Use this URL to cite or link to this record in EThOS:
Title: Efficient drift-free mosaicking of fetoscopic videos using an electromagnetic tracker
Author: Tella Amo, Marcel
ISNI:       0000 0004 7970 6574
Awarding Body: UCL (University College London)
Current Institution: University College London (University of London)
Date of Award: 2019
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Twin-to-Twin Transfusion Syndrome is a fetal illness in which twins share vascular connections in the placenta. This results in an imbalance in the blood flow that might be fatal for both twins. Surgeons need to be very well trained to be able to localise and further photo-coagulate the anastomoses in the placenta given the small field-of-view of the fetoscope and lack of texture of the imagery in the fetoscopic site. We investigate mosaicking as a means of expanding the field-of-view to a larger image of the explored area as the camera moves. However, the complexity of fetoscopic data makes current state-of-the-art algorithms lack robustness. Additionally, vision-only mosaicking algorithms suffer from drift. The main focus of this thesis is to study the incorporation of an electromagnetic tracker into the mosaicking pipeline. We demonstrate that the guidance of the electromagnetic tracker can mitigate the drift in twp steps: First exploring a dynamic state-space model that reduces the drift. Despite being suitable for online operation, we investigate a fully probabilistic model that completely eliminates the drift. Then, we use the proposed algorithms to investigate pruning strategies, aiming to a achieve mosaics built at clinically acceptable update rates. The results suggest that the joint use of the electromagnetic tracker with the imagery can improve the accuracy, robustness, and efficiency with respect to algorithms that use exclusively imagery. We believe the inclusion of the electromagnetic tracker is a step forward towards clinical translation of mosaicking for fetoscopy.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available