Review Second 2

8/9/2019 Review Second 2

1/22

Colorectal Polyp Detection using

CAD-CTC System Integration

Under the guidence of

Prof. P.Tamije Selvy,

Presented ByM.VANITHA

II M.E CSE 08


2/22

ABSTRACT

Computed Tomography Colonography(CTC) is a rapidly evolving noninvasive

medical investigation that is viewed by

radiologists as a potential screening

technique for the detection of colorectalpolyps. The aim of this paper is to detail the

implementation of a fully integrated CAD-

CTC system that is able to robustly identifythe clinically significant polyps in the CT

data.


3/22

Contd. The CAD-CTC system described in this paper is a

multistage implementation whose main system

components are:1.automatic colon segmentation,2.candidate surface extraction,

3.feature extraction and 4.classification. The

developed system has been evaluated on synthetic

and real patient CT data acquired with standard

and low-dose data.


4/22

Literature Review

Paper : G.Iordanescu, P.J. Pickhardt, J.R. Choi, andR.M. Summers, Automated seed placement for colon

segmentation in CT colonogrphy, Acad. Rad., vol. 12, pp.

182-190, 2005.

Abstract : Present an algorithm to automatically locateseeds for colon segmentation in computed tomography

colonography (CTC).

The information inferred from this :

Fully automatic seed placement for colonic segmentation

is feasible in the majority of cases without seeding of

undesired extracolonic air was analyzed.


5/22

Contd Paper : O.Ghita and P.F.Whelan,A bin picking system

based on depth from defocus,Mach. Vis. Appl., vol. 13,

no. 2, pp. 234-244, 2003.

Abstract : Develop versatile bin-picking systemscapable of grasping and manipulation operations, accurate

3-D information is required

The information inferred from this :the attitude of the recognized object is evaluated using an

eigenimage approach augmented with range data analysis.

The full bin-picking system will be outlined, and a number

of experimental results will be examined.


6/22

Contd Paper : G.Kiss,J.Van Cleynenbreugel, M. Thomeer, P.Suetens,

and G. Marchalc, Computer diagnosis for CT Colonography via

combination of surface normal and sphere fitting methods,Eur. Rad.,Vol. 12, no. 1,pp.77-81, 2002.

Abstract :finding an enhanced version of the techniquefor the extraction of the polyp candidate surfaces.

The information inferred from this : methodsfor the extraction of the polyp candidate surfaces are

analyzed.


7/22

Existing System The existing CAD-CTC system can robustly

identify the clinically significant polyps in

the CT data. But it generates more false

positives from the small convex surfaces .In

that situation the application of these

systems to clinical studies impractical. Sothe reduction of false positives is very

important.


8/22

Proposed System

The fully integrated CAD-CTC system is able to robustlyidentify the clinically significant in the CT data.

The proposed system will returns the highest sensitivity in

Polyp detection.

The application of this system will be useful in the clinical

examinations.

The proposed system will achieve robust polyp detection at alow level of false positives.

This system has been evaluated on synthetic and real patient

CT data acquired with standard and low-dose radiation levels.


9/22

Development Tools

Hardware requirementsProcessor : Intel Pentium IV

Processor Speed : 1.4 GHz

Memory (RAM) : 512 MBHard disk : 40 GB

Monitor : 15 Color Monitor

Key board : 104 keys Standard Keyboard

Mouse : Standard Three button Mouse


10/22

Development Tools Contd.

Software requirements

Operating System : Windows XP

Language : MAT

LAB


11/22

Block Diagram


12/22

Key Features of MATLAB

High-level language for technical computing

Development environment for managing code, files, and data

Interactive tools for iterative exploration, design, and problemsolving

Mathematical functions for linear algebra, statistics, Fourieranalysis, filtering, optimization, and numerical integration

2-D and 3-D graphics functions for visualizing data

Tools for building custom graphical user interfaces

Functions for integrating MATLAB based algorithms with

external applications and languages, such as C, C++, Fortran,Java, COM, and Microsoft Excel


13/22

Modules

Automatic colon segmentation

Candidate surface extraction Feature extraction

Classification


14/22

Goal:

To identify the colons in the CT data

Steps:

Surrounding air voxel removal

Lung detection

Labelling

V/L analysis Colon reconstruction

Algorithm:

Seeded Region Growing Algorithm

Automatic colon Segmentaion


15/22

Candidate Surface ExtractionGoal:

Extraction of polyp candidate surfaces

Step:Finding intersection of the normal vectors for a

number of normal concentration points.

Algorithms:

Gaussian weighted averaging operationNon maxima suppression algorithm

Surface convexity test


16/22


17/22


18/22

Data Classification

Goal: Robustly identify the clinically significant polyps in the

CT data.

Steps:

Training database is created using the featuresdetailed in features extraction for each polyps and

folds.

Features of each class is normalized.

Algorithms:

Feature Normalized Nearest Neighbor Classifier(FNNN)

Probabilistic Neural Network (PNN)


19/22

Comparision of Existing and proposed systen

with any one of the metrics


20/22

References


21/22

Conclusion

we conclude that robust polyp detection is

possible even at radiation does as low as 13m

as / rotation. The required by this system to

process completely is lower than the time

required to analyze the data manually. CAD-

CTC system is fully integrated so its

performance makes it suitable to be applied in

clinical examinations.


22/22

Thank YOU

Documents

Review Second 2