Abstract
In biological research, fluorescence microscopy has become one of the vital tools used for observation, allowing researchers to study, visualise and image the details of intracel-lular structures which result in better understanding of biology. However, analysis of large numbers of samples is often required to draw statistically verifiable conclusions. Automated methods for analysis of microscopy image data make it possible to handle large datasets, and at the same time reduce the risk of bias imposed by manual techniques in the image analysis pipeline. This work covers automated methods for extracting quan-titative measurements from microscopy images, enabling the detection of spots resulting from different experimental conditions. The work resulted in four main significant con-tributions developed around the microscopy image analysis pipeline. Firstly, an investiga-tion into the importance of spot detection within the automated image analysis pipeline is conducted. Experimental findings show that poor spot detection adversely affected the remainder of the processing pipeline...
D.Ing. (Electrical and Electronic Engineering)