Scribd
Upload
47 views10 pages

Presentation Data

Image processing has many medical applications including diagnostic imaging. It enables quantitative analysis and extraction of information from medical images. A computer aided diagnosis system can be developed using image processing algorithms for tasks like image de-noising, segmentation, and classification. This would help researchers and doctors analyze images, diagnose problems, and develop treatment plans. The presented work aims to develop such algorithms to analyze and quantify brain images for diagnosis of neurological diseases.

Uploaded by

Prashantyelekar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
47 views10 pages

Presentation Data

Image processing has many medical applications including diagnostic imaging. It enables quantitative analysis and extraction of information from medical images. A computer aided diagnosis system can be developed using image processing algorithms for tasks like image de-noising, segmentation, and classification. This would help researchers and doctors analyze images, diagnose problems, and develop treatment plans. The presented work aims to develop such algorithms to analyze and quantify brain images for diagnosis of neurological diseases.

Uploaded by

Prashantyelekar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Slide 3

Image Processing is considered to be important areas of


research and technology with many applications in Medical
imaging, computer vision, remote sensing and so on

The principle objective of image processing is


improvement of pictorial information for human interpretation
and processing of image data for storage, transmission and
reception for autonomous machine perception.

The use of image processing technique in medical field


began in late 1960’s and early 1970’s which has found its great
importance for the researchers and clinical practice.

Diagnostic imaging is an invaluable tool in medicine today.


(MRI), (CT), digital mammography, and other imaging
modalities provide an effective means for noninvasively
mapping the anatomy of a subject.

These technologies have increased knowledge of normal


and diseased anatomy for medical research and helpful in
diagnosis and treatment planning.
Image processing application enables quantitative analysis of
medical images. Through image processing important
information can be extracted from these images which can be
used for the assessment of different diseases parameters.
A Computer aided diagnosis system can be developed through
various image processing algorithms for image de-noising,
segmentation, classification etc.

Slide 4
Humans are highly skilled and fast in the analysis of visual
patterns, but are slow (usually) in arithmetic operations with
large numbers of values.

Computers can perform millions of arithmetic operations or


computations per second.
However, the recognition of objects and patterns in images using
mathematical procedures requires huge numbers of operations:
slow response from low level computers.

A trained human observer can usually recognize an object or a


pattern in an instant.

Slide 4

Humans could be affected by fatigue, boredom, and


environmental factors: susceptible to committing errors.

Working with large numbers of images in one sitting, such as in


breast cancer screening, poses practical difficulties.
A human observer could be distracted by other events in the
surrounding areas and may miss uncommon signs present in
some images.

Computers, being inanimate but mathematically accurate and


consistent machines, can be designed to perform
computationally specific and repetitive tasks.

Slide 5

Analysis by humans is usually subjective and


qualitative.

Computers can assist in quantitative and objective


analysis.

Quantitative analysis becomes possible by the


application of computers to biomedical images.

The logic of medical or clinical diagnosis via image


analysis could then be objectively encoded and
consistently applied in routine or repetitive tasks.
–138–
Slide 6
 To develop computational methods and algorithms to
analyze and quantify the medical data.
 To develop a Computer aided diagnosis system with which
researchers and doctors can share data, analyses them,
diagnose the problem and prescribe the treatment to the
patients.

Slide 7
Quantitative evaluation of image data is the most important
aspect of image processing.

Now a day, capturing and storing of medical images are done


digitally.

Medical images mostly contain complicated structure and the


interpretation of details in it is still time-consuming.

and their precise segmentation is necessary for clinical diagnosis

Image segmentation helps to facilitate the treatment of patients.

It is helpful in extracting clinical useful information in order to


facilitates abnormality detection, surgical planning, post-surgical
assessment

In MRI brain image researcher are interested in segmentation of


gray matter (GM), white matter (WM) and cerebrospinal fluid
(CSF).
The quantification of important parameters such as volume of
various tissue types enables to understands, diagnose and treat
neurobehavioral disorder

Slide 8

An adaptive mean-shift methodology to classify brain voxels


into one of three main tissue types: gray matter, white matter,
and Cerebro spinal fluid.MRI brain

Image segmentation plays a very important role in spotting the


tumors in an image. Improved mountain clustering technique [3]
is used for MRI brain image segmentation for spotting tumors
where cluster entropy parameter is used as a measure of
information for comparison with some existing techniques.

Zi-Xuan Ji et al [4] proposed modified fast fuzzy c-means for


brain MR images segmentation to take intensity inhomogeneity,
noise and partial volume (PV) effects into account to improve
the accuracy of image segmentations. Modified fuzzy c-means is
mostly used for brain MRI images [5, 6].

Slide 9

Akselrod-Ballin et al [7] introduced a multi-scale approach that


combines segmentation with classification to detect abnormal
brain structures in medical imagery, and demonstrate its utility
in automatically detecting multiple sclerosis (MS) lesions in 3-D
multichannel magnetic resonance (MR) images.

Multilevel brain tumor segmentation technique with integrated


Bayesian model [8] is used to detect and segment brain tumor
and edema in multichannel MR volumes.

Bayesian mixture model [9] is also used by Adelino R et al for


exploring normal mixture models with an unknown number of
components in the context of magnetic resonance imaging
(MRI) segmentation.

Markov Random Field (MRF) models have been used brain


tumor segmentation [10, 11].

A variational level set approach is used in a multi-phase


formulation to segmentation of brain magnetic resonance (MR)
images with intensity inhomogeneity where the local image
intensities are characterized by Gaussian distributions with
different means and variances [12].

Slide 10
Development of various image processing algorithms for image
de-noising, image segmentation, classification of brain images
will be the basic aim of this study.

These algorithms will be used to analyze and quantify brain


images for diagnosis of diseases. The plan of research work is as
follows

Slide 11

 Development of image de-noising algorithms

Medical images often consist of low-contrast objects corrupted


by random noise arising in the image acquisition process. Thus,
image de-noising is one of the fundamental tasks required by
medical imaging analysis. MRI images also suffer from noise
and RF inhomogeneity.

Different methods have been used for MRI de-noising such as


linear filtering methods, nonlinear filtering methods, anisotropic
nonlinear diffusion filtering, a Markov random field (MRF)
models, wavelet models.
These methods have advantages and disadvantages in terms of
computation cost, de-noising, quality of de-noising and
boundary preserving.

Linear filters are conceptually simple. They update value of a


pixel by (weighted) average of its neighborhood. These filters
reduce noise but degrade image details and the edges of the
image; therefore, restored image looks blurred.

In contrast to linear filters, nonlinear filters have better


performance in edge preserving but degrade fine structure;
therefore, the resolution of the image is reduced.

Development of different image processing algorithms for


smoothing, morphological filtering or multi-resolution analysis
for removal of noise from brain images will be the first step of
this project.

Slide 12
 Brain image segmentation and quantitative analysis
Brain image segmentation is complicated and challenging area
in Medical field.

Its accurate segmentation is very important for detecting tumors,


edema, and necrotic tissues which is very important in
diagnostic systems.

Brain image segmentation is also useful in clinical diagnosis of


neurodegenerative and psychiatric disorders, treatment
evaluation, and surgical planning.

Mostly used techniques for image segmentation are K-means


clustering, Fuzzy C-means clustering, active appearance model,
active shape model etc. Most recent techniques for image
segmentation are Rough set and Near set.

Because of unknown noise, inhomogenity, and weak boundaries,


brain image segmentation is still a challenging area of research.
The next step would be to improve currently available
techniques and propose the new method for brain image
segmentation so as to improve the results in terms of intensity
inhomogeneity, computation cost and de-noising.

Slide 13

Classification and assessment of brain images for clinical


application

After segmentation of brain images, classification of brain tumor


type from primary gliomas to Metastases can be done. The next
step will be grading of gliomas from high grade to low grade
(Neoplasm).

You might also like