wrsta, 13 august, 2006 rough sets in hybrid intelligent systems for breast cancer detection by aboul...

21
WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer and Information, IT Dept. email: [email protected]

Post on 18-Dec-2015

213 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection

By

Aboul Ella Hassanien

Cairo University, Faculty of Computer and Information, IT Dept.email: [email protected] 

Page 2: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Outline Introduction

Digital mammography Hybrid intelligent systems

Objective What is Mammogram? Mammogram Analysis Framework

Pre-processing phase Segmentation Feature Extraction phase Feature Representation phase Generated Rules phase Classification phase

Hybrid Intelligent System Pre-processing Algorithm – Fuzzy Image Processing Rough Set data analysis Rough neural Classifier Evaluation

Results Conclusion and Future Work

Page 3: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Introduction

According to the National Cancer Institute: Breast cancer is the leading cause of cancer deaths in women

today and it is the most common type of cancer in women. Each year about 180,000 women in the United States

develop breast cancer, and About 48,000 lose their lives to this disease. It is also reported that a woman's lifetime risk of developing

breast cancer is one in eight. Currently, digital mammography is one of the most

promising cancer control strategies in earliest stages.

Page 4: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

What is a mammograms?

A mammogram is a special kind of X-ray that allows the doctor to see into the breast tissue

Page 5: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Introduction

Hybridization of intelligent systems is A promising research field of modern artificial intelligence concerned with the

development of the next generation of intelligent systems. A fundamental stimulus to the investigations of Hybrid Intelligent Systems (HIS) is the

awareness in the academic communities that combined and integrated approaches will be necessary if the remaining tough problems in artificial intelligence are to be solved.

Recently, hybrid intelligent systems are becoming popular due to their capabilities in handling many real world complex problems, involving imprecision, uncertainty and vagueness, high-dimensionality.

A hybrid intelligent system isis one that combines at least two intelligent technologies. For example,one that combines at least two intelligent technologies. For example,

Combining a neural network with a fuzzy system results in a hybrid neuro-fuzzy system.Combining a neural network with a fuzzy system results in a hybrid neuro-fuzzy system. Combining a neural network with a rough system results in a hybrid neuro-rough system. Etc.Combining a neural network with a rough system results in a hybrid neuro-rough system. Etc.

The combination of probabilistic reasoning, fuzzy logic, neural networks and evolutionary computation forms the core of soft computing, an emerging approach to building hybrid intelligent systems capable of reasoning and learning in an uncertain and imprecise environment.

Page 6: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Intelligent Systems

Rough Sets

Fuzzy Logic

Neural Networks

Evolutionary Algorithms

Chaos & Fractals

Belief

Networks

The primordial soup

Page 7: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Fuzzy Logic : the algorithms for dealing with imprecision and uncertainty Neural Networks : the machinery for learning and function approximation with noise Evolutionary Algorithms : the algorithms for reinforced search and optimization

RSRough Sets

uncertainty arising from the granularity in the domain of discourse

Different methods = different roles

Page 8: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Comparison of Expert Systems, Fuzzy Systems,Comparison of Expert Systems, Fuzzy Systems,Neural Networks and Genetic AlgorithmsNeural Networks and Genetic Algorithms

Knowledge representation

Uncertainty tolerance

Imprecision tolerance

Adaptability

Learning ability

Explanation ability

Knowledge discovery and data mining

Maintainability

ES FS NN GA

* The terms used for grading are:

- bad, - rather bad, - good - rather good and

Page 9: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Objective

Introduce a rough neural intelligent approach for: Rule generation and image classification. An application of breast cancer imaging has been

chosen and hybridization of intelligent computing techniques has been applied to see their ability and accuracy to classify the breast cancer images into two outcomes: malignant cancer or benign cancer.

Computer-based to assist radiologists in mammography classification of breast cancer images (Computer Aided Diagnosis System)

Page 10: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Mammogram Analysis Framework

Page 11: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Mammogram Analysis Framework

Pre-processing phase – Fuzzy theory Enhancement Segmentation: Region of Interest (ROI) Region Boundary Enhancement

Feature Extraction phase Statistical features – concurrence Matrix

Rough Sets Data Analysis Feature representation – Rough information system Reduct generation Rule generation

Classification phase Rough neural classifier

Evaluation

Page 12: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Pre-Processing – Fuzzy theory

Mammograms are images that are difficult to interpret; therefore, techniques are needed to: Enhance the quality of these images for a better

interpretation. For this purpose, a pre-processing phase of the images is

adopted to improve the quality of the images and to make the feature extraction phase more reliable.

It contains several processes; to enhance the contrast of the whole image;

Fuzzy histogram hyperbolization algorithm (FHH) to extract the region of interest;

Modified Fuzzy c-mean clustering algorithm to enhance the edges surrounding the region of interest.

Fuzzy histogram hyperbolization algorithm (FHH)

Page 13: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Feature Extraction

Once the pre-processing was completed, features relevant to region of interest classification are extracted, normalized and represented in a database as vector values

Gray level co-occurrence matrix (GLCM) Energy, entropy, contrast and inverse difference moment.

Page 14: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Rough Sets Data Analysis

Create decision table Compute some reduct

with minimal number of attributes.

Significance of attributes: calculate the weight of the attributes.

Rule Generation Rule Evaluation

Page 15: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Rough neural network: rough neuron

Page 16: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Results (Enhancement)

Page 17: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Results (Segmentation)

Page 18: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Page 19: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Average Execution time

Page 20: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Number of generated rules and classification accuracy

Page 21: WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer

WRSTA, 13 August, 2006

Conclusion

Introducing a hybrid scheme that combines the advantages of different soft computing techniques for breast cancer detection. Fuzzy sets is used as a pre-processing techniques to

enhance the contrast of the whole image; to extracts the region of interest and then to enhance the edges surrounding the region of interest.

Then, subsequently extract features from the extracted regions characterizing the underlying texture of the interested regions.

Feature extractions acquired in this work are derived from the gray-level co-occurrence matrix.

A rough set approach to attribute reduction and rule generation has been used.

Rough neural networks were designed for discrimination for different regions of interest to test whether they are cancer or nun-cancer.

The results proved that the soft computing techniques are very successful and has high detection accuracy.