Author

Abu-Amara

Date of Award

4-2007

Degree Name

Master of Science in Engineering

Department

Electrical and Computer Engineering

First Advisor

Dr. Ikhlas Abdel-Qadar

Second Advisor

Dr. Janos Grantner

Third Advisor

Dr. Ala Al-Fuqaha

Access Setting

Masters Thesis-Open Access

Abstract

Screening mammograms by a radiologist is a repetitive task that causes fatigue and eye strain. For every thousand cases analyzed by a radiologist, only 3 to 4 are cancerous and thus an abnormality may be overlooked. Computer-Aided Detection (CAD) algorithms have been developed to assist radiologists in detecting mammographic lesions. CAD algorithms have improved total radiologists' detection accuracy of cancerous tissues. In this thesis, a computer aided detection and diagnosis (CADD) system for breast cancer is developed. The algorithm framework is based on combining principal component analysis (PCA), independent component analysis (ICA), and fuzzy classifier to identify and label suspicious regions from digitized mammograms. This proposed algorithm is novel in utilizing a fuzzy classifier integrated with the ICA model. This system is implemented and tested by using images from the MIAS database and results in labeling the tested image as either normal or abnormal. If abnormal, CADD differentiates it into a benign or a malignant tissue. Experimental results show that the proposed algorithm has 84.03% accuracy in detecting all kinds of abnormalities and 78% diagnosis accuracy.

Share

COinS