scispace - formally typeset
D

Dirk Loeckx

Researcher at Katholieke Universiteit Leuven

Publications -  77
Citations -  2524

Dirk Loeckx is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Image registration & Segmentation. The author has an hindex of 24, co-authored 75 publications receiving 2375 citations. Previous affiliations of Dirk Loeckx include The Catholic University of America & Catholic University of Leuven.

Papers
More filters
Journal ArticleDOI

Evaluation of Registration Methods on Thoracic CT: The EMPIRE10 Challenge

TL;DR: The organization of the challenge, the data and evaluation methods and the outcome of the initial launch with 20 algorithms, which comprised the comprehensive evaluation and comparison of 20 individual algorithms from leading academic and industrial research groups are detailed.
Journal ArticleDOI

Nonrigid Image Registration Using Conditional Mutual Information

TL;DR: CMI was compared to the classical global mutual information (gMI) approach in theoretical, phantom, and clinical settings and it is shown that cMI significantly outperforms gMI for all applications.
Journal ArticleDOI

Relationship between fluorodeoxyglucose uptake in the large vessels and late aortic diameter in giant cell arteritis

TL;DR: GCA-patients with increased FDG uptake in the aorta may be more prone to develop thoracic aortic dilatation than GCA patients without this sign of aorti involvement.
Journal ArticleDOI

Three-Dimensional Cardiac Strain Estimation Using Spatio–Temporal Elastic Registration of Ultrasound Images: A Feasibility Study

TL;DR: Preliminary results on clinical data taken in vivo from three healthy volunteers and one patient with an apical aneurism confirmed these findings in a qualitative manner as the strain curves obtained with the proposed method have an amplitude and shape similar to what could be expected.
Journal ArticleDOI

Semi-automatic level set segmentation of liver tumors combining a spiral-scanning technique with supervised fuzzy pixel classification

TL;DR: The described method outperformed the semi-automatic methods of the other participants of the "3D Liver Tumor Segmentation Challenge 2008" and led to an average overlap error of 32.6% and an average volume difference of 17.9%.