Application of learning-based autofocus in 4D Digital Subtraction Angiography, incorporating implicit neural models for advance encoding of motion and 4D blood flow information.
[2024] Motion Compensation for 4D Digital Subtraction Angiography via Deep Autofocus and Implicit Neural Motion Models
Huang H, Lu A, Gonzales F, Ehtiati T, Siewerdsen JH, Sisniega A. Motion Compensation for 4D Digital Subtraction Angiography via Deep Autofocus and Implicit Neural Motion Models. 8th International Conference on Image Formation in X-Ray Computed Tomography. 2024; Bamberg, Germany.
Presentation Slides
4D-DSA offers time-resolved 3D information of contrast concentration in vascular structures and has seen increased use in the neuro-interventional suite. Most current approaches to 4D-DSA are implemented using interventional cone-beam CT systems and involve the acquisition of a non-contrast-enhanced reference mask and a contrast-enhanced volume during contrast administration. The final 4D-DSA dataset is obtained under assumptions of perfect stationarity of the patient during both CBCT scans. However, cone-beam CT often shows moderately long acquisition time, making it susceptible to motion artifacts that could significantly degrade the accuracy of 4D-DSA. Recent developments in motion compensation with image-based autofocus, integrating learning-based autofocus metrics and implicit neural representation of the motion trajectory, has demonstrated reliable and robust performance in solving complex motion in CBCT images. In this work, we propose a novel framework that incorporates motion compensation into the 4D-DSA pipeline. 4D-DSA is obtained via a multi-stage approach involving deep autofocus motion estimation acting on the non-contrast-enhanced mask, simultaneous motion estimation and registration of the contrast-enhanced volume, and estimation of the time-dependent volumetric contrast distribution.
