Institute of Computer-aided Product Development Systems
Master Thesis
Evaluation and implementation of segmentation methods on medical image processing
In the context of digital mammography, mammographic breast density is the fraction of image occupied by radiographically dense tissue (glandular tissue). Many authors have already developed methods to estimate the percentage of glandular tissue but from a 2D point of view. Considering density measurement as a two-dimensional problem considers only a part of a three-dimensional phenomenon.
In order to calculate the ratio glandular_thickness/fat_thickness in a mammographic image, calculations are applied on each interesting pixel. Before doing this calculation the image should be segmented into interesting and not interesting pixels.
The objective of this Master Thesis is to find and implement a method of image-segmentation applied on digital mammograms.
The project can be held in English or German.
Main goals
Planning of the project
Understanding the semantic meaning of the pixels
Understanding of the most important contents of the DICOM standard
Study and evaluation of different methods of segmentation
UZ) | © Universität Stuttgart | Legal Notice