Improving automatic cerebral 3D-2D CTA-DSA registration
Charles Downs (Erasmus MC)
P. Matthijs van der Sluijs (Erasmus MC)
Sandra A.P. Cornelissen (Erasmus MC)
Frank te Nijenhuis (Erasmus MC, TU Delft - Electrical Engineering, Mathematics and Computer Science)
Wim H.van Zwam (Maastricht University Medical Center)
Vivek Gopalakrishnan (Massachusetts Institute of Technology)
Xucong Zhang (TU Delft - Pattern Recognition and Bioinformatics)
Ruisheng Su (Eindhoven University of Technology, Erasmus MC, TU Delft - Biomechanical Engineering)
Theo van Walsum (TU Delft - Biomechanical Engineering, Erasmus MC)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Purpose : Stroke remains a leading cause of morbidity and mortality worldwide, despite advances in treatment modalities. Endovascular thrombectomy (EVT), a revolutionary intervention for ischemic stroke, is limited by its reliance on 2D fluoroscopic imaging, which lacks depth and comprehensive vascular detail. We propose a novel AI-driven pipeline for 3D CTA to 2D DSA cross-modality registration, termed DeepIterReg. Methods : The proposed pipeline integrates neural network-based initialization with iterative optimization to align pre-intervention and peri-intervention data. Our approach addresses the challenges of cross-modality alignment, particularly in scenarios involving limited shared vascular structures, by leveraging synthetic data, vein-centric anchoring, and differentiable rendering techniques. Results : We assess the efficacy of DeepIterReg through quantitative analysis of capture ranges and registration accuracy. Results show that our method can accurately register 70% of a test set of 20 patients and can improve capture ranges when performing an initial pose estimation using a convolutional neural network. Conclusions : DeepIterReg demonstrates promising performance for 3D-to-2D stroke intervention image registration, potentially aiding clinicians by improving spatial understanding during EVT and reducing dependence on manual adjustments.