Image Processing Reference
In-Depth Information
5
Rough Hybrid Scheme: An
application of breast cancer imaging
5.1
Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
5-1
5.2
Fuzzy sets, rough sets and neural networks: Brief
Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
5-3
Fuzzy Sets Rough sets Neural networks Create
gray-level co-occurrence matrix from image
5.3
Rough Hybrid Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
5-5
Aboul Ella Hassanien
Cairo University, Egypt
Pre-processing: Intensity Adjustment through Fuzzy
histogram hyperbolization algorithm Clustering and
Feature Extraction: Modified fuzzy c-mean clustering
algorithm and Gray level co-occurrence matrix Rough
sets analysis Rough Neural Classifier
Hameed Al-Qaheri
Kuwait University
5.4
Results and Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
5-11
Ajith Abraham
Norwegian University of Science and
Technology
5.5
Conclusion
5-12
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Bibliography
5-14
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
5.1
Introduction
Breast carcinomas are a leading cause of death for women throughout the world. It is
second or third most common malignancy among women in developing countries (Rajendra,
Ng, Y. H. Chang, and Kaw, 2008). The incidence of breast cancer is increasing globally
and the disease remains a significant public health problem. Statistics from the National
Cancer Institute of Canada show that the lifetime probability of a woman developing breast
cancer is one in nine, with a lifetime probability of one in 27 of death due to the disease,
also about 385,000 of the 1.2 million women diagnosed with breast cancer each year occur
in Asia (Organization, 2005). Because only localized cancer is deemed to be treatable and
curable, as opposed to metastasized cancer, early detection of breast cancer is of utmost
importance. Mammography is, at present, the best available tool for early detection of
breast cancer. However, the sensitivity of screening mammography is influenced by image
quality and the radiologists level of expertise. Contrary to masses and calcifications, the
presence of architectural distortion is usually not accompanied by a site of increased density
in mammograms. The detection of architectural distortion is performed by a radiologist
through the identification of subtle signs of abnormality, such as the presence of spiculations
and distortion of the normal oriented texture pattern of the breast.
Mammography is currently the gold standard/method to detect early breast cancer before
it becomes clinically palpable. The use of mammography results in a 25% to 30% decreased
mortality rate in screened women compared with controls after 5 to 7 years
(Nystrom,
5-1
 
 
 
 
 
 
 
 
 
 
Search WWH ::




Custom Search