Computer vision for multimodal surgical guidance in brain tumour resection
File(s)
Author(s)
Roddan, Alfie
Type
Thesis or dissertation
Abstract
Medical devices play a central role in neurosurgery, where millimetre-scale accuracy is essential for preserving brain function and guiding surgical decisions. Despite the wide use of navigation and imaging tools, few provide real-time, multi-scale tissue characterization. This thesis investigates a multimodal guidance framework that combines macroscopic hyperspectral imaging with probe-based confocal laser endomicroscopy for cellular-level detail. The work advances each modality individually and explores their combination within a broader framework, drawing on photonics, deep learning, and computer vision to improve data acquisition, interpretation, and integration across scales.
Date Issued
2025-10-03
Date Awarded
2026-02-01
Copyright Statement
Attribution-NonCommercial 4.0 International Licence (CC BY-NC)
License URL
Advisor
Giannarou, Stamatia
Elson, Daniel
Sponsor
Engineering and Physical Sciences Research Council
Intel Corporation
Grant Number
WSGG/G01744
Publisher Department
Department of Surgery & Cancer
Publisher Institution
Imperial College London
Qualification Level
Doctoral
Qualification Name
Doctor of Philosophy (PhD)