Mammographic density assessment for breast cancer detection

• Main Author: Liu, Xukun.
• Other Authors: School of Electrical and Electronic Engineering
• Format: Final Year Project
• Language: English
• Published: 2011
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Medical electronics
• Online Access: http://hdl.handle.net/10356/46007
• Institution: Nanyang Technological University

Mammographic density is a good indicator for the risk of breast cancer but the assessment of mammographic density is a time consuming process and requires a lot of effort from doctors. With the progress of technology, mammographic density assessment software can be developed to assist doctors to evaluate the risk of breast cancer and prevent misdiagnoses such as oversights. In this thesis, we study various techniques of mammographic density assessment and propose a novel image segmentation algorithm to segment dense areas from mammograms which achieves 10 percent increase on accuracy over existing methods. We also write the software MammoAid which implements the algorithm in C# with a user friendly interface which can be learned and used intuitively.