Paper Title
Feature Level Fusion Of Information From Mammogram And Ultrasound Images For Detection Of Micro- Calcification In Breast
Abstract
Breast cancer is the most common, life-threatening cancer in women. Detection of Microcalcification plays a
crucial role in diagnosis of breast cancer. Different medical modalities like mammogram, ultrasound, MRI, etc. are used in
all phases of cancer detection, which provide morphological, metabolic and functional information of tissues. By integrating
this extracted information from multimodalities in a meaningful way assists in clinical decision making. Proposed work
helps in classification of breast microcalcification as benign or malignant for early detection of breast cancer using
mammograms and Ultrasound modalities. This approach is based on the fusion of information from two modalities at feature
level. Discriminative statistical, spatial and texture features of malignant microcalcifications in mammograms and ultrasound
are extracted and fused. SVM classifiers are used to classify malignant microcalcifications which achieved 91.3%
sensitivity.
Keywords- Microcalcification, Mammogram, Ultrasound, Fusion, Dualmodality