Intensity-based Similarity Measures Evaluation for CT to Ultrasound 2D Registration - Archive ouverte HAL Access content directly
Journal Articles Innovation and Research in BioMedical engineering Year : 2013

Intensity-based Similarity Measures Evaluation for CT to Ultrasound 2D Registration

(1) , (1)
1

Abstract

Ultrasound is a non-invasive image modality which allows for real time acquisition. Nevertheless, the low quality of the acquired images makes this a difficult-to-interpret modality during surgical procedures. To overcome this, the registration of ultrasound images with pre-operative CT or MR images has been routinely used to fuse complementary information. This work presents the evaluation of eight similarity measures used in the registration of ultrasound and CT images of the left atrium and the pulmonary veins. Each intensity-based similarity measure was evaluated computing its accuracy, capture range, distinctiveness of the optimum, risk and non-convergence and number of minima. The results show, that the Woods criterion presents a globally better performance than the other similarity measures. This is especially true for the accuracy and distinctiveness of the optimum indicators. Preprocessing US images does not improve the performance of all similarity measures, except for Woods criterion that shows the optimal accuracy.
Fichier principal
Vignette du fichier
IRBM-Sandoval.pdf (3.81 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inserm-00879579 , version 1 (04-11-2013)

Identifiers

Cite

Zulma Sandoval, Jean-Louis Dillenseger. Intensity-based Similarity Measures Evaluation for CT to Ultrasound 2D Registration. Innovation and Research in BioMedical engineering, 2013, 34 (4-5), pp.278-282. ⟨10.1016/j.irbm.2013.08.001⟩. ⟨inserm-00879579⟩
286 View
428 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More