0 Voturi pozitive0 Voturi negative

3 (de) vizualizări4 pagini.//./.,./,m./,.,/./,

Mar 22, 2017

© © All Rights Reserved

PDF, TXT sau citiți online pe Scribd

.//./.,./,m./,.,/./,

© All Rights Reserved

3 (de) vizualizări

.//./.,./,m./,.,/./,

© All Rights Reserved

- Hidden Figures: The American Dream and the Untold Story of the Black Women Mathematicians Who Helped Win the Space Race
- Hidden Figures Young Readers' Edition
- The Law of Explosive Growth: Lesson 20 from The 21 Irrefutable Laws of Leadership
- The E-Myth Revisited: Why Most Small Businesses Don't Work and
- The Wright Brothers
- The Power of Discipline: 7 Ways it Can Change Your Life
- The Other Einstein: A Novel
- The Kiss Quotient: A Novel
- State of Fear
- State of Fear
- The 10X Rule: The Only Difference Between Success and Failure
- Being Wrong: Adventures in the Margin of Error
- Algorithms to Live By: The Computer Science of Human Decisions
- The Black Swan
- Prince Caspian
- The Art of Thinking Clearly
- A Mind for Numbers: How to Excel at Math and Science Even If You Flunked Algebra
- The Last Battle
- The 6th Extinction
- HBR's 10 Must Reads on Strategy (including featured article "What Is Strategy?" by Michael E. Porter)

Sunteți pe pagina 1din 4

Ling Wang, Hong Cheng, Hai Lan, Yingjie Zheng, Kainan Li

in the elderly. In this paper, an automatic and efficient

classification method of femoral pertrochanteric fractures is

proposed based on image segmentation techniques. The types

of femoral pertrochanteric fracture are defined firstly according !"#!$%"&&'()

to the difference of fracture parts. To reduce the computational

complexity, only four directions images are used in each

3D femur, i.e. the anterior, the anterolateral, the posterior *+,)"&-.")+"(/,/'$(

and the posterolateral images of a femur. And then those

fracture images are segmented from background using level set

method. Considering the numerical errors and the instability

of evolution in conventional level set formulations, a distance 0"1/2!"&-3"/"%/'$(

regularization term and an external energy constraint term are "!/!$%8,(/"!'%--

used, which are able to maintain a desired shape of the level set 9!,%/2!"-:$;"5

function and speed up the motion of the zero level contour in *+,)"&- ,!/'/'$(

evolution process. After segmentation, the Canny edge detector

is used to extract the fracture edges on femur. The types of

femoral pertrochanteric fracture are classified by comparing

the difference of edges between reference normal images and the 45,&&'6'%,/'$(-7-3',)($&'&

testing images. Except the given four directions of 3D image, the

classification is processed automatically. Experimental results Fig. 1: The framework of pertrochanteric fracture automatic

illustrated the effectiveness of the proposed method. detection.

I. I NTRODUCTION

The incidence of femur fractures increased significantly Max/Min Rule, Product Rule, are fused to design as com-

among people over 60 years old. Most of these orthopedic bining classifier [4], [5]. Fracture is detected by computing

and trauma surgical interventions need careful classification the pixels value of each images column or row in [6], where

in order to decide the position and type of implant to be a threshold is set, there would be a fracture if the value is

used intraoperative. Automatic recognition and classification less than the threshold.

of femur fractures plays an important role in quantitative

In the above mentioned investigations, most of them either

analysis.

only detect the fractures or design a general classifier, such

For the fracture clinical diagnosis is widely based on

as traverse fracture, open fracture, simple fracture and com-

computer-aided images, such as X-ray, CT, ultrasound and

minuted fracture. In this paper, a subtle pertrochanteric frac-

MRI images, many investigations on fracture detection and

ture classifier is proposed, which can distinguish five types

diagnosis are based on image processing. Morphological

of pertrochanteric fracture. The classification model is shown

gradient based image segmentation is used in [1] to detect

in Fig. 1, the original CT image is denoised and smoothed

radius bone fracture. Fracture detection is performed by a

by Gaussian filter, and then the distance regularization level

registered active shape model in [2], where the pelvic CT

set method is used to segment the region of interest (ROI).

images are preprocessed by adaptive windowing, bound-

After that, the Canny edge detection is used to detect the

ary tracing and wavelet transform. Stacked random forests

construction of femur and then the image is divided into

feature fusion is used in [3] to detect fracture in X-ray

several parts according to the definition of pertrochanteric

images. After edge and shape features are extracted from

fracture.

bone, multiple classifiers, such as Back Propagation Neural

Network, K-Nearest Neightbour, Support Vector Machine, For there usually are noises in the segmentation, filters

are used to remove the smaller noise regions and edges

*Research supported by the grant from National Natural Science by mistaken segmentation as shown in Fig. 2. A continues

Foundation of China (NSFC) ( No. 61273256, No. 61305033 and No. region would be considered as a outliers if its size is less

U1233103F01).

L. Wang and H. Cheng are with Center for Robotics, University of than 10 10, and then this region would be moved out. A

Electronic Science and Technology of China, Chengdu, China 611731. continues line would be moved out if its length is less than

(email: eewangling@uestc.edu.cn, hcheng@uestc.edu.cn). one forth of the width of each image. The pertrochanteric

H. Lan and Y. Zheng and K. Li are with Affiliated Hospital of

Chengdu University, Chengdu, China 610106. (email: 13714777@qq.com, fracture is classified by comparing the difference of each

183729860@qq.com, Likainan1961@126.com). part with reference normal images.

!" #" $" (a) Two parts fracture (b) Three parts fracture 1

%" '" &"

segmented image by level set, (c) is the region of interest.

(d) is the extracted edges by Canny detector, (e) is the edges

in yellow rectangle region of (d), (f) is the lines of interest

(e) Five parts fracture 1 (f) Five parts fracture 2

in (e).

For the diagnosis of fracture, the types of femoral (g) Six parts fracture

pertrochanteric fractures are defined as five classes [7]: the

Fig. 3: Definition of Pertrochanteric Fracture.

two parts, three parts, four parts, five parts and six parts

fractures. In two parts fracture the fracture line is cross the

pertrochanteric, as shown in Fig. 3a, it is between in greater

trochanter and lesser trochanter. The three parts fracture is is derived as the gradient flow that minimizes an energy

defined as follows. There are fractures in greater trochanter functional. The energy function is consisted of a distance

or lesser trochanter go with two parts fracture, as shown regularization term and an external energy that drives the

in Fig. 3b and Fig. 3c. In four parts fracture, there are motion of the zero level set toward desired locations.

greater and lesser trochanter fractures go with two parts Let be a level set function defined in a domain , an

fracture, as shown in Fig. 3d. In five parts fracture, there energy function E() is define as

is anterior or posterior lateral fracture go with four parts

E() = R() + Eext (), (2)

fracture, as shown in Fig. 3e and Fig. 3f. In six parts

fracture, there is anterior and posterior lateral fractures go where > 0 is a constant, R() is the level set regularization

with four parts fracture, as shown in Fig. 3g. According to term and Eext () is an external energy that depends on the

this definition, only four images of each femur are used in data of interest.

following discussion, i.e. the anterior, the anterolateral, the The distance regularization term R() is defined with a

posterior and the posterolateral images of a femur.

potential function p(x) as R() = p()dx. It makes

III. I MAGE S EGMENTATION level set evolution has a unique forward-and-backward dif-

fusion effect and maintain a desired shape of the level

Level set method is a tool for numerical analysis of shapes, set function, particularly a signed distance profile near the

which is used to image segmentation from background zero level set. The distance regularization effect eliminates

widely. In two dimensions image, the level set method the need for reinitialization and thereby avoids its induced

aims to representing a closed curve by using a level set numerical errors. In order to maintain the signed distance

auxiliary function . is represented as the zero of by property = 1 only in a vicinity of the zero level set,

= (x, y)|(x, y) = 0. If the curve moves in the normal while keeping the as a constant, with = 0, at locations

direction with a speed v, then the level set function satisfies far away from the zero level set. The p(x) is a double-well

the level set equation function, which has two minimum values at x = 1 and x = 0.

It is defined as p(x) = (x 1)2 /2. Then the derivative of

= v||, (1)

t R() is

R

where | | is the Euclidean norm, t is time. = div(dp (||)), (3)

In the level set formulations, the level set function maybe

develops irregularities during its evolution, which may cause

here div() is the divergence operator and dp (x) = dp(x)

xdx .

numerical errors and eventually destroy the stability of evo-

The external energy function

lution. To overcome this difficulty, in [8], Li et.al proposed

a variation level set formulation to regularize the level

Eext () = gH()dx + g()dx, (4)

set function during the evolution. The level set evolution

3852

here R and > 0 are coefficients, g is an edge indicator

1

function of image I, which defined as g = (1+GI 2 ) and G

are Heaviside function and Dirac delta function, which are

!" #" $" %" &"

introduced to speed up the motion of the zero level contour

in the evolution process and minimize the energy when the Fig. 4: Image segmentation and edge extraction. (a) The

zero level contour is located at the object boundaries. In original image. (b) The segmented image. (c) The edges of

practice, the and H are approximated by the following segmented image. (d) The skeletons of image. (e) The edges

smooth functions, in bone.

{ 1 [ ]

2 1 + cos( x

) , x6

(x) = (5)

0, x> V. D IAGNOSIS

[ ] According to the definition of the five fracture classes,

) , x6

1 x 1

2 1+ + sin( x the images are divided to several parts as intertrochanteric,

H(x) = 1, x> (6) greater trochanter section, lesser trochanter section, anterior

0, x < and posterior lateral femur section. As shown in Fig. 5, the

first row is the images of a reference normal femur in four

The standard method to minimize the energy function directions, where the green rectangles are regions of greater

E() is to find the steady state solution of the gradient flow trochanter, the red rectangles are regions of lesser trochanter,

equation the yellow rectangles are regions of anterior lateral femur, the

E black rectangles are regions of posterior lateral femur. The

= = div(dp (||)) + g() second row is the images of a trochanter fracture, the third

t

and forth rows are extracted edges from each part where

+()div(g ). (7) the skeletons are subtracted. Then the fracture is classified

||

by comparing the difference between the test image and

Given an initial 0 (x), the Eqn. (7) can be solved by an iter- reference image among the mentioned sections.

ative narrow-band implementation. The readers are referred Let I1 I4 are the four direction images of each patient,

to [8] for more details. The 2D images are segmented from H2 H6 are the hypothesis of two parts fracture to six parts

background by using this level set function. In this paper, fracture as defined in section II, F1 F4 are the above men-

the parameters of the segmentation model are set as follows. tioned four sections fracture, and N, Ng , Nr , Ny , Nk are the

The = 0.2/t, = 10, = 5, = 0.8, in Eqn. (7), (5) number of edges in skeleton, green block, red block, yellow

and (6), where t = 5 is the time step of implementation, block and black block, respectively. Then the diagnosis is

the = 5 is parameter of Gaussian kernel G. formulated as hypothesis testing as follows.

IV. E DGE E XTRACTION

P (F2 = 1) = P (Nr > 1|I1 ) P (Nr > 1|I2 ) P (Nr > 1|I3 )

P (F3 = 1) = P (Ny > 1|I1 ) P (Ny > 1|I2 ) P (Ny > 1|I4 )

For the fracture diagnosis is based on the information of

P (F4 = 1) = P (Nk > 1|I3 )

edges on bone, the edge detector is used to extract the struc-

tural information from the segmented images. Among the

P (H2 = 1) = P (N > 1|I1 ) P (N > 1|I3 )

presented edge detection methods, the Canny edge detection

P (H4 = 1) = P (H2 = 1) P (F1 = 1) P (F2 = 1)

algorithm [9] is one of the most strictly defined methods that

P (H3 = 1) = P (H4 = 0) (P (F1 = 1) P (F2 = 1))

provides good and reliable detection. Owing to its optimality

P (H6 = 1) = P (H4 = 1) P (F3 = 1) P (F4 = 1)

to meet with the criteria for edge detection and the simplicity

P (H5 = 1) = P (H6 = 0) (P (F3 = 1) P (F4 = 1))

of process for implementation, it is used to extract the edges

on femoral trochanter fracture. The image is smoothed by

Gaussian filter and two threshold values [t1, t2] are used to

determine potential edges. In the following experiment, the VI. E XPERIMENTAL R ESULTS

threshold of Canny edge detector is set as [0.2, 0.35]. This section shows the results of the proposed classi-

A demo results of image segmentation and edge extraction fication model for real clinical images. 38 patients with

are shown in Fig. 4, where (a) is the original image, (b) is pertrochanteric fracture were collected, where there are

the segmented image, (c) is the edges of image, (d) is the 9, 6, 7, 14, 2 people with two parts to six parts fracture,

skeletons of image and (e) is the edges without skeleton. It respectively. Some samples are shown in Fig. 6. The original

is noted that the line in (d) is considered as a skeleton if it reconstructed 3D images from CT are 1024 1024 pixels,

is continues with external contour. Fig. 4 illustrated that the which are down-sampled to 256256 pixels. It is noted that,

algorithms of segmentation and edge extraction play good the size of segmented images is different from each other for

performance. the difference of viewpoint and difference of patient.

3853

Fig. 5: The partials of images. The first row is the reference images of a normal femur, the second row is the test images

of a trochanter fracture, the third and the forth rows are the extracted edges from each part of the test images.

R EFERENCES

[1] B. Swathika, Anandhanarayanan.K, Baskaran.B, and Govindaraj.R,

Radius bone fracture detection using morphological gradient based

image segmentation technique, Int. J. of Comput. Sci. and Inform.

Fig. 6: Five classes fracture images. From the first image to Tech., vol. 6, no. 2, pp. 110, Feb 2015.

the last image, it is two parts to six parts fracture respectively. [2] J. Wu, P. Davuluri, K. R. Ward, C. Cockrell, R. Hobson, and K. Na-

jarian, Fracture detection in traumatic pelvic CT images, Int. J. of

Biomed. Imag., 2012.

TABLE I: The recognition rates [3] Y. Cao, H. Wang, M. Moradi, P. Prasanna, and T. Syeda-Mahmood,

Fracture detection in x-ray images through stacked random forests

Classes Two Three Four Five Six feature fusion, in IEEE Int. Symp. Biomed.l Imag. (ISBI), April 2015,

Data Number 9 6 7 14 2 pp. 801805.

[4] N. Umadevi and S. Geethalakshmi, Multiple classification system for

Recognition Rate 8/9 5/6 5/7 12/14 2/2 fracture detection in human bone x-ray images, in Int. Conf. Comput.

Commun. Net.g Technol. (ICCCNT), July 2012, pp. 18.

[5] V. L. F. Lum, W. K. Leow, Y. Chen, T. S. Howe, and M. A. Png,

Combining classifiers for bone fracture detection in x-ray images, in

The recognition rates of each classes are shown in Table IEEE Int. Conf. Image Process., vol. 1, Sept 2005, pp. 11491152.

I. The average recognition rate is 84.2%. There are some [6] L. Nascimento and M. Graca Ruano, Computer-aided bone fracture

identification based on ultrasound images, in IEEE Portuguese Meeting

estimation error for the greater or lesser trochanter fracture on Bioeng. (ENBENG), Feb 2015, pp. 16.

are not clearly even diagnosed by human eyes. For the [7] Z. Chen, K. Li, and Z. Zhang, A finite element analysis of six-segment

definition of the five types femoral pertrochanteric fractures classification of femur intertrochanteric fracture, China J. Orthop.

Trauma., vol. 17, no. 5, pp. 433437, May 2015.

is a novel subject, there is fewer methods to compare. [8] C. Li, C. Xu, C. Gui, and M. D. Fox, Distance regularized level

set evolution and its application to image segmentation, IEEE Trans.

Image Process., 2010.

VII. C ONCLUSION [9] J. Canny, A computational approach to edge detection, IEEE Trans.

Pattern Anal. Mach. Intell., vol. PAMI-8, no. 6, pp. 679698, Nov 1986.

This paper explore the pertrochanteric fracture classifica-

tion in 3D CT-images. A distance regularization level set

method is used to segment ROI from noisy background,

Canny edge detect operator is used to extract fracture edges,

and then by comparing the difference of edges between

reference normal images and testing images, the fracture is

classified according to the definition of pertrochanteric frac-

ture. Compared with existed works, the proposed method can

classify subtle fractures on pertrochanteric. The experimental

results illustrated the good performance of this method. In

future work, we will discuss the sparse feature representation

and supervised machine learning method on large data sets.

3854

- Preattentive grouping and Attentive selection for early visual computationÎncărcat deKetan_8
- Major Project Report 4th Year IT EDGE DETECTION FinalÎncărcat deAnish Prasad
- ZERO TO HEROÎncărcat dedidine
- The Best Jumper Points Design of the Sewing MachineÎncărcat deSEP-Publisher
- i w 3515281533Încărcat deAnonymous 7VPPkWS8O
- Java Image Processing IEEE Projects 2012 @ Seabirds ( Trichy, Thanjavur, Pudukkottai, Perambalur, Karur, Namakkal )Încărcat desathish20059
- ZitnickDollarECCV14edgeBoxesÎncărcat deSandra Rodriguez
- A Methodology for Extracting Standing Human Bodies from Single ImagesÎncărcat dejournal
- 53.Încărcat decintemani
- Semi-supervised Method of Multiple Object Segmentation with a Region Labeling and Flood FillÎncărcat desipij
- Object Detection By Global Contour ShapeÎncărcat deRaghavender Samala
- 11segmentationÎncărcat dedrashokyvuce
- 1012Încărcat deOnet GB
- CT-44112_Digital Image ProcessingÎncărcat deSisay AD
- Identifing the Levels of Skin Cancer Using Texture DistinctivenessÎncărcat deInternational Journal of Innovative Science and Research Technology
- RTIPÎncărcat deapi-26172869
- Vision SensorÎncărcat desubramanya1982
- Canny SlideÎncărcat dekoustubhthorat
- 10.1.1.68Încărcat deVm An
- R2Vmanual1Încărcat deDEEPAK KUMAR MALLICK
- Dorsal hand vein recognition based on 2D Gabor filtersÎncărcat deVinsmoke Sanji
- [IJCST-V5I2P55]: Aruna BajpaiÎncărcat deEighthSenseGroup
- Spatial Relationship Based Approach for Detection of HookwormÎncărcat deInternational Journal of Innovative Science and Research Technology
- e 021042024Încărcat deIOSRJEN : hard copy, certificates, Call for Papers 2013, publishing of journal
- A Survey on Improved Edge Detection for Flame and Fire Image ProcessingÎncărcat deEighthSenseGroup
- Isha PoojavarshaÎncărcat dePooja Angurala
- Design and Simulation of Robot Vision System Using SimulinkÎncărcat dePeyman Alizadeh
- Fuzzy LogicÎncărcat deamalxplod
- WangÎncărcat deCricket Live Streaming
- RSOBIA DocumentationÎncărcat deBouhadjar Meguenni

- List of Papers-icastÎncărcat deAnonymous Ndsvh2so
- EC8251 Circuit AnalysisÎncărcat deAnonymous Ndsvh2so
- Ec8251 Rejinpaul Iq April May 2019-1Încărcat deAnonymous Ndsvh2so
- Dsp Lab ProgramsÎncărcat deAnonymous Ndsvh2so
- Annaexure i Journals in IndiaÎncărcat deAnonymous Ndsvh2so
- Calendar-2018-2019Încărcat deAnonymous Ndsvh2so
- Journal NameÎncărcat deAnonymous Ndsvh2so
- Communication EnglishÎncărcat deAnonymous Ndsvh2so
- Partnership Deed FormatÎncărcat deShubham Jain
- Manage the DepartmentÎncărcat deAnonymous Ndsvh2so
- DiabeticÎncărcat deAnonymous Ndsvh2so
- Researchpaper Smart Bin Implementation for Smart CitiesÎncărcat deAnonymous Ndsvh2so
- Conference Paper 4Încărcat deAnonymous Ndsvh2so
- Boost Derived Hybrid Converter Implementatio1 GhÎncărcat deAnonymous Ndsvh2so
- ABSTRact foetal.docÎncărcat deAnonymous Ndsvh2so
- Blind Stick PaperÎncărcat deAnonymous Ndsvh2so
- Classification of Tweets in Real-time and Detecting Live TrendsÎncărcat deAnonymous Ndsvh2so
- A Hybrid Approach for Human Capital Valuation (2)Încărcat deAnonymous Ndsvh2so
- Confirmation of Attending the ConferenceÎncărcat deAnonymous Ndsvh2so
- IntroductionÎncărcat deAnonymous Ndsvh2so
- ABSTRact FoetalÎncărcat deAnonymous Ndsvh2so
- BaseÎncărcat deAnonymous Ndsvh2so
- 1 Cover PageÎncărcat deAnonymous Ndsvh2so
- MahaÎncărcat deAnonymous Ndsvh2so
- ytyeytryryrtÎncărcat deAnonymous Ndsvh2so
- Design-And-Implementation-Of-Bank-Locker-Security-System-Based-On-Fingerprint-Sensing-Circuit-And-Rfid-Reader.pdfÎncărcat deAnonymous Ndsvh2so
- Irjet-v2i149.pdfÎncărcat deAnonymous Ndsvh2so
- 233-W057.pdfÎncărcat deAnonymous Ndsvh2so
- FingerÎncărcat deAnonymous Ndsvh2so

- 32 bit floating point ALUÎncărcat deBalachandarVetrivelan
- Stata ModelÎncărcat deHector
- SDK ReadmeÎncărcat deslimehat
- EGI Technical Upgrade 71 Day1Încărcat deGlen Paul Pogi
- d2anlgÎncărcat dedompin
- IT_support_resume_template.docÎncărcat deWaliy BELLO
- Agile GlossaryÎncărcat deSrinivas Yugender Tera
- Primary and Standby on Windows PDFÎncărcat desajjad
- t030-ch-1-en.pdfÎncărcat deJosé
- userspace.txtÎncărcat deAnonymous 8Lu7Hllc1N
- Type1FF1Încărcat deAustin Clyde
- Chapter 6, Management of Process QualityÎncărcat deRameez Ramzan Ali
- Compositional Data With R BoogaartÎncărcat deParag Jyoti Dutta
- Sequence and SeriesÎncărcat deEr Puneet Goyal
- Latest Checklist of Courses for Industrial Training - Bcs (1)Încărcat dejam1976
- ALUÎncărcat deNavhakar Rahul
- Error Function PDFÎncărcat deSara
- EN_ISD-DEMOI5100-3900-15C00_User_Manual.pdfÎncărcat deJames Ash
- Setup LogÎncărcat deDani Kewek
- Matlab Functions CMÎncărcat deNuraddeen Magaji
- Wifi pptÎncărcat demahendra choudhary
- HausmanÎncărcat deTubagus Ajie Rahmansyah
- Privacy Policy Inference of User-UploadedÎncărcat deSyed Adil
- Improve Scheduling Task Based Task Grouping in Cloud Computing SystemÎncărcat dephanikumar
- PHP Image Convert Type Function Upload Tutorial.pdfÎncărcat debharat
- qbank.functions.docxÎncărcat deCosmicBlue24
- INCREASING OPEN SOURCE SOFTWARE INTEGRATION ON THE DEPARTMENT OF DEFENSE UNCLASSIFIED DESKTOPÎncărcat dekander1169
- ATI Stream SDK Installation NotesÎncărcat dejviloria111
- 64386 - Mouse M7Încărcat defilipe
- 121270Încărcat deVinith M

## Mult mai mult decât documente.

Descoperiți tot ce are Scribd de oferit, inclusiv cărți și cărți audio de la editori majori.

Anulați oricând.