Evolutionary built decision trees for supervised segmentation of follicular lymphoma images

Lymphoma is a broad term encompassing a variety of cancers of the lymphatic system. Lymphoma is differentiated by the type of cell that multiplies and how the cancer presents itself. It is very important to get an exact diagnosis regarding lymphoma and to determine the treatments that will be most effective for the patient's condition. Our work was focused on the identification of lymphomas by finding follicles in microscopy images provided by the Laboratory of Pathology in the University Hospital of Tenerife, Spain. Roughly we can divide our work in two stages: in the first stage we did image pre-processing and feature extraction, and in the second stage we used evolutionary built decision trees for pixel classification and feature ranking. Decision trees, a popular symbolic machine teaming approach, are often neglected when looking for approaches for image analysis. Enhanced with the evolutionary option, they don't offer us more generalizing power, but we gain on better coverage of method parameter's search space. Better exploitation of a method usually manifests in better results, and the goal is reached. The results we got are very promising and show that combination of both approaches can be successful in image analysis applications.