In current scenario back pain is a leadingcause of work absenteeism. Another area of concerns is the cervical spinetrauma which causes majority of spinal lesions. Many of these problems are theconsequence of an abnormal spinal motion. In past a Greek method was applied forplacing the displaced bones at their original positions. This method was knownas automatic method as no machines were used and force was applied manually.

Then with the advancement automatic traction therapy was replaced by mechanicaltraction. The Skin traction was used at a great extent during the Civil War forfractured femurs (thigh bone). It was commonly known as the “American Methodfor treating bones fractures and dislocation”. Now a day’s Decompression Traction Therapybecomes an effective treatment for spinal traction treatment. It is lessexpensive than surgery. Decompression Traction Therapy is the new therapeuticdevice for treatment of painful nerve compression and disc herniationsyndromes.”Mainly we can perform traction either incontinuous manner or an intermittent manner. Usually static traction is usedfor cervical spondylosis and osteoarthritis or degenerative disc disease DDDand intermittent traction is common for Facet joint Dysfunction and joint hypomobility.

Both of the intermittent and the continuous cervical traction had asignificant effect on neck and arm pain reduction, a significant improvement innerve function and a significant increase in neck mobility 1Cervical traction is a method in which a distracting force is administered tothe neck so as to separate the cervical segments and relieve compression ofnerve roots by intervertebral disk distraction 2. Traction mayimprove conduction by improving blood flow to cervical nerve roots. Cervicaltraction has a significant biomechanical effect on spinal structures, which canbe demonstrated by CT evaluation before and after traction. 3 One practical deviceto extract spine motion in real-time is the digital video fluoroscopy (DVF). 4 Advances inmedical image processing have led to increase in large image collections.Hence, techniques that are computer assisted are becoming more promisingapproach in medical image analysis. The feasibility of computer assistedtechniques for the segmentation of vertebral bodies in spine X-ray images hasbeen of great interest 24, 25 to biomedical researchers.

Reliable extractionof vertebrae boundaries is a prerequisite for subsequent pathology validationand Content-Based Image Retrieval (CBIR) research. However, fully automatedsegmentation of spine X-ray images is a very challenging problem.  A smart approach is discussed for cervicaltraction which is a combination of image Processing and Physics theory. Afundamental issue faced in the design of image analysis techniques is theidentification and characterization of the image space. In plain words, oneends up having first to answer the question “What do we meanmathematically by images?” A pertinent example of this point can be foundin the variational approach to image de-noising, the goal of which is toestimate the original version of an image from a given degraded one. Thevariation approach to this problem seeks to exhibit the “restored”image as the minimize of a functional defined over the space of all images.

Thefirst task is clearly to decide which space of functions to take images from.For instance, it is easy to see why Sobolev spaces are ill suited for thispurpose: their elements cannot have discontinuities across co-dimension onesurfaces, and yet any successful model of images should allow for them. Suchdiscontinuities need to be allowed because one of the most important featuresof images, namely “edges” (places where one object in the scene endsand another begins) correspond squarely to this type of behavior. The space offunctions of bounded variation therefore provides the more appropriate setting.(Another example comes from the variational approach to the image segmentationproblem, where the correct space of functions for minimizing one of the mostsuccessful models in this context, the Mumford-Shah segmentation model, turnsout to be a subset of functions of bounded variation, known as specialfunctions of bounded variation) 32.

Roughly the various approaches to image analysis is divided intothree categories: (A) Statistical representations (B) Spectral and wavelet representations,and (C) Scale-space representations.Statistical approaches treat images assamples from random fields, which are often modeled by Markov/Gibbs fields orvia statistical learning from an image database. This approach was pioneered inthe 80’s by Grenander (Brown) and the Gemans (Brown and John Hopkins. Spectral and wavelet representations are themathematical foundation for JPEG Internet image coding protocols. It has usesbeyond image compression. In fields like computer vision and medical imaging,there is great demand for efficient and accurate image processors.

Transform Used     Making of                                                                                                         Model      Fig: Designing of Image ProcessorMajortask is how to design an image processor that performs efficiently and well?Typical tasks would be: denoising, edge detection, intensity enhancement, andcompression and decompression. In addition to these relatively low-level tasks,there are mid- and high-level tasks like image segmentation, and patternidentification and recognition.Initiallya suitable model is constructed for the given task. Currently, the developed processing models(Fig) are using tools like Bayesian 34, 35 decision, inverse problems,variational optimization, etc. The need of these approaches arise mainly in the fields of statistical mechanics, nonlinearPDEs, differential geometry and topology, the calculus of variations, ,harmonic and functional analysis, and numerical analysis. Image denoising isone of the major problem faced during analysis of image.

Numerous methods hasbeen proposed for image denoising problem, from using transformations andstatistical methods to using PDEs. For transformations, typically spectral transformationare used and recently Curvlet or Ridgelet transformation are used. Another problemin Image reconstruction is inpainting. The Digital inpainting problem, isrelated to disocclusion problem.

There are various approaches for the imagesegmentation problem: using snake methods or region growing and mergingtechniques or global optimization approaches using energy functional orBayesian approaches 33, 34.When onehas a processing model, the next stage is its analysis, keeping in mind the endgoal to answer inquiries like presence and uniqueness, dependability, propertiesof solutions etc. Many image processing model are nonlinear and they requiresnew mathematical insights, they require rigorous mathematical analysis.

Asthere are many transformation algorithms present ,the major question arises iswhich among the many techniques proposed for the same task is superior, whateffect the various parameters that appear in a method have on its behavior, andunder what conditions a given technique can be expected to perform well.  Finally,what is an effective algorithm for implementing the image analysis model? Onecan certainly create, implement and plan schemes without performing the type ofnumerical analyses described above. But one runs the risk of developing analgorithm that performs ineffectively in the presence of noise. Also, thehistory of scientific computing shows that the breakthroughs that led tomassive speed-up would have been unimaginable without a profound understandingof the mathematics. Mostly the mathematical calculations can be converted intoefficient and robust algorithms.

The methods currently being used in imageprocessing come from almost all branches of scientific computing including fastfourier and wavelet transforms, multigrid algorithm, dynamic programming,combinatorial optimization, computational PDEs, NLA, and Monte-Carlosimulations.We canuse the important step of image preprocessing i.e image segmentation to analyzehow mathematics has contributed to image processing in the stages discussedabove: modeling, analysis, and implementation 36.

The goal of segmentation isto divide up the image domain into as smaller segments as possible, so thatimage features (such as gray-scale intensity, or color) either slowly varyingin each piece or approximately constant. This procedure helps differentiatebetween parts of the image domain occupied by distinct objects in the scene. Itis a challenging problem that is intimately connected with edge detection.Typically, physics plays a vital role incultivating the knowledge of natural sciences and establishing the foundation of logistic and scientificmethods. The application of physics to medical sciences has been developed inpractice for centuries 5.X-Ray, CT scan and MRI images of the spine provide a practical approach fordetecting and assessing vertebral abnormalities.

For accurate vertebradetection number of features of an image can be extracted and meaningfulinformation can be obtain from low level information in the image usingsegmentation. Image segmentation is observed to be the maximum important partin digital image processing. Segmentation is nothing but however a portion ofany photo and object is extracted and analyzed to get useful information. Inimage segmentation, digital photo is splitted into a couple of set of pixels. Main objective of segmentation is topartition the image into the meaningful areas 6.The segmentation techniques used for medical images are specific to the typebody part and imaging modality to be used.

Consistent algorithms are necessary for the explanation ofanatomical structures and other regions of interest (ROI).As the time growalgorithmic complexity increases. As medicalimages are complex and rarely have linear feature, segmentation of medicalimages becomes a difficult task. There is no universal algorithm which can giveappropriate results for every image.

While using segmentation algorithmdifferent artifacts and noise introduce by electronic system must be taken inconsideration 7.A comparison of three generation medical image segmentation technique isprovided in literature 8.Vertebrae localization is a difficult taskto perform manually.

Model-based approach is used for vertebra detection,identification and segmentation in the case of CT images 9.Each cervical vertebra has a unique morphology, which make quantitativeanalysis a challenging task. So developing an approach which is robust,efficient and capable of robustly determining the location of the spine and thecontour of the vertebrae is essential. Author proposes fully automaticframework for cervical spine mobility analysis on radiographs 10 which is based on-fully automatic vertebra detection, vertebra segmentation and vertebramobility analysis.Digital medical images have some degree ofnoise it gets corrupted with noise during its acquisition from various sensorsand transmission process. Sincedifferent types of images have different characteristics and differentapplications have different requirements, the filtering algorithms should bedesigned for each case properly. Mostly the medical images quality cannotsatisfy the medical analysis and the applied requirements.

The denoising ofmedical image plays an important role in the image processing, and it is thebasic of further analysis and computation. The image edge are easilyinterrupted by noise, but the traditional image denoising smooth out the edgesof the reconstructed images which caused edge to be blurred, and made theinformation lost. Thedenoising algorithms based on partial differential of total variation isproposed 11. Author ensures thatthe algorithm works to obtain clear medical image and preserve the edgeinformation integrally at the same time.Mostly, themedical images quality cannot satisfy the medical analysis so to get bestquality image a set of textures and images is analyzed to determine the bestmeasure of image activity and it has showed that image activity measure haspowerful ability to capture the activities and differentiating between variousimages 12.To detect degenerative changes which occurs due to narrowing of  intervertebral disc space author introduce amachine learning approach to detect and localize degenerative changes in X-rayimage analysis of cervical spine and author receive accuracy of 95%for a patientdata set of 103patients 13. Another authordiscussed the same problem of detecting degenerative changes in particularlyC3-C6 vertebra of cervical.

The result range from 82% to 94% ,author proposed segmentationand clustering from where distance features are computed and mapped 14.  To preserve edges and fine details whileeffectively removing noise, both local gradient and variance are incorporatedinto the diffusion model 15 16. A newertechnique is introduced for noise removal using fractional-order anisotropicdiffusion equations, which uses the discrete Fourier transform and an iterativescheme in the frequency domain 17.Image filtering is an effective means for improving image quality. Authorproposed local activity-tuned filtering frameworks for noise removal and image smoothing,where the local activity measurement is given by the clipped and normalizedlocal variance or standard deviation. Local activity-tuned relative totalvariation framework achieves good performance for image smoothing andrepresents the image in different scale-space and it has been used for depthimage denoising 18.

x

Hi!
I'm Katy!

Would you like to get a custom essay? How about receiving a customized one?

Check it out