Share Email Print

Proceedings Paper

Technical note: probabilistic visual and electromagnetic data fusion for robust drift-free sequential mosaicking: application to fetoscopy
Author(s): Marcel Tella-Amo; Loic Peter; Dzhoshkun I. Shakir; Jan Deprest; Danail Stoyanov; Juan Eugenio Iglesias; Tom Vercauteren; Sebastien Ourselin
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The most e↵ective treatment for Twin-to-Twin Transfusion Syndrome is laser photocoagulation of the shared vascular anastomoses in the placenta. Vascular connections are extremely challenging to locate due to their caliber and the reduced field of view of the fetoscope. Therefore, mosaicking techniques are beneficial to expand the scene, facilitate navigation and allow vessel photocoagulation decision-making. Local vision-based mosaicking algorithms inherently drift over time due to the use of pairwise transformations. We propose the use of an electromagnetic tracker (EMT) sensor mounted at the tip of the fetoscope to obtain camera pose measurements, which we incorporate into a probabilistic framework with frame-to-frame visual information to achieve globally consistent sequential mosaics. We parametrize the problem in terms of plane and camera poses constrained by EMT measurements to enforce global consistency while leveraging pairwise image relationships in a sequential fashion through the use of Local Bundle Adjustment. We show that our approach is drift-free and performs similarly to state-of-the-art global alignment techniques like Bundle Adjustment albeit with much less computational burden. Additionally, we propose a version of Bundle Adjustment that uses EMT information. We demonstrate the robustness to EMT noise and loss of visual information and evaluate mosaics for synthetic, phantom-based and ex vivo datasets.

Paper Details

Date Published: 13 March 2018
PDF: 8 pages
Proc. SPIE 10576, Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling, 105760I (13 March 2018); doi: 10.1117/12.2319839
Show Author Affiliations
Marcel Tella-Amo, Univ. College London (United Kingdom)
Loic Peter, Univ. College London (United Kingdom)
Dzhoshkun I. Shakir, Univ. College London (United Kingdom)
Jan Deprest, Univ. College London (United Kingdom)
KU Leuven (Belgium)
Danail Stoyanov, Univ. College London (United Kingdom)
Juan Eugenio Iglesias, Univ. College London (United Kingdom)
Tom Vercauteren, Univ. College London (United Kingdom)
KU Leuven (Belgium)
Sebastien Ourselin, Univ. College London (United Kingdom)

Published in SPIE Proceedings Vol. 10576:
Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling
Baowei Fei; Robert J. Webster III, Editor(s)

© SPIE. Terms of Use
Back to Top