One of the most helpful factors to consider when evaluating the development of breast cancer is the independent risk factor known as breast density. The breast density factor is the ratio between the volume of fibroglandular tissue to the total volume of the breasts. It is a measurement that always has to be considered by the radiologists for detection and diagnosis of breast cancer.
In this thesis we present an analysis method to calculate this breast density factor, the analysis is based on image segmentation algorithms. The images being segmented come from breast magnetic resonance imaging, breast MRI, which provides better results than conventional x-ray mammograms.
The first part of this thesis focuses on the breast MRI template-based segmentation method. The implemented method was first proposed by Muqing Lin et al. in our center back in 2010. The developed method is applied to segment the different slices with 1-3 mm thickness obtained for every breast. As also demonstrated in this first part of the thesis, the method provides successful results for segmentation and calculation of the percentage of breast density.
The second part of this thesis is dedicated to describe a method used to reconstruct a 3D model of the breasts from the MRI slices obtained for each patient. The tool performs a breast alignment correction, followed by the 3D reconstruction and a video generation where we can observe the 3D model from different angles and with different rotation and speed.
Finally, the third part of this thesis involves the study of the breasts by the regional segmentation of the quadrants. Several studies have demonstrated that the probability of breast cancer is not the same at every quadrant. Therefore it is an interesting option for the radiologists to be able to observe a 3D representation of the breast divided in quadrants.