ETRO VUB
About ETRO  |  News  |  Events  |  Vacancies  |  Contact  
Home Research Education Industry Publications About ETRO

Master theses

Current and past ideas and concepts for Master Theses.

Optimization of a Computer Aided Diagnosis System for lung nodule detection

Subject

Lung cancer is one of the deadliest cancers worldwide and its early detection is of high importance. Towards this purpose, in the last two decades many automatic systems have been proposed for automatically detecting pulmonary nodules in CT images. These Computer Aided Diagnosis systems mainly consist of a detection and a classification component. However, the ratio between the number of detected candidate structures versus the real malignant structures is at the level of 200:1, leading to highly imbalanced datasets that hinder the learning process of the classifiers.

Kind of work

The objective of this master thesis is to improve the performance of an existing CAD system developed within the group. The student will investigate different methods for feature selection and classification on extracted features as well as methods for balancing the highly imbalanced datasets. The focus will be on optimizing the parameters of existing classifiers and data balancing methods using tools available in literature.

Relevant Literature:
https://arxiv.org/pdf/1612.08012.pdf

Framework of the Thesis

Python

Number of Students

1

Promotor

Prof. Dr. Bart Jansen

+32 (0)2 629 1034

bjansen@etrovub.be

more info

Supervisor

Ir. Evgenia Papavasileiou

+32 (0)2 629 1687

epapavas@etrovub.be

more info

Image

- Contact person

- IRIS

- AVSP

- LAMI

- Contact person

- Thesis proposals

- ETRO Courses

- Contact person

- Spin-offs

- Know How

- Journals

- Conferences

- Books

- Vacancies

- News

- Events

- Press

Contact

ETRO Department

info@etro.vub.ac.be

Tel: +32 2 629 29 30

©2019 • Vrije Universiteit Brussel • ETRO Dept. • Pleinlaan 2 • 1050 Brussels • Tel: +32 2 629 2930 (secretariat) • Fax: +32 2 629 2883 • WebmasterDisclaimer