Analyzing the breast tissue in mammograms using deep learning

Identificador:  TDX:3860

Handle: https://hdl.handle.net/20.500.11797/TDX3860

Autors:  Saffari Tabalvandani, Nasibeh

Resum:
Mammographic breast density (MBD) reflects the amount of fibroglandular breast tissue area that appears white and bright on mammograms, commonly referred to as breast percent density (PD%). MBD is a risk factor for breast cancer and a risk factor for masking tumors. However, accurate MBD estimation with visual assessment is still a challenge due to faint contrast and significant variations in background fatty tissues in mammograms. In addition, correctly interpreting mammogram images requires highly trained medical experts: it is difficult, time-consuming, expensive, and error-prone. Nevertheless, dense breast tissue can make it harder to identify breast cancer and be associated with an increased risk of breast cancer. For example, it has been reported that women with a high breast density compared to women with a low breast density have a four- to six-fold increased risk of developing the disease. The primary key of breast density computing and breast density classification is to detect the dense tissues in the mammographic images correctly. Many methods have been proposed for breast density estimation; however, most are not automated. Besides, they have been badly affected by low signal-to-noise ratio and variability of density in appearance and texture. It would be more helpful to have a computer-aided diagnosis (CAD) system to assist the doctor analyze and diagnosing it automatically. Current development in deep learning methods motivates us to improve current breast density analysis systems. The main focus of the present thesis is to develop a system for automating the breast density analysis ( such as; breast density segmentation(BDS), breast density percentage (BDP), and breast density classification ( BDC)), using deep learning techniques and applying it on the temporal mammograms after treatment for analyzing the breast density changes to find a risky and suspicious patient.