CN117218091B - Fracture line extraction method for fracture map construction - Google Patents
Fracture line extraction method for fracture map construction Download PDFInfo
- Publication number
- CN117218091B CN117218091B CN202311213604.XA CN202311213604A CN117218091B CN 117218091 B CN117218091 B CN 117218091B CN 202311213604 A CN202311213604 A CN 202311213604A CN 117218091 B CN117218091 B CN 117218091B
- Authority
- CN
- China
- Prior art keywords
- fracture
- line
- femur neck
- fracture line
- femur
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 15
- 238000000605 extraction Methods 0.000 title claims abstract description 13
- 210000002436 femur neck Anatomy 0.000 claims abstract description 120
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 206010017076 Fracture Diseases 0.000 claims description 256
- 208000010392 Bone Fractures Diseases 0.000 claims description 250
- 208000020089 femoral neck fracture Diseases 0.000 claims description 32
- 239000011159 matrix material Substances 0.000 claims description 21
- 230000007547 defect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 210000000689 upper leg Anatomy 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 2
- 101150039322 outE gene Proteins 0.000 claims 1
- 230000008439 repair process Effects 0.000 abstract description 5
- 238000011960 computer-aided design Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010020462 Humerus fracture Diseases 0.000 description 1
- 208000001132 Osteoporosis Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000399 orthopedic effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
- Surgical Instruments (AREA)
Abstract
The invention discloses a fracture line extraction method for fracture map construction, and belongs to the technical field of computer aided design. The method comprises the following steps: step one: preprocessing a femur neck fracture image; step two: constructing a femur neck fracture line trend template; step three: extracting femur neck fracture line; step four: drawing a femur neck fracture map according to the femur neck fracture line. According to the continuity and the directionality of the femur neck fracture line, the trend of the femur neck fracture line is designed, trend templates matched with the trends are respectively defined, and the trend templates are matched with fracture lines to repair the fuzzy, missing and other areas in the fracture image. Meanwhile, the fracture line detection method based on the adjustable circle is provided, and the rapid detection of the fracture line is realized. The method has the characteristics of simplicity, flexibility, high efficiency and the like, provides a new method for extracting the femur neck fracture line, and has important significance for constructing the fracture map.
Description
Technical Field
The invention relates to a fracture line extraction method for fracture map construction, and belongs to the technical field of computer aided design.
Background
Fracture maps, i.e. "fracture line distribution maps", were first proposed by the university of minnesota orthopedics research team in 2009. In the construction of fracture map, the fracture lines of a plurality of cases are superimposed on a standard bone model through computer image simulation, so that the fracture characteristics are intuitively and quantitatively displayed. The fracture map provides scientific basis for fracture diagnosis, treatment scheme selection, implant design and fracture standardization model establishment. The current research of fracture map mainly focuses on pilot fracture, posterior condylar fracture, hoffa fracture, tibial plateau fracture, proximal humerus fracture and the like. Femoral neck fractures are the most common injuries to the hip, meaning fractures from the lower femoral head to the base of the femoral neck. In particular, in recent years, as people's lifestyle changes and the incidence of osteoporosis increases, patients suffering from fracture of the neck of femur have increased year by year. The fracture form of the femur neck provides a main reference for the formulation of the surgical scheme. The method is limited by the prior medical imaging technology and is interfered by external environment, and the femur neck fracture line presents the phenomena of rough edges, missing edges and the like with different degrees due to the special position of the femur neck, so that the identification difficulty is increased, and the construction of the femur neck fracture map is seriously influenced. There are few reports on the construction of a map of the fracture of the femoral neck.
According to the continuity and the directionality of the femur neck fracture line, the trend of the femur neck fracture line is designed, trend templates matched with the trends are respectively defined, and the trend templates are matched with fracture lines to repair the fuzzy, missing and other areas in the fracture image. Meanwhile, the fracture line detection method based on the adjustable circle is provided, and the rapid detection of the fracture line is realized. The method has the characteristics of simplicity, flexibility, high efficiency and the like, provides a new method for extracting the femur neck fracture line, and has important significance for constructing the fracture map.
Disclosure of Invention
The invention aims to solve the technical problem of how to construct a fracture line trend template, so that the extraction efficiency of femur neck femur fold lines is improved, and the construction of a femur neck fracture map is facilitated. The invention provides a fracture line extraction method for femur neck fracture map construction, which is used for quickly repairing a blurred and missing fracture line by constructing a fracture line trend template. Meanwhile, the fracture line detection method based on the adjustable circle realizes the rapid detection of the fracture line. The method has the characteristics of simplicity, flexibility, high efficiency and the like, provides a new method for repairing the fracture line, and further provides a data base for accurately constructing the femur neck fracture map.
In order to solve the technical problems, the invention adopts the following technical scheme:
the fracture line extraction method for fracture map construction comprises the following steps:
step one: preprocessing a femur neck fracture image;
step two: constructing a femur neck fracture line trend template;
step three: extracting femur neck fracture line;
step four: drawing a femur neck fracture map according to the femur neck fracture line.
The first step comprises the following steps:
step 1a: denoising the acquired femur neck fracture image;
step 1b: and (3) performing binarization processing on the femoral neck fracture image obtained in the step (1 a) to obtain a femoral neck fracture binarization image.
The binarization processing method comprises the following steps:
on the basis of step 1a noise removal, the threshold value T is maintained to be greater than 0 Will be less than the threshold T 0 The pixel value of (2) is set to 0, i.e. the background is black; the specific calculation formula of the binarized image dst (x, y) is as follows:
T 0 the initial value of (1) is [100,150]Arbitrary values in between; src (x, y) represents the pixel value on the denoised image obtained in step 1 a; x and y represent coordinates of the pixel point.
The second step comprises:
step 2a: calculating the trend of the femur neck fracture line:
the trend of the femur neck fracture line refers to an included angle alpha between the femur neck fracture line and the horizontal direction; alpha is [0,2 pi ]]Arbitrary value in between, dividing α into m classes, setting m=8, that is: alpha 1 ＝[0，π/4)，α 2 ＝[π/4，π/2)，α 3 ＝[π/2，3π/4)，α 4 ＝[3π/4，π)，α 5 ＝[π，5π/4)，α 6 ＝[5π/4，3π/2)，α 7 = [3 pi/2, 7 pi/4) and alpha 8 = [ 7pi/4, 2pi); the dividing is to unify the directions of the femur neck fracture lines to 8 directions of upper, lower, left, right, left upper, right upper, left lower and right lower;
step 2b: determining a femur neck fracture line trend template according to the trend of the femur neck fracture line, wherein the template comprises the size and weight of the template:
the femur neck fracture line trend template refers to a square matrix, which defines a femur neck fracture line, and is characterized by that from current fracture characteristic point A fractrue To the next fracture characteristic point B fractrue The connection rule between the two; the femur neck fracture line trend template is represented by an i×i square matrix and is marked as T j (j＝1,2,3,...,2 i ) 2 altogether i The templates are also m templates;
characteristic point B of fracture at next position fractrue Refers to the characteristic point A of the current fracture fractrue On the basis of the position of (1), advancing a characteristic point on a fracture line obtained by 1 pixel in the Y positive direction;
the size of the femur neck fracture line trend template refers to the size of an i×i square matrix;
the weight of the femur neck fracture line trend template refers to the element value in the i multiplied by i square matrix, and is expressed as 2 k ，k＝0,1,2,...,i。
Designing a next fracture characteristic point B by combining the range value of alpha in the step 2a fractrue With the current fracture characteristic point A fractrue The connection between the two is 8 neighborhood; corresponding to the division accuracy of alpha in step 2a, 2 i =m=8, thereby pushing out i=3; then the femur neck broken line trend template is expressed as a 3×3 square matrix, and the elements in the square matrix are 0,2 0 ，2 1 ，2 2 And 2 3 The method comprises the steps of carrying out a first treatment on the surface of the The center of the square matrix represents the current fracture characteristic point A fractrue The rest elements represent the current fracture characteristic point A fractrue The closer the weight values of 8 adjacent points are to the current fracture characteristic point A fractrue The greater the direction, the greater the weight, and the maximum the weight is 2 3 The farther away from the current fracture characteristic point A fractrue The smaller the weight, the smallest is 0.
The third step comprises:
step 3a: repairing defect and fuzzy segment in femur neck fracture line:
representing femur neck fracture line as point set composed of n fracture characteristic pointsThe method comprises the steps of carrying out a first treatment on the surface of the Marking a fracture characteristic point on the fracture line of the femoral neck in the Y direction every advancing Ym, and marking as E i (i=0, 1,2, … p, … q, …, n); that is, the femoral neck fracture line is dispersed into a point set composed of n fracture characteristic points, and ym=1 pixel is initially set;
at the defect fuzzy position in the femur neck fracture line, calculating the current clear fracture characteristic point E p To the nearest next distinct fracture characteristic point E q Included angle beta between line segment and horizontal line 1 ，0<β 1 <Pi; at the same time, calculate E p And E is q A height h in the Y direction therebetween; according to beta 1 Selecting a corresponding femur neck fracture line trend template, at E p On the basis of the above, 1 pixel is advanced in the Y direction, and a target fracture characteristic point E is drawn along the direction given by the femoral neck fracture line trend template p+1 The method comprises the steps of carrying out a first treatment on the surface of the Then calculate E p+1 To E q Included angle beta between line segment and horizontal line 2 ，0<β 2 <Pi; according to beta 2 Selecting a corresponding femur neck fracture line trend template, at E p+1 On the basis of (1) pixel forward in the Y direction, drawing a target fracture characteristic point E p+2 The method comprises the steps of carrying out a first treatment on the surface of the And so on until proceeding r times in the Y direction, r=q-p; r=h; thereby, E is drawn in turn s (s=p, p+1, p+2,.,) r; obtaining a repaired femur neck fracture line;
step 3b: detecting a new femoral neck fracture line based on the adjustable circle:
in the fracture of the femoral neck, two or more femoral neck fracture lines exist, and therefore, the fracture characteristic point detection method based on the adjustable circle is provided, and comprises the following steps:
step 3ba: selecting the fracture characteristic point on the fracture line of the femoral neck in the step 3a as the center of an adjustable circle, and marking as O 1 (X1, Y1, Z1), setting the initial circle radius to R x =1 pixel;
step 3bb: radius of R x Gradually increasing 1 pixel, if the point with the pixel value of 1 can be reached, namely a new fracture characteristic point is detected, marking as O f1 (X1,Y1,Z1)；
Step 3bc: advancing Yn in the Y direction, initially setting Yn=1 pixels, and moving the center of the adjustable circle to the coordinate O 2 (X2, Y2, Z2); repeating the step 3ab to obtain O in turn fr (Xr, yr, zr) until returning to the original point of origin O 1 (X1,Y1,Z1)；
O fr The fracture characteristic points on the extracted new fracture line of the femoral neck are obtained; connecting fracture characteristic points O fr Thus obtaining a new femur neck fracture line.
The fourth step comprises:
and drawing the repaired femur neck fracture line and the new femur neck fracture line to the same femur neck model to obtain a femur neck fracture map.
Types of femoral neck fractures include subtotal fractures, wraparound neck fractures, and basal fractures.
The femur neck fracture map obtained by the fracture line extraction method facing the fracture map construction is adopted.
The invention has the beneficial effects that the trend template is defined according to the continuity and the directionality of the fracture line of the femur neck and by combining the trend of the fracture line commonly presented when the femur neck is fractured, and the extraction method of the fracture characteristics of the femur neck is provided. The method has the characteristics of simplicity, flexibility, high efficiency and the like, provides a new method for extracting the femur neck fracture line, and has important significance for improving the femur neck fracture map construction efficiency.
According to the continuity and the directionality of the femur neck fracture line, the trend of the femur neck fracture line is designed, trend templates matched with the trends are respectively defined, and the trend templates are matched with fracture lines to repair the fuzzy, missing and other areas in the fracture image. Meanwhile, the fracture line detection method based on the adjustable circle is provided, and the rapid detection of the fracture line is realized. The method has the characteristics of simplicity, flexibility, high efficiency and the like, provides a new method for extracting the femur neck fracture line, and has important significance for constructing the fracture map.
The invention provides a fracture line extraction method for fracture map construction, which is used for quickly repairing a blurred and missing fracture line by constructing a fracture line trend template. The method has the characteristics of simplicity, flexibility, high efficiency and the like, provides a new method for extracting the fracture line, and further provides a data base for accurately constructing the fracture map.
Drawings
FIG. 1 is a schematic diagram of the present invention;
FIG. 2 is a blurred view of the fracture line of a basal femoral neck fracture;
FIG. 3 is a schematic illustration of the lack of occlusion of a fracture line around a neck-type femoral neck fracture;
FIG. 4 is a schematic view of 8 runs of a fracture line;
FIG. 5 is a schematic view of fracture line strike definitions;
FIG. 6 is a schematic diagram of the weight setting of 8 trend templates corresponding to 8 trends of the fracture line in FIG. 5;
FIG. 7 is a schematic diagram of 8 trend templates;
FIG. 8 is a schematic illustration of femoral neck fracture line repair based on strike templates;
FIG. 9 is a graph showing the effect of the fracture line treatment of a basal femoral neck fracture;
FIG. 10 is a graph showing the effect of the treatment of a fracture line around a neck-type femoral neck fracture;
FIG. 11 is a schematic illustration of a femoral neck fracture line detection based on an adjustable circle;
fig. 12 is a schematic representation of a femoral neck fracture map drawn from 15 fracture samples.
Detailed Description
The invention will be further described with reference to the accompanying drawings.
As shown in fig. 1, the fracture line extraction method for fracture map construction comprises the following steps:
step one: preprocessing a femur neck fracture image;
step two: constructing a femur neck fracture line trend template;
step three: extracting femur neck fracture line;
step four: and drawing a fracture map according to the femur neck fracture line.
The method comprises the following specific steps:
step 1a: and denoising the acquired femur neck fracture image.
The femur neck fracture line presents the phenomena of rough edges, missing edges, shielding edges and the like with different degrees, and the extraction difficulty is increased. Fig. 2 is a blurred view of the fracture line of the basal femoral neck fracture, and fig. 3 is a broken view of the fracture line of the wraparound neck femoral neck fracture due to occlusion.
The denoising process in this step employs a denoising technique commonly used in image processing. The two-dimensional Gaussian kernel is convolved with the femur neck fracture image, so that the value of each pixel point is obtained by weighted average of the value of each pixel point and other pixel values in the neighborhood. Gaussian filtering uses the product of two one-dimensional gaussian functions, x and y, the standard deviation σ in both dimensions x and y x Sum sigma y Equal values of u, u x And u y The values are all 0, and the two-dimensional Gaussian function formula is as follows:
step 1b: and (3) performing binarization processing on the femoral neck fracture image obtained in the step (1 a) to obtain a femoral neck fracture binarization image.
On the basis of step 1a noise removal, the threshold value T is maintained to be greater than 0 Will be less than the threshold T 0 The pixel value of (2) is set to 0, i.e. the background is black. The specific calculation formula of the binarized image dst (x, y) is as follows:
according to experience, T 0 The initial value of the method can be set to be [100,150]And (3) determining the final value by repeated testing. src (x, y) represents the pixel value on the denoised image obtained in step 1 a.
The second step comprises:
step 2a: and calculating the trend of the femur neck fracture line.
As shown in fig. 4, the trend of the femur neck fracture line refers toIs the included angle alpha between the femur neck fracture line and the horizontal direction. Alpha is [0,2 pi ]]Any value in between, α can be classified into m classes. In combination with clinical experience and conventional division accuracy, m=8 is set, i.e., α is divided into 8 classes, i.e.: alpha 1 ＝[0,π/4)，α 2 ＝[π/4,π/2)，α 3 ＝[π/2,3π/4)，α 4 ＝[3π/4,π)，α 5 ＝[π,5π/4)，α 6 ＝[5π/4,3π/2)，α 7 = [3 pi/2, 7 pi/4) and alpha 8 = [ 7pi/4, 2pi). The dividing can unify the directions of the femur neck fracture lines to 8 directions of upper, lower, left, right, left upper, right upper, left lower and right lower.
Step 2b: and determining a femur neck fracture line trend template according to the trend of the femur neck fracture line, wherein the template comprises the size and weight of the template.
As shown in fig. 5, the femoral neck fracture line trend template refers to a square matrix, and defines a characteristic point A of the current fracture on a femoral neck fracture line fractrue To the next fracture characteristic point B fractrue Connection rules between the two. The trend template is expressed by an i multiplied by i square matrix and is marked as T j (j＝1,2,3,...,2 i ) 2 altogether i The number of templates is also m.
The next fracture characteristic point refers to a characteristic point on a fracture line obtained by advancing 1 pixel in the Y positive direction on the basis of the position of the current fracture characteristic point.
The dimensions of the strike-pattern plate refer to the dimensions of the i x i square matrix. The weight refers to the element value in the i×i matrix, expressed as 2 k ，k＝0,1,2,...,i。
And (3) designing the connection between the next fracture characteristic point and the current fracture characteristic point as an 8-neighborhood by combining the range value of alpha in the step (2 a). The 8 neighborhood is a term commonly used in image processing. Namely, the relation between the next fracture characteristic point and the current fracture characteristic point is a position immediately adjacent to the current fracture characteristic point and a position obliquely adjacent to the current fracture characteristic point, namely: upper, lower, left, right, upper left, upper right, lower left, lower right.
As shown in fig. 6, 2 corresponds to the division accuracy of α in step 2a i =m=8, thereby pushing out i=3. Then, femur neckThe bone fracture line trend template is expressed as a 3 multiplied by 3 square matrix, and the elements in the square matrix are 0,2 0 ，2 1 ，2 2 And 2 3 . The center of the square matrix represents the current fracture characteristic point, the rest elements represent the weight values of 8 adjacent points of the current point, and the closer to the target direction, the greater the weight (the maximum is 2 3 ) The smaller (minimum 0) the opposite.
Referring to the weight setting method of FIG. 6, 8 trend templates T 1 -T 8 As shown in fig. 7.
Step 3a: repairing defect and fuzzy segment in femur neck fracture line.
To facilitate repair of a fracture line, the fracture line is represented as a set of points consisting of a series of fracture characteristic points. On the fracture line, a fracture feature point is marked every time Ym advances in the positive Y direction (ym=1 pixel is initially set), and is marked as E i (i=0, 1,2, … p, … q, …, n). That is, the fracture line is discretized into a point set composed of n fracture feature points.
As shown in FIG. 8, at the defect blur in the fracture line, the current clear fracture characteristic point E is calculated p To the nearest next distinct fracture characteristic point E q Included angle beta between line segment and horizontal line 1 (0<β 1 <Pi). At the same time, calculate E p And E is q Height h in the Y direction. According to beta 1 Selecting a corresponding fracture line trend template, at E p On the basis of (1) pixel in the Y direction, and drawing a target fracture characteristic point E along the direction given by the trend template p+1 . Then calculate E p+1 To E q Included angle beta between line segment and horizontal line 2 (0<β 2 <Pi). According to beta 2 Selecting a corresponding fracture line trend template, at E p+1 On the basis of (1) pixel forward in the Y direction, drawing a target fracture characteristic point E p+2 . And so on until proceeding r times in the Y direction, r=q-p, h=r. Thereby, E is drawn in turn s (s＝p,p+1,p+2,...,r)。E s Is a repaired femur neck fracture line.
FIG. 9 is a graph showing the effect of the fracture line treatment of a basal femoral neck fracture; fig. 10 is a graph showing the effect of the treatment of the fracture line around the neck of the femur.
Step 3b: new fracture characteristics are detected based on the adjustable circle.
As shown in fig. 11, two or more fracture lines may be present in the femoral neck fracture. Therefore, a fracture characteristic point detection method based on an adjustable circle is provided. The fracture characteristic point detection method of the adjustable circle comprises the following steps:
step 3ba: selecting the fracture characteristic point on the fracture line of the femoral neck in the step 3a as the center of an adjustable circle, and marking as O 1 (X1, Y1, Z1), setting the initial circle radius to R x =1 pixel.
Step 3bb: radius of R x Gradually increasing 1 pixel, if the point with the pixel value of 1 can be reached, namely a new fracture characteristic point is detected, marking as O f1 (X1,Y1,Z1)。
Step 3bc: advancing Yn in Y direction (initial setting ym=1 pixel), moving the center of the adjustable circle to the coordinate O 2 (X2, Y2, Z2). Repeating the step 3ab to obtain O in turn tr (Xr, yr, zr) (r=0, 1,2,..and f,) until returning to the original point of center O 1 (X1,Y1,Z1)。
O fr And the f fracture characteristic points on the extracted characteristic line are obtained. And connecting the fracture characteristic points to obtain a new fracture characteristic line.
The fourth step comprises:
according to the division of the fracture types of the femoral neck in orthopaedics, the femoral neck fracture comprises: subtotal fracture characteristics, cervical fracture characteristics, and basal fracture characteristics.
Collecting femur neck fracture samples, including under-head fracture, neck-surrounding fracture and basal fracture, preprocessing femur neck fracture images through a step, extracting femur neck fracture lines through a step three, and drawing the extracted fracture lines to the same femur neck model to obtain a femur neck fracture map.
A femoral neck fracture map was drawn from 15 femoral neck fracture samples as shown in fig. 12.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules or units or groups of devices in the examples disclosed herein may be arranged in a device as described in this embodiment, or alternatively may be located in one or more devices different from the devices in this example. The modules in the foregoing examples may be combined into one module or may be further divided into a plurality of sub-modules.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or groups of embodiments may be combined into one module or unit or group, and furthermore they may be divided into a plurality of sub-modules or sub-units or groups. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of the above description, will appreciate that other embodiments are contemplated within the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is intended to be illustrative, but not limiting, of the scope of the invention, which is defined by the appended claims.
Claims (6)
1. The fracture line extraction method for fracture map construction is characterized by comprising the following steps of:
step one: preprocessing a femur neck fracture image;
step two: constructing a femur neck fracture line trend template;
step three: extracting femur neck fracture line;
step four: drawing a femur neck fracture map according to the femur neck fracture line;
the second step comprises:
step 2a: calculating the trend of the femur neck fracture line:
the trend of the femur neck fracture line refers toIncluded angle between femur neck fracture line and horizontal directionα；αIs [0,2 pi ]]Arbitrary value in between, willαDivided intomClass, setm=8, i.e.:α 1 =[0，π/4），α 2 =[π/4，π/2），α 3 =[π/2，3π/4），α 4 =[3π/4，π），α 5 =[π，5π/4），α 6 =[5π/4，3π/2），α 7 = [3 pi/2, 7 pi/4) andα 8 = [ 7pi/4, 2pi); the dividing is to unify the directions of the femur neck fracture lines to 8 directions of upper, lower, left, right, left upper, right upper, left lower and right lower;
step 2b: determining a femur neck fracture line trend template according to the trend of the femur neck fracture line, wherein the template comprises the size and weight of the template:
the femur neck fracture line trend template refers to a square matrix, which defines a femur neck fracture line, and the current fracture characteristic point is followedA fractrue To the next fracture characteristic pointB fractrue The connection rule between the two; the femur neck fracture line trend template is adoptedi×iSquare matrix representation, denoted asT j （j=1, 2, 3, ...,2 i ) 2 altogether i Templates, toomA template;
characteristic point of fracture at next positionB fractrue Refers to the characteristic point of the current fractureA fractrue Based on the position of (a)YAdvancing 1 pixel in the positive direction to obtain a characteristic point on a fracture line;
the size of the femur neck fracture line trend template refers toi×iThe size of the square matrix;
the weight of the femur neck broken line trend template refers toi×iThe element values in the square matrix are denoted as 2 k ，k=0,1, 2,...,i；
Combining in step 2aαIs used for designing the characteristic point of the next fractureB fractrue And the current fracture characteristic pointA fractrue The connection between the two is 8 neighborhood; and in step 2aαCorresponding to the division accuracy of (a)，2 i =m=8, thereby push outi=3; then the femur neck broken line trend template is expressed as a 3×3 square matrix, and the elements in the square matrix are 0,2 0 ，2 1 ，2 2 And 2 3 The method comprises the steps of carrying out a first treatment on the surface of the The center of the square matrix represents the current fracture characteristic pointA fractrue The rest elements represent the current fracture characteristic pointsA fractrue The closer the weight values of 8 adjacent points are to the current fracture characteristic pointA fractrue The greater the direction, the greater the weight, and the maximum the weight is 2 3 The farther away from the current fracture characteristic pointA fractrue The smaller the weight, the minimum is 0;
the third step comprises:
step 3a: repairing defect and fuzzy segment in femur neck fracture line:
representing the femur neck fracture line as a result ofnA point set consisting of individual fracture feature points; on the fracture line of the neck of femur, atYEvery forward movement in the positive directionYm marks a fracture characteristic point and is recorded asE i (i=0,1, 2,…p,…q,…,n) The method comprises the steps of carrying out a first treatment on the surface of the That is, the broken line of the femur neck is dispersed into the broken line bynInitial setting of point set formed by individual fracture characteristic pointsYm=1 pixel;
at the defect fuzzy position in the femur neck fracture line, calculating the current clear fracture characteristic pointE p To the nearest next clear fracture characteristic pointE q Included angle between line segment and horizontal lineβ 1 ，0<β 1 <Pi; at the same time calculateE p AndE q betweenYHeight of directionhThe method comprises the steps of carrying out a first treatment on the surface of the According toβ 1 Selecting corresponding femur neck fracture line trend template, inE p On the basis of (1), on the basis ofYAdvancing by 1 pixel along the direction, and drawing target fracture characteristic points along the direction given by the femur neck fracture line trend templateE p+1 The method comprises the steps of carrying out a first treatment on the surface of the Then, calculateE p+1 To the point ofE q Included angle between line segment and horizontal lineβ 2 ，0<β 2 <Pi; according toβ 2 Selecting corresponding femur neck fracture line trend template, inE p+1 On the basis of (1), on the basis ofYAdvancing by 1 pixel in the direction to draw the characteristic point of the target fractureE p+2 The method comprises the steps of carrying out a first treatment on the surface of the And so on untilYForward in the directionrIn a second time, the first time,r=q-p；r=hthe method comprises the steps of carrying out a first treatment on the surface of the Thereby sequentially drawing outE s （s=p, p+1, p+2, ..., r) The method comprises the steps of carrying out a first treatment on the surface of the Obtaining a repaired femur neck fracture line;
step 3b: detecting a new femoral neck fracture line based on the adjustable circle:
in the fracture of the femoral neck, two or more femoral neck fracture lines exist, and therefore, the fracture characteristic point detection method based on the adjustable circle is provided, and comprises the following steps:
step 3ba: selecting the fracture characteristic points on the fracture line of the femoral neck in the step 3a as the circle center of the adjustable circle, and marking asO 1 （X1,Y1,Z1) Setting the initial circle radius asR x =1 pixel;
step 3bb: radius of pairR x Gradually increasing 1 pixel, if the point with the pixel value of 1 can be reached, namely the new fracture characteristic point is detected, marking asO f1 （X1,Y1,Z1）；
Step 3bc: at the position ofYForward in the directionYn, initial settingYn=1 pixels, moving the center of the adjustable circle to the coordinatesO 2 （X2,Y2,Z2) The method comprises the steps of carrying out a first treatment on the surface of the Repeating the steps 3ba to obtainO fr （Xr,Yr,Zr) Until returning to the original center pointO 1 （X1,Y1,Z1）；
O rf The fracture characteristic points on the extracted new fracture line of the femoral neck are obtained; connecting fracture feature pointsO rf Thus obtaining a new femur neck fracture line.
2. The method of claim 1, wherein step one comprises:
step 1a: denoising the acquired femur neck fracture image;
step 1b: and (3) performing binarization processing on the femoral neck fracture image obtained in the step (1 a) to obtain a femoral neck fracture binarization image.
3. The method according to claim 2, wherein the binarization processing method comprises:
on the basis of step 1a noise removal, remain greater than thresholdT 0 Will be less than the threshold valueT 0 The pixel value of (2) is set to 0, i.e. the background is black; binarized imagedst(x,y) The specific calculation formula of (2) is as follows:
；
T 0 the initial value of (1) is [100,150]Arbitrary values in between;src(x,y) Representing the pixel values on the denoised image obtained in step 1 a;x,yrepresenting the coordinates of the pixel points.
4. The method of claim 1, wherein step four comprises:
and drawing the repaired femur neck fracture line and the new femur neck fracture line to the same femur neck model to obtain a femur neck fracture map.
5. The method of claim 1, wherein the types of femoral neck fractures include subtotal fractures, wraparound neck fractures, and basal fractures.
6. A femoral neck fracture map obtained by the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311213604.XA CN117218091B (en) | 2023-09-19 | 2023-09-19 | Fracture line extraction method for fracture map construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311213604.XA CN117218091B (en) | 2023-09-19 | 2023-09-19 | Fracture line extraction method for fracture map construction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117218091A CN117218091A (en) | 2023-12-12 |
| CN117218091B true CN117218091B (en) | 2024-03-29 |
Family
ID=89036759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311213604.XA Active CN117218091B (en) | 2023-09-19 | 2023-09-19 | Fracture line extraction method for fracture map construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117218091B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106023094A (en) * | 2016-05-10 | 2016-10-12 | 中南大学 | Image-based bone tissue microstructure restoration system and restoration method thereof |
| WO2018023917A1 (en) * | 2016-07-30 | 2018-02-08 | 上海联影医疗科技有限公司 | Method and system for extracting lower limb blood vessel |
| CN111354057A (en) * | 2020-03-10 | 2020-06-30 | 中南大学 | Bone fracture line map drawing method based on image deformation technology |
| CN112215771A (en) * | 2020-10-10 | 2021-01-12 | 徐州医科大学 | Intelligent construction method and system for orthopedic implant class characteristics |
| CN113298784A (en) * | 2021-05-25 | 2021-08-24 | 中南大学 | Bone fracture line extraction and mapping method based on visual angle |
| CN114494704A (en) * | 2022-02-16 | 2022-05-13 | 重庆大学 | Method and system for extracting framework from binary image in anti-noise manner |
| WO2023078309A1 (en) * | 2021-11-05 | 2023-05-11 | 苏州微创畅行机器人有限公司 | Method and apparatus for extracting target feature point, and computer device and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220301281A1 (en) * | 2019-06-06 | 2022-09-22 | The Research Foundation For The State University Of New York | System and method for identifying fractures in digitized x-rays |
-
2023
- 2023-09-19 CN CN202311213604.XA patent/CN117218091B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106023094A (en) * | 2016-05-10 | 2016-10-12 | 中南大学 | Image-based bone tissue microstructure restoration system and restoration method thereof |
| WO2018023917A1 (en) * | 2016-07-30 | 2018-02-08 | 上海联影医疗科技有限公司 | Method and system for extracting lower limb blood vessel |
| CN111354057A (en) * | 2020-03-10 | 2020-06-30 | 中南大学 | Bone fracture line map drawing method based on image deformation technology |
| CN112215771A (en) * | 2020-10-10 | 2021-01-12 | 徐州医科大学 | Intelligent construction method and system for orthopedic implant class characteristics |
| CN113298784A (en) * | 2021-05-25 | 2021-08-24 | 中南大学 | Bone fracture line extraction and mapping method based on visual angle |
| WO2023078309A1 (en) * | 2021-11-05 | 2023-05-11 | 苏州微创畅行机器人有限公司 | Method and apparatus for extracting target feature point, and computer device and storage medium |
| CN114494704A (en) * | 2022-02-16 | 2022-05-13 | 重庆大学 | Method and system for extracting framework from binary image in anti-noise manner |
Non-Patent Citations (2)
| Title |
|---|
| Articular coronal fracture angle of posteromedial tibial plateau fragments: A computed tomography fracture mapping study;Rik J. Molenaars等;《Injury》;20190226;第50卷(第2期);489-496 * |
| 三维重建髋臼骨折地图的绘制和髋臼T形骨折内固定的有限元分析;钟子毅;《中国优秀硕士学位论文全文数据库医药卫生科技辑》;20200515;E066-91 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117218091A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bandyopadhyay et al. | Long-bone fracture detection in digital X-ray images based on digital-geometric techniques | |
| Kim et al. | A fully automatic vertebra segmentation method using 3D deformable fences | |
| Yahalomi et al. | Detection of distal radius fractures trained by a small set of X-ray images and Faster R-CNN | |
| Farda et al. | Sanders classification of calcaneal fractures in CT images with deep learning and differential data augmentation techniques | |
| CN109830289B (en) | Rib image display device | |
| CN111047572A (en) | Automatic spine positioning method in medical image based on Mask RCNN | |
| CN105139409B (en) | Two dimensional image dividing method based on ant group algorithm | |
| CN104616289A (en) | Removal method and system for bone tissue in 3D CT (Three Dimensional Computed Tomography) image | |
| CN104346799A (en) | Method for extracting spinal marrow in CT (Computed Tomography) image | |
| Zhang et al. | LPAQR-Net: efficient vertebra segmentation from biplanar whole-spine radiographs | |
| Ruikar et al. | Contrast stretching-based unwanted artifacts removal from CT images | |
| CN106202930B (en) | A kind of Lung neoplasm risk forecasting system based on SS-ELM | |
| Liang et al. | Fracture identification of X-ray image | |
| Bayram et al. | Diffract: Diaphyseal femur fracture classifier system | |
| CN117218091B (en) | Fracture line extraction method for fracture map construction | |
| Bakthula et al. | Automated human bone age assessment using image processing methods-survey | |
| Vijayakumar et al. | Quantitative analysis and fracture detection of pelvic bone X-ray images | |
| Bhandarkar et al. | Computer vision guided virtual craniofacial reconstruction | |
| Zamora et al. | Estimation of orientation and position of cervical vertebrae for segmentation with active shape models | |
| CN113205153B (en) | Training method of pediatric pneumonia auxiliary diagnosis model and model obtained by training | |
| CN111127636B (en) | Intelligent complex intra-articular fracture desktop-level three-dimensional diagnosis system | |
| Wei et al. | Study on recognition of the fracture injure site based on X-ray images | |
| Wu et al. | Fracture detection and quantitative measure of displacement in pelvic CT images | |
| Chen et al. | Detection of Various Dental Conditions on Dental Panoramic Radiography Using Faster R-CNN | |
| Wang et al. | Artificial Intelligence model trained with sparse data to detect facial and cranial bone fractures from head CT |
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 |