Wavelet Transform and LTP Transform in Mammogram Analysis and Classification

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering

Final Year Thesis Oral Defense

Title: "Wavelet Transform and LTP Transform in Mammogram Analysis and 
        Classification"

by

WENG Jiaqi

Abstract:

Breast cancer is most common diagnosed cancer among Hong Kong females. The 
diagnose of breast cancer in early stage is crucial and optimal. However, 
many women in less developed area do not have regular medical examination. 
Even with a well-produced mammogram image, a doctor needs to consider many 
aspects and features. By applying both Wavelet transform and LTP on the 
image, the method proposed in this report can extract features that most 
represent the suspicious mass region. A fully trained classification model 
can decide on an input area with an acceptable accuracy, which enables 
doctors to only define a rough region of interest in diagnosing process.


Date            : 4 May 2019 (Saturday)

Time            : 11:30 - 12:10

Venue           : Room 2128A (near lift 19), HKUST

Advisor         : Prof. CHUNG Albert Chi-Shing

2nd Reader      : Dr. SANDER Pedro