Mammogram Analysis

1
Mammogram Analysis Tumor classification

• - Geethapriya Raghavan

2
Background

• Mammogram
• X-Ray image (of gray levels) of inner breast
  tissue to detect cancer
• Shows the levels of contrast characterizing
  normal tissue and vessels
• Issues
• Detect abnormalities (tumors)
• Diagnosis - Classify as benign or malignant
• Remove noise

3
Methods ..

• Non-linear classifiers preferred over linear
  classifiers given the randomness in occurrence of
  tumor cells allowing the trade off that mapping
  has to be done on a higher dimensional space
• Contemporary methods treat as supervised learning
  problem (Wei et al., 2005)
• Support Vector Machines (SVM) (Vapnik et al.,
  1997)
• Kernel Fisher Discriminant (KFD)
• Relevance Vector Machines (RVM)

4
Methods ..

• SVM was used by Chang et al., on US images to
  diagnose the nature of tumor
• Use of wavelet transform to uncorrelate data
  (image) (Borges et al., 2001)
• Obtain wavelet coefficients as features
• Normalize coefficients and feed into Nearest
  Neighborhood classifier

5
Proposed work

• Issues open need for a classifier that gives
  more accuracy in lesser time
• Design and train an SVM classifier on mammograms
• Extend on Borges et al.s work on wavelet
  features and use a different classifier on the
  feature vectors.