CN114601483B - Bone age analysis method and system based on image processing - Google Patents
Bone age analysis method and system based on image processing Download PDFInfo
- Publication number
- CN114601483B CN114601483B CN202210506664.XA CN202210506664A CN114601483B CN 114601483 B CN114601483 B CN 114601483B CN 202210506664 A CN202210506664 A CN 202210506664A CN 114601483 B CN114601483 B CN 114601483B
- Authority
- CN
- China
- Prior art keywords
- radius
- period
- grade
- pixel points
- rectangular window
- 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
- 210000000988 bone and bone Anatomy 0.000 title claims abstract description 62
- 238000004458 analytical method Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 title claims abstract description 23
- 210000002745 epiphysis Anatomy 0.000 claims abstract description 46
- 230000004927 fusion Effects 0.000 claims abstract description 42
- 210000002411 hand bone Anatomy 0.000 claims abstract description 22
- 210000003275 diaphysis Anatomy 0.000 claims description 31
- 230000008859 change Effects 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 8
- 230000018109 developmental process Effects 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 8
- 230000000877 morphologic effect Effects 0.000 description 7
- 230000011164 ossification Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 210000000707 wrist Anatomy 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000012010 growth Effects 0.000 description 3
- 230000014461 bone development Effects 0.000 description 2
- 210000000845 cartilage Anatomy 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 210000004349 growth plate Anatomy 0.000 description 2
- 230000004660 morphological change Effects 0.000 description 2
- 230000003698 anagen phase Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/505—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of bone
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
-
- 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
- G06T7/60—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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Surgery (AREA)
- High Energy & Nuclear Physics (AREA)
- Theoretical Computer Science (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Optics & Photonics (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- General Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention relates to the field of artificial intelligence, in particular to a bone age analysis method and system based on image processing. Acquiring an image of a radius area, and extracting a radius contour edge to determine a radius period; when the radius is in a first period, comparing the epiphyseal width of the radius with a set threshold value, and judging the radius grade in the first period; when the radius is in the second period, performing curve fitting on the lower side edge pixel points of the epiphysis of the radius, and judging the radius grade in the second period; when the radius is in the third period, establishing a rectangular window, and obtaining the area of a highlight area formed by highlight pixel points in the rectangular window to calculate highlight fusion; acquiring the column number with the dark pixel points, calculating the dark fusion degree, and judging the grade of the radius in the third period; and estimating the bone age of different hand bones by integrating the grades of the radius at all times. The invention judges the bone age by dividing the radius period and judging the radius grade of each period, thereby improving the efficiency and the accuracy of judging the bone age grade.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a bone age analysis method and system based on image processing.
Background
In the process of growth and development of people, due to genetic and environmental influences, the individual development degree and speed of each person have obvious difference, and the individual development condition cannot be judged by the age alone. Therefore, it is proposed to reflect the degree of development by using physiological age.
The bone age represents the development degree of bones and can be used for representing the actual bone development condition of children. The judgment of the bone age is carried out on the basis of body bone X-ray films, wherein the left-hand X-ray films are most commonly used, the wrist bone age identification standard-Chinese human wrist bone development standard-Chinese 05-is established in China, and the bone age is judged by a counting method.
Therefore, the invention provides a bone age analysis method and system based on image processing, which can be used for comprehensively analyzing the bone age by classifying the radius by using the morphological characteristics of the radius and grading the characteristics of the radius in each period on the basis of extracting the radius area of the left-hand X-ray film image.
Disclosure of Invention
The invention provides a bone age analysis method and a bone age analysis system based on image processing, which aim to solve the existing problems and comprise the following steps: acquiring an image of a radius area, and extracting a radius contour edge to determine a radius period; when the radius is in a first period, comparing the epiphyseal width of the radius with a set threshold value, and dividing the radius grade of the first period; when the radius is in the second period, performing curve fitting on pixel points at the lower side edge of the epiphysis of the radius, and dividing the radius grade in the second period; when the radius is in the third period, establishing a rectangular window, and obtaining the area of a highlight area formed by highlight pixel points in the rectangular window to calculate highlight fusion; acquiring the column number with the dark pixel points to calculate the dark fusion degree, and grading the radius in the third period; and estimating the bone age of different hand bones by integrating the grades of the radius at all times.
According to the technical means provided by the invention, the radius is staged by utilizing the morphological characteristics of the radius, and the characteristics of the radius in each stage are digitized, so that the grades of the radius in different periods are accurately divided, the subjective judgment on the bone age can be effectively reduced, and the evaluation efficiency and accuracy on the bone age grade are improved.
The invention adopts the following technical scheme that a bone age analysis method based on image processing comprises the following steps:
acquiring a hand bone image, acquiring a radius area image in the hand bone image, extracting the contour edge of the radius, and determining the radius period according to the number of the extracted contour edges of the radius.
Classifying the radius grade of each period according to the determined radius period, wherein the method for classifying the radius grade of each period comprises the following steps:
when the confirmed radius is in the first period, the radius confirmed in the first period is graded by using the epiphyseal width and the diaphyseal width of the radius in the first period.
And when the confirmed radius is in the second period, acquiring all edge pixel points at the lower side of the epiphysis of the radius in the period, fitting all edge pixel points at the lower side of the epiphysis of the radius in the period to obtain a curve, and grading the radius in the second period according to the slope change of the curve.
And when the confirmed radius is in the third period, establishing a rectangular window by using the backbone of the radius in the third period, setting the size of the window according to the backbone width of the radius in the third period, and acquiring the highlight pixel points and the dark pixel points in the rectangular window according to the gray value of the pixel points in the rectangular window.
And calculating the area of a highlight region formed by all highlight pixel points in the rectangular window, and calculating highlight fusion according to the area of the highlight region and the area of the rectangular window.
And screening each column of pixel points in the rectangular window to obtain the column number of the dark pixel points, and calculating the dark fusion degree according to the column number of the dark pixel points in the rectangular window and the column number of all the pixel points in the rectangular window.
And grading the radius in the third period according to the obtained high light fusion degree and dark fusion degree.
And evaluating the bone age of the hand bones by using the determined period of the radius in the hand bones and the corresponding grade of the radius in the period.
Further, a bone age analysis method based on image processing extracts contour edges of a radius, and when the number of the extracted contour edges is one, the radius in the radius area image is the radius in the third period; when the number of the extracted contour edges is two, the radius in the radius area image is the first period radius or the second period radius.
Further, when the number of the extracted contour edges is two, the two contours are respectively an epiphyseal contour and a diaphyseal contour, and the width of the epiphyseal contour and the width of the diaphyseal contour are compared:
when the epiphysis contour width is larger than the diaphysis contour width, the radius in the radius area image is the radius in the second period;
when the diaphyseal contour width is larger than the epiphyseal contour width, the radius in the radius area image is the first-stage radius.
Further, a bone age analysis method based on image processing, a method for grading the radius at the first time period is as follows:
setting a threshold value by using the diaphysis width of the radius in the first time period
According to the set threshold value and the epiphyseal width of the radius in the first period of time
And (3) comparison:
when in use
Then, the radius grade of the first period is grade 1;
when in use
When the first period radius grade is grade 2;
when in use
When the first period radius grade is grade 3;
when in use
Then, the radius grade of the first period is 4 grade;
when in use
Then, the radius grade of the first period is grade 5;
when in use
The first time period radius grade is 6.
Further, a bone age analysis method based on image processing, the method for classifying the radius grade of the second period comprises the following steps:
performing polynomial curve fitting on all edge points on the lower side of the epiphysis of the radius in the second period to obtain an edge curve on the lower side, sequentially calculating the slope corresponding to each edge point on the curve, and judging the grade of the radius in the second period according to the change trend of the slope of the edge points:
when the change trend of the slope of the edge point is flat, the radius grade of the second period is 7 grades;
when the change trend of the slope of the edge point is changed from large to small until the slope is flat, the radius grade in the second period is 8 grades;
when the change trend of the slope of the edge point is gradual from large to small, the slope is increased from small to large again, and the radius grade in the second period is 9 grades.
Further, a bone age analysis method based on image processing obtains highlight fusion according to the ratio of the area of a highlight region formed by highlight pixels in a rectangular window of radius in the third period to the area of the rectangular window
(ii) a Obtaining the dark fusion degree according to the ratio of the number of lines with dark pixels in the rectangular window to the number of lines with all pixels in the rectangular window
。
Further, a bone age analysis method based on image processing, the method for classifying the radius grade of the third period is as follows:
when P is present L Not less than 60% and not more than 0 and not more than P B When the percentage is less than 20 percent, the radius grade of the third period is 10 grade;
when 60% < P L P is less than or equal to 70 percent and less than or equal to 20 percent B When the percentage is less than 40%, the radius grade of the third period is 11 grade;
when 70% < P L P is not less than 80 percent and not more than 40 percent B When the percentage is less than 60%, the radius grade of the third period is 12 grade;
when 80% < P L P is not less than 90 percent and not more than 60 percent B When the rate is less than 80%, the radius grade of the third period is 13 grade;
when P is present L P is more than 90 percent and more than or equal to 80 percent B < 100%, the radius grade at the third stage was 14.
An image processing based bone age analysis system comprising: the device comprises a radius period determining module, a first period radius grade dividing module, a second period radius grade dividing module, a third period radius grade dividing module and a comprehensive bone age evaluating module;
the radius period determining module is used for acquiring the hand bone image, acquiring a radius region image in the hand bone image, extracting the radius contour edge and judging the radius period according to the number of the extracted radius contour edges;
the first period radius grading module is used for grading the radius determined as the first period by using the epiphysis width and the diaphysis width of the radius at the period;
the second-period radius grading module is used for obtaining all edge pixel points on the lower side of the epiphysis of the radius in the period, fitting all edge pixel points on the lower side of the epiphysis of the radius in the period to obtain a curve, and grading the radius in the second period according to the slope change of the curve;
the radius grade division module in the third period is used for establishing a rectangular window by using the backbone of the radius in the third period, setting the size of the window according to the backbone width of the radius in the third period, and acquiring highlight pixel points and dark pixel points in the rectangular window according to the gray value of the pixel points in the rectangular window;
calculating the area of a highlight region formed by all highlight pixel points in the rectangular window, and calculating highlight fusion according to the area of the highlight region and the area of the rectangular window;
screening each column of pixel points in the rectangular window to obtain the column number of the dark pixel points, and calculating the dark fusion degree according to the column number of the dark pixel points in the rectangular window and the column number of all the pixel points in the rectangular window;
grading the radius in the third period according to the obtained high-brightness fusion degree and dark fusion degree;
and the comprehensive bone age evaluation module is used for comprehensively evaluating the hand bone ages in different periods by integrating the radius grades in each period respectively obtained by the first period radius grade dividing module, the second period radius grade dividing module and the third period radius grade dividing module.
The invention has the beneficial effects that: according to the technical means provided by the invention, the radius is staged by utilizing the morphological characteristics of the radius, and the characteristics of the radius in each stage are digitized, so that the grades of the radius in different periods are accurately divided, the subjective judgment on the bone age can be effectively reduced, and the evaluation efficiency and accuracy on the bone age grade are improved.
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, and 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 these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a bone age analysis method based on image processing according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a bone age analysis system based on image processing according to an embodiment of the present invention;
fig. 3 is a schematic illustration of a radius grade and age control of the embodiment of the invention of fig. 1.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a bone age analysis method based on image processing according to an embodiment of the present invention includes:
101. the method comprises the steps of collecting a hand bone image, obtaining a radius area image in the hand bone image, extracting the radius contour edge, and determining the radius period according to the number of the extracted radius contour edges.
The present invention is directed to the following scenarios: in the process of evaluating the bone age, the radius area of the X-ray film of the left hand is firstly distinguished, and the bone age is judged according to the morphological characteristics of the epiphysis and the diaphysis of the radius and the fusibility between the epiphysis and the diaphysis of the radius. Therefore, the judgment of the age of the radius needs to be realized by extracting the radius area of the X-ray film of the left hand and acquiring the morphological characteristics of epiphysis and diaphysis of the radius, so that the efficiency of the doctor in judging the grade of the age of the radius is improved, and a reference is provided for the judgment of the age of the radius.
The invention needs to obtain the image of the radius area through the X-ray film image of the left hand, so the radius needs to be extracted first, and the area outside the radius needs to be removed.
The invention adopts a DNN semantic segmentation method to segment the radius in the left-hand X-ray film image.
The content of the DNN semantic segmentation network of the invention is as follows:
the left-hand X-ray film image of the hospital is collected as a data set for semantic segmentation.
The X-ray data set is labeled manually, pixels needing to be segmented in the network are a background class and a wrist class, pixels at corresponding positions belong to the background class (such as phalanges, metacarpals and the like) and are labeled with 0, and pixels belonging to the radius class (such as radius epiphysis and diaphysis) are labeled with 1.
Since the task of the network is classification, a cross entropy loss function is adopted as the loss function of the network.
Because the image after semantic segmentation is only a rough boundary and may contain the cartilage tissue of the palm, the invention constructs the radius mask according to the prior knowledge: the invention adopts OTSU threshold segmentation and region growing algorithm to reprocess the image after semantic segmentation, because the possible noise, other bone tissues and the density of the same bone are different, the morphological close operation is carried out on the image which is subjected to the region merging algorithm, and a connected domain with the largest area is reserved, thus finally obtaining the complete radius mask.
The morphological change of the ossification center of the radius can be used as the basis for judging the bone age, the change sequence and the morphology of the ossification center are basically the same among different individuals, and the ossification center is determined according to the evaluation standard of the radius age in Chinese human wrist development Standard-China 05: the occurrence of ossification center of radius indicates that cartilage of the ossification center begins to be converted into bone tissue, namely radius 1 grade; the epiphysis of the radius is small and large (a major variable feature), with morphological changes, i.e. radius grade 2-6; the appearance of bony landmarks, shape changes (a major variable feature), with progressively larger epiphyses, i.e. radius 7-9 grades; fusion of the radial epiphysis and the radial diaphysis, i.e., radius grade 10-14.
Therefore, according to the shape change of the radius epiphysis and diaphysis in different periods, the radius is divided into 3 periods: 1. epiphyseal growth phase (grade 1-6); 2. epiphyseal change phase (grade 7-9); 3. epiphyseal diaphyseal fusion stage (grade 10-14).
Namely, the radius corresponding to the first period is the epiphyseal growth period, the radius corresponding to the second period is the epiphyseal change period, and the radius corresponding to the third period is the epiphyseal fusion period.
The outline of the mask is extracted by performing a global scan of pixels of a mask image of the radius from top to bottom and from left to right, recording a point where a change in pixel value occurs (if the pixel value of the point is 1, but the pixel value of the next point is 0, recording the coordinates of the point whose pixel value is 1, and if the pixel value of the point is 0, but the pixel value of the next point is 1, recording the coordinates of the point whose pixel value is 1).
Extracting the contour edges of the radius, wherein when the number of the extracted contour edges is one, the radius in the radius area image is the radius in the third period; when the number of the extracted contour edges is two, the radius in the radius area image is the first period radius or the second period radius.
When the number of the extracted contour edges is two, further analyzing the existence of two contour edges, respectively calculating the distance values of edge points (namely, the leftmost point and the rightmost point) of two contours (epiphysis and diaphysis), wherein the two contours are respectively an epiphysis contour and a diaphysis contour, and comparing the width of the epiphysis contour with the width of the diaphysis contour:
when the epiphysis contour width is larger than the diaphysis contour width, the radius in the radius area image is the radius in the second period;
when the diaphyseal contour width is larger than the epiphyseal contour width, the radius in the radius area image is the first-stage radius.
102. When the determined radius is in the first period, calculating the epiphyseal width and the diaphyseal width of the radius in the first period, setting a threshold value by using the diaphyseal width of the radius in the first period, comparing the epiphyseal width of the radius in the first period with the set threshold value, and grading the radius in the first period according to the comparison result.
According to the evaluation standard of the age of the radius in Chinese human hand carpal development Standard-China 05, the characteristic that the radius changes most in the growing period of the radius epiphysis is the widening of the radius epiphysis, so the invention extracts the characteristic in the growing period of the radius epiphysis according to the difference between the epiphysis and the diaphysis.
The obtained leftmost edge point (x) of the epiphysis 11 ，y 11 ) Rightmost edge point (x) 12 ，y 12 ) And the leftmost edge point (x) of the backbone 21 ，y 21 ) Rightmost edge point (x) 22 ，y 22 ) Calculating epiphyseal width
And width of backbone
And judging the bone age of the epiphyseal growth period by comparing the difference between the two.
The method for grading the radius in the first period comprises the following steps:
by usingSetting threshold value for diaphysis width of radius in first time period
According to the set threshold value and the epiphyseal width of the radius in the first period of time
And (3) comparison:
when in use
When the radius grade of the first period is grade 1;
when in use
When the first period radius grade is grade 2;
when in use
Then, the radius grade of the first period is grade 3;
when in use
Then, the radius grade of the first period is 4 grade;
when in use
When the first period radius grade is 5 grade;
when in use
Then, the radius grade of the first period is 6 grade;
103. and when the determined radius is in the second period, acquiring all edge pixel points at the lower side of the epiphysis of the radius in the second period, performing curve fitting on all edge pixel points at the lower side of the epiphysis of the radius in the second period, and grading the radius in the second period according to the change of the slope of the curve.
According to the evaluation standard of the age of the radius bone of Chinese staff carpal development standard-China 05, the biggest change in the radius in the epiphyseal change stage is that the epiphyseal and the diaphysis are closer and closer, and the epiphyseal gradually covers the diaphysis at one side (usually the inner side) or two sides to present a state of starting fusion. Therefore, the invention divides the epiphyseal change period according to the curve characteristic of the lower part of the epiphyseal part (the side close to the diaphysis).
And performing polynomial curve fitting on all edge points on the lower side of the epiphysis to obtain an edge curve Y on the lower side, sequentially calculating the slope of each edge point on the curve, and judging the bone age by comparing the distribution of the slopes of the curve.
The curve Y is formulated as:
slope k of each edge point on curve Y i ：
Wherein A, B, C are coefficients of polynomial fitting,
is the x-coordinate of a point on the edge, to
Establishing a coordinate system for the ordinate and x for the abscissa by comparing points of the edge
The trend of change was evaluated for bone age.
The method for classifying the radius grade of the second period comprises the following steps:
performing polynomial curve fitting on all edge points on the lower side of the epiphysis of the radius in the second period to obtain an edge curve on the lower side, sequentially calculating the slope corresponding to each edge point on the curve, and dividing the radius grade in the second period according to the change trend of the slope of the edge points:
when the change trend of the slope of the edge point is flat, the radius grade of the second period is 7 grades;
when the change trend of the slope of the edge point is changed from large to small until the slope is flat, the radius grade in the second period is 8 grades;
when the change trend of the slope of the edge point is gradual from large to small, the slope of the edge point is gradually increased from small to large, and the radius grade in the second period is 9 grades.
104. And when the determined radius is in the third period, establishing a rectangular window by using the backbone of the radius in the third period, setting the size of the window according to the backbone width of the radius in the third period, and acquiring the highlight pixel points and the dark pixel points in the rectangular window according to the gray value of the pixel points in the rectangular window.
The epiphyseal diaphysis fusion period is mainly characterized in that a epiphyseal cartilage plate is arranged between epiphyses and diaphyses, a left-hand X-ray film shows a ghost image in a highlight area, and a black dark band is arranged, so that the epiphyses and the diaphyses are connected into a whole along with continuous proliferation of the epiphyseal cartilage plate.
The X-ray film appears in this process as: the dark band gradually decreased and disappeared. In the process of fusing the double images of the highlight area, the area is gradually reduced until the double images disappear, the method extracts the double images according to the gray characteristic value of the radius epiphysis diaphysis fusion period, and the age grade of the radius is divided.
Obtaining a point of which the leftmost edge point of the diaphysis of the radius in the third period is the length of the rectangle side, and taking the point upwards
Line 4, take down
Line 5, length of
(distance between the leftmost edge point and the most lateral edge point of the diaphysis), a rectangular window is created containing the epiphyseal cartilaginous plate, part of the epiphyses and the diaphysis.
And calculating the area of a highlight region formed by all the highlight pixel points, and calculating the highlight fusion according to the area of the highlight region and the area of the rectangular window.
For highlight areas: establishing a gray histogram for pixel points in a rectangular window for threshold segmentation, setting the point with the gray value larger than 245 as 1, setting the point with the gray value smaller than 245 as 0, performing threshold segmentation on the image in the rectangular frame, wherein the area with the pixel point value of 1 is a highlight area on the radius, and calculating the area S of the highlight area L (the number of pixel points with a pixel value of 1) and the area S of the rectangular frame, thereby obtaining the epiphyseal skeleton highlight fusion degree P L The expression is:
and screening each column of pixel points in the rectangular window to obtain the column number of the dark pixel points, and calculating the dark fusion degree according to the column number of the dark pixel points in the rectangular window and the column number of all the pixel points in the rectangular window.
For black dark bands: since the black dark band in the rectangular window is a sequence with smaller gray value, the bone age grade is judged by searching the area size of the black dark band.
The method comprises the steps of enabling gray values to be sharply reduced to be represented as black dark bands in an image, scanning pixel points in a rectangular window row by row, setting a counter n, recording only the first point with sharply reduced gray values (the gray value difference between the previous point and the next point is larger than 50) appearing in the window, and adding 1 to the counter if the pixel points in the row show stores with sharply reduced gray values.
The dark fusion degree of epiphysis diaphysis is calculated by acquiring the column number of dark pixel points in all the column pixel points and the total column number in the rectangular window
The expression is:
wherein n is the number of columns with dark pixels.
Obtaining the highlight fusion degree according to the ratio of the area of the highlight region formed by the highlight pixel points in the rectangular window of the radius in the third period to the area of the rectangular window
(ii) a Obtaining the dark fusion degree according to the ratio of the number of lines with dark pixels in the rectangular window to the number of lines with all pixels in the rectangular window
。
And grading the radius in the third period according to the obtained high light fusion degree and dark fusion degree.
The method for classifying the radius grade in the third period comprises the following steps:
when P is L Not less than 60% and not more than 0 and not more than P B When the percentage is less than 20 percent, the radius grade of the third period is 10 grade;
when 60% < P L P is less than or equal to 70 percent and less than or equal to 20 percent B When the percentage is less than 40%, the radius grade of the third period is 11 grade;
when 70% < P L P is not less than 80 percent and not more than 40 percent B When the percentage is less than 60%, the radius grade of the third period is 12 grade;
when 80% < P L P is not less than 90 percent and not more than 60 percent B If the radius grade is less than 80%, the radius grade in the third period is 13 grade;
when P is present L P is more than 90 percent and more than or equal to 80 percent B < 100%, the radius grade at the third stage was 14.
105. And estimating the bone age of different hand bones by integrating the grades of the radius at all times.
As shown in fig. 3, a schematic diagram of comparison between radius grade and bone age according to an embodiment of the present invention is given, so that after grade determination is performed on morphological features of radius epiphysis and diaphysis in a radius image, bone age determination is achieved, efficiency of bone age grade determination by a doctor is improved, and reference is provided for bone age determination.
As shown in fig. 2, a schematic flow chart of a bone age analysis system based on image processing according to an embodiment of the present invention is provided, including: the device comprises a radius period determining module, a first period radius grade dividing module, a second period radius grade dividing module, a third period radius grade dividing module and a comprehensive bone age evaluating module;
the radius period determining module is used for acquiring the hand bone image, acquiring a radius region image in the hand bone image, extracting the radius contour edge and judging the radius period according to the number of the extracted radius contour edges;
the first period radius grading module is used for grading the radius determined as the first period by using the epiphysis width and the diaphysis width of the radius at the period;
the second-period radius grading module is used for obtaining all edge pixel points on the lower side of the epiphysis of the radius in the period, fitting all edge pixel points on the lower side of the epiphysis of the radius in the period to obtain a curve, and grading the radius in the second period according to the slope change of the curve;
the radius grade division module in the third period is used for establishing a rectangular window by using the backbone of the radius in the third period, setting the size of the window according to the backbone width of the radius in the third period, and acquiring highlight pixel points and dark pixel points in the rectangular window according to the gray value of the pixel points in the rectangular window;
calculating the area of a highlight region formed by all highlight pixel points in the rectangular window, and calculating highlight fusion according to the area of the highlight region and the area of the rectangular window;
screening each column of pixel points in the rectangular window to obtain the column number of the dark pixel points, and calculating the dark fusion degree according to the column number of the dark pixel points in the rectangular window and the column number of all the pixel points in the rectangular window;
grading the radius in the third period according to the obtained high-brightness fusion degree and dark fusion degree;
and the comprehensive bone age evaluation module is used for comprehensively evaluating the hand bone ages in different periods by integrating the radius grades in each period respectively obtained by the first period radius grade dividing module, the second period radius grade dividing module and the third period radius grade dividing module.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A bone age analysis method based on image processing is characterized by comprising the following steps:
acquiring a hand bone image, acquiring a radius area image in the hand bone image, extracting the radius contour edge, and determining the radius period according to the number of the extracted radius contour edges;
classifying the radius grade of each period according to the determined radius period, wherein the method for classifying the radius grade of each period comprises the following steps:
when the confirmed radius is in a first period, grading the radius confirmed to be in the first period by using the epiphysis width and the diaphysis width of the radius in the first period;
when the confirmed radius is in the second period, acquiring all edge pixel points on the lower side of the epiphysis of the radius in the second period, fitting all edge pixel points on the lower side of the epiphysis of the radius in the second period to obtain a curve, and grading the radius in the second period according to the slope change of the curve;
when the confirmed radius is in a third period, establishing a rectangular window by using the backbone of the radius in the third period, setting the size of the window according to the backbone width of the radius in the third period, and acquiring highlight pixel points and dark pixel points in the rectangular window according to the gray value of the pixel points in the rectangular window;
calculating the area of a highlight region formed by all highlight pixel points in the rectangular window, and calculating highlight fusion according to the area of the highlight region and the area of the rectangular window;
screening each column of pixel points in the rectangular window to obtain the column number of the dark pixel points, and calculating the dark fusion degree according to the column number of the dark pixel points in the rectangular window and the column number of all the pixel points in the rectangular window;
grading the radius in the third period according to the obtained high-brightness fusion degree and dark fusion degree;
and evaluating the bone age of the hand bones by using the determined period of the radius in the hand bones and the corresponding grade of the radius in the period.
2. The method for analyzing bone age based on image processing as claimed in claim 1, wherein contour edges of radius are extracted, and when the number of the extracted contour edges is one, the radius in the radius area image is a radius in a third period; and when the number of the extracted contour edges is two, the radius in the radius area image is the first period radius or the second period radius.
3. The method of claim 2, wherein when the number of extracted contour edges is two, the two contours are an epiphyseal contour and a diaphyseal contour, respectively, and the width of the epiphyseal contour and the width of the diaphyseal contour are compared:
when the epiphyseal contour width is larger than the diaphyseal contour width, the radius in the radius area image is the radius in the second period;
when the diaphyseal contour width is larger than the epiphyseal contour width, the radius in the radius area image is the first-stage radius.
4. The bone age analysis method based on image processing as claimed in claim 1, wherein the method for grading the radius at the first period comprises:
setting a threshold value by using the diaphysis width of the radius in the first time period
According to a set threshold and a first time periodEpiphyseal width of bone
A comparison is made wherein
Represents the diaphyseal width of the radius during the first period;
when in use
Then, the radius grade of the first period is grade 1;
when in use
When the first period radius grade is grade 2;
when in use
Then, the radius grade of the first period is grade 3;
when the temperature is higher than the set temperature
Then, the radius grade of the first period is 4 grade;
when in use
Then, the radius grade of the first period is grade 5;
when in use
The first time period radius grade is 6.
5. The bone age analysis method based on image processing as claimed in claim 1, wherein the method for classifying the radius grade of the second period is as follows:
performing polynomial curve fitting on all edge points on the lower side of the epiphysis of the radius in the second period to obtain an edge curve on the lower side, sequentially calculating the slope corresponding to each edge point on the curve, and judging the grade of the radius in the second period according to the change trend of the slope of the edge points:
when the change trend of the slope of the edge point is flat, the radius grade of the second period is 7 grades;
when the change trend of the slope of the edge point is changed from large to small until the slope is flat, the radius grade in the second period is 8 grades;
when the change trend of the slope of the edge point is gradual from large to small, the slope is increased from small to large again, and the radius grade in the second period is 9 grades.
6. The method of claim 1, wherein the highlight fusion degree is obtained according to a ratio of a highlight region area formed by highlight pixels to an area of a rectangular window in the radius of the third period
(ii) a Obtaining the dark fusion degree according to the ratio of the number of lines with dark pixels in the rectangular window to the number of lines with all pixels in the rectangular window
。
7. The bone age analysis method based on image processing as claimed in claim 6, wherein the method for classifying the radius grade of the third period is as follows:
when P is L Not less than 60% and not more than 0 and not more than P B When the percentage is less than 20 percent, the radius grade of the third period is 10 grade;
when 60% < P L P is less than or equal to 70 percent and less than or equal to 20 percent B When the percentage is less than 40%, the radius grade of the third period is 11 grade;
when 70% < P L Not less than 80% and not more than 40% of P B When the percentage is less than 60%, the radius grade of the third period is 12 grade;
when 80% < P L Not less than 90% and not less than 60% of P B < 80%, the third period radius was rated13 stages;
when P is present L P is more than 90 percent and more than or equal to 80 percent B < 100%, the radius grade at the third stage was 14.
8. An image processing-based bone age analysis system, comprising: the device comprises a radius period determining module, a first period radius grade dividing module, a second period radius grade dividing module, a third period radius grade dividing module and a comprehensive bone age evaluating module;
the radius period determining module is used for acquiring the hand bone image, acquiring a radius region image in the hand bone image, extracting the radius contour edge and judging the radius period according to the number of the extracted radius contour edges;
the first period radius grading module is used for grading the radius determined as the first period by using the epiphysis width and the diaphysis width of the radius at the period;
the second-period radius grading module is used for obtaining all edge pixel points on the lower side of the epiphysis of the radius in the period, fitting all edge pixel points on the lower side of the epiphysis of the radius in the period to obtain a curve, and grading the radius in the second period according to the slope change of the curve;
the radius grade division module in the third period is used for establishing a rectangular window by using the backbone of the radius in the third period, setting the size of the window according to the backbone width of the radius in the third period, and acquiring highlight pixel points and dark pixel points in the rectangular window according to the gray value of the pixel points in the rectangular window;
calculating the area of a highlight region formed by all highlight pixel points in the rectangular window, and calculating highlight fusion according to the area of the highlight region and the area of the rectangular window;
screening each column of pixel points in the rectangular window to obtain the column number of the dark pixel points, and calculating the dark fusion degree according to the column number of the dark pixel points in the rectangular window and the column number of all the pixel points in the rectangular window;
grading the radius in the third period according to the obtained high-brightness fusion degree and dark fusion degree;
and the comprehensive bone age evaluation module is used for comprehensively evaluating the hand bone ages in different periods by integrating the radius grades in each period respectively obtained by the first period radius grade dividing module, the second period radius grade dividing module and the third period radius grade dividing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210506664.XA CN114601483B (en) | 2022-05-11 | 2022-05-11 | Bone age analysis method and system based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210506664.XA CN114601483B (en) | 2022-05-11 | 2022-05-11 | Bone age analysis method and system based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114601483A CN114601483A (en) | 2022-06-10 |
| CN114601483B true CN114601483B (en) | 2022-08-16 |
Family
ID=81869288
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210506664.XA Active CN114601483B (en) | 2022-05-11 | 2022-05-11 | Bone age analysis method and system based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114601483B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115049678A (en) * | 2022-08-17 | 2022-09-13 | 南昌工程学院 | Transmission line corona discharge image segmentation method based on night ultraviolet imaging technology |
| CN116402824B (en) * | 2023-06-09 | 2023-10-03 | 山东第一医科大学第二附属医院 | Endocrine abnormality detection method based on children bone age X-ray film |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325734A (en) * | 2020-02-25 | 2020-06-23 | 杭州电子科技大学 | Bone age prediction method and device based on visual model |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100942050B1 (en) * | 2007-09-19 | 2010-02-11 | 한양대학교 산학협력단 | Apparatus and Method for extracting Epiphysis image |
| KR100864434B1 (en) * | 2007-10-05 | 2008-10-20 | 길호석 | An apparatus for measuring bone age |
| CN102945545A (en) * | 2012-10-18 | 2013-02-27 | 重庆医科大学 | Method for preprocessing robust skeletal age evaluation image and positioning skeletal key point |
| CN107895367B (en) * | 2017-11-14 | 2021-11-30 | 中国科学院深圳先进技术研究院 | Bone age identification method and system and electronic equipment |
| CN108836338A (en) * | 2018-04-04 | 2018-11-20 | 浙江康体汇科技有限公司 | A kind of calculating of online stone age and prediction of height method based on web database |
| CN108968991B (en) * | 2018-05-08 | 2022-10-11 | 平安科技（深圳）有限公司 | Hand bone X-ray film bone age assessment method, device, computer equipment and storage medium |
| CN109215013B (en) * | 2018-06-04 | 2023-07-21 | 平安科技（深圳）有限公司 | Automatic bone age prediction method, system, computer device and storage medium |
| CN109377484B (en) * | 2018-09-30 | 2022-04-22 | 杭州依图医疗技术有限公司 | Method and device for detecting bone age |
| CN109300150B (en) * | 2018-10-16 | 2021-10-29 | 杭州电子科技大学 | Hand bone X-ray image texture feature extraction method for bone age assessment |
| CN109741309B (en) * | 2018-12-27 | 2021-04-02 | 北京深睿博联科技有限责任公司 | Bone age prediction method and device based on deep regression network |
| CN110503624A (en) * | 2019-07-02 | 2019-11-26 | 平安科技（深圳）有限公司 | Stone age detection method, system, equipment and readable storage medium storing program for executing |
| CN110782450B (en) * | 2019-10-31 | 2020-09-29 | 北京推想科技有限公司 | Hand carpal development grade determining method and related equipment |
| CN110853003B (en) * | 2019-10-31 | 2020-07-24 | 北京推想科技有限公司 | Hand epiphysis development grade determination method and related equipment |
| KR102380873B1 (en) * | 2020-01-30 | 2022-03-31 | 경기대학교 산학협력단 | Device and method for estimating bone age automatically |
| CN111402213B (en) * | 2020-03-05 | 2023-10-27 | 北京深睿博联科技有限责任公司 | Bone age evaluation method and device, electronic equipment and computer readable storage medium |
| CN113331849A (en) * | 2021-06-08 | 2021-09-03 | 北京中医药大学 | Ulna bone age grade assessment system and method |
| CN113570618B (en) * | 2021-06-28 | 2023-08-08 | 内蒙古大学 | Weighted bone age assessment method and system based on deep learning |
-
2022
- 2022-05-11 CN CN202210506664.XA patent/CN114601483B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325734A (en) * | 2020-02-25 | 2020-06-23 | 杭州电子科技大学 | Bone age prediction method and device based on visual model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114601483A (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114601483B (en) | Bone age analysis method and system based on image processing | |
| CN109961049B (en) | Cigarette brand identification method under complex scene | |
| CN110084803B (en) | Fundus image quality evaluation method based on human visual system | |
| CN108416360B (en) | Cancer diagnosis system and method based on breast molybdenum target calcification features | |
| CN106340016B (en) | A kind of DNA quantitative analysis method based on microcytoscope image | |
| Harangi et al. | Automatic detection of the optic disc using majority voting in a collection of optic disc detectors | |
| Manos et al. | Segmenting radiographs of the hand and wrist | |
| CN116542966B (en) | Intelligent bone age analysis method for children endocrine abnormality detection | |
| CN112308822A (en) | Intervertebral disc CT image detection method based on deep convolutional neural network | |
| CN113139977B (en) | Mouth cavity curve image wisdom tooth segmentation method based on YOLO and U-Net | |
| CN110310291A (en) | A kind of rice blast hierarchy system and its method | |
| CN116246174B (en) | Sweet potato variety identification method based on image processing | |
| CN109871900A (en) | The recognition positioning method of apple under a kind of complex background based on image procossing | |
| CN115294377A (en) | System and method for identifying road cracks | |
| CN101404062A (en) | Automatic screening method for digital galactophore image based on decision tree | |
| Chithra et al. | Otsu's Adaptive Thresholding Based Segmentation for Detection of Lung Nodules in CT Image | |
| CN115841600B (en) | Deep learning-based sweet potato appearance quality classification method | |
| Vyshnavi et al. | Breast density classification in mammogram images | |
| CN115661187A (en) | Image enhancement method for Chinese medicinal preparation analysis | |
| WO2021139447A1 (en) | Abnormal cervical cell detection apparatus and method | |
| CN114049345A (en) | Liver CT image classification method based on data set | |
| CN113763407A (en) | Ultrasonic image nodule edge analysis method | |
| Mohammed et al. | Osteoporosis detection using convolutional neural network based on dual-energy X-ray absorptiometry images | |
| CN111354000A (en) | Automatic segmentation method for articular cartilage tissue in three-dimensional medical image | |
| CN117893530B (en) | Throat image analysis system based on artificial intelligence |
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 |