Improving automatic cerebral 3D-2D CTA-DSA registration
Name
11548_2025_Article_3412.pdf
Size
1.34 MB
Format
Adobe PDF
Checksum (MD5)
164594484d591e2b28a811f3e368fb52
Author(s)
Downs, Charles
Sluijs, P. M. v. d.
Cornelissen, Sandra A. P.
Nijenhuis, Frank t.
Zwam, Wim H. v.
Gopalakrishnan, Vivek
Zhang, Xucong
Su, Ruisheng
Walsum, Theo v.
Date Issued
May 23, 2025
Journal
International Journal of Computer Assisted Radiology and Surgery
Publisher
Springer International Publishing
Citation
Downs, C., Sluijs, P.M.v.d., Cornelissen, S.A.P. et al. Improving automatic cerebral 3D-2D CTA-DSA registration. Int J CARS 20, 1451–1460 (2025).
Version
Final published version
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.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s11548-025-03412-2
