combination with the above analysis, in order to optimize the enhancement effect of the image, the present embodiment obtains the characteristic coefficient of the kidney biopsy by analyzing the gray distribution difference condition and the shape difference condition in different edge regions in the gray map of the kidney biopsy for subsequent analysis and processing.
Specifically, taking a gray level image of any one kidney biopsy slice as an example, inputting the gray level image of the kidney biopsy slice into a Canny edge detection algorithm to obtain an edge detection image of the kidney biopsy slice; marking each pixel point with gray value not being 0 in the kidney biopsy edge detection diagram as an initial edge pixel point; each closed region surrounded by all the initial edge pixel points in the kidney biopsy edge detection image is marked as an edge cell region, and the region with the same position as the edge cell region in the kidney biopsy slice gray scale image is marked as an initial cell region. Wherein each kidney biopsy section gray scale map comprises a plurality of initial cell areas; in addition, the Canny edge detection algorithm is a well-known technique, and this embodiment will not be described in detail. It should be noted that each of the edge cell regions may include a plurality of initial edge pixel points, and each of the initial cell regions may include a plurality of initial cell regions.
Further, taking any initial cell area as an example, the area gray scale consistency of the initial cell area is obtained according to the distribution difference of gray scale values in the initial cell area. As an example, the regional gray scale uniformity of the initial cellular region can be calculated by the following formula:
In the method, in the process of the invention, A region gray scale uniformity representing the initial cell region; /(I)Representing the average value of gray values of all pixel points in the initial cell area; /(I)Representing the number of all pixels in the initial cell region; /(I)Indicating the first/>, in the initial cell regionGray values of the individual pixels; /(I)Representing an exponential function based on natural constants, the examples employ/>Model to present inverse proportional relationship and normalization process,/>For model input, the implementer may choose the inverse proportion function and the normalization function according to the actual situation. Wherein, if the area gray level consistency of the initial cell area is larger, the gray level distribution in the initial cell area is more regular, which reflects that the initial cell area is more likely to belong to the area of the glomerular cells.
Further, each pixel point on the edge of the initial cell area is marked as an edge pixel point; acquiring a normal vector of each edge pixel point, and acquiring a Euclidean distance between each edge pixel point and a mass center in the initial cell area; and obtaining the edge smoothness of the initial cell area according to the normal vector of each edge pixel point and the Euclidean distance between each edge pixel point and the mass center in the initial cell area. The obtaining of the euclidean distance is a well-known technique, and this embodiment will not be described in detail. As an example, the edge smoothness of the initial cell region may be calculated by the following formula:
In the method, in the process of the invention, An edge smoothness representing the initial cell region; /(I)Representing the number of all edge pixels in the initial cell region; /(I)Indicating the/>, within the initial cell regionNormal vector of each edge pixel point; /(I)Indicating the/>, within the initial cell regionThe Euclidean distance between each edge pixel point and the mass center in the initial cell area; /(I)Indicating the first cell regionNormal vector of each edge pixel point; /(I)Indicating the/>, within the initial cell regionThe Euclidean distance between each edge pixel point and the mass center in the initial cell area; /(I)Representing an exponential function based on natural constants, the examples employ/>Model to present inverse proportional relationship and normalization process,/>For model input, the implementer may choose the inverse proportion function and the normalization function according to the actual situation. Wherein if the edge smoothness of the initial cell region is larger, it indicates that the edge of the initial cell region changes smoothly, the shape of the initial cell region approaches to an ellipse, and the cell region is more likely to belong to the glomerular cell region reflecting the parameter.
Further, a reference cell area is presetWherein the present embodiment is described as/>To describe the example, the present embodiment is not particularly limited, wherein/>Depending on the particular implementation; the area of the initial cell region is determinedThe absolute value of the difference in (2) is referred to as the area difference value, and the inverse proportion normalization value of the area difference value is referred to as the cell area difference degree of the initial cell region. The present embodiment adopts/>The model presents the area and/>, of the initial cell regionNormalized value of inverse proportion of the difference value of (2)/>For model input, the implementer may choose the inverse proportion function and the normalization function according to the actual situation.
Further, the product of the region gray level consistency of the initial cell region, the edge smoothness of the initial cell region and the edge smoothness of the initial cell region is recorded as a kidney biopsy characteristic coefficient of the initial cell region; the kidney biopsy characterization coefficients of all initial cell areas were obtained.
To this end, the kidney biopsy characteristic coefficients of all the initial cell areas were obtained by the above method.
Step S003: and adjusting a gray scale interval according to the kidney biopsy characteristic coefficient, and optimizing and enhancing the gray scale image of each kidney biopsy slice.
Specifically, a threshold value of the characteristic coefficient of the kidney biopsy is presetWherein the present embodiment is described as/>To describe the example, the present embodiment is not particularly limited, wherein/>Depending on the particular implementation; the characteristic coefficient of the kidney biopsy is larger than the number/>Is designated as the target kidney biopsy cell region; the minimum gray value is marked as the minimum kidney biopsy gray value and the maximum gray value is marked as the maximum kidney biopsy gray value in the gray values of all pixel points in all target kidney biopsy cell areas; the gray value interval formed by the minimum kidney biopsy gray value and the maximum kidney biopsy gray value is marked as a kidney biopsy core gray value interval, the interval formed by all gray values before the kidney biopsy core gray value is marked as a first gray value interval, and the interval formed by all gray values after the kidney biopsy core gray value is marked as a second gray value interval.
Further, the first gray scale interval is taken as a gray scale value range [0, a ], the kidney biopsy core gray scale interval is taken as a gray scale value range [ a, b ], and the second gray scale interval is taken as a gray scale value range [ b, e ]; compressing the gray value range [0, a ] and the gray value range [ b, e ], linearly expanding the gray value range [ a, b ] to obtain an image after gray conversion, and marking the image as an optimized enhanced image of the gray image of the kidney biopsy slice; an optimized enhanced image of the gray-scale map of all kidney biopsy slices is acquired. The process of compressing the gray value ranges [0, a ] and [ b, e ] and linearly expanding the gray value ranges [ a, b ] to obtain the image after gray conversion is a well-known content of the application of piecewise linear gray conversion in molten pool edge extraction, and the embodiment is not repeated.
This embodiment is completed. Referring to fig. 3, a feature relation flow chart of a method for optimizing and enhancing images of a kidney biopsy slice is shown.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (6)
1. A method for optimizing and enhancing a kidney biopsy slice image, which is characterized by comprising the following steps:
Collecting a plurality of kidney biopsy slice gray level images;
Dividing the region of the gray level image of the kidney biopsy slice according to the change condition of the gray level value of the pixel point in the gray level image of the kidney biopsy slice to obtain a plurality of initial cell regions; obtaining a kidney biopsy characteristic coefficient of each initial cell region according to the overall gray level difference condition of different regions in the gray level map of the kidney biopsy slice, the shape arrangement difference condition on different edges in the same region and the region size difference condition;
adjusting a gray scale interval according to the kidney biopsy characteristic coefficient, and optimizing and enhancing the gray scale image of each kidney biopsy slice;
The specific method for obtaining the kidney biopsy characteristic coefficient of each initial cell area according to the overall gray scale difference condition of different areas in the gray scale map of the kidney biopsy slice, the shape arrangement difference condition on different edges in the same area and the area size difference condition comprises the following steps:
for any initial cell area, obtaining the area gray consistency of the initial cell area according to the distribution difference condition of gray values in the initial cell area;
Obtaining the edge smoothness of the initial cell area according to the distribution condition of the pixel points on the edge of the initial cell area;
Obtaining the cell area difference degree of the initial cell area according to the difference between the area size of the initial cell area and the ideal situation;
Marking the product of the regional gray level consistency of the initial cell region, the edge smoothness of the initial cell region and the edge smoothness of the initial cell region as a kidney biopsy characteristic coefficient of the initial cell region;
The method for obtaining the regional gray level consistency of the initial cell region according to the distribution difference condition of gray level values in the initial cell region comprises the following specific steps:
In the method, in the process of the invention, A region gray scale uniformity representing an initial cell region; /(I)Representing the average value of gray values of all pixel points in the initial cell area; /(I)Representing the number of all pixel points in the initial cell area; /(I)Represents the/>, in the initial cell regionGray values of the individual pixels; /(I)An exponential function that is based on a natural constant;
according to the distribution condition of the pixel points on the edge of the initial cell area, the edge smoothness of the initial cell area is obtained, and the specific method comprises the following steps:
Marking each pixel point on the edge of the initial cell area as an edge pixel point; acquiring a normal vector of each edge pixel point, and acquiring a Euclidean distance between each edge pixel point and a centroid in an initial cell area; according to the normal vector of each edge pixel point and the Euclidean distance between each edge pixel point and the mass center in the initial cell area, the edge smoothness of the initial cell area is obtained, and the specific formula is as follows:
In the method, in the process of the invention, Edge smoothness representing the initial cell area; /(I)Representing the number of all edge pixels in the initial cell area; /(I)Represents the/>, within the initial cell regionNormal vector of each edge pixel point; /(I)Represents the/>, within the initial cell regionThe Euclidean distance between each edge pixel point and the mass center in the initial cell area; /(I)Represents the/>, within the initial cell regionNormal vector of each edge pixel point; /(I)Represents the/>, within the initial cell regionThe Euclidean distance between each edge pixel point and the mass center in the initial cell area; /(I)An exponential function that is based on a natural constant;
The method for obtaining the cell area difference degree of the initial cell area according to the size difference condition of the area size of the initial cell area and the ideal condition comprises the following specific steps:
Presetting a reference cell area ; Area of initial cell region and/>The absolute value of the difference of (2) is denoted as the area difference value, and the inverse proportion normalization value of the area difference value is denoted as the cell area difference degree of the initial cell region.
2. The method for optimizing and enhancing the image of the kidney biopsy slice according to claim 1, wherein the method for dividing the gray level image of the kidney biopsy slice into a plurality of initial cell areas according to the change condition of the gray level value of the pixel point in the gray level image of the kidney biopsy slice comprises the following specific steps:
Inputting the grey level image of the kidney biopsy slice into a Canny edge detection algorithm to obtain an edge detection image of the kidney biopsy slice for any grey level image of the kidney biopsy slice; marking all pixels with gray values different from 0 in the kidney biopsy edge detection diagram as initial edge pixels; each closed region surrounded by all the initial edge pixel points in the kidney biopsy edge detection map is marked as an edge cell region, and the region with the same position as the edge cell region in the kidney biopsy slice gray scale map is marked as an initial cell region.
3. The method for optimizing and enhancing the image of the kidney biopsy slice according to claim 1, wherein the gray scale interval is adjusted according to the characteristic coefficient of the kidney biopsy slice, and each kidney biopsy slice gray scale image is optimized and enhanced, and the specific method comprises the following steps:
for any one of the grey-scale images of the kidney biopsy slices, presetting a threshold value of the kidney biopsy characteristic coefficient ; According to the threshold value/>, of the characteristic coefficient of renal biopsyScreening all initial cell areas in the gray level diagram of the kidney biopsy slice to obtain a plurality of target kidney biopsy cell areas;
the minimum gray value is marked as the minimum kidney biopsy gray value and the maximum gray value is marked as the maximum kidney biopsy gray value in the gray values of all pixel points in all target kidney biopsy cell areas; obtaining a kidney biopsy core gray scale interval, a first gray scale interval and a second gray scale interval according to the minimum kidney biopsy gray scale value and the maximum kidney biopsy gray scale value;
And carrying out gray level transformation according to the gray level interval, the first gray level interval and the second gray level interval of the kidney biopsy core to obtain an optimized enhanced image of the gray level image of the kidney biopsy slice.
4. A method for optimizing and enhancing a renal biopsy slice image as defined in claim 3, wherein said threshold value is based on a renal biopsy characteristic coefficientScreening all initial cell areas in a grey level chart of the kidney biopsy slice to obtain a plurality of target kidney biopsy cell areas, wherein the specific method comprises the following steps:
The characteristic coefficient of the kidney biopsy is greater than a plurality Is designated as the target kidney biopsy cell area.
5. The method for optimizing and enhancing the image of a kidney biopsy slice according to claim 3, wherein the obtaining the kidney biopsy core gray scale interval, the first gray scale interval and the second gray scale interval according to the minimum kidney biopsy gray scale value and the maximum kidney biopsy gray scale value comprises the following specific steps:
the gray value interval formed by the minimum kidney biopsy gray value and the maximum kidney biopsy gray value is marked as a kidney biopsy core gray value interval, the interval formed by all gray values before the kidney biopsy core gray value is marked as a first gray value interval, and the interval formed by all gray values after the kidney biopsy core gray value is marked as a second gray value interval.
6. The method for optimizing and enhancing the image of the kidney biopsy slice according to claim 3, wherein the method for optimizing and enhancing the image of the kidney biopsy slice gray level image by performing gray level transformation according to the kidney biopsy core gray level interval, the first gray level interval and the second gray level interval comprises the following specific steps:
taking the first gray scale interval as a gray scale value range [0, a ], taking the kidney biopsy core gray scale interval as a gray scale value range [ a, b ], and taking the second gray scale interval as a gray scale value range [ b, e ]; compressing the gray value range [0, a ] and the gray value range [ b, e ], linearly expanding the gray value range [ a, b ] to obtain an image after gray conversion, and marking the image as an optimized enhanced image of the gray image of the kidney biopsy slice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410391207.XA CN117974528B (en) | 2024-04-02 | 2024-04-02 | Kidney biopsy slice image optimization enhancement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410391207.XA CN117974528B (en) | 2024-04-02 | 2024-04-02 | Kidney biopsy slice image optimization enhancement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117974528A CN117974528A (en) | 2024-05-03 |
| CN117974528B true CN117974528B (en) | 2024-06-18 |
Family
ID=90864754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410391207.XA Active CN117974528B (en) | 2024-04-02 | 2024-04-02 | Kidney biopsy slice image optimization enhancement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117974528B (en) |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1405734A (en) * | 2002-10-28 | 2003-03-26 | 武汉大学 | A Method of Edge Enhancement for Medical Image |
| CN101275897A (en) * | 2008-03-06 | 2008-10-01 | 上海交通大学 | A method for identifying the characteristics of hematopoietic cells in bone marrow biopsy |
| EP3161787B1 (en) * | 2014-06-30 | 2018-06-13 | Ventana Medical Systems, Inc. | Detecting edges of a nucleus using image analysis |
| US10489903B2 (en) * | 2015-04-27 | 2019-11-26 | Wuhan Wuda Zoyon Science And Technology Co., Ltd. | Stepwise refinement detection method for pavement cracks |
| US10957041B2 (en) * | 2018-05-14 | 2021-03-23 | Tempus Labs, Inc. | Determining biomarkers from histopathology slide images |
| CN110490840B (en) * | 2019-07-11 | 2024-09-24 | 平安科技（深圳）有限公司 | Cell detection method, device and equipment for glomerular pathological section image |
| CN113393454A (en) * | 2021-07-02 | 2021-09-14 | 北京邮电大学 | Method and device for segmenting pathological target examples in biopsy tissues |
| CN117689600A (en) * | 2022-08-11 | 2024-03-12 | 宁德时代新能源科技股份有限公司 | Cell detection method, device, apparatus, readable storage medium and program product |
| CN115272346A (en) * | 2022-09-30 | 2022-11-01 | 江苏炜盛光电科技有限公司 | PCB production process online detection method based on edge detection |
| CN117058033A (en) * | 2023-08-17 | 2023-11-14 | 吉林省珵康医疗科技有限公司 | Glomerular pathology image enhancement method based on kidney biopsy slice |
| CN117422628B (en) * | 2023-12-18 | 2024-03-05 | 三亚中心医院(海南省第三人民医院、三亚中心医院医疗集团总院) | Optimized enhancement method for cardiac vascular ultrasonic examination data |
| CN117541482B (en) * | 2024-01-10 | 2024-03-26 | 中国人民解放军空军军医大学 | Cervical image enhancement system |
-
2024
- 2024-04-02 CN CN202410391207.XA patent/CN117974528B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 一种肾切片图像的肾小球边界增强滤波算法;朱虹 等;《中国生物医学工程学报》;20030830;第22卷(第4期);全文 * |
| 医学图像识别技术的研究;许朝晖;《中国优秀硕士论文全文数据库 信息科技辑》;20030615(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117974528A (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116152505B (en) | Bone target identification and segmentation method based on X-ray data | |
| CN114022872B (en) | Dynamic neural network-based method for identifying leaf diseases of various crops | |
| CN103295191A (en) | Multi-scale vision self-adaptation image enhancing method and evaluating method | |
| CN117408929A (en) | Tumor CT image area dynamic enhancement method based on image characteristics | |
| CN118115498B (en) | Method and system for rapidly detecting glossiness of titanium rod | |
| CN115359052A (en) | Medical image enhancement method based on clustering algorithm | |
| CN111402261B (en) | Improved skull segmentation method based on Hessian matrix enhancement | |
| CN115578660B (en) | Land block segmentation method based on remote sensing image | |
| CN117541582B (en) | IGBT insulation quality detection method for high-frequency converter | |
| CN117314940B (en) | Laser cutting part contour rapid segmentation method based on artificial intelligence | |
| CN116721099B (en) | Image segmentation method of liver CT image based on clustering | |
| CN116109933A (en) | Dynamic identification method for ecological restoration of abandoned mine | |
| CN117252893A (en) | Segmentation processing method for breast cancer pathological image | |
| CN117974528B (en) | Kidney biopsy slice image optimization enhancement method | |
| CN118314067B (en) | Tumor radio frequency accurate ablation system based on CT image | |
| CN117237245B (en) | Industrial material quality monitoring method based on artificial intelligence and Internet of things | |
| CN101897592A (en) | Method and device for extracting metallic foreign body from X-ray image | |
| CN117542488B (en) | Intelligent processing method for brain tumor CT data | |
| CN117934516A (en) | Automatic mitochondrial fluorescence image segmentation method and system | |
| CN117952974A (en) | Image processing method for organoid recognition | |
| CN117635718A (en) | Mine car positioning method and system based on image enhancement in low-light environment | |
| CN116645288A (en) | Improved homomorphic filtering and CLAHE-based infrared image enhancement method for photovoltaic panel | |
| CN118134919B (en) | Rapid extraction method of hand bones for bone age identification | |
| CN114820397B (en) | Image enhancement method and system based on attention degree | |
| CN107665487B (en) | A digital shape extraction and reconstruction method for image acquisition of model organisms |
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 |